文章详情

题名 · 作者 · 摘要 · 关键词 · DOI · 参考文献

基于改进YOLOv8n的轻量化工地堆放木材异常检测算法

王浩宇

(太原师范学院 计算机科学与技术学院,山西 晋中 030619)

栏目:人工智能 · 第 2025 年第 7 期 · 页码:58-63,70 · 2096-4706(2025)07-0058-07 · 中图分类号:TP183;TP391 · 文献标识码:A · DOI:10.19850/j.cnki.2096-4706.2025.07.011

摘要

在工地堆放木材物料时,室外环境容易导致木材表面出现受潮变形、干裂等异常状况。针对现有检测算法在木材物料表面异常检测方面精度欠佳、模型计算复杂度高等问题,提出一种以YOLOv8n为基础模型的轻量级小目标检测算法(YOLO-ESN)。该算法引入空间-通道重构卷积(SCConv)模块以及针对小目标检测的归一化Wasserstein距离(NWD)损失函数,同时将基于跨空间学习的高效多尺度注意力模块(EMA)嵌入主干网络,以此减轻遮挡及背景干扰带来的影响。改进后的算法在木材缺陷数据集上进行了实验验证,相较于原算法,其mAP@0.5提升了3.6%,参数量降低了23.3%,实现了对堆放木材物料异常情况的实时准确检测。

关键词

改进YOLOv8n算法;工地木材异常检测;轻量化;小目标检测

参考文献

  1. [1] 冯利军.建筑安全事故成因分析及预警管理研究 [D].天津:天津财经大学,2008.
  2. [2] 裴文博,王水亮.建筑工地常见的安全隐患问题原因分析及对策建议 [J].建筑安全,2020,35(10):52-55.
  3. [3] QAYYUM R,KAMAL K,ZAFAR T,et al. Wood Defects Classification Using GLCM Based Features and PSO Trained Neural Network [C]//2016 22nd International Conference on Automation and Computing (ICAC).Colchester:IEEE,2016:273-277.
  4. [4] AGRAWAL P,GIRSHICK R,MALIK J. Analyzing the Performance of Multilayer Neural Networks for Object Recognition [C]//Computer Vision-ECCV 2014.Zurich:Springer,2014:329-344.
  5. [5] GIRSHICK R. Fast R-CNN [C]//2015 IEEE International Conference on Computer Vision (ICCV).Santiago:IEEE,2015:1440-1448.
  6. [6] REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [C]//IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(6):1137-1149.
  7. [7] REDMON J,DIVVALA S,GIRSHICK R,et al. You Only Look Once: Unified, Real-Time Object Detection [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas:IEEE,2016:779-788.
  8. [8] LIU W,ANGUELOV D,ERHAN D,et al. SSD: Single Shot MultiBox Detector [C]//Computer Vision-ECCV 2016.Amsterdam:Springer,2016:21-37.
  9. [9] SERMANET P,EIGEN D,ZHANG X,et al. OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks [J/OL]. arXiv:1312.6229 [cs.CV].[2024-10-16].https://doi.org/10.48550/arXiv.1312.6229.
  10. [10] 陈俊宇.探究智慧工地在建筑工程安全管理和质量管理中的应用 [J].产品可靠性报告,2023(8):45-46.
  11. [11] 韩强.面向小目标检测的改进YOLOv8算法研究 [D].长春:吉林大学,2023.
  12. [12] OUYANG D L,HE S,ZHANG G Z,et al. Efficient Multi-Scale Attention Module with Cross-Spatial Learning [C]//CASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).Rhodes Island:IEEE,2023:1-5.
  13. [13] WANG J W,XU C,YANG W,et al. A Normalized Gaussian Wasserstein Distance for Tiny Object Detection [J/OL].arXiv:2110.13389 [cs.CV].[2024-10-23].https://doi.org/10.48550/arXiv.2110.13389.
  14. [14] LI J F,WEN Y,HE L H,et al. SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy [C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Vancouver:IEEE,2023:6153-6162.
  15. [15] CHEN Y P,DAI X Y,LIU M C,et al. Dynamic Convolution: Attention Over Convolution Kernels [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle:IEEE,2020:11027-11036.
  16. [16] HU J,SHEN L,SUN G. Squeeze-and-Excitation Networks [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:7132-7141.
  17. [17] WOO S,PARK J,LEE J Y,et al. CBAM: Convolutional Block Attention Module [J/OL].arXiv:1807.06521 [cs.CV].[2024-09-28].https://doi.org/10.48550/arXiv.1807.06521.
  18. [18] IANDOLA F N,HAN S,MOSKEWICZ M W,et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and<0.5 MB model size [J/OL].arXiv:1602.07360 [cs.CV].[2024-09-12].https://doi.org/10.48550/arXiv.1602.07360.
  19. [19] HOWARD A G,ZHU M L,CHEN B,et al. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications [J/OL].arXiv:1704.04861 [cs.CV].[2024-09-10].https://doi.org/10.48550/arXiv.1704.04861.

作者简介

王浩宇(1996—),男,汉族,山西长治人,硕士研究生在读,研究方向:图像处理。