[1]董蕊芳,柳长安,杨国田.一种基于改进TF-IDF的SLAM回环检测算法[J].东南大学学报(自然科学版),2019,49(2):251-258.[doi:10.3969/j.issn.1001-0505.2019.02.008]
 Dong Ruifang,Liu Changan,Yang Guotian.TF-IDF based loop closure detection algorithm for SLAM[J].Journal of Southeast University (Natural Science Edition),2019,49(2):251-258.[doi:10.3969/j.issn.1001-0505.2019.02.008]
点击复制

一种基于改进TF-IDF的SLAM回环检测算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
49
期数:
2019年第2期
页码:
251-258
栏目:
自动化
出版日期:
2019-03-20

文章信息/Info

Title:
TF-IDF based loop closure detection algorithm for SLAM
作者:
董蕊芳柳长安杨国田
华北电力大学控制与计算机工程学院, 北京 102206
Author(s):
Dong Ruifang Liu Chang’an Yang Guotian
School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
关键词:
SLAM 回环检测 人造建筑场景 二进制LBD 改进的TF-IDF方法
Keywords:
simultaneous localization and mapping(SLAM) loop closure detection man-made environment binary line band descriptor(LBD) term frequency & inverse document frequency(TF-IDF)method
分类号:
TP242
DOI:
10.3969/j.issn.1001-0505.2019.02.008
摘要:
提出了一种基于改进TF-IDF的视觉SLAM回环检测算法,用于检测曾经访问过的位置,来消除定位过程中的累积误差.首先,针对在人造建筑场景中使用SLAM算法对图像点特征进行计算容易导致检测失败的问题,采用图像中的直线作为特征来进行回环检测的计算.其次,在LBD(line band descriptor)图像线特征描述子的基础上进一步提取了二进制LBD描述子来进行视觉词典的构建,保证了线特征的处理效率.提出了一种改进的TF-IDF(term frequency & inverse document frequency)单词权重确定方法,提高了视觉单词评分之间的区分度.最后,以室内建筑环境和输电线路场景为例进行实验,结果显示,所提出的基于线特征的回环检测算法比基于点特征的算法有较高的检测准确率,有助于提高SLAM算法的计算性能.
Abstract:
A term frequency & inverse document frequency(TF-IDF)based loop closure detection algorithm for vision-based simultaneous localization and mapping(SLAM)was presented. The algorithm could detect the revisited places of the robot to eliminate the accumulated error during localization. Firstly, line features were used to detect the loop closure in the man-made environment, which is due to the point features could lead to a failure of SLAM. Secondly, the binary line band descriptor(LBD)was constructed based on LBD to build the vision dictionary, improving the efficiency of processing line features. Thirdly, a variant of TF-IDF was proposed to enhance the word discrimination. Finally, the experiments were carried out on indoor scene and transmission line scene.Experimental results show that the line-based algorithm outperforms point-based algorithm on the detection rate. It can help in ensuring the proformance of the SLAM computation.

参考文献/References:

[1] Gao X, Zhang T. Unsupervised learning to detect loops using deep neural networks for visual SLAM system[J]. Autonomous Robots, 2017, 41(1): 1-18. DOI:10.1007/s10514-015-9516-2.
[2] Ho K L, Newman P. Detecting loop closure with scene sequences[J]. International Journal of Computer Vision, 2007, 74(3): 261-286. DOI:10.1007/s11263-006-0020-1.
[3] Beeson P, Modayil J, Kuipers B. Factoring the mapping problem: Mobile robot map-building in the hybrid spatial semantic hierarchy[J]. The International Journal of Robotics Research, 2010, 29(4): 428-459. DOI:10.1177/0278364909100586.
[4] Cummins M, Newman P. Appearance-only SLAM at large scale with FAB-MAP 2.0[J]. The International Journal of Robotics Research, 2011, 30(9): 1100-1123. DOI:10.1177/0278364910385483.
[5] Siam S M, Zhang H. Fast-SeqSLAM: A fast appearance based place recognition algorithm[C]//2017 IEEE International Conference on Robotics and Automation(ICRA). Singapore, 2017: 5702-5708. DOI:10.1109/ICRA.2017.7989671.
[6] Latif Y, Cadena C, Neira J. Robust loop closing over time for pose graph SLAM[J]. The International Journal of Robotics Research, 2013, 32(14): 1611-1626. DOI:10.1177/0278364913498910.
[7] Labbe M, Michaud F. Appearance-based loop closure detection for online large-scale and long-term operation[J]. IEEE Transactions on Robotics, 2013, 29(3): 734-745. DOI:10.1109/tro.2013.2242375.
[8] Galvez-Lopez D, Tardos J D. Bags of binary words for fast place recognition in image sequences[J]. IEEE Transactions on Robotics, 2012, 28(5): 1188-1197. DOI:10.1109/tro.2012.2197158.
[9] Nister D, Stewenius H. Scalable recognition with a vocabulary tree[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’06), New York, NY, USA, 2006: 2161-2168. DOI:10.1109/CVPR.2006.264.
[10] Angeli A, Filliat D, Doncieux S, et al. Fast and incremental method for loop-closure detection using bags of visual words[J]. IEEE Transactions on Robotics, 2008, 24(5): 1027-1037. DOI:10.1109/tro.2008.2004514.
[11] Lee j H, Zhang G, Lim J, et al. Place recognition using straight lines for vision-based SLAM [C]// IEEE International Conference on Robotics and Automation(ICRA). Karlsruhe, Germany, 2013: 3799-3806.
[12] Zhang L L, Koch R. An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency[J]. Journal of Visual Communication and Image Representation, 2013, 24(7): 794-805. DOI:10.1016/j.jvcir.2013.05.006.
[13] von GioiR G, Jakubowicz J, Morel J M, et al. LSD: a line segment detector[J]. Image Processing on Line, 2012, 2: 35-55. DOI:10.5201/ipol.2012.gjmr-lsd.
[14] Zhang G, Lee J H, Lim J, et al. Building a 3-D line-based map using stereo SLAM[J].IEEE Transactions on Robotics, 2015, 31(6):1364-1377. DOI: 10.1109/TRO.2015.2489498.
[15] Murphy L, Morris T, Fabrizi U, et al. Experimental comparison of odometry approaches[J]. Springer Tracts in Advanced Robotics, 2013, 88:877-890. DOI: 10.1007/978-3-319-00065-7_58.
[16] Liu C A, Dong R F, Wu H, et al. A 3D laboratory test-platform for overhead power line inspection[J]. International Journal of Advanced Robotic Systems, 2016, 13(2): 72. DOI:10.5772/62800.

备注/Memo

备注/Memo:
收稿日期: 2018-09-27.
作者简介: 董蕊芳(1989—),女,博士生;柳长安(联系人),男,博士,教授,博士生导师,liuchangan@ncepu.edu.cn.
基金项目: 国家自然科学基金资助项目(61105083)、中央高校基本科研业务费专项资金资助项目(2018ZD06).
引用本文: 董蕊芳,柳长安,杨国田.一种基于改进TF-IDF的SLAM回环检测算法[J].东南大学学报(自然科学版),2019,49(2):251-258. DOI:10.3969/j.issn.1001-0505.2019.02.008.
更新日期/Last Update: 2019-03-20