Abstract
The loop closure problem is central to topological simultaneous localization and mapping (SLAM); by associating features between distant portions of a trajectory, the odometry error that has accumulated between two observations can be eliminated and a more consistent map can be built. Bayesian pattern recognition techniques such as bag of visual words (BoVW) have recently shown outstanding results in solving the loop closure problem completely in image space using very simple, inexpensive cameras, without the requirement for highly accurate metric information, 3D reconstruction, or camera calibration. In this paper, a modified BoVW descriptor that incorporates simple geometric relationships within an image is used with the fast appearance-based mapping (FAB-MAP) algorithm. In direct comparisons with the traditional BoVW descriptor, an improved recall rate is observed with an acceptable increase in computational time. The proposal of a BoVW-compatible descriptor and the use of the proposed descriptor with a well-known BoVW classifier demonstrate the ability of the BoVW metaphor to be generalized, which could pave the way for more various BoVW descriptors in the same way that many individual visual feature descriptors exist within the computer vision community.
Similar content being viewed by others
References
Thrun S (2001) Probabilistic robotics. MIT Press, Cambridge
Bradski G (2000) OpenCV. Dr Dobb’s J Softw Tools
Fischler M, Bolles R (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395
Sivic J, Zisserman A (2003) Video Google: a text retrieval approach to object matching in videos. Int Conf Comput Vis 2:1470–1477. doi:10.1109/ICCV.2003.1238663
Cummins M, Newman P (2008) FAB-MAP: probabilistic localization and mapping in the space of appearance. Int J Robot Res 27(6):647–665. doi:10.1177/0278364908090961
Cummins M, Newman P (2010) Appearance-only SLAM at large scale with FAB-MAP 2.0. Int J Robot Res 30(9):1100–1123. doi:10.1177/0278364910385483
Pérez J, Caballero F, Merino L (2015) Enhanced Monte Carlo localization with visual place recognition for robust robot localization. J Intell Robot Syst 1–16. doi:10.1007/s10846-015-0198-y
Yang C, Shengnan C, Jingdong W, Quan L (2014) Low-rank sift: an affine invariant feature for place recognition. Comput Res Repos 1–5. arXiv:1408.1688
Sünderhauf N, Dayoub F, Shirazi S, Upcroft B, Milford M (2015) On the performance of ConvNet features for place recognition. Comput Res Repos 1–8. arXiv:1501.04158
Cao J, Chen T, Fan J (2014) Fast online learning algorithm for landmark recognition based on BoW framework. IEEE Trans Ind Appl 1163–1168. doi:10.1109/ICIEA.2014.6931341
Johns E, Yang G (2014) Pairwise probabilistic voting: fast place recognition without RANSAC. Comput Vis ECCV 505–519. doi:10.1007/978-3-319-10605-2_33
Bolovinou A, Pratikakis I, Perantonis S (2012) Bag of spatio-visual words for context inference in scene classification. Pattern Recognit 46(3):1039–1053. doi:10.1016/j.patcog.2012.07.024
Duda R, Hart P, Stork D (2000) Pattern classification. Wiley, New York
Bay H, Tuytelaars T, Van Gool L (2006) SURF: speeded up robust features. Comput Vis ECCV 404–417. doi:10.1007/11744023_32
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 602(2):91–110. doi:10.1023/B:VISI.0000029664.99615.94
Rublee E, Rabaud V (2011) ORB: an efficient alternative to SIFT or SURF. Comput Vis ECCV 2564–2571. doi:10.1109/ICCV.2011.6126544
Calonder M, Lepetit V, Strecha C, Fua P (2010) Brief: binary robust independent elementary features. Comput Vis ECCV IV:778–792. doi:10.1007/978-3-642-15561-1_56
Cormen T, Leiserson C, Rivest R, Stein C (2001) Introduction to algorithms, 2nd edn. MIT Press, Cambridge
Chow C, Lee C (1968) Approximating discrete probability distributions with dependence trees. IEEE Trans Inf Theory 14(3):462–467. doi:10.1109/TIT.1968.1054142
Acknowledgments
This research was supported by the MOTIE under the Industrial Foundation Technology Development Program supervised by KEIT (No. 10051155) and by Basic Science Research Program through the NRF funded by MSIP (No. 2007-0056094).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Stalbaum, J., Chae, HW. & Song, JB. Scene recognition with bag of visual nouns and prepositions. Intel Serv Robotics 8, 115–125 (2015). https://doi.org/10.1007/s11370-015-0167-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11370-015-0167-0