A Robust Moving Objects Detection Algorithm Based on Gaussian Mixture Model
Song Xuehua, Yu Chen, Geng Jianfeng, Jingzhu Chen · 2009
The paper proposes a novel algorithm which can effectively resolve the problems of background disturbance and light changes in allusion to the problem that the background subtraction is sensitive to light changes. The algorithm, combined with the methods of background subtraction and adjacent frame difference, adopts Gaussian mixture model to avoid the impact of background disturbance. By using the idea of adjacent frame difference for reference, it deals with light changes by background reconstruction and constructing the function of dynamic learning efficiency. The algorithm is simulated under the circumstance of background disturbance and light changes, the experimental results show that the algorithm is more efficient and robust than traditional methods, and it can attain background model in the complex condition quickly. The algorithm is particularly suitable to the intelligent video surveillance with static cameras.