改进的ViBe运动目标检测算法  

Improved ViBe algorithm for detecting moving objects

作　　者：于明[1] 刘帅[1] 师硕[1] 

机构地区：[1]河北工业大学计算机科学与软件学院,天津300401

出　　处：《河北工业大学学报》2017年第1期65-70,共6页Journal of Hebei University of Technology

基　　金：天津市科技计划项目(14RCGFGX00846;15ZCZDNC00130);河北省自然科学基金(F2015202239)

摘　　要：ViBe算法存在初始化背景建模效果不佳、不适应复杂背景变化以及消除鬼影较慢的问题.为了解决这些问题,提出一种改进的ViBe算法.此算法首先采用多帧图像梯度幅值进行背景建模,在背景更新时,引入阈值自适应调整因子,实现动态更新阈值,为提高消除鬼影效率,在鬼影消除判别过程中采用基于运动目标区域整体性的判别方法.实验结果表明,改进的算法能快速的消除鬼影,在复杂背景、光线变化环境中有更好的适应性和更高的检测精度.The initial background modeling of the existing ViBe algorithm is not effective and it do not adapt to the complex background change as well as the rate of eliminating ghost is slower. To solve this problems, an improved algorithm was proposed in the paper. First, the background of the algorithm is modeled by multi-frame image gradient amplitude. In the background update, a threshold adaptive factor is introduced to realize the threshold of dynamic updating. The paper adds a method based on integral discrimination of moving objects to enhance the rate of eliminating ghost. The experimental results show that the improved algorithm can eliminate the ghost more quickly, and has better adaptability and higher detection precision in complicated background and light changing environment.

关 键 词：ViBe 目标检测 梯度幅值 自适应阈值 鬼影消除 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]