Pedestrian recognition using stereo vision and Histogram of Oriented Gradients

In this paper, we propose a fast and stable pedestrian recognition approach using the features from both stereo vision and HOG (Histogram of Oriented Gradient) filter. It inquires the histogram of disparity from the stereo images and builds a mask image to extract the features from foreground regions exclusively. HOG and PCA (Principal Component Analysis) are then applied to the foreground edge image and pedestrian recognition is performed by Naive Bayes classifier to achieve the real-time performance. The real road experiments showed effectiveness and efficiency of the proposed approach.