Feature and data-level fusion of infrared and visual images

In both military and civilian applications, increasing interest is being shown in fusing IR and vision images for improved situational awareness. In previous work, the authors have developed a fusion method for combining the thermal and vision images into a single image emphasizing the most salient features of the surrounding environment. This approach is based on the assumption that although the thermal and vision data are uncorrelated, they are complementary and can be fused using a suitable disjunctive function. This paper, as a continuation of that work, will describe the development of an information based real-time data level fusion method. In addition, applicability of the algorithms that we developed for data level fusion to feature level techniques will be investigated.

[1]  Sankar K. Pal,et al.  Multilayer perceptron, fuzzy sets, and classification , 1992, IEEE Trans. Neural Networks.

[2]  Mongi A. Abidi,et al.  Fuzzy logic-based data integration: theory and applications , 1994, Proceedings of 1994 IEEE International Conference on MFI '94. Multisensor Fusion and Integration for Intelligent Systems.

[3]  Steven K. Rogers,et al.  Perceptual-based image fusion for hyperspectral data , 1997, IEEE Trans. Geosci. Remote. Sens..

[4]  D. W. McMichael,et al.  Data fusion for vehicle-borne mine detection , 1996 .

[5]  Robin R. Murphy,et al.  Dempster-Shafer theory for sensor fusion in autonomous mobile robots , 1998, IEEE Trans. Robotics Autom..

[6]  Charles W. Therrien,et al.  An adaptive technique for the enhanced fusion of low-light visible with uncooled thermal infrared imagery , 1997, Proceedings of International Conference on Image Processing.

[7]  M. E. Ulug High speed edge detection by sampling a time series with an orthogonal neural network , 1997, Proceedings of International Conference on Robotics and Automation.