Hybrid Channel Based Pedestrian Detection

TL;DR

This paper introduces a pedestrian detection framework that combines handcrafted features with CNN features, leveraging higher spatial resolution from handcrafted channels to improve detection accuracy, especially for small instances.

Contribution

It extends the RPN+BF framework by integrating handcrafted features with CNN features using RoI-pooling, enhancing detection performance for small pedestrians.

Findings

Handcrafted features outperform CNN features from VGG-16 in detection accuracy.

Combining handcrafted and CNN features yields better results than using either alone.

The proposed method achieves competitive results on the Caltech pedestrian dataset.

Abstract

Pedestrian detection has achieved great improvements with the help of Convolutional Neural Networks (CNNs). CNN can learn high-level features from input images, but the insufficient spatial resolution of CNN feature channels (feature maps) may cause a loss of information, which is harmful especially to small instances. In this paper, we propose a new pedestrian detection framework, which extends the successful RPN+BF framework to combine handcrafted features and CNN features. RoI-pooling is used to extract features from both handcrafted channels (e.g. HOG+LUV, CheckerBoards or RotatedFilters) and CNN channels. Since handcrafted channels always have higher spatial resolution than CNN channels, we apply RoI-pooling with larger output resolution to handcrafted channels to keep more detailed information. Our ablation experiments show that the developed handcrafted features can reach better detection accuracy than the CNN features extracted from the VGG-16 net, and a performance gain can be achieved by combining them. Experimental results on Caltech pedestrian dataset with the original annotations and the improved annotations demonstrate the effectiveness of the proposed approach. When using a more advanced RPN in our framework, our approach can be further improved and get competitive results on both benchmarks.