Open Access iconOpen Access

ARTICLE

crossmark

Contamination Identification of Lentinula Edodes Logs Based on Improved YOLOv5s

Xuefei Chen1, Wenhui Tan2, Qiulan Wu1,*, Feng Zhang1, Xiumei Guo1, Zixin Zhu1

1 School of Information Science & Engineering, Shandong Agricultural University, Tai’an, 271018, China
2 Department of Regulations, Tai’an Service Center for Urban Comprehensive Management, Tai’an, 271018, China

* Corresponding Author: Qiulan Wu. Email: email

Intelligent Automation & Soft Computing 2023, 37(3), 3143-3157. https://doi.org/10.32604/iasc.2023.040903

Abstract

In order to improve the accuracy and efficiency of Lentinula edodes logs contamination identification, an improved YOLOv5s contamination identification model for Lentinula edodes logs (YOLOv5s-CGGS) is proposed in this paper. Firstly, a CA (coordinate attention) mechanism is introduced in the feature extraction network of YOLOv5s to improve the identifiability of Lentinula edodes logs contamination and the accuracy of target localization. Then, the CIoU (Complete-IOU) loss function is replaced by an SIoU (SCYLLA-IoU) loss function to improve the model’s convergence speed and inference accuracy. Finally, the GSConv and GhostConv modules are used to improve and optimize the feature fusion network to improve identification efficiency. The method in this paper achieves values of 97.83%, 97.20%, and 98.20% in precision, recall, and mAP@0.5, which are 2.33%, 3.0%, and 1.5% better than YOLOv5s, respectively. mAP@0.5 is better than YOLOv4, Ghost-YOLOv4, and Mobilenetv3-YOLOv4 (improved by 4.61%, 5.16%, and 6.04%, respectively), and the FPS increased by two to three times.

Keywords


Cite This Article

APA Style
Chen, X., Tan, W., Wu, Q., Zhang, F., Guo, X. et al. (2023). Contamination identification of lentinula edodes logs based on improved yolov5s. Intelligent Automation & Soft Computing, 37(3), 3143-3157. https://doi.org/10.32604/iasc.2023.040903
Vancouver Style
Chen X, Tan W, Wu Q, Zhang F, Guo X, Zhu Z. Contamination identification of lentinula edodes logs based on improved yolov5s. Intell Automat Soft Comput . 2023;37(3):3143-3157 https://doi.org/10.32604/iasc.2023.040903
IEEE Style
X. Chen, W. Tan, Q. Wu, F. Zhang, X. Guo, and Z. Zhu "Contamination Identification of Lentinula Edodes Logs Based on Improved YOLOv5s," Intell. Automat. Soft Comput. , vol. 37, no. 3, pp. 3143-3157. 2023. https://doi.org/10.32604/iasc.2023.040903



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 515

    View

  • 254

    Download

  • 1

    Like

Share Link