Remote sensing image fusion based on fuzzy theory in pixel level and assessing the quality of resulting images

The technology of image fusion now has been used in the process of remote sensing data. It can integrate the information from multi-sensor data so as to complement the shortage of single sensor image, then more suitable for the purpose of human visual perception, computer-aided object detection, and target recognition. Currently, there are many methods of image fusion we can get from other researcher's study, but these methods of image fusion have some disadvantages. This paper presented the approach of image fusion in pixel level with the fuzzy theory, the source of data used in this paper come from QuickBird image, the resolutions of multi-spectral with four bands and panchromatic image are 2.44m and 0.61m respectively. The process of image fusion is implemented mainly in the fuzzy tool of Matlab. Lastly, assessing the quality of resulting images and these methods of evaluation is based on visually and statistically. The findings that the fused image has remained the attributes of multi-spectral image and high resolution image with 0.61m instead of 2.44m. It is indicated that the fused image is finer than the original multi-spectral image. So the approach of this paper has presented could be a good method to process remote sensing image fusion.

[1]  Wl Lau,et al.  Comparison of image data fusion techniques using entropy and INI , 2016 .

[2]  S. Sides,et al.  Comparison of three different methods to merge multiresolution and multispectral data: Landsat TM and SPOT panchromatic , 1991 .

[3]  Lotfi A. Zadeh,et al.  Fuzzy logic, neural networks, and soft computing , 1993, CACM.

[4]  T. Meitzler,et al.  Fuzzy Logic Based Image Fusion , 2002 .

[5]  Mohammad Reza Saradjian,et al.  Fuzzy Logic System for Road Identification Using Ikonos Images , 2002 .

[6]  Mark J. Shensa,et al.  The discrete wavelet transform: wedding the a trous and Mallat algorithms , 1992, IEEE Trans. Signal Process..

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

[8]  敬忠良,et al.  Multiresolution image fusion scheme based on fuzzy region feature , 2006 .

[9]  R. Crippen A simple spatial filtering routine for the cosmetic removal of scan-line noise from Landsat TM P-tape imagery , 1989 .

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

[11]  Shuang Liu,et al.  Multisource Image Fusion Based on Wavelet Transform , 2006 .

[12]  Christine Pohl,et al.  Multisensor image fusion in remote sensing: concepts, methods and applications , 1998 .

[13]  Yun Zhang PROBLEMS IN THE FUSION OF COMMERCIAL HIGH-RESOLUTION SATELLITE AS WELL AS LANDSAT 7 IMAGES AND INITIAL SOLUTIONS , 2002 .

[14]  L. Wald,et al.  Fusion of satellite images of different spatial resolutions: Assessing the quality of resulting images , 1997 .

[15]  Curt H. Davis,et al.  A hierarchical fuzzy classification approach for high-resolution multispectral data over urban areas , 2003, IEEE Trans. Geosci. Remote. Sens..

[16]  Anil K. Jain,et al.  Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images , 1994, IEEE Trans. Geosci. Remote. Sens..

[17]  J. C. Price,et al.  Comparison of the Information Content of Data from the LANDSAT-4 Thematic Mapper And the Multispectral Scanner , 1984, IEEE Transactions on Geoscience and Remote Sensing.