EUVIMEDOpdag EUVIMED
Crossref

Geometry‐Aware 3D Point Cloud Learning for Precise Cutting‐Point Detection in Unstructured Field Environments

Hongjun Wang, Gengming Zhang, Hao Cao, Kewei Hu, Quanchao Wang, Yuqin Deng, Junfeng Gao, Yunchao Tang

Journal of Field Robotics · 2025-10 · 42 (7) · 3063-3076

DOI: 10.1002/rob.22567 ↗

At a glance

Journal article in Journal of Field Robotics, published online on 2025-04-21. Written by Hongjun Wang and 7 co-authors. Cited 141 times so far (Crossref); 47 references.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

In automated lychee harvesting, the complex geometric structures of branches, leaves, and clustered fruits pose significant challenges for robotic cutting point detection, where even minor positioning errors can lead to harvest damage and operational failures. This study introduces the Fcaf3d‐lychee network model, specifically designed for precise lychee picking point localization. The data acquisition system utilizes Microsoft's Azure Kinect DK time‐of‐flight camera to capture point cloud data through multi‐view stitching, enabling comprehensive spatial information capture. The proposed model enhances the Fully Convolutional Anchor‐Free 3D Object Detection (Fcaf3d) architecture by incorporating a squeeze‐and‐excitation (SE) module, which leverages human visual attention mechanisms to improve feature extraction capabilities. Experimental results demonstrate the model's superior performance, achieving an score of 88.57% on the test data set, significantly outperforming existing approaches. Field tests in real orchard environments show robust performance under varying occlusion conditions, with detection accuracies of 0.932, 0.824, and 0.765 for unobstructed, partially obstructed, and severely obstructed scenarios, respectively. The model maintains localization errors within 1.5 cm in all directions, demonstrating exceptional precision for practical harvesting applications. This research advances the field of automated fruit harvesting by providing a reliable solution for accurate picking point detection, contributing to the development of more efficient agricultural robotics systems.

Cite

APA

Wang, H., Zhang, G., Cao, H., Hu, K., Wang, Q., Deng, Y., Gao, J., & Tang, Y. (2025). Geometry‐Aware 3D Point Cloud Learning for Precise Cutting‐Point Detection in Unstructured Field Environments. Journal of Field Robotics, 42(7), 3063-3076. https://doi.org/10.1002/rob.22567

Vancouver

Wang H, Zhang G, Cao H, Hu K, Wang Q, Deng Y, et al. Geometry‐Aware 3D Point Cloud Learning for Precise Cutting‐Point Detection in Unstructured Field Environments. Journal of Field Robotics. 2025;42(7):3063-3076. doi:10.1002/rob.22567

BibTeX
@article{Wang2025,
  author = {Wang, Hongjun and Zhang, Gengming and Cao, Hao and Hu, Kewei and Wang, Quanchao and Deng, Yuqin and Gao, Junfeng and Tang, Yunchao},
  title = {Geometry‐Aware 3D Point Cloud Learning for Precise Cutting‐Point Detection in Unstructured Field Environments},
  journal = {Journal of Field Robotics},
  year = {2025},
  volume = {42},
  number = {7},
  pages = {3063--3076},
  doi = {10.1002/rob.22567}
}
Start for free →