Pedestrian Collision Warning of Advanced Driver Assistance Systems
Ying‐Che Kuo, Ci-Ming Fu, Cheng‐Tao Tsai, Chun‐Cheng Lin, Ghih-Hao Chang · 2016
Pedestrian collision warning system is one of the major functions of Advanced Driver Assistance Systems. The proposal uses single camera and a cascade detection algorithm to develop the pedestrian collision warning system. Harris corner detection algorithm is applied for getting the features of pedestrian's contour. The modified Lucas-Kanade optical flow algorithm is used to estimate motion vector of pedestrian. Grey theory is used to predict the future driving path of vehicle. And the proposed collision warning system is based on the motion vector of pedestrian and the future driving path of vehicle.