Edge detection of remote sensing image based on Grünwald-Letnikov fractional difference and Otsu threshold

Chao Chen; Hua Kong; Bin Wu; Chao Chen; Hua Kong; Bin Wu

doi:10.3934/era.2023066

Electronic Research Archive

2023, Volume 31, Issue 3: 1287-1302. doi: 10.3934/era.2023066

Previous Article Next Article

Research article

Edge detection of remote sensing image based on Grünwald-Letnikov fractional difference and Otsu threshold

1.
Southwest University of Science and Technology, Sichuan Province, Mianyang 621010, China
2.
Key Laboratory of Numerical Simulation in Sichuan University, Neijiang 641100, China

Academic Editor: Alain Miranville

Received: 17 October 2022 Revised: 12 December 2022 Accepted: 19 December 2022 Published: 09 January 2023

With the development of remote sensing technology, the resolution of remote sensing images is improving, and the presentation of geomorphic information is becoming more and more abundant, the difficulty of identifying and extracting edge information is also increasing. This paper demonstrates an algorithm to detect the edges of remote sensing images based on Grünwald–Letnikov fractional difference and Otsu threshold. First, a convolution difference mask with two parameters in four directions is constructed by using the definition of the Grünwald–Letnikov fractional derivative. Then, the mask is convolved with the gray image of the remote sensing image, and the edge detection image is obtained by binarization with Otsu threshold. Finally, the influence of two parameters and threshold values on detection results is discussed. Compared with the results of other detectors on the NWPU VHR-10 dataset, it is found that the algorithm not only has good visual effect but also shows good performance in quantitative evaluation indicators (binary graph similarity and edge pixel ratio).
- fractional difference,
- Otsu threshold,
- edge detection,
- remote sensing image
Citation: Chao Chen, Hua Kong, Bin Wu. Edge detection of remote sensing image based on Grünwald-Letnikov fractional difference and Otsu threshold[J]. Electronic Research Archive, 2023, 31(3): 1287-1302. doi: 10.3934/era.2023066

Related Papers:

Abstract

With the development of remote sensing technology, the resolution of remote sensing images is improving, and the presentation of geomorphic information is becoming more and more abundant, the difficulty of identifying and extracting edge information is also increasing. This paper demonstrates an algorithm to detect the edges of remote sensing images based on Grünwald–Letnikov fractional difference and Otsu threshold. First, a convolution difference mask with two parameters in four directions is constructed by using the definition of the Grünwald–Letnikov fractional derivative. Then, the mask is convolved with the gray image of the remote sensing image, and the edge detection image is obtained by binarization with Otsu threshold. Finally, the influence of two parameters and threshold values on detection results is discussed. Compared with the results of other detectors on the NWPU VHR-10 dataset, it is found that the algorithm not only has good visual effect but also shows good performance in quantitative evaluation indicators (binary graph similarity and edge pixel ratio).

References

[1]	C. He, S. L. Li, D. H. Xiong, P. Z. Fang, M. S. Liao, Remote sensing image semantic segmentation based on edge information guidance, Remote Sens., 12 (2020). https://doi.org/10.3390/rs12091501 doi: 10.3390/rs12091501
[2]	Z. Z. Tu, Y. Ma, C. L. Li, J. Tang, B. Luo, Edge-guided non-local fully convolutional network for salient object detection, IEEE Trans. Circuits Syst. Video Technol., 31 (2021), 582–593. https://doi.org/10.1109/TCSVT.2020.2980853 doi: 10.1109/TCSVT.2020.2980853
[3]	H. L. Zhao, B. Wu, Y. B. Guo, G. Chen, D. Ye, SSWS: An edge detection algorithm with strong semantics and high detectability for spacecraft, Optik, 247 (2021). https://doi.org/10.1016/j.ijleo.2021.168037 doi: 10.1016/j.ijleo.2021.168037
[4]	C. Xu, H. Liu, W. M. Cao, J. Q. Feng, Multispectral image edge detection via Clifford gradient, Sci. China-Inf. Sci., 55 (2012), 260–269. https://doi.org/10.1007/s11432-011-4540-0 doi: 10.1007/s11432-011-4540-0
[5]	S. Amstutz, J. Fehrenbach, Edge detection using topological gradients: A scale-space approach, J. Math. Imaging Vision, 52 (2015), 249–266. https://doi.org/10.1007/s10851-015-0558-z doi: 10.1007/s10851-015-0558-z
[6]	J. T. Tang, Q. B. Shi, S. G. Hu, Z. Y. Ren, Edge detection based on curvature of gravity gradient tensor, Chin. J. Geophys. Chin. Edit., 62 (2019), 1872–1884. https://doi.org/10.6038/cjg2019M0427 doi: 10.6038/cjg2019M0427
[7]	V. B. S. Prasath, D. N. H. Thanh, N. Q. Hung, L. M. Hieu, Multiscale gradient maps augmented fisher information-based image edge detection, IEEE Access, 8 (2020), 141104–141110. https://doi.org/10.1109/ACCESS.2020.3013888 doi: 10.1109/ACCESS.2020.3013888
[8]	H. H. Zhao, P. F. Xiao, X. Z. Feng, Optimal Gabor filter-based edge detection of high spatial resolution remotely sensed images, J. Appl. Remote Sens., 11 (2017). https://doi.org/10.1117/1.JRS.11.015019 doi: 10.1117/1.JRS.11.015019
[9]	W. C. Lin, J. W. Wang, Edge detection in medical images with quasi high-pass filter based on local statistics, Biomed. Signal Process. Control, 39 (2018), 294–302. https://doi.org/10.1016/j.bspc.2017.08.011 doi: 10.1016/j.bspc.2017.08.011
[10]	G. B. Chen, Z. W. Sun, Z. Li, Road identification algorithm for remote sensing images based on wavelet transform and recursive operator, IEEE Access, 8 (2020), 141824–141837. https://doi.org/10.1109/ACCESS.2020.3012997 doi: 10.1109/ACCESS.2020.3012997
[11]	A. Isar, C. Nafornita, G. Magu, Hyperanalytic wavelet-based robust edge detection, Remote Sens., 13 (2021), 141104–141110. https://doi.org/10.3390/rs13152888 doi: 10.3390/rs13152888
[12]	M. Han, X. Yang, E. Jiang, An extreme learning machine based on cellular automata of edge detection for remote sensing images, IEEE Access, 19 (2015), 27–34. https://doi.org/10.1016/j.neucom.2015.08.121 doi: 10.1016/j.neucom.2015.08.121
[13]	L. Huang, X. Q. Yu, X. Q. Zuo, Edge detection in UAV remote sensing images using the method integrating zernike moments with clustering algorithms, Int. J. Aerosp. Eng., 2017 (2017), 141104–141110. https://doi.org/10.1109/ACCESS.2020.3013888 doi: 10.1109/ACCESS.2020.3013888
[14]	Z. Qu, S. Y. Wang, L. Liu, D. Y. Zhou, Visual cross-image fusion using deep neural networks for image edge detection, IEEE Access, 7 (2019), 57604–57615. https://doi.org/10.1109/ACCESS.2019.2914151 doi: 10.1109/ACCESS.2019.2914151
[15]	X. G. Zheng, GPNRBNN: A robot image edge detection method based on gaussian positive-negative radial basis neural network, Sens. Imaging, 22 (2021). https://doi.org/10.1007/s11220-021-00351-5 doi: 10.1007/s11220-021-00351-5
[16]	G. B. Chen, Z. Y. Jiang, M. M. Kamruzzaman, Radar remote sensing image retrieval algorithm based on iImproved sobel operator, J. Visual Commun. Image Represent., 8 (2019), https://doi.org/10.1016/j.jvcir.2019.102720 doi: 10.1016/j.jvcir.2019.102720
[17]	M. Mohammadpour, A. Bahroudi, M. Abedi, Automatic lineament extraction method in mineral exploration using CANNY algorithm and hough transform, IEEE Access, 54 (2020), 366–382. https://doi.org/10.1134/S0016852120030085 doi: 10.1134/S0016852120030085
[18]	H. Q. Wu, J. Yan, The mechanism of digitized landscape architecture design under edge computing, Plos One, 16 (2021), 141104–141110. https://doi.org/10.1371/journal.pone.0252087 doi: 10.1371/journal.pone.0252087
[19]	G. Wang, C. Lopez-Molina, B. D. Baets, Automated blob detection using iterative Laplacian of Gaussian filtering and unilateral second-order Gaussian kernels, Digital Signal Process., 96 (2019). https://doi.org/10.1016/j.dsp.2019.102592 doi: 10.1016/j.dsp.2019.102592
[20]	R. Chetia, S. M. B. Boruah, P. P. Sahu, Quantum image edge detection using improved Sobel mask based on NEQR, Quantum Inf. Process., 20 (2021). https://doi.org/10.1007/s11128-020-02944-7 doi: 10.1007/s11128-020-02944-7
[21]	A. Jan, S. A. Parah, B. A. Malik, M. Rashid, Secure data transmission in IoTs based on CLoG edge detection, Future Generat. Comput. Syst. Int. J. Esci., 121 (2021), 59–73. https://doi.org/10.1016/j.future.2021.03.005 doi: 10.1016/j.future.2021.03.005
[22]	P. Amoako-Yirenkyi, J. K. Appati, I. K. Dontwi, A new construction of a fractional derivative mask for image edge analysis based on Riemann-Liouville fractional derivative, Adv. Differ. Equations, 2016 (2016). https://doi.org/10.1186/s13662-016-0946-8 doi: 10.1186/s13662-016-0946-8
[23]	Y. F. Pu, P. Siarry, A. Chatterjee, Z. N. Wang, Z. Yi, Y. G. Liu, et al., A fractional-order variational framework for retinex: fractional-order partial differential equation-based formulation for multi-scale nonlocal contrast enhancement with texture preserving, IEEE Trans. Image Process., 27 (2018), 1214–1229. https://doi.org/10.1109/TIP.2017.2779601 doi: 10.1109/TIP.2017.2779601
[24]	K. Liu, Y. Z. Tian, Research and analysis of deep learning image enhancement algorithm based on fractional differential, Chaos, Solitons Fractals, 131 (2020), 14–110. https://doi.org/10.1016/j.chaos.2019.109507 doi: 10.1016/j.chaos.2019.109507
[25]	Q. T. Ma, F. F. Dong, D. X. Kong, A fractional differential fidelity-based PDE model for image denoising, IEEE Access, 28 (2017), 635–647. https://doi.org/10.1007/s00138-017-0857-z doi: 10.1007/s00138-017-0857-z
[26]	Q. Wang, J. Ma, S. Y. Yu, L. Y. Tan, Noise detection and image denoising based on fractional calculus, Chaos, Solitons Fractals, 131 (2020), 109463. https://doi.org/10.1016/j.chaos.2019.109463 doi: 10.1016/j.chaos.2019.109463
[27]	Y. S. Zhang, F. Zhang, B. Z. Li, Image restoration method based on fractional variable order differential, IEEE Access, 29 (2018), 999–1024. https://doi.org/10.1007/s11045-017-0482-z doi: 10.1007/s11045-017-0482-z
[28]	F. F. Dong, Q. T. Ma, Single image blind deblurring based on the fractional-order differential, IEEE Access, 78 (2019), 1960–1977. https://doi.org/10.1016/j.camwa.2019.03.033 doi: 10.1016/j.camwa.2019.03.033
[29]	Y. S. Zhang, Y. R. Tian, A new active contour medical image segmentation method based on fractional varying-order differential, Mathematics, 10 (2022), https://doi.org/10.3390/math10020206 doi: 10.3390/math10020206
[30]	J. E. Lavín-Delgado, J. E. Solís-Pérez, J. F. Gómez–Aguilar, R. F. Escobar–Jiménez, A new fractional–order mask for image edge detection based on Caputo-Fabrizio fractional-order derivative without singular kernel, Circuits, Syst. Signal Process., 39 (2020), 1419–1448. https://doi.org/10.1007/s00034-019-01200-3 doi: 10.1007/s00034-019-01200-3
[31]	A. Nandal, H. Gamboa-Rosales, A. Dhaka, J. M. Celaya-Padilla, Image edge detection using fractional calculus with feature and contrast enhancement, Circuits Syst. Signal Process., 37 (2018), 3946–3972. https://doi.org/10.1109/ACCESS.2020.3013888 doi: 10.1109/ACCESS.2020.3013888
[32]	M. Hacini, F. Hachouf, A. Charef, A bi-directional fractional-order derivative mask for image processing applications, IET Image Process., 14 (2020), 2512–2524. https://doi.org/10.1049/iet-ipr.2019.0467 doi: 10.1049/iet-ipr.2019.0467
[33]	S. K. Mishra, K. K. Singh, R. Dixit, M. K. Bajpai, Design of fractional calculus based differentiator for edge detection in color images, IEEE Access, 80 (2021), 29965–29983. https://doi.org/10.1007/s11042-021-11187-2 doi: 10.1007/s11042-021-11187-2
[34]	N. R. Babu, K. Sanjay, P. Balasubramaniam, EED: Enhanced edge detection algorithm via generalized integer and fractional-order operators, Circuits, Syst. Signal Process., 41 (2022), 5492–5534. https://doi.org/10.1007/s00034-022-02028-0 doi: 10.1007/s00034-022-02028-0
[35]	C. P. Li, D. L. Qian, Y. Q. Chen, On Riemann–Liouville and caputo derivatives, Discrete Dyn. Nat. Soc., 2011 (2011), 1–15. https://doi.org/10.1155/2011/562494 doi: 10.1155/2011/562494
[36]	G. Y. Zhang, J. P. Liu, J. Wang, Z. H. Tang, Y. F. Xie, FoGDbED: Fractional-order Gaussian derivatives-based edge-relevant structure detection using Caputo-Fabrizio definition, Digital Signal Process., 98 (2019). https://doi.org/10.1016/j.dsp.2019.102639 doi: 10.1016/j.dsp.2019.102639
[37]	N. Aboutabit, A new construction of an image edge detection mask based on Caputo–Fabrizio fractional derivative, Vis. Comput., 37 (2020), 1545–1557. https://doi.org/s00371-020-01896-4
[38]	D. G. Shao, T. Zhou, F. Liu, S. L. Yi, Y. Xiang, L. Ma, et al., Ultrasound speckle reduction based on fractional order differentiation, J. Med. Ultrason., 44 (2016), 227–237. https://doi.org/10.1007/s10396-016-0763-4 doi: 10.1007/s10396-016-0763-4
[39]	S. Balochian, H. Baloochian, Edge detection on noisy images using Prewitt operator and fractional order differentiation, Multimedia Tools Appl., 81 (2022), 9759–9770. https://doi.org/10.1007/s11042-022-12011-1 doi: 10.1007/s11042-022-12011-1
[40]	G. Cheng, J. W. Han, P. C. Zhou, G. Lei, Multi-class geospatial object detection and geographic image classification based on collection of part detectors, ISPRS J. Photogramm. Remote Sens., 98 (2014), 119–132. https://doi.org/10.1016/j.isprsjprs.2014.10.002 doi: 10.1016/j.isprsjprs.2014.10.002
[41]	F. M. Atici, S. Chang, J. Jonnalagadda, Grünwald-Letnikov fractional operators: From past to present, Fract. Differ. Calculus, 11 (2021), 147–159. https://doi.org/10.7153/fdc-2021-11-10 doi: 10.7153/fdc-2021-11-10
[42]	Y. L. Song, J. F. Qu, C. M. Liu, Real-time registration of remote sensing images with a Markov chain model, J. Real-Time Image Process., 18 (2020), 1527–1540. https://doi.org/10.1007/s11554-020-01043-1 doi: 10.1007/s11554-020-01043-1
[43]	X. Lu, Y. J. Zhang, Human body flexibility fitness test based on image edge detection and feature point extraction, IEEE Access, 24 (2020), 8673–8683. https://doi.org/10.1007/s00500-020-04869-w doi: 10.1007/s00500-020-04869-w
[44]	S. Roy, D. Das, S. Lal, J. Kini, Novel edge detection method for nuclei segmentation of liver cancer histopathology images, J. Ambient Intell. Hum. Comput., 2021 (2021). https://doi.org/10.1007/s12652-021-03308-4 doi: 10.1007/s12652-021-03308-4
[45]	N. Tariq, R. A. Hamzah, T. F. Ng, S. L. Wang, H. Ibrahim, Quality assessment methods to evaluate the performance of edge dtection algorithms for digital image: A systematic literature review, IEEE Access, 9 (2021). 87763–87776. https://doi.org/10.1109/ACCESS.2021.3089210 doi: 10.1109/ACCESS.2021.3089210
[46]	Y. Han, M. Yin, P. H. Duan, P. Ghamisi, Edge-preserving filtering-based dehazing for remote sensing images, IEEE Geosci. Remote Sens. Lett., 2021 (2021). https://doi.org/10.1109/LGRS.2021.3103381 doi: 10.1109/LGRS.2021.3103381
[47]	D. D. He, G. Wang, An algorithm of fuzzy edge detection for wetland remote sensing image based on fuzzy theory, Appl. Nanosci., 2022 (2022). https://doi.org/10.1007/s13204-021-02209-4 doi: 10.1007/s13204-021-02209-4

Reader Comments

Your name:*

Email:*
© 2023 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)