UTILISING SIMULATED TREE DATA TO TRAIN SUPERVISED CLASSIFIERS

Abstract. The aim of our research was to examine whether simulated forest data can be utilized for training supervised classifiers. We included two classifiers namely the random forest classifier and the novel convolutional neural network classifier that utilizes feature images. We simulated tree parameters and created a feature vector for each tree. The original feature vector was utilised with random forest classifier. However, these feature vectors were also converted into feature images suitable for input into a YOLO (You Only Look Once) convolutional neural network classifier. The selected features were red colour, green colour, near-infrared colour, tree height divided by canopy diameter, and NDVI. The random forest classifier and convolutional neural network classifier performed similarly both with simulated data and field-measured reference data. As a result, both methods were able to identify correctly 97.5 % of the field-measured reference trees. Simulated data allows much larger training data than what could be feasible from field measurements.

• Publication year

  2022

• Venue

  The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

• Publication date

  2022-05-30

• Fields of study

  Not labeled

• Identifiers
  DOI 10.5194/isprs-archives-xliii-b2-2022-633-2022
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks

  2020cited by this paper
• Moving to Automated Tree Inventory: Comparison of UAS-Derived Lidar and Photogrammetric Data with Manual Ground Estimates

  2020cited by this paper
• Individual tree detection and species classification of Amazonian palms using UAV images and deep learning

  2020cited by this paper
• Sub-pixel electron detection using a convolutional neural network.

  2020cited by this paper
• Individual Tree-Crown Detection in RGB Imagery Using Semi-Supervised Deep Learning Neural Networks

  2019cited by this paper
• A Review of Deep Learning-Based Semantic Segmentation for Point Cloud

  2019cited by this paper
• Convolutional neural network: a review of models, methodologies and applications to object detection

  2019cited by this paper
• Building Instance Change Detection from Large-Scale Aerial Images using Convolutional Neural Networks and Simulated Samples

  2019cited by this paper
• Tree Species Classification in a Highly Diverse Subtropical Forest Integrating UAV-Based Photogrammetric Point Cloud and Hyperspectral Data

  2019cited by this paper
• RESNET-BASED TREE SPECIES CLASSIFICATION USING UAV IMAGES

  2019cited by this paper
• Object-Based Tree Species Classification Using Airborne Hyperspectral Images and LiDAR Data

  2019cited by this paper
• CASI: A Convolutional Neural Network Approach for Shell Identification

  2019cited by this paper
• Young and mature oil palm tree detection and counting using convolutional neural network deep learning method

  2019cited by this paper
• Fish species identification using a convolutional neural network trained on synthetic data

  2018cited by this paper
• On automated source selection for transfer learning in convolutional neural networks

  2018cited by this paper
• Fight Recognition in Video Using Hough Forests and 2D Convolutional Neural Network

  2018cited by this paper
• A Fully Convolutional Neural Network for Beamforming Ultrasound Images

  2018cited by this paper
• Deep Convolutional Neural Network for Ultrasound Image Enhancement

  2018cited by this paper
• Pixel- and object-based multispectral classification of forest tree species from small unmanned aerial vehicles

  2018influential reference
• Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection

  2017cited by this paper
• Systematic Testing of Convolutional Neural Networks for Autonomous Driving

  2017cited by this paper
• Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images

  2017cited by this paper
• Classification of ships using real and simulated data in a convolutional neural network

  2016cited by this paper
• Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

  2016cited by this paper
• Näslundin pituuskäyrä ja siihen perustuvia malleja läpimitan ja pituuden välisestä riippuvuudesta suomalaisissa talousmetsissä

  2016cited by this paper
• Comparison of Tree Species Classifications at the Individual Tree Level by Combining ALS Data and RGB Images Using Different Algorithms

  2016cited by this paper
• Deep learning-based tree classification using mobile LiDAR data

  2015cited by this paper
• You Only Look Once: Unified, Real-Time Object Detection

  2015cited by this paper
• Tree species identification in aerial image data using directional reflectance signatures

  2014influential reference
• Tree Species Classification and Input Data Evaluation

  2013cited by this paper
• Region-based segmentation on depth images from a 3D reference surface for tree species recognition

  2013cited by this paper
• Mapping Savanna Tree Species at Ecosystem Scales Using Support Vector Machine Classification and BRDF Correction on Airborne Hyperspectral and LiDAR Data

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Species identification of individual trees by combining high resolution LiDAR data with multi‐spectral images

  2008cited by this paper
• GradientBased Learning Applied to Document Recognition

  2001cited by this paper
• Random Forests

  2001cited by this paper
• A logical calculus of the ideas immanent in nervous activity

  1990cited by this paper
• Polynomial Theory of Complex Systems

  1970cited by this paper

• Multispectral airborne laser scanning for tree species classification: a benchmark of machine learning and deep learning algorithms

  2025cites this paper