计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (1): 175-183.doi: 10.11896/jsjkx.230200037

• 计算机图形学&多媒体 • 上一篇    下一篇

一种多深度特征连接的红外弱小目标检测方法

王维佳1,2, 熊文卓1, 朱圣杰1,2, 宋策1, 孙翯1, 宋玉龙1   

  1. 1 中国科学院长春光学精密机械与物理研究所 长春130033
    2 中国科学院大学大珩学院 北京100049
  • 收稿日期:2023-02-06 修回日期:2023-03-29 出版日期:2024-01-15 发布日期:2024-01-12
  • 通讯作者: 熊文卓(xwenzi@tom.com)
  • 作者简介:(549272937@qq.com)
  • 基金资助:
    国家自然科学基金(62205332)

Method of Infrared Small Target Detection Based on Multi-depth Feature Connection

WANG Weijia1,2, XIONG Wenzhuo1, ZHU Shengjie1,2, SONG Ce1, SUN He1, SONG Yulong1   

  1. 1 Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China
    2 Daheng College,University of Chinese Academy of Sciences,Beijing 100049,China
  • Received:2023-02-06 Revised:2023-03-29 Online:2024-01-15 Published:2024-01-12
  • About author:WANG Weijia,born in 1998,master.Her main research interests include computer vision and aerial image target detection.
    XIONG Wenzhuo,born in 1967,master,researcher.His main research interests include aerial photoelectric imaging and photoelectric sensor technology.
  • Supported by:
    National Natural Science Foundation of China(62205332).

PDF (PC)

1497

摘要： 针对红外弱小目标像元数量少、图像背景复杂、检测精度低且耗时较长的问题,文中提出了一种多深度特征连接的红外弱小目标检测模型(MFCNet)。首先,提出了多深度交叉连接主干形式以增加不同层间的特征传递,增强特征提取能力;其次,设计了注意力引导的金字塔结构对深层特征进行目标增强,分离背景与目标;提出非对称融合解码结构加强解码中纹理信息与位置信息保留;最后,引入点回归损失得到中心坐标。所提网络模型在SIRST公开数据集与自建长波红外弱小目标数据集上进行训练并测试,实验结果表明,与现有数据驱动和模型驱动算法相比,所提算法在复杂场景下具有更高的检测精度及更快的速度,模型的平均精度相比次优模型提升了5.41%,检测速度达到100.8 FPS。

关键词: 红外弱小目标, 深度学习, 目标检测, 特征连接, 注意力机制

Abstract: Small infrared targets have the characteristics of a small number of pixels and a complex background,which leads to the problems of low detection accuracy and high time-consumption.This paper proposes a multi-depth feature connection network.Firstly,the model proposes a multi-depth cross-connect backbone to increase feature transfer between different layers and enhance feature extraction capabilities.Secondly,an attention-guided pyramid structure is designed to enhance the deep features and separate the background from the target.Thirdly,an asymmetric fusion decoding structure is proposed to enhance the preservation of texture information and position information in decoding.Finally,the model introduces point regression loss to get the center coordinates.The proposed network model is trained and tested on the SIRST dataset and the self-built infrared small target dataset.Experimental results show that compared with existing data-driven and model-driven algorithms,the proposed model has higher detection accuracy and faster speed in complex scenes.Compared with the suboptimal model,the average precision of the model is improved by 5.41%,and the detection speed reaches 100.8 FPS.

Key words: Infrared small target detection, Deep learning, Object detection, Feature connection, Attention mechanism

中图分类号: 

