| 一种基于奇异点检测的光流场去噪方法 |
| |
| 引用本文： | 聂烜,吴成富,陈怀民.一种基于奇异点检测的光流场去噪方法[J].计算机工程,2009,35(5):207-208. |
| |
| 作者姓名： | 聂烜 吴成富 陈怀民 |
| |
| 作者单位： | 1. 西北工业大学软件与微电子学院,西安,710072
2. 西北工业大学无人机特种技术国家重点实验室,西安,710065 |
| |
| 摘 要： | 针对各种滤波方法对光流场进行去噪处理时会造成目标运动矢量改变的不足，提出一种基于奇异点检测的光流场去噪方法，利用表征信号奇异点特征的Lip指数建立噪声矢量判定准则，可以在目标无损的情况下检测出光流场噪声并消除。实验证明该方法能较好地消除噪声，同时不会造成目标运动矢量的损失。
|
| 关 键 词： | 图像序列 运动矢量 光流场 奇异点检测 |
| 修稿时间： | |
Noise-eliminating Method in Optical Flow Field Based on Singularity Detection |
| |
| NIE Xuan,WU Cheng-fu,CHEN Huai-min.Noise-eliminating Method in Optical Flow Field Based on Singularity Detection[J].Computer Engineering,2009,35(5):207-208. |
| |
| Authors: | NIE Xuan WU Cheng-fu CHEN Huai-min |
| |
| Affiliation: | 1.College of Software and Microelectronics;Northwestern Polytechnical University;Xi'an 710072;2.National Key Laboratory of UAV Special Technology;Xi'an 710065 |
| |
| Abstract: | Conventional filtering methodologies may lead to insufficient changes of objective motion vector when it is used in noise-elimination. This paper proposes a novel noise-eliminating method in motion field based on singularity detection.It utilizes the Lip exponent to provide signal's singularity characteristics and establish noise-vector judgment principle,which can eliminate the noise without lossing of the object.Experimental results demonstrate that it is able to eliminate noise perfectly without loss of ... |
| |
| Keywords: | image sequence motion vector optical flow field singularity detection |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程》浏览原始摘要信息 |
|
点击此处可从《计算机工程》下载全文 |
