计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (10): 287-294.doi: 10.11896/jsjkx.230800013

• 计算机图形学&多媒体 • 上一篇    下一篇

基于可见光-红外跨域迁移的红外弱小目标检测

薛如翔1, 卫俊杰2, 周华伟2, 杨海1, 王喆1   

  1. 1 华东理工大学 信息科学与工程学院 上海 200237
    2 上海航天控制技术研究院 上海 201109
  • 收稿日期:2023-08-03 修回日期:2023-12-28 出版日期:2024-10-15 发布日期:2024-10-11
  • 通讯作者: 王喆(wangzhe@ecust.edu.cn)
  • 作者简介:(y30221070@mail.ecust.edu.cn)
  • 基金资助:
    中国科技国防计划(2021-JCJQ-JJ-0041);中国航天科技集团有限公司第八研究院产学研合作基金(SAST2021-007)

Infrared Dim and Small Target Detection Based on Cross-domain Migration of Visible Light andInfrared

XUE Ruxiang1, WEI Junjie2, ZHOU Huawei2, YANG Hai1, WANG Zhe1   

  1. 1 School of Information Science and Engineering,East China University of Science and Technology,Shanghai 200237,China
    2 Shanghai Academy of Spaceflight Technology,Shanghai 201109,China
  • Received:2023-08-03 Revised:2023-12-28 Online:2024-10-15 Published:2024-10-11
  • About author:XUE Ruxiang,born in 1999,postgra-duate.Her main research interests include image processing and object detection.
    WANG Zhe,born in 1981,Ph.D,professor,is a member of CCF(No.16666M).His main research interests include pattern recognition and image processing.
  • Supported by:
    Chinese Defense Program of Science and Technology(2021-JCJQ-JJ-0041) and China Aerospace Science and Technology Corporation Industry-University-Research Cooperation Foundation of the Eighth Research Institute(SAST2021-007).

PDF (PC)

296

摘要： 红外弱小目标检测任务是红外探测领域的重点研究内容之一。然而由于其应用场景的特殊性,包含红外弱小目标的数据并不多见,且标注往往并不充分,这给由数据驱动的深度学习目标检测模型带来了挑战和困难。针对红外弱小目标数据集少、缺乏标记信息等问题,提出一种基于可见光-红外跨域迁移的红外弱小目标检测模型,将数据量更丰富的可见光域监督信息迁移到红外域中,实现红外域的无监督训练。首先,在YOLOv5的基础上设计通道增强的数据处理方法,利用低成本的通道分离技巧将可见光图像转换成类红外图像,缩小可见光域和红外域之间的模态差异。然后,构建多尺度域自适应模块,采用对抗训练的方式,对骨干网络提取得到的不同尺度特征在特征空间中进行域混淆以减小域偏移的影响,提高模型对弱小目标的检测性能。实验结果表明,所提方法改进后的模型相比各版本的YOLOv5模型检测精度均有所提升;与其他现有的无监督域自适应目标检测算法相比,所提方法在红外弱小目标的检测精度上明显占优。

关键词: 红外弱小目标, 目标检测, 深度学习, 域自适应, 无监督

Abstract: The task of infrared dim and small target detection is one of the key research contents in the field of infrared detection.However,due to the particularity of its application scenarios,the data containing infrared dim and small targets is rare,and often not fully labeled,which poses challenges and difficulties for data-driven deep learning object detection models.In order to solve the problems of limited datasets and lack of label information,an infrared dim and small target detection model based on cross-domain migration of visible light and infrared is proposed to migrate the more abundant visible light domain supervision information to the infrared domain,so as to achieve unsupervised training in the infrared domain.First,a channel augmentation data proces-sing method is designed on the basis of YOLOv5,utilizing low-cost channel separation techniques to convert visible light images into infrared like images,reducing the modal differences between the visible and infrared domains.Then,a multi-scale domain adaptive module is constructed,and the features of different scales extracted by the backbone network are used in the way of adversarial training.Domain confusion is performed in the feature space to reduce the impact of domain shift and improve the detection performance of dim and small target detection.Experimental results show that the improved model by the proposed method can improve the average detection precision compared to various versions of the YOLOv5 original model.Compared with other existing unsupervised domain adaptive target detection algorithms,the proposed method is obviously superior in the detection accuracy of small infrared targets.

