Learning proposal for front-vehicle detection
Jie Tang, Jian Li, Xiangjing An · 2015
It has been proven that a small set of generated candidate windows can speed up the classical sliding windows object detection. To prevent rear-end collisions and accidents, we provide a novel approach to get front-vehicle proposal for vehicle detection. Observing that on road the front vehicle has obvious edges, the proposed method stands on precise edge features detected by Structured Edge detector. With the help of integral image, we can find the proposals quickly, and linear SVM is adopted to rank the proposals. Using Non-Maximal Suppression(NMS), we can balance the numbers of the proposals and the precision. In particular, given less than several hundreds proposals per image, our method can achieve over 93.3% recall at an overlap threshold of 0.7 per image within 1 second which is really challenging.