| 基于单目视觉的移动机器人全局定位 |
| |
| 引用本文： | 厉茂海,洪炳镕,罗荣华,蔡则苏.基于单目视觉的移动机器人全局定位[J].机器人,2007,29(2):140-144. |
| |
| 作者姓名： | 厉茂海 洪炳镕 罗荣华 蔡则苏 |
| |
| 作者单位： | 1. 哈尔滨工业大学计算机科学与技术学院,黑龙江,哈尔滨,150001
2. 华南理工大学计算机科学与工程学院,广东,广州,510640 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划)
,
国家自然科学基金 |
| |
| 摘 要： | 提出在基于单目视觉创建的环境地图中实现移动机器人全局定位．基于KD树的最近邻搜索实现特征匹配．应用尺度不变特征变换(SIFT)方法提取特征,并用多维向量描述,保证了对图像光强变化、尺度缩放、三维视角和噪声具有不变性．提出了一种基于RANSAC的鲁棒定位方法．在实际室内环境Pioneer3机器人上进行的实验表明本文提出方法高效、可靠．
|
| 关 键 词： | 移动机器人 全局定位 KD树 特征提取 RANSAC 单目视觉 |
| 文章编号： | 1002-0446（2007）02-0140-05 |
| 修稿时间： | 2006-04-21 |
Monocular-Vision-Based Mobile Robot Global Localization |
| |
| LI Mao-hai,HONG Bing-rong,LUO Rong-hua,CAI Ze-su.Monocular-Vision-Based Mobile Robot Global Localization[J].Robot,2007,29(2):140-144. |
| |
| Authors: | LI Mao-hai HONG Bing-rong LUO Rong-hua CAI Ze-su |
| |
| Affiliation: | 1. School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China; 2. School of Computer Science and Engineering, South China University of Technology, Guangzhou 510640, China |
| |
| Abstract: | An environmental map built with monocular vision is used to implement mobile robot global localization.The feature matching is implemented with the KD-treebased nearest search approach.The features are extracted with Scale Invariant Feature Transform(SIFT),and discribed with highly distinctive multi-dimensional vector,making features be invariant to changes in illumination,scale,3D viewpoint and noise.A robust localization based on RANSAC(RANdom SAmple Consensus) approach is presented.Experiments on robot Pioneer 3 with monocular CCD camera in our real indoor environment show that our method is of high precision and stability. |
| |
| Keywords: | mobile robot global localization KD-tree feature extraction RANSAC(RANdom SAmple Consensus) monocular vision |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《机器人》浏览原始摘要信息 |
|
点击此处可从《机器人》下载全文 |
|
