改进型ViBe算法及其在运动目标提取中的应用  

Improved ViBe Algorithm and Its Application to Moving Object Extraction

作　　者：杨青 张著洪 YANG Qing;ZHANG Zhuhong(College of Big Data and Information Engineering, Guizhou Unversity, Guiyang 550025, China)

机构地区：[1]贵州大学大数据与信息工程学院,贵州贵阳550025

出　　处：《贵州大学学报（自然科学版）》2019年第2期74-78,共5页Journal of Guizhou University:Natural Sciences

基　　金：国家自然科学基金项目资助(61563009)

摘　　要：提出一种基于阈值半径自适应更新及阴影与鬼影检测的改进型Vi Be算法,解决运动场景下Vi Be算法的目标提取效果易受背景高频扰动、摄像机抖动、阴影、鬼影的影响问题。算法设计中,依据当前帧的像素点梯度与背景图序列对应像素点的灰度均方差设计阈值自适应更新策略;依据背景图在HSV空间中的像素值设计阴影去除规则;利用前景-邻域直方图的相似度匹配规则设计鬼影清除规则。实验结果表明,改进型Vi Be算法在保留原有的高效性的同时,能够较好地消除视频图像中隐含的阴影和鬼影,以及抖动对目标提取的影响。An improved Vi Be algorithm based on threshold radius update and also shadow and ghost’s detection was proposed to improve the effect of target extraction,since the basic Vi Be algorithm is easily influenced by high frequency disturbance,camera jitter,shadow and ghost. In the design of the algorithm,an adaptive threshold update strategy was acquired based on pixel gradients of the current image and background images’ gray mean square deviations;the shadow and ghost’ s removal rules were designed according to the pixel values of background images in the HSV space and the similarity matching rule of the foreground-neighborhood histogram. Numerical results show that the improved Vi Be algorithm can eliminate the hidden shadows and ghosts in video images,and also the influence of jitter on target extraction.

关 键 词：ViBe算法 鬼影检测 阴影消除 阈值半径自适应更新 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]