Weakly-Supervised Learning for Tree Instances Segmentation in Airborne Lidar Point Clouds

2025-08-21

AI Summary

To address the high annotation cost and poor model generalization caused by data diversity in airborne LiDAR point cloud tree instance segmentation, this paper proposes a quality-score-based weakly supervised learning framework. Unlike conventional methods requiring pixel- or instance-level annotations, our approach only leverages coarse-grained quality scores assigned by human operators to initial segmentation results—generated either by non-fine-tuned models or closed-form algorithms—to train a quality classification model that learns human evaluation criteria. An iterative feedback mechanism then guides segmentation model refinement. Our key contribution is introducing quality scores as weak supervision signals, establishing a closed-loop “segmentation–evaluation–optimization” paradigm. Experiments demonstrate a 34% improvement in tree instance detection accuracy and a significant reduction in false positives for non-tree objects. However, performance remains suboptimal in sparse forests and complex backgrounds containing shrubs or rocks.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Tree instance segmentation of airborne laser scanning (ALS) data is of utmost importance for forest monitoring, but remains challenging due to variations in the data caused by factors such as sensor resolution, vegetation state at acquisition time, terrain characteristics, etc. Moreover, obtaining a sufficient amount of precisely labeled data to train fully supervised instance segmentation methods is expensive. To address these challenges, we propose a weakly supervised approach where labels of an initial segmentation result obtained either by a non-finetuned model or a closed form algorithm are provided as a quality rating by a human operator. The labels produced during the quality assessment are then used to train a rating model, whose task is to classify a segmentation output into the same classes as specified by the human operator. Finally, the segmentation model is finetuned using feedback from the rating model. This in turn improves the original segmentation model by 34% in terms of correctly identified tree instances while considerably reducing the number of non-tree instances predicted. Challenges still remain in data over sparsely forested regions characterized by small trees (less than two meters in height) or within complex surroundings containing shrubs, boulders, etc. which can be confused as trees where the performance of the proposed method is reduced.

Problem

• Tree instance segmentation in airborne LiDAR data
• Reducing expensive precise labeling for supervision
• Improving segmentation accuracy with weak supervision

Innovation

• Weakly-supervised learning for tree segmentation
• Human quality rating labels train rating model
• Fine-tuning segmentation model using rating feedback