Electronic Science and Technology ›› 2021, Vol. 34 ›› Issue (6): 34-39.doi: 10.16180/j.cnki.issn1007-7820.2021.06.006

Previous Articles     Next Articles

Dual-Exposure Fusion Algorithm for Low-Light Image Enhancement

LIU Tingting,ZHANG Yujin,XIONG Shiting   

  1. College of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China
  • Received:2020-02-16 Online:2021-06-15 Published:2021-06-01
  • Supported by:
    Natural Science Foundation of Shanghai(17ZR1411900);The Opening Project of Shanghai Key Laboratory of Integrated Administration Technologies for Information Security(AGK2015006);The Post-Graduation Innovation Project of Shanghai University of Engineering Science(18KY0208)


Image enhancement techniques can improve the visibility of low-light image effectively. In view of the problem of over-enhancement and under-enhancement of contrast introduced by existing image enhancement methods, a dual-exposure fusion algorithm for low-light image enhancement is proposed. The weight matrix of image fusion is obtained by the illumination estimation techniques. The dual-exposure image is synthesized by the camera response model. The best exposure ratio is identified so that the synthetic image is well-exposed in the regions where the original image is under-exposed. The enhanced result is obtained by fusing the input image and the synthetic image according to the weight matrix. The scene illumination map of low illuminated pixels is reflected differently in different channels. In order to avoid the inaccuracy of brightness component caused by too large difference, the low illuminated pixels and brightness component are defined to calculate the optimal exposure ratio. Experiments show that compared with the existing methods, the proposed method has less brightness distortion and running time.

Key words: image enhancement, low-light, contrast, exposure fusion, weight matrix, image fusion, brightness, the optimal exposure ratio

CLC Number: 

  • TP391.41