一种基于边缘高斯混合模型的运动目标检测方法

Moving Object Detection Based on Edged Mixture Gaussian Models

针对现有方法在复杂多变环境下不能很好地检测出运动物体的问题,结合图像边缘轮廓信息和自适应高斯混合模型提出了一种新的运动目标提取算法,利用图像边缘信息不随光照的变化而发生突变的特性,对图像边缘进行混合高斯建模,学习背景的边缘信息,从而有效地提取运动目标的轮廓信息。与传统方法相比,提出的运动目标检测方法能更好地适应光线的变化,可有效地提高运动目标检测的准确度。

Learning background statistics is an essential task for several visual surveillance applications such as incident detection and traffic management. In this paper we present an adaptive foreground object extraction algorithm for real-time video surveillance. The proposed algorithm improves the classic Gaussian mixture background models (GMMs) to remove the undesirable subtraction results due to sudden illumination change. This is achieved by replacing the whole image with edge image to build mixture Gaussian model at every frame. Experimental results on real surveillance video are shown to demonstrate the robustness of the proposed algorithm under a variety of different environments with lighting variations.