Loading [MathJax]/jax/output/SVG/jax.js
Search Advanced

Electronic Research Archive

2024, Volume 32, Issue 1: 643-669. doi: 10.3934/era.2024031
Previous Article Next Article
Research article Special Issues

Attention-guided cross-modal multiple feature aggregation network for RGB-D salient object detection

  • State Grid Fujian Electric Power Research Institute, No.64 Shoushan Road, Cangshan District, Fuzhou, China

  • Academic Editor: William Guo

  • The goal of RGB-D salient object detection is to aggregate the information of the two modalities of RGB and depth to accurately detect and segment salient objects. Existing RGB-D SOD models can extract the multilevel features of single modality well and can also integrate cross-modal features, but it can rarely handle both at the same time. To tap into and make the most of the correlations of intra- and inter-modality information, in this paper, we proposed an attention-guided cross-modal multi-feature aggregation network for RGB-D SOD. Our motivation was that both cross-modal feature fusion and multilevel feature fusion are crucial for RGB-D SOD task. The main innovation of this work lies in two points: One is the cross-modal pyramid feature interaction (CPFI) module that integrates multilevel features from both RGB and depth modalities in a bottom-up manner, and the other is cross-modal feature decoder (CMFD) that aggregates the fused features to generate the final saliency map. Extensive experiments on six benchmark datasets showed that the proposed attention-guided cross-modal multiple feature aggregation network (ACFPA-Net) achieved competitive performance over 15 state of the art (SOTA) RGB-D SOD methods, both qualitatively and quantitatively.

    Citation: Bojian Chen, Wenbin Wu, Zhezhou Li, Tengfei Han, Zhuolei Chen, Weihao Zhang. Attention-guided cross-modal multiple feature aggregation network for RGB-D salient object detection[J]. Electronic Research Archive, 2024, 32(1): 643-669. doi: 10.3934/era.2024031

    Related Papers:

    [1] Ladislas Mutunda Kangaji, Atanda Raji, Efe Orumwense . Cutting-edge progress in offshore wind and tidal stream power technology—State-of-the-Art. AIMS Energy, 2025, 13(1): 188-230. doi: 10.3934/energy.2025007
    [2] Ferhat Bingol . Feasibility of large scale wind turbines for offshore gas platform installation. AIMS Energy, 2018, 6(6): 967-978. doi: 10.3934/energy.2018.6.967
    [3] Takvor Soukissian, Anastasios Papadopoulos, Panagiotis Skrimizeas, Flora Karathanasi, Panagiotis Axaopoulos, Evripides Avgoustoglou, Hara Kyriakidou, Christos Tsalis, Antigoni Voudouri, Flora Gofa, Petros Katsafados . Assessment of offshore wind power potential in the Aegean and Ionian Seas based on high-resolution hindcast model results. AIMS Energy, 2017, 5(2): 268-289. doi: 10.3934/energy.2017.2.268
    [4] Navid Majdi Nasab, Jeff Kilby, Leila Bakhtiaryfard . Integration of wind and tidal turbines using spar buoy floating foundations. AIMS Energy, 2022, 10(6): 1165-1189. doi: 10.3934/energy.2022055
    [5] Rashid Al Badwawi, Mohammad Abusara, Tapas Mallick . Speed control of synchronous machine by changing duty cycle of DC/DC buck converter. AIMS Energy, 2015, 3(4): 728-739. doi: 10.3934/energy.2015.4.728
    [6] D. Marene Larruskain, Inmaculada Zamora, Oihane Abarrategui, Garikoitz Buigues, Víctor Valverde, Araitz Iturregi . Adapting AC Lines to DC Grids for Large-Scale Renewable Power Transmission. AIMS Energy, 2014, 2(4): 385-398. doi: 10.3934/energy.2014.4.385
    [7] Wen-Tien Tsai . Overview of wind power development over the two past decades (2000-2019) and its role in the Taiwan's energy transition and sustainable development goals. AIMS Energy, 2021, 9(2): 342-354. doi: 10.3934/energy.2021018
    [8] Zeid Al Qaisi, Qais Alsafasfeh, Ahmad Harb . Stability impact of integrated small scale hybrid (PV/Wind) system with electric distribution network. AIMS Energy, 2018, 6(5): 832-845. doi: 10.3934/energy.2018.5.832
    [9] Nour Khlaifat, Ali Altaee, John Zhou, Yuhan Huang . A review of the key sensitive parameters on the aerodynamic performance of a horizontal wind turbine using Computational Fluid Dynamics modelling. AIMS Energy, 2020, 8(3): 493-524. doi: 10.3934/energy.2020.3.493
    [10] Eugene Freeman, Davide Occello, Frank Barnes . Energy storage for electrical systems in the USA. AIMS Energy, 2016, 4(6): 856-875. doi: 10.3934/energy.2016.6.856

  • The goal of RGB-D salient object detection is to aggregate the information of the two modalities of RGB and depth to accurately detect and segment salient objects. Existing RGB-D SOD models can extract the multilevel features of single modality well and can also integrate cross-modal features, but it can rarely handle both at the same time. To tap into and make the most of the correlations of intra- and inter-modality information, in this paper, we proposed an attention-guided cross-modal multi-feature aggregation network for RGB-D SOD. Our motivation was that both cross-modal feature fusion and multilevel feature fusion are crucial for RGB-D SOD task. The main innovation of this work lies in two points: One is the cross-modal pyramid feature interaction (CPFI) module that integrates multilevel features from both RGB and depth modalities in a bottom-up manner, and the other is cross-modal feature decoder (CMFD) that aggregates the fused features to generate the final saliency map. Extensive experiments on six benchmark datasets showed that the proposed attention-guided cross-modal multiple feature aggregation network (ACFPA-Net) achieved competitive performance over 15 state of the art (SOTA) RGB-D SOD methods, both qualitatively and quantitatively.


    Highlights

    ● Increased offshore wind mainly replaces LNG generation.

    ● Offshore wind improved overall demand coverage compared to LNG.

    ● Offshore wind shares were maximized through development near high-demand regions.

    1.   Background

    To mitigate the adverse effects of anthropogenic climate change, the United Nations Framework Convention on Climate Change (UNFCCC) established the Paris Agreement to regulate CO2 emissions [1], as these contributed 76% of global greenhouse gas emissions [2]. As a result, governments around the world that signed the agreement are currently attempting to decarbonize their economies.

    Through its energy sector decarbonization strategy, the Japanese government aims to achieve zero CO2 emissions by 2050 [3]. To do this, the government regularly formulates Strategic Energy Plans (SEP) updated approximately every 3 years, and currently in its 6th revision [4], which are led by three principles, namely efficient supply, energy security and environmental protection, supported by the condition of safe operation [5]. Mid-term targets include the reduction of greenhouse gas emissions by 26% from 2013 levels by 2030, and to achieve a 25% self-sufficiency ratio (Defined as the ration of energy produced from domestic sources and that imported from overseas) by this date [5], up from 20.3% in 2010, and 11.6% following the 2011 Tohoku Earthquake and Tsunami (11.2% as of 2021[6]).

    To achieve these targets, the 6th SEP has set more ambitious targets for renewable sources for electricity (RES-E) than the 5th SEP, increasing total RES-E target shares from 22~24% to 36~38% for 2030, and prioritizing and maximizing renewable energy integration (see Table 1).

    Table 1.  Projected energy mix in 2030 according to the 5th and 6th SEP.
    Nuclear LNG Coal Oil Hydrogen Solar Wind Geothermal Hydropower Biomass
    5th SEP 20~22% 27% 26% 3% 0% 7% 1.7% 1~1.1% 8.8~9.2% 3.8~4.6%
    6th SEP 20~22% 20% 19% 2% 1% 14~16% 5% 1% 11% 5%
     | Show Table
    DownLoad: CSV

    The focus of the 6th SEP is to decrease the share of fossil fuels in electricity generation, while doubling solar PV and almost tripling the wind share. The government of Japan aims to achieve the latter by not only increasing the installed onshore wind capacity but also by newly introducing 10 GW of offshore wind, thereby increasing the wind resource overall by 19.7 GW compared to 2021 (4.6 GW). Indeed, while wind has not played an important role in the Japanese energy mix until now, offshore wind capacity is planned to be developed in three stages between 2030 (10 GW), 2040 (30~45 GW) and 2050 (90 GW) to achieve carbon neutrality [7], as well as enhance domestic self-sufficiency [5]. The distribution of the planned capacities by region is summarized in Table 2.

    Table 2.  Regional distribution of offshore wind capacity (GW) by year.
    Total Hokkaido Tohoku Kanto Chubu Hokuriku Kansai Shikoku Chugoku Kyushu
    2020 0.06 0.0012 0.02 0.032 0 0 0 0 0 0.005
    2030 10.72 1.24 4.07 0.35 1.35 0.7 0.75 0 0.06 2.2
    2040 45 14.65 9 3.7 1.35 1.3 0.9 1.7 0.5 11.9
     | Show Table
    DownLoad: CSV

    Therefore, by 2030 wind could play a much more substantial role in the Japanese energy system than it does as of 2022. Furthermore, other than for electricity generation, wind energy is also planned to be used for hydrolysis to generate H2 for the transport sector [8]. For this purpose, Hokkaido prefecture carried out evaluations in 2018 [9], and Kyushu prefecture conducted experiments in 2021 [10]. While plans to develop hydrolysis capacity as a collaboration between government and companies (such as Hitachi, Muroran Institute of Technology, NTT Facilities and Nagasaki industrial promotion foundation) in Hokkaido and Kyushu have been confirmed [9,10], it is unclear as of July 2022 how much hydrolysis capacity is planned in these regions.

