Title :
Pedestrian detection using mixed partial derivative based histogram of oriented gradients
Author :
Mahmoud, Ali ; El-Barkouky, Ahmed ; Graham, James ; Farag, Aly
Author_Institution :
ECE Dept., Univ. of Louisville, Louisville, KY, USA
Abstract :
Recently, several approaches for pedestrian detection have been investigated using discriminatively trained part based models with which Histogram of Oriented Gradients (HOG) showed to be a robust feature. In this paper, we propose a new feature based on HOG to be used with the discriminatively trained part framework for pedestrian detection. Our method is based on computing the image mixed partial derivatives to be used to redefine the gradients of some pixels and to reweigh the vote at all pixels with respect to the original HOG. Our approach was tested on the PASCAL2007 and INRIA person dataset and showed to have an outstanding performance.
Keywords :
image recognition; object detection; INRIA person dataset; PASCAL2007; image mixed partial derivatives; oriented gradients histogram; pedestrian detection; Histogram of Oriented Gradients; Mixed Partial Derivative; Pedestrian Detection;
Conference_Titel :
Image Processing (ICIP), 2014 IEEE International Conference on
Conference_Location :
Paris
DOI :
10.1109/ICIP.2014.7025473