The EKF-Based Visual SLAM System with Relative Map Orientation Measurements

This paper presents the extension of the feature-based, visual SLAM with additional measurements of the relative orientation between the current and past poses of the camera. The well known inverse depth representation of the point features was replaced with the combination of local maps and simplified features to allow orientation measurements via the estimation of the essential matrix. The proposed modification was evaluated using the openly available PUT RGB-D database. The incorporation of additional measurements resulted in reduction of the RMS of the trajectory reconstruction error by 17%.

[1]  Hauke Strasdat,et al.  Visual SLAM: Why filter? , 2012, Image Vis. Comput..

[2]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[3]  Adam Schmidt,et al.  An Indoor RGB-D Dataset for the Evaluation of Robot Navigation Algorithms , 2013, ACIVS.

[4]  Adam Schmidt,et al.  FPGA Implementation of the Robust Essential Matrix Estimation with RANSAC and the 8-Point and the 5-Point Method , 2011, Facing the Multicore-Challenge.

[5]  Adam Schmidt,et al.  Visual Simultaneous Localization and Mapping with Direct Orientation Change Measurements , 2013, ICMMI.

[6]  Ignacy Duleba,et al.  On the application of elastic band method to repeatable inverse kinematics in robot manipulators , 2013 .

[7]  Olivier Stasse,et al.  MonoSLAM: Real-Time Single Camera SLAM , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  G. Klein,et al.  Parallel Tracking and Mapping for Small AR Workspaces , 2007, 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality.

[9]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

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

[11]  Wolfram Burgard,et al.  G2o: A general framework for graph optimization , 2011, 2011 IEEE International Conference on Robotics and Automation.

[12]  Wolfram Burgard,et al.  Towards a benchmark for RGB-D SLAM evaluation , 2011, RSS 2011.

[13]  Adam Schmidt,et al.  On augmenting the visual slam with direct orientation measurement using the 5-point algorithm , 2013 .

[14]  Javier Civera,et al.  Inverse Depth Parametrization for Monocular SLAM , 2008, IEEE Transactions on Robotics.

[15]  Marek Kraft,et al.  System on Chip Coprocessors for High Speed Image Feature Detection and Matching , 2011, ACIVS.