Abstract
Mobile robotics has achieved important progress and level of maturity. Nevertheless, to increase the complexity of the tasks that mobile robots can perform in indoor environments, we need to provide them with a scene understanding of their surrounding. Scene recognition usually involves building image classifiers using training data. These classifiers work with features extracted from the images to recognize different categories. Later on, these classifiers can be used to label any image taken by the robot. The problem is that the training data used to recognize the scene might be redundant and noisy, thus reducing significantly the performance of the classifiers. To avoid this, we propose an unsupervised algorithm able to recognize when an image is unrepresentative, redundant or outlier. We have tested our algorithm in real and difficult environments achieving very promising results which take us a step closer to a complete unsupervised scene recognition with high accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Santos-Saavedra, D., Canedo-Rodriguez, A., Pardo, X.M., Iglesias, R., Regueiro, C.V.: Scene recognition for robot localization in difficult environments. LNCS, vol. 9108, pp. 193–202 (2015)
Canedo-Rodriguez, A., Alvarez-Santos, V., Santos-Saavedra, D., Gamallo, C., Fernandez-Delgado, M., Iglesias, R., Regueiro, C.V.: Robust multi-sensor system for mobile robot localization. In: Natural and Artificial Computation in Engineering and Medical Applications. 5th International Work-Conference on the Interplay between Natural and Artificial Computation. LNCS, vol. 7931, pp. 92–101 (2013)
Tardos, J.D., Neira, J., Newman, P.M., Leonard, J.J.: Robust mapping and localization in indoor environments using sonar data. IJRR 21(4), 311–330 (2002)
Christian, F., et al.: RFID-based hybrid metric-topological SLAM for GPS-denied environments. In: 2013 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2013)
Santos-Saavedra, D., Pardo, X.M., Iglesias, R., Álvarez-Santos, V., Canedo-Rodríguez, A., Regueiro, C.V.: Global image features for scene recognition invariant to symmetrical reflections in robotics. In: XV Workshop of Physical Agents, pp. 29–37 (2014)
Santos-Saavedra, D., Pardo, X.M., Iglesias, R., Canedo-Rodríguez, A., Álvarez-Santos, V.: Scene recognition invariant to symmetrical reflections and illumination conditions in robotics. LNCS, vol. 9117, pp. 130–137 (2015)
Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (SURF). Computer Vision and Image Understanding 110(3), 346–359 (2008)
Meng, X., Wang, Z., Wu, L.: Building global image features for scene recognition. Pattern Recognition 45(1), 373–380 (2012)
Wu, J., Rehg, J.M.: CENTRIST: A Visual Descriptor for Scene Categorization. IEEE Trans. Pattern Analysis and Machine Intelligence 33(8), 1489–1501 (2011)
Simon, I., Snavely, N., Seitz, S.M.: Scene summarization for online image collections. In: ICCV, vol. 7, pp. 1–8 (2007)
Hall, P.M., Owen, M.: Simple canonical views. In: BMVC (2005)
Mitra, P., Murthy, C.A., Pal, S.K.: Unsupervised feature selection using feature similarity. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(3), 301–312 (2002)
Aurenhammer, F., Klein, R.: Voronoi diagrams. In: Sack, J.-R., Urrutia, J. (eds.) Handbook of Computational Geometry, pp. 201–290. North-Holland, Amsterdam (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Santos-Saavedra, D., Iglesias, R., Pardo, X.M. (2016). Unsupervised Method to Remove Noisy and Redundant Images in Scene Recognition. In: Reis, L., Moreira, A., Lima, P., Montano, L., Muñoz-Martinez, V. (eds) Robot 2015: Second Iberian Robotics Conference. Advances in Intelligent Systems and Computing, vol 418. Springer, Cham. https://doi.org/10.1007/978-3-319-27149-1_54
Download citation
DOI: https://doi.org/10.1007/978-3-319-27149-1_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27148-4
Online ISBN: 978-3-319-27149-1
eBook Packages: Computer ScienceComputer Science (R0)