Human Detection Using Multiple Classifiers Based on Subtraction Stereo with HOG Features

Abstract

In this paper, we propose a fast and stable human detection based on “Subtraction Stereo” which can measure distance information of foreground regions. Scanning an input image by detection windows is controlled about their window sizes and number using the distance information obtained from subtraction stereo. This control can skip a large number of detection windows and leads to reduce the computational time and false detection for fast and stable human detection. Additionally, we construct a human detection method with little incorrect detection using multiple detectors. The effectiveness of our method is verified by experiments.