Fast Pedestrian Detection with Multi-scale Classifiers
Baoyin Yu, Yingdong Ma, Jun Li · 2017
Computing image feature pyramid has been a common approach in pedestrian detection for improving detection accuracy. However, building feature pyramid is a time consuming task. In this paper we propose a new multi-scale classifier based method. We approximate the nearby scale classifier instead of extracting features multiple times form the resizing images. These approximated classifiers can be applied to achieve object detection without image resizing. In addition, we introduce a new feature, BPG (Binary Pattern of Gradient), to further accelerate the feature extraction speed. The experimental result demonstrates that the new feature is efficient in pedestrian detection. It is also proved that the proposed method not only reduces the detection speed, but also has performance comparable to some state-of-the-art pedestrian detection approaches.