Abstract:In the research of modern urban planning, the in-depth analysis of the information that focuses on human is crucial. The use of an effective video analysis technology to analyze and monitor video can greatly expand the basic data of pedestrian, which is of great significant to urban quantitative researches. This study deals with video that shot pedestrians in the same street for a period of time. Deep learning is used for detecting pedestrians in the specified monitoring area of the video based on the forward propagation convolution neural network model. In order to ensure the accuracy of the information for pedestrians, it tracks the detected pedestrians and determines whether the target is lost. Finally, it quantifies the number of pedestrians, the direction and speed of movement, the time of retention, etc., and carries out corresponding data analysis. The results show that the method can effectively quantify data of pedestrian information, then provide accurate and effective data support for urban quantitative studies.