Pedestrian Detection for a Near Infrared Imaging System

This paper considers pedestrian detection, specialized for a near infrared imaging system at night. The main objective is the detection of a distant pedestrian, beyond an illuminated area in a low-beam mode, using a monocular on-board camera. In this method, the region of interest (ROI) is first selected by extracting bright regions, and shape information from a whole human body, is later used for verification. Motion information is not used, due to difficulties in cancellation of ego-motion. The ROI selector is implemented by a modified boosted cascade, in combination with dynamic perspective constraints. After filtering out typical non-pedestrian objects, the remaining ROIs are verified using a support vector machine (SVM). The verified ROIs are tracked with a simple alpha-beta tracker, in combination with final validation, based on a classification score from the SVM. The effectiveness of the proposed modules has been confirmed using several typical night time scenarios.