Histograms of Oriented Gradients for Human Detection
Navneet Dalal and William Triggs
In: CVPR 2005, 20-26 June 2005, San Diego, California.
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.
|EPrint Type:||Conference or Workshop Item (Paper)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||William Triggs|
|Deposited On:||30 December 2004|