基于BA优化和KL散度的RGB-D SLAM系统

doi:10.12068/j.issn.1005-3026.2020.07.004

东北大学学报:自然科学版 ›› 2020, Vol. 41 ›› Issue (7): 933-937.DOI: 10.12068/j.issn.1005-3026.2020.07.004

基于BA优化和KL散度的RGB-D SLAM系统

徐岩，安卫凤

(天津大学电气自动化与信息工程学院，天津300072)

收稿日期:2019-05-24 修回日期:2019-05-24 出版日期:2020-07-15 发布日期:2020-07-15
通讯作者: 徐岩
作者简介:徐岩(1977-)，女，辽宁沈阳人，天津大学副教授.
基金资助:
国家自然科学基金资助项目(61632018)；青海省基础研究项目(2017-ZJ-753).

RGB-D SLAM System Based on BA Optimization and KL Divergence

XU Yan， AN Wei-feng

School of Electrical and Information Engineering， Tianjin University， Tianjin 300072， China.

Received:2019-05-24 Revised:2019-05-24 Online:2020-07-15 Published:2020-07-15
Contact: AN Wei-feng
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对深度相机采集深度图像的噪声对位姿估计精度的影响，以及误差随时间累积的严重问题，设计了一种改进的基于RGB-D相机的视觉SLAM系统.首先，建立重投影误差模型，通过最小化重投影误差，对位姿和特征点进行非线性优化.此外，提出了一种闭环检测的算法，建立字典模型，用频率-逆文档频率计算权重，用Kullback-Leibler散度计算相似度，并使用相对相似度机制检测闭环，减少了累积误差.使用15个公开的图像序列对算法进行评价，同3个流行的RGB-D SLAM系统对比，精度平均最高提高119.07%，最低提高4.24%.实验结果证明，提出的方法比目前流行的RGB-D SLAM系统具有更好的精度.

关键词: 机器视觉, 同时定位与建图, BA优化, KL散度, 闭环检测

Abstract: To reduce the impact of noise in depth image acquisition on the accuracy of pose estimation and to solve the serious problem of cumulative error over time， an improved RGB-D SLAM system was designed. Firstly， the re-projection error model was established to nonlinearly optimize the poses and features by minimizing the re-projection error. In addition， a closed-loop detection algorithm was proposed. The dictionary model was established and the frequency-inverse document frequency(TF-IDF) was used to calculate the weight. Kullback-Leibler divergence was used to calculate the similarity， and a relative similarity mechanism was used for the closed-loop detection. The cumulative error was decreased. The algorithm was evaluated using 15 public image sequences. Compared with three popular RGB-D SLAM systems， the maximum increase of accuracy is averagely 119.07% and the minimum increase is 4.24%. Experimental results show that the proposed method has better accuracy than the current popular RGB-D SLAM systems.

Key words: machine vision, simultaneous localization and mapping, BA optimization, KL divergence, closed-loop detection

中图分类号:

TP242.6

徐岩，安卫凤. 基于BA优化和KL散度的RGB-D SLAM系统[J]. 东北大学学报:自然科学版, 2020, 41(7): 933-937.

XU Yan， AN Wei-feng. RGB-D SLAM System Based on BA Optimization and KL Divergence[J]. Journal of Northeastern University Natural Science, 2020, 41(7): 933-937.

