摘要
针对视频监控中运动目标检测时间复杂度高的问题,提出一种基于灰度特征模型的背景消除方法。通过提取视频图像像素的灰色特征,将视频图像中每个位置上的像素点用一个灰度特征集合来表征,并以此为依据计算各像素点灰度值与灰度特征集合中的像素点灰度值之间的距离,判别对应像素点的背景与前景状态,从而实现视频图像的背景消除。实验结果表明,该方法在处理效果接近的情况下,可以显著提升运动目标的检测速度,降低处理的时间复杂度。
In the respect of moving target detection,focused on the high complexity of present algorithms,a gray feature model-based background subtraction method is proposed. By extracting the gray features of the pixels in the video image, the pixel of the video image can be presented by a set of gray features, which is taken as a basis for determining the background/foreground state of the corresponding pixel in the video image by computing the distance between the gray value of the pixel in the video image and the gray value of the pixel in the gray feature set. Experimental results show that, the gray feature model-based background subtraction method can significantly enhance the processing speed and reduce the time complexity of the moving target detection,in case of the same detecting results.
出处
《计算机工程》
CAS
CSCD
北大核心
2015年第6期240-246,257,共8页
Computer Engineering
基金
国家社会科学基金资助项目(13CFX055)
新疆维吾尔自治区高校科研计划科学研究基金资助重点项目(XJEDU2013I34)
关键词
运动目标检测
视频监控
背景消除
灰度特征模型
特征分析
moving target detection
video surveillance
background subtraction
gray feature model
feature analysis
