A new feature parametrization for monocular SLAM using line features

This paper presents a new monocular SLAM algorithm that uses straight lines extracted from images to represent the environment. A line is parametrized by two pairs of azimuth and elevation angles together with the two corresponding camera centres as anchors making the feature initialization relatively straightforward. There is no redundancy in the state vector as this is a minimal representation. A bundle adjustment (BA) algorithm that minimizes the reprojection error of the line features is developed for solving the monocular SLAM problem with only line features. A new map joining algorithm which can automatically optimize the relative scales of the local maps is used to combine the local maps generated using BA. Results from both simulations and experimental datasets are used to demonstrate the accuracy and consistency of the proposed BA and map joining algorithms.

[1]  Hauke Strasdat,et al.  Real-time monocular SLAM: Why filter? , 2010, 2010 IEEE International Conference on Robotics and Automation.

[2]  Ruth F. Curtain,et al.  Proceedings of the 48th IEEE Conference on Decision and Control, CDC 2009, combined withe the 28th Chinese Control Conference, December 16-18, 2009, Shanghai, China , 2009, CDC.

[3]  Tom Drummond,et al.  Edge landmarks in monocular SLAM , 2009, Image Vis. Comput..

[4]  Teresa A. Vidal-Calleja,et al.  Impact of Landmark Parametrization on Monocular EKF-SLAM with Points and Lines , 2011, International Journal of Computer Vision.

[5]  Henrik Schiøler,et al.  Trophallaxis in robotic swarms - beyond energy autonomy , 2008, 2008 10th International Conference on Control, Automation, Robotics and Vision.

[6]  Lei Yan,et al.  Large-scale monocular SLAM by local bundle adjustment and map joining , 2010, 2010 11th International Conference on Control Automation Robotics & Vision.

[7]  Gamini Dissanayake,et al.  3D I-SLSJF: A consistent sparse local submap joining algorithm for building large-scale 3D Map , 2009, Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference.

[8]  Andrew J. Davison,et al.  Real-time simultaneous localisation and mapping with a single camera , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  Lei Yan,et al.  Parallax angle parametrization for monocular SLAM , 2011, 2011 IEEE International Conference on Robotics and Automation.

[10]  Teresa A. Vidal-Calleja,et al.  Large scale multiple robot visual mapping with heterogeneous landmarks in semi-structured terrain , 2011, Robotics Auton. Syst..

[11]  Kurt Konolige,et al.  FrameSLAM: From Bundle Adjustment to Real-Time Visual Mapping , 2008, IEEE Transactions on Robotics.

[12]  Gamini Dissanayake,et al.  Convergence and Consistency Analysis for Extended Kalman Filter Based SLAM , 2007, IEEE Transactions on Robotics.

[13]  Thierry Peynot,et al.  Reliable automatic camera-laser calibration , 2010, ICRA 2010.

[14]  Teresa A. Vidal-Calleja,et al.  A fast visual line segment tracker , 2008, 2008 IEEE International Conference on Emerging Technologies and Factory Automation.

[15]  Hauke Strasdat,et al.  Scale Drift-Aware Large Scale Monocular SLAM , 2010, Robotics: Science and Systems.

[16]  Juan D. Tardós,et al.  Hierarchical SLAM: real-time accurate mapping of large environments , 2005, IEEE Transactions on Robotics.

[17]  Gamini Dissanayake,et al.  Iterated D-SLAM map joining: evaluating its performance in terms of consistency, accuracy and efficiency , 2009, Auton. Robots.

[18]  Gamini Dissanayake,et al.  Sparse Local Submap Joining Filter for Building Large-Scale Maps , 2008, IEEE Transactions on Robotics.

[19]  Udo Frese,et al.  A Benchmark Data Set for Data Association , 2009 .

[20]  Adrien Bartoli,et al.  Structure-from-motion using lines: Representation, triangulation, and bundle adjustment , 2005, Comput. Vis. Image Underst..

[21]  Andrew Zisserman,et al.  "Here's looking at you, kid". Detecting people looking at each other in videos , 2011, BMVC.

[22]  David J. Kriegman,et al.  Structure and Motion from Line Segments in Multiple Images , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Walterio W. Mayol-Cuevas,et al.  Real-Time Model-Based SLAM Using Line Segments , 2006, ISVC.

[24]  Ian D. Reid,et al.  Real-Time Monocular SLAM with Straight Lines , 2006, BMVC.

[25]  Lina María Paz,et al.  Optimal local map size for EKF-based SLAM , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[26]  D. Simon,et al.  Kalman filtering with state equality constraints , 2002 .

[27]  David W. Murray,et al.  Improving the Agility of Keyframe-Based SLAM , 2008, ECCV.

[28]  Michel Dhome,et al.  Generic and real-time structure from motion using local bundle adjustment , 2009, Image Vis. Comput..

[29]  J. M. M. Montiel,et al.  The SPmap: a probabilistic framework for simultaneous localization and map building , 1999, IEEE Trans. Robotics Autom..

[30]  Roland Siegwart,et al.  People detection and tracking from aerial thermal views , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[31]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[32]  Joseph J. LaViola,et al.  On Kalman Filtering With Nonlinear Equality Constraints , 2007, IEEE Transactions on Signal Processing.

[33]  David W. Murray,et al.  Full-3D Edge Tracking with a Particle Filter , 2006, BMVC.

[34]  Teresa A. Vidal-Calleja,et al.  Undelayed initialization of line segments in monocular SLAM , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[35]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Simon Lacroix,et al.  Monocular-vision based SLAM using Line Segments , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.