PACANet: A Paired-Attention central axis aggregation network for plant population point cloud segmentation and phenotypic trait Extraction—A case study on maize

Abstract

Advanced phenotyping techniques are required in the breeding and management of maize, which is crucial for global food security. Traditional in situ three-dimensional (3D) field phenotyping entails labour-intensive data acquisition. Light detection and ranging technology offers high-resolution maize canopy point clouds under outdoor field conditions, establishing a technical foundation for automated phenotypic trait extraction. However, accurately segmenting individual plants from dense and structurally complex canopy point clouds for single-plant trait analysis is challenging. To address this challenge, we propose a novel framework named Paired-Attention Central Axis Aggregation Network (PACANet) for 3D point cloud-based plant segmentation. Firstly, a 3D paired-attention backbone network is introduced to enhance point-wise feature representations by integrating spatial and channel information, thereby enabling effective learning of high-dimensional point cloud features. Secondly, a projection-based central axis aggregation strategy is incorporated to guide instance separation by projecting plant point clouds onto their respective central axis skeletons, which improves the spatial coherence of segmentation. Additionally, a simulation-based point cloud generation approach is proposed to reduce reliance on large-scale manual annotations, facilitating model training in scenarios with limited real-world population data. Comprehensive experimental evaluations across multiple datasets demonstrate that PACANet consistently outperforms existing plant population segmentation methods. Notably, when trained solely on simulated data, PACANet achieves a state-of-the-art average precision of 0.9246. Finally, based on the segmentation results, phenotypic traits at both the individual plant and organ levels are analyzed under various planting densities, including the field-level distributions of plant height, plant width, leaf base angle and leaf inclination angle, all of which exhibit strong consistency with the validation data. These results highlight the potential of PACANet as a robust and scalable solution for high-throughput phenotyping in smart breeding and precision agriculture. This study provides a new tool for smart breeding and precision agriculture, and the source code and data are available at https://github.com/yangxin6/3D-PACA-Network.git.