PointNeXt-DBSCAN: a hybrid point cloud deep learning framework for multi-stage cotton leaf instance segmentation.

Abstract

This study addresses the challenge of organ-level instance segmentation in cotton point clouds, which arises from significant morphological variations and leaf occlusion across growth stages. To achieve high-precision leaf extraction, a hybrid framework integrating PointNeXt and DBSCAN is proposed. A dataset containing 1,065 cotton plants from seedling to boll-opening stages was constructed via multi-view image reconstruction and augmented through random rotation and scaling. Methodologically, a two-stage pipeline was designed: semantic segmentation was first performed using the PointNeXt network, where its residual MLP blocks enhanced edge and local feature learning; instance segmentation was then conducted by applying density-adaptive DBSCAN clustering to the semantic results, effectively mitigating over-segmentation in emerging leaves. Experimental results indicate that the semantic segmentation achieved an mIoU of 0.9846, representing a 7.2% improvement over PointNet++. The subsequent instance segmentation attained an ARI of 0.983, reduced the over-segmentation rate by 63%, and maintained an error below 3% for leaves smaller than 5 cm 2 . The framework provides reliable technical support for the automated extraction of key phenotypic traits such as leaf area index and leaf inclination distribution.

Plant phenotyping relevance

綿花葉の点群から器官レベルの葉を自動抽出するセグメンテーション手法を開発・評価し、葉面積指数や葉傾斜分布などの表現型形質への応用を示しているため、方法が中心的である。

Code and data availability

The supplied blocks describe a cotton point cloud dataset (1,065 plants) and a PointNeXt-DBSCAN pipeline, but contain no public data or code availability statement, no repository deposit, and no author-provided URL. allowed_urls is empty, so no paper-specific public asset can be verified.

No evidence-backed public reproduction asset is currently recorded.