    Despite the relatively high potential of offshore wind as a domestic resource (ca. 91 GW [7]), it remains largely undeveloped as of 2022. Partially, this is due to the water depth off the east coast of Japan, which results in a high construction cost for wind turbines [11]. Further, Japan is prone to typhoons between July and October, which can force currently available turbine models to shut down and even cause severe structural damage [12,13].

    To address this problem and harvest the potential energy from typhoon-strength winds, various companies have begun developing so-called "T-class" turbine models. These include the SG 11.0-200 DD by Siemens Gamesa [14], the V174-9.5 MWTM [15] and the V236-15MWTM by Vestas [16], the MySE 16.0-242 by MingYang Smart Energy [17], as well as the Haliade-X 12-14.7MW-220 by General Electric [18]. The two former turbine models had prototypes installed successfully in 2021 [19] and 2020 [20], respectively, with orders made in the Netherlands, Germany and Taiwan [21]. For V236-15MWTM, the installation of a prototype turbine is planned for the second half of 2022 and serial production by 2024 [22]. The MySE 16.0-242 is scheduled for prototype rollout in 2022, prototype installation in the first half of 2023 and commercial production in the first half of 2024 [23].

    Offshore wind will likely become more important to the energy mix of Japan given the development of T-class turbines and the government's long-term targets to support it. In this context, it is important to understand how an increase in wind capacity would affect the energy mix and which measures would be best suited to fulfill the overall Japanese energy policy targets. Energy system models can assess this impact on the energy mix and are therefore a useful tool in this context. Previous energy models have assessed the viability of various energy mixes for Japan toward 2030 [24,25,26,27,28,29,30,31] and 2050 [32,33]. These studies assess major resources such as oil, LNG, coal, nuclear, solar PV, onshore wind, biomass, geothermal, pumped hydro storage and battery storage. However, given that it was a negligible resource as of 2022, offshore wind was not considered in any such existing research regarding Japan to the best of the authors' knowledge.

    Based on the identified gaps, this work will introduce offshore wind as a major resource when simulating the energy mix in Japan for 2030, using both the projected capacity for that year, as well as the expected maximum capacity of 91 GW. In doing so, the authors aim to determine the potential contribution of offshore wind to the Japanese energy system by 2030 and in the long-term. Finally, the authors estimate whether the resource capacity distribution planned by the government of Japan can be improved, from the perspective of maximizing the integration opportunities of offshore wind into the system.

    2.   Methodology

    2.1.   Model overview

    Simulations were carried out using the Energy System Simulation Model (EnSym) developed by Knüpfer et al. [31]. EnSym simulates all major resources including nuclear, coal, oil, LNG and renewable resources, such as hydro power, solar PV, onshore wind, biomass, and geothermal, as well as utility scale batteries and pumped hydro storage. The simulations use an hourly time-scale, and include all regions in Japan except the Ryukyu Islands, as this chain of southern Japanese islands is not connected to the main grid. EnSym takes into account inter-regional electricity transmission and can flexibly adopt different dispatch hierarchies for resources. In this study, variable renewables (e.g., wind, solar PV, and utility scale batteries and pumped hydro charged by them) were prioritised over flexible energy resources (e.g., LNG, biomass and geothermal), which were in turn prioritised over thermal resources (e.g., nuclear and coal). Nuclear power, hydro and coal act as baseloads. For a detailed overview of the model, please see Knüpfer et al. [31]. In the present work, the authors modified EnSym to newly introduce offshore wind power into the model. Further, the balancing procedure was improved compared to the previous version of the model.

    2.2.   Electricity supply

    The target installed capacities for all major resources for 2030 were obtained from the most recent projection by the Ministry of Economy, Trade and Industry [34] for coal, LNG, oil, nuclear, solar, geothermal, onshore wind, offshore wind, biomass, and conventional hydropower. For these resources, previous projections for 2030 by the government of Japan were assumed to still be up-to-date [35]. Further, for any capacity with a target range, the average value was taken (see Table 3).

    Table 3.  Target installed capacities for all major resources for 2030 (sources: METI [34]; OCCTO [35]; ANRE [36]; JAIF [37]).
    Resources Installed capacity (GW)
    Coal 51.9
    LNG 84.9
    Oil 30.8
    Nuclear 38
    Solar 87.6
    Geothermal 1.4~1.6
    Onshore wind 13.3~15.3
    Offshore wind 1.7~3.7
    Biomass 7.2
    Conventional hydropower (Small-to-mid-scale) 10.94~11.65
     | Show Table
    DownLoad: CSV

    Among the planned capacities shown in Table 3, the authors adjusted those for nuclear power, solar and offshore wind. Due to the decommission of existing nuclear capacity and the lack of sufficient new capacity being planned by 2030, the authors assumed that the installed capacity of nuclear power by 2030 will not exceed 33.2 GW (see Appendix for details). For solar PV, the planned capacity of 88 GW [34] seems to be an underestimation compared with the expected installed capacity for 2030 of 139.12 GW by ANRE [36] (The PV generation share targets for 2030 set by the 5th SEP were achieved in 2020 (7%), and the capacity targets for 2020 (64 GW) have also been exceeded (136 GW, if all already approved capacity is included, see Knüpfer et al. [38]). Therefore, the authors adopt the latter value. For offshore wind, the planned distribution of newly developed capacities for 2030 is unclear as of July 2022. Therefore, the authors based the distribution on offshore wind projects that are currently undergoing environmental assessment [39]. The regional distribution of all other resources follows Knüpfer et al. [31]. Where total installed capacity volumes differ from Knüpfer et al. [31], the additional expected capacities were either distributed proportionately over the regions, or according to known regional development projects (see the Appendix)).

    Table 4 provides an overview of the total expected capacity projected by METI [34] and the business-as-usual base case (BAU) based on amendments by the authors ("Japan realistic"), as well as the associated regional distributions (also based on the estimates by the authors).

    Table 4.  Installed capacity (GW) of each resource in each region of Japan in 2030 (for the BAU).
    Resource METI projection Japan realistic Hokkaido Tohoku Kanto Chubu Hokuriku Kansai Shikoku Chugoku Kyushu
    Coal 51.9 51.9 1.9 4.3 17.3 7.5 0.8 9.6 1.9 3.3 5.3
    LNG 84.9 84.9 3.1 7 28.2 12.3 1.4 15.7 3.1 5.4 8.7
    Oil 30.8 30.8 1.1 2.5 10.2 4.5 0.5 5.7 1.1 2 3.1
    Nuclear 38 33.2 2.1 2.8 1.1 3.6 11.3 6.5 0.9 0.8 4.1
    Hydro Conventional 23.75 23.75 1.4 3.9 1.5 8 4 0.87 0.98 1.1 2
    Hydro pumped 27.47 27.47 1 0.5 5.3 10.1 1.6 4 0.6 2.1 2.3
    Solar PV 87.6 139.12 4.27 16.06 52.37 15.15 1.2 12.2 3.66 7.8 26.4
    Onshore wind 14.3 14.3 2.2 5.2 0.46 0.7 0.47 1.39 0.7 1.28 1.86
    Offshore wind 2.7 10 1.5 4.5 0.4 0 0.7 0.7 0 0 2.2
    Geothermal 1.5 1.5 0.08692 0.85 0.00005 0.00057 0.00024 0.0001 0 0.00005 0.55483
    Biomass 7.2 7.2 0.32 1.14 1.08 1.26 0.58 0.6 0.42 0.92 0.9
     | Show Table
    DownLoad: CSV

    Utility scale batteries were also considered [40], with their capacity assumed to remain unchanged between 2020 and 2030 (Table 5) as no information regarding development plans could be identified. Obviously, an increase in the capacity of batteries will result in a more robust and stable system [26], and thus assuming that this remains constant represents a conservative assumption.

    Table 5.  Announced, commissioned and operational large-scale battery rated power (MWh) as of 2021 (Source: DOE [40]).
    Storage medium Japan Hokkaido Tohoku Kanto Chubu Hokuriku Kansai Shikoku Chugoku Kyushu
    Battery 910 73.8 323.5 180.8 0.0 0.0 2.7 0.0 25.3 303.9
     | Show Table
    DownLoad: CSV

    To simulate the full estimated potential (91 GW) of offshore wind in Scenarios 1 and 2, the installed capacity was adjusted based on its current development plan [39]. As some regions had no offshore wind capacity installed in the BAU, the offshore wind capacity distribution for 91 GW was based on the 2040 regional target (45 GW), which has capacity installed in every region [39], and then scaled up proportionally to reach 91 GW (see Table 6).

    Table 6.  Expected offshore wind regional distribution for 91 GW.
    Total Hokkaido Tohoku Kanto Chubu Hokuriku Kansai Shikoku Chugoku Kyushu
    Installed capacity (GW) 91 29.4 18.2 7.5 2.7 2.6 1.8 3.4 1.0 24.3
     | Show Table
    DownLoad: CSV

    The hourly electricity generation potential for solar PV and onshore wind was calculated using hourly meteorological data from one measurement station per prefecture [41]. The station locations for onshore wind were adapted from Knüpfer et al. [31]. For offshore wind, one measurement station per region was chosen [42] (see the Appendix for all stations used), considering only those stations that were not in the wind shadow of mountains and close to the coastline. (The furthest station from the coast was 303 meters inland). For solar PV installed capacity, it was assumed that every panel was a Hanwha G5-280 series, and for offshore wind capacity that every turbine was a V236-15MWTM (see Appendix for details). It was also assumed that each offshore wind park was directly connected to the respective regional grid through typical submarine cables (see Appendix).

    As for thermal resources, it was assumed that there is no requirement of maintenance throughout the year and the only output constraint is the capacity factor (see Table 7).

