Abstract：An RGB-D SLAM (simultaneous localization and mapping) algorithm based on semi-direct visual odometry is proposed. By using the advantages of both the direct method and the traditional feature-based method, and combining with robust back-end optimization and closed-loop detection, the localization and mapping accuracy of the algorithm in complex environments is effectively improved. At the localization stage, the initial pose of camera is estimated by the direct method, which is further optimized by matching the features and minimizing the reprojection error. By selecting map points and optimizing the posture output strategy, it can deal with the problems of low-texture, illumination change, moving objects and so on. In addition, the algorithm has the ability of global relocation. A new key frame selection strategy is proposed for back-end optimization, that maintains two separate key frames in parallel, i.e. the local key frames selected by the direct method, and the global key frames selected by the feature-based method. These key frame are optimized in sliding window and feature map respectively. The algorithm improves the global consistency of SLAM through closed-loop detection and optimization on the global key frames. The experimental results based on standard datasets and real scenes show that the performance of the proposed algorithm is better than the main RGB-D SLAM algorithms in many real scenes, and it has strong robustness to the environments with low-texture and moving objects.
[1] 张国良,姚二亮,林志林,等.融合直接法与特征法的快速双目SLAM算法[J].机器人,2017,39(6):879-888.Zhang G L, Yao E L, Lin Z L, et al. Fast binocular SLAM algorithm combining the direct method and the feature-based method[J]. Robot, 2017, 39(6):879-888. [2] Klein G, Murray D. Parallel tracking and mapping for small AR workspaces[C]//6th IEEE and ACM International Symposium on Mixed and Augmented Reality. Piscataway, USA:IEEE, 2007. DOI:10.1109/ISMAR.2007.4538852. [3] Mur-Artal R, Montiel J M M, Tardos J D. ORB-SLAM:A versatile and accurate monocular SLAM system[J]. IEEE Transactions on Robotics, 2015, 31(5):1147-1163. [4] Bay H, Ess A, Tuytelaars T, et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3):346-359. [5] Rublee E, Rabaud V, Konolige K, et al. ORB:An efficient alternative to SIFT or SURF[C]//IEEE International Conference on Computer Vision. Piscataway, USA:IEEE, 2011:2564-2571. [6] Kerl C, Sturm J, Cremers D. Robust odometry estimation for RGB-D cameras[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2013:3748-3754. [7] Newcombe R A, Izadi S, Hilliges O, et al. KinectFusion:Real-time dense surface mapping and tracking[C]//10th IEEE/ACM International Symposium on Mixed and Augmented Reality. Piscataway, USA:IEEE, 2011:127-136. [8] Krombach N, Droeschel D, Behnke S. Combining feature-based and direct methods for semi-dense real-time stereo visual odometry[C]//14th International Conference on Intelligent Autonomous Systems. Cham, Switzerland:Springer, 2016:855-868. [9] Kim P, Lee H, Kim H J. Autonomous flight with robust visualodometry under dynamic lighting conditions[J]. Autonomous Robots, 2019, 43(6):1605-1622. [10] Lee S H, Civera J. Loosely-coupled semi-direct monocular SLAM[J]. IEEE Robotics and Automation Letters, 2019, 4(2):399-406. [11] Younes G, Asmar D, Zelek J. A unified formulation for visualodometry[EB/OL]. (2019-03-11)[2019-04-10]. https://arxiv.org/abs/1903.04253v1. [12] Forster C, Zhang Z, Gassner M, et al. SVO:Semidirect visualodometry for monocular and multicamera systems[J]. IEEE Transactions on Robotics, 2017, 33(2):249-265. [13] Bu S H, Zhao Y, Wan G, et al. Semi-direct tracking and mapping with RGB-D camera for MAV[J]. Multimedia Tools and Applications, 2017, 76(3):4445-4469. [14] Gálvez-López D, Tardós J D. Bags of binary words for fast place recognition in image sequences[J]. IEEE Transactions on Robotics, 2012, 28(5):1188-1197. [15] Triggs B, McLauchlan P F, Hartley R I, et al. Bundle adjustment-A modern synthesis[C]//International Workshop on Vision Algorithms. Berlin, Germany:Springer, 1999:298-372. [16] Engel J, Schöps T, Cremers D. LSD-SLAM:Large-scale direct monocular SLAM[C]//13th European Conference on Computer Vision. Cham, Switzerland:Springer, 2014:834-849. [17] Mur-Artal R, Tardós J D. ORB-SLAM2:An open-sourceSLAM system for monocular, stereo, and RGB-D cameras[J]. IEEE Transactions on Robotics, 2017, 33(5):1255-1262. [18] Engel J, Koltun V, Cremers D. Direct sparse odometry[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(3):611-625. [19] Kerl C, Sturm J, Cremers D. Dense visual SLAM for RGB-D cameras[C]//IEEE/RSJ International Conference on IntelligentRobots and Systems. Piscataway, USA:IEEE, 2013:2100-2106. [20] Gao X, Wang R, Demmel N, et al. LDSO:Direct sparse odometry with loop closure[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2018:2198-2204.. [21] Sturm J, Engelhard N, Endres F, et al. A benchmark for the evaluation of RGB-D SLAM systems[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2012:573-580. [22] Handa A, Whelan T, McDonald J, et al. A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2014:1524-1531.