参考文献

[1]Reuter S，Dietmayer K，Vo B N，et al.The labeled multi-bernoulli filter［J］.IEEE Transactions on Signal Processing，2014，62(12):3246-3260.
[2]Mur-Artal R，Montiel J M M，Tard′os J D.ORB-SLAM:a versatile and accurate monocular SLAM system［J］.IEEE Transactions on Robotics，2015，31(5):1147-1163.
[3]Sujan V，Dubowsky S.Efficient information-based visual robotic mapping in unstructured environments［J］.International Journal of Robotics Research，2005，24(4):275-293.
[4]Janabi-Sharifi F，Marey M.A Kalman-filter-based method for pose estimation in visual servoing［J］.IEEE Transactions on Robotics，2010，26(5):939-947.
[5]Li S，Ni P.Square-root unscented Kalman filter based simultaneous localization and mapping［C］//IEEE International Conference on Information and Automation.Harbin，2010:2384-2388.
[6]Lee J S，Nam S Y，Chung G W K.Robust RBPF-SLAM for indoor mobile robots using sonar sensors in non-static environments［J］.Advanced Robotics，2011，25(9/10):1227-1248.
[7]Triggs B，McLauchlan P F，Hartlry R I，et al.Bundle adjustment a modern synthesis［C］//Vision Algorithms:Theory and Practice.New York，2000:298-372.
[8]Davison A J，Reid I D，Molton N D，et al.MonoSLAM:real-time single camera SLAM［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2007，29(6):1052-1067.
[9]Kim J，Yoon K J，Kim J S，et al.Visual SLAM by single-camera catadioptric stereo［C］//Proceedings of International Joint Conference on SICE-ICASE.Busan，2006:2005-2009.
[10]Han C，Xiang Z，Liu J，et al.Stereo vision based SLAM in outdoor environments［C］//Proceedings of IEEE International Conference on Robotics and Biomimetics.Sanya，2007:1653-1658.
[11]Paz L M，Pinies P，Tardos D，et al.Large-scale 6-DOF SLAM with stereo-in-hand［J］.IEEE Transactions on Robotics，2008，24(5):946-957.
[12]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.
[13]Engel J，Stückler J，Cremers D.Large-scale direct SLAM with stereo cameras［C］//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS).Hamburg，2015:1935-1942.
[14]Henry P，Krainin M，Herbst E，et al.RGB-D mapping:using depth cameras for dense 3D modeling of indoor environments［C］//Proceedings of International Symposium on Experimental Robotics(ISER).Delhi，2010:477-491 .
[15]Concha A，Civer J.RGBDTAM:a cost-effective and accurate RGB-D tracking and mapping system［C］//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems.Vancouver，2017:6756-6763.
[16]Whwlan T，Salas-Moreno R F，Glocker B，et al.ElasticFusion:real-time dense SLAM and light source estimation［J］.The International Journal of Robotics Research，2016，35(14):1697-1716.
[17]Jafari O H，Mitzel D，Leibe B.Fast ICP-SLAM for a bi-steerable mobile robot in large environments［C］//2015 International Conference on Advanced Robotics.Istanbul，2015:5636-5643.
[18]Endres F，Hess J，Sturm J，et al.3-D mapping with an RGB-D camera［J］.IEEE Transactions on Robotics，2014，30(1):177-187.
[19]Mur-Artal R，Montiel J M M，Tard′os J D.ORB-SLAM2:an open-source SLAM system for monocular，stereo and RGB-D cameras［J］.IEEE Transactions on Robotics，2017，33(5):1255-1262.
[20]Gavez-Lopez D，Tard′os J D.Bags of binary words for fast place recognition in image sequences［J］.IEEE Transactions on Robotics，2012，28(5):1188-1197.
[21]Robertso N，Stephe N.Understanding inverse document frequency:on theoretical arguments for IDF［J］.Journal of Documentation，2004，60(5):503-520.
[22]Chen J N，Matzinger H，Zhai H Y，et al.Centroid estimation based on symmetric KL divergence for multinomial text classification problem［C］//Proceedings of IEEE International Conference on Machine Learning and Applications.Orlando，2018:1174-1177.
[23]Dong Y，Yao K S，Su H，et al.KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition［C］//IEEE International Conference on Acoustics.Vancouver，2013:7893-7897.
[24]Anysha V，Meher S.Facial expression recognition using local binary patterns and Kullback-Leibler divergence［C］//Proceedings of IEEE International Conference on Communications and Signal Processing.Melmaruvathur，2015:349-353.
[25]Toru W，Yamashita Y.Affine-invariant recognition of handwritten characters via accelerated KL divergence minimization［C］//Proceedings of International Conference on Document Analysis & Recognition.Beijing，2011:1095-1099.
[26]Strasdat H，Montiel J M M，Davison A J.Scale drift-aware large scale monocular SLAM［C］//Proceedings of Robotics:Science and Systems.Zaragoza，2010:73-80.
[27]Sturm J，Englhard N，Endres F，et al.A benchmark for the evaluation of RGB-D SLAM systems［C］//Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems.Vilamoura，2012:573-580.
[15]关守平，房少纯.一种新型的区间-粒子群优化算法［J］.东北大学学报(自然科学版)，2012，33(10):1381-1384.(Guan Shou-ping，Fang Shao-chun.A new interval particle swarm optimization algorithm［J］.Journal of Northeastern University(Natural Science)，2012，33(10):1381-1384.)

基于BA优化和KL散度的RGB-D SLAM系统

RGB-D SLAM System Based on BA Optimization and KL Divergence

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	张德富，宋克臣，牛孟辉，颜云辉. 基于一维卷积的生产线冷态重轨表面缺陷快速检测[J]. 东北大学学报（自然科学版）, 2021, 42(2): 276-281.
[2]	刘宇，魏希来，王帅，戴丽. 基于深度学习的光纤收卷机器视觉自动检测技术[J]. 东北大学学报（自然科学版）, 2021, 42(1): 68-74.
[3]	张尧;刘伟嵬;邢芝涛;颜云辉;. 采用多分类器集成方法的带钢表面缺陷图像识别[J]. 东北大学学报(自然科学版), 2012, 33(2): 267-270.
[4]	王植;吴立新;孔祥勤;. 盲环境移动定位(Ⅰ):序列编码图形路标识别算法[J]. 东北大学学报(自然科学版), 2011, 32(5): 732-735.
[5]	郭阳;徐心和;. 交比不变量在机器视觉中的误差分析及应用[J]. 东北大学学报(自然科学版), 2007, 28(8): 1077-1080.