    Table 7.  Resource capacity factor (Sources: Geothermal Energy [43]; USACE [44]).
    Resource Capacity factor
    Coal 0.7
    Oil 0.85
    LNG 0.7
    Nuclear 0.9
    Biomass 0.8
    Geothermal 0.85
     | Show Table
    DownLoad: CSV

    2.3.   Electricity demand

    This study assumes an annual electricity demand for 2030 of 1065 TWh [36]. The hourly demand profile was based on that previously estimated by Knüpfer et al. [31], using monthly demand values for each prefecture from 2017 [45]. The hourly time series of demand throughout the day was obtained by distributing these monthly values through a weighting factor, using as a base the hourly demand values of the Kanto region [46]. The hourly demand used in the simulation employs hourly values from the 2017 base year, and proportionately adjusted them based on the change in the expected future annual demand. For further details, please refer to Knüpfer et al. [31].

    2.4.   Scenario set-up

    The present research has two aims. First, to understand the potential contribution to the energy mix that offshore wind could make by 2030 and in the long-term. Second, to estimate whether the planned long-term spatial distribution of offshore wind capacity is optimal for the maximum integration of wind into the energy system.

    To achieve the first aim, a business-as-usual (BAU) and Scenario 1 were defined. The objective of the BAU was to estimate the impact of offshore wind on the energy mix based on the 2030 capacity target. Scenario 1 estimates the impact of offshore wind on the energy mix in the long-term by simulating the maximum estimated capacity of 91 GW [7], which is approximately the same as the current maximum planned capacity of 90 GW [7]. The 91 GW capacity is distributed proportionately according to current plans for 2040 [39].

    To achieve the second aim, the authors assumed an installed capacity of 91 GW for offshore wind in Japan in Scenario 2 and re-distributed the planned [39] regional offshore wind capacity using the model simulation to maximize its integration potential, while keeping all other resources and transmission grid capacity constant. Table 8 summarizes the scenario settings.

    Table 8.  Scenario and BAU definitions, objectives and settings in the EnSym model.
    Scenario Description and objective Installed capacity RES-E generation share (%)
    BAU Simulate electricity generation for Japan with the expected resource shares in 2030 according to the 6th Strategic Energy Plan 6th SEP 6th SEP
    1 Estimate the impact of integrating the maximum offshore wind capacity for the Japanese energy mix 6th SEP with 91GW offshore wind (regional distribution of offshore according to government of Japan) Estimated through the simulation
    2 Estimate whether offshore wind integration can be improved by adjusting regional distribution 6th SEP with 91GW offshore wind (regional distribution of offshore optimized by model) Estimated through the simulation
     | Show Table
    DownLoad: CSV

    3.   Results

    3.1.   BAU: the impact of offshore wind on the energy mix by 2030

    Figure 1 shows the 6th SEP energy target for each resource in 2030, together with the simulated BAU. Compared to the 6th SEP energy mix target, oil and LNG respectively represent 1.35% and 11.52% more of the energy mix than expected, while conventional hydro, biomass, geothermal, wind and solar did not reach their target shares.

    Figure 1.  a) The 6th SEP target share for each resource in 2030 and b) The BAU energy mix with the planned installed capacity for each resource in 2030.
    DownLoad: Full-Size Img PowerPoint

    Figure 2 shows the energy mix over 24 hours on one of the highest demand days (8th August 2030) in the year for Japan.

    Figure 2.  BAU energy mix on 8th August 2030.
    DownLoad: Full-Size Img PowerPoint

    Table 9 shows how some differences can be observed between the 8th August 2030 and the annual generation shares for each resource. While the overall tendency is similar to the annual energy mix, the share of offshore wind and solar PV were 0.99% and 6.4% lower, respectively. This reduction was balanced by biomass, geothermal, oil and LNG.

    Table 9.  Energy mix by resource on 8th August 2030 (GWh).
    Nuclear Coal Hydro conv. Biomass geothermal oil Pumped hydro Batteries Onshore wind Offshore wind Solar PV LNG
    612.7
    (20.4%)    		 554.4
    (18.5%)    		 215.6
    (7.20%)    		 129.6
    (4.33%)    		 25.15
    (0.84%)    		 115.9
    (3.87%)    		 0.579
    (0.02%)    		 0.051
    (0.002%)    		 37.16
    (1.24%)    		 21.15
    (0.71%)    		 90.71
    (3.03%)    		 1193.2
    (39.8%)
     | Show Table
    DownLoad: CSV

    3.2.   Scenario 1: the 6th SEP energy mix with maximized offshore wind capacity

    After obtaining the BAU energy mix, the installed capacity of offshore wind was increased from 10 to 91 GW at the country-level, and regionally distributed as described in section 2.2. The installed capacities for all other resources were kept constant. Increasing the offshore wind capacity increased the annual share of wind from 3.07% to 8.56% (see Figure 3). Further, solar PV increased by 0.28%, while the generation of all other resources (except pumped hydro and batteries), decreased as they were replaced by the increase in variable renewables.

    Figure 3.  a) Annual energy mix for BAU and b) Scenario 1.
    DownLoad: Full-Size Img PowerPoint

    Figure 4 shows the energy mix for 24 hours on a high demand day in Japan (8th August 2030).

    Figure 4.  Scenario 1 energy mix on 8th August 2030.
    DownLoad: Full-Size Img PowerPoint

    Table 10 shows the respective resource generation shares for the BAU and Scenario 1 on 8th August 2030. Compared to the BAU, Scenario 1 increased offshore wind generation, replacing 208 GWh of LNG and oil generation throughout the day.

    Table 10.  Energy mix by resource on 8th August 2030 (GWh).
    Scenario Nuclear Coal Hydro convent. Biomass Geothermal Oil Pumped hydro Batteries Onshore wind Offshore wind Solar PV LNG
    BAU 612.7
    (20.4%)    		 554.4
    (18.5%)    		 215.6
    (7.20%)    		 129.6
    (4.33%)    		 25.15
    (0.84%)    		 115.9
    (3.87%)    		 0.579
    (0.02%)    		 0.051
    (0.002%)    		 37.16
    (1.24%)    		 21.15
    (0.71%)    		 90.71
    (3.03%)    		 1193.2
    (39.8%)
    1 612.7
    (20.4%)    		 554.4
    (18.5%)    		 215.6
    (7.20%)    		 123.9
    (4.14%)    		 24.30
    (0.81%)    		 36.07
    (1.20%)    		 1.686
    (0.06%)    		 0.222
    (0.01%)    		 36.94
    (1.23%)    		 233.2
    (7.78%)    		 92.17
    (3.08%)    		 1065.0
    (35.5%)
     | Show Table
    DownLoad: CSV

    3.3.   Scenario 2: improving wind integration through capacity distribution

    The objective of Scenario 2 was to estimate whether offshore wind integration can be improved by adjusting its planned regional distribution [39] through EnSym, while assuming that all other resource- and transmission capacities remain unchanged. Figure 5 compares resource generation shares in the energy mix between Scenarios 1 and 2.

    Figure 5.  a) Annual energy mix for Scenario 1 and b) Scenario 2.
    DownLoad: Full-Size Img PowerPoint

    By adjusting the distribution of the offshore wind resource compared to the current plan [39], the share of offshore wind increased by 2.49% and overall demand coverage improved from 99.53% (Scenario 1) to 99.61% (Scenario 2), with the RES-E share increasing from 30.16% to 32.80%, mainly by replacing LNG (–2.21%), as well as some nuclear, coal, and oil.

    Table 11 provides an overview of the differences in offshore wind capacity distribution between the current plan ([39]; Scenario 1) and the distribution which the authors determined through the simulation (Scenario 2). In Scenario 1 it can be observed that there is a general trend for offshore wind distribution to follow the distribution of the resource potential (mainly in Hokkaido and Kyushu) [39]. In Scenario 2 the capacity distribution estimated through the simulation for maximized integration of the resource in the energy mix focuses on development in or directly neighboring high electricity demand regions. Only Tohoku is a focus region in both Scenario 1 and Scenario 2, as it has both high resource potential in itself, as well as neighboring a high demand region (Kanto, where Tokyo is located).

    Table 11.  Offshore wind installed capacity regional distribution (GW).
    Scenario Total Hokkaido Tohoku Kanto Chubu Hokuriku Kansai Shikoku Chugoku Kyushu
    1 91 29.35 18.22 7.49 2.73 2.63 1.82 1.01 3.44 24.29
    2 91 2 13 27.35 11.6 0.05 10 9 9 9
     | Show Table
    DownLoad: CSV

    Figure 6 shows that, on a high demand day, the difference in the resource distribution between Scenario 1 and Scenario 2 (Table 12) is minor, with a slight tendency for biomass, oil and wind to increase.

