A Shape-Independent-Method for Pedestrian Detection with Far-Infrared-Images

Night-time driving is more dangerous than day-time driving — particularly for older drivers. Three to four times as many deaths occur at night than in the day time [1]. To improve safety of night driving, automatic pedestrian detection based on infrared images has drawn increasing attention because pedestrians tend to stand out more against the background in infrared images than they do in visible light images. Nevertheless, pedestrian detection is by no means trivial in infrared images — many of the known difficulties carry over from visible light images, such as image variability occasioned by pedestrians being in different poses. Typically, several different pedestrian templates have to be used in order to deal with a range of poses. Furthermore, pedestrian detection is difficult because of poor infrared image quality (low resolution, low contrast, few distinguishable feature points, little texture information, etc.) and misleading signals To address these problems, this paper introduces a shape-independent pedestrian detection method. Our segmentation algorithm first estimates pedestrians ’ horizontal locations through “Projection-based” horizontal segmentation, and then determines pedestrians ’ vertical locations through “Brightness/Bodyline-based ” vertical segmentation. Our classification method defines multi-dimensional histogram-, inertial-, and contrast-based classification features, which are shape-independent, complementary to one another, and capture the statistical similarities of image patches containing pedestrians with different poses. Thus, our pedestrian detection system needs only one pedestrian template — corresponding to a generic walking pose — and avoids brute-force search for pedestrians throughout whole images, which typically involve