Visual Hybrid SLAM: An Appearance-Based Approach to Loop Closure
This paper proposes an appearance-based method to detect loop closure in visual SLAM (Simultaneous Localization and Mapping). To solve this problem, we make use of omnidirectional images and the internal odometry captured by a robot in a real indoor environment. We build an appearance-based model and, subsequently, two maps of the environment are constructed, one metric and other topological with relationships between them. These relationships are updated in each step of our hybrid approach. The topological map is a graph built from the appearance information in the scenes. A new node is added when the new visual information is different enough from the previous information. At the same time, we check a possible topological loop closure with previous nodes. On the other hand we estimate the metric position of the new pose using a Monte-Carlo approach with the aim of building a metric map. The experimental results demonstrate the reasonable performance of our method.
KeywordsAppearance-base descriptor Omnidirectional Images Monte-Carlo SLAM Hybrid Metric-Topological mapping Loop closure detection
Unable to display preview. Download preview PDF.
- 1.Amorós, F., Payá, L., Reinoso, Ó., Fernández, L., Marín, J.M.: Visual map building and localization with an appearance-based approach - comparisons of techniques to extract information of panoramic images. In: Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2010, pp. 423–426 (2010)Google Scholar
- 2.Amorós, F., Payá, L., Reinoso, Ó., Jiménez, L.M.: Comparison of global-appearance techniques applied to visual map building and localization. In: Proceedings of the International Conference on Computer Vision Theory and Applications, VISAPP 2012, pp. 395–398 (2012)Google Scholar
- 4.Gil, A., Reinoso, O., Ballesta, M., Juliá, M.: Multi-robot visual SLAM using a rao-blackwellized particle filter. Robotics and Autonomous Systems, enviado (2008)Google Scholar
- 6.Lui, W., Jarvis, R.: A pure vision-based approach to topological slam. In: 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3784–3791 (2010)Google Scholar
- 7.Paya, L., Fernandez, L., Reinoso, O., Gil, A., Ubeda, D.: Appearance-based dense maps creation. comparison of compression techniques with panoramic images. In: Proc. of the Int. Conf. on Informatics in Control, Automation and Robotics, pp. 238–246. INSTICC, Milan (2009)Google Scholar
- 10.Seber, G.: Multivariate observations. Wiley Interscience (1984)Google Scholar
- 13.Valgren, C., Lilienthal, A.: SIFT, SURF and seasons: Long-term outdoor localization ugin local features. In: Proc. of the 3rd European Conference on Mobile Robots (ECMR), Freiburg, Germany (2007)Google Scholar