吉林大学学报(信息科学版) ›› 2026, Vol. 44 ›› Issue (2): 435-445.

• • 上一篇    下一篇

基于 LogRetinex-Net 的低照度站库监控图像增强方法

张 岩, 汪靖哲, 张永雪, 魏子心, 张林军, 陈柏汉   

  1. 东北石油大学 计算机与信息技术学院, 黑龙江 大庆 163318
  • 收稿日期:2024-09-29 出版日期:2026-04-14 发布日期:2026-04-15
  • 作者简介:张岩(1980— ),男,辽宁大连人,东北石油大学副教授,博士生导师, 主要从事数字图像处理、机器学习、计算机视觉等研究, (Tel)86-13644598086(E-mail)zhangyuanyan_309@126.com。
  • 基金资助:
    东北石油大学特色科研团队基金资助项目 (2023TSTD-04)

An Enhancement Method of Low-Light Monitoring Image for Storage Facilities Based on LogRetinex-Net

ZHANG Yan, WANG Jingzhe, ZHANG Yongxue, WEI Zixin, ZHANG Linjun, CHEN Bohan   

  1. School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318, China
  • Received:2024-09-29 Online:2026-04-14 Published:2026-04-15

摘要: 针对目前低照度增强算法应用于原油站库时, 由于现场图像照度与对比度过低, 增强后的图像容易出现颜色失真和过度锐化的问题, 提出基于 LogRetinex-Net 的低亮度图像增强方法。首先, Retinex-Net网络中引入对数变换层, 提升图像的整体灰度, 降低原油站库图像低照度与低对比度造成的影响; 其次, 利用通道注意力机制提高网络对色彩通道的关注度, 减少颜色失真问题;最后,在原油站库数据集上进行训练与验证。实验结果表明, LogRetinex-Net网络改善了伪影和过度锐化现象, 图像质量得到了显著提高。

关键词:

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.

Key words:

中图分类号: 

  • TP391