以單眼視覺SLAM建立場景三維特徵地圖輔助相機定位之定位精度與適應性分析

Feasibility and Accuracy Analysis of Camera Localization Aided by a 3D Feature Map Established by Monocular Visual SLAM

林緯程(Wei-Cheng Lin) ； 饒見有(Jiann-Yeou Rau)

《航測及遙測學刊》 27卷1期 (2022/03) Pp. 29-42

https://doi.org/10.6574/JPRS.202203_27(1).0003

摘要

基於影像特徵點之視覺SLAM（Visual Simultaneous Localization and Mapping, V-SLAM），以重複的三維特徵地圖建立、影像特徵至三維特徵地圖的匹配和空間後方交會過程定位相機。若其建立之三維特徵地圖能做場景先驗控制重複使用，則可解決無可靠GNSS訊號環境之定位問題。然環境光照條件常影響影像特徵點萃取和匹配結果，因此值得進一步探討不同光照條件下建立之三維特徵地圖，其相機定位成果對光照條件改變之適應性。本研究輸入不同光照條件下建立之三維特徵地圖至ORB-SLAM系統，藉其地圖再利用功能輔助相機定位。研究成果表明，三維特徵地圖輔助之相機定位，能獲接近參考地圖精度的相機定位精度，為無可靠GNSS訊號環境之定位問題的可能解決方案。

關鍵字

ORB-SLAM ； 三維特徵地圖 ； 坐標轉換

並列摘要

The feature-based Visual Simultaneous Localization and Mapping (V-SLAM) systems localize cameras by repeatly establishing the 3D feature maps, matching the image features to the 3D feature maps and conducting space resection. By reusing the 3D feature maps established during SLAM processing, it can be considered as a control field to solve the GNSS-denied localization problem. However, the different lighting condition in the outdoor environments can possibly affect the results of image feature extraction and matching, which will lead to different localization results. This study applies ORB-SLAM to establish the 3D feature maps, and the map-aided camera localization is conducted under ORB-SLAM Localization Mode. The experimental results demonstrate the camera localization aided by a 3D feature map can reach close camera localization accuracy as the accuracy of its' reference 3D feature maps. As a result, the camera localization aided by a 3D feature map can become a potential solution of GNSS-denied localization problem.

並列關鍵字

ORB-SLAM ； 3D Feature Map ； Coordinate Transformation

參考文獻

Geiger, A., Lenz, P., Stiller, C., and Urtasun, R., 2013. Vision meets robotics: The KITTI dataset, The International Journal of Robotics Research, 32: 1231-1237.

Mur-Artal, R., Montiel, J.M.M., and Tardos, J.D., 2015. ORB-SLAM: A versatile and accurate monocular SLAM system, IEEE Transactions on Robotics, 31: 1147-1163.

Mur-Artal, R., and Tardos, J.D., 2017. ORB-SLAM2: An open-source SLAM system for monocular, stereo, and RGB-D cameras, IEEE Transactions on Robotics, 33: 1255-1262.

Nobis, F., Papanikolaou, O., Betz, J., and Lienkamp, M., 2020. Persistent map saving for visual localization for autonomous vehicles: An ORB-SLAM 2 extension, Proceedings of the 2020 Fifteenth International Conference on Ecological Vehicles and Renewable Energies (EVER), Monte-Carlo, Monaco, pp. 1-9.

Ranganathan, A., Matsumoto, S., and Ilstrup, D., 2013. Towards illumination invariance for visual localization, Proceedings of the 2013 IEEE International Conference on Robotics and Automation, Karlsruhe, Germany, pp. 3791-3798.