视觉同步定位与地图重建—–基于先验信息的SIFT 匹配算法 Prior information constrained SIFT matching algorithm for visual<br /> simultaneous localization and mapping期刊界 All Journals 搜尽天下杂志传播学术成果专业期刊搜索期刊信息化学术搜索

视觉同步定位与地图重建—–基于先验信息的SIFT 匹配算法

引用本文：	孟旭炯,蒋荣欣,陈耀武.视觉同步定位与地图重建—–基于先验信息的SIFT 匹配算法[J].控制与决策,2011,26(6):911-915.

作者姓名：	孟旭炯蒋荣欣陈耀武

作者单位：	浙江大学数字技术及仪器研究所,杭州,310027

基金项目：	浙江省科技计划重大科技专项重点项目(2006C11200)

摘要：	鉴于尺度不变特征转换（SIFT）匹配算法存在计算效率不高且容易出现误匹配的问题，针对视觉同步定位与地图重建，提出了一种基于先验信息的SIFT匹配算法．该算法首先根据机器人和特征点的相对距离变化来预测尺度空间的变化；然后根据机器人和特征点的当前状态来预测特征点的图像位置；最后在预测的图像位置进行SIFT匹配．实验结果表明...
关键词：	视觉同步定位与地图重建特征匹配尺度空间扩展卡尔曼滤波
收稿时间：	2010/3/30 0:00:00
修稿时间：	2010/6/2 0:00:00
Prior information constrained SIFT matching algorithm for visual simultaneous localization and mapping

MENG Xu-jiong,JIANG Rong-xin,CHEN Yao-wu.Prior information constrained SIFT matching algorithm for visual simultaneous localization and mapping[J].Control and Decision,2011,26(6):911-915.

Authors:	MENG Xu-jiong JIANG Rong-xin CHEN Yao-wu

Affiliation:	(Institute of Advanced Digital Technologies and Instrumentation,Zhejiang University,Hangzhou 310027,China.

Abstract:	The scale invariant feature transform(SIFT) algorithm has the problem of computational inefficiency and mismatch. Therefor, a prior information constrained SIFT matching algorithm is proposed for the visual simultaneous localization and mapping(vSLAM) applications. Firstly, the scale space is predicted according to the relative distance from the robot to the feature. Then the feature position is estimated according to the state of both the robot and the feature. Finally, sift matching is conducted within the predicted image region. The experiment results show that the proposed algorithm can achieve better computational efficiency and matching performance.

Keywords:	visual simultaneous localization and mapping： feature matching~ scale space~ extended Kalman filter
本文献已被 CNKI 万方数据等数据库收录！
	点击此处可从《控制与决策》浏览原始摘要信息
	点击此处可从《控制与决策》下载全文

设为首页 | 免责声明 | 关于勤云 | 加入收藏