| 改进SIFT用于全景视觉移动机器人定位 |
| |
| 引用本文： | 夏桂华,王博,朱齐丹.改进SIFT用于全景视觉移动机器人定位[J].计算机工程与应用,2010,46(18):196-198. |
| |
| 作者姓名： | 夏桂华 王博 朱齐丹 |
| |
| 作者单位： | 哈尔滨工程大学,自动化学院,哈尔滨,150001 |
| |
| 基金项目： | 国家自然科学基金，国家211工程项目，哈尔滨工程大学校基金 |
| |
| 摘 要： | 经典SIFT算法的计算量比较巨大，在应用到图像匹配中，尤其是多地图检索的图像匹配定位中时不能满足系统实时性的要求。可用于全景视觉传感器图像的改进SIFT算法，在不改变原算法匹配稳定性的基础上，通过修改原算法的采样规则，同时针对对复杂和简单两种情况下的图像采用不同的采样方式，使系统基本可以达到实时的效果。结果表明，改进算法可以实现高效、准确的定位。
|
| 关 键 词： | 尺度不变特征变换 特征提取 图像匹配 全景视觉 定位 |
| 收稿时间： | 2009-3-3 |
| 修稿时间： | 2009-5-11
|
Modified SIFT for localization of omnidirectional vision robot |
| |
| XIA Gui-hua,WANG Bo,ZHU Qi-dan.Modified SIFT for localization of omnidirectional vision robot[J].Computer Engineering and Applications,2010,46(18):196-198. |
| |
| Authors: | XIA Gui-hua WANG Bo ZHU Qi-dan |
| |
| Affiliation: | College of Automation,Harbin Engineering University,Harbin 150001,China |
| |
| Abstract: | Huge time are needed in feature extraction and matching with classical SIFT in image matching as well as in image retrieval,and a real-time system can not be built when mobile robot located itself with classical SIFT.A modified SIFT is proposed by changing the cycle sequence of sample pickup and setting two different modes on feature pickup.This modified SIFT can be used in omnidirectional vison images.Invariances to image translation,scaling,rotation are kept.A new real-time location system is built with modified SIFT.Examples are presented that this modified SIFT algorithm can realize the localization effectively and stably. |
| |
| Keywords: | Scale Invariant Feature Transform（SIFT） feature extraction image matching omnidirectional vision localization |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
