AUTHOR=Chen Sichao , Li Zhenfei , Shen Dilong , An Yunzhu , Yang Jian , Lv Bin , Zhou Guohua 

TITLE=Multi-exposure electric power monitoring image fusion method without ghosting based on exposure fusion framework and color dissimilarity feature

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 16 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2022.1105385

DOI=10.3389/fnbot.2022.1105385

ISSN=1662-5218

ABSTRACT=To solve the ghosting artifacts problem in dynamic scene multi-scale exposure fusion, an improved multi-exposure fusion method has been proposed without ghosting based on the exposure fusion framework and the color dissimilarity feature in this paper. This fusion method can be further applied to power system monitoring and unmanned aerial vehicle monitoring fields. Firstly, an improved exposure fusion framework based on the camera response model is applied in this paper to preprocess the input image sequence. Secondly, the initial weight map is estimated by multiplying four weight items. In the constitution of removing ghosting weight term, an improved color dissimilarity feature is used to detect the object motion features in dynamic scenes. Finally, the improved pyramid model is adopted to retain the details information about the poor exposure areas. Experimental results indicate that the proposed method improves the performance of images in terms of sharpness, detail processing, and ghosting artifacts removal and is superior to the five existing multi-exposure image fusion (MEF) methods in quality evaluation.