Multi-exposure image fusion method based on space-borne area array CMOS camera for high dynamic scene

Conference: ICMLCA 2021 - 2nd International Conference on Machine Learning and Computer Application
12/17/2021 - 12/19/2021 at Shenyang, China

Proceedings: ICMLCA 2021

Pages: 5Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Qian, Jinzhuo; Ma, Jun (School of Software, Henan University, Kaifeng, China)
Xin, Lei; Li, Feng (Qian Xuesen Laboratory of Space Technology, China Academy of Space Technology, Beijing, China)

Abstract:
In aerospace remote sensing, the dynamic range images cannot be captured well due to the short integration time of the area array CMOS camera, resulting in dim images and loss of details. In order to solve the problems, a multi-exposure image fusion method based on space-borne area array CMOS cameras combining image registration with digital time delay integration (TDI) technology for high dynamic scenes was proposed in this paper. A multi-exposure image fusion algorithm with deblurring was used to generate a high dynamic range (HDR) image with adaptive exposure based on multi-exposure images captured by the area array CMOS camera. Experimental results show that our method has superior image quality compared with other exposure fusion methods. It can effectively solve the limitation of the dynamic range of aerospace remote sensing cameras.