Key words: Infrared dim and small targets, Object detection, Deep learning, Domain adaptive, Unsupervised

中图分类号: 

  • TP391
[1]ZHU Y,HAO Y G,WANG H Y.Deep learning based salientobject detection in infrared video [J].Computer Science,2023,50(9):227-234.
[2]ZHAO M,LI W,LI L,et al.Single-frame infrared small-target detection:A survey [J].IEEE Geoscience and Remote Sensing Magazine,2022,10(2):87-119.
[3]QIN Y,LI B.Effective infrared small target detection utilizing anovel local contrast method [J].IEEE Geoscience and Remote Sensing Letters,2016,13(12):1890-1894.
[4]JIAO J,XIE Y J,ZHANG H L,et al.Infrared dim and small target detection based on background prediction by wavelet filter [J].Computer Science,2016,43(2):60-63.
[5]CHEN C P,LI H,WEI Y T,et al.A local contrast method forsmall infrared target detection [J].IEEE Transactions on Geoscience and Remote Sensing,2013,52(1):574-581.
[6]DENG H,SUN X,LIU M,et al.Infrared small-target detection using multiscale gray difference weighted image entropy [J].IEEE Transactions on Aerospace and Electronic Systems,2016,52(1):60-72.
[7]GAO C,MENG D,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.
[8]REN S,HE K,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.
[9]REDMON J,DIVVALA S.GIRSHICK R,et al.You only look once:Unified,real-time object detection [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA:IEEE,2016:779-788.
[10]DAI Y,WU Y,ZHOU F,et al.Asymmetric contextual modulation for infrared small target detection [C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision.IEEE,2021:950-959.
[11]ZHANG M,ZHANG R,YANG Y,et al.ISNet:Shape matters for infrared small target detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans,LA,USA:IEEE,2022:877-886.
[12]LI B,XIAO C,WANG Y,et al.Dense nested attention network for infrared small target detection [J].IEEE Transactions on Image Processing,2022,32:1745-1758.
[13]ZHUANG F,QI Z,DUAN K,et al.A comprehensive survey on transfer learning [J].Proceedings of the IEEE,2020,109(1):43-76.
[14]FARAHANI A,VOGHOEI S,RASHEED K,et al.A brief review of domain adaptation [C]//Advances in Data Science and Information Engineering:Proceedings from ICDATA 2020 and IKE 2020.2021:877-894.
[15]CHEN Y,LI W,SAKARIDIS C,et al.Domain adaptive faster r-cnn for object detection in the wild [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA:IEEE,2018:3339-3348.
[16]SAITO K,USHIKU Y,HARADA T,et al.Strong-weak distribution alignment for adaptive object detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach,CA,USA:IEEE,2019:6956-6965.
[17]LIU X Y,LI W Y,YANG Q S,et al.Towards robust adaptive object detection under noisy annotations [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.New Orleans,LA,USA:IEEE,2022:14207-14216.
[18]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,NV,USA:IEEE,2016:770-778.
[19]HE K,ZHANG X,REN S,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition [J].IEEE Tran-sactions on Pattern Analysis and Machine Intelligence,2015,37(9):1904-1916.
[20]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection [C]//Proceedings of the IEEE Conference on Computer Vision and PatternRecognition.Hono-lulu,HI,USA:IEEE,2017:2117-2125.
[21]LIU S,QI L,QIN H F,et al.Path aggregation network for instance segmentation [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA:IEEE,2018:8759-8768.
[22]BOCHKOVSKIY A,WANG C Y,LIAO H Y M,et al.YOLOv4:Optimal Speed and Accuracy of Object Detection [J].arXiv:2004.10934,2020.
[23]XIA D X,LIU H J,XU L L,et al.Visible-infrared person re-identification with data augmentation via cycle-consistent adversarial network [J].Neurocomputing,2021,443:35-46.
[24]YE M,RUAN W J,DU B,et al.Channel augmented joint lear-ning for visible-infrared recognition [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.IEEE,2021:13567-13576.
[25]LUO Y W,ZHENG L,GUAN T,et al.Taking a closer look at domain shift:Category-level adversaries for semantics consistent domain adaptation [C]//Proceedings of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.Long Beach,CA,USA:IEEE,2019:2507-2516.
[26]GANIN Y,USTINOVA E,AJAKAN H,et al.Domain-adversarial training of neural networks [J].The Journal of Machine Learning Research,2016,17(1):2096-2030.
[27]BEN-DAVID S,BLITZER J,GRAMMAR K,et al.A theory of learning from different domains [J].Machine Learning,2010,79:151-175.
[28]COLUCCIA A,FASCISTA A,SCHUMANN A,et al.Drone-vs-bird detection challenge at IEEE AVSS2021 [C]//2021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance(AVSS).IEEE,2021:1-8.
[29]SUN X L,GUO L C,ZHANG W L,et al.A dataset for small infrared moving target detection under clutter background[EB/OL].https://doi.org/10.11922/sciencedb.j00001.00.
[30]XU C,WANG J W,YANG W,et al.Dot distance for tiny object detection in aerial images [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2021:1192-1201.
[31]LIU T,ZHAO Y,WEI Y C,et al.Concealed object detection for activate millimeter wave image [J].IEEE Transactions on Industrial Electronics,2019,66(12):9909-9917.
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