A Pedestrian Detection Method Using 3D Laser Scanner

Three-dimensional (3D) laser scanning system not only has the ability of generating images, but also has good measurement and location ability, thus it was used to detect pedestrian in front of the host vehicle. In this paper, the laser data points scanned by 3D laser scanner were converted to gray range image using the mapping algorithm. Moreover, according to characteristics of obtained laser gray range image, some preprocessing algorithms were used to improve its performance. In addition, a linear classifier was designed to recognize pedestrians in the gray range image based on shape features and coordinate matching algorithm was used for pedestrian location. Experiment results indicate that the proposed pedestrian detection system based on the 3D laser scanner has good reliability and robustness when it is used to detect pedestrian.