Individual Tree Detection in Urban ALS Point Clouds with 3D Convolutional Networks

Abstract

Since trees are a vital part of urban green infrastructure, automatic mapping of individual urban trees is becoming increasingly important for city management and planning. Although deep-learning-based object detection networks are the state-of-the-art in computer vision, their adaptation to individual tree detection in urban areas has scarcely been studied. Some existing works have employed 2D object detection networks for this purpose. However, these have used three-dimensional information only in the form of projected feature maps. In contrast, we exploited the full 3D potential of airborne laser scanning (ALS) point clouds by using a 3D neural network for individual tree detection. Specifically, a sparse convolutional network was used for 3D feature extraction, feeding both semantic segmentation and circular object detection outputs, which were combined for further increased accuracy. We demonstrate the capability of our approach on an urban topographic ALS point cloud with 10,864 hand-labeled ground truth trees. Our method achieved an average precision of 83% regarding the common 0.5 intersection over union criterion. 85% percent of the stems were found correctly with a precision of 88%, while tree area was covered by the individual tree detections with an F1 accuracy of 92%. Thereby, we outperformed traditional delineation baselines and recent detection networks.

Influence of urban forests on residential property values: A systematic review of remote sensing-based studies

“…The geographical distribution of urban forest ES influences on housing prices, and costs versus benefits of urban forest management are highly limited to countries such as the U.S., China, and those in Europe. These specific neighborhood-level tree cover and city level forest cover needs can be ascertained using LiDAR point cloud data and multispectral imagery to detect and reconstruct individual tree crowns and represent them within 3D city models [ 82 , 83 ]. RS technologies cover extensive spatial areas and provide historical data over a longer period of time, which can be used to conduct large-scale studies across cities to measure urban forests biomass for carbon credits payments, vegetation greenness, ES, detect tree health and forest fragmentation, and monitor urban forest fire.…”

Metamorphism of Als Point Data for Multitude Application

“…The tree data that is optimally, semantically, and ontologically stored in the proposed framework can be leveraged for applications pertaining to this domain. Some of the analysis include region-wise tree count in city (Schmohl et al, 2022), tree type classification using individual tree point cloud (Jombo et al, 2022), biomass calculation (Yang et al, 2022), etc. The analysis and geo-location enabled statistics can be used for efficient planning.…”

Classification of Forest LiDAR Data Using Deep Learning Pipeline Algorithm and Geometric Feature Analysis

“…Regarding the methods used for tree detection, Tarsha Kurdi et al [30] summarized the main approaches based on the ML Random Forest algorithm for tree detection. Schmohl et al [31] used a 3D neural network for individual tree detection from 3D ALS point clouds. Windrim et al [32] also used deep learning models to isolate individual trees, determine tree stem points, and build a segmented model of the main tree stem that includes tree height, diameter, taper, and sweep from airborne laser scanning (ALS) of forests.…”