吉林大学学报（信息科学版）2026，Vol.44Issue(2)：435-445,11.
基于LogRetinex-Net的低照度站库监控图像增强方法
An Enhancement Method of Low-Light Monitoring Image for Storage Facilities Based on LogRetinex-Net
摘要
Abstract
Currently,low illumination enhancement algorithms applied to crude oil storage stations are prone to color distortion and excessive sharpening in the enhanced images due to the low illumination and contrast of on-site images.Therefore a low brightness image enhancement method is proposed based on LogRetinex-Net.First,a logarithmic transformation layer is introduced to the Retinex-Net to enhance the overall grayscale of the images,reducing the impact of low illumination and contrast in crude oil storage station images.Then,a channel attention mechanism is utilized to increase the network's focus on color channels,thereby mitigating the issue of color distortion.Finally,the model is trained and validated on a crude oil storage station dataset.Experimental results show that the LogRetinex-Net network improves artifacts and over-sharpening phenomena,significantly enhancing image quality.关键词
对数Log变换/通道注意力/低照度图像增强/Retinex-Net网络Key words
Log transformation/channel attention/low illumination image enhancement/Retinex-Net分类
信息技术与安全科学引用本文复制引用
张岩,汪靖哲,张永雪,魏子心,张林军,陈柏汉..基于LogRetinex-Net的低照度站库监控图像增强方法[J].吉林大学学报（信息科学版）,2026,44(2):435-445,11.基金项目
东北石油大学特色科研团队基金资助项目(2023TSTD-04) （2023TSTD-04）
