DETECTION AND TRACKING OF PEDESTRIANS USING DOPPLER LIDAR
Pedestrian detection and tracking plays an essential role in autonomous vehicles and mobile service robots. This thesis presents a novel solution to pedestrian detection and tracking for urban scenarios based on Doppler LiDAR that records both position and velocity of the targets. The workflow consists of two stages. In the detection stage, the input point cloud is first segmented to form clusters frame by frame. A subsequent re-clustering process is introduced to further separate pedestrians close to each other. While a simple speed classifier is capable of extracting most of the moving pedestrians, a supervised machine learning-based classifier is adopted to detect pedestrians with insignificant radial velocity. In the tracking stage, pedestrian’s state is estimated by a Kalman filter, which uses the speed information to measure the pedestrian’s dynamics. Based on the similarity between the predicted and detected states of pedestrians, a greedy algorithm is adopted to associate the trajectories with the detection results. The presented detection and tracking methods are tested on two datasets collected in San Francisco, California by a mobile Doppler LiDAR system. The results of pedestrian detection show that the proposed two-step classifier can improve the detection performance, particularly for detecting pedestrians far from the sensor. For both datasets, the speed information increases the F1-score and the recall by 10% and 20%, respectively. Moreover, the quantitative evaluation of tracking results shows the Kalman filter with speed information is able to enhance the accuracy of the position estimation and improve the multiple object tracking accuracy (MOTA) by 5% for both datasets.