一种面向机器视觉感知的暗光图像增强网络  

Dark light image enhancement network for machine vision perception

作　　者：冯欣[1] 王思平 张智先 焦晓宁 薛明龙 Feng Xin;Wang Siping;Zhang Zhixian;Jiao Xiaoning;Xue Minglong(School of Computer Science&Engineering,Chongqing University of Technology,Chongqing 400054,China;State Key Laboratory of Novel Software Technology,Nanjing University,Nanjing 210046,China)

机构地区：[1]重庆理工大学计算机科学与工程学院,重庆400054 [2]南京大学计算机软件新技术国家重点实验室,南京210046

出　　处：《计算机应用研究》2024年第6期1910-1915,共6页Application Research of Computers

基　　金：重庆市自然科学基金面上项目(CSTB2022NSCQ-MSX0493);重庆市技术创新与应用发展重点项目(cstc2021jscx-dxwtBX0018);重庆市研究生科研创新项目(CYS23678);重庆理工大学研究生教育高质量发展资助项目(gzlcx20222062,gzlcx20233218)。

摘　　要：低光照等恶劣环境下的目标检测一直都是难点,低光照和多雾因素往往会导致图像出现可视度低、噪声大等情况,严重干扰目标检测的检测精度。针对上述问题,提出了一个面向机器视觉感知的低光图像增强网络MVP-Net,并与YOLOv3目标检测网络整合,构建了端到端的增强检测框架MVP-YOLO。MVP-Net采用了逆映射网络技术,将常规RGB图像转换为伪RAW图像特征空间,并提出了伪ISP增强网络DOISP进行图像增强。MVP-Net旨在发挥RAW图像在目标检测中的潜在优势,同时克服其在直接应用时所面临的限制。模型在多个真实场景暗光数据上取得了优于先前工作效果并且能够适应多种不同架构的检测器。其端到端检测框mAP(50%)指标达到了78.3%,比YOLO检测器提高了1.85%。Target detection in adverse conditions such as low illumination has always been a challenging.The factors of low light and fog can lead to reduced visibility and increased noise in images,significantly disrupting the precision of object detection.To address these issues,this paper proposed and integrated a low-light image enhancement network for machine vision perception,MVP-Net,with the YOLOv3 object detection network to construct an end-to-end enhancement detection framework,MVPYOLO.MVP-Net employed inverse mapping network technology to transform conventional RGB images into pseudo-RAW image feature space and introduced a pseudo-ISP enhancement network,DOISP,for image enhancement.The objective of MVP-Net is to harness the potential advantages of RA W images in object detection while overcoming the limitations encountered in their direct application.The model has outperformed previous works on multiple real-world low-light datasets and is adaptable to detectors with various architectures.Its end-to-end detection framework achieves a mAP(50%)metric of 78.3%,an improvement of 1.85%over the YOLO detectors.

关 键 词：低光图像增强 机器视觉 RAW图像 ISP处理 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]