Output details
11 - Computer Science and Informatics
University of Manchester
A low-cost pedestrian-detection system with a single optical camera
<22> Pedestrian-detection systems aim to reduce pedestrian-vehicle related injury. This paper is significant because it uses a single optical camera, which has greater detection range and temperature tolerance than more expensive and sophisticated equipment, combined with machine learning (classification) and pattern recognition (object templates) to identify pedestrians that may cross the vehicle’s path (based on direction of movement and distance from the vehicle). Performance in pedestrian detection and direction identification are very good, comparable to the state-of-the-art using more expensive infra-red cameras, offering a low-cost practical approach.approach.