Urban tree detection and species classification using aerial imagery

Mahdi Maktab Dar Oghaz; Lakshmi Babu Saheer; Javad Zarrin

doi:10.1007/978-3-031-10464-0_32

Urban tree detection and species classification using aerial imagery

Mahdi Maktab Dar Oghaz^*, Lakshmi Babu Saheer, Javad Zarrin

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Trees are essential for climate change adaptation or even mitigation to some extent. To leverage their potential, effective forest and urban tree management is required. Automated tree detection, localisation, and species classification are crucial to any forest and urban tree management plan. Over the last decade, many studies aimed at tree species classification using aerial imagery yet due to several environmental challenges results were sub-optimal. This study aims to contribute to this domain by first, generating a labelled tree species dataset using Google Maps static API to supply aerial images and Trees In Camden inventory to supply species information, GPS coordinates (Latitude and Longitude), and tree diameter. Furthermore, this study investigates how state-of-the-art deep Convolutional Neural Network models including VGG19, ResNet50, DenseNet121, and InceptionV3 can handle the species classification problem of the urban trees using aerial images. Experimental results show our best model, InceptionV3 achieves an average accuracy of 73.54 over 6 tree species.

Original language	English
Title of host publication	Intelligent Computing
Subtitle of host publication	Proceedings of the 2022 Computing Conference
Editors	Kohei Arai
Place of Publication	Cham
Publisher	Springer International Publishing AG
Pages	469-483
Number of pages	15
Volume	2
ISBN (Electronic)	9783031104640
ISBN (Print)	9783031104633
DOIs	https://doi.org/10.1007/978-3-031-10464-0_32
Publication status	Published - 7 Jul 2022
Externally published	Yes
Event	Computing Conference 2022 - Virtual, United Kingdom Duration: 14 Jul 2022 → 15 Jul 2022 https://saiconference.com/Conferences/Computing2022

Publication series

Name	Lecture Notes in Networks and Systems
Publisher	Springer
Volume	507
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	Computing Conference 2022
Country/Territory	United Kingdom
Period	14/07/22 → 15/07/22
Internet address	https://saiconference.com/Conferences/Computing2022

Keywords

Urban tree detection
Convolutional neural network
Aerial imagery

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-031-10464-0_32

Embargoed Document

Zarrin_UrbanTreeDetection_Accepted_2022
Accepted author manuscript, 1.61 MB
Embargo ends: 7/07/23

Cite this

@inproceedings{f5a19f9a542d4b9d8bca0a12db620cfc,

title = "Urban tree detection and species classification using aerial imagery",

abstract = "Trees are essential for climate change adaptation or even mitigation to some extent. To leverage their potential, effective forest and urban tree management is required. Automated tree detection, localisation, and species classification are crucial to any forest and urban tree management plan. Over the last decade, many studies aimed at tree species classification using aerial imagery yet due to several environmental challenges results were sub-optimal. This study aims to contribute to this domain by first, generating a labelled tree species dataset using Google Maps static API to supply aerial images and Trees In Camden inventory to supply species information, GPS coordinates (Latitude and Longitude), and tree diameter. Furthermore, this study investigates how state-of-the-art deep Convolutional Neural Network models including VGG19, ResNet50, DenseNet121, and InceptionV3 can handle the species classification problem of the urban trees using aerial images. Experimental results show our best model, InceptionV3 achieves an average accuracy of 73.54 over 6 tree species.",

author = "Oghaz, {Mahdi Maktab Dar} and Saheer, {Lakshmi Babu} and Javad Zarrin",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Computing Conference 2022 ; Conference date: 14-07-2022 Through 15-07-2022",

year = "2022",

month = jul,

day = "7",

doi = "10.1007/978-3-031-10464-0_32",

language = "English",

isbn = "9783031104633",

volume = "2",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer International Publishing AG",

pages = "469--483",

editor = "Kohei Arai",

booktitle = "Intelligent Computing",

address = "Switzerland",

url = "https://saiconference.com/Conferences/Computing2022",

}

Oghaz, MMD, Saheer, LB & Zarrin, J 2022, Urban tree detection and species classification using aerial imagery. in K Arai (ed.), Intelligent Computing: Proceedings of the 2022 Computing Conference. vol. 2, Lecture Notes in Networks and Systems, vol. 507, Springer International Publishing AG, Cham, pp. 469-483, Computing Conference 2022, United Kingdom, 14/07/22. https://doi.org/10.1007/978-3-031-10464-0_32

Urban tree detection and species classification using aerial imagery. / Oghaz, Mahdi Maktab Dar; Saheer, Lakshmi Babu; Zarrin, Javad.
Intelligent Computing: Proceedings of the 2022 Computing Conference. ed. / Kohei Arai. Vol. 2 Cham: Springer International Publishing AG, 2022. p. 469-483 (Lecture Notes in Networks and Systems; Vol. 507).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Urban tree detection and species classification using aerial imagery

AU - Oghaz, Mahdi Maktab Dar

AU - Saheer, Lakshmi Babu

AU - Zarrin, Javad

PY - 2022/7/7

Y1 - 2022/7/7

N2 - Trees are essential for climate change adaptation or even mitigation to some extent. To leverage their potential, effective forest and urban tree management is required. Automated tree detection, localisation, and species classification are crucial to any forest and urban tree management plan. Over the last decade, many studies aimed at tree species classification using aerial imagery yet due to several environmental challenges results were sub-optimal. This study aims to contribute to this domain by first, generating a labelled tree species dataset using Google Maps static API to supply aerial images and Trees In Camden inventory to supply species information, GPS coordinates (Latitude and Longitude), and tree diameter. Furthermore, this study investigates how state-of-the-art deep Convolutional Neural Network models including VGG19, ResNet50, DenseNet121, and InceptionV3 can handle the species classification problem of the urban trees using aerial images. Experimental results show our best model, InceptionV3 achieves an average accuracy of 73.54 over 6 tree species.

AB - Trees are essential for climate change adaptation or even mitigation to some extent. To leverage their potential, effective forest and urban tree management is required. Automated tree detection, localisation, and species classification are crucial to any forest and urban tree management plan. Over the last decade, many studies aimed at tree species classification using aerial imagery yet due to several environmental challenges results were sub-optimal. This study aims to contribute to this domain by first, generating a labelled tree species dataset using Google Maps static API to supply aerial images and Trees In Camden inventory to supply species information, GPS coordinates (Latitude and Longitude), and tree diameter. Furthermore, this study investigates how state-of-the-art deep Convolutional Neural Network models including VGG19, ResNet50, DenseNet121, and InceptionV3 can handle the species classification problem of the urban trees using aerial images. Experimental results show our best model, InceptionV3 achieves an average accuracy of 73.54 over 6 tree species.

U2 - 10.1007/978-3-031-10464-0_32

DO - 10.1007/978-3-031-10464-0_32

M3 - Conference contribution

SN - 9783031104633

VL - 2

T3 - Lecture Notes in Networks and Systems

SP - 469

EP - 483

BT - Intelligent Computing

A2 - Arai, Kohei

PB - Springer International Publishing AG

CY - Cham

T2 - Computing Conference 2022

Y2 - 14 July 2022 through 15 July 2022

ER -