Low illumination and rain superposition image enhancement method based on TSDFF-Net

The invention discloses a TSDFF-Net-based low illumination and rain superposition image enhancement method, which comprises the steps of (1) constructing an LLR-Train and LLR-Test data set, (2) training a rain prior feature extraction module, (3) training a low illumination enhancement module, and (...

Full description

Saved in:
Bibliographic Details
Main Authors LI MENGTONG, XIONG BANGSHU, JIANG ZETAO
Format Patent
LanguageChinese
English
Published 19.12.2023
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The invention discloses a TSDFF-Net-based low illumination and rain superposition image enhancement method, which comprises the steps of (1) constructing an LLR-Train and LLR-Test data set, (2) training a rain prior feature extraction module, (3) training a low illumination enhancement module, and (4) testing the TSDFF-Net. The method can improve the model enhancement quality according to rain imprint information, and has a good effect on image rain removal and low illumination enhancement in a weak light rainy day. 本发明公开一种基于TSDFF-Net的低照度与雨叠加图像增强方法，包括：1）构建LLR-Train与LLR-Test数据集；2）训练雨先验特征提取模块；3）训练低照度增强模块；4）测试TSDFF-Net。这种方法能依据雨痕信息，提高模型增强质量，对弱光雨天图像去雨及低照度增强具有良好的效果。
Bibliography:Application Number: CN202311217591