用人工评分弱监督提升机载激光点云树实例分割精度
Weakly-Supervised Learning for Tree Instances Segmentation in Airborne Lidar Point Clouds
- 用人工标注初始分割结果质量，训练评分模型
- 评分模型反馈使树实例识别率提升34%，误检非树减少
- 适合数据标注成本高、需提升分割准确率的森林监测场景
机载激光雷达（ALS）数据中的树实例分割对森林监测至关重要，但受传感器分辨率、植被状态、地形特征等因素影响，分割难度大。精确标注数据获取成本高昂，难以支撑全监督方法。为此，本文提出一种弱监督方法：由人工对初始分割结果（来自未微调模型或闭式算法）进行质量评分，生成标签用于训练评分模型，该模型可将分割输出分类为与人工标注一致的类别；随后利用评分模型反馈对分割模型进行微调。实验表明，该方法使树实例识别率提升34%，显著降低非树实例误检数量。然而，在树木稀疏、树高低于两米或周围有灌木、岩石等复杂环境区域，性能仍受限。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。