Filtered channel features for pedestrian detection

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 dif...

Full description

Saved in:
Bibliographic Details
Published in2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1751 - 1760
Main Authors Zhang, Shanshan, Benenson, Rodrigo, Schiele, Bernt
Format Conference Proceeding Journal Article
LanguageEnglish
Published IEEE 01.06.2015
Subjects
Channels
Computer vision
Conferences
Decision trees
Detectors
Feature extraction
Filter banks
Filtering
Image color analysis
Optical filters
Optical flow
Pattern recognition
Pedestrians
Recall
Shape
Training
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:1063-6919
1063-6919
2575-7075
DOI:10.1109/CVPR.2015.7298784