Augmenting Mobile Robot Geometric Map with Photometric Information

In this paper we discuss methods to increase the discriminative properties of the laser-based geometric features used in SLAM by employing monocular vision data. Vertical edges extracted from images enable to estimate the length of partially observed line segments. Salient visual features are represented as the SIFT descriptors. These photometric features augment the 2D line segments extracted from the laser data and form a new feature type.

[1]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[2]  J. M. M. Montiel,et al.  Relocation using laser and vision , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

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

[4]  Roland Siegwart,et al.  Multisensor on-the-fly localization: : Precision and reliability for applications , 2001, Robotics Auton. Syst..

[5]  José A. Castellanos,et al.  Mobile Robot Localization and Map Building: A Multisensor Fusion Approach , 2000 .

[6]  Paul Newman,et al.  SLAM-Loop Closing with Visually Salient Features , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[7]  Piotr Skrzypczynski.  Merging Probabilistic and Fuzzy Frameworks for Uncertain Spatial Knowledge Modelling , 2005, CORES.

[8]  Robert M. Haralick.  Propagating Covariance in Computer Vision , 1996, Int. J. Pattern Recognit. Artif. Intell..

[9]  Piotr Skrzypczynski,et al.  Spatial Uncertainty Management for Simultaneous Localization and Mapping , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[10]  José A. Castellanos,et al.  Mobile Robot Localization and Map Building , 1999 .