基于ICFIE-YOLO的低照度图像目标检测方法

秦嘉奇; 江泽涛; 雷晓春

doi:10.12263/DZXB.20240648

您当前的位置：

首页 >

文章列表页 >

基于ICFIE-YOLO的低照度图像目标检测方法

学术论文 | 更新时间：2025-12-08

- 基于ICFIE-YOLO的低照度图像目标检测方法
- Low Illumination Image Object Detection Method Based on ICFIE-YOLO
- 电子学报 2025年53卷第2期页码：514-526
- 作者机构：
  
  桂林电子科技大学广西图像图形与智能处理重点实验室，广西桂林 541004
- 作者简介：
  
  [ "秦嘉奇男，博士研究生，讲师，系统架构设计师.主要研究领域为计算机视觉.E-mail: 18878396109@163.com" ]
  [ "江泽涛男，博士，教授，博士生导师.主要研究领域为深度学习、计算机视觉.E-mail: zetaojiang@guet.com" ]
  [ "雷晓春女，博士，硕士生导师.主要研究领域为计算机视觉、深度学习.E-mail: 22704797@qq.com" ]
- 基金信息：
  
  国家自然科学基金(62172118);广西自然科学基金重点项目(2021GXNSFDA196002);广西图像图形智能处理重点实验项目(GIIP2302;GIIP2303;GIIP2304);研究生创新基金(2024YCXB09;2024YCXS039)
- DOI：10.12263/DZXB.20240648
  中图分类号： TP391;
- 收稿：2024-07-09，
  
  修回：2024-12-16，
  
  纸质出版：2025-02-25
- 稿件说明：
移动端阅览
秦嘉奇, 江泽涛, 雷晓春. 基于ICFIE-YOLO的低照度图像目标检测方法[J]. 电子学报, 2025, 53(02): 514-526.

QIN Jia-qi, JIANG Ze-tao, LEI Xiao-chun. Low Illumination Image Object Detection Method Based on ICFIE-YOLO[J]. Acta Electronica Sinica, 2025, 53(02): 514-526.
秦嘉奇, 江泽涛, 雷晓春. 基于ICFIE-YOLO的低照度图像目标检测方法[J]. 电子学报, 2025, 53(02): 514-526. DOI：10.12263/DZXB.20240648

QIN Jia-qi, JIANG Ze-tao, LEI Xiao-chun. Low Illumination Image Object Detection Method Based on ICFIE-YOLO[J]. Acta Electronica Sinica, 2025, 53(02): 514-526. DOI：10.12263/DZXB.20240648

摘要

低照度环境下获取的图像往往亮度低、对比度低、光照不均匀，从而造成图像特征变弱及模糊难于提取，同时在有限提取的特征中也存在大量噪声信息，导致目标难于检测识别，因而现有低照度目标检测成果极少.针对低照度目标特征难于提取及特征空间噪声大的问题，本文提出一种基于光照矫正与特征交互增强（Illumination Correction and Feature Interacted Enhancement，ICFIE-YOLO）网络的低照度目标检测方法.该方法首先利用提出的ICFIE-YOLO内部多尺度光照矫正网络（Multi Scale Illumination Correction Network，MSICN）对低照度图像进行光照矫正，突出隐藏在图像背景中目标的模糊特征，使特征提取模块能更好地提取到目标特征；其次，为充分利用有效特征信息，过滤特征图中的噪声干扰，提出特征交互增强（Feature Interacted Enhancement，FIE）检测头，通过特征注意力交互方式实现特征增强，建立低照度图像中各个区域特征之间的空间关联和语义关联，从而抑制噪声对有效特征的干扰，实现降噪效果；最后，在增强特征及去除噪声的基础上用改进的检测头实现高精度目标检测.在ExDark和DarkFace数据集上的实验表明，所提方法较主流目标检测方法mAP提高2.1个百分点以上，较现有低照度目标检测方法召回率提高4.2个百分点以上，同时召回率较基线模型提高了2.6个百分点，所提方法具有较好的泛化性.

Abstract

Images obtained in low light environments often have low brightness

low contrast

and uneven lighting

resulting in weakened and blurred image features that are difficult to extract. At the same time

there is also a large amount of noise information in the limited extracted features

making it difficult to detect and recognize objects. Therefore

there are very few existing low light object detection results. This paper proposes a low illumination object detection method based on the Illumination Correction and Feature Interaction Enhancement (ICFIE-YOLO) network to address the difficulties in extracting features from low illumination objects and the large noise in the feature space. This method first utilizes the proposed ICFIE-YOLO internal Multi Scale Illumination Correction Network (MSICN) to correct low illumination images

highlighting the blurry features of objects hidden in the image’s background

and enabling the feature extraction module to better extract object features. Secondly

to fully utilize effective feature information and filter out noise interference in feature maps

a Feature Interacted Enhancement (FIE) detection head is proposed. Through feature attention interaction

feature enhancement is achieved

establishing spatial and semantic correlations between features in different regions of low illumination images

thereby suppressing the interference of noise on effective features and achieving feature enhancement. Finally

on the basis of enhancing features and removing noise

an improved detection head is used to achieve high-precision object detection. Experiments on the ExDark and DarkFace datasets show that the proposed Method improves mAP by over 2.1 percentage points compared to mainstream object detection models

increases recall by over 4.2 percentage points compared to existing low light object detection Methods

and improves recall by 2.6 percentage points compared to baseline models. The proposed Method has good generalization performance.

关键词

Keywords

references

REN S Q , HE K M , GIRSHICK R , et al . Faster R-CNN: Towards real-time object detection with region proposal networks [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 6 ): 1137 - 1149 .

KIM H , LEE E C , SEO Y , et al . Character detection in animated movies using multi-style adaptation and visual attention [J ] . IEEE Transactions on Multimedia , 2020 , 23 : 1990 - 2004 .

HE K M , GKIOXARI G , DOLLÁR P , et al . Mask R-CNN [EB/OL ] . ( 2018-01-24 )[ 2024-07-09 ] . https://arxiv.org/abs/1703.06870 https://arxiv.org/abs/1703.06870 .

ZHU Y S , ZHAO C Y , WANG J Q , et al . CoupleNet: Coupling global structure with local parts for object detection [C ] // 2017 IEEE International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2017 : 4124 - 4134 .

WANG X L , SHRIVASTAVA A , GUPTA A . A-fast-RCNN: Hard positive generation via adversary for object detection [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 2606 - 2615 .

REDMON J , FARHADI A . YOLOv3: An incremental improvement [EB/OL ] . ( 2018-04-08 )[ 2024-07-09 ] . https://arxiv.org/abs/1804.02767v1 https://arxiv.org/abs/1804.02767v1 .

GE Z , LIU S T , WANG F , et al . YOLOX: Exceeding YOLO series in 2021 [EB/OL ] . ( 2021-08-06 )[ 2024-07-09 ] . https://arxiv.org/abs/2107.08430v2 https://arxiv.org/abs/2107.08430v2 .

BOCHKOVSKIY A , WANG C Y , LIAO H M . YOLOv4: Optimal speed and accuracy of object detection [EB/OL ] .( 2020-04-23 )[ 2024-07-09 ] . https://arxiv.org/abs/2004.10934v1 https://arxiv.org/abs/2004.10934v1 .

PAN H D , JIANG J , CHEN G F . TDFSSD: Top-down feature fusion single shot MultiBox detector [J ] . Signal Processing: Image Communication , 2020 , 89 : 115987 .

CUI L S , MA R , LV P , et al . MDSSD: Multi-scale deconvolutional single shot detector for small objects [J ] . Science China Information Sciences , 2020 , 63 ( 2 ): 120113 .

VAIDWAN H , SETH N , PARIHAR A S , et al . A study on transformer-based object detection [C ] // 2021 International Conference on Intelligent Technologies (CONIT) . Piscataway : IEEE , 2021 : 25 - 27 .

LOH Y P , CHAN C S . Getting to know low-light images with the Exclusively Dark dataset [J ] . Computer Vision and Image Understanding , 2019 , 178 : 30 - 42 .

YUAN J J , HU Y L , SUN Y F , et al . A plug-and-play image enhancement model for end-to-end object detection in low-light condition [J ] . Multimedia Systems , 2024 , 30 ( 1 ): 27 .

XUE R , DUAN J L , DU Z W . MPE-DETR: A multiscale pyramid enhancement network for object detection in low-light images [J ] . Image and Vision Computing , 2024 , 150 : 105202 .

CHEN C , CHEN Q F , XU J , et al . Learning to see in the dark [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 3291 - 3300 .

YIN X C , YU Z D , FEI Z T , et al . PE-YOLO: Pyramid enhancement network for dark object detection [M ] // Artificial Neural Networks and Machine Learning - ICANN 2023 . Cham : Springer , 2023 : 163 - 174 .

CUI Z T , QI G J , GU L , et al . Multitask AET with orthogonal tangent regularity for dark object detection [C ] // 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2021 : 2533 - 2542 .

江泽涛 , 翟丰硕 , 钱艺 , 等 . 结合特征增强和多尺度感受野的低照度目标检测 [J ] . 计算机研究与发展 , 2023 , 60 ( 4 ): 903 - 915 .

JIANG Z T , ZHAI F S , QIAN Y , et al . Low illumination object detection combined with feature enhancement and multi-scale receptive field [J ] . Journal of Computer Research and Development , 2023 , 60 ( 4 ): 903 - 915 . (in Chinese)

江泽涛 , 李慧 , 雷晓春 , 等 . 一种基于SAM-MSFF网络的低照度目标检测方法 [J ] . 电子学报 , 2024 , 52 ( 1 ): 81 - 93 .

JIANG Z T , LI H , LEI X C , et al . A low-light object detection method based on SAM-MSFF network [J ] . Acta Electronica Sinica , 2024 , 52 ( 1 ): 81 - 93 . (in Chinese)

PARTHASARATHY S , SANKARAN P . Fusion based multi scale RETINEX with color restoration for image enhancement [C ] // 2012 International Conference on Computer Communication and Informatics . Piscataway : IEEE , 2012 : 1 - 7 .

