Exposure Fusion by Fast and Adaptive Bidimensional Empirical Mode Decomposition

Ilias Lousis, Konstantinos Ioannidis, and Ioannis Andreadis

Keywords

High Dynamic Range Imaging, Exposure Fusion, FABEMD

Abstract

A new method for fusing a scene of two or more different exposed images is proposed. The process of Fast and Adaptive Bidimensional Empirical mode Decomposition is adopted in order to decompose the illumination component of the input images in their Intrinsic Mode Functions (IMFs). The features of each image can then be detected by applying local energy operators within the IMFs and the final fused image is derived as a collection of features from the input images. Finally, the color information is selected from the “best exposed” pixels of the input sequence. Experimental results show that this method captures all the features from the input images while the fused images display uniform pixel values in the entire image region.

Important Links:

Go Back