LeafInst - Unified Instance Segmentation Network for Fine-Grained Forestry Leaf Phenotype Analysis: A New UAV based Benchmark

TL;DR

This paper introduces LeafInst, a novel instance segmentation framework designed for fine-grained forestry leaf analysis in open-field UAV imagery, supported by a new annotated dataset, achieving state-of-the-art performance.

Contribution

The paper presents a new UAV-based forestry leaf dataset and a specialized segmentation model, LeafInst, tailored for irregular, multi-scale leaf structures in natural environments.

Findings

LeafInst achieves 68.4 mAP on Poplar-leaf, outperforming YOLOv11 and MaskDINO.

On PhenoBench, LeafInst reaches 52.7 box mAP, surpassing MaskDINO.

The model demonstrates strong generalization and practical utility for large-scale leaf phenotyping.

Abstract

Intelligent forest tree breeding has advanced plant phenotyping, yet existing research largely focuses on large-leaf agricultural crops, with limited attention to fine-grained leaf analysis of sapling trees in open-field environments. Natural scenes introduce challenges including scale variation, illumination changes, and irregular leaf morphology. To address these issues, we collected UAV RGB imagery of field-grown saplings and constructed the Poplar-leaf dataset, containing 1,202 branches and 19,876 pixel-level annotated leaf instances. To our knowledge, this is the first instance segmentation dataset specifically designed for forestry leaves in open-field conditions. We propose LeafInst, a novel segmentation framework tailored for irregular and multi-scale leaf structures. The model integrates an Asymptotic Feature Pyramid Network (AFPN) for multi-scale perception, a Dynamic Asymmetric Spatial Perception (DASP) module for irregular shape modeling, and a dual-residual Dynamic Anomalous Regression Head (DARH) with Top-down Concatenation decoder Feature Fusion (TCFU) to improve detection and segmentation performance. On Poplar-leaf, LeafInst achieves 68.4 mAP, outperforming YOLOv11 by 7.1 percent and MaskDINO by 6.5 percent. On the public PhenoBench benchmark, it reaches 52.7 box mAP, exceeding MaskDINO by 3.4 percent. Additional experiments demonstrate strong generalization and practical utility for large-scale leaf phenotyping.