Combining background subtraction and temporal persistency in pedestrian detection from static videos

This paper presents a method that incorporates background subtraction and temporal persistency with the HOG pedestrian detector to detect pedestrians from videos captured by a fixed camera. We use a codebook based method and interpolation to extract a series of foreground sub-images for the HOG detector. This allows the detector to focus on pedestrian detection on smaller image regions and thereby reduce its computational cost and lower its false positive error rate. We employ a temporal persistency constraint to overcome problems that may arise from background subtraction. Compared to other state-of-art techniques, the performance of our method is pleasantly promising.