基于深度学习的红外小目标检测方法综述
A Review of Deep Learning-Based Infrared Weak Target Detection Methods
摘要: 红外小目标检测作为智能安防的核心技术，针对低信噪比、弱表征等难题，系统构建了红外小目标检测的理论框架与方法体系。首先，通过公开数据集开展多维度特性分析，结合背景杂波建模与目标辐射特性揭示成像机理。继而聚焦深度学习范式，建立分类研究体系。单阶段检测方向聚焦YOLO与SSD系列算法的效率与精度平衡机制改进。在CNN方法层面，关注多尺度特征融合、注意力协同、轻量化编解码、密集嵌套特征交互关键技术以及Transformer与小样本学习在红外小目标检测中的应用。最后指出，未来应倾向于物理模型驱动的新型网络架构设计，通过辐射特性建模与深度学习特征融合提升算法鲁棒性。发展边缘计算友好的轻量化模型，采用神经架构搜索技术实现模型参数量压缩。探索红外、可见光、雷达多模态协同检测机制。开发自监督小样本学习范式，利用生成对抗网络缓解数据稀缺问题。这些突破将检测技术向全天候、高实时、强泛化方向持续演进。
Abstract: Infrared Small Target Detection (ISTD), a pivotal technology in intelligent security systems, addresses challenges such as low signal-to-noise ratio (SNR) and weak feature representation through a systematic framework. The methodology begins with multi-dimensional characteristic analysis using public datasets, integrating background clutter suppression and target radiation modeling to elucidate imaging mechanisms. Under a deep learning paradigm, the research establishes a dual-axis classification: Single-stage detection optimizes efficiency and accuracy trade-offs in YOLO and SSD architectures via anchor-free designs and feature pyramid enhancements. CNN-based innovations focus on multi-scale fusion, attention mechanisms (spatial-channel and coordination), lightweight encoders (depthwise separable convolutions), dense cross-layer interaction for enhanced feature extraction, as well as cutting-edge applications of Transformer and few-shot learning in infrared small target detection. Future priorities emphasize: Physics-guided networks merging radiation physics with deep features for robustness. Edge-optimized lightweight models via neural architecture search (NAS) and pruning. Explore the multimodal cooperative detection mechanism of infrared, visible light and radar. Self-supervised few-shot learning using GANs to overcome data scarcity. These breakthroughs will continue to evolve the detection technology towards all-weather, high real-time, and strong generalization.
文章引用：阿勒尔呷. 基于深度学习的红外小目标检测方法综述[J]. 计算机科学与应用, 2025, 15(6): 220-230. https://doi.org/10.12677/csa.2025.156172

参考文献

[1] Ren, S., He, K., Girshick, R. and Sun, J. (2017) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] [PubMed]
[2] Liu, T., Yin, Q., Yang, J., Wang, Y. and An, W. (2023) Combining Deep Denoiser and Low-Rank Priors for Infrared Small Target Detection. Pattern Recognition, 135, Article ID: 109184. [Google Scholar] [CrossRef] 
[3] Deng, H., Liu, J. and Chen, Z. (2010) Infrared Small Target Detection Based on Modified Local Entropy and EMD. Chinese Optics Letters, 8, 24-28.
[4] Chen, J., Zhu, Z., Hu, H., Qiu, L., Zheng, Z. and Dong, L. (2023) Multi-Scale Local Contrast Fusion Based on LOG in Infrared Small Target Detection. Aerospace, 10, Article 449. [Google Scholar] [CrossRef] 
[5] Shao, X., Fan, H., Lu, G. and Xu, J. (2012) An Improved Infrared Dim and Small Target Detection Algorithm Based on the Contrast Mechanism of Human Visual System. Infrared Physics & Technology, 55, 403-408. [Google Scholar] [CrossRef] 
[6] Liu, C., Xie, F., Zhang, H., Jiang, Z. and Zheng, Y. (2023) Infrared Small Target Detection Based on Multi-Perception of Target Features. Infrared Physics & Technology, 135, Article ID: 104927. [Google Scholar] [CrossRef] 
[7] Gao, R. and Cai, Z. (2023) Object Detection in Thermal Infrared Image Based on Improved YOLOX. IEEE Geoscience and Remote Sensing Letters, 20, 1-4. [Google Scholar] [CrossRef] 
[8] Zhang, L., Lin, W., Shen, Z., Zhang, D., Xu, B., Wang, K., et al. (2023) Infrared Dim and Small Target Sequence Dataset Generation Method Based on Generative Adversarial Networks. Electronics, 12, Article 3625. [Google Scholar] [CrossRef] 
[9] He, Y., Li, M., Zhang, J. and An, Q. (2015) Small Infrared Target Detection Based on Low-Rank and Sparse Representation. Infrared Physics & Technology, 68, 98-109. [Google Scholar] [CrossRef] 
[10] Gao, C.Q., Zhang, T.Q. and Li, Q. (2012) Small Infrared Target Detection Using Sparse Ring Representation. IEEE Aerospace and Electronic Systems Magazine, 27, 21-30. [Google Scholar] [CrossRef] 
[11] Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[12] Huang, X,. Wang, X., Lv, W., et al. (2021) PP-YOLOv2: A Practical Object Detector. arXiv: 2104.10419.
[13] Lin, X.P. (2019) Object Detection System Based on Vehiclebrone Infrared Image. Beijing Jiaotong University.
[14] Redmon, J. and Farhadi, A. (2018) Yolov3: An Incremental Improvement. arXiv: 1804.02767.
[15] Mukai, L., Tao, Z. and Wennan, C. (2020) Research of Infrared Small Pedestrian Target Detection Based on YOLOv3. Infrared Technology, 42, 176-181.
[16] Xu, Q., Huang, H., Zhou, C. and Zhang, X. (2021) Research on Real-Time Infrared Image Fault Detection of Substation High-Voltage Lead Connectors Based on Improved YOLOv3 Network. Electronics, 10, Article 544. [Google Scholar] [CrossRef] 
[17] Liu, M., Wang, X., Zhou, A., Fu, X., Ma, Y. and Piao, C. (2020) UAV-YOLO: Small Object Detection on Unmanned Aerial Vehicle Perspective. Sensors, 20, Article 2238. [Google Scholar] [CrossRef] [PubMed]
[18] Jocher, G., Stoken, A., Borovec, J., et al. (2021) ultralytics/yolov5: v4. 0-nn. SiLU () Activations, Weights & Biases logging, PyTorch Hub Integration. Zenodo.
[19] Li, S., Li, Y., Li, Y., Li, M. and Xu, X. (2021) YOLO-FIRI: Improved YOLOv5 for Infrared Image Object Detection. IEEE Access, 9, 141861-141875. [Google Scholar] [CrossRef] 
[20] Mou, X., Lei, S. and Zhou, X. (2023) YOLO-FR: A YOLOv5 Infrared Small Target Detection Algorithm Based on Feature Reassembly Sampling Method. Sensors, 23, Article 2710. [Google Scholar] [CrossRef] [PubMed]
[21] Fan, X., Ding, W., Qin, W., Xiao, D., Min, L. and Yuan, H. (2023) Fusing Self-Attention and CoordConv to Improve the YOLOv5s Algorithm for Infrared Weak Target Detection. Sensors, 23, Article 6755. [Google Scholar] [CrossRef] [PubMed]
[22] Wei, Z., Zhao, J., Chen, X., Wang, A., Li, F. and Gu, Y. (2023) Infrared Target Detection Based on the Fusion of Attention Mechanism and YOLOv5. 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), Changchun, 24-26 February 2023, 933-936. [Google Scholar] [CrossRef] 
[23] 蔡仁昊, 程宁, 彭志勇, 等. 基于深度学习的轻量化红外弱小车辆目标检测算法研究[J]. 红外与激光工程, 2022, 51(12): 357-367.
[24] Dang, L., Liu, G., Hou, Y., et al. (2024) YOLO-FNC: An Improved Method for Small Object Detection in Remote Sensing Images Based on YOLOv7. IAENG International Journal of Computer Science, 51, 1281-1290.
[25] Mingkai, Y.U.E., Kangnan, Q., Cong, Z., et al. (2024) Research on Infrared Small Target Detection Algorithm Based on Improved YOLOv8. Infrared Technology, 46, 1286-1292.
[26] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., et al. (2016) SSD: Single Shot MultiBox Detector. In: Leibe, B., Matas, J., Sebe, N. and Welling, M., Eds., Computer Vision—ECCV 2016, Springer, 21-37. [Google Scholar] [CrossRef] 
[27] Fu, C.Y., Liu, W., Ranga, A., et al. (2017) DSSD: Deconvolutional Single Shot Detector. arXiv: 1701.06659.
[28] Singh, B., Najibi, M. and Davis, L.S. (2018) Sniper: Efficient Multi-Scale Training. arXiv: 1805.09300.
[29] Lin, T., Dollar, P., Girshick, R., He, K., Hariharan, B. and Belongie, S. (2017) Feature Pyramid Networks for Object Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 936-944. [Google Scholar] [CrossRef] 
[30] Ding, L., Xu, X., Cao, Y., Zhai, G., Yang, F. and Qian, L. (2021) Detection and Tracking of Infrared Small Target by Jointly Using SSD and Pipeline Filter. Digital Signal Processing, 110, Article ID: 102949. [Google Scholar] [CrossRef] 
[31] Shen, Z., Liu, Z., Li, J., Jiang, Y., Chen, Y. and Xue, X. (2017) DSOD: Learning Deeply Supervised Object Detectors from Scratch. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 1937-1945. [Google Scholar] [CrossRef] 
[32] Wang, K., Li, S., Niu, S. and Zhang, K. (2019) Detection of Infrared Small Targets Using Feature Fusion Convolutional Network. IEEE Access, 7, 146081-146092. [Google Scholar] [CrossRef] 
[33] Song, Z., Zhang, Y., Liu, Y., Yang, K. and Sun, M. (2022) MSFYOLO: Feature Fusion-Based Detection for Small Objects. IEEE Latin America Transactions, 20, 823-830. [Google Scholar] [CrossRef] 
[34] Fang, H., Xia, M., Zhou, G., Chang, Y. and Yan, L. (2022) Infrared Small UAV Target Detection Based on Residual Image Prediction via Global and Local Dilated Residual Networks. IEEE Geoscience and Remote Sensing Letters, 19, 1-5. [Google Scholar] [CrossRef] 
[35] Wang, Y., Zhao, L., Ma, Y., Shi, Y. and Tian, J. (2023) Multiscale YOLOv5-AFAM-Based Infrared Dim-Small-Target Detection. Applied Sciences, 13, Article 7779. [Google Scholar] [CrossRef] 
[36] Chen, F., Gao, C., Liu, F., Zhao, Y., Zhou, Y., Meng, D., et al. (2022) Local Patch Network with Global Attention for Infrared Small Target Detection. IEEE Transactions on Aerospace and Electronic Systems, 58, 3979-3991. [Google Scholar] [CrossRef] 
[37] Zuo, Z., Tong, X., Wei, J., Su, S., Wu, P., Guo, R., et al. (2022) AFFPN: Attention Fusion Feature Pyramid Network for Small Infrared Target Detection. Remote Sensing, 14, Article 3412. [Google Scholar] [CrossRef] 
[38] Qi, M., Liu, L., Zhuang, S., Liu, Y., Li, K., Yang, Y., et al. (2022) FTC-Net: Fusion of Transformer and CNN Features for Infrared Small Target Detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 8613-8623. [Google Scholar] [CrossRef] 
[39] Wang, Z., Zang, T., Fu, Z., Yang, H. and Du, W. (2023) RLPGB-Net: Reinforcement Learning of Feature Fusion and Global Context Boundary Attention for Infrared Dim Small Target Detection. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-15. [Google Scholar] [CrossRef] 
[40] Wu, S.C. and Zuo, Z.R. (2019) Small Target Detection in Infrared Images Using Deep Convolutional Neural Networks. Journal of Infrared, Millimeter, and Terahertz Waves, 38, 371-380.
[41] Wang, H., Li, H., Zhou, H. and Chen, X. (2021) Low-altitude Infrared Small Target Detection Based on Fully Convolutional Regression Network and Graph Matching. Infrared Physics & Technology, 115, Article ID: 103738. [Google Scholar] [CrossRef] 
[42] Zhang, L., Han, P., Xi, J. and Zuo, Z. (2023) Infrared Small Target Detection Based on a Temporally-Aware Fully Convolutional Neural Network. Remote Sensing, 15, Article 4198. [Google Scholar] [CrossRef] 
[43] Chi, W., Liu, J., Wang, X., Feng, R. and Cui, J. (2023) DBGNet: Dual-Branch Gate-Aware Network for Infrared Small Target Detection. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-14. [Google Scholar] [CrossRef] 
[44] Li, B., Xiao, C., Wang, L., Wang, Y., Lin, Z., Li, M., et al. (2023) Dense Nested Attention Network for Infrared Small Target Detection. IEEE Transactions on Image Processing, 32, 1745-1758. [Google Scholar] [CrossRef] [PubMed]
[45] Lv, G., Dong, L., Liang, J. and Xu, W. (2022) Novel Asymmetric Pyramid Aggregation Network for Infrared Dim and Small Target Detection. Remote Sensing, 14, Article 5643. [Google Scholar] [CrossRef] 
[46] Iandola, F.N., Han, S., Moskewicz, M.W., et al. (2016) SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and < 0.5 MB Model Size. arXiv: 1602.07360.
[47] Zang, Y., Fan, C., Zheng, Z. and Yang, D. (2021) Pose Estimation at Night in Infrared Images Using a Lightweight Multi-Stage Attention Network. Signal, Image and Video Processing, 15, 1757-1765. [Google Scholar] [CrossRef] 
[48] Fu, J., Li, F., Zhao, J., Tong, J. and Zhang, H. (2023) Infrared Small Dim Target Detection under Maritime near Sea-Sky Line Based on Regional-Division Local Contrast Measure. IEEE Geoscience and Remote Sensing Letters, 20, 1-5. [Google Scholar] [CrossRef] 
[49] 杜妮妮, 单凯东, 卫莎莎. LPformer：基于拉普拉斯金字塔多级Transformer的红外小目标检测[J]. 红外技术, 2023, 45(6): 630-638.
[50] Yang, H., Mu, T., Dong, Z., Zhang, Z., Wang, B., Ke, W., et al. (2024) PBT: Progressive Background-Aware Transformer for Infrared Small Target Detection. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-13. [Google Scholar] [CrossRef] 
[51] Ciocarlan, A., Hégarat-Mascle, S.L., Lefebvre, S., et al. (2024) Robust Infrared Small Target Detection Using Self-Supervised and a Contrario Paradigms. arXiv: 2410.07437.
[52] Han, G. and Lim, S. (2024) Few-Shot Object Detection with Foundation Models. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 16-22 June 2024, 28608-28618. [Google Scholar] [CrossRef] 
[53] Zhang, J., Lei, J., Xie, W., Fang, Z., Li, Y. and Du, Q. (2023) SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-15. [Google Scholar] [CrossRef]