morinson 发表于 2017-9-3 12:23:53

基于SURF和ORB全局特征的快速闭环检测

基于SURF和ORB全局特征的快速闭环检测








基于SURF和ORB全局特征的快速闭环检测
刘国忠1, 胡钊政1,2
1. 河北工业大学电子信息工程学院,天津 300401;
2. 武汉理工大学智能交通系统研究中心,湖北 武汉 430063

Fast Loop Closure Detection Based on Holistic Features from SURF and ORB
LIU Guozhong1, HU Zhaozheng1,2
1. School of Information Engineering, Hebei University of Technology, Tianjin 300401, China;
2. ITS Research Center, Wuhan University of Technology, Wuhan 430063, China







全文: PDF (789 KB)   HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要 针对移动机器人SLAM(同时定位与地图创建)中的闭环检测问题,提出了一种基于SURF(加速鲁棒特征)和ORB(oriented FAST and rotated BRIEF)全局特征的快速闭环检测算法.首先利用SURF与ORB分别提取查询图像的全局特征,实现对图像的特征表征.在特征提取过程中,对查询图像进行归一化操作,并将归一化的图像中心直接作为SURF与ORB的特征点位置,从而避免了耗时的特征点定位过程.然后将归一化的图像直接作为特征点的邻域区域,把计算的SURF与ORB局部特征描述符作为图像的全局特征.为了融合SURF与ORB全局特征实现查询图像的位置识别,提出了H-KNN(混合K最近邻)的改进算法:WH-KNN(加权混合K最近邻).最后通过跟踪模型实现闭环检测,其核心思想是利用之前闭环检测的结果预测查询图像在地图图像中的位置范围.实验中分别使用采集数据集和牛津大学公开数据集对本文算法进行了验证,同时与传统的BOW(词袋)算法进行了对比.本文算法在两种数据集上分别达到了94.3%和94.5%的准确率,并且查询图像位置识别与全局特征提取的平均时间不到3ms.其准确性及计算速度都超过了BOW算法,可以准确快速地实现实时闭环检测.

关键词 : 同时定位与地图创建,闭环检测,机器人,全局特征,跟踪模型   
Abstract:A fast loop closure detection algorithm based on holistic features from SURF (speeded-up robust feature) and ORB (oriented FAST and rotated BRIEF) is proposed for the loop closure detection problem in mobile robot SLAM (simultaneous localization and mapping). Firstly, holistic features of a query image are extracted for feature representation by using SURF and ORB. The query image is normalized and its center is directly set as the feature point position of SURF and ORB in the process of extracting holistic features, so that the time-consuming step of feature point localization is avoided. Afterwards, the normalized image is directly used as the patch of the feature point. The local feature descriptors computed from SURF and ORB are then used as the holistic features of the image. In order to fuse the holistic features from SURF and ORB for image matching, an improved method of H-KNN (hybrid K-nearest neighbor) called WH-KNN (weighted hybrid K-nearest neighbor) is also proposed. Finally, loop closure detection is finished by a tracking model. The core idea behind the model is to utilize the previous loop closure detection results to predict the position of the query image in the map. In the experiments, the proposed algorithm is not only tested with the collected datasets and the public datasets of Oxford University, but also compared with the classic BOW (Bag of Words) algorithm. It can achieve 94.3% and 94.5% detection accuracy on these two datasets, respectively. In average, it takes less than 3 ms to match each query image and extract holistic features. The test results demonstrate that the proposed algorithm outperforms the BOW method both in term of detection accuracy and computation efficiency. Therefore, the algorithm is accurate and fast enough for real-time loop closure detection.
Key words: simultaneous localization and mapping         loop closure detection         robot         holistic feature         tracking model
收稿日期: 2016-07-04      出版日期: 2016-12-26

1:TP242

基金资助:国家自然科学基金(51679181,51208168);河北省普通高等院校青年拔尖人才计划(BJ2014-013);湖北省技术创新专项重大项目(2016AAA007);湖北省自然科学基金(2015CFB252)
通讯作者: 胡钊政,zhaozheng.hu@gmail.com    E-mail: zhaozheng.hu@gmail.com
作者简介: 刘国忠(1990-),男,硕士生.研究领域:移动机器人SLAM,模式识别,计算机视觉.
胡钊政(1979-),男,博士,教授.研究领域:3D计算机视觉理论与应用,视觉与激光SLAM定位,智能交通系统等.

引用本文:   
刘国忠, 胡钊政. 基于SURF和ORB全局特征的快速闭环检测. 机器人, 2017, 39(1): 36-45.      
LIU Guozhong, HU Zhaozheng. Fast Loop Closure Detection Based on Holistic Features from SURF and ORB. ROBOT, 2017, 39(1): 36-45.



链接本文:
http://robot.sia.cn/CN/10.13973/j.cnki.robot.2017.0036    或   http://robot.sia.cn/CN/Y2017/V39/I1/36





页: [1]
查看完整版本: 基于SURF和ORB全局特征的快速闭环检测