TreeSeg-Net: An End-to-End Instance Segmentation Network for Leaf-Off Forest Point Clouds Using Global Context and Spatial Proximity

TL;DR

This paper introduces TreeSeg-Net, a new method for accurately identifying individual trees in 3D forest data during the leaf-off season.

Contribution

TreeSeg-Net uses global context and spatial proximity modules to improve segmentation accuracy in complex forest point clouds.

Findings

TreeSeg-Net achieved 97.2% average precision in instance segmentation tasks.

The method reached 99.7% mean intersection over union in semantic segmentation.

It outperforms existing methods in handling fuzzy boundaries and instance adhesion in leaf-off forests.

Abstract

Forest ecosystems play a pivotal role in maintaining the balance of the global carbon cycle and conserving biodiversity. High-density point clouds derived from unmanned aerial vehicle (UAV) structure from motion (SfM) and multi-view stereo (MVS) technologies offer a cost-effective solution for data acquisition. These technologies have become efficient tools for facilitating precision forest resource management and extracting individual tree structural parameters. However, in complex forest scenarios during the leaf-off season, canopies exhibit unstructured branch network morphologies due to the absence of leaf occlusion, and adjacent crowns are heavily interlaced. Consequently, existing segmentation methods struggle to overcome challenges associated with fuzzy boundaries and instance adhesion. To address these challenges, this study proposes TreeSeg-Net, an end-to-end instance segmentation network designed to precisely separate individual trees directly from raw point clouds. The network incorporates a global context attention module (GCAM) to capture long-range feature dependencies, thereby compensating for the limitations of sparse convolution in perceiving global information. Simultaneously, a spatial proximity weighting module (SPWM) is designed. By introducing geometric center constraints and a distance penalty mechanism, this module effectively mitigates under-segmentation issues caused by the feature similarity of adjacent branches in high-canopy-density environments. Experimental results demonstrate that TreeSeg-Net achieves an average precision (AP) of 97.2% in instance segmentation tasks and a mean intersection over union (mIoU) of 99.7% in semantic segmentation tasks. Compared to mainstream networks, the proposed method exhibits superior segmentation accuracy, providing an efficient and automated technical solution for precise resource inventory in complex forest environments.

Figures