摘要
为了克服传统背景差分法所存在的不足,提出了一种基于边缘特征和改进K-均值聚类相结合运动目标检测方法。运用改进的K-均值聚类方法建立背景模型,将其与前景图像相差后得到的二值化图像,通过前景边缘信息的鲁棒性来判别及去除存在的虚假目标。实验结果表明,该方法可以有效去除背景中突然有物体移入或移出引起的虚假运动目标,提高了运动目标检测的准确性。
In order to overcome the drawbacks of the traditional background subtraction method, a moving target detection method based on the combination of edge features and improved K-means clustering is provided. Background model is established using improved K-means clustering method. The difference between foreground image and background image is calculated and the binarization process is employed. False targets are judged and rejected with the foreground edge information. Experimental results show that the method can effectively eliminate the false moving target resulted from object move-in or move-out and improve the accuracy of moving target detection.
出处
《计算机工程与应用》
CSCD
2012年第20期206-210,共5页
Computer Engineering and Applications
基金
甘肃省自然基金项目(No.1010RJZA046)
甘肃省教育厅研究生导师基金项目(No.0914ZTB003)
关键词
K-均值聚类
背景差
边缘信息
虚假运动目标
K-means clustering
background subtraction
edge information
false moving target
