EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Grapevine Branch Recognition and Pruning Point Localization Technology Based on Image Processing

Zhangnan Chen, Yaxiong Wang, Siyuan Tong, Chongchong Chen, Feng Kang

Applied Sciences · 15.04.2024 · 14 (8) · 3327

DOI: 10.3390/app14083327 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 15.04.2024. Verfasst von Zhangnan Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ningxia Hui Autonomous Region key research and development plan project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The identification of branches and bud points is the key to intelligent pruning of dormant grapevine branches and precise positioning of the pruning point on the branch is an important prerequisite for robotic arm pruning. This study takes Cabernet Sauvignon wine grapes as the experimental object and proposes a depth image-based pruning point localization algorithm based on pruning rules. In order to solve the problem of bud recognition in complex backgrounds, this study adopts a detection method that combines semantic segmentation and target detection. Firstly, the semantic segmentation algorithm PSP-net is used to separate the branches and the main stem from the background and the separated image undergoes two kinds of processing: one is to skeletonize it using the Zhang–Suen thinning algorithm and the other is to identify the buds and obtain the center coordinates of the buds using the target-detection method YOLOv5; finally, combining with the depth information of the depth image, we use the coordinates of the buds to determine the location of the pruning point located on the skeleton image. The results show that PSP-net has better results in segmentation performance with mIoU reaching 83.73%. YOLOv5 performs better in target detection with mAP reaching 81.06% and F1 reaching 0.80. The accuracy of this method in determining the location of pruning points reaches 82.35%. It can provide a method for fruit tree pruning robots to determine the location of pruning points.

Förderung

  • Ningxia Hui Autonomous Region key research and development plan project

Zitieren

APA

Chen, Z., Wang, Y., Tong, S., Chen, C., & Kang, F. (2024). Grapevine Branch Recognition and Pruning Point Localization Technology Based on Image Processing. Applied Sciences, 14(8), 3327. https://doi.org/10.3390/app14083327

Vancouver

Chen Z, Wang Y, Tong S, Chen C, Kang F. Grapevine Branch Recognition and Pruning Point Localization Technology Based on Image Processing. Applied Sciences. 2024;14(8):3327. doi:10.3390/app14083327

BibTeX
@article{Chen2024,
  author = {Chen, Zhangnan and Wang, Yaxiong and Tong, Siyuan and Chen, Chongchong and Kang, Feng},
  title = {Grapevine Branch Recognition and Pruning Point Localization Technology Based on Image Processing},
  journal = {Applied Sciences},
  year = {2024},
  volume = {14},
  number = {8},
  pages = {3327},
  doi = {10.3390/app14083327}
}
Kostenlos starten →