    Figure 6.  Scenario 2 energy mix on 8th August 2030.
    DownLoad: Full-Size Img PowerPoint
    Table 12.  Energy mix by resource on 8th August 2030 (GWh).
    Scenario Nuclear Coal Hydro convent. Biomass Geothermal Oil Pumped hydro Batteries Onshore wind Offshore wind Solar PV LNG
    1 612.7
    (20.4%)    		 554.4
    (18.5%)    		 215.6
    (7.20%)    		 123.9
    (4.14%)    		 24.30
    (0.81%)    		 36.07
    (1.20%)    		 1.686
    (0.06%)    		 0.222
    (0.01%)    		 36.94
    (1.23%)    		 233.2
    (7.78%)    		 92.17
    (3.08%)    		 1065.0
    (35.5%)
    2 612.7
    (20.4%)    		 554.4
    (18.5%)    		 215.6
    (7.20%)    		 124.9
    (4.17%)    		 24.32
    (0.81%)    		 36.17
    (1.21%)    		 1.612
    (0.05%)    		 0.197
    (0.01%)    		 36.94
    (1.23%)    		 243.1
    (8.11%)    		 92.17
    (3.08%)    		 1054.1
    (35.2%)
     | Show Table
    DownLoad: CSV

    4.   Discussion

    4.1.   Comparisons between scenarios

    The higher share of LNG and oil in the BAU compared to the planned generation according to the 6th SEP is likely due to the relationship between the spatial distribution of the capacity of these resources with respect to the electricity demand distribution. Both oil and LNG capacities are near the major demand centers and are flexible, meaning they can be dispatched irrespective of weather conditions (which solar PV and wind are dependent on) and at short notice. To minimize the burden on the grid, the model prefers dispatching resources as close to demand locations as possible. Therefore, during hours of low solar PV and wind availability, LNG and oil will be more likely to increase their generation than biomass, hydro or geothermal in high-demand regions which are mainly Kanto and Kansai. Lastly, assuming that enough solar PV and wind capacity are installed to technically achieve the target share, then the lack in generation observed in Figure 1 may also be due to the meteorological conditions of the base year chosen, which was 2018.

    4.2.   Difference in distribution strategy

    The offshore wind capacity distribution between Scenario 1 (in accordance with METI [39]) and Scenario 2 (estimated by the authors through the simulation) show significant strategic differences. While the distribution aimed for by the government of Japan is focused on the resource-rich regions of Hokkaido and Kyushu, the simulation by the authors focused on the electricity demand centers of Kanto and Kansai, as well as their direct neighbors.

    There are two main reasons for these differences. First, the government of Japan aims to use some of the offshore capacity in Hokkaido and Kyushu for H2 production by water electrolysis. This would reduce the pressure on the transmission grid and could allow for the efficient use of wind generated in these regions in a way which cannot be reflected in the model's current configuration. Second, the model was more likely to prefer placing capacity in regions other than Kyushu and Hokkaido as these two regions only have limited transmission capacity between them, compared to the two or three in other regions, which provides more flexible opportunities for transmission in the simulation.

    Even though the model does not currently reflect the transport sector use of wind generation capacity, the distribution estimated by the authors in Scenario 2 can serve as an indicator as to an optimized resource capacity distribution for maximized integration opportunities. This may be useful for companies planning to develop offshore wind power capacity for interconnection to the grid rather than direct H2 production by electrolysis.

    4.3.   Model limitations

    The model aims to match the power demand in each region for each hour with the corresponding power supply. In the present simulation, the increase in offshore wind between scenarios improved the overall demand coverage achieved (from 99.25% to 99.61%), as well as the total RES-E share (from 24.86% to 32.80%), with the latter improvement mostly being due to the increase in offshore wind (up by 8.07%), which mainly replaced LNG (down by 6.56% between the BAU and Scenario 2). The discrepancy between generation and demand (0.39% in Scenario 2) is mainly due to a compounding rounding error recorded each hour due to the categorization of variables. Removing this error should be addressed in further development of the model. The model has, while being tested during development, achieved 100% demand coverage on several occasions but this is not yet consistent. Despite this shortcoming, EnSym does improve on previous models by including several types of storage capacities (compared to Wakiyama and Kuriyama [29]), and avoiding looping issues by defining flow rules that track transmission line usage (compared to Kainou [47] and Yoshihara and Ohashi [30]). Also, it should be noted that the model detailed here does not include the charging of electrical vehicles, hybrid cards or electrolyzes, which should be targeted in further improvements to the model. Further, EnSym does not currently distinguish between the various demand groups (for example, households, industry). In the future it would be useful to differentiate between the various demand groups, as their patterns may change and interact with renewables such as solar PV. Further, to increase the representativeness of the results, particularly related to meteorologically dependent data, more years should be simulated.

    5.   Conclusions

    Despite the relatively high potential for offshore wind generation in Japan, this resource is less developed than other RES-E, in part because turbines that are currently on the market do not generate efficiently or at all during typhoon events. In this study, the authors expanded the EnSym model to simulate offshore wind electricity generation and integration potential for the estimated wind resource of Japan (91 GW) as part of the energy mix by 2030. In doing so, the authors made three observations:

    ● While the target capacity for offshore wind in 2030 according to the 6th SEP is 10 GW, the resource could be effectively integrated into the energy system even at 91 GW capacity without reinforcement of the existing onshore transmission grid. This suggests that an even higher capacity development target could safely be set for 2030.

    ● The introduction of T-class turbines to Japan could significantly increase the wind generation share in the energy mix.

    ● A focus on developing offshore wind off the coast of high-demand and well-connected regions could improve opportunities for the integration of this resource into the energy mix compared to the current policy strategy, which seems to focus more on development in regions with high resource potential. However, for uses that do not depend on transmission grid integration, such as electrolysis directly on-site, Hokkaido and Kyushu may be highly efficient regions to develop offshore wind capacity.

    Acknowledgements

    A part the present work was performed as a part of activities of Research Institute of Sustainable Future Society, Waseda Research Institute for Science and Engineering, Waseda University. This research was supported by Japan Science and technology Agency (JST) as part of the Belmont Forum Grant Number JPMJBF18T2.

    Conflict of interest

    The authors declare no conflicts of interest.

    Appendix

    Nuclear power target capacity adjustment from 38 GW to 33.2 GW.

    Based on the list of current status of nuclear plants provided by the Japan Atomic Industrial Forum [48], Table A1 lists the power plants which currently under operation and expect to be working in 2030 (some of which may eventually have their working life extended over 60 years).

    Table A1.  Installed nuclear capacity (MW) assumed to be available in 2030 by region (Source: JAIF [48]).
    Plant name Owner Location Capacity
    TOKAI-2 JAPC Kanto 1100
    TSURUGA-2 JAPC Hokuriku 1160
    TOMARI-1 Hokkaido EPC Hokkaido 579
    TOMARI-2 Hokkaido EPC Hokkaido 579
    TOMARI-3 Hokkaido EPC Hokkaido 912
    ONAGAWA-2 Tohoku EPC Tohoku 825
    ONAGAWA-3 Tohoku EPC Tohoku 825
    HIGASHIDORI-1 Tohoku EPC Tohoku 1100
    KASHIWAZAKI KARIWA-1 TEPCO Hokuriku 1100
    KASHIWAZAKI KARIWA-2 TEPCO Hokuriku 1100
    KASHIWAZAKI KARIWA-3 TEPCO Hokuriku 1100
    KASHIWAZAKI KARIWA-4 TEPCO Hokuriku 1100
    KASHIWAZAKI KARIWA-5 TEPCO Hokuriku 1100
    KASHIWAZAKI KARIWA-6 TEPCO Hokuriku 1356
    KASHIWAZAKI KARIWA-7 TEPCO Hokuriku 1356
    HAMAOKA-3 Chubu EPC Chubu 1100
    HAMAOKA-4 Chubu EPC Chubu 1137
    HAMAOKA-5 Chubu EPC Chubu 1380
    SHIKA-1 Hokuriku EPC Hokuriku 540
    SHIKA-2 Hokuriku EPC Hokuriku 1358
    MIHAMA-3 Kansai EPC Hokuriku 826
    TAKAHAMA-1 Kansai EPC Hokuriku 826
    TAKAHAMA-2 Kansai EPC Hokuriku 826
    TAKAHAMA-3 Kansai EPC Hokuriku 870
    TAKAHAMA-4 Kansai EPC Hokuriku 870
    OHI-3 Kansai EPC Hokuriku 1180
    OHI-4 Kansai EPC Hokuriku 1180
    SHIMANE-2 Chugoku EPC Chugoku 820
    IKATA-3 Shikoku EPC Shikoku 890
    GENKAI-3 Kyushu EPC Kyushu 1180
    GENKAI-4 Kyushu EPC Kyushu 1180
    SENDAI-1 Kyushu EPC Kyushu 890
    SENDAI-2 Kyushu EPC Kyushu 890
    Total operable capacity: 33,235
     | Show Table
    DownLoad: CSV

    Planned geothermal regional capacity development projects to 2030

    There are five geothermal plants, totaling 66.1 MW, that are scheduled to connect to the energy system by 2030, as shown in Table A2. Based on this information, additional capacity was added to Hokkaido and Tohoku individually, while the remaining was distributed proportionally amongst regions.

    Table A2.  Geothermal power plants planned to operate before 2030 (JPOWER [49]; JOGMEC [50]; METI [34]).
    Project name Region Planned capacity (MW) Planned start date Developer
    Minamikayabe Hokkaido 6.5 2022 FIT
    Onikoube Tohoku 14.9 2023 JPOWER
    Appi Tohoku 14.9 2024 JPOWER
    Oyasu Tohoku 14.9 2026 FIT
    Kijiyama Tohoku 14.9 2029 FIT
     | Show Table
    DownLoad: CSV

    Solar and wind data measurement stations

    Table A3 lists the locations and station IDs used to measure solar and wind potential generation [41,42].

