Accurate feature matching for autonomous vehicle navigation in urban environments

The research presented in this paper ultimately aims at accurate Unmanned Aerial Vehicle (UAV) navigation using camera(s) to augment inertial navigation unit data while flying through an urban environment. Accurate position and depth determination requires precise image feature location and matching. This paper investigates accurate feature matching enabling determination of image depth. The paper offers two unique contributions to the field. First, it is shown how to improve feature matching accuracy when a good position estimate is available. Secondly, it is shown how to increase the number of matched features. In this way, there is more data and it may be possible, in future research, to identify the depth plane a feature belongs to and so increase the accuracy of position determination. Preliminary results are reported.

[1]  W. Dixon,et al.  Position and Orientation of an Aerial Vehicle through Chained, Vision-Based Pose Reconstruction , 2006 .

[2]  Peter Kovesi,et al.  Image Features from Phase Congruency , 1995 .

[3]  Jurek Z. Sasiadek,et al.  Vision-Based UAV Navigation , 2008 .

[4]  K. Kaiser,et al.  Localization and Control of an Aerial Vehicle through Chained, Vision-Based Pose Reconstruction , 2007, 2007 American Control Conference.

[5]  S. M. Steve.  SUSAN - a new approach to low level image processing , 1997 .

[6]  Andrew Zisserman,et al.  Feature Based Methods for Structure and Motion Estimation , 1999, Workshop on Vision Algorithms.

[7]  Monish D. Tandale,et al.  Vision-Based Sensor and Navigation System for Autonomous Air Refueling , 2005 .

[8]  Guoqiang Hu,et al.  Daisy Chaining Based Visual Servo Control Part II: Extensions, Applications and Open Problems , 2007, 2007 IEEE International Conference on Control Applications.

[9]  Mario G. Perhinschi,et al.  AUTONOMOUS AERIAL REFUELING FOR UAVS USING A COMBINED GPS-MACHINE VISION GUIDANCE , 2004 .

[10]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

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

[12]  Peter Kovesi,et al.  Phase Congruency Detects Corners and Edges , 2003, DICTA.

[13]  J. Sasiadek,et al.  Feature Detector Performance for UAV Navigation , 2010 .

[14]  Rachid Deriche,et al.  A Robust Technique for Matching two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry , 1995, Artif. Intell..

[15]  Richard J. Prazenica,et al.  Vision-Based State Estimation for Autonomous Micro Air Vehicles , 2004 .

[16]  James R. Bergen,et al.  Visual odometry for ground vehicle applications , 2006, J. Field Robotics.

[17]  Jurek Z. Sasiadek,et al.  Feature matching for UAV navigation in urban environments , 2010, 2010 15th International Conference on Methods and Models in Automation and Robotics.

[18]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[19]  Guoqiang Hu,et al.  Daisy Chaining Based Visual Servo Control Part I: Adaptive Quaternion-Based Tracking Control , 2007, 2007 IEEE International Conference on Control Applications.

[20]  T. Kanade,et al.  Real-time and 3D vision for autonomous small and micro air vehicles , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[21]  J. A. Volpe.  Vulnerability Assessment of the Transportation Infrastructure Relying on the Global Positioning Syst , 2001 .