Moving Target Detection based on Multi-feature Adaptive Background Model

For the problems of shadow and the influence of dynamic background, a moving object detection method based on multi-feature adaptive background model is presented in this paper. Firstly, establish the chromaticity model and texture model respectively to represent each pixel. Then, adjust the model adaptively according to the background complexity and extract the moving object. Finally, find the inner contour of extracted object to fill, which makes the results more complete. At the same time, update the background model. The test results show that the presented method can eliminate the influence of shadow and dynamic background well. Compared with several other methods, it has a better overall performance.