Image Processing Based Pedestrians Detection Algorithms Research And Framework Design Using Single Camera

Computer intelligent video surveillance system (CIVSS) is one of important high-tech application fields and front topics in Computer Vision domain. It spans many subjects including computer science, machine vision, image engineering, pattern analysis, artificial intelligence, etc. CIVSS can automatically analyze the sequence of images by the methods of computer vision and video analysis. The system can detect, position, recognize and track objects in a moving environment in real-time. Furthermore, it can also analyze and judge the movement of objects. The aims of CIVSS are to understand the meanings and contents of video stream and to explain the scenes. As to computer intelligent video surveillance, there are still many problems either in theory research or in applications although broad applications in various fields. This article made use of the current popular surveillance technical and did research on moving pedestrians'detecting and tracking under a fixed CCD camera.Firstly, this article has introduced the basic settings of this system that camera need to be fixed on the entrance. Then self-adaptive background subtraction algorithms would use camera-captured data to segment the moving pedestrians. After that, system restrained noise with morphologic operation. To extract the pedestrians, system made use of theirs contours. In order to track pedestrians, the blob feature of pedestrians was introduced to represent pedestrians. It improved quality of tracking when using a detecting area and a queue to help analyze. Based on tracing, the system calculated the pedestrians'number. At last, the system sent the data to database using web service and wireless network.Experiments under several surroundings showed this system could detect and track pedestrians very well. But at the same time, it also figured out the system was vulnerable to the merge-split action of people and the unstable changeable lights. More efforts should be made to enhance the robustness of detection, improve the accurateness of counting and integrate the video system with other technology to make it have a better performance.