摘要
研究带有运动景物的复杂背景中视频图像运动目标的检测 .用图像差分法提取运动目标信息 ;针对运动景物在差分图像中产生强脉冲干扰的特点 ,提出 K邻域自适应滤波算法 ;采用二维熵准则选择最佳二值化阈值 ;最后用图像形态学运算处理目标的分割碎块 .
The detection of moving object in video image has been studied in this paper, which was in complex background with swaying things. A new filter algorithm named K neighborhood adaptive filter is proposed here for smoothing strong impulse disturbance in the difference image. The optimum threshold was get from the two dimensional entropy criterion. And then the segmentation fragments were dealt with binary morphological operation. The experiment of image preprocessing is also described.
出处
《内蒙古大学学报（自然科学版）》
CAS
CSCD
北大核心
2001年第6期670-674,共5页
Journal of Inner Mongolia University：Natural Science Edition