  • TP391
[1]DAI X,ZHAO X,LI L P,et al.Infrared dim small target detection algorithm based on improved YOLOv5 in complex background [J].Infrared Technology,2022,44(5):504-512.
[2]ZHANG Q,ZHU H T,CHENG H.Light weight infrared dimsmall target detection algorithm [J].Progress in Laser and Optoelectronics,2022,59(16):282-288.
[3]CHEN M S,SUN W X,LI M Y,et al.Infrared small target detection under various complex backgrounds[J].Journal of Jilin University(Engineering and Technology Edition),2020,50(6):2288-2294.
[4]GAO C Q,MENG D Y,YANG Y,et al.Infrared patch image model for small target detection in a single image [J].IEEE Transactions on Image Processing,2013,22(12):4996-5009.
[5]GAO C,MENG D,YANG Y,et al.Infrared patch-image model for small target detection in a single image[C]//IEEE Transactions on Image Processing.2013:4996-5009.
[6]LI X F,WANG S Q,WENG X,et al.Remote sensing of floating macroalgae blooms in the East China Sea based on UNet deep learning model[J].Acta Optica Sinica,2021,41(2):18-26.
[7]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towardsreal-time object detection with region proposal networks[C]//International Conference on Neural Information Processing Systems.MIT Press,2015:91-99.
[8]REDMON J,FARHADI A.Yolov3:An incremental improve-ment[J].arXiv:1804.02767,2018.
[9]PAN X H,SHAO Q,LU J G.Small object detection algorithm based on CBD-YOLOv3.Journal of Chinese Computer Systems.2022,43(10):2143-2149.
[10]ZHANG H D,ZHANG R Q,TONG L.A vehicle target detection method based on improved YOLOv5s [J].Journal of Chongqing University of Technology(Natural Science),2023,37(7):80-89.
[11]DAI D E,ZHU R F,CHEN C Z,et al.Aviation small target detection algorithm based on improved Yolov5l [J].Computer Engineering and Design,2023,44(9):2610-2618.
[12]ZHANG S,ZHU X,LEI Z,et al.S3FD:Single shot scale-inva-riant face detector[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:192-201.
[13]ZHU S J,LIU J,TIAN Y,et al.Rapid Vehicle Detection in Ae-rial Images under the Complex Background of Dense Urban Areas[J].Remote Sensing,2022,14(9):2088.
[14]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014.
[15]HE K,ZHANG X,REN S,et al.Identity mappings in deep residual networks[C]//European Conference on Computer Vision.2016:630-645.
[16]HUANG G,LIU S,VANDER M L,et al.CondenseNet:An efficient DenseNet using learned group convolutions[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:2752-2761.
[17]WANG J,SUN K,CHENG T,et al.Deep high-resolution representation learning for visual recognition [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,43(10):3349-3364.
[18]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.2015:234-241.
[19]ZHANG T,CAO S,PU T,et al.Agpcnet:Attention-guided pyramid context networks for infrared small target detection[J].arXiv:2111.03580,2021.
[20]NEWELL A,YANG K,DENG J.Stacked hourglass networksfor human pose estimation[C]//European Conference on Computer Vision.2016:483-499.
[21]WANG X,GIRSHICK R,GUPTA A,et al.Non-local neural networks[C]//IEEE Conference on Computer Vision and Pattern Recognition.2018:7794-7803.
[22]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,2017,40(4):834-848.
[23]DAI Y,WU Y,ZHOU F,et al.Asymmetric contextual modulation for infrared small target detection[C]//IEEE/CVF Winter Conference on Applications of Computer Vision.2021:950-959.
[24]CHEN C L,LI H,WEI Y T,et al.A local contrast method for small infrared target detection [J].IEEE Transactions on Geoscience and Remote Sensing,2014:52(1):574-581.
[25]DUAN K,BAI S,XIE L,et al.Centernet:Keypoint triplets for object detection[C]//IEEE/CVF International Conference on Computer Vision.2019:6569-6578.
[26]LIN L K,WANG S Y,TANG Z X.Point target detection me-thod of infrared oversampling scanned image based on deep convolution neural network [J].Journal of Infrared and Millimeter Wave,2018,37(2):219-226.
[27]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shotmultibox detector[C]//European Conference on Computer Vision.Cham:Springer,2016:21-37.
[28]XU Y,YAN W,YANG G,et al.CenterFace:joint face detection and alignment using face as point[J].Scientific Programming,2020,2020:1-8.
[29]SHI Y,WEI Y,YAO H,et al.High-boost-based multiscale local contrast measure for infrared small target detection[J].IEEE Geoscience and Remote Sensing Letters,2017,15(1):33-37.
[30]MORADI S,MOALLEM P,SABAHI M F.Fast and robustsmall infrared target detection using absolute directional mean difference algorithm[J].Signal Processing,2020,177:107727.
[31]ZHANG H,ZHANG L,YUAN D,et al.Infrared small target detection based on local intensity and gradient properties[J].Infrared Physics & Technology,2018,89:88-96.
[32]WEI Y,YOU X,LI H.Multiscale patch-based contrast measure for small infrared target detection[J].Pattern Recognition,2016,58:216-226.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发