What Can Help Pedestrian Detection?

Abstract

Aggregating extra features has been considered as an effective approach to boost traditional pedestrian detection methods. However, there is still a lack of studies on whether and how CNN-based pedestrian detectors can benefit from these extra features. The first contribution of this paper is exploring this issue by aggregating extra features into CNN-based pedestrian detection framework. Through extensive experiments, we evaluate the effects of different kinds of extra features quantitatively. Moreover, we propose a novel network architecture, namely HyperLearner, to jointly learn pedestrian detection as well as the given extra feature. By multi-task training, HyperLearner is able to utilize the information of given features and improve detection performance without extra inputs in inference. The experimental results on multiple pedestrian benchmarks validate the effectiveness of the proposed HyperLearner.

Accepted to IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2017

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Fully Convolutional Networks for Semantic Segmentation
• Scale-aware Fast R-CNN for Pedestrian Detection
• How Far are We from Solving Pedestrian Detection?
• Local Decorrelation For Improved Detection
• Filtered Channel Features for Pedestrian Detection
• Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
• Is Faster R-CNN Doing Well for Pedestrian Detection?