.png){kind=icon}
.png){kind=icon}
Return
Optimizing Label Efficiency for Learning-Based Leaf–Wood Separation in Tree Point Clouds
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2025.3632346.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The accurate separation of leaves from woody material in individual-tree point clouds is crucial for the precise estimation of tree structural parameters. While supervised deep learning methods have demonstrated state-of-the-art performance in this domain, they rely extensively on large volumes of labeled data. However, the process of collecting and annotating tree point cloud data presents significant challenges due to the complexity of the intricate structures of trees, which necessitate substantial human resources and expertise. These constraints highlight the critical need to reduce labeling requirements, a challenge that remains largely unexplored. To address this, the present study first systematically analyzes the model performance under limited data annotation. This analysis is divided into two scenarios, with limited number of annotated trees (LT) and limited point annotations per tree. In addition, based on the aforementioned analysis, we propose a specified weakly supervised framework that integrates consistency regularization, contrastive learning, and prototype learning to further improve performance under limited labeling. A series of experiments conducted on a variety of tree species has indicated that the diversity of tree samples is preferable to the use of more labeled points in the context of limited data annotations. The proposed weakly supervised framework demonstrated a mean intersection over union (mIoU) of 82.0% under the extreme scenario of one point per class per tree (i.e., one leaf point and one wood point per tree) annotation. This result is nearly on par with the 84.3% mIoU achieved by a fully supervised model. This study offers significant insight into the improvement of label efficiency in the context of learning-based tree leaf–wood separation, paving the way for the development of efficient and scalable methodologies for 3-D structural analyses in forestry and subsequent practical applications. The implementation code is available on https://github.com/wdczz/PCLNet.
Keywords:
Contrastive learning
label efficiency
leaf–wood separation
point cloud
prototype learning
weakly-supervised learning
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W