基于YOLOv8-SPH的防震锤缺失检测
作者:
作者单位:

1.三峡大学机械与动力学院;2.三峡大学电气与新能源学院

基金项目:


Detection of Missing Shockproof Hammers Based on YOLOv8-SPH
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [25]
  • | | | |
  • 文章评论
    摘要:

    针对输电线路中防震锤尺寸小,图像背景复杂,防震锤缺失难以检测的问题,提出一种轻量化YOLOv8-SPH的防震锤缺失检测模型。通过在YOLOv8n网络的颈部引入160×160和320×320的浅层尺度特征图,并在检测头中融入相应尺度的目标检测模块,提升了特征图之间的上下文信息融合能力,有效扩大了模型的感受野,使得模型能够捕捉到更多防震锤缺失的特征语义信息。还创新性地提出了多尺度高效特征提取模块(MultFaster),通过部分卷积、多级特征提取和残差连接机制,在保持防震锤特征检测精度的同时,减少网络的计算量和参数量。此外,在颈部网络中引入动态上采样算子,提高重建特征图的分辨率,提高了该模型对防震锤缺失检测的精度,同时,将原模型解耦式检测头更换为轻量化检测头,降低了模型计算的复杂度并提升检测效率。最后对改进后的网络进行基于幅值的层自适应稀疏化剪枝,进一步减小模型参数及计算量。在针对自制防震锤缺失数据集的测试中,YOLOv8-SPH表现卓越,其mAP@0.5达到了91.51%,相比原始YOLOv8n提高了6.3%,参数量减少了80.73%,计算量减少了48.14%,模型尺寸减少了62.41%。该模型在计算量和参数量降低的同时,提高了检测精度,充分满足了对输电线路中的防震锤进行高效和准确检测的需求,具有实用性。

    Abstract:

    To address challenges in detecting missing Shockproof Hammers on transmission lines due to their small size, complex image backgrounds, and subtle presence, this study proposes a lightweight YOLOv8-SPH model for damper absence detection. The model introduces shallow-scale feature maps of 160×160 and 320×320 within the neck of the YOLOv8n network and integrates multi-scale detection modules within the detection head. This enhances contextual information fusion across feature maps, effectively expanding the receptive field, enabling the model to capture richer semantic features related to damper absence.An innovative multi-scale high-efficiency feature extraction module (MultFaster) is also introduced, utilizing partial convolutions, multi-level feature extraction, and residual connections. This structure maintains detection accuracy for damper features while reducing computational complexity and parameter load. Additionally, a dynamic upsampling operator is incorporated into the neck network to improve feature map resolution, improving the model's accuracy in detecting missing Shockproof Hammers. To further optimize, the original model’s decoupled detection head is replaced with a lightweight detection head, reducing computational complexity and boosting detection efficiency.The enhanced network undergoes amplitude-based layer-adaptive sparse pruning, significantly reducing model parameters and computational load. Testing on a custom damper absence dataset demonstrates YOLOv8-SPH exhibited remarkable performance, achieving an mAP@0.5 of 91.51%, which marks a 6.3% improvement over the original YOLOv8n. Additionally, parameter count is reduced by 80.73%, computational load by 48.14%, and model size by 62.41%. The model achieves improved detection accuracy while reducing computational complexity and parameter size, effectively meeting the demands for efficient and precise detection of Shockproof Hammers in transmission lines, showcasing significant practical value.

    参考文献
    [1] 赵海洋,林来鑫,仝鑫,等.金具滑移对输电线路的危害分析与防治[J].自动化应用,2024,65(10):148-150+153.
    [2] Yong J Z ,Ke Y ,Zhen Y Z ,et al. Geometric characteristic learning R-CNN for shockproof hammer defect detection[J].Engineering Applications of Artificial Intelligence,2022,116.
    [3] Zhi Q X ,Fan G ,Li H W , et al. Simulation analysis on vibration characteristics of 220kV vertically arranged double bundled conductors[J].Journal of Physics: Conference Series,2021,1871(1):
    [4] 董武,张健,周勤勇,等.中国电力系统安全稳定性演化综述[J/OL].中国电力,1-12[2024-06-26].
    [5] Fahmani L ,Benhadou S .Optimizing 2D path planning for unmanned aerial vehicle inspection of electric transmission lines[J].Scientific African,2024,24e02203-.
    [6] Wang Y ,Wang H ,Liu Y , et al.6-DOF UAV Path planning and tracking control for obstacle avoidance: a deep learning-based integrated approach[J].Aerospace Science and Technology,2024,151109320-109320.
    [7] 王宏霞,卫洁,杜明俐.为电网装上“慧眼”[N].中国电力报,2024-06-25(003).
    [8] 周景,李鑫乐.基于改进型DETR的输电线路防震锤检测[J].计算机仿真,2023,40(11):101-106.
    [9] 梁华刚,赵慧霞,刘丽华,等.结合跨层特征融合与级联检测器的防震锤缺陷检测[J].中国图象图形学报,2023,28(11):3485-3496.
    [10] 高伟,董云云,刘军,等.融合注意力机制的输电部件及缺陷检测模型[J].计算机工程与设计,2023,44(03):929-936.
    [11] 陈思雨,付章杰.融合高效注意力的多尺度输电线路部件检测[J].计算机工程与应用,2024,60(01):327-336.
    [12] 裘瑾怡,任新新,陈希.基于卷积神经网络的输电线路金具缺陷检测方法[J].自动化与信息工程,2022,43(04):36-41+47.
    [13] Dong C ,Zhang K ,Xie Z ,et al. An improved cascade RCNN detection method for key components and defects of transmission lines[J].IET Generation, Transmission & Distribution,2023,17(19):4277-4292.
    [14] 宋立业,刘帅,王凯,等.基于改进EfficientDet的电网元件及缺陷识别方法[J].电工技术学报,2022,37(09):2241-2251.
    [15] Yang Z,Xu X F and Wang K K ,et al. Multitarget Detection of Transmission Lines Based on DANet and YOLOv4[J]. Scientific Programming.2021.
    [16] 吴志成,林秀贵,许家浩,等.一种采用航拍图像识别高压输电线路防震锤缺失的检测算法[J].应用科技,2021,48(05):35-41+53.
    [17] 吴志成,林秀贵,许家浩,等.一种采用航拍图像识别高压输电线路防震锤缺失的检测算法[J].应用科技,2021,48(05):35-41+53.
    [18] Guo J, Xie J,Yuan J,Jiang Y and Lu S.Fault Identification of Transmission Line Shockproof Hammer Based on Improved YOLO V4.2021 International Conference on Intelligent Computing, Automation and Applications (ICAA), Nanjing, China, 2021, pp. 826-833.
    [19] Liu W, Lu H, Fu H, et al. Learning to Upsample by Learning to Sample[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2023: 6027-6037.
    [20] Chen J. et al.Run, Don''t Walk: Chasing Higher FLOPS for Faster Neural Networks.2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 2023, pp. 12021-12031.
    [21] LEE J H, PARK S, MO S, et al. Layer-adaptive sparsity for the Magnitude-based Pruning[J]. arXiv: Learning,arXiv: Learning, 2020.
    [22] S. Ren, K. He, R. Girshick and J. Sun.Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 1 June 2017.
    [23] K. He, G. Gkioxari, P. Dollár and R. Girshick. Mask R-CNN.2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2980-2988.
    [24] Wang, Chien-Yao et al.YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. ArXiv abs/2402.13616 (2024): n. pag.
    [25] C. -Y. Wang, A. Bochkovskiy and H. -Y. M. Liao.YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors.2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 2023, pp. 7464-7475.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文
分享
文章指标
  • 点击次数:12
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2024-07-16
  • 最后修改日期:2024-12-05
  • 录用日期:2024-12-09
文章二维码