Individual tree detection and counting based on high-resolution imagery and the canopy height model data

Individual Tree Detection-and-Counting (ITDC) is among the important tasks in town areas, and numerous methods are proposed in this direction. Despite their many advantages, still, the proposed methods are inadequate to provide robust results because they mostly rely on the direct field investigatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Ye Zhang, Moyang Wang, Joseph Mango, Liang Xin, Chen Meng, Xiang Li
Format: Article
Language:English
Published: Taylor & Francis Group 2024-11-01
Series:Geo-spatial Information Science
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/10095020.2023.2299146
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846127695075737600
author Ye Zhang
Moyang Wang
Joseph Mango
Liang Xin
Chen Meng
Xiang Li
author_facet Ye Zhang
Moyang Wang
Joseph Mango
Liang Xin
Chen Meng
Xiang Li
author_sort Ye Zhang
collection DOAJ
description Individual Tree Detection-and-Counting (ITDC) is among the important tasks in town areas, and numerous methods are proposed in this direction. Despite their many advantages, still, the proposed methods are inadequate to provide robust results because they mostly rely on the direct field investigations. This paper presents a novel approach involving high-resolution imagery and the Canopy-Height-Model (CHM) data to solve the ITDC problem. The new approach is studied in six urban scenes: farmland, woodland, park, industrial land, road and residential areas. First, it identifies tree canopy regions using a deep learning network from high-resolution imagery. It then deploys the CHM-data to detect treetops of the canopy regions using a local maximum algorithm and individual tree canopies using the region growing. Finally, it calculates and describes the number of individual trees and tree canopies. The proposed approach is experimented with the data from Shanghai, China. Our results show that the individual tree detection method had an average overall accuracy of 0.953, with a precision of 0.987 for woodland scene. Meanwhile, the R2 value for canopy segmentation in different urban scenes is greater than 0.780 and 0.779 for canopy area and diameter size, respectively. These results confirm that the proposed method is robust enough for urban tree planning and management.
format Article
id doaj-art-cd3cd0209f9547dda8a79f0c76b24e03
institution Kabale University
issn 1009-5020
1993-5153
language English
publishDate 2024-11-01
publisher Taylor & Francis Group
record_format Article
series Geo-spatial Information Science
spelling doaj-art-cd3cd0209f9547dda8a79f0c76b24e032024-12-11T11:57:33ZengTaylor & Francis GroupGeo-spatial Information Science1009-50201993-51532024-11-012762162217810.1080/10095020.2023.2299146Individual tree detection and counting based on high-resolution imagery and the canopy height model dataYe Zhang0Moyang Wang1Joseph Mango2Liang Xin3Chen Meng4Xiang Li5Key Laboratory of Geographic Information Science (Ministry of Education) and School of Geographic Sciences, East China Normal University, Shanghai, ChinaKey Laboratory of Geographic Information Science (Ministry of Education) and School of Geographic Sciences, East China Normal University, Shanghai, ChinaDepartment of Transportation and Geotechnical Engineering, University of Dar es Salaam, Dar es salaam, TanzaniaCollege of Surveying and Geographic Informatics, Tongji University, Shanghai, ChinaSchool of Ecology and Environmental Sciences, East China Normal University, Shanghai, ChinaKey Laboratory of Geographic Information Science (Ministry of Education) and School of Geographic Sciences, East China Normal University, Shanghai, ChinaIndividual Tree Detection-and-Counting (ITDC) is among the important tasks in town areas, and numerous methods are proposed in this direction. Despite their many advantages, still, the proposed methods are inadequate to provide robust results because they mostly rely on the direct field investigations. This paper presents a novel approach involving high-resolution imagery and the Canopy-Height-Model (CHM) data to solve the ITDC problem. The new approach is studied in six urban scenes: farmland, woodland, park, industrial land, road and residential areas. First, it identifies tree canopy regions using a deep learning network from high-resolution imagery. It then deploys the CHM-data to detect treetops of the canopy regions using a local maximum algorithm and individual tree canopies using the region growing. Finally, it calculates and describes the number of individual trees and tree canopies. The proposed approach is experimented with the data from Shanghai, China. Our results show that the individual tree detection method had an average overall accuracy of 0.953, with a precision of 0.987 for woodland scene. Meanwhile, the R2 value for canopy segmentation in different urban scenes is greater than 0.780 and 0.779 for canopy area and diameter size, respectively. These results confirm that the proposed method is robust enough for urban tree planning and management.https://www.tandfonline.com/doi/10.1080/10095020.2023.2299146Individual tree detection-and-counting (ITDC)deep learninghigh-resolution imageryCanopy Height Model data (CHM)
spellingShingle Ye Zhang
Moyang Wang
Joseph Mango
Liang Xin
Chen Meng
Xiang Li
Individual tree detection and counting based on high-resolution imagery and the canopy height model data
Geo-spatial Information Science
Individual tree detection-and-counting (ITDC)
deep learning
high-resolution imagery
Canopy Height Model data (CHM)
title Individual tree detection and counting based on high-resolution imagery and the canopy height model data
title_full Individual tree detection and counting based on high-resolution imagery and the canopy height model data
title_fullStr Individual tree detection and counting based on high-resolution imagery and the canopy height model data
title_full_unstemmed Individual tree detection and counting based on high-resolution imagery and the canopy height model data
title_short Individual tree detection and counting based on high-resolution imagery and the canopy height model data
title_sort individual tree detection and counting based on high resolution imagery and the canopy height model data
topic Individual tree detection-and-counting (ITDC)
deep learning
high-resolution imagery
Canopy Height Model data (CHM)
url https://www.tandfonline.com/doi/10.1080/10095020.2023.2299146
work_keys_str_mv AT yezhang individualtreedetectionandcountingbasedonhighresolutionimageryandthecanopyheightmodeldata
AT moyangwang individualtreedetectionandcountingbasedonhighresolutionimageryandthecanopyheightmodeldata
AT josephmango individualtreedetectionandcountingbasedonhighresolutionimageryandthecanopyheightmodeldata
AT liangxin individualtreedetectionandcountingbasedonhighresolutionimageryandthecanopyheightmodeldata
AT chenmeng individualtreedetectionandcountingbasedonhighresolutionimageryandthecanopyheightmodeldata
AT xiangli individualtreedetectionandcountingbasedonhighresolutionimageryandthecanopyheightmodeldata