Special Session on Emerging Issues in Image Fusion

Abstract

Multisensor data fusion is an area of great interest in the research community. Investigations into multisensor fusion at the signal, image, feature, and symbol/decision levels (also called distributed detection) of representation are all popular. Signal-level fusion refers to the direct combination of several signals in order to provide a signal that has the same general format as the source signals. Our focus here is on image-level fusion (called image fusion here), which generates a fused image in which each pixel is determined from a set of pixels in each source image. The fused image should contain a better view of the scene than do any of the source images, thus improving computer or human interpretation. It is worth noting that image-level fusion, or image fusion, is closely related to signal-level fusion since an image can be considered a two-dimensional signal. In recent years, image fusion has been attracting a large amount of attention in a wide variety of applications such as concealed weapon detection, remote sensing, intelligent robots, medical diagnosis, defect inspection, and military surveillance. This special session will focus on what we feel are the most important emerging issues in image fusion as given by the following papers (full papers were sent directly to the conference).