门控卷积和高频特征融合的红外小目标检测

doi:10.3778/j.issn.1002-8331.2311-0326

摘要/Abstract

摘要： 针对在远距离复杂场景下红外小目标尺寸和形状差异大、检测精度欠佳的问题，提出了一种基于门控卷积和高频特征融合的红外小目标检测模型。为了解决复杂场景下目标尺寸差异的问题，通过在U-Net下采样过程中使用门控快速傅里叶卷积（gated fast Fourier convolution， GFFC）模块提取多尺度的全局和局部特征，为提升模型在不同复杂程度数据集上的训练效果，利用超参数门控调节网络对目标全局和局部特征的权重，以平衡对全局和局部特征的需求。为解决红外小目标形状差异的问题，采用了高频特征融合（high-frequency feature fusion， HFF）模块，进一步提取高频子带特征，增强红外小目标细节纹理信息。在SIRST和IRSTD数据集上的实验结果表明，相比基准UCF方法，提出的方法在两个数据集的评价指标下分别提升了0.83个百分点、0.40个百分点和5.18个百分点、0.23个百分点，证明了该方法的有效性。

关键词: 门控快速傅里叶卷积, 高频特征融合, 红外小目标检测

Abstract: Aiming at the problem of poor detection accuracy of infrared small targets with large differences in size and shape in remote complex scenes, an infrared small target detection model based on gated convolution and high-frequency feature fusion is proposed. In order to solve the problem of differences in target sizes in complex scenes, multi-scale global and local features are extracted by using the gated fast Fourier convolution (GFFC) module during U-Net downsampling, the hyperparameter gating is utilized to adjust the weights of the target’s global and local features to balance the demand for global and local features in order to improve the training effect of the model on datasets with different levels of complexity. In order to solve the problem of shape difference of infrared small targets, the high-frequency feature fusion (HFF) module is used to further extract high-frequency sub-band features to enhance the detailed texture information of infrared small targets. The experimental results on the SIRST and IRSTD datasets show that compared to the benchmark UCF method, the proposed method improves 0.83 percentage points, 0.40 percentage points, and 5.18 percentage points, 0.23 percentage points under the evaluation metrics of the two datasets, respectively, which proves the effectiveness of the method.

Key words: gated fast Fourier convolution (GFFC), high-frequency feature fusion (HFF), infrared small target detection

刘奎, 唐慧萍, 苏本跃. 门控卷积和高频特征融合的红外小目标检测[J]. 计算机工程与应用, 2025, 61(7): 306-314.

LIU Kui, TANG Huiping, SU Benyue. Gated Convolution and High-Frequency Feature Fusion for Infrared Small Target Detection[J]. Computer Engineering and Applications, 2025, 61(7): 306-314.

