Identification of linear vegetation elements in a rural landscape using LiDAR point clouds

Chris Lucas, Willem Bouten, Zsófia Koma, W. Daniel Kissling, Arie C. Seijmonsbergen

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Modernization of agricultural land use across Europe is responsible for a substantial decline of linear vegetation elements such as tree lines, hedgerows, riparian vegetation, and green lanes. These linear objects have an important function for biodiversity, e.g., as ecological corridors and local habitats for many animal and plant species. Knowledge on their spatial distribution is therefore essential to support conservation strategies and regional planning in rural landscapes but detailed inventories of such linear objects are often lacking. Here, we propose a method to detect linear vegetation elements in agricultural landscapes using classification and segmentation of high-resolution Light Detection and Ranging (LiDAR) point data. To quantify the 3D structure of vegetation, we applied point cloud analysis to identify point-based and neighborhood-based features. As a preprocessing step, we removed planar surfaces such as grassland, bare soil, and water bodies from the point cloud using a feature that describes to what extent the points are scattered in the local neighborhood. We then applied a random forest classifier to separate the remaining points into vegetation and other. Subsequently, a rectangularity-based region growing algorithm allowed to segment the vegetation points into 2D rectangular objects, which were then classified into linear objects based on their elongatedness. We evaluated the accuracy of the linear objects against a manually delineated validation set. The results showed high user's (0.80), producer's (0.85), and total accuracies (0.90). These findings are a promising step towards testing our method in other regions and for upscaling it to broad spatial extents. This would allow producing detailed inventories of linear vegetation elements at regional and continental scales in support of biodiversity conservation and regional planning in agricultural and other rural landscapes.

Original languageEnglish
Article number292
Pages (from-to)1-16
Number of pages16
JournalRemote Sensing
Volume11
Issue number3
DOIs
Publication statusPublished - 1 Feb 2019

Fingerprint

rural landscape
vegetation
regional planning
agricultural land
biodiversity
hedgerow
upscaling
testing method
riparian vegetation
conservation planning
treeline
bare soil
modernization
segmentation
detection
grassland
spatial distribution
land use
habitat

Keywords

  • Classification
  • LiDAR
  • Linear vegetation
  • Object recognition
  • Point cloud
  • Rectangularity
  • Rural landscapes
  • Segmentation

Cite this

Lucas, Chris ; Bouten, Willem ; Koma, Zsófia ; Kissling, W. Daniel ; Seijmonsbergen, Arie C. / Identification of linear vegetation elements in a rural landscape using LiDAR point clouds. In: Remote Sensing. 2019 ; Vol. 11, No. 3. pp. 1-16.
@article{2764e295836f44dc82122296b33b3edc,
title = "Identification of linear vegetation elements in a rural landscape using LiDAR point clouds",
abstract = "Modernization of agricultural land use across Europe is responsible for a substantial decline of linear vegetation elements such as tree lines, hedgerows, riparian vegetation, and green lanes. These linear objects have an important function for biodiversity, e.g., as ecological corridors and local habitats for many animal and plant species. Knowledge on their spatial distribution is therefore essential to support conservation strategies and regional planning in rural landscapes but detailed inventories of such linear objects are often lacking. Here, we propose a method to detect linear vegetation elements in agricultural landscapes using classification and segmentation of high-resolution Light Detection and Ranging (LiDAR) point data. To quantify the 3D structure of vegetation, we applied point cloud analysis to identify point-based and neighborhood-based features. As a preprocessing step, we removed planar surfaces such as grassland, bare soil, and water bodies from the point cloud using a feature that describes to what extent the points are scattered in the local neighborhood. We then applied a random forest classifier to separate the remaining points into vegetation and other. Subsequently, a rectangularity-based region growing algorithm allowed to segment the vegetation points into 2D rectangular objects, which were then classified into linear objects based on their elongatedness. We evaluated the accuracy of the linear objects against a manually delineated validation set. The results showed high user's (0.80), producer's (0.85), and total accuracies (0.90). These findings are a promising step towards testing our method in other regions and for upscaling it to broad spatial extents. This would allow producing detailed inventories of linear vegetation elements at regional and continental scales in support of biodiversity conservation and regional planning in agricultural and other rural landscapes.",
keywords = "Classification, LiDAR, Linear vegetation, Object recognition, Point cloud, Rectangularity, Rural landscapes, Segmentation",
author = "Chris Lucas and Willem Bouten and Zs{\'o}fia Koma and Kissling, {W. Daniel} and Seijmonsbergen, {Arie C.}",
year = "2019",
month = "2",
day = "1",
doi = "10.3390/rs11030292",
language = "English",
volume = "11",
pages = "1--16",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "3",

