一种基于梯度和Vibe算法的运动检测算法  

A motion detection algorithm based on gradient and Vibe algorithm

作　　者：王丹[1] 樊永生[1] 王秀川[1] 

机构地区：[1]中北大学计算机与控制工程学院,山西太原030051

出　　处：《电视技术》2017年第3期100-104,共5页Video Engineering

摘　　要：针对运动检测算法在动态背景下准确性不高的问题,提出了一种基于梯度图和改进后的Vibe算法相结合的运动检测算法。该算法首先利用Sobel算子计算出梯度图,然后采用Vibe算法与三帧差分法相融合的方法对梯度图进行检测,获取运动目标。该算法改变了传统的以原始图像来构建背景模型的思想,提出了用梯度来构建背景模型,有效地改善了运动检测中的误检问题。实验结果表明,与GMM(高斯混合模型)、Codebook相比,该算法在静态背景和动态背景下实时性和准确性都较好。Aiming at the problem of low accuracy of motion detection algorithm in dynamic background, a motion detection algorithm based on gradient map and improved Vibe algorithm is proposed. Firstly, the gradient map is calculated by the Sobel operator, then the Vibe algorithm and the three frame difference method is used to detect the gradient map, and the moving object is obtained. The algorithm changes the traditional idea of the original image to build background model, and proposes a gradient to build the background model, which can effectively improve the error detection in motion detection. Experimental results show that the proposed algorithm is better in both real-time and accuracy than GMM and Codebook in static background and dynamic back- ground.

关 键 词：梯度 SOBEL算子 Vibe算法 三帧差分 背景减除法 高斯混合模型 CODEBOOK 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]