A new moving target detection algorithm

2019 International Conference on Advanced Electronic Materials, Computers and Materials Engineering

无线电电子学;计算机科学;材料科学

Fan, Chaonan^1 ; Li, Shixin^1 ; Zhang, Hai^1 ; Tian, Jicai^2 ; Ren, Liqiang^2

Tianjin University of Technology and Education, Tianjin, China^1

Tianjin Shitai Group Co.Ltd, Tianjin, China^2

关键词: Balance coefficients;    False detections;    Illumination changes;    Inter-frame difference methods;    Moving target detection;    Moving targets;    Video image sequences;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/563/5/052026/pdf
DOI  :  10.1088/1757-899X/563/5/052026

来源: IOP

【 摘 要 】

The traditional GMM can easily detect the background as a moving target and is sensitive to the illumination changes. So this paper put forward a moving target detection algorithm combining the improved custom GMM with the five-frame interframe difference method. After the video image sequence is preprocessed, the GMM is added with the balance coefficient and the merged useless Gaussian distribution is combined. Then the improved GMM is combined with the five-frame interframe difference method to obtain the detected target. Simulation experiments show that the improved algorithm adapt the environment better. The improved algorithm reduces the impact of illumination changes on moving target detection, and significantly reduces the false detection rate.