Visual SLAM from image sequences acquired by unmanned aerial vehicles

Visual SLAM from image sequences acquired by unmanned aerial vehicles This thesis shows that Kalman filter based approaches are sufficient for the task of simultaneous localization and mapping from image sequences acquired by unmanned aerial vehicles. Using solely direction measurements to solve the problem of simultaneous localization and mapping (SLAM) is an important part of autonomous systems. Because the need for real-time capable systems, recursive estimation techniques, Kalman filter based approaches are the main focus of interest. Unfortunately, the non-linearity of the triangulation using the direction measurements cause decrease of accuracy and consistency of the results. The first contribution of this work is a general derivation of the recursive update of the Kalman filter. This derivation is based on implicit measurement equations, having the classical iterative non-linear as well as the non-iterative and linear Kalman filter as specializations of our general derivation. Second, a new formulation of linear-motion models for the single camera state model and the sliding window camera state model are given, that make it possible to compute the prediction in a fully linear manner. The third major contribution is a novel method for the initialization of new object points in the Kalman filter. Empirical studies using synthetic and real data of an image sequence of a photogrammetric strip are made, that demonstrate and compare the influences of the initialization methods of new object points in the Kalman filter. Forth, the accuracy potential of monoscopic image sequences from unmanned aerial vehicles for autonomous localization and mapping is theoretically analyzed, which can be used for planning purposes.

[1]  Kurt Konolige,et al.  Visual Odometry Using Sparse Bundle Adjustment on an Autonomous Outdoor Vehicle , 2006, AMS.

[2]  Matteo Matteucci,et al.  Integration of 3D Lines and Points in 6DoF Visual SLAM by Uncertain Projective Geometry , 2007, EMCR.

[3]  Henry A. Kautz,et al.  Voronoi tracking: location estimation using sparse and noisy sensor data , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[4]  Pere Ridao,et al.  Underwater SLAM in man‐made structured environments , 2008, J. Field Robotics.

[5]  Evangelos E. Milios,et al.  Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Andrew Calway,et al.  Real-Time Visual SLAM with Resilience to Erratic Motion , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  Karl-Rudolf Koch,et al.  Parameter estimation and hypothesis testing in linear models , 1988 .

[8]  Andreas Nüchter,et al.  EXTRACTING DRIVABLE SURFACES IN OUTDOOR 6 D SLAM , 2006 .

[9]  Philip F. McLauchlan,et al.  A batch/recursive algorithm for 3D scene reconstruction , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[10]  Sebastian Thrun,et al.  Simultaneous localization and mapping with unknown data association using FastSLAM , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[11]  Patric Jensfelt,et al.  EKF SLAM updates in O(n) with Divide and Conquer SLAM , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[12]  Salah Sukkarieh,et al.  Robust multi-loop airborne SLAM in unknown wind environments , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[13]  Andreas Nüchter,et al.  Parallelization of Scan Matching for Robotic 3D Mapping , 2007, EMCR.

[14]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[15]  Reg G. Willson,et al.  INCREMENTAL BUNDLE ADJUSTMENT TECHNIQUES USING NETWORKED OVERHEAD AND GROUND IMAGERY FOR LONG-RANGE AUTONOMOUS MARS ROVER LOCALIZATION , 2005 .

[16]  P. Sturm,et al.  On Calibration, Structure from Motion and Multi-View Geometry for Generic Camera Models , 2006 .

[17]  Cordelia Schmid,et al.  An Affine Invariant Interest Point Detector , 2002, ECCV.

[18]  Edward M. Mikhail,et al.  Observations And Least Squares , 1983 .

[19]  S. Julier,et al.  A General Method for Approximating Nonlinear Transformations of Probability Distributions , 1996 .

[20]  Matthew N. Dailey,et al.  Rapid 3D visualization of indoor scenes using 3D occupancy grid isosurfaces , 2009, 2009 6th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[21]  Michel Dhome,et al.  Monocular Vision Based SLAM for Mobile Robots , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[22]  Benjamin Kuipers,et al.  The Spatial Semantic Hierarchy , 2000, Artif. Intell..

[23]  Michel Devy,et al.  Undelayed initialization in bearing only SLAM , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[24]  Simultaneous Localisation and Mapping (SLAM) mit Hierarchischen Partikelfiltern , 2005 .

[25]  John J. Leonard,et al.  Robust Mapping and Localization in Indoor Environments Using Sonar Data , 2002, Int. J. Robotics Res..

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

[27]  D. Simon.  Optimal State Estimation: Kalman, H Infinity, and Nonlinear Approaches , 2006 .

[28]  David W. Murray,et al.  A unifying framework for structure and motion recovery from image sequences , 1995, Proceedings of IEEE International Conference on Computer Vision.

[29]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Wolfgang Förstner,et al.  On Visual Real Time Mapping for Unmanned Aerial Vehicles , 2008 .

[32]  Marc Levoy,et al.  Efficient variants of the ICP algorithm , 2001, Proceedings Third International Conference on 3-D Digital Imaging and Modeling.

[33]  Javier Civera,et al.  Unified Inverse Depth Parametrization for Monocular SLAM , 2006, Robotics: Science and Systems.

[34]  Eduardo Mario Nebot,et al.  Scan-SLAM: Combining EKF-SLAM and Scan Correlation , 2005, FSR.

[35]  Aníbal Ollero,et al.  Motion compensation and object detection for autonomous helicopter visual navigation in the COMETS system , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[36]  Andrew Howard,et al.  Fast visual mapping for mobile robot navigation , 1997, 1997 IEEE International Conference on Intelligent Processing Systems (Cat. No.97TH8335).

[37]  Andrew Calway,et al.  Real-Time Camera Tracking Using a Particle Filter , 2005, BMVC.

[38]  Jeffrey K. Uhlmann,et al.  Using covariance intersection for SLAM , 2007, Robotics Auton. Syst..

[39]  John J. Leonard,et al.  Towards Constant-Time SLAM on an Autonomous Underwater Vehicle Using Synthetic Aperture Sonar , 2003, ISRR.

[40]  Gaurav S. Sukhatme,et al.  The Iterated Sigma Point Kalman Filter with Applications to Long Range Stereo , 2006, Robotics: Science and Systems.

[41]  P. Protzel,et al.  Using the Unscented Kalman Filter in Mono-SLAM with Inverse Depth Parametrization for Autonomous Airship Control , 2007, 2007 IEEE International Workshop on Safety, Security and Rescue Robotics.

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

[43]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[44]  Sebastian Thrun,et al.  Robotic mapping: a survey , 2003 .

[45]  Jeffrey K. Uhlmann,et al.  New extension of the Kalman filter to nonlinear systems , 1997, Defense, Security, and Sensing.

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

[47]  Sebastian Thrun,et al.  The Graph SLAM Algorithm with Applications to Large-Scale Mapping of Urban Structures , 2006, Int. J. Robotics Res..

[48]  Wolfram Burgard,et al.  An Efficient Extension to Elevation Maps for Outdoor Terrain Mapping and Loop Closing , 2007, Int. J. Robotics Res..

[49]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using orthonormal matrices , 1988 .

[50]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[51]  Gabe Sibley.  Sliding Window Filters for SLAM , 2006 .

[52]  Ramón Galán,et al.  Consistency improvement for SLAM - EKF for indoor environments , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[53]  Christian Beder,et al.  Recursive Estimation with Implicit Constraints , 2007, DAGM-Symposium.

[54]  Stergios I. Roumeliotis,et al.  A unified framework for nearby and distant landmarks in bearing-only SLAM , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..