Homography-based ground plane detection for mobile robot navigation using a Modified EM algorithm

In this paper, a homography-based approach for determining the ground plane using image pairs is presented. Our approach is unique in that it uses a Modified Expectation Maximization algorithm to cluster pixels on images as belonging to one of two possible classes: ground and non-ground pixels. This classification is very useful in mobile robot navigation because, by segmenting out the ground plane, we are left with all possible objects in the scene, which can then be used to implement many mobile robot navigation algorithms such as obstacle avoidance, path planning, target following, landmark detection, etc. Specifically, we demonstrate the usefulness and robustness of our approach by applying it to a target following algorithm. As the results section shows, the proposed algorithm for ground plane detection achieves an almost perfect detection rate (over 99%) despite the relatively higher number of errors in pixel correspondence from the feature matching algorithm used: SIFT.

[1]  Guilherme N. DeSouza,et al.  Instataneous geo-location of multiple targets from monocular airborne video , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[2]  Avinash C. Kak,et al.  Vision for Mobile Robot Navigation: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Baoxin Li,et al.  Robust Ground Plane Detection with Normalized Homography in Monocular Sequences from a Robot Platform , 2006, 2006 International Conference on Image Processing.

[4]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[5]  Martial Hebert,et al.  Laser intensity-based obstacle detection , 1998, Proceedings. 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems. Innovations in Theory, Practice and Applications (Cat. No.98CH36190).

[6]  Hakil Kim,et al.  Layered ground floor detection for vision-based mobile robot navigation , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[7]  T. Wekel,et al.  Vision based obstacle detection for wheeled robots , 2008, 2008 International Conference on Control, Automation and Systems.

[8]  Jun Zhao,et al.  Global Correlation Based Ground Plane Estimation Using V-Disparity Image , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[9]  Robert E. Mahony,et al.  Spatio-Temporal RANSAC for Robust Estimation of Ground Plane in Video Range Images for Automotive Applications , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[10]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[11]  Manuela M. Veloso,et al.  Visual sonar: fast obstacle avoidance using monocular vision , 2003, Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453).

[12]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[13]  Viii Supervisor.  Sonar-Based Real-World Mapping and Navigation , 2001 .

[14]  Vassilios Morellas,et al.  Accurate 3D ground plane estimation from a single image , 2009, 2009 IEEE International Conference on Robotics and Automation.

[15]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Jeffrey C. Lagarias,et al.  Convergence Properties of the Nelder-Mead Simplex Method in Low Dimensions , 1998, SIAM J. Optim..

[17]  Baoxin Li,et al.  Homography-based ground detection for a mobile robot platform using a single camera , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[18]  P. Lombardi,et al.  Unified stereovision for ground, road, and obstacle detection , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[19]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .