Accuracy enhancement for the front-end tracking algorithm of RGB-D SLAM

Springer Science and Business Media LLC - Tập 13 - Trang 207-218 - 2019
Fuwen Hu1, Jingli Cheng1, Yunchang Bao1, Yunhua He2
1School of Mechanical and Material Engineering, North China University of Technology, Beijing, China
2Department of Mechanical and Electronic Engineering, Shandong University of Science and Technology, Tai’an, China

Tóm tắt

A robust and accurate simultaneous localization and mapping (SLAM) in working scenarios is an essential competence to perform mobile robotic tasks autonomously. Plenty of research indicates that the extraction of point features from RGB-D data that simultaneously take into account the images and the depth data increases the robustness and precision of the visual odometry method, used either as a self-reliant localization system, or as a front-end in pose-based SLAM. However, due to pure rotation, sudden movements, motion blur, noise and large depth variations, RGB-D SLAM systems often suffer from tracking loss in data association. The front-end tracking process of the ORB-SLAM system requires screening step by step, which is more likely to cause tracking loss. In order to solve the above problems, this work is intended to improve the ORB-SLAM front-end tracking algorithm based on the uniform speed model tracking effective frame and the matching of nearby frame algorithms. Then three datasets selected from TUM datasets with more motion blur are used to further verify the effect of the improved front-end algorithmic architecture. The experimental results suggested that the proposed improved scheme can not only effectively increase the number of tracked frames, but also reduce the amount of computation by about two times under the premise of guaranteeing the path accuracy.

