Pedestrian detection using improved Histogram of Oriented Gradients

Histogram of Oriented Gradients (HOG) has been proved to be an effective way of solving pedestrian detection in real scenes, but great computation amount makes it far from practical application. So we propose a new detection system based on improved HOG features with faster detecting speed. While calculating HOG, the pixels irrelevant to object contour shape are neglected. Then we decrease dimension number of the feature vector by 80%, making the SVM classification model much more simplified. Although the accuracy only drops down no more than 5%, our improved method performs over 5 times faster than the previous one. After entirely scanning a image, we use mean shift clustering algorithm to merge multiple positive responses belonging to same one positive case. Experiments show our method’s performance on both test dataset and in real scene images.