基于多尺度时空流U-Net的红外小目标检测模型

苏毅; 陈洁; 闫科; 赖正超

doi:10.7527/S1000-6893.2026.33940

航空学报 >

0 1 - 0

DOI: https://doi.org/10.7527/S1000-6893.2026.33940

基于多尺度时空流U-Net的红外小目标检测模型

苏毅 ,
陈洁 ,
闫科 ,
赖正超

展开

1. 电子科技大学
2. 北京遥感设备研究所

收稿日期: 2026-05-25

修回日期: 2026-09-03

网络出版日期: 2026-09-10

收起

Infrared Small Target Detection Model Based on Multi-Scale Temporal-Spatial Stream U-Net

SU Yi ,
CHEN Jie ,
YAN Ke ,
LAI Zheng-Chao

Expand

Received date: 2026-05-25

Revised date: 2026-09-03

Online published: 2026-09-10

Fold

摘要

针对复杂背景下红外弱小目标检测存在的背景杂波强、信噪比低及目标特征微弱等问题，提出一种多尺度时空流U-Net模型。该模型通过并行的空域背景建模支路与时域动态建模支路，分别建模背景的空间结构与时间演化特性；设计自适应时空融合模块，动态融合双支路特征；并引入目标感知加权损失与时空一致性约束，在强效抑制背景的同时保留弱小目标信号。在仿真与实测多类数据集上的实验表明：多尺度时空流U-Net的平均检测准确率达到97.5%，虚警率低至2.2%，均显著优于现有方法。该模型为复杂动态场景下的红外小目标检测提供了高精度、低虚警的有效解决方案。

关键词： 红外弱小目标检测; 背景抑制; 残差网络; 深度学习; 图像识别

本文引用格式

苏毅 , 陈洁 , 闫科 , 赖正超 . 基于多尺度时空流U-Net的红外小目标检测模型[J]. 航空学报, 0 : 1 -0 . DOI: 10.7527/S1000-6893.2026.33940

Abstract

Aiming at the problems of strong background clutter, low signal-to-noise ratio (SNR) and weak target features existing in infrared dim and small target detection under complex backgrounds, a multi-scale temporal-spatial U-Net model is proposed. The model constructs a parallel spatial background modeling branch and a temporal dynamic modeling branch to model spatial structure of the background and temporal evolution characteristics of the environment respectively. An adaptive spatio-temporal fusion module is designed to dynamically fuse the features of dual branches via learnable weights. Meanwhile, target-aware weighted loss and spatio-temporal consistency constraint are introduced to effectively suppress the background while retaining the signals of dim and small targets. Experiments on multiple simulated and measured datasets show that the proposed model achieves an average detection accuracy of 97.5% and a false alarm rate as low as 2.2%, which are significantly superior to existing methods. The proposed model provides an effective solution with high precision and low false alarm for infrared small target detection in complex dynamic scenarios.

Key words： infrared small target detection; background suppression; residual network; deep learning; image recognition

