Histograms of Oriented Gradients for Human Detection
Top Cited Papers
- 20 June 2005
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 886-893
- https://doi.org/10.1109/cvpr.2005.177
Abstract
International audienceWe study the question of feature sets for robust visual object recognition, adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of Histograms of Oriented Gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgroundsKeywords
This publication has 15 references indexed in Scilit:
- A performance evaluation of local descriptorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Scale & Affine Invariant Interest Point DetectorsInternational Journal of Computer Vision, 2004
- Object Detection Using the Statistics of PartsInternational Journal of Computer Vision, 2004
- Detecting pedestrians using patterns of motion and appearancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Matching shapesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Efficient matching of pictorial structuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Example-based object detection in images by componentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- A Trainable System for Object DetectionInternational Journal of Computer Vision, 2000
- Spatial mapping in the primate sensory projection: Analytic structure and relevance to perceptionBiological Cybernetics, 1977