Moving object extraction using the improved adaptive Gaussian mixture model and shadow detection model

作者：Zeng Zhigao^*; Liu Lihong; Yi Shengqiu; Wen Zhiqiang; Yang Fanwen; Guan Lianhua

来源：Journal of Information and Computational Science, 2015, 12(14): 5515-5522.

DOI：10.12733/jics20106664

• Adaptive Gaussian mixture models
• Background model
• HSV space
• Learning mechanism
• Moving object extraction
• Moving objects
• New parameters
• Shadow detections

In order to overcome the shortcomings that the parameters of the adaptive Gaussian mixture model which is used for the background modeling update slowly, a new parameters learning mechanism is proposed in this paper. Then, according to the characteristics of the shadows of moving objects in HSV space, a background modeling algorithm is proposed using the improved adaptive Gaussian mixture model to extract the moving object. Simultaneously, in order to remove the shadow of the moving object, a shadow detection model is proposed in this paper. Experiments show that the shadow of moving objects can be eliminated effectively and the background modeling algorithm has good robustness.

• 出版日期2015