MASPC_Transform: A Plant Point Cloud Segmentation Network Based on Multi-Head Attention Separation and Position Code

Abstract

Plant point cloud segmentation is an important step in 3D plant phenotype research. Because the stems, leaves, flowers, and other organs of plants are often intertwined and small in size, this makes plant point cloud segmentation more challenging than other segmentation tasks. In this paper, we propose MASPC_Transform, a novel plant point cloud segmentation network base on multi-head attention separation and position code. The proposed MASPC_Transform establishes connections for similar point clouds scattered in different areas of the point cloud space through multiple attention heads. In order to avoid the aggregation of multiple attention heads, we propose a multi-head attention separation loss based on spatial similarity, so that the attention positions of different attention heads can be dispersed as much as possible. In order to reduce the impact of point cloud disorder and irregularity on feature extraction, we propose a new point cloud position coding method, and use the position coding network based on this method in the local and global feature extraction modules of MASPC_Transform. We evaluate our MASPC_Transform on the ROSE_X dataset. Compared with the state-of-the-art approaches, the proposed MASPC_Transform achieved better segmentation results.

Plant phenotyping relevance

植物点群から器官を分割する新規ネットワークを開発・評価しており、3D植物表現型研究のための形態・構造形質抽出手法が中心である。

Code and data availability

The paper evaluates MASPC_Transform on the ROSE_X dataset, but ROSE_X is cited prior work (Dutagaci et al.), not a paper-specific asset. The Data Availability Statement says 'Not applicable,' and no author code, models, or data URLs are provided.

No evidence-backed public reproduction asset is currently recorded.