基于改进的高斯混合模型的运动目标检测

运动目标检测是实现目标跟踪、视频监控的基础.针对基于高斯混合模型的运动目标检测算法的不足,提出了一种基于分块思想和高斯模型个数自适应的改进高斯混合算法.利用对视频图像分块的思想,在提高目标检测效率的同时,实现对视频的滤波处理;并利用高斯混合模型中高斯分布个数自适应操作来降低算法复杂度,提高运动目标检测的速度.实验结果表明:该算法比传统高斯混合模型运动目标检测算法具有更快的检测速度和更好的检测效果,并降低了检测噪声,能有效地检测运动目标,适用于运动目标的实时检测.

Moving Target Detection Based on Improved Gaussian Mixture Model

Moving object detection is the basis for object tracking and video surveillance.An improved Gaussian mixture algorithm for moving objects detection based on block and the self-adaptive number of Gaussian mixture model was proposed,aiming at the deficiency of moving target detection algorithm based on Gaussian mixture model.Idea of video image blocking is used to improve efficiency of target detection and at the same time realize video filtering processing.And self-adaptive operation based on number of Gaussian distribution in Gaussian mixture model is used to reduce complexity of algorithm,improve speed of moving target detection.Experimental results indicate that the improved Gaussian mixture algorithm possesses faster detection speed,better detecting effect,and reduces detection noise.It can detect moving target effectively,and is suitable for real-time detection of moving targets.