This paper describes a probabilistic approach to the problem of recognizing places based on their appearance. The system we present is not limited to localization, but can determine that a new observation comes from a previously unseen place, and so augment its map. Effectively this is a SLAM system in the space of appearance. Our probabilistic approach allows us to explicitly account for perceptual aliasing in the environment—identical but indistinctive observations receive a low probability of having come from the same place. We achieve this by learning a generative model of place appearance. By partitioning the learning problem into two parts, new place models can be learned online from only a single observation of a place. The algorithm complexity is linear in the number of places in the map, and is particularly suitable for online loop closure detection in mobile robotics.
Bach, F.R. and Jordan, M.I. (2002). Thin junction trees. Advances in Neural Information Processing Systems.
2.
Bay, H., Tuytelaars, T. and Van Gool, L. (2006). SURF: Speeded Up Robust Features. Proceedings of the 9th European Conference on Computer Vision, Graz, Austria, Vol. 13, pp. 404-417.
3.
Bishop, Y.M., Fienberg, S.E. and Holland, P.W. (1977). Discrete Multivariate Analysis: Theory and Practice . Cambridge, MA, MIT Press.
4.
Bowling, M., Wilkinson, D. and Ghodsi, A. (2006). Subjective mapping. Twenty-First National Conference on Artificial Intelligence. Boston, MA, AAAI Press.
5.
Bowling, M., Wilkinson, D., Ghodsi, A. and Milstein, A. (2005). Subjective localization with action respecting embedding. Proceedings of the International Symposium of Robotics Research.
6.
Chen, C. and Wang, H. (2006). Appearance-based topological Bayesian inference for loop-closing detection in a cross-country environment. International Journal of Robotics Research, 25(10): 953-983.
7.
Chow, C. and Liu, C. (1968). Approximating discrete probability distributions with dependence trees. IEEE Transactions on Information Theory , 14(3): 462-467.
8.
Cormen, T.H., Leiserson, C.E., Rivest, R.L. and Stein, C. (2001). Introduction to Algorithms, 2nd edn. Cambridge, MA, MIT Press .
9.
Cummins, M. and Newman, P. (2007). Probabilistic appearance based navigation and loop closing. Proceedings IEEE International Conference on Robotics and Automation (ICRA'07), Rome.
10.
Dementiev, R., Sanders, P., Schultes, D. and Sibeyn, J. (2004). Engineering an external memory minimum spanning tree algorithm. Proceedings 3rd International Conference on Theoretical Computer Science.
11.
Ferreira, F., Santos, V. and Dias, J. (2006). Integration of multiple sensors using binary features in a Bernoulli mixture model. Proceedings IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems, pp. 104-109.
12.
Filliat, D. (2007). A visual bag of words method for interactive qualitative localization and mapping. Proceedings IEEE International Conference on Robotics and Automation, 3921- 3926.
13.
Frome, A., Huber, D., Kolluri, R., Bulow, T. and Malik, J. (2004). Recognizing objects in range data using regional point descriptors. Proceedings of the European Conference on Computer Vision . Berlin, Springer.
14.
Goedemé, T. (2006). Visual navigation. Ph.D. Thesis, Katholieke Universiteit Leuven.
15.
Gumbel, E.J. (1958). Statistics of Extremes. New York, Columbia University Press.
16.
Gutmann, J. and Konolige, K. (1999). Incremental mapping of large cyclic environments . Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA). Monterey, CA, pp. 318-325. http://citeseer.ist.psu.edu/gutmann00incremental.html .
17.
Ho, K. and Newman, P. (2005a). Combining visual and spatial appearance for loop closure detection. Proceedings of the European Conference on Mobile Robotics .
18.
Ho, K. and Newman, P. (2005b). Multiple map intersection detection using visual appearance. Proceedings of the International Conference on Computational Intelligence, Robotics and Autonomous Systems, Singapore.
19.
Ho, K.L. and Newman, P. (2007). Detecting loop closure with scene sequences. International Journal of Computer Vision, 74(3): 261-286.
20.
Johnson, A. (1997). Spin-Images: a representation for 3-D surface matching. Ph.D. thesis, Robotics Institute, Carnegie Mellon University, Pittsburgh, PA.
21.
Jordan, M.I., Ghahramani, Z., Jaakkola, T.S. and Saul, L.K. (1999). An introduction to variational methods for graphical models. Machine Learning, 37(2): 183-233.
22.
Kröse, B.J.A., Vlassis, N.A., Bunschoten, R. and Motomura, Y. (2001). A probabilistic model for appearance-based robot localization. Image and Vision Computing, 19(6): 381- 391.
23.
Lamon, P., Nourbakhsh, I., Jensen, B. and Siegwart, R. (2001). Deriving and matching image fingerprint sequences for mobile robot localization. Proceedings of the IEEE International Conference on Robotics and Automation, Seoul, Korea.
