| 基于C-V模型的运动目标水平集提取方法 |
| |
| 引用本文： | 杨莉,张荣国,胡静,刘焜.基于C-V模型的运动目标水平集提取方法[J].太原科技大学学报,2012,33(4):254-258. |
| |
| 作者姓名： | 杨莉 张荣国 胡静 刘焜 |
| |
| 作者单位： | 1. 太原科技大学计算机科学与技术学院,太原,030024
2. 合肥工业大学机械与汽车工程学院,合肥,230009 |
| |
| 基金项目： | 国家自然科学基金(51075113);山西省教育厅科技开发项目(20111024) |
| |
| 摘 要： | 针对视频图像中的运动目标检测问题,提出了一种基于C-V模型的运动目标水平集提取新方法：使用改进的帧间差分法对运动区域进行初始检测,通过相邻视频帧的相减,选用自适应阈值判断出当前视频帧中的运动目标像素;经形态学处理后通过定义最小化能量函数构建运动目标轮廓提取的水平集C-V模型,实现运动目标轮廓的提取。实验结果表明,本文所提方法的边缘准确率和检出率更高,能够更有效地提取运动目标。
|
| 关 键 词： | 运动目标提取 帧间差分 自适应阈值 水平集 C-V模型 |
A Motion Object Extraction Algorithm Based on Level Set C-V Model |
| |
| YANG Li,ZHANG Rong-guo,HU Jing,LIU.A Motion Object Extraction Algorithm Based on Level Set C-V Model[J].Journal of Taiyuan University of Science and Technology,2012,33(4):254-258. |
| |
| Authors: | YANG Li ZHANG Rong-guo HU Jing LIU |
| |
| Institution: | Kun2(1.School of Computer Science and Technology,Taiyuan University of Science & Technology,Taiyuan 030024,China;2.School of Mechanical and Automotive Engineering,Hefei University of Technology,Hefei 230009,China) |
| |
| Abstract: | Aimed at the motion object detection problem in video sequence,a novel approach for motion object extracting algorithm was presented based on level set C-V model.The improved frame difference algorithm was used for dealing with the problem of initial motion object detection,and adjacent moving object pixels in current image were detected through self-adaptive threshold and adjacent video frame subtracting technique.After being processed by morphology,the level set C-V model of extracting the moving object was constructed by defining the minimum energy function to realize the extraction of motion object contour.Experimental results show that the proposed approach for extracting moving object,whose edge and detecting accuracy rate are more powerful,can effectively extract the moving object. |
| |
| Keywords: | motion object extraction frame difference self-adaptive threshold level set C-V model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
