Unsupervised Tree Detection from UAV Imagery and 3D Point Clouds via Distance Transform-Based Circle Estimation and AIC Optimization

Abstract

This work proposes a novel tree detection methodology, named DTCD (Distance Transform Circle Detection), based on a fast circle detection method via Distance Transform and Akaike Information Criterion (AIC) optimization. More specifically, a visible-band vegetation index (RGBVI) is calculated to enhance canopy regions, followed by morphological filtering to delineate individual tree crowns. The Euclidean Distance Transform is then applied, and the local maxima of the smoothed distance map are extracted as candidate tree locations. The final detections are iteratively refined using the AIC to optimize the number of trees with respect to canopy coverage efficiency. Additionally, this work introduces DTCD-PC, a modified algorithm tailored for point clouds, which significantly enhances detection accuracy in complex environments. This work makes a significant contribution to tree detection in the following ways: (1) by creating a tree detection framework entirely based on an unsupervised technique, which outperforms state-of-the-art unsupervised and supervised tree detection methods; (2) by introducing a new urban dataset, named AgiosNikolaos-3, that consists of orthomosaics and photogrammetrically reconstructed 3D point clouds, allowing the assessment of the proposed method in complex urban environments. The proposed DTCD approach was evaluated on the Acacia-6 dataset, consisting of UAV images of six-month-old Acacia trees in Southeast Asia, demonstrating superior detection performance compared to existing state-of-the-art techniques, both unsupervised and supervised. Additional experiments were conducted in the custom-developed Urban Dataset, confirming the robustness and generalizability of the DTCD-PC method in heterogeneous environments.

Plant phenotyping relevance

UAV画像・3D点群から個体樹冠を抽出する新規手法を開発し、複数データセットで精度・頑健性を評価しているため、植物形態の取得・抽出が中心である。

Code and data availability

The authors state that the MATLAB code implementing the DTCD/DTCD-PC method, together with the datasets (Acacia-6, AgiosNikolaos-3) and results, is publicly available at their project page. Since the article is published (accepted), this is an actionable public asset containing the paper's tree-detection analysis code,