Stereo Matching Based on Enhanced Message Passing for Investigation of Traffic Accident Scenes

doi:10.16182/j.issn1004731x.joss.17WJP-007

Abstract

Abstract: The investigation of traffic accident scenes requires restoring real scenes in a given time, and it can be implemented through binocular vision technique. For its core procedure—stereo matching, we studied the popular hierarchical belief propagation (HBP) algorithm and presented an improved approach which contained two modules: optimization in the native level and cost transmission between adjacent levels. The optimization ability is improved by enhancing the impact of message passing within and between levels for estimating disparities of unmatched points and correcting wrong disparities. Experiment results show that the optimization ability of the improved approach has been enhanced, and it provides a reference for applications of establishing more accurate and complete 3D models such as the investigation of traffic accident scenes.

Key words: stereo matching, disparity space image, hierarchical belief propagation, enhanced message passing, investigation of traffic accident scenes

CLC Number:

TP391.9

Huang Jingzhou, Zhou Houpan, Wang Liliang, Huang Xiaofang, Li Na. Stereo Matching Based on Enhanced Message Passing for Investigation of Traffic Accident Scenes[J]. Journal of System Simulation, 2019, 31(3): 413-421.

References

[1] 刘昱岗, 王卓君, 王福景, 等. 基于双目立体视觉的倒车环境障碍物测量方法[J]. 交通运输系统工程与信息, 2016, 16(4): 79-87.
Liu Yu-gang, Wang Zhuo-jun, Wang Fu-jing, et al.Vehicle Reversing Obstacle Measurement Based on Binocular-camera Stereo Vision[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(4): 79-87.
[2] 刘文超, 胡孟夏, 王岩, 等. 基于双目立体视觉的车载式交通事故现场快速勘查系统[J]. 汽车安全与节能学报, 2012, 3(3): 239-244.
Liu Wen-chao, Hu Meng-xia, Wang Yan, et al.Quick Investigation System in Vehicle Based on Binocular Vision for Traffic Accident Scenes[J]. Journal Of Automotive Safety and Energy, 2012, 3(3): 239-244.
[3] 刘文超, 王岩, 胡孟夏, 等. 一种新型的便携式交通事故现场快速勘查系统[J]. 测绘通报, 2014,7: 117-120.
Liu Wen-chao, Wang Yan, Hu Meng-xia, et al.A New Type of Portable Investigation System in Traffic Accident Scenes[J]. Bulletin of Surveying and Mapping, 2014, 7: 117-120.
[4] Jian Sun, Nan-Ning Zheng, Heung-Yeung Shum.Stereo Matching Using Belief Propagation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2003, 25(7): 787-800.
[5] Olga Veksler.Graph Cut Based Optimization for MRFs with Truncated Convex Priors[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (S1063-6919). New York: IEEE, 2007:2142-2149.
[6] Tatsunori Taniai, Yasuyuki Matsushita, Takeshi Naemura.Graph Cut Based Continuous Stereo Matching Using Locally Shared Labels[C]// Lisa O’Conner. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH: IEEE, 2014: 1613-1620.
[7] Jian Sun, Nan-Ning Zheng, Heung-Yeung Shum.Stereo Matching Using Belief Propagation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2003, 25(7): 787-800.
[8] Pedro F Felzenszwalb, Daniel P Huttenlocher.Efficient Belief Propagation for Early Vision[J]. International Journal of Computer Vision (S0920-5691), 2006, 70(1): 41-54.
[9] Tianli Yu, Ruei-Sung Lin, Bei Tang, et al.Efficient Message Representations for Belief Propagation[C]// Proceedings of IEEE International Conference on Computer Vision. Rio de Janeiro: IEEE, 2007: 1-8.
[10] Qingxiong Yang, Liang Wang, Narendra Ahuja.A Constant-Space Belief Propagation Algorithm for Stereo Matching[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010: 1458-1465.
[11] Chia-Kai Liang, Chao-Chung Cheng, Yen-Chieh Lai, et al.Hardware-Efficient Belief Propagation[J]. IEEE Transactions on Circuits and Systems for Video Technology (S1051-8215), 2011, 21(5): 525-537.
[12] 张丽红,何树成. 基于差值绝对值之和和置信传播的快速收敛立体匹配算法[J]. 计算机应用, 2014, 34(3): 824-827.
Zhang Li-hong, He Shu-cheng.Fast Convergent Stereo Matching Algorithm Based on Sum of Absolute Difference and Belief Propagation[J]. Journal of Computer Applications, 2014, 34(3): 824-827.
[13] 张红颖,刘奕萱,杨宇. 快速收敛的置信度传播立体匹配算法[J]. 计算机应用, 2013, 33(2): 484-486.
Zhang Hong-ying, Liu Yi-xuan, Yang Yu.Stereo Matching Algorithm Based on Fast-Converging Belief Propagation[J]. Journal of Computer Applications, 2013, 33(2): 484-486.
[14] 何凯,穆星,邹刚. 基于图像分割的三维立体匹配改进算法[J]. 吉林大学学报:工学版, 2014, 44(1): 219-224.
He Kai, Mu Xing, Zou Gang.Improved Segment-Based 3D Surface Stereo Matching Algorithm[J]. Journal of Jilin University Engineering and Technology Edition, 2014, 44(1): 219-224.
[15] Bok-Suk Shin, Diego Caudillo, Reinhard Klette.Evaluation of Two Stereo Matchers on Long Real-World Video Sequences[J]. Pattern Recognition (S0031-3203), 2015, 48(4): 1113-1124.
[16] Menglong Yang, Yiguang Liu, Zhisheng You, et al.A Homography Transform Based Higher-Order MRF Model for Stereo Matching[J]. Pattern Recognition Letters (S0167-8655), 2014, 40: 66-71.
[17] Stefano Mattoccia.Stereo Vision: Algorithms and Applications[R]. University of Bologna: Department of Computer Science and Engineering (DISI), 2013.
[18] Qingxiong Yang, Liang Wang, Ruigang Yang, et al.Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation, and Occlusion Handling[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2009, 31(3): 492-504.
[19] Dorin Comaniciu, Peter Meer.Mean Shift: A Robust Approach toward Feature Space Analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2002, 24(5): 603-619.
[20] Jingzhou Huang.Stereo Matching Based on Segmented B-Spline Surface Fitting and Accelerated Region Belief Propagation[J]. IET Computer Vision (S1751-9632), 2015, 9(4): 456-466.
[21] Kuk-Jin Yoon, In So Kweon.Adaptive Support-Weight Approach for Correspondence Search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2006, 28(4): 650-656.