Moving Target Detection Algorithm in Image Sequences Based on Edge Detection and Frame Difference
In order to overcome the drawbacks of the traditional frame-difference method that is used in moving target detection,and to achieve both accurate and robust detection result,a novel approach for moving objects detection based on improved Canny edge detection and adaptive frame difference method is proposed in this paper.Firstly,select the threshold value of three-frame difference method adaptively by using Otsu algorithm,but the edge of target is not continuous enough.And then the boundary of current frame is obtained by using improved Canny operator,the edge information is more accurate,complete and continuous.Finally integrate the two results and use morphological approach to process the isolated noise spot and the hole in the target area,complete the moving target detection.Experimental results show that this algorithm can improve the moving target detection-rate in real-time.
moving target detection frame difference Canny operator Otsu morphology algorithm
Guiming Shi Jidong Suo Chang Liu Kang Wan Xiaoying Lv
School of Information Science and Technology,Dalian Maritime University;School of Electrical Enginee School of Information Science and Technology,Dalian Maritime University School of Electrical Engineering,Dalian Institute of Science Technology Dalian,China
国际会议
重庆
英文
740-744
2017-10-03（万方平台首次上网日期，不代表论文的发表时间）