DONG X , WANG G , PANG Y , et al . Fast efficient algorithm for enhancement of low lighting video [C ] // 2011 IEEE International Conference on Multimedia and Expo . Piscataway : IEEE , 2011 : 1 - 6 .

江泽涛 , 覃露露 . 一种基于U-Net生成对抗网络的低照度图像增强方法 [J ] . 电子学报 , 2020 , 48 ( 2 ): 258 - 264 .

JIANG Z T , QIN L L . Low-light image enhancement method based on U-Net generative adversarial network [J ] . Acta Electronica Sinica , 2020 , 48 ( 2 ): 258 - 264 . (in Chinese)

LU B B , PANG Z B , GU Y N , et al . Channel splitting attention network for low-light image enhancement [J ] . IET Image Processing , 2022 , 16 ( 5 ): 1403 - 1414 .

江泽涛 , 钱艺 , 伍旭 , 等 . 一种基于ARD-GAN的低照度图像增强方法 [J ] . 电子学报 , 2021 , 49 ( 11 ): 2160 - 2165 .

JIANG Z T , QIAN Y , WU X , et al . Low-light image enhancement method based on ARD-GAN [J ] . Acta Electronica Sinica , 2021 , 49 ( 11 ): 2160 - 2165 . (in Chinese)

江泽涛 , 覃露露 , 秦嘉奇 , 等 . 一种基于MDARNet的低照度图像增强方法 [J ] . 软件学报 , 2021 , 32 ( 12 ): 3977 - 3991 .

JIANG Z T , QIN L L , QIN J Q , et al . Low-light image enhancement method based on MDARNet [J ] . Journal of Software , 2021 , 32 ( 12 ): 3977 - 3991 . (in Chinese)

SHANG X K , AN N , ZHANG S M , et al . Toward robust and efficient low-light image enhancement: Progressive attentive retinex architecture search [J ] . Tsinghua Science and Technology , 2023 , 28 ( 3 ): 580 - 594 .

JIANG Y F , GONG X Y , LIU D , et al . EnlightenGAN: Deep light enhancement without paired supervision [J ] . IEEE Transactions on Image Processing , 2021 , 30 : 2340 - 2349 .

GUO C L , LI C Y , GUO J C , et al . Zero-reference deep curve estimation for low-light image enhancement [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 1777 - 1786 .

陈科圻 , 朱志亮 , 邓小明 , 等 . 多尺度目标检测的深度学习研究综述 [J ] . 软件学报 , 2021 , 32 ( 4 ): 1201 - 1227 .

CHEN K Q , ZHU Z L , DENG X M , et al . Deep learning for multi-scale object detection: A survey [J ] . Journal of Software , 2021 , 32 ( 4 ): 1201 - 1227 . (in Chinese)

YANG W H , YUAN Y , REN W Q , et al . Advancing image understanding in poor visibility environments: A collective benchmark study [J ] . IEEE Transactions on Image Processing , 2020 , 29 : 5737 - 5752 .

CAI Y H , BIAN H , LIN J , et al . Retinexformer: One-stage retinex-based transformer for low-light image enhancement [C ] // 2023 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2023 : 12470 - 12479 .

YAN Q S , FENG Y X , ZHANG C , et al . You only need one color space: An efficient network for low-light image enhancement [EB/OL ] . ( 2024-06-17 )[ 2024-07-09 ] . https://arxiv.org/abs/2402.05809v3 https://arxiv.org/abs/2402.05809v3 .

YANG S Z , DING M X , WU Y M , et al . Implicit neural representation for cooperative low-light image enhancement [C ] // 2023 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2023 : 12872 - 12881 .

JOCHER G , NISHIMURA K , MINEEVA T . YOLOv5 [EB/OL ] . ( 2022-11-12 )[ 2024-07-09 ] . https://github.com/ultralytics/yolov5 https://github.com/ultralytics/yolov5 .

WANG C Y , BOCHKOVSKIY A , LIAO H M . YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [EB/OL ] . ( 2022-07-06 )[ 2024-07-09 ] . https://arxiv.org/abs/2207.02696v1 https://arxiv.org/abs/2207.02696v1 .

TAN M X , PANG R M , LE Q V . EfficientDet: Scalable and efficient object detection [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 10781 - 10790 .

DUAN K W , BAI S , XIE L X , et al . CenterNet: Keypoint triplets for object detection [C ] // Proceedings of the IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2019 : 6568 - 6577 .

TIAN Z , SHEN C H , CHEN H , et al . FCOS: Fully convolutional one-stage object detection [C ] // 2019 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2019 : 9627 - 9636 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于分层提议与解耦监督的目标检测增量学习

基于红外偏振成像的复杂干扰环境下无人机目标检测方法

基于视觉与深度学习的无人机自主着陆场景感知方法研究进展

AI-DETR：自适应加权的可解释目标检测方法