LGM-YOLOv11：融合多尺度注意力机制的水下目标检测模型

doi:10.3778/j.issn.1002-8331.2506-0362

摘要/Abstract

摘要： 水下图像在海洋生态环境监测、水下资源开发等应用中发挥着重要作用。然而，水下图像通常受到光散射、悬浮颗粒和颜色衰减等因素影响，导致图像呈现低对比度、边缘模糊和噪声干扰等特征，进而降低了水下目标检测的准确性和效率。针对这些挑战，提出了一种融合多尺度注意力机制的水下目标检测模型以提升水下环境物体的检测性能。引入拉普拉斯-高斯主干模块（LoGStem），代替YOLOv11主干网络的前两层卷积，增强了对水下图像的边缘和纹理细节的提取能力。提出门控激活卷积模块（GSConv）嵌入特征金字塔网络中，利用门控机制为每个空间位置和通道启用动态特征，增强了模型捕捉细节能力；提出了多尺度增强并行注意力模块（MSEPA），并将其集成到C3k2中，再通过多尺度特征融合和多重注意力机制的协同作用，从而增大感受野并增强特征表示；为了提高小目标定位的精度和稳定性，使用了Shape-NWD损失函数。在UTDAC、DUO、RUOD和水下垃圾数据集上的实验表明，所提出的方法相较于对比模型达到了最佳检测精度。

关键词: 水下目标检测, 多尺度注意力, YOLOv11, Shape-NWD

Abstract: Underwater images play a crucial role in applications such as marine ecological environment monitoring and underwater resource development. However, underwater images are often affected by factors such as light scattering, suspended particles, and color attenuation, resulting in low contrast, blurred edges, and noise interference, which in turn reduces the accuracy and efficiency of underwater target detection. To address these challenges, a waterborne target detection model integrating a multi-scale attention mechanism is proposed to enhance the detection performance of underwater objects. Firstly, the Laplacian-of-Gaussian stem (LoGStem) is introduced to replace the first two convolutional layers of the YOLOv11 backbone network, enhancing the extraction ability of edge and texture details in underwater images. Secondly, the gated activation convolution module (GSConv) is proposed and embedded in the feature pyramid network, using the gating mechanism to enable dynamic features for each spatial position and channel, thereby enhancing the model’s ability to capture details. Then, the multi-scale enhanced parallel attention module (MSEPA) is proposed and integrated into C3k2, and through the collaborative effect of multi-scale feature fusion and multiple attention mechanisms, the receptive field is enlarged and the feature representation is enhanced. Finally, to improve the accuracy and stability of small target localization, the Shape-NWD loss function is used. Experiments on the UTDAC, DUO, RUOD and underwater garbage datasets show that the proposed method achieves the best detection accuracy compared with the contrast models.

Key words: underwater object detection, multi-scale attention, YOLOv11, Shape-NWD

陈辉, 虞永杰. LGM-YOLOv11：融合多尺度注意力机制的水下目标检测模型[J]. 计算机工程与应用, 2025, 61(23): 248-263.

CHEN Hui, YU Yongjie. LGM-YOLOv11: Underwater Object Detection Model Fusing Multi-Scale Attention Mechanism[J]. Computer Engineering and Applications, 2025, 61(23): 248-263.

