CiteWeb id: 20050000001

CiteWeb score: 15279

DOI: 10.1109/CVPR.2005.177

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.

The publication "Histograms of oriented gradients for human detection" is placed in the Top 1000 of the best publications in CiteWeb. Also in the category Computer Science it is included to the Top 100. Additionally, the publicaiton "Histograms of oriented gradients for human detection" is placed in the Top 100 among other scientific works published in 2005.
Links to full text of the publication: