Pedestrian Detection on Multispectral Images in Different Lighting Conditions

Abstract

Autonomous vehicles keep evolving in years. Pedestrian detection is a significant function for autonomous vehicles. However, there is an issue that affects the performance of pedestrian detection, which is the lighting condition. Pedestrian detection performance usually decreases at nighttime. This research utilized Deep Neural Network as a tool to accomplish a pedestrian detection task in different lighting conditions. RGB, thermal infrared, and multispectral images were inputted to the DNN for pedestrian detection and it was evaluated afterward. The results imply that the multispectral image-based pedestrian detection can achieve better performance than the RGB image-based or thermal image-based pedestrian detections.