EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Novel Method for Filled/Unfilled Grain Classification Based on Structured Light Imaging and Improved PointNet++

Shihao Huang, Zhihao Lu, Yuxuan Shi, Jiale Dong, Lin Hu, Wanneng Yang iD, Chenglong Huang iD

Sensors · 12.07.2023 · 23 (14) · 6331

DOI: 10.3390/s23146331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.07.2023. Verfasst von Shihao Huang und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Engineering, Huazhong Agricultural University, Wuhan 430070, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Key Research and Development Plan of Hubei Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

China is the largest producer and consumer of rice, and the classification of filled/unfilled rice grains is of great significance for rice breeding and genetic analysis. The traditional method for filled/unfilled rice grain identification was generally manual, which had the disadvantages of low efficiency, poor repeatability, and low precision. In this study, we have proposed a novel method for filled/unfilled grain classification based on structured light imaging and Improved PointNet++. Firstly, the 3D point cloud data of rice grains were obtained by structured light imaging. And then the specified processing algorithms were developed for the single grain segmentation, and data enhancement with normal vector. Finally, the PointNet++ network was improved by adding an additional Set Abstraction layer and combining the maximum pooling of normal vectors to realize filled/unfilled rice grain point cloud classification. To verify the model performance, the Improved PointNet++ was compared with six machine learning methods, PointNet and PointConv. The results showed that the optimal machine learning model is XGboost, with a classification accuracy of 91.99%, while the classification accuracy of Improved PointNet++ was 98.50% outperforming the PointNet 93.75% and PointConv 92.25%. In conclusion, this study has demonstrated a novel and effective method for filled/unfilled grain recognition.

Schlagwörter

Stichwörter der Autor:innen

3D structured lightdata enhancementdeep learninggrain classificationnormal vectorpoint cloud segmentation

Autor:innen und Institutionen

  • College of Engineering, Huazhong Agricultural University, Wuhan 430070, China.
  • Shenzhen Institute of Nutrition and Health, Huazhong Agricultural University, Wuhan 430070, China.
  • Shenzhen Branch, Guangdong Laboratory for Lingnan Modern Agriculture, Genome Analysis Laboratory of the Ministry of Agriculture, Agricultural Genomics Institute at Shenzhen, Chinese Academy of Agricultural Sciences, She…
  • National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research (Wuhan), Huazhong Agricultural University, Wuhan 430070, China.

ORCID-Profile: Wanneng Yang, Chenglong Huang

Förderung

  • National Natural Science Foundation of China
  • National Key R&D Program of China
  • Key Research and Development Plan of Hubei Province
  • the Fundamental Research Funds for the Central Universities
  • HZAU-AGIS Cooperation Fund
  • National Key R&D Program of China

Zitieren

APA

Huang, S., Lu, Z., Shi, Y., Dong, J., Hu, L., Yang, W., & Huang, C. (2023). A Novel Method for Filled/Unfilled Grain Classification Based on Structured Light Imaging and Improved PointNet++. Sensors, 23(14), 6331. https://doi.org/10.3390/s23146331

Vancouver

Huang S, Lu Z, Shi Y, Dong J, Hu L, Yang W, et al. A Novel Method for Filled/Unfilled Grain Classification Based on Structured Light Imaging and Improved PointNet++. Sensors. 2023;23(14):6331. doi:10.3390/s23146331

BibTeX
@article{Huang2023,
  author = {Huang, Shihao and Lu, Zhihao and Shi, Yuxuan and Dong, Jiale and Hu, Lin and Yang, Wanneng and Huang, Chenglong},
  title = {A Novel Method for Filled/Unfilled Grain Classification Based on Structured Light Imaging and Improved PointNet++},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {14},
  pages = {6331},
  doi = {10.3390/s23146331}
}
Kostenlos starten →