Filtered Channel Features for Pedestrian Detection

Abstract

This paper starts from the observation that multiple top performing pedestrian detectors can be modelled by using an intermediate layer filtering low-level features in combination with a boosted decision forest. Based on this observation we propose a unifying framework and experimentally explore different filter families. We report extensive results enabling a systematic analysis. Using filtered channel features we obtain top performance on the challenging Caltech and KITTI datasets, while using only HOG+LUV as low-level features. When adding optical flow features we further improve detection quality and report the best known results on the Caltech dataset, reaching 93% recall at 1 FPPI.

References in corpus (3)

• Ten Years of Pedestrian Detection, What Have We Learned?
• Local Decorrelation For Improved Detection
• Pedestrian Detection with Unsupervised Multi-Stage Feature Learning

Cited by in corpus (7)

• CityPersons: A Diverse Dataset for Pedestrian Detection
• Multispectral Deep Neural Networks for Pedestrian Detection
• End-to-end people detection in crowded scenes
• Grid Loss: Detecting Occluded Faces
• Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator
• Is Faster R-CNN Doing Well for Pedestrian Detection?
• A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection