|
|||||
|
|
| 一种改进的Lucas—Kanade光流估计方法 | |
| 引用本文： | 张永亮,卢焕章,高劼,刘晓春.一种改进的Lucas—Kanade光流估计方法[J].海军航空工程学院学报,2009,24(4):443-446,452. |
| 作者姓名： | 张永亮 卢焕章 高劼 刘晓春 |
| 作者单位： | 1. 国防科学技术大学,ATR实验室,长沙,410073 2. 海军航空工程学院,科研部,山东,烟台,264001 3. 海军航空工程学院,管理系,山东,烟台,264001 |
| 基金项目： | 国家863高技术研究发展计划资助项目 |
| 摘 要： | Lucas—Kanade算法是一种重要的光流估计技术，在计算机视觉领域有广泛的应用。但对于图像纹理欠丰富的区域，Lucas—Kanade算法光流估计结果较差。文章提出了一种改进的Lucas—Kanade算法：首先，计算跟踪置信度因子；然后，通过阈值检测剔除不可靠的光流估计结果；最后，进行邻域填充。该方法改善了纹理欠丰富区域的光流估计，对矮人模型图像序列进行了实验，证明了方法的有效性及优于Poelman方法和Chiba方法。 |
| 关 键 词： | Lilcas—Kanade方法 跟踪置信度因子 光流 运动估计 |
Improvement of Lucas-Kanade Method for Optical Flow Estimation |
|
| ZHANG Yong-liang,LU Huan-zhang,GAO Jie,LIU Xiao-chun.Improvement of Lucas-Kanade Method for Optical Flow Estimation[J].Journal of Naval Aeronautical Engineering Institute,2009,24(4):443-446,452. | |
| Authors: | ZHANG Yong-liang LU Huan-zhang GAO Jie LIU Xiao-chun |
| Affiliation: | 1. ATR Lab, National University of Defense Technology, Changsha 410073, China; 2. Naval Aeronautical and Astronautical University a. Department of Scientific Research; b. Department of Management, Yantai Shandong 264001, China) |
| Abstract: | The Lucas-Kanade method is one of the best optical flow estimation techniques, because it is fast and simple to implement. But a big problem of it is that many regions of typical real images do not contain sufficient texture to produce reliable optical flow estimation. An improvement of Lucas-Kanade method was proposed to remedy the problem, which used tracking confidence to threshold the estimation of any resolution level and recomputed the optical flow by their neighboring regions. Experiments using image sequences of dwarf model showed that our method was effective and better than Poelman＇s and Chiba＇s method. |
| Keywords: | Lucas-Kanade method texture confidence optical flow motion estimation |
| 本文献已被 维普 万方数据 等数据库收录！ | |
