Change Detector Combination in Remotely Sensed Images Using Fuzzy Integral

Decision fusion is one of hot research topics in classification area, which aims to achieve the best possible performance for the task at hand. In this paper, we investigate the usefulness of this concept to improve change detection accuracy in remote sensing. Thereby, outputs of two fuzzy change detectors based respectively on simultaneous and comparative analysis of multitemporal data are fused by using fuzzy integral operators. This method fuses the objective evidences produced by the change detectors with respect to fuzzy measures that express the difference of performance between them. The proposed fusion framework is evaluated in comparison with some ordinary fuzzy aggregation operators. Experiments carried out on two SPOT images showed that the fuzzy integral was the best performing. It improves the change detection accuracy while attempting to equalize the accuracy rate in both change and no change classes.

Authors:

• H. Nemmour
• Y. Chibani

Keywords:

• change detection
• decision fusion
• fuzzy logic
• remote sensing.

References:

[1] Bárdossy, A., and Samaniego, L. (2002). Fuzzy Rule-Based
Classification of Remotely Sensed Imagery. IEEE
Transactions on Geoscience and Remote Sensing, 40, 362-
374.
[2] Cho, S. B. (1995). Fuzzy Aggregation of Modular Neural
Networks With Ordered Weighted Averaging Operators.
International journal of approximate reasoning ,13, 359-375.
[3] Cho, S. B., and Kim, J. H. (1995). Combining Multiple
Neural Networks by Fuzzy Integrals for Robust
Classification. IEEE Transactions on Systems, Man and
Cybernetics, 25, 380- 384.
[4] Cho, S. B. (2002). Fusion of Neural Networks with Fuzzy
Logic and Genetic Algorithm. Integrated Computer-Aided
Engineering, IOS Press, 9, 363-372.
[5] Deer, P. (1998). Digital Change Detection in Remotely
Sensed Imagery Using Fuzzy Set Theory. PHD thesis,
Department of Geography and Department of Computer
Science, University of Adelaide, Australia.
[6] Foody, G.M., McCulloch, B., and Yates, W. B. (1995).
Classification of Remotely Sensed Data by an Artificial
Neural Network: Issues Related to Training Data
Characteristics. Photogrammetric Engineering & Remote
Sensing, 61, 391-401.
[7] Kittler, J., Hatef, M., Robert, P. W., and Matas, J. (1998). On
Combining Classifiers. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 20, 226-239.
[8] Bárdossy, A., and Samaniego, L. (2002). Fuzzy Rule-Based
Classification of Remotely Sensed Imagery. IEEE
Transactions on Geoscience and Remote Sensing, 40, 362-
374.
[9] Lambin, E. F., and Strahler, A. H. (1994). Change vector
analysis in multitemporal space : a tool to detect and
categorize land cover change processes using heigh temporal
resolution satellite data. Remote Sensing. Environ, 48, 231-
244.
[10] Lipnickas, A., Malmqvist, K., and Verikas, A. (2000). Fuzzy
Measures in Neural Networks Fusion. ISSN 1392-124X
Informacins Technologijos, 2, 7-16.
[11] Lipnickas, A. (2001). Classifiers Fusion with Data
Dependent Aggregation Schemes. In proceedings of
International Conference on Information Networks, Systems
and Technologies, 147-153.
[12] Liu, Q. Z. et al. (2001). Dynamic Image Sequence Analysis
Using Fuzzy Measures. IEEE transactions on systems, man,
and cybernetics-Part B: Cybernetics, 31, 557- 572.
[13] Verikas, A., Lipnikas, A., Malmqvist, K., Bacauskiene, M.,
and Gelzinis, A. (1999). Soft Combination of Neural
Classifiers: A Comparative Study. Pattern recognition letters,
Elsevier Science, 2, 429-443.
[14] Fullér, R. (1995). Neural Fuzzy System. , .Åbo Academy,
Sweden.