参考文献

[1] 赵兴科, 李明磊, 张弓, 等. 基于显著图融合的无人机载热红外图像目标检测方法[J]. 自动化学报, 2021, 47(9): 2120-2131.
ZHAO X K, LI M L, ZHANG G, et al. Object detection method based on saliency map fusion for UAV-borne thermal images[J]. Acta Automatica Sinica, 2021, 47(9): 2120-2131.
[2] 李其昌, 李兵伟, 王宏臣. 非制冷红外成像技术发展动态及其军事应用[J]. 军民两用技术与产品, 2016(21): 54-57.
LI Q C, LI B W, WANG H C. Development trend of uncooled infrared imaging technology and its military application[J]. Dual Use Technologies & Products, 2016(21): 54-57.
[3] 王云杰, 王艳林, 夏润秋, 等. 大视场红外告警系统中目标高精度方位提取[J]. 激光技术, 2023, 47(2): 200-204.
WANG Y J, WANG Y L, XIA R Q, et al. High precision azimuth extraction of target in large field of view infrared warning system[J]. Laser Technology, 2023, 47(2): 200-204.
[4] 杨亚东, 黄胜一, 谭毅华. 基于低秩和重加权稀疏表示的红外弱小目标检测算法[J]. 应用科学学报, 2023, 41(5): 753-765.
YANG Y D, HUANG S Y, TAN Y H. Infrared dim and small target detection algorithm based on low-rank and reweighted sparse representation[J]. Journal of Applied Sciences, 2023, 41(5): 753-765.
[5] 张婷, 张兴忠, 王慧民, 等. 基于图神经网络的变电站场景三维目标检测[J]. 计算机工程与应用, 2023, 59(9): 329-336.
ZHANG T, ZHANG X Z, WANG H M, et al. 3D object detection in substation scene based on graph neural network[J]. Computer Engineering and Applications, 2023, 59(9): 329-336.
[6] 黄磊, 杨媛, 杨成煜, 等. FS-YOLOv5: 轻量化红外目标检测方法[J]. 计算机工程与应用, 2023, 59(9): 215-224.
HUANG L, YANG Y, YANG C Y, et al. FS-YOLOv5: lightweight infrared rode target detection method[J]. Computer Engineering and Applications, 2023, 59(9): 215-224.
[7] 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.
[8] DAI Y M, WU Y Q. Reweighted infrared patch-tensor model with both nonlocal and local priors for single-frame small target detection[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(8): 3752-3767.
[9] 王志武, 张子淼, 许凯, 等. 基于最佳偏振角的线性位姿测量方法研究[J]. 红外与激光工程, 2022, 51(3): 329-338.
WANG Z W, ZHANG Z M, XU K, et al. Research on linear pose measurement method based on optimal polarization angle[J]. Infrared and Laser Engineering, 2022, 51(3): 329-338.
[10] ZHU H, LIU S M, DENG L Z, et al. Infrared small target detection via low-rank tensor completion with top-hat regularization[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(2): 1004-1016.
[11] ZHANG L D, PENG Z M. Infrared small target detection based on partial sum of the tensor nuclear norm[J]. Remote Sensing, 2019, 11(4): 382.
[12] 陆慧敏, 杨朔. 基于深度神经网络的自动驾驶场景三维目标检测算法[J]. 北京工业大学学报, 2022, 48(6): 589-597.
LU H M, YANG S. Three-dimensional object detection algorithm based on deep neural networks for automatic driving[J]. Journal of Beijing University of Technology, 2022, 48(6): 589-597.
[13] DAI Y M, WU Y Q, ZHOU F, et al. Asymmetric contextual modulation for infrared small target detection[C]//Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2021: 950-959.
[14] DAI Y M, WU Y Q, ZHOU F, et al. Attentional local contrast networks for infrared small target detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(11): 9813-9824.
[15] LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 10012-10022.
[16] ZHANG T F, CAO S Y, PU T, et al. AGPCNet: attention-guided pyramid context networks for infrared small target detection[J]. arXiv:2111.03580, 2021.
[17] WANG C Y, WANG H, PAN P W. Local contrast and global contextual information make infrared small object salient again[J]. arXiv:2301.12093, 2023.
[18] LIU F C, GAO C Q, CHEN F, et al. Infrared small and dim target detection with transformer under complex backgrounds[J]. IEEE Transactions on Image Processing, 2023, 32: 5921-5932.
[19] 易图明, 王先全, 袁威, 等. 基于导向滤波和小波变换的红外可见光图像融合改进算法研究[J]. 现代信息科技, 2023, 7(6): 41-45.
YI T M, WANG X Q, YUAN W, et al. Research on improved infrared visible light image fusion algorithm based on guided filtering and wavelet transform[J]. Modern Information Technology, 2023, 7(6): 41-45.
[20] YU Y C, ZHAN F N, LU S J, et al. WaveFill: a wavelet-based generation network for image inpainting[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2021: 14094-14103.
[21] MA J Y, TANG L F, FAN F, et al. SwinFusion: cross-domain long-range learning for general image fusion via swin transformer[J]. IEEE/CAA Journal of Automatica Sinica, 2022, 9(7): 1200-1217.
[22] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer, 2015: 234-241.