Haar-Like Multi-Granularity Texture Features for Pedestrian Detection

Abstract

Pedestrian detection has been a significant problem for decades and remains a hot topic in computer vision. Pedestrian detection is one of the key algorithms for self-driving cars and some other functions in robotics, including driver support systems, road surveillance systems. In this paper, based on the characteristics of the human body and the Haar feature, the Haar-like multi-granularity local texture feature, i.e., multi-granularity Haar-like LBP (mgh-LBP), is proposed for pedestrian detection. The mgh-LBP feature combines four characteristics of the human body and their backgrounds to construct the Haar-like features, which can better describe human body texture and edge information. Compared with other texture features, including the rotation-invariant LBP feature, uniform LBP feature and basic-LBP feature, the proposed method greatly reduces the feature dimension and computational complexity, and obtains a higher pedestrian detection rate and robust detection performance.