摘要
Vibe(Visual background extractor,视觉背景提取)算法速度快,能有效抑制噪声,但是也有缺陷,比如无法有效去除运动目标阴影,且不能快速去除"鬼影"区域。针对上述问题,提出了一种基于融合帧差法的改进Vibe算法。利用新的帧差法,提出如下改进:在灰度空间进行前景检测并利用亮度信息去除运动目标的阴影;巧妙运用帧差法的特性,利用两种方法所得的背景进行"与"操作,快速去除Vibe产生的"鬼影"。最后用形态学方法对检测结果进行改善,给出实验验证结果。结果表明,文中提出的改进方法可以很好地去除阴影,并能快速去除"鬼影",从实际效果上提高了算法的可靠性和检测的准确性。
Vibe（ Visual background extractor） algorithm runs very quickly and can restrain the impact of noise,but it does has flaw s. For example,the several classical related papers didn＇t propose the efficient method to remove shadow s,and couldn＇t remove the ＂ ghost＂ areas quickly. On the issues mentioned above,propose an improved Vibe algorithm based on fusing frame differential method. Using a new frame differential method,it gives tw o improvements. On the one hand,a new way to detect and remove the shadow using the brightness information only in gray space is proposed. On the other hand,it can remove the ＂ ghost＂ area quickly,via using the frame differential feature skillfully,means doing ＂ And＂ operation betw een the tw o kinds of background images. Finally,improve the result with morphological method and show the result of experimental verification. The results show that this improved method does remove the shadow s well and remove the ＂ ghost＂ well. Besides it improves the reliability and accuracy of the detection from the practical effect.
出处
《计算机技术与发展》
2015年第3期76-80,共5页
Computer Technology and Development
基金
国家自然科学基金资助项目(61302156)
江苏省高校自然科学研究面上项目(13KJB510021)
关键词
Vibe改进
帧差法
阴影去除
“鬼影”去除
前景检测
Vibe improvement
frame differential method
shadow removal
＂ ghost＂ removal
foreground image detection
