How to Improve the Quality of Pedestrian Detection Using the Priori Knowledge

Using the privileged information classification to solve the challenge between the speed and the quality in pedestrian detection is a new direction of research in the compute vision smca. In this paper, we apply Histogram Intersection Kernel (HIK) into Learning model Using Privileged Information (LUPI)to improve the quality of pedestrian detection problem. All experimental results show the robustness and effectiveness of the proposed method. Under the help of the privileged information and histogram intersection kernel together, the accuracy of the pedestrian detection can obtain a significant improvement.