Abstract
Real world applications need to cope with unreliable data sources that affect negatively the performance of visual systems, adding error to the whole process. Existing solutions focus their efforts on decreasing the probability of making errors, but if an error occurs, there is no mechanism to deal with it. This work focuses in dealing with this problem by modelling the quality of the segmentation phase in order to apply control mechanisms to mitigate negative effects in later stages. Our control mechanism is based on determining the reliability of local features to discard the less reliables. Local features are characterized using colour, texture, and an illumination reliability model to quantify the quality of illumination. The use of local features enables us to deal with partial occlusion problems by determining the global object position via local features consensus. Experiments were performed, showing promising results in object position estimation under poor illumination conditions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Open dataset extracted from Alfheim Stadium, the home arena for TromsøIL (Norway). Available from: http://home.ifi.uio.no/paalh/dataset/alfheim/.
- 3.
Interdisciplinary Center of Neuroscience of Valparaiso, Chile. http://cinv.uv.cl/en/.
References
Kalal, Z., Matas, J., Mikolajczyk, K.: Tracking learning detection. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1409–1422 (2011)
Yang, F., Lu, H., Yang, M.: Robust superpixel tracking. IEEE Trans. Image Process. 23, 1639–1651 (2014)
Toyama, K., Krumm, J., Brumitt, B., Meyers, B.: Wallflower: principles and practice of background maintenance. In: Proceedings of the International Conference on Computer Vision (ICCV 1999), pp. 255–261 (1999). doi:10.1109/ICCV.1999.791228
Troya-Galvis, A., Gancarski, P., Passat, N., Berti-Equille, L.: Unsupervised quantification of under- and over-segmentation for object-based remote sensing image analysis. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 8, 1936–1945 (2015)
Correia, P.L., Pereira, F.: Objective evaluation of video segmentation quality. IEEE Trans. Image Process. 12, 186–200 (2003)
Erdem, Ç.E., Sankur, B., et al.: Performance measures for video object segmentation and tracking. IEEE Trans. Image Process. 13, 937–951 (2004)
Lee, S., Horio, K.: Human tracking using particle filter with reliable appearance model. In: 2013 Proceedings of SICE Annual Conference (SICE), pp. 1418–1424 (2013)
Wang, L., Yan, H., Wu, H.Y., Pan, C.: Forward-backward mean-shift for visual tracking with local-background-weighted histogram. IEEE Trans. Intell. Transp. Syst. 14, 1480–1489 (2013)
Sun, L., Liu, G.: Visual object tracking based on combination of local description and global representation. IEEE Trans. Circ. Syst. Video Technol. 21, 408–420 (2011)
Adam, A., Rivlin, E., Shimshoni, I.: Robust fragments-based tracking using the integral histogram. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 798–805 (2006)
Breitenstein, M., Reichlin, F., Leibe, B., Koller-Meier, E., Van Gool, L.: Robust tracking-by-detection using a detector confidence particle filter. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1515–1522 (2009)
Zuniga, M.D., Bremond, F., Thonnat, M.: Real-time reliability measure driven multi-hypothesis tracking using 2D and 3D features. EURASIP J. Adv. Signal Process. 2011, 142 (2011). doi:10.1186/1687-6180-2011-142
McIvor, A.: Background subtraction techniques. In: Proceedings of the Conference on Image and Vision Computing (IVCNZ 2000), Hamilton, New Zealand, pp. 147–153 (2000)
Rosten, E., Drummond, T.: Machine learning for high-speed corner detection. In: Proceedings of the IEEE European Conference on Computer Vision (ECCV 2006), vol. 1, pp. 430–443 (2006)
Alahi, A., Ortiz, R., Vandergheynst, P.: Freak: fast retina keypoint. In: Procedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2012), pp. 510–517 (2012)
Bhattacharyya, A.: On a measure of divergence between two statistical populations defined by probability distributions. Bull. Calcutta Math. Soc. 35, 99–110 (1943)
Acknowledgements
This research has been supported, in part, by Fondecyt Project 11121383, Chile.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Orellana, C.M., Zuniga, M.D. (2017). Object Tracking Guided by Segmentation Reliability Measures and Local Features. In: Braz, J., et al. Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2016. Communications in Computer and Information Science, vol 693. Springer, Cham. https://doi.org/10.1007/978-3-319-64870-5_26
Download citation
DOI: https://doi.org/10.1007/978-3-319-64870-5_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-64869-9
Online ISBN: 978-3-319-64870-5
eBook Packages: Computer ScienceComputer Science (R0)