Abstract
In the last decade, local image features have been widely used in robot visual localization. In order to assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image with those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, in this paper we compare several candidate combiners with respect to their performance in the visual localization task. For this evaluation, we selected the most popular methods in the class of non-trained combiners, namely the sum rule and product rule. A deeper insight into the potential of these combiners is provided through a discriminativity analysis involving the algebraic rules and two extensions of these methods: the threshold, as well as the weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. Furthermore, we address the process of constructing a model of the environment by describing how the model granularity impacts upon performance. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance, confirming the general agreement on the robustness of this rule in other classification problems. The voting method, whilst competitive with the product rule in its standard form, is shown to be outperformed by its modified versions.
Similar content being viewed by others
References
Wang, J., Cipolla, R., Zha, H.: Vision-based global localization using a visual vocabulary. IEEE International Conference on Robotics and Automation, pp. 4230–4235. IEEE, Barcelona, Spain (2005)
Fraundorfer, F., Engels, C., Nister, D.: Topological mapping, localization and navigation using image collections. IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3872–3877. IEEE, San Diego, CA (2007)
Ramisa, A., Tapus, A., Aldavert, D., Toledo, R.: Robust vision-based robot localization using combinations of local feature region detectors. Auton. Robot. 27, 373–385 (2009)
Valgren, C., Lilienthal, A.J.: SIFT, SURF & seasons: appearance-based long-term localization in outdoor environments. Robot. Auton. Syst. 58, 149–156 (2010)
Jurie, F., Triggs, B.: Creating efficient codebooks for visual recognition. IEEE International Conference on Computer Vision, pp. 604–610. IEEE (2005)
Boiman, O., Shechtman, E., Irani, M.: In defense of nearest-neighbor based image classification. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)
Li, F., Yang, X., Kosecka, J.: Global localization and relative positioning based on scale-invariant keypoints. Robot. Auton. Syst. 52, 27–38 (2005)
Goedemé, T., Nuttin, M., Tuytelaars, T., Van Gool, L.: Omnidirectional vision based topological navigation. Int. J. Comput. Vis. 74, 219–236 (2007)
Campos, F.M., Correia, L., Calado, J.MF.: Global localization with non-quantized local image features. Robot. Auton. Syst. 60, 1011–1020 (2012)
Campos, F.M., Correia, L., Calado, J.MF.: An evaluation of local feature combiners for robot visual localization. Robotica 2013, 13th International Conference on Autonomous Robot Systems and Competitions, pp. 44–46 (2013)
Kuncheva, L.: Combining Pattern Classifiers: Methods and Algorithms. Wiley, Hoboken, New Jersey (2004)
Tax, D., Breukelen, M.V., Duin, R., Kittler, J.: Combining multiple classifiers by averaging or by multiplying?Pattern Recognit. 33, 1475–1485 (2000)
Alkoot, F.M., Kittler, J.: Modified product fusion. Pattern Recognit. Lett. 23, 957–965 (2002)
Fumera, G., Roli, F.: A theoretical and experimental analysis of linear combiners for multiple classifier systems. IEEE Trans. Pattern Anal. Mach. Intell. 27, 942–956 (2005)
Misra, H., Bourlard, H., Tyagi, V.: New entropy based combination rules in HMM/ANN multi-stream ASR. In: Proceedings of IEEE International Conference Acoustics, Speech, and Signal Processing (ICASSP ’03), vol. 2, pp. 741–744 (2003)
Sanderson, C., Paliwal, K.: Noise compensation in a person verification system using face and multiple speech features. Pattern Recognit. 36, 293–302 (2003)
Heckmann, M., Berthommier, F., Kroschel, K.: Noise adaptive stream weighting in audio-visual speech recognition. EURASIP J. Appl. Signal Process., 1260–1273 (2002)
Wark, T., Sridharan, S.: Adaptive fusion of speech and lip information for robust speaker identification. Digit. Signal Process. 11, 169–186 (2001)
Seymour, R., Stewart, D., Ming, J.: Audio-visual integration for robust speech recognition using maximum weighted stream posteriors, pp. 654–657. INTERSPEECH (2007)
Gurban, M., Thiran, J.: Dynamic modality weighting for multi-stream hmms inaudio-visual speech recognition. Proceedings of the 10th Conference on Multimodal Interfaces, pp. 237–240. ACM (2008)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004)
Campos, F.M., Correia, L., Calado, J.MF.: Mobile robot global localization with non-quantized SIFT features. The 15th International Conference on Advanced Robotics, pp. 582–587. IEEE, Tallin, Estonia (2011)
Siagian, C., Itti, L.: Rapid biologically-inspired scene classification using features shared with visual attention. IEEE Trans. Pattern Anal. Mach. Intell. 29, 300–312 (2007)
Siagian, C., Itti, L.: Biologically inspired mobile robot vision localization. IEEE Trans. Robot. 25, 861–873 (2009)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Campos, F.M., Correia, L. & Calado, J.M.F. Robot Visual Localization Through Local Feature Fusion: An Evaluation of Multiple Classifiers Combination Approaches. J Intell Robot Syst 77, 377–390 (2015). https://doi.org/10.1007/s10846-013-0016-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-013-0016-3