FAST PEDESTRIAN DETECTION AND TRACKING BASED ON VIBE COMBINED HOG-SVM SCHEME

Taking into account the problem of low speed of pedestrian detection with a HOG-SVM detector, this paper proposes a modified algorithm according to the characteristic of the video surveillance. The first step is using the ViBe method to extract the foreground objects zone in the video. However, the shadows of objects can affect the efficiency of pedestrian detection, so this paper removes shadows for each frame before the ViBe method. Then, three steps, i.e., eroding and dilating, 4-neighborhood searching algorithm and border expanding, are performed to make further alterations to the extracted foreground. At the same time, the Histogram of Oriented Gradients (HOG) feature of the extracted zone is calculated and then sent into the Support Vector Machine (SVM) classifier to judge whether there are pedestrians or not. The last step is using a template matching technique to further track detected pedestrians. Experimental results indicate that the proposed method outperforms the traditional HOG+SVM and G-MM+HOG+SVM algorithms in terms of both recognition accuracy and processing speed.