TY - GEN
T1 - A monovision-based 3D pose estimation system for vehicle behavior prediction
AU - Wang, Weinong
AU - Wang, Fei
AU - Liu, Pengyu
AU - He, Yicong
AU - Zhang, Xuetao
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/8/19
Y1 - 2016/8/19
N2 - Collision accidents have become a crucial and urgent problem. Advanced Driver Assistance Systems (ADAS) can enhance traffic safety and improve efficiency. Toward this direction, we propose a robust low-cost system based on monovision to estimate the accurate 3D pose information of the target vehicles for further behavior prediction. Firstly, we combine the Haar features with AdaBoost classification for vehicle detection, and then use the Hypothesis Verification to remove the false detection; Then, the system keeps tracking and locates the license plate(LP); Finally, the typical PnP problem is applied to estimate the 3D pose infor-mation including the rotation matrix and translation matrix rela-tive to the target vehicles. Compared to stereovision systems, the monovision-based system significantly reduces the computational cost and has a lower requirement for equipment. Moreover, it can work on slope road and is easily applied to different countries due to the standardized LP in each country. The experiments in the real-world have been tested, showing excellent performance in vehicle detection, LP location and 3D pose estimation.
AB - Collision accidents have become a crucial and urgent problem. Advanced Driver Assistance Systems (ADAS) can enhance traffic safety and improve efficiency. Toward this direction, we propose a robust low-cost system based on monovision to estimate the accurate 3D pose information of the target vehicles for further behavior prediction. Firstly, we combine the Haar features with AdaBoost classification for vehicle detection, and then use the Hypothesis Verification to remove the false detection; Then, the system keeps tracking and locates the license plate(LP); Finally, the typical PnP problem is applied to estimate the 3D pose infor-mation including the rotation matrix and translation matrix rela-tive to the target vehicles. Compared to stereovision systems, the monovision-based system significantly reduces the computational cost and has a lower requirement for equipment. Moreover, it can work on slope road and is easily applied to different countries due to the standardized LP in each country. The experiments in the real-world have been tested, showing excellent performance in vehicle detection, LP location and 3D pose estimation.
KW - 3D pose information
KW - ADAS
KW - PnP
KW - monovision
KW - vehicle detection
UR - https://www.scopus.com/pages/publications/84988443652
U2 - 10.1109/ICVES.2016.7548177
DO - 10.1109/ICVES.2016.7548177
M3 - 会议稿件
AN - SCOPUS:84988443652
T3 - Proceedings - 2016 IEEE International Conference on Vehicular Electronics and Safety, ICVES 2016
SP - 95
EP - 100
BT - Proceedings - 2016 IEEE International Conference on Vehicular Electronics and Safety, ICVES 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE International Conference on Vehicular Electronics and Safety, ICVES 2016
Y2 - 10 July 2016 through 12 July 2016
ER -