Journal of System Simulation
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.
Recommended Citation
Huang, Jingzhou; Zhou, Houpan; Wang, Liliang; Huang, Xiaofang; and Na, Li
(2019)
"Stereo Matching Based on Enhanced Message Passing for Investigation of Traffic Accident Scenes,"
Journal of System Simulation: Vol. 31:
Iss.
3, Article 6.
DOI: 10.16182/j.issn1004731x.joss.17WJP-007
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol31/iss3/6
First Page
413
DOI Link
https://doi.org/10.16182/j.issn1004731x.joss.17WJP-007
Last Page
421
CLC
TP391.9
Recommended Citation
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.
DOI
10.16182/j.issn1004731x.joss.17WJP-007
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons