Computer Science ›› 2024, Vol. 51 ›› Issue (6A): 230600081-7.doi: 10.11896/jsjkx.230600081

• Image Processing & Multimedia Technolog • Previous Articles     Next Articles

MCC-based Back-end Optimization Method and Its Application in ORB-SLAM2

WANG Ting, CHENG Lan, XU Xinying, YAN Gaowei, REN Mifeng, ZHANG Zhe   

  1. College of Electrical and Power Engineering,Taiyuan University of Technology,Taiyuan 030024,China
  • Published:2024-06-06
  • About author:WANG Ting,born in 1998,postgra-duate.Her main research interests include VSLAM and back-end optimization.
    CHENG Lan,born in 1984,Ph.D,associate professor.Her main research interests include navigation system high-precision positioning and robot cooperative visual localization and mapping.
  • Supported by:
    National Natural Science Foundation of China(62073232,61973226) and Foundation for Scientific Cooperation and Exchanges of Shanxi Province(202104041101030).

Abstract: Autonomous localization and environment awareness are prerequisites for robots to achieve complex tasks,and vision simultaneous localization and mapping(VSLAM) technology is an effective solution.In VSLAM,sensor errors and environmental noise,etc.,affect the localization and mapping accuracy,resulting in cumulative errors.Back-end optimization plays a key role in eliminating the accumulated error in VSLAM.Existing back-end optimization algorithms are usually premised on Gaussian noise and belong to the back-end algorithms as per the MSE standard.However,due to the non-convex nature of images and non-Gaussian noise generated in real scenes,the Gaussian noise assumption does not always valid,leading to performance degradation of existing algorithms when running in real scenes.In view of this,a back-end optimization method based on the MCC criterion is proposed by taking advantage of the maximum correlation entropy(MCC) criterion in dealing with non-Gaussian noise,and the proposed method is applied to the ORB-SLAM2 framework to test the performance of the proposed method in terms of localization and image building accuracy.Finally,experiments are conducted on EuRoC and KITTI public datasets,and the experimental results show that the proposed method outperforms the Huber-based back-end optimization algorithm as well as the Cauchy-based back-end optimization algorithm in the original ORB-SLAM2 for the majority of sequences,both indoor and outdoor.

Key words: VSLAM, Back-end optimization, MCC, non-Gaussian noise

CLC Number: 

  • TP242
[1]SUMIKURA S,SHIBUYA M,SAKURADA K.Openvslam:A versatile visual slam framework[C]//Proceedings of the 27th ACM International Conference on Multimedia,2019:2292-2295.
[2]CONCHA A,CIVERA J.An evaluation of robust cost functions for RGB direct mapping[C]//European Conference on Mobile Robots.IEEE,2015:1-8.
[3]LIU W,POKHAREL P P,PRINCIPE J C.Correntropy:A localized similarity measure[C]//The 2006 IEEE International Joint Conference on Neural Network Proceedings.IEEE,2006:4919-4924.
[4]CHEN B,XING L,LIANG J,et al.Steady-state mean-square error analysis for adaptive filtering under the maximum correntropy criterion[J].IEEE signal Processing Letters,2014,21(7):880-884.
[5]BARRON J T.A general and adaptive robust loss function[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:4331-4339.
[6]WILSON A M,PANIGRAHI T,MISHRA B P,et al.Adaptive Geman-McClure Estimator for Robust Distributed Channel Estimation[J].IEEE Access,2021(99):1-1.
[7]PRINCIPEJ C.Information Theoretic Learning:Renyi’s Entropy and Kernel Perspectives[M].Springer Publishing Company,Incorporated,2010.
[8]CHENG L,WANG K,REN M,et al.Adaptive Filter Approach for GPS Multipath Estimation Under Correntropy Criterion in Dynamic Multipath Environment[J].IEEE Transactions on Signal Processing,2019,67(22):5798-5810.
[9]CHENG L,WANG K,REN M,et al.Comprehensive Analysisof Multipath Estimation Algorithms in the Framework of Information Theoretic Learning[J].IEEE Access,2018(99):1-1.
[10]SUN Q N.Research on the Back-end of SLAM Based on Maximum Correntropy Criterion Filtering[D].Chongqing:Southwest University,2021.
[11]LOURAKISM.SBA:A software package for generic sparsebundle adjustment[J].Acm Trans.math.softw,2009,36:1-30.
[12]ARRA,Á,CHIN T J,ERIKSSON A,et al.Visual SLAM:Why Bundle Adjust?[C]//International Conference on Robotics and Automation(ICRA).IEEE,2019:2385-2391.
[13]MACTAVISH K,BARFOOT T D.At all Costs:A Comparison of Robust Cost Functions for Camera Correspondence Outliers[C]//Conference on Computer & Robot Vision.IEEE ComputerSociety,2015:62-69.
[14]MORÉ J J.The levenberg-marquardt algorithm:implementation and theory,in:Numerical Analysis[C]//Proceedings of the Biennial Conference Held at Dundee.Springer,2006:105-116.
[15]KAUTSKY J,GOLUB G.On the calculation of jacobi matrices[J].Linear Algebra and Its Applications,1983,52:439-455.
[16]MARTÍNEZ J M.Algorithms for solving nonlinear systems of equations[J].Algorithms for continuous optimization:the state of the art,1994,434:81-108.
[17]BURRI M,NIKOLIC J,GOHL P,et al.The EuRoC micro aerial vehicle datasets[J].International Journal of Robotics Research,2016,35(10):1157-1163.
[18]GEIGER A,LENZ P,STILLERC,et al.Vision meets robotics:The KITTI dataset[J].International Journal of Robotics Research,2013,32(11):1231-1237.
[19]MUR-ARTAL R,TARDÓS J D.ORB-SLAM2:An Open-Source SLAM System for Monocular,Stereo,and RGB-D Cameras[J].IEEE Transactions on Robotics,2017,33:1255-1262.
[20]KUMMERLE R,GRISETTI G,STRASDAT H,et al.G2o:A general framework for graph optimization[C]//IEEE International Conference on Robotics & Automation.IEEE,2011,3607-3613.
[1] SHAO Zeng-zhen,WANG Hong-guo,LIU Hong,CHENG Zhao-qianu,YIN Hui-juan. Sequential Evolutionary Game Simulation Characterized by Learning and Emotion [J]. Computer Science, 2011, 38(8): 197-200.
[2] . [J]. Computer Science, 2006, 33(6): 267-269.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!