Novel method on dual-band infrared image fusion for dim small target detection

The paper puts forward a fractal dimension algorithm that fuses mid-wave and long-wave infrared images and detects targets. Usually, the targets in infrared images are man-made, and their fractal dimensions are different from that of their natural background. In the fractal dimension algorithm, the source images are first decomposed by wavelet transformation. Then in the wavelet transformation domain, fractal dimensions are calculated and fusion rules that merge corresponding sub images of two matching source images are set up, and new sub images are created. Finally, the image is reconstructed by inverse wavelet transformation and a fused image is obtained. The fusion results have shown that the contrast between the targets and their background has changed significantly, and the targets can be easily detected by applying a contrast threshold. The experimental results have shown that the method using fractal dimension to fuse dualband infrared images and detect targets is superior to the one using mid-wave or longwave infrared images to detect targets alone.

[1]  Francesco Camastra,et al.  Data dimensionality estimation methods: a survey , 2003, Pattern Recognit..

[2]  Vladimir Petrovic,et al.  Cross-band pixel selection in multiresolution image fusion , 1999, Defense, Security, and Sensing.

[3]  Hongxing Sun,et al.  The precise position and attitude resolution in MMS based on the integration of GPS/INS , 2005, International Conference on Space Information Technology.

[4]  John K. Goutsias,et al.  Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators , 2004, J. Electronic Imaging.

[5]  Rama Chellappa,et al.  A multi-fractal formalism for stabilization, object detection and tracking in FLIR sequences , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[6]  C. Roques-carmes,et al.  Fractal approach to two-dimensional and three-dimensional surface roughness , 1986 .

[7]  Dana H. Brooks,et al.  Point target detection in IR image sequences: a hypothesis-testing approach based on target and clutter temporal profile matching , 2000 .

[8]  Guangxi Zhu,et al.  Recognition of low-contrast FLIR tank object based on multiscale fractal character vector , 1996, Defense, Security, and Sensing.

[9]  Lorenzo Bruzzone,et al.  Image fusion techniques for remote sensing applications , 2002, Inf. Fusion.

[10]  Pramod K. Varshney.  Multisensor data fusion , 1997 .

[11]  Nirupam Sarkar,et al.  An Efficient Differential Box-Counting Approach to Compute Fractal Dimension of Image , 1994, IEEE Trans. Syst. Man Cybern. Syst..

[12]  Rick S. Blum.  Robust image fusion using a statistical signal processing approach , 2005, Inf. Fusion.

[13]  B. S. Manjunath,et al.  Multisensor Image Fusion Using the Wavelet Transform , 1995, CVGIP Graph. Model. Image Process..

[14]  Alexander Toet,et al.  Fusion of visible and thermal imagery improves situational awareness , 1997, Defense, Security, and Sensing.

[15]  Jian Liu,et al.  Background suppression based-on wavelet transformation to detect infrared target , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[16]  Joseph Naor,et al.  Multiple Resolution Texture Analysis and Classification , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Heesung Kwon,et al.  Adaptive target detection in forward-looking infrared imagery using the eigenspace separation transform and principal component analysis , 2004 .

[18]  Jian Liu,et al.  Infrared image dim small target detection based on double energy accumulation , 2005, International Conference on Space Information Technology.

[19]  Kuo-Chu Chang,et al.  Target identification with Bayesian networks in a multiple hypothesis tracking system , 1997 .

[20]  Zhenming Peng,et al.  Dim target detection based on nonlinear multifeature fusion by Karhunen-Loeve transform , 2004 .

[21]  Alex Pentland,et al.  Fractal-Based Description of Natural Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.