A Low-Light Object Detection Method Based on SAM-MSFF Network

JIANG Ze-tao; LI Hui; LEI Xiao-chun; ZHU Ling-hong; Shi Dao-quan; ZHAI Feng-shuo

doi:10.12263/DZXB.20220666

您当前的位置：

首页 >

文章列表页 >

A Low-Light Object Detection Method Based on SAM-MSFF Network

PAPERS | 更新时间：2026-04-10

- A Low-Light Object Detection Method Based on SAM-MSFF Network
- ACTA ELECTRONICA SINICA Vol. 52, Issue 1, Pages: 81-93(2024)
- 作者机构：
  
  1.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
  2.南昌航空大学，江西南昌 330063
- 作者简介：
- 基金信息：
  
  Key Projects of Guangxi Natural Science Foundation(2021GXNSFDA196002);Guangxi Key Laboratory of Image and Graphic Intelligent Processing under Grants(GIIP2006;GIIP2007;GIIP2008);Innovation Project of Guangxi Graduate Education(YCB2021070;YCBZ2018052;YCSW2022269;2021YCXS071)
- DOI：10.12263/DZXB.20220666
  CLC： TP319;
- Received：09 June 2022，
  
  Revised：2022-10-17，
  
  Published：25 January 2024
- 稿件说明：
移动端阅览
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(01):81-93.

JIANG Ze-tao,LI Hui,LEI Xiao-chun,et al.A Low-Light Object Detection Method Based on SAM-MSFF Network[J].ACTA ELECTRONICA SINICA,2024,52(01):81-93.
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(01):81-93. DOI： 10.12263/DZXB.20220666.

JIANG Ze-tao,LI Hui,LEI Xiao-chun,et al.A Low-Light Object Detection Method Based on SAM-MSFF Network[J].ACTA ELECTRONICA SINICA,2024,52(01):81-93. DOI： 10.12263/DZXB.20220666.

摘要

由于低照度图像具有对比度低、细节丢失严重、噪声大等缺点，现有的目标检测算法对低照度图像的检测效果不理想.为此，本文提出一种结合空间感知注意力机制和多尺度特征融合（Spatial-aware Attention Mechanism and Multi-Scale Feature Fusion，SAM-MSFF）的低照度目标检测方法.该方法首先通过多尺度交互内存金字塔融合多尺度特征，增强低照度图像特征中的有效信息，并设置内存向量存储样本的特征，捕获样本之间的潜在关联性；然后，引入空间感知注意力机制获取特征在空间域的长距离上下文信息和局部信息，从而增强低照度图像中的目标特征，抑制背景信息和噪声的干扰；最后，利用多感受野增强模块扩张特征的感受野，对具有不同感受野的特征进行分组重加权计算，使检测网络根据输入的多尺度信息自适应地调整感受野的大小.在ExDark数据集上进行实验，本文方法的平均精度（mean Average Precision，mAP）达到77.04%，比现有的主流目标检测方法提高2.6%~14.34%.

Abstract

The existing object detection methods are insufficient for low-light images due to their intrinsic property such as low contrast

detail loss and high noise. To solve this problem

a low-light object detection method that combines spatial-aware attention mechanism with multi-scale feature fusion (SAM-MSFF) is proposed. Firstly

multi-scale features are fused by multi-scale interactive memory pyramid to enhance effective information under low-illumination condition

and features of memory vector storage samples are set to capture potential correlation between samples. Then

a spatial-aware attention mechanism is introduced to obtain long-distance context information and local information of features in spatial domain

thereby enhancing the object features in low-light images and suppressing the interference of background information and noise. Finally

multiple receptive field enhancement module is used to expand receptive field of the features

and the features with different receptive fields are grouped and re-weighted

so that detection network can adaptively adjust the size of receptive field according to input multi-scale information. Experimental results on the ExDark dataset show that mAP (mean Average Precision) of the proposed method reaches 77.04%

which is 2.6%~14.34% higher than existing mainstream object detection methods.

关键词

Keywords

references

ZHOU Y , WEN S J , WANG D L , et al . Object detection in autonomous driving scenarios based on an improved Faster-RCNN [J]. Applied Sciences , 2021 , 11 ( 24 ): 11630 .

GORSCHLÜTER F , ROJTBERG P , PÖLLABAUER T . A survey of 6D object detection based on 3D models for industrial applications [J]. Journal of Imaging , 2022 , 8 ( 3 ): 53 .

HU Y Y , WU X J , ZHENG G D , et al . Object detection of UAV for anti-UAV based on improved YOLO v3 [C]// 2019 Chinese Control Conference (CCC) . Piscataway : IEEE , 2019 : 8386 - 8390 .

ZHANG Y E , YE L , FANG L , et al . Benchmarking the robustness of object detection based on near-real military scenes [J]. Wireless Communications and Mobile Computing , 2022 , 2022 : 5884625 .

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 .

REDMON J , DIVVALA S , GIRSHICK R , et al . You only look once: Unified, real-time object detection [EB/OL]. ( 2015-06-08 )[ 2022-06-09 ]. https://arxiv.org/abs/1506.02640 https://arxiv.org/abs/1506.02640 .

REDMON J , FARHADI A . YOLO9000: Better, faster, stronger [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 6517 - 6525 .

REDMON J , FARHADI A . YOLOv3: An incremental improvement [EB/OL]. ( 2018-04-08 )[ 2022-06-09 ]. https://arxiv.org/abs/1804.02767 https://arxiv.org/abs/1804.02767 .

BOCHKOVSKIY A , WANG C Y , LIAO H Y M . YOLOv4: Optimal speed and accuracy of object detection [EB/OL]. ( 2020-04-23 )[ 2022-06-09 ]. https://arxiv.org/abs/2004.10934 https://arxiv.org/abs/2004.10934 .

GE Z , LIU S T , WANG F , et al . YOLOX: Exceeding YOLO series in 2021 [EB/OL]. ( 2021-08-06 )[ 2022-06-09 ]. https://arxiv.org/abs/2107.08430 https://arxiv.org/abs/2107.08430 .

WANG W J , YANG W H , LIU J Y . HLA-face: Joint high-low adaptation for low light face detection [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 16190 - 16199 .

MIAO Y , LIU F , HOU T , et al . A nighttime vehicle detection method based on YOLO v3 [C]// 2020 Chinese Automation Congress (CAC) . Piscataway : IEEE , 2021 : 6617 - 6621 .

XIAO Y X , JIANG A W , YE J H , et al . Making of night vision: Object detection under low-illumination [J]. IEEE Access , 2020 , 8 : 123075 - 123086 .

HU J , SHEN L , SUN G . Squeeze-and-excitation networks [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 7132 - 7141 .

WOO S , PARK J , LEE J Y , et al . CBAM: Convolutional block attention module [C]// European Conference on Computer Vision . Cham : Springer , 2018 : 3 - 19 .

WANG X L , GIRSHICK R , GUPTA A , et al . Non-local neural networks [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 7794 - 7803 .

WANG C Y , MARK LIAO H Y , WU Y H , et al . CSPNet: A new backbone that can enhance learning capability of CNN [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) . Piscataway : IEEE , 2020 : 1571 - 1580 .

HE K M , ZHANG X Y , REN S Q , et al . Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 , 37 ( 9 ): 1904 - 1916 .

LIN T Y , DOLLÁR P , GIRSHICK R , et al . Feature pyramid networks for object detection [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2017 : 936 - 944 .

LIU S , QI L , QIN H F , et al . Path aggregation network for instance segmentation [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 8759 - 8768 .

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 : 10778 - 10787 .

CHEN L C , PAPANDREOU G , KOKKINOS I , et al . DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 , 40 ( 4 ): 834 - 848 .

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 .

CAI Z W , VASCONCELOS N . Cascade R-CNN: Delving into high quality object detection [C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 6154 - 6162 .

LU X , LI B Y , YUE Y X , et al . Grid R-CNN [C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 7355 - 7364 .

PANG J M , CHEN K , SHI J P , et al . Libra R-CNN: Towards balanced learning for object detection [C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 821 - 830 .

SUN P Z , ZHANG R F , JIANG Y , et al . Sparse R-CNN: End-to-end object detection with learnable proposals [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 14449 - 14458 .

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 , 2020 : 9626 - 9635 .

ZHANG X S , WAN F , LIU C , et al . FreeAnchor: Learning to match anchors for visual object detection [EB/OL]. ( 2019-09-05 )[ 2022-06-09 ]. https://arxiv.org/abs/1909.02466 https://arxiv.org/abs/1909.02466 .

CAO Y H , CHEN K , LOY C C , et al . Prime sample attention in object detection [C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 11580 - 11588 .

KIM K , LEE H S . Probabilistic anchor assignment with IoU prediction for object detection [C]// European Conference on Computer Vision . Cham : Springer , 2020 : 355 - 371 .

ZHU C C , HE Y H , SAVVIDES M . Feature selective anchor-free module for single-shot object detection [C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2020 : 840 - 849 .

ZHANG H Y , WANG Y , DAYOUB F , et al . VarifocalNet: An IoU-aware dense object detector [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 8510 - 8519 .

CHEN Q , WANG Y M , YANG T , et al . You only look one-level feature [C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2021 : 13034 - 13043 .

HUANG Y S , JIANG Z T , LAN R S , et al . Infrared image super-resolution via transfer learning and PSRGAN [J]. IEEE Signal Processing Letters , 2021 , 28 : 982 - 986 .

HUANG Y S , JIANG Z T , WANG Q Z , et al . Infrared image super-resolution via heterogeneous convolutional WGAN [C]// Pacific Rim International Conference on Artificial Intelligence . Cham : Springer , 2021 : 461 - 472 .

HUANG Y S , WANG Q Z , OMACHI S . Rethinking degradation: Radiograph super-resolution via AID-SRGAN [EB/OL]. ( 2022-08-05 )[ 2022-10-17 ]. https://arxiv.org/abs/2208.03008 https://arxiv.org/abs/2208.03008 .

JIANG Z T , PI K , HUANG Y S , et al . Difference value network for image super-resolution [J]. IEEE Signal Processing Letters , 2021 , 28 : 1070 - 1074 .

权宇 , 李志欣 , 张灿龙 , 等 . 融合深度扩张网络和轻量化网络的目标检测模型 [J]. 电子学报 , 2020 , 48 ( 2 ): 390 - 397 .

QUAN Y , LI Z X , ZHANG C L , et al . Fusing deep dilated convolutions network and light-weight network for object detection [J]. Acta Electronica Sinica , 2020 , 48 ( 2 ): 390 - 397 . (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Low-Illumination Object Detection Method Based on Night-YOLOX

Object Detection Networks Based on Refined Multi-scale Depth Feature

An Infrared Polarization Based UAV Detection Method for Complex Environment

Related Author

JIANG Ze-tao

SHI Dao-quan

LEI Xiao-chun

HE Yu-ting

LI Hui

ZHOU Yong-gang

JIANG Ze-tao

SHI Dao-quan

Related Institution

Guangxi Key Laboratory of Image and Graphic Intelligent Processing， Guilin University of Electronic Technology

Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University

School of Automation, Northwestern Polytechnical University

Naval Aeronautical University

⁰