24.
Levin, A. and Szeliski, R. (2004). Visual odometry and map correlation. Proceedings IEEE Conference on Computer Vision and Pattern Recognition , pp. 611-618.
25.
Li, F. and Kosecka, J. (2006). Probabilistic location recognition using reduced feature set. IEEE International Conference on Robotics and Automation. Orlando, FL.
26.
Lowe, D.G. (1999). Object recognition from local scale-invariant features. Proceedings of the 7th International Conference on Computer Vision, Kerkyra, pp. 1150-1157.
27.
Meila, M. (1999). An accelerated Chow and Liu algorithm: Fitting tree distributions to high-dimensional sparse data. ICML '99: Proceedings of the Sixteenth International Conference on Machine Learning. San Francisco, CA, Morgan Kaufmann, pp. 249-257.
28.
Meila2-Predoviciu, M. (1999). Learning with mixtures of trees. Ph.D. Thesis, Massachusetts Institute of Technology.
29.
Mozos, O., Stachniss, C. and Burgard, W. (2005). Supervised learning of places from range data using AdaBoost. Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1730-1735.
30.
Newman, P. and Ho, K. (2005). SLAM - loop closing with visually salient features . Proceedings of the IEEE International Conference on Robotics and Automation.
31.
Newman, P.M., Cole, D.M. and Ho, K. (2006). Outdoor SLAM using visual appearance and laser ranging. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Orlando, FL.
32.
Nister, D. and Stewenius, H. (2006). Scalable recognition with a vocabulary tree. Proceedings of the Conference on Computer Vision and Pattern Recognition , Vol. 2, pp. 2161- 2168.
33.
Page, L., Brin, S., Motwani, R. and Winograd, T. (1998). The PageRank citation ranking: bringing order to the web. Technical Report, Stanford Digital Library Technologies.
34.
Ramos, F.T., Upcroft, B., Kumar, S. and Durrant-Whyte, H.F. (2005). A Bayesian approach for place recognition. Proceedings of the IJCAI Workshop on Reasoning with Uncertainty in Robotics.
35.
Ranganathan, A. and Dellaert, F. (2006). A Rao-Blackwellized particle filter for topological mapping. Proceedings of International Conference on Robotics and Automation, Orlando, FL.http://www.cc.gatech.edu/dellaert/pub/Ranganathan06icra.pdf.
36.
Schindler, G., Brown, M., and Szeliski, R. (2007). City-scale location recognition. Proceedings IEEE Conference on Computer Vision and Pattern Recognition , pp. 1-7.
37.
Se, S., Lowe, D.G. and Little, J. (2005). Vision based global localisation and mapping for mobile robots. IEEE Transactions on Robotics, 21(3): 364-375.
38.
Silpa-Anan, C. and Hartley, R. (2004). Localisation using an image-map. Proceedings of the Australian Conference on Robotics and Automation .
39.
Silpa-Anan, C. and Hartley, R. (2005). Visual localization and loop-back detection with a high resolution omnidirectional camera. Proceedings of the Workshop on Omnidirectional Vision.
40.
Sim, R. and Dudek, G. (1998). Mobile robot localization from learned landmarks . Proceedings of the IEEE International Conference on Intelligent Robots and Systems, p. 2.
41.
Sivic, J. and Zisserman, A. (2003). Video Google: a text retrieval approach to object matching in videos. Proceedings of the International Conference on Computer Vision, Nice, France.
42.
Squire, D., Müller, W., Müller, H. and Pun, T. (2000). Content-based query of image databases: inspirations from text retrieval. Pattern Recognition Letters, 21(13-14): 1193- 1198.
43.
Srebro, N. (2001). Maximum likelihood bounded tree-width markov networks . Proceedings of the 17th Annual Conference on Uncertainty in Artificial Intelligence (UAI-01). San Francisco, CA, Morgan Kaufmann, pp. 504-551.
44.
Torralba, A., Murphy, K.P., Freeman, W.T. and Rubin, M.A. (2003). Context-based vision system for place and object recognition. ICCV '03: Proceedings of the Ninth IEEE International Conference on Computer Vision. Washington, DC, IEEE Computer Society, p. 273
45.
Ulrich, I. and Nourbakhsh, I. (2000). Appearance-based place recognition for topological localization. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Vol. 2, pp. 1023-1029.
46.
Wang, J., Zha, H. and Cipolla, R. (2005). Vision-based global localization using a visual vocabulary. Proceedings of the IEEE International Conference on Robotics and Automation.
47.
Wolf, J., Burgard, W. and Burkhardt, H. (2005). Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization. IEEE Transactions on Robotics, 21(2): 208-216.
48.
Zivkovic, Z., Bakker, B. and Kröse, B. (2005). Hierarchical map building using visual landmarks and geometric constraints. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 7-12.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
