Moving Objects Detection Method Based on the Improved Adaptive Background Mixture Model
Li Shaozi · Journal of Xiamen University · 2008
Aiming at the slow learning rate of traditional mixture Gaussian model, our paper proposed a moving object detection algorithm .First, the mixed Gaussian model was constructed, and a new way was adopted to update background, which utilized different equations at different phases.Then, a coarse foreground image could be obtained by background subtraction.Next, moving shadows was eliminated by a shadow detection algorithm using light, color and gradient information.Finally, we performed post processing, including morphology filtering, connected component analysis and seeded region growing.The experimental results showed that the proposed method, in indoor and outdoor environment, could remove shadows well and extract moving objects accurately.