Wide-Baseline Visible Features for Highly Dynamic Scene Recognition
This paper describes a new visual feature to especially address the problem of highly dynamic place recognition. The feature is obtained by identifying existing local features, such as SIFT or SURF, that have wide baseline visibility within the place. These identified local features are then compressed into a single representative feature, a wide-baseline visible feature, which is computed as an average of all the features associated with it. The proposed feature is especially robust against highly dynamical changes in scene; it can be correctly matched against a number of features collected from many dynamic images. This paper also describes an approach to using these features for scene recognition. The recognition proceeds by matching individual feature to a set of features from testing images, followed by majority voting to identify a place with the highest matched features. The proposed feature is trained and tested on 2000+ outdoor omnidirectional. Despite its simplicity, wide-baseline visible feature offers two times better rate of recognition (ca. 93%) than other features. The number of features can be further reduced to speed up the time without dropping in accuracy, which makes it more suitable to long-term scene recognition and localization.
KeywordsMajority Vote Distant Object Outdoor Scene Scene Recognition Place Recognition
Unable to display preview. Download preview PDF.
- 1.Kittler, J., et al.: On Combining Classifiers. IEEE T PAMI 20(3), 226–239 (1998)Google Scholar
- 2.Filliat, D.: A visual bag of words method for interactive qualitative localization and mapping. In: ICRA (2007)Google Scholar
- 3.Lazebnik, S., et al.: Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories. In: CVPR (2006)Google Scholar
- 4.Thrun, S.: Finding Landmarks for Mobile Robot Navigation. In: ICRA (1998)Google Scholar
- 5.Ullah, M.M., et al.: Towards Robust Place Recognition for Robot Localization. In: ICRA (2008)Google Scholar
- 8.Torralba, A., et al.: Context-Based Vision System for Place and Object Recognition. In: ICCV (2003)Google Scholar
- 9.Wu, J., Rehg, J.M.: Where am I: Place instance and category recognition using spatial PACT. In: CVPR (2008)Google Scholar
- 10.Cummins, M., Newman, P.: FAB-MAP: Probabilistic Localization and Mapping in the Space of Appearance. IJRR 27(6), 647–665 (2008)Google Scholar
- 11.Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. IEEE T PAMI 27(10), 1615–1630 (2005)Google Scholar
- 12.Kivinen, J.J., et al.: Learning Multiscale Representation of Natural Scenes Using Dirichlet Processes. In: ICCV (2007)Google Scholar
- 15.Ulrich, I., Nourbakhsh, I.R.: Appearance-based Place Recognition for Topological Localization. In: ICRA (2000)Google Scholar
- 16.Fei-Fei, L., Perona, P.: A Bayesian Hierarchical Model for Learning Natural Scene Categories. In: CVPR (2005)Google Scholar