标志辅助的多特征融合定位算法

doi:10.3778/j.issn.1002-8331.2111-0316

摘要/Abstract

摘要： 单目同步定位与地图构建的精度依赖于图像中特征的提取与匹配算法，最终估算的轨迹常因其中误差的累积而有所偏移。针对此问题，提出一种标志辅助的多特征融合定位算法，结合标志所处的环境平面结构信息辅助定位。该算法使用点、标志、平面多个特征提高位姿估计的精度，标志特征提供更鲁棒的特征点，面特征以更少的参数表达更大的结构，减少遮挡对特征匹配的影响；且通过环境结构中的平面关系建立标志间关联，使标志在优化中更满足相互之间的几何位置关系，从而减少累积误差造成的漂移。实验结果表明，该算法可以有效地在含有标志的环境中定位相机，且在困难环境中能更好地校正回环，与同类方法相比，精度明显提升。

关键词: 同步定位与建图, 单目相机, 误差累积, 标志特征, 平面特征

Abstract: Monocular simultaneous localization and mapping accuracy relies on the feature extraction and association algorithm in image. The estimated trajectory will draft because of the error accumulation. Aiming at the problem, this paper proposes a marker-assisted multi-feature fusion localization algorithm, which combines the environment planar structure where the markers are located to assist localization. The algorithm uses point, marker and plane features to improve the accuracy of pose estimation. Marker feature provides more robust points. Plane feature uses fewer parameters to represent larger structure, reducing the impact of occlusion on feature matching. It establishes the relationships between markers by the planar structures, which can make markers more satisfy the geometric position relationship between each other in the optimization, thereby reducing the drift caused by the accumulated error. Experimental results show that the algorithm can effectively track in the environment containing markers, and can better correct the loop in difficult environments. Compared with similar methods, the accuracy is significantly improved.

Key words: simultaneous localization and mapping, monocular camera, error accumulation, marker feature, plane feature

刘嘉敏, 陈圣伦, 王智慧, 李豪杰. 标志辅助的多特征融合定位算法[J]. 计算机工程与应用, 2023, 59(6): 187-195.

LIU Jiamin, CHEN Shenglun, WANG Zhihui, LI Haojie. Marker-Assisted Multi-Feature Fusion Localization Method[J]. Computer Engineering and Applications, 2023, 59(6): 187-195.

参考文献

[1] 刘浩敏，章国锋，鲍虎军.基于单目视觉的同时定位与地图构建方法综述[J].计算机辅助设计与图形学学报，2016，28（6）：855-868.
LIU H M，ZHANG G F，BAO H J.A survey of monocular simultaneous localization and mapping[J].Journal of Computer-Aided Design & Computer Graphics，2016，28（6）：855-868.
[2] 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.
[3] KLEIN G，DAVID M.Parallel tracking and mapping for small AR workspaces[C]//6th IEEE and ACM International Symposium on Mixed and Augmented Reality.Nara，Japan：IEEE Press，2007：225-234.
[4] MUR-ARTAL R，TARDOS J D.ORB-SLAM2：an open-source SLAM system for monocular，stereo，and RGB-D cameras[J].IEEE Transactions on Robotics，2017，33（5）：1147-1163.
[5] PUMAROLA A，VAKHITOV A，AGUDO A，et al.PL-SLAM：real-time monocular visual SLAM with points and lines[C]//IEEE International Conference on Robotics & Automation.Singapore：IEEE Press，2017：4503-4508.
[6] ARNDT C，SABZEVARI R，CIVERA J.From points to planes-adding planar constraints to monocular SLAM factor graphs[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems（IROS）.Las Vegas，NV，USA：IEEE Press，2020：4917-4922.
[7] YANG S，SCHERER S.Monocular object and plane SLAM in structured environments[J].IEEE Robotics and Automation Letters，2019，4（4）：3145-3152.
[8] NEUNERT M，BLOESCH M，BUCHLI J.An open source，fiducial based，visual-inertial motion capture system[C]//19th International Conference on Information Fusion.Heidelberg，Germany：IEEE Press，2016：1523-1530.
[9] HE G，ZHONG S，GUO J.A lightweight and scalable visual-inertial motion capture system using fiducial markers[J].Autonomous Robots，2019，43（7）：1895-1915.
[10] MUNOZ-SALINAS R，MARIN-JIMENEZ M，MEDINA-CARNICER R.SPM-SLAM：simultaneous localization and mapping with squared planar markers[J].Pattern Recognition，2019，86：156-171.
[11] MUNOZ-SALINAS R，MEDINA-CARNICER R.UcoSLAM：simultaneous localization and mapping by fusion of keypoints and squared planar markers[J].Pattern Recognition，2020，101：107193.
[12] REKIMOTO J.Matrix：a realtime object identification and registration method for augmented reality[C]//Third Asian Pacific Computer and Human Interaction.Kangawa，Japan：IEEE Press，1998：63-69.
[13] KATO H，BILLINGHURST M.Marker tracking and HMD calibration for a video-based augmented reality conferencing system[C]//2nd IEEE and ACM International Workshop on Augmented Reality.San Francisco，CA，USA：IEEE Press，1999：85-94.
[14] OLSON E.AprilTag：a robust and flexible visual fiducial system[C]//Proceedings of the IEEE International Conference on Robotics and Automation.Shanghai，China：IEEE Press，2011：3400-3407.
[15] DEGOL J，BRETL T，HOIEM D.ChromaTag：a colored marker and fast detection algorithm[C]//International Conference on Computer Vision.Venice，Italy：IEEE Press，2017：1481-1490.
[16] GARRIDO-JURADO S，MUNOZ-SALINAS R，MADRID-CUEVAS F，et al.Generation of fiducial marker dictionaries using mixed integer linear programming[J].Pattern Recognition，2016，51：481-491.
[17] ROMERO-RAMIREZ F，MUNOZ-SALINAS R，MEDINA-CARNICER R.Speeded up detection of squared fiducial markers[J].Image and Vision Computing，2018，76：38-47.
[18] TANG F，WU Y.Efficient circle-based camera pose tracking free of PnP[EB/OL].[2019-08-13].http：//arxiv.org/abs/1907.10219.pdf.
[19] TANAKA H.Ultra-high-accuracy visual marker for indoor precise positioning[C]//International Conference on Robotics and Automation.Paris，France：IEEE Press，2020：2338-2343.
[20] SCHWEIGHOFER G，PINZ A.Robust pose estimation from a planar target[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2006，28：2024-2030.
[21] COLLINS T，BARTOLI A.Infinitesimal plane-based pose estimation[J].International Journal of Computer Vision，2014，109（3）：252-286.