Delving into the Potential of Deep Learning Algorithms for Point Cloud Segmentation at Organ Level in Plant Phenotyping
Remote Sensing · 04.09.2024 · 16 (17) · 3290
DOI: 10.3390/rs16173290 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 04.09.2024. Verfasst von Kai Xie und 7 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 98 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Three-dimensional point clouds, as an advanced imaging technique, enable researchers to capture plant traits more precisely and comprehensively. The task of plant segmentation is crucial in plant phenotyping, yet current methods face limitations in computational cost, accuracy, and high-throughput capabilities. Consequently, many researchers have adopted 3D point cloud technology for organ-level segmentation, extending beyond manual and 2D visual measurement methods. However, analyzing plant phenotypic traits using 3D point cloud technology is influenced by various factors such as data acquisition environment, sensors, research subjects, and model selection. Although the existing literature has summarized the application of this technology in plant phenotyping, there has been a lack of in-depth comparison and analysis at the algorithm model level. This paper evaluates the segmentation performance of various deep learning models on point clouds collected or generated under different scenarios. These methods include outdoor real planting scenarios and indoor controlled environments, employing both active and passive acquisition methods. Nine classical point cloud segmentation models were comprehensively evaluated: PointNet, PointNet++, PointMLP, DGCNN, PointCNN, PAConv, CurveNet, Point Transformer (PT), and Stratified Transformer (ST). The results indicate that ST achieved optimal performance across almost all environments and sensors, albeit at a significant computational cost. The transformer architecture for points has demonstrated considerable advantages over traditional feature extractors by accommodating features over longer ranges. Additionally, PAConv constructs weight matrices in a data-driven manner, enabling better adaptation to various scales of plant organs. Finally, a thorough analysis and discussion of the models were conducted from multiple perspectives, including model construction, data collection environments, and platforms.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Xie, K., Zhu, J., Ren, H., Wang, Y., Yang, W., Chen, G., Lin, C., & Zhai, R. (2024). Delving into the Potential of Deep Learning Algorithms for Point Cloud Segmentation at Organ Level in Plant Phenotyping. Remote Sensing, 16(17), 3290. https://doi.org/10.3390/rs16173290
Vancouver
Xie K, Zhu J, Ren H, Wang Y, Yang W, Chen G, et al. Delving into the Potential of Deep Learning Algorithms for Point Cloud Segmentation at Organ Level in Plant Phenotyping. Remote Sensing. 2024;16(17):3290. doi:10.3390/rs16173290
BibTeX
@article{Xie2024,
author = {Xie, Kai and Zhu, Jianzhong and Ren, He and Wang, Yinghua and Yang, Wanneng and Chen, Gang and Lin, Chengda and Zhai, Ruifang},
title = {Delving into the Potential of Deep Learning Algorithms for Point Cloud Segmentation at Organ Level in Plant Phenotyping},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {17},
pages = {3290},
doi = {10.3390/rs16173290}
}
EUVIMED