Soutenance de thèse Hironobu Fujiyoshi

FAST OBJECT DETECTION WITH BINARY FEATURE REPRESENTATION

Date : Friday 25th of september - 1:30 p.m. to 2:30 p.m., room 160

Abstract: Object detection involves classification of a huge number of detection windows obtained by raster scanning of an input image. In this talk, we introduce an approximate computation of linear SVM with binary feature representation to object detection. We will show that the proposed method is about 16 times faster than the conventional HOG and linear SVM and improves the classification accuracy by about 6%.