Learning Photometric Invariance for Object Detection
- 253 Downloads
Color is a powerful visual cue in many computer vision applications such as image segmentation and object recognition. However, most of the existing color models depend on the imaging conditions that negatively affect the performance of the task at hand. Often, a reflection model (e.g., Lambertian or dichromatic reflectance) is used to derive color invariant models. However, this approach may be too restricted to model real-world scenes in which different reflectance mechanisms can hold simultaneously.
Therefore, in this paper, we aim to derive color invariance by learning from color models to obtain diversified color invariant ensembles. First, a photometrical orthogonal and non-redundant color model set is computed composed of both color variants and invariants. Then, the proposed method combines these color models to arrive at a diversified color ensemble yielding a proper balance between invariance (repeatability) and discriminative power (distinctiveness). To achieve this, our fusion method uses a multi-view approach to minimize the estimation error. In this way, the proposed method is robust to data uncertainty and produces properly diversified color invariant ensembles. Further, the proposed method is extended to deal with temporal data by predicting the evolution of observations over time.
Experiments are conducted on three different image datasets to validate the proposed method. Both the theoretical and experimental results show that the method is robust against severe variations in imaging conditions. The method is not restricted to a certain reflection model or parameter tuning, and outperforms state-of-the-art detection techniques in the field of object, skin and road recognition. Considering sequential data, the proposed method (extended to deal with future observations) outperforms the other methods.
KeywordsObject detection Color models Learning Photometric invariance Combining classifiers Diversified ensembles
Unable to display preview. Download preview PDF.
- Álvarez, J. M., López, A. M., & Baldrich, R. Illuminant-invarariant model-based road segmentation. In Proceedings of the 2008 IEEE international vehicles symposium (IV’08), Eindhoven, The Netherlands. Google Scholar
- Brown, G., Wyatt, J., Harris, R., & Yao, X. (2005). Diversity creation methods: a survey and categorisation. Google Scholar
- Finlayson, G. D., Drew, M. S., & Lu, C. (2004). Intrinsic images by entropy minimization. In Proceedings of the European conference on computer vision (ECCV) (Vol. 3, pp. 582–595). Google Scholar
- Finlayson, G., Hordley, S., Lu, C., & Drew, M. (2006). On the removal of shadows from images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(1). Google Scholar
- Fleck, M. M., Forsyth, D. A., & Bregler, C. (1996). Finding naked people. In Proceedings of the European conference on computer vision (ECCV) (Vol. 3, pp. 593–602). Berlin: Springer Google Scholar
- Ikonomakis, N., Plataniotis, K., & Venetsanopoulos, A. (2000). Color image segmentation for multimedia applications. Journal of Intelligent Robotics Systems, 28(1–2). Google Scholar
- Kender, J. (2005). Saturation, hue and normalized color: calculation, digitation effects, and use (Tech. Rep. CMU-RI-TR-05-40). Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. Google Scholar
- Kovac, J., Peer, P., & Solina, F. (2003). Human skin color clustering for face detection. In International conference on computer as a tool (EUROCON). Google Scholar
- Markowitz, H. M. (1959). Portfolio selection: efficient diversification of investments. New York: Wiley. Google Scholar
- Melville, P., & Mooney, R. J. (2005). Creating diversity in ensembles using artificial data. Information Fusion, 6(3), 1553–1563. Google Scholar
- Michaud, R. O., & Michaud, R. (2008). Estimation error and portfolio optimization: a resampling solution. Journal of Investment Management, 6(1), 8–28. Google Scholar
- Michaud, R. O. (1998). Efficient asset management: a practical guide to stock portfolio optimization and asset allocation. Oxford: Oxford University Press. Google Scholar
- Rasmussen, M. (2003). Quantitative portfolio optimisation, asset allocation and risk management (Finance and capital markets). Basingstoke: Palgrave Macmillan. Google Scholar
- Rotaru, C., Graf, T., & Zhang, J. (2008). Color image segmentation in hsi space for automotive applications. Journal of Real-Time Image Processing, 1164–1173. Google Scholar
- Scherer, B. (2002). Portfolio construction and risk budgeting (Chap. 4). London: Rosk Books. Google Scholar
- Sotelo, M., Rodriguez, F., Magdalena, L., Bergasa, L., & Boquete, L. (2004). A color vision-based lane tracking system for autonomous driving in unmarked roads. Autonomous Robots, 16(1). Google Scholar
- Tan, C., Hong, T., Chang, T., & Shneier, M. (2006). Color model-based real-time learning for road following. In Proceedings of the IEEE international conference on intelligent transport systems (pp. 939–944). Google Scholar
- Usmen, N. M. H. (2003). Resampled frontiers versus diffuse Bayes: an experiment. Journal of Investment Management, 1(4), 1–17. Google Scholar
- van de Sande, K. E. A., Gevers, T., & Snoek, C. G. M. (2008). Evaluation of color descriptors for object and scene recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 453–464). Google Scholar
- Weber, M. (1999). The Caltech frontal face dataset. California Inst. of Tech., USA. http://www.vision.caltech.edu/html-files/archive.html. Accessed 1 March 2010.
- Wyszecki, G., & Stiles, W. (1982). Color science: concepts and methods, quantitative data and formulae (2nd ed.). New York: Wiley. Google Scholar