参考文献

[1] BENISTO L C L, SUKUMARAN R, SARAVANAN M. Architecture, localization techniques, routing protocols and challenges for UWNS[C]//Proceedings of the International Conference on Data Science and Network Security. Piscataway: IEEE, 2023: 1-7.
[2] LIN C, HAN G J, JIANG J F, et al. Underwater pollution tracking based on software-defined multi-tier edge computing in 6G-based underwater wireless networks[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(2): 491-503.
[3] MILLER K A, THOMPSON K F, JOHNSTON P, et al. An overview of seabed mining including the current state of development, environmental impacts, and knowledge gaps[J]. Frontiers in Marine Science, 2018, 4: 418.
[4] NOMIKOS N, GKONIS P K, BITHAS P S, et al. A survey on UAV-aided maritime communications:deployment considerations, applications, and future challenges[J]. IEEE Open Journal of the Communications Society, 2023, 4: 56-78.
[5] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587.
[6] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440-1448.
[7] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[8] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of the European Conference on Computer Vision. Cham: Springer International Publishing, 2016: 21-37.
[9] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788.
[10] FENG J F, JIN T. CEH-YOLO: a composite enhanced YOLO-based model for underwater object detection[J]. Ecological Informatics, 2024, 82: 102758.
[11] LI X, ZHAO Y, SU H, et al. Efficient underwater object detection based on feature enhancement and attention detection head[J]. Scientific Reports, 2025, 15(1): 5973.
[12] CHEN R L, ZHOU H B, XIE H, et al. YOLO-CE: an underwater low-visibility environment target detection algorithm based on YOLO11[J]. The Journal of Supercomputing, 2025, 81(5): 723.
[13] 梁秀满, 李然, 于海峰, 等. 改进YOLOv7的水下目标检测算法[J]. 计算机工程与应用, 2024, 60(6): 89-99.
LIANG X M, LI R, YU H F, et al. Improved underwater object detection algorithm of YOLOv7[J]. Computer Engineering and Applications, 2024, 60(6): 89-99.
[14] 陶洋朱腾, 钟邦乾. RepViTS-YOLOX: 水下模糊及遮挡目标检测方法[J]. 计算机工程与应用, 2024, 60(13): 200-208.
TAO Y Z T, ZHONG B Q. RepViTS-YOLOX: underwater blurred and occluded target detection method[J]. Computer Engineering and Applications, 2024, 60(13): 200-208.
[15] ER M J, CHEN J, ZHANG Y, et al. Research challenges, recent advances, and popular datasets in deep learning-based underwater marine object detection: a review[J]. Sensors (Basel), 2023, 23(4): 1990.
[16] LU W, CHEN S B, LI H D, et al. LEGNet: lightweight edge-Gaussian driven network for low-quality remote sensing image object detection[J]. arXiv:2503.14012, 2025.
[17] ZHANG H, ZHANG S. Shape-IoU: more accurate metric considering bounding box shape and scale[J]. arXiv:2312.
17663, 2023.
[18] WANG J, XU C, YANG W, et al. A normalized Gaussian Wasserstein distance for tiny object detection[J]. arXiv:2110.
13389, 2021.
[19] LU W, CHEN S B, TANG J, et al. A robust feature downsampling module for remote-sensing visual tasks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-12.
[20] LIANG X T, SONG P H. Excavating RoI attention for underwater object detection[C]//Proceedings of the IEEE International Conference on Image Processing. Piscataway: IEEE, 2022: 2651-2655.
[21] LI S Y, KE L, DANELLJAN M, et al. Matching anything by segmenting anything[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 18963-18973.
[22] 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 IEEE International Conference on Multimedia and Expo. Piscataway: IEEE, 2024: 1-6.
[23] LU W, CHEN S B, DING C H Q, et al. LWGANet: a lightweight group attention backbone for remote sensing visual tasks[J]. arXiv:2501.10040, 2025.
[24] ZHANG M J, ZHANG C, ZHANG Q M, et al. ESSAformer: efficient Transformer for hyperspectral image super-resolution[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2023: 23016-23027.
[25] XI D J, QIN Y, WANG S J. YDRSNet: an integrated YOLOv5-Deeplabv3+real-time segmentation network for gear pitting measurement[J]. Journal of Intelligent Manufacturing, 2023, 34(4): 1585-1599.
[26] HUSSAIN M. YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection[J]. Machines, 2023, 11(7): 677.
[27] WANG A, CHEN H, LIU L, et al. YOLOv10: real-time end-to-end object detection[C]//Advances in Neural Information Processing Systems, 2024: 107984-108011.
[28] KHANAM R, HUSSAIN M. YOLOv11: an overview of the key architectural enhancements[J]. arXiv:2410.17725, 2024.
[29] TIAN Y, YE Q, DOERMANN D. YOLOv12: attention-centric real-time object detectors[J]. arXiv:2502.12524, 2025.
[30] LEI M, LI S, WU Y, et al. YOLOv13: real-time object detection with hypergraph-enhanced adaptive visual perception[J]. arXiv:2506.17733, 2025.
[31] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 2999-3007.
[32] CAI Z W, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 6154-6162.
[33] ZHANG H Y, WANG Y, DAYOUB F, et al. VarifocalNet: an IoU-aware dense object detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 8510-8519.
[34] DAI L H, LIU H, SONG P H, et al. Edge-guided representation learning for underwater object detection[J]. CAAI Transactions on Intelligence Technology, 2024, 9(5): 1078-1091.
[35] QIAO S Y, CHEN L C, YUILLE A. DetectoRS: detecting objects with recursive feature pyramid and switchable atrous convolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 10208-10219.
[36] WANG C, HE W, NIE Y, et al. Gold-YOLO: efficient object detector via gather-and-distribute mechanism[C]//Advances in Neural Information Processing Systems, 2023: 51094-51112.
[37] FENG Y, HUANG J, DU S, et al. Hyper-YOLO: when visual object detection meets hypergraph computation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025, 47(4): 2388-2401.
[38] WANG Z, LI C, XU H, et al. Mamba-YOLO: SSMs-based YOLO for object detection[J]. arXiv:2406.05835, 2024.
[39] XIAO Y, XU T F, XIN Y, et al. FBRT-YOLO: faster and better for real-time aerial image detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2025: 8673-8681.
[40] WANG Y, YE H, SHU X. BSE-YOLO: an enhanced lightweight multi-scale underwater object detection model[J]. Sensors (Basel), 2025, 25(13): 3890.
[41] LUO Y, WU A, FU Q. MAS-YOLOv11: an improved underwater object detection algorithm based on YOLOv11[J]. Sensors (Basel), 2025, 25(11): 3433.
[42] LUO S F, DONG C, DONG G X, et al. YOLO-DAFS: a composite-enhanced underwater object detection algorithm[J]. Journal of Marine Science and Engineering, 2025, 13(5): 947.
[43] LIU J X, ZHOU R G, LI Y C, et al. Enhanced underwater object detection with YOLO-LDFE: a model for improved accuracy with balanced efficiency[J]. Journal of Real-Time Image Processing, 2025, 22(2): 58.
[44] HUANG S H, LU Z C, CUN X D, et al. DEIM: detr with improved matching for fast convergence[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2025: 15162-15171.
[45] ZHAO Y A, LV W Y, XU S L, et al. DETRs beat YOLOs on real-time object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2024: 16965-16974.
[46] LIU F L, ZHENG Q H, TIAN X Y, et al. Rethinking the multi-scale feature hierarchy in object detection transformer (DETR)[J]. Applied Soft Computing, 2025, 175: 113081.
[47] LIU C W, LI H J, WANG S C, et al. A dataset and benchmark of underwater object detection for robot picking[C]//Proceedings of the IEEE International Conference on Multimedia & Expo Workshops. Piscataway: IEEE, 2021: 1-6.
[48] FU C P, LIU R S, FAN X, et al. Rethinking general underwater object detection: datasets, challenges, and solutions[J]. Neurocomputing, 2023, 517: 243-256.