Pedestrian tracking is a hotspot and a difficult topic in computer vision research. Through the tracking of pedestrians in video materials, trajectories can be extracted to support the analysis of individual or collected behavior dynamics. In this review, we first discuss the difference between pedestrian tracking and pedestrian detection. Then we summarize the development of traditional tracking algorithms and deep learning-based tracking algorithms, and introduce classic pedestrian dynamic models. In the end, typical applications, including intelligent monitoring, congestion analysis, and anomaly detection are introduced systematically. With the rising use of big data and deep learning techniques in the area of computer vision, the research on pedestrian tracking has made a leap forward, which can support more accurate, timely extraction of behavior patterns and then to facilitate large-scale dynamic analysis of individual or crowd behavior.