Abstract
A new feature-level image fusion technique for object segmentation is presented. The proposed technique approaches fusion as a feature selection problem, utilizing a selection criterion based on mutual information. Starting with object regions roughly detected from one sensor, the proposed technique aims to extract relevant information from another sensor to best complete the object segmentation. First, a contour-based feature representation is presented that implicitly captures object shape. The notion of relevance across sensor modalities is then defined using mutual information computed based on the affinity between contour features. Finally, a heuristic selection scheme is proposed to identify the set of contour features having the highest mutual information with the input object regions. The approach works directly from the input image pair without relying on a training phase. The proposed algorithm is evaluated using a typical surveillance setting. Quantitative results and comparative analysis with other potential fusion methods are presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Chapter's References
T. Bakert and P. Losiewicz. Force aggregation via bayesian nodal analysis. In Proceedings of Information Technology Conference, 1998
P. Bogler. Shafer-Dempster reasoning with applications to multisensor target identification systems. IEEE Transactions on System, Man, and Cybernetics, 17:968–977, 1987
D. Borghys, P. Verlinde, C. Perneel, and M. Acheroy. Multi-level data fusion for the detection of targets using multi-spectral image sequences. SPIE Optical Engineering, Special Issue on Sensor Fusion, 37:477–484, 1998
P.J. Burt and R.J. Kolczynski. Enhanced image capture through fusion. In Proceedings of Computer Vision and Pattern Recognition, 173–182, 1993
F. Corbett et al. Fused ATR algorithm development for ground to ground engagement. In Proceedings of the 6th National Sensory Symposium, volume 1, pages 143–155, 1993
T. Cover and J. Thomas. Elements of Information Theory. J. Wiley, New York, 1991
N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In Proceedings of the International Conference Computer Vision, pages 886–893, 2005
S. Das and W. Krebs. Sensor fusion of multi-spectral imagery. Electronics Letters, 36:1115– 1116, 2000
B. Dasarathy. Decision Fusion. IEEE Computer Society Press, Washington, DC, 1994
J. Davis and V. Sharma. Background-subtraction in thermal imagery using contour saliency. International Journal of Computer Vision, 71(2):161–181, 2007
J. Davis and V. Sharma. Background-subtraction using contour-based fusion of thermal and visible imagery. Computer Vision and Image Understanding, 106(2–3):162–182, 2007
R. Delaonoy, J. Verly, and D. Dudgeon. Pixel-level fusion using interest images. In Proceedings of the 4th National Symposium on Sensor Fusion, volume 1, pages 29–41. IRIA (ERIM), 1991
D.A. Fay et al. Fusion of multi-sensor imagery for night vision: Color visualization, target learning and search. In 3rd International Conference on Information Fusion, pages TuD3-3– TuD3-10, 2000
M. Hinman. Some computational approaches for situation assessment and impact assessment. In Proceedings of the Fifth International Conference on Information Fusion, pages 687–693, 2002
N. Kwak and C. Choi. Input feature selection by mutual information based on parzen window. IEEE Transactions Pattern Analyis and Machine Intelligence, 24(12):1667–1671, 2002
L. Lazofson and T. Kuzma. Scene classification and segmentation using multispectral sensor fusion implemented with neural networks. In Proceedings of the 6th National Sensor Symposium, volume 1, pages 135–142, 1993
J. Lewis, R. O'Callaghan, S. Nikolov, D. Bull, and C. Cangarajah. Region-based image fusion using complex wavelets. In International Conference on Information Fusion, pages 555–562, 2004
N. Li, S. Dettmer, and M. Shah. Visually recognizing speech using eigensequences. In Motion-Based Recognition, pages 345–371. Kluwer Academic, Dordrecht, 1997
H. Li, B.S. Manjunath, and S.K. Mitra. Multisensor image fusion using the wavelet transform. In Graphical Model and Image Processing, volume 57, pages 234–245, 1995
J. Lowrance, T. Garvey, and T. Strat. A framework for evidential reasoning system. In Proceedings of the Fifth National Conference on Artificial Intelligence, pages 896–901, 1986
K. Mikolajczyk, A. Zisserman, and C. Schmid. Shape recognition with edge-based features. In British Machine Vision Conference, pages 779–788, 2003
B. Park and J. Marron. Comparison of data-driven bandwidth selectors. Journal of American Statistics Association, 85(409):66–72, 1990
M. Pavel, J. Larimer, and A. Ahumada. Sensor fusion for synthetic vision. In AIAA Conference on Computing in Aerospace 8. A Collection of Technical Papers, vol. CP9110-1, pp. 164–173, AIAA, Washington, DC, 1991
H. Peng, F. Long, and C. Ding. Feature selection based on mutual information criteria of max-dependency, max-relevance and min-redundancy. IEEE Transaction Pattern Analyis and Machine Intelligence, 27(8):1226–1238, 2005
V. Petrovic and C. Xydeas. Gradient-based multiresolution image fusion. IEEE Transactions on Image Processing, 13(2):228–237, 2004
G. Piella. A region-based multiresolution image fusion algorithm. In Information Fusion, pages 1557–1564, 2002
C. Ramac, M. Uner, P. Varshney, M. Alford, and D. Ferris. Morphological filters and wavelet-based image fusion for concealed weapons detection. Proceedings of SPIE, 3376:110–119, 1998
R. Raskar, A. Llie, and J. Yu. Image fusion for context enhancement and video surrealism. In Non-Photorealistic Animation and Rendering, pages 85–94. ACM, 2004.
C. Van Rijsbergen. Information Retrieval. 2nd ed. University of Glasgow, Glasgow, 1979
P. Scheunders. Multiscale edge representation applied to image fusion. In Wavelet Applications in Signal and Image Processing VIII, pages 894–901, 2000
V. Sharma and J. Davis. Feature-level fusion for object segmentation using mutual information. In IEEE International Workshop on Object Tracking and Classification Beyond the Visible Spectrum, 2006
E. Sharon, A. Brandt, and R. Basri. Completion energies and scale. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(10):1117–1131, 2000
D.A. Socolinsky and L.B. Wolff. A new visualization paradigm for multispectral imagery and data fusion. In Proceedings of Computer Vision and Pattern Recognition, pages 319–324, 1999
A. Toet. Hierarchical image fusion. Machine Vision and Applications, 3:1–11, 1990
K. Torkkola. Feature extraction by non-parametric mutual information maximization. The Journal of Machine Learning Research, 3:1415–1438, 2003
P. Varshney. Distributed Detection and Data Fusion. Springer Verlag, New York, 1996
L. Williams and D. Jacobs. Stochastic completion fields: A neural model of illusory contour shape and salience. Neural Computation, 9(4):837–858, 1997
M. Kokar, and Z. Korona. Model-based fusion for multisensor target recognition. Proceedings of SPIE, 2755:178–189, 1996
Z. Zhang and R. Blum. Region-based image fusion scheme for concealed weapon detection. In Proceedings of the 31st Annual Conference on Information Sciences and Systems, pp. 168– 173, 1997
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Sharma, V., Davis, J.W. (2009). Feature-Level Fusion for Object Segmentation Using Mutual Information. In: Hammoud, R.I. (eds) Augmented Vision Perception in Infrared. Advances in Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-84800-277-7_13
Download citation
DOI: https://doi.org/10.1007/978-1-84800-277-7_13
Publisher Name: Springer, London
Print ISBN: 978-1-84800-276-0
Online ISBN: 978-1-84800-277-7
eBook Packages: Computer ScienceComputer Science (R0)