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 (...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
19.12.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |