date: 2020-12-21T09:04:17Z
pdf:PDFVersion: 1.5
pdf:docinfo:title: Beyond Measurement: Extracting Vegetation Height from High Resolution Imagery with Deep Learning
xmp:CreatorTool: LaTeX with hyperref package
access_permission:can_print_degraded: true
subject:  Measuring and monitoring the height of vegetation provides important insights into forest age and habitat quality. These are essential for the accuracy of applications that are highly reliant on up-to-date and accurate vegetation data. Current vegetation sensing practices involve ground survey, photogrammetry, synthetic aperture radar (SAR), and airborne light detection and ranging sensors (LiDAR). While these methods provide high resolution and accuracy, their hardware and collection effort prohibits highly recurrent and widespread collection. In response to the limitations of current methods, we designed Y-NET, a novel deep learning model to generate high resolution models of vegetation from highly recurrent multispectral aerial imagery and elevation data. Y-NET's architecture uses convolutional layers to learn correlations between different input features and vegetation height, generating an accurate vegetation surface model (VSM) at 11 m resolution. We evaluated Y-NET on 235 km2 of the East San Francisco Bay Area and find that Y-NET achieves low error from LiDAR when tested on new locations. Y-NET also achieves an R2 of 0.83 and can effectively model complex vegetation through side-by-side visual comparisons. Furthermore, we show that Y-NET is able to identify instances of vegetation growth and mitigation by comparing aerial imagery and LiDAR collected at different times. 
dc:format: application/pdf; version=1.5
pdf:docinfo:creator_tool: LaTeX with hyperref package
access_permission:fill_in_form: true
pdf:encrypted: false
dc:title: Beyond Measurement: Extracting Vegetation Height from High Resolution Imagery with Deep Learning
modified: 2020-12-21T09:04:17Z
cp:subject:  Measuring and monitoring the height of vegetation provides important insights into forest age and habitat quality. These are essential for the accuracy of applications that are highly reliant on up-to-date and accurate vegetation data. Current vegetation sensing practices involve ground survey, photogrammetry, synthetic aperture radar (SAR), and airborne light detection and ranging sensors (LiDAR). While these methods provide high resolution and accuracy, their hardware and collection effort prohibits highly recurrent and widespread collection. In response to the limitations of current methods, we designed Y-NET, a novel deep learning model to generate high resolution models of vegetation from highly recurrent multispectral aerial imagery and elevation data. Y-NET's architecture uses convolutional layers to learn correlations between different input features and vegetation height, generating an accurate vegetation surface model (VSM) at 11 m resolution. We evaluated Y-NET on 235 km2 of the East San Francisco Bay Area and find that Y-NET achieves low error from LiDAR when tested on new locations. Y-NET also achieves an R2 of 0.83 and can effectively model complex vegetation through side-by-side visual comparisons. Furthermore, we show that Y-NET is able to identify instances of vegetation growth and mitigation by comparing aerial imagery and LiDAR collected at different times. 
pdf:docinfo:subject:  Measuring and monitoring the height of vegetation provides important insights into forest age and habitat quality. These are essential for the accuracy of applications that are highly reliant on up-to-date and accurate vegetation data. Current vegetation sensing practices involve ground survey, photogrammetry, synthetic aperture radar (SAR), and airborne light detection and ranging sensors (LiDAR). While these methods provide high resolution and accuracy, their hardware and collection effort prohibits highly recurrent and widespread collection. In response to the limitations of current methods, we designed Y-NET, a novel deep learning model to generate high resolution models of vegetation from highly recurrent multispectral aerial imagery and elevation data. Y-NET's architecture uses convolutional layers to learn correlations between different input features and vegetation height, generating an accurate vegetation surface model (VSM) at 11 m resolution. We evaluated Y-NET on 235 km2 of the East San Francisco Bay Area and find that Y-NET achieves low error from LiDAR when tested on new locations. Y-NET also achieves an R2 of 0.83 and can effectively model complex vegetation through side-by-side visual comparisons. Furthermore, we show that Y-NET is able to identify instances of vegetation growth and mitigation by comparing aerial imagery and LiDAR collected at different times. 
