Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Road environment recognition method in complex traffic situations based on stereo vision
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 %.
Road environment recognition method in complex traffic situations based on stereo vision
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 %.
Road environment recognition method in complex traffic situations based on stereo vision
Yu-Sung Chen, (Autor:in) / An-Chih Tsai, (Autor:in) / Ta-Te Lin, (Autor:in)
01.11.2012
853233 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Stereo vision-based road conditioning monitoring
| TIBKAT | 2021
Road traffic sign recognition system based on machine vision
| Europäisches Patentamt | 2021