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.
Histograms of oriented gradients for human detection
01.01.2005
247177 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
AdaBoost Learning for Human Detection Based on Histograms of Oriented Gradients
Springer Verlag | 2007
|Pedestrian Detection using Infrared images and Histograms of Oriented Gradients
British Library Conference Proceedings | 2006
|PEDESTRIAN DETECTION USING HISTOGRAMS OF ORIENTED GRADIENTS OF GRANULE FEATURE
British Library Conference Proceedings | 2013
|