The invention provides a 4S store potential customer behavior analysis system based on a Reid and face recognition technology, and the system comprises the following steps: (1), decoding a video stream from video monitoring, and extracting a picture frame at regular time; (2), performing pedestrian detection on the picture frame to obtain a pedestrian human body picture; (3) calculating pedestrianpictures by using a Reid model, and extracting pedestrian feature vectors; (4) storing the data in the step (3) into a database, including picture shooting time and camera numbers; (5), screening human body trajectory data associated with a human face so as to know trajectory behavior data of a corresponding customer; for each subsequent picture frame, calculating a pedestrian feature vector, andjudging whether the pedestrian appears before or not; the passenger flow calculation reliability is higher, the data is more complete, and the repeated passenger flow can be effectively removed. Datais collected in a non-inductive mode, customer behaviors are not intervened, and the experience feeling is good.