Tài liệu tham khảo

Lv Q, Lin H, Wang G, Wei H, Wang Y (2017) ORB-SLAM-based tracing and 3D reconstruction for robot using Kinect 2.0. In: Control and decision conference. IEEE, pp 3319–3324 Lenac K, Kitanov A, Cupec R, Petrović I (2017) Fast planar surface 3D SLAM using LIDAR. Robot Auton Syst 92:197–220 Liu L, Guo R, Wu J (2018) A collision-free motion planning method by integrating complexity-reduction SLAM and learning-based artificial force design. Robot Auton Syst 100:132–149 Cho H, Kim EK, Kim S (2018) Indoor SLAM application using geometric and ICP matching methods based on line features. Robot Auton Syst 100:206–224 Shin DW, Ho YS (2017) Local patch descriptor using deep convolutional generative adversarial network for loop closure detection in SLAM. In: Asia-Pacific signal and information processing association summit and conference, pp 546–549 Mustafa M, Stancu A, Delanoue N, Codres E (2018) Guaranteed SLAM—an interval approach. Robot Auton Syst 100:160–170 Pire T, Fischer T, Castro G, Decristóforis P, Civera J, Jacoboberlles J (2017) S-PTAM: stereo parallel tracking and mapping. Robot Auton Syst 93:27–42 Younes G, Asmar D, Shammas E, Zelek J (2017) Keyframe-based monocular SLAM: design, survey, and future directions. Robot Auton Syst 98:67–88 Evers C, Naylor PA (2017) Optimized self-localization for SLAM in dynamic scenes using probability hypothesis density filters. IEEE Trans Signal Process 99:1 Cadena C, Carlone L, Carrillo H, Latif Y, Scaramuzza D, Neira J et al (2016) Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. IEEE Trans Robot 32(6):1309–1332 Cheeseman P, Smith R, Self M (1987) A stochastic map for uncertain spatial relationships. In: 4th international symposium on robotic research, pp 467–474 Frese U (2006) A discussion of simultaneous localization and mapping. Auton Robots 20(1):25–42 Spero DJ, Jarvis RA (2007) A review of robotic SLAM, Monash University, Technical Report, MECSE-4-2007 Thrun S, Fox D, Burgard W, Dellaert F (2001) Robust Monte Carlo localization for mobile robots. Artif Intell 128(1–2):99–141 Montemerlo M, Thrun S, Koller D, Wegbreit B (2002) FastSLAM: a factored solution to the simultaneous localization and mapping problem. In: Aaai/iaai, pp 593–598 Montemerlo M, Thrun S, Koller D, Wegbreit B (2003) FastSLAM 2.0: an improved particle filtering algorithm for simultaneous localization and mapping that provably converges. In: IJCAI, pp 1151–1156 Davison AJ (2003) Real-time simultaneous localisation and mapping with a single camera. In: ICCV. IEEE, p 1403 Clemente L, Davison A, Reid I, Neira J, Tardós J (2007) Mapping large loops with a single hand-held camera. In: Proceedings of robotics sciences & systems, pp 297–304 Karlsson N, Bernardo ED, Ostrowski JP, Goncalves L, Pirjanian P, Munich ME (2006) The vSLAM algorithm for robust localization and mapping. In: IEEE international conference on robotics & automation. IEEE Klein G (2007) Parallel tracking and mapping for small AR workspaces. In: Proceedings of sixth IEEE and ACM international symposium on mixed and augmented reality (ISMAR 2007). IEEE, Nara, Japan Engel J, Schöps T, Cremers D (2014) LSD-SLAM: large-scale direct monocular SLAM. In: European conference on computer vision. Springer, Cham Engel J, Sturm J, Cremers D (2013) Semi-dense visual odometry for a monocular camera. In: 2013 IEEE international conference on computer vision (ICCV). IEEE Computer Society Forster C, Pizzoli M, Scaramuzza D (2014) SVO: fast semi-direct monocular visual odometry. In: IEEE international conference on robotics and automation (ICRA). IEEE, Hong Kong Engel J, Koltun V, Cremers D (2017) Direct sparse odometry. IEEE Trans Pattern Anal Mach Intell 40(3):611–625 Labbé M, Michaud F (2014) Online global loop closure detection for large-scale multi-session graph-based SLAM. In: 2014 IEEE/RSJ international conference on intelligent robots and systems. IEEE Newcombe RA, Lovegrove SJ, Davison AJ (2011) DTAM: dense tracking and mapping in real-time. In: IEEE international conference on computer vision, ICCV 2011. IEEE, Barcelona, Spain, November 6–13 Mur-Artal R, Tardos JD (2017) ORB-SLAM2: an open-source slam system for monocular, stereo, and RGB-D cameras. IEEE Trans Robot 33:1–8 Mohanty V, Agrawal S, Datta S, Ghosh A, Sharma VD, Chakravarty D (2016) Deepvo: a deep learning approach for monocular visual odometry Yousif K, Bab-Hadiashar A, Hoseinnezhad R (2015) An overview to visual odometry and visual SLAM: applications to mobile robotics. Intell Ind Syst 1(4):289–311 Gálvez-López D, Tardos JD (2012) Bags of binary words for fast place recognition in image sequences. IEEE Trans Robot 28(5):1188–1197 Chai Z, Matsumaru T (2017) ORB-SHOT SLAM: trajectory correction by 3D loop closing based on bag-of-visual-words (BoVW) model for RGB-D visual SLAM. J Robot Mechatron 29(2):365–380 Sturm J, Engelhard N, Endres F, Burgard W, Cremers D (2012) A benchmark for the evaluation of RGB-D SLAM systems. In: 2012 IEEE/RSJ international conference on intelligent robots and systems. IEEE Zhao X, Min H, Xu Z, Wu X, Li X, Sun P (2018) Image antiblurring and statistic filter of feature space displacement: application to visual odometry for outdoor ground vehicle. J Sens 2018:14 Mustaniemi J, Kannala J, Särkkä S, Matas J, Heikkilä J (2018) Fast motion deblurring for feature detection and matching using inertial measurements. In: 2018 24th international conference on pattern recognition (ICPR). IEEE, pp 3068–3073 Russo LO, Farulla GA, Indaco M, Rosa S, Rolfo D, Bona B (2013) Blurring prediction in monocular SLAM. In: 2013 8th IEEE design and test symposium. IEEE, pp 1–6 Atashgah MA, Malaek SMB (2013) Prediction of aerial-image motion blurs due to the flying vehicle dynamics and camera characteristics in a virtual environment. Proc Inst Mech Eng Part G J Aerosp Eng 227(7):1055–1067 Amiri Atashgah MA, Malaek SMB (2011) A simulation environment for path and image generation in an aerial single-camera vision system. Proc Inst Mech Eng Part G J Aerosp Eng 225(5):541–558 Atashgah MA, Gholampour P, Malaek SMB (2014) Integration of image de-blurring in an aerial Mono-SLAM. Proc Inst Mech Eng Part G J Aerosp Eng 228(8):1348–1362