首页 | 本学科首页   官方微博 | 高级检索  
     检索      

融合高斯混合模型和prewitt算子的运动目标检测
引用本文:陈世文,谭建斌,周汉达.融合高斯混合模型和prewitt算子的运动目标检测[J].嘉应学院学报,2011,29(5):31-34.
作者姓名:陈世文  谭建斌  周汉达
作者单位:1. 嘉应学院计算机学院,广东梅州,514015
2. 佛山职业技术学院电子信息系,广东佛山,528237
摘    要:提出一种融合高斯混合模型和prewitt算子的运动目标检测算法.通过高斯混合模型拟合背景信息,利用prewitt算子提取图像的边缘特征信息,将两者融合起来.边缘信息反映了局部区域内容的结构信息,可作为颜色信息的补偿;模型保证了在线更新背景信息时的稳定性和收敛性,同时弥补了目标分割中颜色信息接近时容易导致误判的不足.实验结果表明,与一般高斯混合模型比较,本方法具有较高的分割精度,提高了目标检测的鲁棒性.

关 键 词:高斯混合模型  prewitt算子  目标检测

Moving Object Detection Using A Gaussian mixture Model and Prewitt Operator
CHEN Shi-wen,TAN Jian-Bin,ZHOU Hah-Da.Moving Object Detection Using A Gaussian mixture Model and Prewitt Operator[J].Journal of Jiaying University,2011,29(5):31-34.
Authors:CHEN Shi-wen  TAN Jian-Bin  ZHOU Hah-Da
Institution:1.School of Computer Science,Jiaying University,Meizhou 514015,China; 2.Department of Information Engineering,Foshan Polytechnic,Foshan 528237,China)
Abstract:A moving object detection method is proposed by combining a Gaussian mixture model with the prewitt operator.The prewitt operator is employed to extract edge information and a Gaussian mixture model is employed to update the background.Color information and edge information are integrated for segmentation.The edge information,which reflects area information,can compensate color information' flaw in segmentation.The method improves the abilities of convergence and stability,and also decreases commission error brought by the method only using color information.Experimental results indicate that the proposed method is superior to the traditional Gaussian mixture model.
Keywords:Gaussian mixture model  prewitt operator  object detection
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号