Mapping the individual trees in urban orchards by incorporating Volunteered Geographic Information and very high resolution optical remotely sensed data

A template matching-based approach

Hossein Vahidi, Brian Klinkenberg, Brian A. Johnson, L. Monika Moskal, Wanglin Yan

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents a collective sensing approach that integrates imperfect Volunteered Geographic Information (VGI) obtained through Citizen Science (CS) tree mapping projects with very high resolution (VHR) optical remotely sensed data for low-cost, fine-scale, and accurate mapping of trees in urban orchards. To this end, an individual tree crown (ITC) detection technique utilizing template matching (TM) was developed for extracting urban orchard trees from VHR optical imagery. To provide the training samples for the TM algorithm, remotely sensed VGI about trees including the crowdsourced data about ITC locations and their crown diameters was adopted in this study. A data quality assessment of the proposed approach in the study area demonstrated that the detected trees had a very high degree of completeness (92.7%), a high thematic accuracy (false discovery rate (FDR) = 0.090, false negative rate (FNR) = 0.073, and F1 score (F1) = 0.918), and a fair positional accuracy (root mean square error (RMSE) = 1.02 m). Overall, the proposed approach based on the crowdsourced training samples generally demonstrated a promising ITC detection performance in our pilot project.

Original languageEnglish
Article number1134
JournalRemote Sensing
Volume10
Issue number7
DOIs
Publication statusPublished - 2018 Jul 1

Fingerprint

orchard
data quality
imagery
cost

Keywords

  • Collective sensing
  • Data quality
  • Individual tree detection
  • Template matching
  • Urban orchard
  • Very high resolution imagery
  • Volunteered geographic information

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)

Cite this

Mapping the individual trees in urban orchards by incorporating Volunteered Geographic Information and very high resolution optical remotely sensed data : A template matching-based approach. / Vahidi, Hossein; Klinkenberg, Brian; Johnson, Brian A.; Moskal, L. Monika; Yan, Wanglin.

In: Remote Sensing, Vol. 10, No. 7, 1134, 01.07.2018.

Research output: Contribution to journalArticle

@article{4afe80ff61bb4e2dbdbb56d6ff26940a,
title = "Mapping the individual trees in urban orchards by incorporating Volunteered Geographic Information and very high resolution optical remotely sensed data: A template matching-based approach",
abstract = "This paper presents a collective sensing approach that integrates imperfect Volunteered Geographic Information (VGI) obtained through Citizen Science (CS) tree mapping projects with very high resolution (VHR) optical remotely sensed data for low-cost, fine-scale, and accurate mapping of trees in urban orchards. To this end, an individual tree crown (ITC) detection technique utilizing template matching (TM) was developed for extracting urban orchard trees from VHR optical imagery. To provide the training samples for the TM algorithm, remotely sensed VGI about trees including the crowdsourced data about ITC locations and their crown diameters was adopted in this study. A data quality assessment of the proposed approach in the study area demonstrated that the detected trees had a very high degree of completeness (92.7{\%}), a high thematic accuracy (false discovery rate (FDR) = 0.090, false negative rate (FNR) = 0.073, and F1 score (F1) = 0.918), and a fair positional accuracy (root mean square error (RMSE) = 1.02 m). Overall, the proposed approach based on the crowdsourced training samples generally demonstrated a promising ITC detection performance in our pilot project.",
keywords = "Collective sensing, Data quality, Individual tree detection, Template matching, Urban orchard, Very high resolution imagery, Volunteered geographic information",
author = "Hossein Vahidi and Brian Klinkenberg and Johnson, {Brian A.} and Moskal, {L. Monika} and Wanglin Yan",
year = "2018",
month = "7",
day = "1",
doi = "10.3390/rs10071134",
language = "English",
volume = "10",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "7",

}

TY - JOUR

T1 - Mapping the individual trees in urban orchards by incorporating Volunteered Geographic Information and very high resolution optical remotely sensed data

T2 - A template matching-based approach

AU - Vahidi, Hossein

AU - Klinkenberg, Brian

AU - Johnson, Brian A.

AU - Moskal, L. Monika

AU - Yan, Wanglin

PY - 2018/7/1

Y1 - 2018/7/1

N2 - This paper presents a collective sensing approach that integrates imperfect Volunteered Geographic Information (VGI) obtained through Citizen Science (CS) tree mapping projects with very high resolution (VHR) optical remotely sensed data for low-cost, fine-scale, and accurate mapping of trees in urban orchards. To this end, an individual tree crown (ITC) detection technique utilizing template matching (TM) was developed for extracting urban orchard trees from VHR optical imagery. To provide the training samples for the TM algorithm, remotely sensed VGI about trees including the crowdsourced data about ITC locations and their crown diameters was adopted in this study. A data quality assessment of the proposed approach in the study area demonstrated that the detected trees had a very high degree of completeness (92.7%), a high thematic accuracy (false discovery rate (FDR) = 0.090, false negative rate (FNR) = 0.073, and F1 score (F1) = 0.918), and a fair positional accuracy (root mean square error (RMSE) = 1.02 m). Overall, the proposed approach based on the crowdsourced training samples generally demonstrated a promising ITC detection performance in our pilot project.

AB - This paper presents a collective sensing approach that integrates imperfect Volunteered Geographic Information (VGI) obtained through Citizen Science (CS) tree mapping projects with very high resolution (VHR) optical remotely sensed data for low-cost, fine-scale, and accurate mapping of trees in urban orchards. To this end, an individual tree crown (ITC) detection technique utilizing template matching (TM) was developed for extracting urban orchard trees from VHR optical imagery. To provide the training samples for the TM algorithm, remotely sensed VGI about trees including the crowdsourced data about ITC locations and their crown diameters was adopted in this study. A data quality assessment of the proposed approach in the study area demonstrated that the detected trees had a very high degree of completeness (92.7%), a high thematic accuracy (false discovery rate (FDR) = 0.090, false negative rate (FNR) = 0.073, and F1 score (F1) = 0.918), and a fair positional accuracy (root mean square error (RMSE) = 1.02 m). Overall, the proposed approach based on the crowdsourced training samples generally demonstrated a promising ITC detection performance in our pilot project.

KW - Collective sensing

KW - Data quality

KW - Individual tree detection

KW - Template matching

KW - Urban orchard

KW - Very high resolution imagery

KW - Volunteered geographic information

UR - http://www.scopus.com/inward/record.url?scp=85050477098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050477098&partnerID=8YFLogxK

U2 - 10.3390/rs10071134

DO - 10.3390/rs10071134

M3 - Article

VL - 10

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 7

M1 - 1134

ER -