Pedestrian detection using shape context and PHOG

Abstract

This paper describes a new method for pedestrian detection. The focus of the proposed method is to enhance the number of detected pedestrian and to achieve high accuracy with low rates of false negative detection. The method has two stages: the first stage detects pedestrians using part based detector (poselet) while the second stage further detects people by combine top-down recognition with bottom-up image segmentation. For feature extraction, Pyramid Histogram of Orientation Gradient (PHOG) and Shape Context (SC) are used. The proposed method was tested on a popular pedestrian detection benchmark dataset “INRIA person data set” and experimental results show that the detection method achieves high accuracy with low rates of false negative detection.