Fusion of Remotely-Sensed Imagery using a Unique Wavelet-based Reconstruction Method

S.P. Kozaitis and M. Ouendeno (USA)


Conditional entropy, entropy, image fusion, mutual information, wavelet transforms


We applied a method to fuse imagery from different sensor types to visible and infrared imagery. The method uses different forward transforms of input images and a common transform to reconstruct the final result. We used entropy and average relative entropy as metrics for evaluating the reconstructed images. We found that this approach generally showed improved results when compared to a more conventional approach.

Important Links:

Go Back