Toulouse 2015 Supervised SVN classification results for 600 urban trees according to a 3 level nomenclature

Hyperspectral data were obtained during an acquisition campaign led on Toulouse (France) urban area on July 2015 using Hyspex instrument which provides 408 spectral bands spread over 0.4 – 2.5 μ. Flight altitude lead to 2 m spatial resolution images. Supervised SVN classification results for 600 urban trees according to a 3 level nomenclature: leaf type (5 classes), family (12 and 19 classes) and species (14 and 27 classes). The number of classes differ for the two latter as they depend on the minimum number of individuals considered (4 and 10 individuals per class respectively). Trees positions have been acquired using differential GPS and are given with centimetric to decimetric precision. A randomly selected subset of these trees has been used to train machine SVM and Random Forest classification algorithms. Those algorithms were applied to hyperspectral images using a number of classes for family (12 and 19 classes) and species (14 and 27 classes) levels defined according to the minimum number of individuals considered during training/validation process (4 and 10 individuals per class, respectively). Global classification precision for several training subsets is given by Brabant et al, 2019 (https://www.mdpi.com/470202) in terms of averaged overall accuracy (AOA) and averaged kappa index of agreement (AKIA).
 
Citation proposal
. Toulouse 2015 Supervised SVN classification results for 600 urban trees according to a 3 level nomenclature. https://idg-tetis.teledetection.fr/geonetwork/srv/api/records/e324c038-08f3-4a11-aca2-7abbeda014e7
 

INSPIRE

Identification

File identifier
e324c038-08f3-4a11-aca2-7abbeda014e7   XML
Hierarchy level
Dataset
Online resource
Protocol
file for download
Protocol
OGC:WMS
Resource identifier
code
e324c038-08f3-4a11-aca2-7abbeda014e7
Metadata language
English
Spatial representation type
Vector
Encoding
Format
ESRI Shapefile
Version
1.0
Projection
code
4326
 

Classification of data and services

Topic category
  • Geoscientific information
  • Environment
 

Classification of data and services

Coupled resource
Coupled resource
 
 

Classification of data and services

Coupled resource
Coupled resource
 
 

Keywords

General ( Theme )
  • remote sensing
  • VHRS imagery
  • HYPERSPECTRAL imagery
  • urban studies
GEMET - INSPIRE themes, version 1.0 ( Theme )
GEMET - Concepts ( Theme )
GCMD Keywords viewer ( Theme )
TETIS Thesaurus, version 1.0 21112019 ( Theme )
Other keywords
 
 

Geographic coverage

N
S
E
W


 

Temporal reference

Temporal extent
Begin
2015-07-01T00:00:00Z
End
2015-07-31T00:00:00Z
Temporal extent
Date ( Revision )
2022-05-17T19:09:06
 

Quality and validity

Lineage
Hyperspectral data were obtained during an acquisition campaign led on Toulouse (France) urban area on July 2015 using Hyspex instrument which provides 408 spectral bands spread over 0.4 – 2.5 μ. Flight altitude lead to 2 m spatial resolution images. Supervised SVN classification results for 600 urban trees according to a 3 level nomenclature: leaf type (5 classes), family (12 and 19 classes) and species (14 and 27 classes). The number of classes differ for the two latter as they depend on the minimum number of individuals considered (4 and 10 individuals per class respectively). Trees positions have been acquired using differential GPS and are given with centimetric to decimetric precision. A randomly selected subset of these trees has been used to train machine SVM and Random Forest classification algorithms. Those algorithms were applied to hyperspectral images using a number of classes for family (12 and 19 classes) and species (14 and 27 classes) levels defined according to the minimum number of individuals considered during training/validation process (4 and 10 individuals per class, respectively). Global classification precision for several training subsets is given by Brabant et al, 2019 (https://www.mdpi.com/470202) in terms of averaged overall accuracy (AOA) and averaged kappa index of agreement (AKIA).
 

Conformity

Conformity
Conformity
 

Conformity

Conformity
Conformity
Explanation
some explanation about the conformance
Explanation
See the referenced specification
Explanation
See the referenced specification
 

Restrictions on access and use

 

Restrictions on access and use

 

Responsible organization (s)

Contact for the resource
Organisation name
UMR TETIS - CNRS
Email
Christiane.Weber@cnrs.fr
 

Responsible organization (s)

Contact for the resource
Organisation name
UMR TETIS - CNRS
Email
Christiane.Weber@cnrs.fr
 

Metadata information

Contact for the metadata
Organisation name
LETG - Univ Rennes 2
Email
thomas.houet@univ-rennes2.fr
Organisation name
UMR TETIS - CNRS
Email
Christiane.Weber@cnrs.fr
Organisation name
UMR TETIS - CNRS
Email
Claudia. Lavalley@cnrs.fr
Date stamp
2022-05-17T19:25:04
Metadata language
English
Character set
UTF8
 
 

SDS

Conformance class 1: invocable

Access Point URL
Endpoint URL
Technical specification
 

Conformance class 2: interoperable

Coordinate reference system
 
Quality of Service
 
Access constraints
Limitation
 
Use constraints
Limitation
 
Responsible custodian
Contact for the resource
 
 

Conformance class 3: harmonized

 
 

  Overviews

SVN Toulouse urban Trees classification

  Provided by

  Share on social sites

         

  Views

Read here the full details and access to the data.

  Associated resources

Not available