Abstract
Tracking objects in environments under non-uniform illumination condition is particularly challenging as the observed appearance may change in space and time. Adapting the appearance model increases the risk of drifts, while iltering out the illumination information through built-in invariance reduces the discriminative capabilities. In this work we adhere to color constancy principles to learn the appearance variation induced by non-uniform illumination and we use this information to perform location-dependent color corrections to boost tracking performance. The training procedure is carried out in an unsupervised manner by exploiting walking people as illumination probes and an on-line, non-parametric regression method is developed to densely predict the location-specific color transformations.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Babenko, B., Yang, M.H., Belongie, S.: Visual tracking with online multiple instance learning. IEEE Trans. on PAMI (August 2011)
Bardet, F., Chateau, T., Ramadasan, D.: Illumination aware mcmc particle filter for long-term outdoor multi-object simultaneous tracking and classification. In: ICCV (2009)
Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: The clear mot metrics. J. Image Video Process (2008)
Vezzani, R., Grana, C., Cucchiara, R.: Probabilistic people tracking with appearance models and occlusion classification. Pattern Recogn. Lett. 32(6) (2011)
Camplani, M., Salgado, L.: Adaptive background modeling in multicamera system for real-time object detection. SPIE Optical Eng. 50(12) (2011)
Chakrabarti, A., Hirakawa, K., Zickler, T.: Color constancy with spatio-spectral statistics. IEEE Trans. on PAMI (2012)
Cristani, M., Farenzena, M., Bloisi, D., Murino, V.: Background subtraction for automated multisensor surveillance: A comprehensive review. EURASIP Journal on Advances in Signal Processing 2010(1), 343057 (2010)
Ellis, L., Dowson, N., Matas, J., Bowden, R.: Linear regression and adaptive appearance models for fast simultaneous modelling and tracking. Int. J. Comput. Vision 95(2), 154–179 (2011)
Finlayson, G., Drew, M., Funt, B.: Diagonal transforms suffice for color constancy. In: ICCV (1993)
Gijsenij, A., Gevers, T., van de Weijer, J.: Computational color constancy: Survey and experiments. IEEE Trans. on Image Processing 20(9), 2475–2489 (2011)
Jepson, A., Fleet, D., El-Maraghi, T.: Robust online appearance models for visual tracking. IEEE Transactions on PAMI 25(10), 1296–1311 (2003)
Lanz, O.: Approximate bayesian multi-body tracking. IEEE Trans. on Pattern Analysis and Machine Intelligence (2006)
Lanz, O., Messelodi, S.: A sampling algorithm for occlusion robust multi-target detection. In: AVSS (2009)
Lecca, M., Messelodi, S.: Linking the von Kries Model to Wien’s Law for the estimation of an Illuminant Invariant Image. Pattern Recognition Letters 32(15), 2086–2096 (2011)
Mutlu, S., Hu, T., Lanz, O.: Learning the scene illumination for color-based people tracking in dynamic environment. In: Petrosino, A. (ed.) ICIAP 2013, Part II. LNCS, vol. 8157, pp. 683–692. Springer, Heidelberg (2013)
Tsai, Y., Ko, C., Hung, Y., Shih, Z.: Background removal of multiview images by learning shape priors. IEEE Trans. on Image Processing (2007)
Zen, G., Lanz, O., Messelodi, S., Ricci, E.: Tracking multiple people with illumination maps. In: ICPR (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Mutlu, S., Rota Bulò, S., Lanz, O. (2014). Exploiting Color Constancy for Robust Tracking Under Non-uniform Illumination. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2014. Lecture Notes in Computer Science(), vol 8815. Springer, Cham. https://doi.org/10.1007/978-3-319-11755-3_45
Download citation
DOI: https://doi.org/10.1007/978-3-319-11755-3_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11754-6
Online ISBN: 978-3-319-11755-3
eBook Packages: Computer ScienceComputer Science (R0)