# Learning Multilayer Channel Features for Pedestrian Detection

arXiv: https://arxiv.org/abs/1603.00124 · HTML: https://mlsanity.com/paper/1603.00124/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2016.

## Built on by (most cited first, 3 of 3)

- [Pedestrian Detection by Exemplar-Guided Contrastive Learning](https://mlsanity.com/paper/2111.08974/) (2021)
- [A PST Algorithm for FPs Suppression in Two-stage CNN Detection Methods](https://mlsanity.com/paper/2406.18553/) (2024)
- [Better Sampling, towards Better End-to-end Small Object Detection](https://mlsanity.com/paper/2407.06127/) (2024)

## Abstract (arXiv)

Pedestrian detection based on the combination of Convolutional Neural Network (i.e., CNN) and traditional handcrafted features (i.e., HOG+LUV) has achieved great success. Generally, HOG+LUV are used to generate the candidate proposals and then CNN classifies these proposals. Despite its success, there is still room for improvement. For example, CNN classifies these proposals by the full-connected layer features while proposal scores and the features in the inner-layers of CNN are ignored. In this paper, we propose a unifying framework called Multilayer Channel Features (MCF) to overcome the drawback. It firstly integrates HOG+LUV with each layer of CNN into a multi-layer image channels. Based on the multi-layer image channels, a multi-stage cascade AdaBoost is then learned. The weak classifiers in each stage of the multi-stage cascade is learned from the image channels of corresponding layer. With more abundant features, MCF achieves the state-of-the-art on Caltech pedestrian dataset (i.e., 10.40% miss rate). Using new and accurate annotations, MCF achieves 7.98% miss rate. As many non-pedestrian detection windows can be quickly rejected by the first few stages, it accelerates detection speed by 1.43 times. By eliminating the highly overlapped detection windows with lower scores after the first stage, it's 4.07 times faster with negligible performance loss.