PT Unknown
AU Victor Borjas
   Jordi Vitria
   Petia Radeva
TI Gradient Histogram Background Modeling for People Detection in Stationary Camera Environments
BT 13th IAPR Conference on Machine Vision Applications
PY 2013
AB Best Poster AwardOne of the big challenges of today person detectors is the decreasing of the false positive rate. In this paper, we propose a novel framework to customize person detectors in static camera scenarios in order to reduce this rate. This scheme includes background modeling for subtraction based on gradient histograms and Mean-Shift clustering. Our experiments show that the detection improved compared to using only the output from the pedestrian detector reducing 87% of the false positives and therefore the overall precision of the detectionwas increased signicantly.
ER