Vehicle detection and tracking for gas station surveillance based on AdaBoosting and optical flow

To solve the problem of low efficiency caused by the heavy traffic in the gas station at the peak time, a method for real-time vehicle detection and tracking using Adaboosting classifier and optical flow tracking is proposed in this paper. The Adaboosting algorithm is used to train the classifier with Haar-like feature extracted from positive samples and negative samples of the gas station vehicles. Optical flow tracking method is used to extract the corner points of the vehicle areas and match the positions of these corners in the consecutive frames to realize the vehicle tracking. Experimental results show that the proposed method has a good performance in real-time detecting and tracking for the vehicles in the gas station.