For common binocular stereo matching algorithms in computer vision, it is not easy to obtain high precision and high matching speed at the same time. In this paper, an improved binocular stereo matching algorithm based on Minimum Spanning Tree (MST) cost aggregation is proposed. Firstly, the performance of the parallel algorithm can be improved by reducing the height of the tree. Then, an improved Root to Leaf (L2R) cost aggregation algorithm is proposed. By combining stereo matching technology with parallel computing technology, the above method can realize synchronous parallel computing at the algorithm level. Experimental results show that the improved algorithm has high accuracy and high matching speed for binocular stereo vision.
Citation: Jian Zhang, Yan Zhang, Cong Wang, Huilong Yu, Cui Qin. Binocular stereo matching algorithm based on MST cost aggregation[J]. Mathematical Biosciences and Engineering, 2021, 18(4): 3215-3226. doi: 10.3934/mbe.2021160
For common binocular stereo matching algorithms in computer vision, it is not easy to obtain high precision and high matching speed at the same time. In this paper, an improved binocular stereo matching algorithm based on Minimum Spanning Tree (MST) cost aggregation is proposed. Firstly, the performance of the parallel algorithm can be improved by reducing the height of the tree. Then, an improved Root to Leaf (L2R) cost aggregation algorithm is proposed. By combining stereo matching technology with parallel computing technology, the above method can realize synchronous parallel computing at the algorithm level. Experimental results show that the improved algorithm has high accuracy and high matching speed for binocular stereo vision.
| [1] | G. Yang, X. Song, C. Huang, Driving stereo: A large-scale dataset for stereo matching in autonomous driving scenarios, IEEE CVF Conference on Computer Vision and Pattern Recognition, 2020,899-908. |
| [2] | A. Z. Joseph, C. L. Priyankac, P. Sankaran, Stereo vision-based speed estimation for autonomous driving, 2019 International Conference on Information Technology, Bhubaneswar, India, 6 (2019), 201-205. |
| [3] |
M. Cheng, Y. Zhang, Y. Su, J. M. Alvarez, H. Kong, Curb detection for road and sidewalk detection, IEEE Trans. Veh. Technol., 67 (2018), 10330-10342. doi: 10.1109/TVT.2018.2865836
|
| [4] | M. Faria, A. Ferreira, H. Pérez-Leon, I. Maza, A. Viguria, Autonomous 3D exploration of large structures using an UAV equipped with a 2D LIDAR, Sensors, 22 (2019), 4849-4852. |
| [5] | R. Wang, M. Z. Luo, N. K. Wang, L. J. Lu, Accuracy study of a binocular-stereo-vision-based navigation robot for minimally invasive interventional procedures, World J. Clin. Cases, 8 (2020), 69-78. |
| [6] | C. Yan, H. He, Y. Qiao, Measuring the wave height based on binocular cameras, Sensors, 19 (2019), 1338-1342. |
| [7] | M. G. Mozerov, V. Joost, One-view occlusion detection for stereo matching with a fully connected CRF model, IEEE T. Image Process., 6 (2019), 1-2. |
| [8] |
C. Zhang, C. He, Z. Chen, W. Liu, M. Li, J. Wu, Edge-preserving stereo matching using minimum spanning tree, IEEE Access, 7 (2019), 177909-177921. doi: 10.1109/ACCESS.2019.2958527
|
| [9] | S. Dutta, D. Patra, H. Shankar, P. A. Verma, Development of GIS tool for the solution of minimum spanning tree problem using prim's algorithm, ISPRS Technical Commission 8th Mid-Term Symposium, 8 (2014), 1105-1114. |
| [10] |
H. Guo, L. Huang, Y. Lu, J. Ma, C. Qian, Z. Wang, Accelerating BFS via data structure-aware prefetching on GPU, IEEE Access, 6 (2018), 60234-60248. doi: 10.1109/ACCESS.2018.2876201
|
Figures(7) / Tables(9)
Jian Zhang, Yan Zhang, Cong Wang, Huilong Yu, Cui Qin. Binocular stereo matching algorithm based on MST cost aggregation[J]. Mathematical Biosciences and Engineering, 2021, 18(4): 3215-3226. doi: 10.3934/mbe.2021160
DownLoad: