基于改进的YOLOv5s刨花板表面小目标缺陷检测算法

doi:10.3778/j.issn.1002-8331.2305-0475

摘要/Abstract

摘要： 针对目前刨花板缺陷检测在小目标检测上精度不佳的问题，提出了一种改进的YOLOv5s刨花板表面小缺陷检测算法YOLOv5s-ATG。对刨花板缺陷存在小目标及尺度变化较大缺陷的问题，将原有检测头与自适应空间特征融合网络（ASFF）相结合，以获得更好的特征融合，提高尺度变化较大情况下小目标检测的精度；在主干网络中引入Transformer模块，利用多头自注意力机制捕获全局空间关系，提升网络的特征提取能力；考虑到平衡模型精度和复杂度，在网络的主干和颈部加入Ghostv2模块，去提升算法的实时性。实验结果表明，改进的算法在实际刨花板缺陷数据集上平均精度（mAP）能够达到0.901，与原始YOLOv5s算法相比，mAP提高了0.046；而对于小目标缺陷类型胶斑，mAP提高了0.138。

关键词: 刨花板表面缺陷检测, YOLOv5s, 深度学习, 小目标检测, 特征融合

Abstract: An improved algorithm YOLOv5s-ATG for defecting particle board defects, based on YOLOv5s, is proposed to address the problem of poor precision in small target detection of particle board defect detection at present. To overcome the issue of particle board defects with small targets and large-scale changes, the original detector head is combined with the adaptive spatial feature fusion (ASFF) network to obtain better feature fusion. Transformer module is introduced into the backbone network, which uses a multi head self-attention mechanism to capture global spatial relationships and enhance the feature extraction capability of the network. For balancing the accuracy and complexity of the model, the Ghostv2 module is added to the backbone and neck of the network to improve the real-time performance of the algorithm. The experimental results show that the mean average precision (mAP) of the improved algorithm in the actual particle board defect data set can reach 0.901, which is 0.046 higher than the original model; for small target defect Gluespots, mAP is increased by 0.138.

Key words: particle board surface defect detection, YOLOv5s, deep learning, small target detection, feature fusion

查健, 陈先中, 王文财, 关淯尹, 张洁. 基于改进的YOLOv5s刨花板表面小目标缺陷检测算法[J]. 计算机工程与应用, 2024, 60(17): 158-166.

ZHA Jian, CHEN Xianzhong, WANG Wencai, GUAN Yuyin, ZHANG Jie. Small Defect Detection Algorithm of Particle Board Surface Based on Improved YOLOv5s[J]. Computer Engineering and Applications, 2024, 60(17): 158-166.

参考文献

[1] 郭慧. 基于机器视觉的刨花板表面缺陷在线检测系统研究[D]. 北京: 中国林业科学研究院, 2019.
GUO H. Study on on-line detection system for surface defects of particleboard based on machine vision[D]. Beijing: Chinese Academy of Forestry, 2019.
[2] 郭慧, 盛振湘, 王霄, 等. 基于机器视觉的刨花板表面缺陷检测系统[J]. 木材工业, 2019, 33(3): 18-22.
GUO H, SHENG Z X, WANG X, et al. A system based on machine vision for detecting surface defects of particleboard[J]. China Wood Industry, 2019, 33(3): 18-22.
[3] 杨锋, 丁之桐, 邢蒙蒙, 等. 深度学习的目标检测算法改进综述[J]. 计算机工程与应用, 2023, 59(11): 1-15.
YANG F, DING Z T, XING M M, et al. Review of object detection algorithm improvement in deep learning[J]. Computer Engineering and Applications, 2023, 59(11): 1-15.
[4] 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, 2014: 580-587.
[5] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[6] REN S, HE K, 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, 2015, 39(6): 1137-1149.
[7] 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, 2016: 779-788.
[8] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
[9] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[10] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[11] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[J]. arXiv:1512.02325, 2015.
[12] 彭煜, 肖书浩, 阮金华, 等. 基于Faster R-CNN 的刨花板表面缺陷检测研究[J]. 组合机床与自动化加工技术, 2020 (3): 91-94.
PENG Y, XIAO S H, RUAN J H, et al. Research on surface defect detection of particleboard based on Faster R-CNN[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2020(3): 91-94.
[13] ZHAO Z, GE Z, JIA M, et al. A particleboard surface defect detection method research based on the deep learning algorithm[J]. Sensors, 2022, 22(20): 7733.
[14] LI B, XU Z, BIAN E K, et al. Particleboard surface defect inspection based on data augmentation and attention mechanisms[C]//Proceedings of the 2022 27th International Conference on Automation and Computing, 2022: 1-6.
[15] ZHAO Z, YANG X, ZHOU Y, et al. Real-time detection of particleboard surface defects based on improved YOLOV5 target detection[J]. Scientific Reports, 2021, 11(1): 21777.
[16] 李科岑, 王晓强, 林浩, 等. 深度学习中的单阶段小目标检测方法综述[J]. 计算机科学与探索, 2022, 16(1): 41-58.
LI K C, WANG X Q, LIN H, et al. Survey of one-stage small object detection methods in deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(1): 41-58.
[17] LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8759-8768.
[18] FENG J, YI C. Lightweight detection network for arbitrary-oriented vehicles in UAV imagery via global attentive relation and multi-path fusion[J]. Drones, 2022, 6(5): 108.
[19] LIU S, HUANG D, WANG Y. Learning spatial fusion for single-shot object detection[J]. arXiv:1911.09516, 2019.
[20] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
[21] TANG Y, HAN K, GUO J, et al. GhostNetV2: enhance cheap operation with long-range attention[J]. arXiv:2211.
12905, 2022.
[22] HAN K, WANG Y, TIAN Q, et al. GhostNET: more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1580-1589.
[23] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J]. arXiv:2207.02696, 2022.