参考文献

[1] ZHU Haiyong, CHEN Junlin, ZENG Zhijiang, et al. Stray light analysis and suppression of long-wave infrared Dewar component for cold optics [J]. Infrared and Laser Engineering, 2023, 52(7): 20220823.
[2] YANG Dezhen, YU Songlin, FENG Jinjun. Dynamic real-time restoration algorithm of defective pixels based on spatio-temporal statistics feature [J]. Infrared and Laser Engineering, 2022, 51(3): 20210798.
[3] HAN Jinhui, WEI Yantao, PENG Zhenming, et al. Infrared dim and small target detection: A review [J]. Infrared and Laser Engineering, 2022, 51(4): 20210393.
[4] LUO X, WANG S, LI B, et al. A mixed noise filter acceleration algorithm based on mean value and variance similarity [C]//2011 Second International Conference on Digital Manufacturing & Automation. IEEE, 2011: 55-58.
[5] HSIEH M H, CHENG F C, SHIE M C, et al. Fast and efficient median filter for removing 1-99% levels of salt-and-pepper noise in images [J]. Engineering Applications of Artificial Intelligence, 2013, 26(4): 1333-1338.
[6] ISMAEL S H, MUSTAFA F M, OKUMUS I T. A new approach of image denoising based on discrete wavelet transform [C]//2016 World Symposium on Computer Applications & Research (WSCAR). IEEE, 2016: 36-40.
[7] WANG Huabing, WAN Lanjun. Small infrared target detection based on contourlet transformation and target characteristic analysis [J]. Journal of Electronic Measurement and Instrument, 2019, 33(3): 120-125.
[8] CAO Y P, HE Z W, YANG J X, et al. A multi-scale non-uniformity correction method based on wavelet decomposition and guided filtering for uncooled long wave infrared camera [J]. Signal Processing: Image Communication, 2018, 60: 13-21.
[9] BUADES A, COLL B, MOREL J M. Non-local means denoising [J]. Image Processing on Line, 2011, 1: 208-212.
[10] DABOV K, FOI A, KATKOVNIK V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering [J]. IEEE Transactions on Image Processing, 2007, 16(8): 2080-2095.
[11] DAI Y M, 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, 2021: 950-959.
[12] LI B, XIAO C, WANG L, et al. Dense nested attention network for infrared small target detection [J]. IEEE Transactions on Image Processing, 2023, 32: 1745-1758.
[13] DESHPANDE S D, ER M H, VENKATESWARLU R, et al. Max-mean and max-median filters for detection of small targets [C]//Signal and Data Processing of Small Targets, SPIE, 1999, 3809: 74-83.
[14] CAO Y, LIU R M, YANG J. Small target detection using two-dimensional least mean square (TDLMS) filter based on neighborhood analysis [J]. International Journal of Infrared and Millimeter Waves, 2008, 29: 188-200.
[15] TOM V T, PELI T, LEUNG M, et al. Morphology-based algorithm for point target detection in infrared backgrounds [C]//Signal and Data Processing of Small Targets, SPIE, 1993, 1954: 2-11.
[16] CHEN C L P, LI H, WEI Y, et al. A local contrast method for small infrared target detection [J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 52(1): 574-581.
[17] ZHANG L, PENG L, ZHANG T, et al. Infrared small target detection via non-convex rank approximation minimization joint l2,1 norm [J]. Remote Sensing, 2018, 10(11): 1821.
[18] 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.
[19] WU Tianshu, ZHANG Zhijia, LIU Yunpeng, et al. A lightweight small object detection algorithm based on improved SSD [J]. Infrared and Laser Engineering, 2018, 47(7): 0703005.
[20] JIANG Xinhao, CAI Wei, YANG Zhiyong, et al. Infrared dim and small target detection based on YOLO-IDSTD algorithm [J]. Infrared and Laser Engineering, 2022, 51(3): 20210106.
[21] Li N, Yang X, Zhao H. DBMSTN: A dual branch multiscale spatio-temporal network for dim-small target detection in infrared image[J]. Pattern Recognition, 2025, 162: 111372.
[22] Xiangsuo Fan , Zhiyong Xu , Jianlin Zhang, Infrared dim and small target background suppression based on improved gradient inverse weighting filter[J], Opto-Electronic Engineering 44 , 719-724 (2017). DOI: 10.3969/j.issn.1003-501X.2017.07.008.
[23] Xueqi Cheng, Fan Wang, Xiaopeng Hu, Xinrong Wu, Min Nuo, IRWT-YOLO: A Background Subtraction-Based Method for Anti-Drone Detection[J], Drones, Vol.9, 2025, doi:10.3390/drones9040297.
[24] [33] Ouyang C, Liu Y, Chen X, A lightweight attention mechanism for Infrared Small-Target Detection[C], the 4th Asia-Pacific Artificial Intelligence and Big Data Forum, 2025.
[25] Y. Sun et al., "Infrared Small Target Detection via Nonconvex Weighted Tensor Rank Minimization and Adaptive Spatial–Temporal Modeling," in IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1-18, 2025, Art no. 5003918, doi: 10.1109/TGRS.2025.3563495.
[26] F. Li, P. Rao, W. Sun, Y. Su and X. Chen, "A New Motion Feature-Enhanced Multiframe Spatial–Temporal Infrared Target Detection Network," in IEEE Transactions on Geoscience and [36] Remote Sensing, vol. 63, pp. 1-19, 2025, Art no. 5006819, doi: 10.1109/TGRS.2025.3603784.
[27] Dongyuan Zang, Weihua Su, DMDNet: A dual-branch infrared small target detection network based on mamba and difference convolution[J], Optics & Laser Technology, Vol.192, 2025, doi: 10.1016/j.optlastec.2025.114090Get rights and content.
[28] Rixiang Ni, Boyang Li, Jun Chen, Yonghao Li, Feiyu Ren, Yuji Wang, Haoyang Yuan, Wujiao He, Wei An, Rethinking IRSTD: Single-Point Supervision Guided Encoder-only Framework is Enough for Infrared Small Target Detection[J], Computer Vision and Pattern Recognition, 2025, doi: 10.48550/arXiv.2604.05363.
[29] Jinmiao Zhao, Zelin Shi, Chuang Yu, Yunpeng Liu, Yimain Dai, Towards robust infrared small target detection: A feature-enhanced and sensitivity-tunable framework[J], Knowledge-Based Systems, Vol. 330, 2025, doi: 10.1016/j.knosys.2025.114519.
[30] R. Li et al., "Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Better," in IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2026.3683258.
[31] R. Li et al., "Direction-Coded Temporal U-Shape Module for Multiframe Infrared Small Target Detection," in IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 1, pp. 555-568, Jan. 2025, doi: 10.1109/TNNLS.2023.3331004
[32] Shuo Zhuang, Jing Peng, Meibin Qi, Di Wang, Kunyuan Li, Yimin Liu, A Temporal-Semantic Interaction Network for multi-frame infrared small target detection[J], Knowledge-Based Systems, Vol. 324, 2025, doi: 10.1016/j.knosys.2025.113840.

Options

摘要页面

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献