Tracking and Location for Moving Targets Using Plane Constraint Based On Digital Video
This paper presents a series of algorithms for tracking and positioning of moving targets with monocular image sequences of sports field recorded by a stationary camera. In the detection of moving objects, we adopted the background-subtraction method based on background updating. Meanwhile, in order to adapt to the luminance variance of the background imagery, we used improved OSTU algorithm to calculate the threshold in real time to extract moving objects.In the tacking of moving object, we extract the connected region of binary image, and then calculate the Minimum Enclosing Rectangle of the connected region to obtain the position of moving objects in the video image. Then we can track moving objects through the position change in every frame, we can extract the feature (area, gray scale) of Enclosing Rectangle to reject the false target caused by image noise or algorithmic error.In the locating of moving object, we set a series control points(whose space coordinates have been measured), using 3D-DLT algorithm and The Space Resection to calculate the camera parameters, using plane constraint conditions, collinearity equation and plane equation to calculate the 3D coordinates of moving objects. This method can do object tacking and locating at the same time.Based on the measurement addressed in this paper, the result of detection and location of moving targets can be acquired at the same time. Experimental results from test field are provided which demonstrate the effectiveness of method. The result of the experiment can be used to analyze the movement of players in the match. The research and analysis of the video can help the team coach to do some research of tactics.
camera calibration movement detection tracking and location plane constraint
Wu Liang1 Li Han Ding Lu Kong Bin-cheng Shi Yang Ji Zheng
School of Remote Sensing and Information Engineering Wuhan University Wuhan, China School of Aeronautics & Astronautics Shanghai Jiao Tong University Shanghai, China
国际会议
三峡
英文
2058-2062
2012-05-18（万方平台首次上网日期，不代表论文的发表时间）