}

Lucas, C, Bouten, W, Koma, Z, Kissling, WD & Seijmonsbergen, AC 2019, 'Identification of linear vegetation elements in a rural landscape using LiDAR point clouds' Remote Sensing, vol. 11, no. 3, 292, pp. 1-16. https://doi.org/10.3390/rs11030292

Identification of linear vegetation elements in a rural landscape using LiDAR point clouds. / Lucas, Chris; Bouten, Willem; Koma, Zsófia; Kissling, W. Daniel; Seijmonsbergen, Arie C.

In: Remote Sensing, Vol. 11, No. 3, 292, 01.02.2019, p. 1-16.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Identification of linear vegetation elements in a rural landscape using LiDAR point clouds

AU - Lucas, Chris

AU - Bouten, Willem

AU - Koma, Zsófia

AU - Kissling, W. Daniel

AU - Seijmonsbergen, Arie C.

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Modernization of agricultural land use across Europe is responsible for a substantial decline of linear vegetation elements such as tree lines, hedgerows, riparian vegetation, and green lanes. These linear objects have an important function for biodiversity, e.g., as ecological corridors and local habitats for many animal and plant species. Knowledge on their spatial distribution is therefore essential to support conservation strategies and regional planning in rural landscapes but detailed inventories of such linear objects are often lacking. Here, we propose a method to detect linear vegetation elements in agricultural landscapes using classification and segmentation of high-resolution Light Detection and Ranging (LiDAR) point data. To quantify the 3D structure of vegetation, we applied point cloud analysis to identify point-based and neighborhood-based features. As a preprocessing step, we removed planar surfaces such as grassland, bare soil, and water bodies from the point cloud using a feature that describes to what extent the points are scattered in the local neighborhood. We then applied a random forest classifier to separate the remaining points into vegetation and other. Subsequently, a rectangularity-based region growing algorithm allowed to segment the vegetation points into 2D rectangular objects, which were then classified into linear objects based on their elongatedness. We evaluated the accuracy of the linear objects against a manually delineated validation set. The results showed high user's (0.80), producer's (0.85), and total accuracies (0.90). These findings are a promising step towards testing our method in other regions and for upscaling it to broad spatial extents. This would allow producing detailed inventories of linear vegetation elements at regional and continental scales in support of biodiversity conservation and regional planning in agricultural and other rural landscapes.

AB - Modernization of agricultural land use across Europe is responsible for a substantial decline of linear vegetation elements such as tree lines, hedgerows, riparian vegetation, and green lanes. These linear objects have an important function for biodiversity, e.g., as ecological corridors and local habitats for many animal and plant species. Knowledge on their spatial distribution is therefore essential to support conservation strategies and regional planning in rural landscapes but detailed inventories of such linear objects are often lacking. Here, we propose a method to detect linear vegetation elements in agricultural landscapes using classification and segmentation of high-resolution Light Detection and Ranging (LiDAR) point data. To quantify the 3D structure of vegetation, we applied point cloud analysis to identify point-based and neighborhood-based features. As a preprocessing step, we removed planar surfaces such as grassland, bare soil, and water bodies from the point cloud using a feature that describes to what extent the points are scattered in the local neighborhood. We then applied a random forest classifier to separate the remaining points into vegetation and other. Subsequently, a rectangularity-based region growing algorithm allowed to segment the vegetation points into 2D rectangular objects, which were then classified into linear objects based on their elongatedness. We evaluated the accuracy of the linear objects against a manually delineated validation set. The results showed high user's (0.80), producer's (0.85), and total accuracies (0.90). These findings are a promising step towards testing our method in other regions and for upscaling it to broad spatial extents. This would allow producing detailed inventories of linear vegetation elements at regional and continental scales in support of biodiversity conservation and regional planning in agricultural and other rural landscapes.

KW - Classification

KW - LiDAR

KW - Linear vegetation

KW - Object recognition

KW - Point cloud

KW - Rectangularity

KW - Rural landscapes

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85061399804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061399804&partnerID=8YFLogxK

U2 - 10.3390/rs11030292

DO - 10.3390/rs11030292

M3 - Article

VL - 11

SP - 1

EP - 16

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 3

M1 - 292

ER -