Takauji Hidenori, Wada Naofumi, Kaneko Shun'ichi, Tanabata Takanari
Department of Electronics and Information Engineering, Faculty of Engineering, Hokkai-Gakuen University, Sapporo 0640926, Japan.
Department of Information Science and Technology, Faculty of Information Science and Technology, Hokkaido University of Science, Sapporo 0068585, Japan.
Sensors (Basel). 2025 Jun 11;25(12):3659. doi: 10.3390/s25123659.
This paper presents a novel method, Histogram of Angles in Linked Features (HALF), designed for the segmentation of 3D point cloud data of plants for robust sensing. The proposed method leverages local angular features extracted from 3D measurements obtained via sensing technologies such as laser scanning, LiDAR, or photogrammetry. HALF enables efficient identification of plant structures-leaves, stems, and knots-without requiring large-scale labeled datasets, making it highly suitable for applications in plant phenotyping and structural analysis. To enhance robustness and interpretability, we extend HALF to a convolution-based mathematical framework and introduce the Sequential Competitive Segmentation Algorithm (SCSA) for phytomer-level classification. Experimental results using 3D point cloud data of soybean plants demonstrate the feasibility of our method in sensor-based plant monitoring systems. By providing a low-cost and efficient approach for plant structure analysis, HALF contributes to the advancement of sensor-driven plant phenotyping and precision agriculture.
本文提出了一种新颖的方法——关联特征角度直方图（HALF），用于分割植物的三维点云数据以实现稳健感知。该方法利用从激光扫描、激光雷达或摄影测量等传感技术获取的三维测量数据中提取的局部角度特征。HALF能够高效识别植物结构——叶子、茎和节，而无需大规模的标注数据集，这使其非常适合用于植物表型分析和结构分析。为了增强鲁棒性和可解释性，我们将HALF扩展到基于卷积的数学框架，并引入了用于叶元水平分类的顺序竞争分割算法（SCSA）。使用大豆植物三维点云数据的实验结果证明了我们的方法在基于传感器的植物监测系统中的可行性。通过为植物结构分析提供低成本且高效的方法，HALF有助于推动传感器驱动的植物表型分析和精准农业的发展。
