边缘信息增强的轻量化红外小目标检测方法

doi:10.3778/j.issn.1002-8331.2501-0166

摘要/Abstract

摘要： 先验知识可以改善基于深度学习技术的红外小目标检测方法的性能。边缘信息是一种重要的先验知识，然而现有方法通常使用构造分支网络的方法将边缘信息加入网络模型中，在提升性能的同时造成了参数量和运算量的提升。针对此问题，提出了一种边缘信息增强的轻量化网络（edge information enhanced lightweight network，EIEL-Net），构造边缘信息增强（edge information enhancing，EIE）模块实现了边缘信息的高效嵌入。同时，构建了高效三向注意力（efficient triple-direction attention，ETDA）模块，从三个维度聚合红外小目标的全局信息，实现多维语义信息的有效融合。此外，为进一步提升骨干网对多样化特征的提取能力，提出了结构重参数化的非对称下采样（structural re-parameterized asymmetric downsampling，SRPAD）模块和高效通道注意力残差块（ECA-ResNeSt block）。EIEL-Net在参数量和浮点运算量分别为0.343×106和1.126×109的情况下，其检测速度可超过100?FPS，且在SIRST、NUDT-SIRST和IRSTD-1k三个公开数据集上的实验结果显示了该方法相比其他主流检测方法的优越性能，展示了该方法在低算力设备上部署的巨大潜力。

关键词: 红外小目标检测, 先验知识, 边缘检测, 三重注意力, 结构重参数化, 模型轻量化

Abstract: Prior knowledge can promote the performance of infrared small target detection methods based on deep learning technology. Edge information is an important type of prior knowledge, but existing methods usually incorporate edge information into the network model by constructing branch networks, which enhances performance but also increases the number of parameters and computational costs. To address this issue, an edge information enhanced lightweight network (EIEL-Net) is proposed, which incorporates an edge information enhancing (EIE) module to achieve efficient embedding of edge information. Meanwhile, an efficient triple-direction attention (ETDA) module is proposed to effectively aggregate global information of infrared small targets from three dimensions, achieving effective fusion of multi-dimensional semantic information. Furthermore, to further improve the backbone??s ability to extract diverse features, a structural re-parameterized asymmetric downsampling (SRPAD) module and an ECA-ResNeSt block are proposed. With 0.343×106 parameters and 1.126×109 FLOPs, EIEL-Net achieves a detection speed exceeding 100 FPS. Experimental results demonstrate that EIEL-Net outperforms existing state-of-the-art methods on the three public datasets SIRST, NUDT-SIRST and IRSTD-1k, highlighting its substantial potential for implementation on devices with limited computational resources.

Key words: infrared small target detection, prior knowledge, edge detection, triplet attention, structural re-parameterization, model lightweighting

王培超, 王家宝, 寇人可, 张睿, 李阳, 苗壮. 边缘信息增强的轻量化红外小目标检测方法[J]. 计算机工程与应用, 2026, 62(8): 255-269.

WANG Peichao, WANG Jiabao, KOU Renke, ZHANG Rui, LI Yang, MIAO Zhuang. Edge Information Enhanced Lightweight Network for Infrared Small Target Detection[J]. Computer Engineering and Applications, 2026, 62(8): 255-269.

参考文献

[1] 胡亮，杨德贵，赵党军，等.改进非凸估计与非对称时空正则化的红外小目标检测方法[J].国防科技大学学报，2024，46（3）：180-194.
HU L，YANG D G，ZHAO D J，et al.Infrared small target detection method based on improved non-convex estimation and asymmetric spatial-temporal regularization[J].Journal of National University of Defense Technology，2024，46（3）：180-194.
[2] KOU R K，WANG C P，PENG Z M，et al.Infrared small target segmentation networks：a survey[J].Pattern Recognition，2023，143：109788.
[3] 杨德贵，韩同欢，胡亮，等.单帧红外弱小目标检测技术研究现状与展望[J].信号处理，2024，40（5）：887-906.
YANG D G，HAN T H，HU L，et al.Research status and prospect of single frame infrared dim small target detection technology[J].Journal of Signal Processing，2024，40（5）：887-906.
[4] ZHAO M J，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.
[5] 董亚盼，高陈强，谌放，等.基于注意力机制的红外小目标检测方法[J].重庆邮电大学学报（自然科学版），2023，35（2）：219-226.
DONG Y P，GAO C Q，CHEN F，et al.Infrared small target detection method based on attention mechanism[J].Journal of Chongqing University of Posts and Telecommunications （Natural Science Edition），2023，35（2）：219-226.
[6] 林再平，罗伊杭，李博扬，等.基于梯度可感知通道注意力模块的红外小目标检测前去噪网络[J].红外与毫米波学报，2024，43（2）：254-260.
LIN Z P，LUO Y H，LI B Y，et al.Gradient-aware channel attention network for infrared small target image denoising before detection[J].Journal of Infrared and Millimeter Waves，2024，43（2）：254-260.
[7] CHEN Y H，LI L Y，LIU X，et al.A multi-task framework for infrared small target detection and segmentation[J].IEEE Transactions on Geoscience and Remote Sensing，2022，60：5003109.
[8] WANG K W，DU S Y，LIU C X，et al.Interior attention-aware network for infrared small target detection[J].IEEE Transactions on Geoscience and Remote Sensing，2022，60：5002013.
[9] ZHANG T F，LI L，CAO S Y，et al.Attention-guided pyramid context networks for detecting infrared small target under complex background[J].IEEE Transactions on Aerospace and Electronic Systems，2023，59（4）：4250-4261.
[10] 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.
[11] SUN H，BAI J X，YANG F，et al.Receptive-field and direction induced attention network for infrared dim small target detection with a large-scale dataset IRDST[J].IEEE Transactions on Geoscience and Remote Sensing，2023，61：5000513.
[12] ZHAO J M，SHI Z L，YU C，et al.Multi-scale direction-aware network for infrared small target detection[EB/OL].[2024-11-27].https：//arxiv.org/abs/2406.02037.
[13] ZHANG M J，ZHANG R，YANG Y X，et al.ISNet：shape matters for infrared small target detection[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2022：867-876.
[14] WANG C，HU X P，GAO X，et al.EEA-Net：edge-enhanced assistance network for infrared small target detection[J].Machine Vision and Applications，2024，35（4）：70.
[15] YAO R，LI W X，ZHOU Y，et al.Dual-stream edge-target learning network for infrared small target detection[J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：5007314.
[16] WANG H，ZHOU L P，WANG L.Miss detection vs.false alarm：adversarial learning for small object segmentation in infrared images[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision.Piscataway：IEEE，2020：8508-8517.
[17] LI B Y，XIAO C，WANG L G，et al.Dense nested attention network for infrared small target detection[J].IEEE Transactions on Image Processing，2023，32：1745-1758.
[18] HOU Q Y，ZHANG L W，TAN F J，et al.ISTDU-Net：infrared small?target detection U?Net[J].IEEE Geoscience and Remote Sensing Letters，2022，19：7506205.
[19] WU X，HONG D F，CHANUSSOT J.UIU-Net：U-Net in U-Net for infrared small object detection[J].IEEE Transactions on Image Processing，2023，32：364-376.
[20] DOSOVITSKIY A，BEYER L，KOLESNIKOV A，et al.An image is worth 16x16 words：transformers for image recognition at scale[EB/OL].[2024?11?30].https：//arxiv.org/abs/2010.11929.
[21] 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.
[22] YUAN S，QIN H L，YAN X，et al.SCTransNet：spatial-channel cross transformer network for infrared small target detection[J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：5002615.
[23] SHI Y K，LIN Y P，WEI P X，et al.Diff-mosaic：augmenting realistic representations in infrared small target detection via diffusion prior[J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：5004311.
[24] JIA G M，CHENG Y，CHEN T.IRGraphSeg：infrared small target detection based on hierarchical GNN[J].IEEE Geoscience and Remote Sensing Letters，2024，21：6005505.
[25] CHEN T X，YE Z，TAN Z T，et al.MiM-ISTD：mamba-in-mamba for efficient infrared small-target detection[J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：5007613.
[26] ZHANG M J，WANG Y C，GUO J，et al.IRSAM：advancing segment anything model forInfrared small target detection[C]//Proceedings of the 18th European Conference on Computer Vision.Cham：Springer，2025：233-249.
[27] NIAN B K，JIANG B，SHI H J，et al.Local contrast attention guide network for detecting infrared small targets[J].IEEE Transactions on Geoscience and Remote Sensing，2023，61：5607513.
[28] 肖扬，周军.图像边缘检测综述[J].计算机工程与应用，2023，59（5）：40-54.
XIAO Y，ZHOU J.Overview of image edge detection[J].Computer Engineering and Applications，2023，59（5）：40-54.
[29] MA X Y，LI Y.Edge-aided multiscale context network for infrared small target detection[J].IEEE Geoscience and Remote Sensing Letters，2023，20：7001405.
[30] LI Q，ZHANG M W，YANG Z G，et al.Edge-guided perceptual network for infrared small target detection[J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：5643510.
[31] WANG Q L，WU B G，ZHU P F，et al.ECA-Net：efficient channel attention for deep convolutional neural networks[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2020：11531-11539.
[32] MISRA D，NALAMADA T，ARASANIPALAI A U，et al.Rotate to attend：convolutional triplet attention module[C]//Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision.Piscataway：IEEE，2021：3138-3147.
[33] DING X H，GUO Y C，DING G G，et al.ACNet：strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision.Piscataway：IEEE，2020：1911-1920.
[34] DING X H，ZHANG X Y，MA N N，et al.RepVGG：making VGG-style ConvNets great again[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2021：13728-13737.
[35] LIU W Z，LU H，FU H T，et al.Learning to upsample by learning to sample[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision.Piscataway：IEEE，2024：6004-6014.
[36] WANG P C，WANG J B，CHEN Y，et al.Paying more attention to local contrast：improving infrared small target detection performance via prior knowledge[EB/OL].[2024?12-07].https：//arxiv.org/abs/2411.13260.
[37] ZHANG H，WU C R，ZHANG Z Y，et al.ResNeSt：split-attention networks[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops.Piscataway：IEEE，2022：2735-2745.
[38] HU J，SHEN L，ALBANIE S，et al.Squeeze-and-excitation networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2020，42（8）：2011-2023.
[39] XIE S N，GIRSHICK R，DOLLáR P，et al.Aggregated residual transformations for deep neural networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway：IEEE，2017：5987-5995.
[40] 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，2021：949-958.
[41] RAHMAN M A，WANG Y.Optimizing intersection-over-union in deep neural networks for image segmentation[C]//Proceedings of the 12th International Symposium on Advances in Visual Computing.Cham：Springer，2016：234-244.
[42] KINGMA D P，BA J.Adam：a method for stochastic optimization[C]//Proceedings of the 3rd International Conference on Learning Representations，2015.
[43] ZHANG M J，YUE K，ZHANG J，et al.Exploring feature compensation and cross-level correlation for infrared small target detection[C]//Proceedings of the 30th ACM International Conference on Multimedia.New York：ACM，2022：1857-1865.
[44] XU S B，ZHENG S C，XU W H，et al.HCF-Net：hierarchical context fusion network for infrared small object detection[C]//Proceedings of the 2024 IEEE International Conference on Multimedia and Expo.Piscataway：IEEE，2024：1-6.
[45] YU C，LIU Y P，ZHAO J M，et al.LR-net：a lightweight and robust network for infrared small target detection[EB/OL].[2024-12-22].https：//arxiv.org/abs/2408.02780.