A Robust Gaussian Mixture Model for Mobile Robots’ Vision-based Pose Estimation

doi:10.11947/j.JGGS.2019.0308

Abstract

Abstract:

In dynamic environments, the moving landmarks can make the accuracy of traditional vision-based pose estimation worse or even failure. To solve this problem, a robust Gaussian mixture model for vision-based pose estimation is proposed. The motion index is added to the traditional graph-based vision-based pose estimation model to describe landmarks’ moving probability, transforming the classic Gaussian model to Gaussian mixture model, which can reduce the influence of moving landmarks for optimization results. To improve the algorithm’s robustness to noise, the covariance inflation model is employed in residual equations. The expectation maximization method for solving the Gaussian mixture problem is derived in detail, transforming the problem into classic iterative least square problem. Experimental results demonstrate that in dynamic environments, the proposed method outperforms the traditional method both in absolute accuracy and relative accuracy, while maintains high accuracy in static environments. The proposed method can effectively reduce the influence of the moving landmarks in dynamic environments, which is more suitable for the autonomous localization of mobile robots.

Key words: vision-based navigation; graph optimization; pose estimation; covariance inflation; expectation maximization

Chuanqi CHENG,Xiangyang HAO,Jiansheng LI,Peng HU,Xu ZHANG. A Robust Gaussian Mixture Model for Mobile Robots’ Vision-based Pose Estimation[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(3): 79-90.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Tab.1

Fig.6

Fig.7

Fig.8

Fig.9

References 25

[1]	PERSSON M, PICCINI T, FELSBERG M , et al. Robust Stereo Visual Odometry from Monocular Techniques [C]//Proceedings of 2015 IEEE Intelligent Vehicles Symposium. Seoul: IEEE, 2015: 686-691.
[2]	HUANG Nannan, LIU Guixi, ZHANG Yinzhe , et al. Unmanned Aerial Vehicle Vision Navigation Algorithm[J]. Infrared and Laser Engineering, 2016,45(7):269-277.
[3]	WU Meiqing, LAM S K, SRIKANTHAN T . A Framework for Fast and Robust Visual Odometry[J]. IEEE Transactions on Intelligent Transportation Systems, 2017,18(12):3433-3448.DOI: 10.1109/TITS.2017.2685433
[4]	QU Xiaozhi, SOHEILIAN B, PAPARODITIS N . Landmark Based Localization in Urban Environment[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018,140:90-103.DOI: 10.1016/j.isprsjprs.2017.09.010.
[5]	CHEN Ruizhi, CHEN Liang . Indoor Positioning with Smartphones:The State-of-the-art and the Challenges[J]. Acta Geodaetica et Cartographica Sinica, 2017,46(10):1316-1326.DOI: 10.11947/j.AGCS.2017.20170383.
[6]	STRASDAT H, DAVISON A J, MONTIEL J M M , et al. Double Window Optimisation for Constant Time Visual SLAM [C]//Proceedings of 2011 International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 2352-2359.
[7]	MUR-ARTAL , MONTIEL J M M, TARDÓS J D . ORB-SLAM:A Versatile and Accurate Monocular SLAM System[J]. IEEE Transactions on Robotics, 2015,31(5):1147-1163.DOI: 10.1109/TRO.2015.2463671.
[8]	CADENA C, CARLONE L, CARRILLO H , et al. Past, Present, and Future of Simultaneous Localization and Mapping:Toward the Robust-perception Age[J]. IEEE Transactions on Robotics, 2016,32(6):1309-1332. DOI: 10.1109/TRO.2016.2624754.
[9]	CARLONE L, KIRA Z, BEALL C , et al. Eliminating Conditionally Independent Sets in Factor Graphs: A Unifying Perspective Based on Smart Factors [C]//Proceedings of 2014 IEEE International Conference on Robotics and Automation. Hong Kong, China: IEEE, 2014: 4290-4297.
[10]	KAESS M, JOHANNSSON H, ROBERTS R , et al. iSAM2: Incremental Smoothing and Mapping with Fluid Relinearization and Incremental Variable Reordering [C]//Proceedings of 2011 IEEE International Conference on Robotics and Automation. Shanghai, China: IEEE, 2011: 3281-3288.
[11]	KVMMERLE R, GRISETTI G, STRASDAT H , et al. G²o: A General Framework for Graph Optimization [C]//Proceedings of 2011 IEEE International Conference on Robotics and Automation. Shanghai, China: IEEE, 2011: 3607-3613.
[12]	SONG Shiyu, CHANDRAKER M, GUEST C C . Parallel, Real-time Monocular Visual Odometry [C]//Proceedings of 2013 IEEE International Conference on Robotics and Automation. Karlsruhe, Germany: IEEE, 2013: 4698-4705.
[13]	ENGEL J, STVCKLER J, CREMERS D . Large-scale Direct SLAM with Stereo Cameras [C]//Proceedings of 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. Hamburg: IEEE, 2015.
[14]	LIU Haomin, ZHANG Guofeng, BAO Hujun . A Survey of Monocular Simultaneous Localization and Mapping[J]. Journal of Computer-aided Design and Computer Graphics, 2016,28(6):855-868. DOI: 10.3969/j.issn.1003-9775.2016.06.001.
[15]	CAO Tianyang, CAI Haoyuan, FANG Dongming , et al. Robot Vision System for Keyframe Global Map Establishment and Robot Localization Based on Graphic Content Matching[J]. Optics and Precision Engineering, 2017,25(8):2221-2232.
[16]	PERERA S, PASQUAL A . Towards Realtime Handheld Mono SLAM in Dynamic Environments [C]//Proceedings of the 7th International Symposium on Advances in Visual Computing. Las Vegas, NV: Springer, 2011: 313-324.
[17]	TAN Wei, LIU Haomin, DONG Zilong , et al. Robust Monocular SLAM in Dynamic Environments [C]//Proceedings of 2013 IEEE International Symposium on Mixed and Augmented Reality. Adelaide, SA, Australia: IEEE, 2013: 209-218.
[18]	WANG C C, THORPE C, THRUN S . Online Simultaneous Localization and Mapping with Detection and Tracking of Moving Objects: Theory and Results from a Ground Vehicle in Crowded Urban Areas [C]//Proceedings of 2003 IEEE International Conference on Robotics and Automation. Taipei, Taiwan, China: IEEE, 2003: 842-849.
[19]	HOCHDORFER S, NEUMANN H, SCHLEGEL C . Landmark Rating and Selection for SLAM in Dynamic Environments [C]//Proceedings of the 13th International Conference on Intelligent Autonomous Systems 13. Cham: Springer, 2014: 401-414.
[20]	AGARWAL P, TIPALDI G D, SPINELLO L , et al. Robust Map Optimization Using Dynamic Covariance Scaling [C]//Proceedings of 2013 IEEE International Conference on Robotics and Automation. Karlsruhe, Germany: IEEE, 2013: 62-69.
[21]	OLSON E, AGARWAL P . Inference on Networks of Mixtures for Robust Robot Mapping[J]. The International Journal of Robotics Research, 2013,32(7):826-840.DOI: 10.1177/0278364913479413.
[22]	SVNDERHAUF N, PROTZEL P . Switchable Constraints for Robust Pose Graph SLAM [C]//Proceedings of 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vilamoura, Portugal: IEEE, 2012: 1879-1884.
[23]	ROGERS J G, TREVOR A J B, NIETO-GRANDA C , et al. SLAM with Expectation Maximization for Moveable Object Tracking [C]//Proceedings of 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems. Taipei, Taiwan, China: IEEE, 2010: 2077-2082.
[24]	KAESS M, RANGANATHAN A, DELLAERT F . iSAM:Incremental Smoothing and Mapping[J]. IEEE Transactions on Robotics, 2008,24(6):1365-1378. DOI: 10.1109/TRO.2008.2006706.
[25]	GEIGER A, LENZ P, URTASUN R . Are We Ready for Autonomous Driving? The KITTI Vision Benchmark Suite [C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI: IEEE, 2012: 3354-3361.

No.	Traditional method					Proposed method
	Absolute errors/m			Relative errors			Absolute errors/m			Relative errors
	mean	median	RMSE	E_trans/(%)	E_rot(deg/m)		mean	median	RMSE	E_trans/(%)	E_rot(deg/m)
00	7.453	7.659	7.750	0.962	0.0035	8.816		9.288	9.305	0.8946	0.0033
01	52.699	47.095	62.484	1.7934	0.0027	17.759		16.927	20.307	1.3769	0.0017
02	15.204	12.818	16.237	0.837	0.0030	9.491		6.367	12.176	0.820	0.0031
03	4.090	4.192	4.218	0.668	0.0017	1.539		1.181	1.779	0.737	0.0018
04	7.641	7.513	7.770	1.090	0.0027	0.689		0.635	0.784	0.435	0.0019
05	3.068	3.300	3.564	0.555	0.0024	3.234		3.401	3.760	0.602	0.0024
06	2.744	2.644	2.948	0.702	0.0022	3.051		2.672	3.371	0.774	0.0023
07	2.660	2.680	3.201	0.888	0.0042	2.983		2.897	3.659	0.984	0.0047
08	11.110	11.224	11.372	1.1574	0.0037	10.153		10.552	10.427	1.0048	0.0030
09	6.450	6.713	7.397	0.902	0.0030	5.502		5.177	6.501	0.857	0.0023
10	4.942	3.936	6.039	0.678	0.0026	4.218		3.487	5.078	0.581	0.0020