RetinexD-Net: A retinex-densenet fusion architecture for low-light image enhancement in drill pipe detection

IF 4.6 2区物理与天体物理 Q1 OPTICS

Optics and Laser Technology Pub Date : 2025-07-17 DOI:10.1016/j.optlastec.2025.113547

Zhongsen Zhang , Xiaofan Liu , Dezheng Hua , Xiaoqiang Guo , Tichun Wang , Xinhua Liu

{"title":"RetinexD-Net: A retinex-densenet fusion architecture for low-light image enhancement in drill pipe detection","authors":"Zhongsen Zhang , Xiaofan Liu , Dezheng Hua , Xiaoqiang Guo , Tichun Wang , Xinhua Liu","doi":"10.1016/j.optlastec.2025.113547","DOIUrl":null,"url":null,"abstract":"<div><div>Visual detection of drill pipes is crucial for the effective operation of coal mine drilling robots. However, insufficient underground lighting often results in images with low brightness, limited detail, and reduced color fidelity, similar to challenges in natural low-light vision applications. To address this, a low-light image enhancement method based on Retinex and an improved DenseNet is proposed, which effectively leverages DenseNet’s dense connectivity and brightness distribution characteristics to enhance image quality. The model comprises four main components: (1) A decomposition network that separates low-light images into illumination and reflectance components; (2) An illumination enhancement network for processing the illumination component; (3) A reflectance adjustment network for refining the reflectance component; and (4) A perceptually-consistent fusion network that combines the enhanced components to produce the final output. Experimental results demonstrate superior PSNR, SSIM, and LPIPS scores compared to state-of-the-art methods. The enhanced images improve drill pipe detection rates by 39.2% and 24.4% under distinct experimental conditions, offering novel approaches for image processing in underground coal mine environments and natural low-light scenes.</div></div>","PeriodicalId":19511,"journal":{"name":"Optics and Laser Technology","volume":"192 ","pages":"Article 113547"},"PeriodicalIF":4.6000,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optics and Laser Technology","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0030399225011387","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPTICS","Score":null,"Total":0}

引用次数: 0

Abstract

Visual detection of drill pipes is crucial for the effective operation of coal mine drilling robots. However, insufficient underground lighting often results in images with low brightness, limited detail, and reduced color fidelity, similar to challenges in natural low-light vision applications. To address this, a low-light image enhancement method based on Retinex and an improved DenseNet is proposed, which effectively leverages DenseNet’s dense connectivity and brightness distribution characteristics to enhance image quality. The model comprises four main components: (1) A decomposition network that separates low-light images into illumination and reflectance components; (2) An illumination enhancement network for processing the illumination component; (3) A reflectance adjustment network for refining the reflectance component; and (4) A perceptually-consistent fusion network that combines the enhanced components to produce the final output. Experimental results demonstrate superior PSNR, SSIM, and LPIPS scores compared to state-of-the-art methods. The enhanced images improve drill pipe detection rates by 39.2% and 24.4% under distinct experimental conditions, offering novel approaches for image processing in underground coal mine environments and natural low-light scenes.

查看原文本刊更多论文

retexd - net：一种用于钻杆检测中弱光图像增强的retexx -densenet融合架构

钻杆的视觉检测是煤矿钻井机器人有效作业的关键。然而，地下照明不足往往导致图像亮度低，细节有限，色彩保真度降低，类似于自然低光视觉应用中的挑战。针对这一问题，提出了一种基于Retinex和改进的DenseNet的弱光图像增强方法，该方法有效地利用DenseNet的密集连通性和亮度分布特性来增强图像质量。该模型主要由四个部分组成：(1)将低照度图像分解为照度和反射率分量的分解网络；(2)用于处理所述照明组件的照明增强网络；(3)用于细化反射率分量的反射率平差网；(4)一个感知一致的融合网络，将增强的组件组合在一起产生最终输出。实验结果表明，与最先进的方法相比，PSNR， SSIM和LPIPS得分更高。在不同的实验条件下，增强图像的钻杆检测率分别提高了39.2%和24.4%，为煤矿井下环境和自然弱光场景的图像处理提供了新的途径。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Optics and Laser Technology 物理-光学

CiteScore

8.50

自引率

10.00%

发文量

1060

审稿时长

3.4 months

期刊介绍： Optics & Laser Technology aims to provide a vehicle for the publication of a broad range of high quality research and review papers in those fields of scientific and engineering research appertaining to the development and application of the technology of optics and lasers. Papers describing original work in these areas are submitted to rigorous refereeing prior to acceptance for publication. The scope of Optics & Laser Technology encompasses, but is not restricted to, the following areas: •development in all types of lasers •developments in optoelectronic devices and photonics •developments in new photonics and optical concepts •developments in conventional optics, optical instruments and components •techniques of optical metrology, including interferometry and optical fibre sensors •LIDAR and other non-contact optical measurement techniques, including optical methods in heat and fluid flow •applications of lasers to materials processing, optical NDT display (including holography) and optical communication •research and development in the field of laser safety including studies of hazards resulting from the applications of lasers (laser safety, hazards of laser fume) •developments in optical computing and optical information processing •developments in new optical materials •developments in new optical characterization methods and techniques •developments in quantum optics •developments in light assisted micro and nanofabrication methods and techniques •developments in nanophotonics and biophotonics •developments in imaging processing and systems