摘要
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.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2009年第S1期72-74,共3页
Journal of System Simulation
基金
北京市属市管高等学校人才强教计划资助PHR(IHLB)
北京市教委面上项目(KM200910009001)
关键词
目标检测
高斯混合模型
边缘检测
光照突变
object detection
Gaussian mixture modes
edge detection
sharp light change