pdf:docinfo:creator: 
PTEX.Fullbanner: This is pdfTeX, Version 3.14159265-2.6-1.40.18 (TeX Live 2017/W32TeX) kpathsea version 6.2.3
trapped: False
meta:creation-date: 2020-11-19T10:05:05Z
created: 2020-11-19T10:05:05Z
access_permission:extract_for_accessibility: true
Creation-Date: 2020-11-19T10:05:05Z
producer: pdfTeX-1.40.18
pdf:docinfo:producer: pdfTeX-1.40.18
pdf:unmappedUnicodeCharsPerPage: 17
dc:description:  Measuring and monitoring the height of vegetation provides important insights into forest age and habitat quality. These are essential for the accuracy of applications that are highly reliant on up-to-date and accurate vegetation data. Current vegetation sensing practices involve ground survey, photogrammetry, synthetic aperture radar (SAR), and airborne light detection and ranging sensors (LiDAR). While these methods provide high resolution and accuracy, their hardware and collection effort prohibits highly recurrent and widespread collection. In response to the limitations of current methods, we designed Y-NET, a novel deep learning model to generate high resolution models of vegetation from highly recurrent multispectral aerial imagery and elevation data. Y-NET's architecture uses convolutional layers to learn correlations between different input features and vegetation height, generating an accurate vegetation surface model (VSM) at 11 m resolution. We evaluated Y-NET on 235 km2 of the East San Francisco Bay Area and find that Y-NET achieves low error from LiDAR when tested on new locations. Y-NET also achieves an R2 of 0.83 and can effectively model complex vegetation through side-by-side visual comparisons. Furthermore, we show that Y-NET is able to identify instances of vegetation growth and mitigation by comparing aerial imagery and LiDAR collected at different times. 
Keywords: deep learning; artificial intelligence; vegetation surface modeling
access_permission:modify_annotations: true
description:  Measuring and monitoring the height of vegetation provides important insights into forest age and habitat quality. These are essential for the accuracy of applications that are highly reliant on up-to-date and accurate vegetation data. Current vegetation sensing practices involve ground survey, photogrammetry, synthetic aperture radar (SAR), and airborne light detection and ranging sensors (LiDAR). While these methods provide high resolution and accuracy, their hardware and collection effort prohibits highly recurrent and widespread collection. In response to the limitations of current methods, we designed Y-NET, a novel deep learning model to generate high resolution models of vegetation from highly recurrent multispectral aerial imagery and elevation data. Y-NET's architecture uses convolutional layers to learn correlations between different input features and vegetation height, generating an accurate vegetation surface model (VSM) at 11 m resolution. We evaluated Y-NET on 235 km2 of the East San Francisco Bay Area and find that Y-NET achieves low error from LiDAR when tested on new locations. Y-NET also achieves an R2 of 0.83 and can effectively model complex vegetation through side-by-side visual comparisons. Furthermore, we show that Y-NET is able to identify instances of vegetation growth and mitigation by comparing aerial imagery and LiDAR collected at different times. 
dcterms:created: 2020-11-19T10:05:05Z
Last-Modified: 2020-12-21T09:04:17Z
dcterms:modified: 2020-12-21T09:04:17Z
title: Beyond Measurement: Extracting Vegetation Height from High Resolution Imagery with Deep Learning
xmpMM:DocumentID: uuid:7aa3ed9a-1029-4af6-9552-33d9958573e5
Last-Save-Date: 2020-12-21T09:04:17Z
pdf:docinfo:keywords: deep learning; artificial intelligence; vegetation surface modeling
pdf:docinfo:modified: 2020-12-21T09:04:17Z
meta:save-date: 2020-12-21T09:04:17Z
pdf:docinfo:custom:PTEX.Fullbanner: This is pdfTeX, Version 3.14159265-2.6-1.40.18 (TeX Live 2017/W32TeX) kpathsea version 6.2.3
Content-Type: application/pdf
X-Parsed-By: org.apache.tika.parser.DefaultParser
dc:subject: deep learning; artificial intelligence; vegetation surface modeling
access_permission:assemble_document: true
xmpTPg:NPages: 22
pdf:charsPerPage: 3079
access_permission:extract_content: true
access_permission:can_print: true
pdf:docinfo:trapped: False
meta:keyword: deep learning; artificial intelligence; vegetation surface modeling
access_permission:can_modify: true
pdf:docinfo:created: 2020-11-19T10:05:05Z