| Abstract: | Aiming at the problems of poor fusion quality, unclear edge contour, low efficiency, poor visibility and low target detection efficiency of the existing infrared and synthetic aperture radar (SAR) image fusion algorithms, a fusion algorithm based on non-subsampled contour wave transform was proposed. Firstly, the preprocessed infrared and SAR images are decomposed by non-subsampled contour wave transform to obtain the respective low-frequency and bandpass direction images. Then, according to the characteristics of infrared and SAR images, the frequency bands containing important target information are selected to fuse the low-frequency and bandpass direction images. In order to test the performance of the proposed algorithm, two groups of infrared and SAR images are used for fusion experiments, and compared with other image fusion algorithms. At the same time, the object detection is carried out on the fused image, which proves that the fusion algorithm can effectively improve the detection rate of multi-source images. |
