A Novel WaveInst-based Network for Tree Trunk Structure Extraction and Pattern Analysis in Forest Inventory

TL;DR

This work tackles the challenge of accurate tree trunk and branch structure extraction from UAV imagery in forestry. It introduces WaveInst, a novel instance segmentation network that fuses a Discrete Wavelet Transform (DWT) branch with an adaptive gated fusion mechanism and a dynamic sampling module to preserve high-frequency details while maintaining efficiency. The approach demonstrates strong performance across synthetic, real, and juvenile-tree datasets, and enables automatic estimation of phenotypic growth parameters like DBH and tree height from 2D images. By providing a new dataset (PoplarDataset) and comprehensive evaluations, the method offers a scalable tool for precision forestry, ecological monitoring, and plant-breeding studies.

Abstract

The pattern analysis of tree structure holds significant scientific value for genetic breeding and forestry management. The current trunk and branch extraction technologies are mainly LiDAR-based or UAV-based. The former approaches obtain high-precision 3D data, but its equipment cost is high and the three-dimensional (3D) data processing is complex. The latter approaches efficiently capture canopy information, but they miss the 3-D structure of trees. In order to deal with the branch information extraction from the complex background interference and occlusion, this work proposes a novel WaveInst instance segmentation framework, involving a discrete wavelet transform, to enhance multi-scale edge information for accurately improving tree structure extraction. Experimental results of the proposed model show superior performance on SynthTree43k, CaneTree100, Urban Street and our PoplarDataset. Moreover, we present a new Phenotypic dataset PoplarDataset, which is dedicated to extract tree structure and pattern analysis from artificial forest. The proposed method achieves a mean average precision of 49.6 and 24.3 for the structure extraction of mature and juvenile trees, respectively, surpassing the existing state-of-the-art method by 9.9. Furthermore, by in tegrating the segmentation model within the regression model, we accurately achieve significant tree grown parameters, such as the location of trees, the diameter-at-breast-height of individual trees, and the plant height, from 2D images directly. This study provides a scientific and plenty of data for tree structure analysis in related to the phenotype research, offering a platform for the significant applications in precision forestry, ecological monitoring, and intelligent breeding.

Figures (12)

• Figure 1: Overview of the proposed WaveInst.
• Figure 2: The information transmission flow of the DWT Block. (a) the structure of the DWT Block; (b) the principles of the Discrete Wavelet Transform and processing results.
• Figure 3: The information transmission flow of the HFE Block.
• Figure 4: The information transmission flow of Adaptive Gated Fusion Module (AGFM).
• Figure 5: The structure diagram of DySample module.