Histograms of oriented gradients for human detection

• Published in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 1; pp. 886 - 893 vol. 1
• Main Authors: Dalal, N., Triggs, B.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2005
• Subjects: High performance computing; Histograms; Humans; Image databases; Image edge detection; Object detection; Object recognition; Robustness; Support vector machines; Testing
• DOI: 10.1109/CVPR.2005.177
• ISBN: 0769523722; 9780769523729
• ISSN: 1063-6919

We 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 backgrounds.