Multi-Sensor Image Fusion Based On Empirical Wavelet Transform

The advancement in technology had led to the requirement for a single image with high spatial and good spectral resolution in various applications such as remote sensing, surveillance and medical diagnosis. Most of the technology and equipment available has already reached the level of saturation in providing such convincing image or data. Image fusion techniques allow the integration of different information sources. From a pair of hyper-spectral image with low spatial and a pan image with high spatial resolutions, the aim is to synthesize a single image with highest spatial resolution and spectral content. However, apart from the standard image fusion techniques, in this paper we propose multi-sensor image fusion using empirical wavelet transform. In this image fusion scheme, the empirical wavelet transforms of the input images are appropriately combined, and the new image is obtained by taking the inverse empirical wavelet transform of the fused wavelet coefficients. With the necessity of multi-sensor data in many fields such as remote sensing, medical imaging, machine vision, military applications, sensor fusion has emerged as an upcoming and promising research area. The main objective of image fusion is to reconstruct new images that are more convincing for human visual perception, highly suitable for object detection and target recognition.