A fast pedestrian detection via modified HOG feature

The Histogram of Oriented Gradient (HOG) feature for pedestrian detection has achieved good results, but it is time-consuming. For resolving this problem, a modified method for HOG is proposed to reduce the dimension of the features. On the base of analyzing the process of HOG, nine independent HOG channels (HOG-C) are extracted according to the gradient orientation interval. Through evaluating the effectiveness of HOG-C for pedestrian detection individually, a combination of HOG channels (CHOG-C) feature is presented based on statistical regularities. Comprehensive experiments on INRIA database demonstrated the promising performance of the CHOG-C feature, and the experimental results shown that the dimension is reduced meanwhile without losing the accuracy.

1 Introduction

Pedestrian detection[1]–[3] is a comprehensive technology associates with many fields such as artificial intelligence, pattern recognition and image processing, which can be applied to driver assistance system, video surveillance, intelligent transportation etc. However, pedestrian detection becomes a long-term difficulty in computer vision because of the influence of the variation in appearance, pose, shadows, and illumination.