Implicit color segmentation features for pedestrian and object detection

We investigate the problem of pedestrian detection in still images. Sliding window classifiers, notably using the Histogram-of-Gradient (HOG) features proposed by Dalal and Triggs are the state-of-the-art for this task, and we base our method on this approach. We propose a novel feature extraction scheme which computes implicit `soft segmentations' of image regions into foreground/background. The method yields stronger object/background edges than gray-scale gradient alone, suppresses textural and shading variations, and captures local coherence of object appearance. The main contributions of our work are: (i) incorporation of segmentation cues into object detection; (ii) integration with classifier learning cf. a post-processing filter; (iii) high computational efficiency. We report results on the INRIA person detection dataset, achieving state-of-the-art results considerably exceeding those of the original HOG detector. Preliminary results for generic object detection on the PASCAL VOC2006 dataset also show substantial improvements in accuracy.