计算机科学 ›› 2026, Vol. 53 ›› Issue (1): 173-179.doi: 10.11896/jsjkx.250300009

• 计算机图形学&多媒体 • 上一篇    下一篇

基于双向交叉注意力跨域融合的航拍图像伪装目标识别方法

李昂, 章杰元, 刘逊韵   

  1. 军事科学院 北京 100091
  • 收稿日期:2025-03-03 修回日期:2025-06-22 发布日期:2026-01-08
  • 通讯作者: 刘逊韵(xunyunliu@outlook.com)
  • 作者简介:(angli.cs@outlook.com)
  • 基金资助:
    国家自然科学基金青年科学基金(62206311)

Camouflaged Object Detection for Aerial Images Based on Bidirectional Cross-attentionCross-domain Fusion

LI Ang, ZHANG Jieyuan, LIU Xunyun   

  1. Academy of Military Sciences, Beijing 100091, China
  • Received:2025-03-03 Revised:2025-06-22 Online:2026-01-08
  • About author:LI Ang,born in 1992,research assistant.His main research interests include computer vison and AI security.
    LIU Xunyun,born in 1989,associate research fellow.His main research in-terests include cloud computing and machine learning.
  • Supported by:
    Young Scientists Fund of the National Natural Science Foundation of China(62206311).

摘要: 针对航拍图像中伪装目标与环境高度融合以及实时性要求高的挑战,提出了一种基于双向交叉注意力跨域融合的伪装目标识别方法。首先,提出跨域双分支特征提取网络,分别从RGB域和频域进行提取特征,从而增强对低对比度图像的特征提取能力。同时,通过设计双向交叉注意力融合模块,在多个尺度上将频域特征与RGB特征进行基于注意力机制的双向特征融合,从而有效提升网络表征能力。实验结果表明,相比其他代表性算法,所提出的方法在目标识别准确性与实时性上达到了更优的平衡。

关键词: 航拍图像, 伪装目标识别, 频域特征, 双向交叉注意力

Abstract: To address the challenges of highly integration with the environment and the high demand for real-time performance,this paper proposes a camouflaged object detection model for aerial images using bidirectional cross-attention cross-domain fusion.Firstly,a feature extraction network with two branches is constructed to extract features from both RGB and frequency domain.Simultaneously,frequency features and RGB features are crossly fused at multiple scales using bidirectional cross-attention fusion modules,effectively improving the network’s representational capacity.Experimental results show that the proposed model achieves a better balance between target recognition accuracy and real-time performance,compared to other representative models.

Key words: Aerial images, Camouflaged object detection, Frequency domain, Bidirectional cross-attention

中图分类号: 

  • TP391.41
[1]ZHU L,WANG X,KE Z,et al.BiFormer:vision transformerwith bi-level routing attention[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2023:10323-10333.
[2]JIANG L,YUAN B,DU J,et al.MFFSODNet:Multi-Scale Feature Fusion Small Object Detection Network for UAV Aerial Images[J].IEEE Transactions on Instrumentation and Mea-surement,2024,73:1-14.
[3]ZHAO J,ZHANG B,WANG G,et al.Spectral CamouflageCharacteristics and Recognition Ability of Targets Based on Vi-sible/Near-Infrared Hyperspectral Images[J].Photonics,2022,9:957-957.
[4]DU W C,YU H,ZENG X J,et al.High resolution single-photon imaging for recognition of camouflaged target[C]//Seventh Symposium on Novel Photoelectronic Detection Technology and Applications.2021.
[5]ANJAR W,DENI S R,SILFIA A,et al.Combination ofSobel+Prewitt Edge Detection Method with Roberts+Canny on Passion Flower Image Identification[J].Journal of Physics:Confe-rence Series,2021,1933(1):012037.
[6]OTSU N.A Threshold Selection Method from Gray-Level Histograms[J].IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66.
[7]KONG L,DONG J,GE J,et al.Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:5886-5895.
[8]YANG F,ZHAI Q,LI X,et al.Uncertainty-guided transformer reasoning for camouflaged object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:4146-4155.
[9]ZHAO J X,LIU J J,FAN D P,et al.Egnet:Edge guidance network for salient object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:8779-8788.
[10]WANG S,XU Y X,ZENG D W,et al.Deep learning-based spec-tral reconstruction in camouflaged target detection[J].International Journal of Applied Earth Observation and Geoinformation,2024,126:103645.
[11]DEEPTI Y,KUMAR M A,CHANDRA K T,et al.Detectionand Identification of Camouflaged Targets using Hyperspectral and LiDAR data[J].Defence Science Journal,2018,68(6):540-540.
[12]FAND P,JI G P,ZHOU T,et al.Pranet:Parallel reverse attention network for polyp segmentation[C]//International Confe-rence on Medical Image Computing and Computer-assisted Intervention.2020:263-273.
[13]MEI H,JI G P,WEI Z,et al.Camouflaged object segmentation with distraction mining[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:8772-8781.
[14]ZHAO Z,BAKAR A B E,RAZAK A B N,et al.Corrosionimage classification method based on EfficientNetV2[J].He-liyon,2024,10(17):e36754.
[15]ZHONG Y J,BO L,LYU T,et al.Detecting Camouflaged Object in Frequency Domain[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:4504-4513.
[16]LIU M Z,DI X G.Extraordinary MHNet:Military high-levelcamouflage object detection network and dataset[J].Neurocomputing,2023,549:126446.
[17]ZHAI Q,LI X,YANG F,et al.Mutual graph learning for cam-ouflaged object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:12997-13007.
[18]LYU Y Q,ZHANG J,DAI Y C,et al.Simultaneously localize,segment and rank the camouflaged objects[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:11591-11601.
[19]LI A X,ZHANG J,LYU Y Q,et al.Uncertainty-aware joint salient object and camouflaged object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:10071-10081.
[20]FAN D P,JI G P,CHENG M M,et al.Concealed object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(10):6024-6042.
[21]HUANG Z,DAI H,XIANG T Z,et al.Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:5557-5566.
[22]FAN D P,CHENG M M,LIU Y,et al.Structure-measure:A new way to evaluate foreground maps[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:4548-4557.
[23]JUTTEN J R,HARRISON J,KJOE M L R P,et al.A novel cognitive-functional composite measure to detect changes in early Alzheimer’s disease:Test-retest reliability and feasibility[J].Alzheimer’s & Dementia:Diagnosis,Assessment & Disease Monitoring,2018,10:153-160.
[24]SINGHAL A,BEDI P.USteg-DSE:Universal quantitativeSteganalysis framework using Densenet merged with Squeeze &Excitation net[J].Signal Processing:Image Communication,2024,128:117171-117171.
[25]DICE L R.Measures of the amount ofecologic association between species[J].Ecology,2023,26:297-302.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!