Moving Object Detection in Tennis Video

摘要

In order to solve the existing problems of noise-sensitive and inefficient background updating in current object detection process, an effective moving object detection method which based on two layers background model is proposed in this paper. The codebook model using brightness and color features is presented in the first layer, while a running average algorithm in the second layer, we get moving target by comprehensive weighted method according to two layers' results. Experimental results demonstrate that the method can detect the object more accurately, completely, update background faster, and it shows good real-time.