Published on Sat Dec 28 2019

Hybrid Channel Based Pedestrian Detection

Fiseha B. Tesema, Hong Wu, Mingjian Chen, Junpeng Lin, William Zhu, Kaizhu Huang

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 may cause a loss of information. In this paper, we propose a new pedestrian

0
0
0
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.

Tue Mar 01 2016
Computer Vision
Learning Multilayer Channel Features for Pedestrian Detection
Pedestrian detection based on the combination of Convolutional Neural Network (CNN) and traditional handcrafted features (i.e., HOG+LUV) has achieved great success. Despite its success, there is still room for improvement. In this paper, we propose a unifying framework called Multilayer
0
0
0
Tue Aug 07 2018
Computer Vision
SAM-RCNN: Scale-Aware Multi-Resolution Multi-Channel Pedestrian Detection
Convolutional neural networks (CNN) have enabled significant improvements in pedestrian detection. The same approach is used for detecting pedestrians of varying scales. It is not guaranteed that the feature representation for pedestrians of a particular scale is optimised.
0
0
0
Fri Oct 25 2019
Computer Vision
Gated Multi-layer Convolutional Feature Extraction Network for Robust Pedestrian Detection
Pedestrian detection methods have been significantly improved with the development of deep convolutional neural networks. Nevertheless, robustly detecting pedestrians with a large variant on sizes and with occlusions remains a challenging problem. We propose a gated multi-layer convolutional feature extraction method.
0
0
0
Thu Oct 01 2020
Computer Vision
From Handcrafted to Deep Features for Pedestrian Detection: A Survey
Pedestrian detection is an important but challenging problem in computer vision. Over the past decade, significant improvements have been witnessed with the help of handcrafted features and deep features. Researchers can track an up-to-date list at https://github.com/JialeCao001/
0
0
0
Sun Dec 20 2020
Computer Vision
Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection
Pedestrian detection benefits greatly from deep convolutional neural networks. It is hard for CNNs to handle situations in the presence of occlusion and scale variation. In this paper, we propose WNet, which attempts to address above challenges.
0
0
0
Fri Jan 23 2015
Computer Vision
Filtered Channel Features for Pedestrian Detection
This paper starts from the observation that multiple top performing detectors can be modelled by using an intermediate layer filtering. Based on this we propose a unifying framework and experimentally explore different filter families. We report extensive results enabling a systematic analysis.
0
0
0