Road Environment Recognition Method in Complex Traffic Situations Based on Stereo Vision

被引:0
|
作者
Chen, Yu-Sung [1 ]
Tsai, An-Chih [2 ]
Lin, Ta-Te [2 ]
机构
[1] Automot Res & Testing Ctr, R&D Div, Changhua, Taiwan
[2] Natl Taiwan Univ, Dept Bio Ind Mech Engn, Taipei, Taiwan
关键词
stereo vision; obstacle detection; obstacle recognition;
D O I
暂无
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
This paper presents a method of the road environment recognition in complex traffic situations by stereo vision system composed of dual cameras. Binocular cameras are mounted on a specially designed mechanism to satisfy the geometric restrictions of the ideal stereo vision system. With the current design and when the distortion of images due to camera lens is corrected by calibration, the disparity image can be estimated by the Semi-Global Blocking Matching method (SGBM). Then the information was used to compute occupancy grid. The obstacle detection was employed in the occupancy grid, and the accuracy of obstacle detection is above 90%. Moreover, two obstacle features were proposed and combining 3D feature constraint Principal Component Analysis (PCA) and Support Vector Machine (SVM) to achieve obstacle recognition. With the real-world environment testing the accuracy of obstacle recognition is above 90%.
引用
收藏
页码:174 / 178
页数:5
相关论文
共 50 条
  • [1] Recognition Method for Complex Environment of Autopilot Vehicle Based on Monocular Vision
    Chen, Wanru
    Fan, Jingjing
    Liu, Yingzhe
    Guo, Jianying
    [J]. CICTP 2020: TRANSPORTATION EVOLUTION IMPACTING FUTURE MOBILITY, 2020, : 620 - 626
  • [2] Generic object recognition method based on stereo vision
    Li, Xinde
    Zhang, Xiao
    Zhu, Bo
    [J]. Dongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Southeast University (Natural Science Edition), 2013, 43 (04): : 711 - 716
  • [3] Early warning and monitoring method of road environment and traffic safety situation based on machine vision
    Zheng, W.
    Nie, Y.
    [J]. Advances in Transportation Studies, 2021, 2021 (Special Issue 3): : 147 - 157
  • [4] An underwater organisms recognition method based on machine vision in complex marine environment
    Meng, Huijuan
    Yang, Qing
    Zhou, Jili
    Gao, Dexin
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (13) : 38551 - 38565
  • [5] An underwater organisms recognition method based on machine vision in complex marine environment
    Huijuan Meng
    Qing Yang
    Jili Zhou
    Dexin Gao
    [J]. Multimedia Tools and Applications, 2024, 83 : 38551 - 38565
  • [6] STEREO VISION METHOD APPLICATION TO ROAD INSPECTION
    Staniek, Marcin
    [J]. BALTIC JOURNAL OF ROAD AND BRIDGE ENGINEERING, 2017, 12 (01): : 38 - 47
  • [7] A Method for Broccoli Seedling Recognition in Natural Environment Based on Binocular Stereo Vision and Gaussian Mixture Model
    Ge, Luzhen
    Yang, Zhilun
    Sun, Zhe
    Zhang, Gan
    Zhang, Ming
    Zhang, Kaifei
    Zhang, Chunlong
    Tan, Yuzhi
    Li, Wei
    [J]. SENSORS, 2019, 19 (05)
  • [8] Three Ways of using Stereo Vision for Traffic Light Recognition
    Fregin, Andreas
    Mueller, Julian
    Dietmayer, Klaus
    [J]. 2017 28TH IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV 2017), 2017, : 430 - 436
  • [9] Stereo Vision Based Road Surface Preview
    Shen, Truman
    Schamp, Gregory
    Haddad, Mario
    [J]. 2014 IEEE 17TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2014, : 1843 - 1849
  • [10] Stereo Vision based Traffic Analysis System
    Surgailis, T.
    Valinevicius, A.
    Eidukas, D.
    [J]. ELEKTRONIKA IR ELEKTROTECHNIKA, 2011, (01) : 15 - 18