    Table A3.  List of JMA station IDs by prefecture and resource (Source: JMA [41,42]).
    Prefecture Onshore wind Offshore wind Solar
    Hokkaido s47420 24101 a0047
    Aomori a1122 s47581
    Akita a0186 32616 a0183
    Iwate a0211 a0236
    Yamagata a1465 s47520
    Miyagi a1626 s47590
    Fukushima s47570 a1034
    Tochigi s47615 a0335
    Ibaraki s47629 s47629
    Saitama s47626 s47626
    Gunma s47624 a1021
    Chiba s47648 a0376
    Tokyo a0371 44226 a0370
    Kanagawa a0392 a1443
    Yamanashi s47638 a1023
    Shizuoka s47655 50506 a0451
    Niigata a1469 54166 s47604
    Nagano a0399 a0399
    Toyama a1533 s47606
    Fukui a1071 s47616
    Ishikawa s47600 s47605
    Gifu a0493 s47632
    Mie a1230 a0509
    Aichi a0470 a0984
    Shiga a0586 a0963
    Nara a0635 s47780
    Wakayama a1485 65036 s47778
    Osaka a1471 s47772
    Kyoto s47750 s47750
    Hyogo s47776 s47770
    Kagawa s47891 s47891
    Tokushima s47895 a1242
    Kochi s47898 74271 a1249
    Ehime a1456 a0739
    Tottori a1519 a1231
    Shimane s47755 a0704
    Okayama s47768 a0668
    Hiroshima a0686 67511 a0686
    Yamaguchi a0779 a0775
    Fukuoka a0943 a0943
    Saga a1610 a0829
    Kumamoto a1240 a0834
    Nagasaki s47805 84072 a0922
    Oita s47814 a1237
    Miyazaki s47822 87492 s47822
    Kagoshima a0895 s47827
     | Show Table
    DownLoad: CSV

    T-class turbine

    The Vestas model V236-15MWTM was chosen as it is classified as an S and T-class turbine, which can stand severe weather conditions such as typhoons. Further, among turbines at this capacity, it had the most publicly available information, such as cut-in and cut-out speed and rotor diameter. The authors estimated a power curve for the model through approximation from the Vestas V100/1.8 turbine, which was chosen due to the public availability of its power curve and due to it being produced by the same manufacturer.

    As the cut-in speed of the two turbines is different, the power of the V236-15MW at its cut-in speed (3 m/s) was calculated by extrapolation:

    Hourly wind generation [Ewind(Wh)] is given by:

    Ewind=12ρAwV3CP (1)

    where ρ is air density which assumed as 1.225 [kgm3], Aw is the wind-swept area [m2], V is the wind velocity [(ms)3] and CP is the power coefficient.

    By substituting this information into the generation equation, a Cp value at 3.5 and 4 m/s can be obtained:

    Ewind[Wh]=12ρAwV3Cp (2)
    413[kWh]×1000=12×1.225×43742×3.53×Cp3.5 (3)
    Cp3.5=0.571 (4)
    876[kWh]×1000=12×1.225×43742×43×Cp4.0 (5)
    Cp4.0=0.763 (6)

    Next, the Cp value at 3 m/s is estimated by extrapolating:

    Cp3.0=0.5Cp4.0−Cp3.5−0.5=0.5×0.763−0.571−0.5=0.38 (7)

    After obtaining the Cp value at 3 m/s, the potential generation at 3 m/s can be estimated:

    Ewind=12×1.225×43742×33×0.38=274800[Wh]=274.8[kWh] (8)

    Based on the potential generation estimated for 3 m/s, the potential generation for the wind speed from 3.5 to 20 m/s is obtained proportionately to the V100/1.8 turbine. Wind speeds between 20 m/s and 30 m/s can generate full power on the V236-15MW turbine. The advantage of a such a turbine is not only that it can withstand typhoons, but that it can also produce power at high cut-out speeds at a high nominal rating. This power curve is summarized in Table A4.

    Table A4.  Power curve data of Vestas turbines.
    Turbine
    Capacity [kW]
    Wind speed [m/s]    		 Vestas 1.8
    1815
    Power [kWh]    		 Vestas 15.0
    15000
    0.00 0 0
    1.50 0 0
    2.00 0 0
    2.50 0 0
    3.00 0 275
    3.50 50 413
    4.00 106 876
    4.50 173 1,430
    5.00 248 2,050
    5.50 338 2,793
    6.00 443 3,661
    6.50 556 4,595
    7.00 705 5,826
    7.50 873 7,215
    8.00 1,063 8,785
    8.50 1,269 10,488
    9.00 1,474 12,182
    9.50 1,641 13,562
    10.00 1,744 14,413
    10.50 1,792 14,810
    11.00 1,808 14,942
    11.50 1,814 14,992
    12.00 1,815 15,000
    12.50 1,815 15,000
    13.00 1,815 15,000
    13.50 1,815 15,000
    14.00 1,815 15,000
    14.50 1,815 15,000
    15.00 1,815 15,000
    15.50 1,815 15,000
    16.00 1,815 15,000
    16.50 1,815 15,000
    17.00 1,815 15,000
    17.50 1,815 15,000
    18.00 1,815 15,000
    18.50 1,815 15,000
    19.00 1,815 15,000
    19.50 1,815 15,000
    20.00 1,815 15,000
    20.50 0 15,000
    21.00 0 15,000
    21.50 0 15,000
    22.00 0 15,000
    22.50 0 15,000
    23.00 0 15,000
    23.50 0 15,000
    24.00 0 15,000
    24.50 0 15,000
    25.00 0 15,000
    25.50 0 15,000
    26.00 0 15,000
    26.50 0 15,000
    27.00 0 15,000
    27.50 0 15,000
    28.00 0 15,000
    28.50 0 15,000
    29.00 0 15,000
    29.50 0 15,000
    30.00 0 15,000
     | Show Table
    DownLoad: CSV

    Based on these values, the power curve for the V236-15MWTM is shown in Figure A1, as compared with the power curve of the V100/1.8 turbine.

    Figure A1.  Power curve of Vestas turbine models.
    DownLoad: Full-Size Img PowerPoint

    Submarine cable parameter

    Table A5.  Information of submarine cable.
    Parameter Material/ Value
    Cable type XLPE (cross linked polyethylene)
    Core number 3
    Voltage [kV] 220
    Cross-section area [mm2] 800
     | Show Table
    DownLoad: CSV


    [1] Y. Zhao, Y. Peng, Saliency-guided video classification via adaptively weighted learning, in 2017 IEEE International Conference on Multimedia and Expo (ICME), (2017), 847–852. https://doi.org/10.1109/ICME.2017.8019343
    [2] X. Hu, Y. Wang, J. Shan, Automatic recognition of cloud images by using visual saliency features, IEEE Geosci. Remote Sens. Lett., 12 (2015), 1760–1764. https://doi.org/10.1109/LGRS.2015.2424531 doi: 10.1109/LGRS.2015.2424531
    [3] J. C. Ni, Y. Luo, D. Wang, J. Liang, Q. Zhang, Saliency-based sar target detection via convolutional sparse feature enhancement and bayesian inference, IEEE Trans. Geosci. Remote Sens., 61 (2023), 1–15. https://doi.org/10.1109/TGRS.2023.3237632 doi: 10.1109/TGRS.2023.3237632
    [4] Z. Yu, Y. Zhuge, H. Lu, L. Zhang, Joint learning of saliency detection and weakly supervised semantic segmentation, in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), (2019), 7222–7232. https://doi.org/10.1109/ICCV.2019.00732
    [5] S. Lee, M. Lee, J. Lee, H. Shim, Railroad is not a train: Saliency as pseudo-pixel supervision for weakly supervised semantic segmentation, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2021), 5491–5501. https://doi.org/10.1109/CVPR46437.2021.00545
    [6] W. Feng, R. Han, Q. Guo, J. Zhu, S, Wang, Dynamic saliency-aware regularization for correlation filter-based object tracking, IEEE Trans.n Image Process., 28 (2019), 3232–3245. https://doi.org/10.1109/TIP.2019.2895411 doi: 10.1109/TIP.2019.2895411
    [7] J. Y. Zhu, J. Wu, Y. Xu, E. Chang, Z. Tu, Unsupervised object class discovery via saliency-guided multiple class learning, IEEE Trans. Pattern Anal. Mach. Intell., 37 (2015), 862–875. https://doi.org/10.1109/TPAMI.2014.2353617 doi: 10.1109/TPAMI.2014.2353617
    [8] S. Wei, L. Liao, J. Li, Q. Zheng, F. Yang, Y. Zhao, Saliency inside: Learning attentive cnns for content-based image retrieval, IEEE Trans. Image Process., 28 (2019), 4580–4593. https://doi.org/10.1109/TIP.2019.2913513 doi: 10.1109/TIP.2019.2913513
    [9] A. Kim, R. M. Eustice, Real-time visual slam for autonomous underwater hull inspection using visual saliency, IEEE Trans. Rob., 29 (2013), 719–733. https://doi.org/10.1109/TRO.2012.2235699 doi: 10.1109/TRO.2012.2235699
    [10] R. Li, C. H. Wu, S. Liu, J. Wang, G. Wang, G. Liu, B. Zeng, SDP-GAN: Saliency detail preservation generative adversarial networks for high perceptual quality style transfer, IEEE Trans. Image Process., 30 (2021), 374–385. https://doi.org/10.1109/TIP.2020.3036754 doi: 10.1109/TIP.2020.3036754
    [11] L. Jiang, M. Xu, X. Wang, L. Sigal, Saliency-guided image translation, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2021), 16504–16513. https://doi.org/10.1109/CVPR46437.2021.01624
    [12] S. Li, M. Xu, Y. Ren, Z. Wang, Closed-form optimization on saliency-guided image compression for HEVC-MSP, IEEE Trans. Multimedia, 20 (2018), 155–170. https://doi.org/10.1109/TMM.2017.2721544 doi: 10.1109/TMM.2017.2721544
    [13] Y. Patel, S. Appalaraju, R. Manmatha, Saliency driven perceptual image compression, in 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), (2021), 227–231. https://doi.org/10.1109/WACV48630.2021.00027
    [14] C. Yang, L. Zhang, H. Lu, X. Ruan, M. H. Yang, Saliency detection via graph-based manifold ranking, in 2013 IEEE Conference on Computer Vision and Pattern Recognition, (2013), 3166–3173. https://doi.org/10.1109/CVPR.2013.407
    [15] W. Zhu, S. Liang, Y. Wei, J. Sun, Saliency optimization from robust background detection, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, (2014), 2814–2821. https://doi.org/10.1109/CVPR.2014.360
    [16] K. Shi, K. Wang, J. Lu, L. Lin, Pisa: Pixelwise image saliency by aggregating complementary appearance contrast measures with spatial priors, in 2013 IEEE Conference on Computer Vision and Pattern Recognition, (2013), 2115–2122. https://doi.org/10.1109/CVPR.2013.275
    [17] M. M. Cheng, N. J. Mitra, X. Huang, P. H. S. Torr, S. M. Hu., Global contrast based salient region detection, IEEE Trans. Pattern Anal. Mach. Intell., 37 (2015), 569–582. https://doi.org/10.1109/CVPR.2011.5995344 https://doi.org/10.1109/CVPR.2011.5995344 doi: 10.1109/CVPR.2011.5995344
    [18] W. C. Tu, S. He, Q. Yang, S. Y. Chien, Real-time salient object detection with a minimum spanning tree, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016), 2334–2342. https://doi.org/10.1109/CVPR.2016.256
    [19] R. Zhao, W. Ouyang, H. Li, X, Wang, Saliency detection by multi-context deep learning, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2015), 1265–1274. https://doi.org/10.1109/CVPR.2015.7298731
    [20] G. Li, Y. Yu, Visual saliency based on multiscale deep features, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2015), 5455–5463.
    [21] L. Wang, H. Lu, X. Ruan, M. H. Yang, Deep networks for saliency detection via local estimation and global search, in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2015), 3183–3192. https://doi.org/10.1109/CVPR.2015.7298938
    [22] Z. Luo, A. Mishra, A. Achkar, J. Eichel, S. Li, P. M. Jodoin, Non-local deep features for salient object detection, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017), 6593–6601. https://doi.org/10.1109/CVPR.2017.698
    [23] P. Zhang, D. Wang, H. Lu, H. Wang, X. Ruan, Amulet: Aggregating multi-level convolutional features for salient object detection, in 2017 IEEE International Conference on Computer Vision (ICCV), (2017), 202–211. https://doi.org/10.1109/ICCV.2017.31
    [24] Q. Hou, M. M. Cheng, X. Hu, A. Borji, Z. Tu, P. Torr, Deeply supervised salient object detection with short connections, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017), 5300–5309. https://doi.org/10.1109/CVPR.2017.563
    [25] W. Wang, Q. Lai, H. Fu, J. Shen, H. Ling, R. Yang, Salient object detection in the deep learning era: An in-depth survey, IEEE Trans. Pattern Anal. Mach. Intell., 44 (2022), 3239–3259. https://doi.org/10.1109/TPAMI.2021.3051099 doi: 10.1109/TPAMI.2021.3051099
    [26] A. Borji, M. M. Cheng, Q. Hou, H. Jiang, J. Li, Salient object detection: A survey, Comput. Vis. Media, 5 (2019), 117–150. https://doi.org/10.1007/s41095-019-0149-9 doi: 10.1007/s41095-019-0149-9
    [27] T. Zhou, D. P. Fan, M. M. Cheng, J. Shen, L. Shao, RGB-D salient object detection: A survey, Comput. Vis. Media, 7 (2021), 37–69. https://doi.org/10.1007/s41095-020-0199-z doi: 10.1007/s41095-020-0199-z
    [28] X. Song, D. Zhou, W. Li, Y. Dai, L. Liu, H. Li, et al., WAFP-Net: Weighted attention fusion based progressive residual learning for depth map super-resolution, IEEE Trans. Multimedia, 24 (2022), 4113–4127. https://doi.org/10.1109/TMM.2021.3118282 doi: 10.1109/TMM.2021.3118282
    [29] P. F. Proença, Y. Gao, Splode: Semi-probabilistic point and line odometry with depth estimation from RGB-D camera motion, in 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), (2017), 1594–1601. https://doi.org/10.1109/IROS.2017.8205967
    [30] X. Xing, Y. Cai, T. Lu, Y. Yang, D. Wen, Joint self-supervised monocular depth estimation and SLAM, in 2022 26th International Conference on Pattern Recognition (ICPR), (2022), 4030–4036. https://doi.org/10.1109/ICPR56361.2022.9956576
    [31] Q. Chen, Z. Liu, Y. Zhang, K. Fu, Q. Zhao, H. Du, RGB-D salient object detection via 3d convolutional neural networks, in Proceedings of the AAAI Conference on Artificial Intelligence, (2021), 1063–1071. https://doi.org/10.1609/aaai.v35i2.16191
    [32] F. Wang, J. Pan, S. Xu, J. Tang, Learning discriminative cross-modality features for RGB-D saliency detection, IEEE Trans. Image Process., 31 (2022), 1285–1297. https://doi.org/10.1109/TIP.2022.3140606 doi: 10.1109/TIP.2022.3140606
    [33] Z. Wu, G. Allibert, F. Meriaudeau, C. Ma, C. Demonceaux, Hidanet: RGB-D salient object detection via hierarchical depth awareness., IEEE Trans. Image Process., 32 (2023), 2160–2173. https://doi.org/10.1109/TIP.2023.3263111 doi: 10.1109/TIP.2023.3263111
    [34] J. Zhang, Q. Liang, Q. Guo, J. Yang, Q. Zhang, Y. Shi, R2net: Residual refinement network for salient object detection, Image Vision Comput., 120 (2022), 104423. https://doi.org/10.1016/j.imavis.2022.104423 doi: 10.1016/j.imavis.2022.104423
    [35] R. Shigematsu, D. Feng, S. You, N. Barnes, Learning RGB-D salient object detection using background enclosure, depth contrast, and top-down features, in 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), (2017), 2749–2757.
    [36] L. Itti, C. Koch, E. Niebur, A model of saliency-based visual attention for rapid scene analysis, IEEE Trans. Pattern Anal. Mach. Intell., 20 (1998), 1254–1259. https://doi.org/10.1109/34.730558 doi: 10.1109/34.730558
    [37] C. Yang, L. Zhang, H. Lu, Graph-regularized saliency detection with convex-hull-based center prior, IEEE Signal Process. Lett., 20 (2013), 637–640. https://doi.org/10.1109/LSP.2013.2260737 doi: 10.1109/LSP.2013.2260737
    [38] P. Jiang, H. Ling, J. Yu, J. Peng, Salient region detection by ufo: Uniqueness, focusness and objectness, in 2013 IEEE International Conference on Computer Vision, (2013), 1976–1983.
    [39] R. S. Srivatsa, R. V. Babu, Salient object detection via objectness measure, in 2015 IEEE International Conference on Image Processing (ICIP), (2015), 4481–4485. https://doi.org/10.1109/ICIP.2015.7351654
    [40] C. Scharfenberger, A. Wong, K. Fergani, J. S. Zelek, D. A. Clausi, Statistical textural distinctiveness for salient region detection in natural images, in 2013 IEEE Conference on Computer Vision and Pattern Recognition, (2013), 979–986. https://doi.org/10.1109/CVPR.2013.131
    [41] A. Borji, M. M. Cheng, H. Jiang, J. Li, Salient object detection: A benchmark, IEEE Trans. Image Process., 24 (2015), 5706–5722. https://doi.org/10.1109/TIP.2015.2487833 doi: 10.1109/TIP.2015.2487833
    [42] J. Han, D. Zhang, G. Cheng, N. Liu, D. Xu, Advanced deep-learning techniques for salient and category-specific object detection: A survey, IEEE Signal Process. Mag., 35 (2018), 84–100. https://doi.org/10.1109/MSP.2017.2749125 doi: 10.1109/MSP.2017.2749125
    [43] A. Krizhevsky, I. Sutskever, G. E. Hinton, Imagenet classification with deep convolutional neural networks, Adv. Neural Inf. Process. Syst., 2012 (2012), 25. https://doi.org/10.1145/3065386 doi: 10.1145/3065386
    [44] K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016), 770–778. https://doi.org/10.1109/CVPR.2016.90
    [45] N. Liu, J. Han, M. H. Yang, Picanet: Learning pixel-wise contextual attention for saliency detection, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018), 3089–3098. https://doi.org/10.1109/CVPR.2018.00326
    [46] S. Chen, X. Tan, B. Wang, X. Hu, Reverse attention for salient object detection, in Proceedings of the European conference on computer vision (ECCV), (2018), 234–250. https://doi.org/10.1007/978-3-030-01240-3_15
    [47] J. J. Liu, Q. Hou, M. M. Cheng, J. Feng, J. Jiang, A simple pooling-based design for real-time salient object detection, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 3912–3921. https://doi.org/10.1109/CVPR.2019.00404
    [48] Y. Pang, X. Zhao, L. Zhang, H. Lu, Multi-scale interactive network for salient object detection, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 9410–9419. https://doi.org/10.1109/CVPR42600.2020.00943
    [49] Q. Hou, M. M. Cheng, X. Hu, A. Borji, Z. Tu, P. H. S. Torr, Deeply supervised salient object detection with short connections, IEEE Trans. Pattern Anal. Mach. Intell., 41 (2019), 815–828. https://doi.org/10.1109/CVPR.2017.563 https://doi.org/10.1109/TPAMI.2018.2815688 doi: 10.1109/CVPR.2017.563
    [50] X. Qin, Z. Zhang, C. Huang, C. Gao, M. Dehghan, M. Jagersand, Basnet: Boundary-aware salient object detection, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 7471–7481. https://doi.org/10.1109/CVPR.2019.00766
    [51] P. Zhang, W. Liu, H. Lu, C. Shen, Salient object detection with lossless feature reflection and weighted structural loss, IEEE Trans. Image Process., 28 (2019), 3048–3060. https://doi.org/10.1109/TIP.2019.2893535 doi: 10.1109/TIP.2019.2893535
    [52] K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, in 3rd International Conference on Learning Representations, 2015.
    [53] W. Wang, S. Zhao, J. Shen, S. C. H. Hoi, A. Borji, Salient object detection with pyramid attention and salient edges, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 1448–1457. https://doi.org/10.1109/CVPR.2019.00154
    [54] T. Zhao, X. Wu, Pyramid feature attention network for saliency detection, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 3080–3089. wangzhi
    [55] S. Chen, X. Tan, B. Wang, H. Lu, X. Hu, Y. Fu, Reverse attention-based residual network for salient object detection, IEEE Trans. Image Process., 29 (2020), 3763–3776. https://doi.org/10.1109/TIP.2020.2965989 doi: 10.1109/TIP.2020.2965989
    [56] M. Feng, H. Lu, E. Ding, Attentive feedback network for boundary-aware salient object detection, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 1623–1632. https://doi.org/10.1109/CVPR.2019.00172
    [57] J. Zhao, J. J. Liu, D. P. Fan, Y. Cao, J. Yang, M. M. Cheng, Egnet: Edge guidance network for salient object detection, in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), (2019), 8778–8787. https://doi.org/10.1109/ICCV.2019.00887
    [58] Y. Niu, Y. Geng, X. Li, F. Liu, Leveraging stereopsis for saliency analysis, in 2012 IEEE Conference on Computer Vision and Pattern Recognition, (2012), 454–461.
    [59] H. Peng, B. Li, W. Xiong, W. Hu, R. Ji, RGBD salient object detection: A benchmark and algorithms, in Computer Vision–ECCV 2014: 13th European Conference, (2014), 92–109. https://doi.org/10.1007/978-3-319-10578-9_7
    [60] Y. Cheng, H. Fu, X. Wei, J. Xiao, X. Cao, Depth enhanced saliency detection method, in Proceedings of international conference on internet multimedia computing and service, (2014), 23–27. https://doi.org/10.1145/2632856.2632866
    [61] R. Ju, L. Ge, W. Geng, T. Ren, G. Wu, Depth saliency based on anisotropic center-surround difference, in 2014 IEEE International Conference on Image Processing (ICIP), (2014), 1115–1119. https://doi.org/10.1109/ICIP.2014.7025222
    [62] J. Ren, X. Gong, L. Yu, W. Zhou, M. Y. Yang, Exploiting global priors for rgb-d saliency detection, in 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), (2015), 25–32. https://doi.org/10.1109/CVPRW.2015.7301391
    [63] A. Wang, M. Wang, RGB-D salient object detection via minimum barrier distance transform and saliency fusion, IEEE Signal Process. Lett., 24 (2017), 663–667. https://doi.org/10.1109/LSP.2017.2688136 doi: 10.1109/LSP.2017.2688136
    [64] R. Cong, J. Lei, H. Fu, J. Hou, Q. Huang, S. Kwong, Going from RGB to RGBD saliency: A depth-guided transformation model, IEEE Trans. Cyber., 50 (2020), 3627–3639. https://doi.org/10.1109/TCYB.2019.2932005 doi: 10.1109/TCYB.2019.2932005
    [65] L. Qu, S. He, J. Zhang, J. Tian, Y. Tang, Q. Yang, RGBD salient object detection via deep fusion, IEEE Trans. Image Process., 26 (2017), 2274–2285. https://doi.org/10.1109/TIP.2017.2682981 doi: 10.1109/TIP.2017.2682981
    [66] Y. Piao, W. Ji, J. Li, M. Zhang, H. Lu, Depth-induced multi-scale recurrent attention network for saliency detection, in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), (2019), 7253–7262. https://doi.org/10.1109/ICCV.2019.00735
    [67] N. Liu, N. Zhang, J. Han, Learning selective self-mutual attention for RGB-D saliency detection, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 13753–13762. https://doi.org/10.1109/CVPR42600.2020.01377
    [68] C. Li, R. Cong, S. Kwong, J. Hou, H. Fu, G. Zhu, et al., ASIF-Net: Attention steered interweave fusion network for RGB-D salient object detection, IEEE Trans. Cyber., 51 (2021), 88–100. https://doi.org/10.1109/TCYB.2020.2969255 doi: 10.1109/TCYB.2020.2969255
    [69] G. Li, Z. Liu, M. Chen, Z. Bai, W. Lin, H. Ling, Hierarchical alternate interaction network for RGB-D salient object detection, IEEE Trans. Image Process., 30 (2021), 3528–3542. https://doi.org/10.1109/TIP.2021.3062689 doi: 10.1109/TIP.2021.3062689
    [70] Y. H. Wu, Y. Liu, J. Xu, J. W. Bian, Y. C. Gu, M. M. Cheng, MobileSal: Extremely efficient RGB-D salient object detection, IEEE Trans. Pattern Anal. Mach. Intell., 44 (2022), 10261–10269. https://doi.org/10.1109/TPAMI.2021.3134684 doi: 10.1109/TPAMI.2021.3134684
    [71] N. Huang, Y. Yang, D. Zhang, Q. Zhang, J. Han, Employing bilinear fusion and saliency prior information for RGB-D salient object detection, IEEE Trans. Multimedia, 24 (2022), 1651–1664. https://doi.org/10.1109/TMM.2021.3069297 doi: 10.1109/TMM.2021.3069297
    [72] X. Wang, S. Li, C. Chen, Y. Fang, A. Hao, H. Qin, Data-level recombination and lightweight fusion scheme for RGB-D salient object detection, IEEE Trans. Image Process., 30 (2021), 458–471. https://doi.org/10.1109/TIP.2020.3037470 doi: 10.1109/TIP.2020.3037470
    [73] X. Zhao, L. Zhang, Y. Pang, H. Lu, L. Zhang, A single stream network for robust and real-time RGB-D salient object detection, in Computer Vision—ECCV 2020: 16th European Conference, (2020), 646–662. https://doi.org/10.1007/978-3-030-58542-6_39
    [74] K. Fu, D. P. Fan, G. P. Ji, Q. Zhao, JL-DCF: Joint learning and densely-cooperative fusion framework for RGB-D salient object detection, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 3049–3059. https://doi.org/10.1109/CVPR42600.2020.00312
    [75] J. Han, H. Chen, N. Liu, C. Yan, X. Li, CNNs-based RGB-D saliency detection via cross-view transfer and multiview fusion, IEEE Trans. Cyber., 48 (2018), 3171–3183. https://doi.org/10.1109/TCYB.2017.2761775 doi: 10.1109/TCYB.2017.2761775
    [76] N. Wang, X. Gong, Adaptive fusion for RGB-D salient object detection, IEEE Access, 7 (2019), 55277–55284. https://doi.org/10.1109/ACCESS.2019.2913107 doi: 10.1109/ACCESS.2019.2913107
    [77] G. Li, Z. Liu, H. Ling, ICNet: Information conversion network for RGB-D based salient object detection, IEEE Trans. Image Process., 29 (2020), 4873–4884. https://doi.org/10.1109/TIP.2020.2976689 doi: 10.1109/TIP.2020.2976689
    [78] H. Chen, Y. Li, Progressively complementarity-aware fusion network for RGB-D salient object detection, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, (2018), 3051–3060. https://doi.org/10.1109/CVPR.2018.00322
    [79] M. Zhang, W. Ren, Y. Piao, Z. Rong, H.Lu, Select, supplement and focus for RGB-D saliency detection, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 3469–3478. https://doi.org/10.1109/CVPR42600.2020.00353
    [80] C. Chen, J. Wei, C. Peng, H. Qin, Depth-quality-aware salient object detection, IEEE Trans. Image Process., 30 (2021), 2350–2363. https://doi.org/10.1109/TIP.2021.3052069 doi: 10.1109/TIP.2021.3052069
    [81] Y. Zhai, D. P. Fan, J. Yang, A. Borji, L. Shao, J. Han, L. Wang, Bifurcated backbone strategy for RGB-D salient object detection, IEEE Trans. Image Process., 30 (2021), 8727–8742. https://doi.org/10.1109/TIP.2021.3116793 doi: 10.1109/TIP.2021.3116793
    [82] W. D. Jin, J. Xu, Q. Han, Y. Zhang, M. M. Cheng, CDNet: Complementary depth network for RGB-D salient object detection, IEEE Trans. Image Process., 30 (2021), 3376–3390. https://doi.org/10.1109/TIP.2021.3060167 doi: 10.1109/TIP.2021.3060167
    [83] Z. Zhang, Z. Lin, J. Xu, W. D. Jin, S. P. Lu, D. P. Fan, Bilateral attention network for RGB-D salient object detection, IEEE Trans. Image Process., 30 (2021), 1949–1961. https://doi.org/10.1109/TIP.2021.3049959 doi: 10.1109/TIP.2021.3049959
    [84] H. Chen, Y. Li, Three-stream attention-aware network for RGB-D salient object detection, IEEE Trans. Image Process., 28 (2019), 2825–2835. https://doi.org/10.1109/TIP.2019.2891104 doi: 10.1109/TIP.2019.2891104
    [85] J. Zhang, D. P. Fan, Y. Dai, S. Anwar, F. S. Saleh, T. Zhang, et al., Uc-net: Uncertainty inspired rgb-d saliency detection via conditional variational autoencoders, iIn 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2020), 8579–8588. https://doi.org/10.1109/CVPR42600.2020.00861
    [86] A. Luo, X. Li, F. Yang, Z. Jiao, H. Cheng, S. Lyu, Cascade graph neural networks for RGB-D salient object detection, in Computer Vision—ECCV 2020: 16th European Conference, (2020), 346–364. https://doi.org/10.1007/978-3-030-58610-2_21
    [87] B. Jiang, Z. Zhou, X. Wang, J. Tang, B. Luo, CmSalGAN: RGB-D salient object detection with cross-view generative adversarial networks, IEEE Trans. Multimedia, 23 (2021), 1343–1353. https://doi.org/10.1109/TMM.2020.2997184 doi: 10.1109/TMM.2020.2997184
    [88] T. Zhou, H. Fu, G. Chen, Y. Zhou, D. P. Fan, L. Shao, Specificity-preserving RGB-D saliency detection, in 2021 IEEE/CVF International Conference on Computer Vision (ICCV), (2021), 4661–4671. https://doi.org/10.1109/ICCV48922.2021.00464
    [89] T. Zhou, Y. Zhou, C. Gong, J. Yang, Y. Zhang, Feature aggregation and propagation network for camouflaged object detection, IEEE Trans. Image Process., 31 (2022), 7036–7047. https://doi.org/10.1109/TIP.2022.3217695 doi: 10.1109/TIP.2022.3217695
    [90] M. Song, W. Song, G. Yang, C. Chen, Improving RGB-D salient object detection via modality-aware decoder, IEEE Trans. Image Process., 31 (2022), 6124–6138. https://doi.org/10.1109/TIP.2022.3205747 doi: 10.1109/TIP.2022.3205747
    [91] Z. Gu, J. Cheng, H. Fu, K. Zhou, H. Hao, Y. Zhao, et al., Ce-net: Context encoder network for 2d medical image segmentation, IEEE Trans. Med. Imaging, 38 (2019), 2281–2292. https://doi.org/10.1109/TMI.2019.2903562 doi: 10.1109/TMI.2019.2903562
    [92] S. Woo, J. Park, J. Y. Lee, I. S. Kweon, Cbam: Convolutional block attention module, in Proceedings of the European Conference on Computer Vision (ECCV), (2018), 3–19. https://doi.org/10.1007/978-3-030-01234-2_1
    [93] W. Gao, G. Liao, S. Ma, G. Li, Y. Liang, W. Lin, Unified information fusion network for multi-modal RGB-D and RGB-T salient object detection, IEEE Trans. Circuits Syst. Video Technol., 32 (2022), 2091–2106. https://doi.org/10.1109/TCSVT.2021.3082939 doi: 10.1109/TCSVT.2021.3082939
    [94] K. He, X. Zhang, S. Ren, J. Sun, Spatial pyramid pooling in deep convolutional networks for visual recognition, IEEE Trans. Pattern Anal. Mach. Intell., 37 (2015), 1904–1916. https://doi.org/10.1007/978-3-319-10578-9_23 doi: 10.1007/978-3-319-10578-9_23
    [95] I. Loshchilov, F. Hutter, Decoupled weight decay regularization, in 7th International Conference on Learning Representations, 2019.
    [96] J. X. Zhao, Y. Cao, D. P. Fan, M. M. Cheng, X. Y. Li, L. Zhang, Contrast prior and fluid pyramid integration for RGB-D salient object detection, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), 3922–3931.
    [97] N. Li, J. Ye, Y. Ji, H. Ling, J. Yu, Saliency detection on light field, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, (2014), 2806–2813. https://doi.org/10.1109/CVPR.2014.359
    [98] D. P. Fan, Z. Lin, Z. Zhang, M. Zhu, M. M. Cheng, Rethinking RGB-D salient object detection: Models, data sets, and large-scale benchmarks, IEEE Trans. Neural Networks Learn. Syst., 32 (2021), 2075–2089. https://doi.org/10.1109/TNNLS.2020.2996406 doi: 10.1109/TNNLS.2020.2996406
    [99] W. Ji, J. Li, M. Zhang, Y. Piao, H. Lu, Accurate RGB-D salient object detection via collaborative learning, in Computer Vision—ECCV 2020: 16th European Conference, (2020), 52–69. https://doi.org/10.1007/978-3-030-58523-5_4
    [100] W. Zhang, G. P. Ji, Z. Wang, K. Fu, Q. Zhao, Depth quality-inspired feature manipulation for efficient RGB-D salient object detection, in Proceedings of the 29th ACM International Conference on Multimedia, 2021. https://doi.org/10.1145/3474085.3475240
    [101] W. Zhang, Y. Jiang, K. Fu, Q. Zhao, BTS-Net: Bi-directional transfer-and-selection network for RGB-D salient object detection, in 2021 IEEE International Conference on Multimedia and Expo (ICME), (2021), 1–6. https://doi.org/10.1109/ICME51207.2021.9428263
    [102] M. Zhang, S. Yao, B. Hu, Y. Piao, W. Ji, C2DFNet: Criss-cross dynamic filter network for rgb-d salient object detection, IEEE Trans. Multimedia, 2022 (2022), 1–13.
    [103] X. Cheng, X. Zheng, J. Pei, H. Tang, Z. Lyu, C. Chen, Depth-induced gap-reducing network for RGB-D salient object detection: An interaction, guidance and refinement approach, IEEE Trans. Multimedia, 2022 (2022).
    [104] Y. Pang, X. Zhao, L. Zhang, H. Lu, Caver: Cross-modal view-mixed transformer for bi-modal salient object detection, IEEE Trans. Image Process., 32 (2023), 892–904. https://doi.org/10.1109/TIP.2023.3234702 doi: 10.1109/TIP.2023.3234702
    [105] D. P. Fan, C. Gong, Y. Cao, B. Ren, M. M. Cheng, A. Borji, Enhanced-alignment measure for binary foreground map evaluation, in Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, (2018), 698–704. https://doi.org/10.24963/ijcai.2018/97
    [106] D. P. Fan, M. M. Cheng, Y. Liu, T. Li, A. Borji, Structure-measure: A new way to evaluate foreground maps, in 2017 IEEE International Conference on Computer Vision (ICCV), (2017), 4558–4567. https://doi.org/10.1109/ICCV.2017.487
    [107] G. Chen, F. Shao, X. Chai, H. Chen, Q. Jiang, X. Meng, Y. S. Ho, Modality-induced transfer-fusion network for RGB-D and RGB-T salient object detection, IEEE Trans. Circuits Syst. Video Technol., 33 (2023), 1787–1801. https://doi.org/10.1109/TCSVT.2022.3215979 doi: 10.1109/TCSVT.2022.3215979
    [108] Z. Liu, Y. Wang, Z. Tu, Y. Xiao, B. Tang, Tritransnet, in Proceedings of the 29th ACM International Conference on Multimedia, 2021. https://doi.org/10.1145/3474085.3475601
    [109] R. Cong, Q. Lin, C. Zhang, C. Li, X. Cao, Q. Huang, Y. Zhao, CIR-Net: Cross-modality interaction and refinement for RGB-D salient object detection, IEEE Trans. Image Process., 31 (2022), 6800–6815. https://doi.org/10.1109/TIP.2022.3216198 doi: 10.1109/TIP.2022.3216198
    [110] Z. Liu, Y. Tan, Q. He, Y. Xiao, Swinnet: Swin transformer drives edge-aware RGB-D and RGB-T salient object detection, IEEE Trans. Circuits Syst. Video Technol., 32 (2022), 4486–4497. https://doi.org/10.1109/TCSVT.2021.3127149 doi: 10.1109/TCSVT.2021.3127149
    [111] R. Cong, H. Liu, C. Zhang, W. Zhang, F. Zheng, R. Song, S. Kwong, Point-aware interaction and cnn-induced refinement network for RGB-D salient object detection, in Proceedings of the 31st ACM International Conference on Multimedia, 2023. https://doi.org/10.1145/3581783.3611982

  • This article has been cited by:

    1. Rodney Itiki, Madhav Manjrekar, Silvio Giuseppe Di Santo, Proposed Extension of the U.S.–Caribbean Super Grid to South America for Resilience during Hurricanes, 2024, 17, 1996-1073, 233, 10.3390/en17010233
    2. Arben Gjukaj, Rexhep Shaqiri, Qamil Kabashi, Vezir Rexhepi, Renewable energy integration and distributed generation in Kosovo: Challenges and solutions for enhanced energy quality, 2024, 12, 2333-8334, 686, 10.3934/energy.2024032
    3. Ali Raza, Marriam Liaqat, Muhammad Adnan, Muhammad Sajid Iqbal, Li Jingzhao, Ijaz Ahmad, SAARC super smart grid: Navigating the future - unleashing the power of an energy-efficient integration of renewable energy resources in the saarc region, 2024, 118, 00457906, 109405, 10.1016/j.compeleceng.2024.109405
    4. Aswani Kumar Eedara, Lakshmi Narasimha Sastry Varanasi, 2024, 9780323939416, 437, 10.1016/B978-0-323-93940-9.00256-5
    5. Anna Peecock, Jiangyi Huang, Alfonso Martinez-Felipe, Russell McKenna, Reviewing sector coupling in offshore energy system integration modelling: the North Sea context, 2025, 210, 13640321, 115220, 10.1016/j.rser.2024.115220
  • Reader Comments
  • © 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索
Electronic Research Archive
1 1.3

Metrics

Article views(1681) PDF downloads(105) Cited by(2)

Preview PDF
Download XML
Export Citation
Article outline
Abstract
   Background
   Methodology
   Results
   Discussion
   Conclusions
Acknowledgements
Conflict of interest
Appendix
References

Figures and Tables

Figures(6)  /  Tables(4)

Other Articles By Authors

Related pages

Tools

Copyright © AIMS Press

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog