EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wood Veneer Defect Detection Based on Multiscale DETR with Position Encoder Net

Yilin Ge, Dapeng Jiang, Liping Sun

Sensors · 17.05.2023 · 23 (10) · 4837

DOI: 10.3390/s23104837 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.05.2023. Verfasst von Yilin Ge und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Control Engineering, Northeast Forestry University, No. 26 Hexing Road, Harbin 150040, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Fundamental Research Funds for the Central Universities, Heilongjiang Provincial Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Wood is one of the main building materials. However, defects on veneers result in substantial waste of wood resources. Traditional veneer defect detection relies on manual experience or photoelectric-based methods, which are either subjective and inefficient or need substantial investment. Computer vision-based object detection methods have been used in many realistic areas. This paper proposes a new deep learning defect detection pipeline. First, an image collection device is constructed and a total of more than 16,380 defect images are collected coupled with a mixed data augmentation method. Then, a detection pipeline is designed based on DEtection TRansformer (DETR). The original DETR needs position encoding functions to be designed and is ineffective for small object detection. To solve these problems, a position encoding net is designed with multiscale feature maps. The loss function is also redefined for much more stable training. The results from the defect dataset show that using a light feature mapping network, the proposed method is much faster with similar accuracy. Using a complex feature mapping network, the proposed method is much more accurate with similar speed.

Schlagwörter

Stichwörter der Autor:innen

convolutional neural networksdefect detectiontransformerwood veneer

Autor:innen und Institutionen

  • College of Computer and Control Engineering, Northeast Forestry University, No. 26 Hexing Road, Harbin 150040, China.

Förderung

  • The Fundamental Research Funds for the Central Universities
  • Heilongjiang Provincial Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Ge, Y., Jiang, D., & Sun, L. (2023). Wood Veneer Defect Detection Based on Multiscale DETR with Position Encoder Net. Sensors, 23(10), 4837. https://doi.org/10.3390/s23104837

Vancouver

Ge Y, Jiang D, Sun L. Wood Veneer Defect Detection Based on Multiscale DETR with Position Encoder Net. Sensors. 2023;23(10):4837. doi:10.3390/s23104837

BibTeX
@article{Ge2023,
  author = {Ge, Yilin and Jiang, Dapeng and Sun, Liping},
  title = {Wood Veneer Defect Detection Based on Multiscale DETR with Position Encoder Net},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {10},
  pages = {4837},
  doi = {10.3390/s23104837}
}
Kostenlos starten →