Semantic classification of urban trees using very high resolution satellite imagery

Dawei Wen, Xin Huang, Hui Liu, Wenzhi Liao, Liangpei Zhang

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

There is an urgent need for urban tree classification, in order to assist with ecological environment protection and provide sustainable development guidance for urban planners. While most of the existing studies have concentrated on tree crown extraction or tree species identification, only a few studies have attempted to conduct semantic classification of urban trees from an urban habitat perspective. The lack of semantic information means that it is difficult to meet the needs of ecological and environmental issues. As such, in this study, a novel three-level (pixel-object-patch) framework for semantic classification of urban trees is proposed to categorize urban trees as park, roadside, and residential-institutional trees. These three categories are cognized and conceptualized by humans and serve as different ecological functions in urban areas. Park is important urban greenery accommodated within recreational and cultural facilities. Roadside and residential-institutional trees are distributed along streets or in neighborhoods. The framework for the semantic classification of urban trees includes the following steps: 1) vegetation information extraction at the pixel level utilizing a spectral vegetation index; 2) vegetation-type classification at the object level employing spectral and textural features; and 3) urban tree classification at the patch level, where a series of metrics related to area, shape, structure, and spatial relationship are considered. Two typical Chinese megacities, Shenzhen and Wuhan, were chosen to demonstrate the applicability and effectiveness of the proposed method. The results reveal that the proposed method can achieve a satisfactory performance, with the overall accuracy reaching 85%. Moreover, the producer's and user's accuracies are generally high for most tree categories (>80%). The further landscape analysis demonstrates some general characteristics of the natural landscape configuration: residential-institutional trees show greater fragmentation and spatial heterogeneity, and park trees show the maximum physical connectedness and aggregation.
LanguageEnglish
Pages1413-1424
Number of pages12
JournalIEEE Journal of Selected Topics in Earth Observation and Remote Sensing
Volume10
Issue number4
DOIs
Publication statusPublished - 20 Jan 2017

Fingerprint

satellite imagery
Satellite imagery
semantics
Semantics
high resolution
Roadsides
Pixels
vegetation
Sustainable development
Agglomeration
pixel
pixels
environment protection
recreational facility
streets
habitats
megacity
general characteristics
vegetation index
environmental issue

Keywords

  • natural landscape
  • very high resolution
  • urban
  • trees
  • semantic classification
  • vegetation mapping
  • remote sensing
  • image resolution
  • geophysical image processing

Cite this

@article{cdaef83ac2c442d99cad99109640d6e0,
title = "Semantic classification of urban trees using very high resolution satellite imagery",
abstract = "There is an urgent need for urban tree classification, in order to assist with ecological environment protection and provide sustainable development guidance for urban planners. While most of the existing studies have concentrated on tree crown extraction or tree species identification, only a few studies have attempted to conduct semantic classification of urban trees from an urban habitat perspective. The lack of semantic information means that it is difficult to meet the needs of ecological and environmental issues. As such, in this study, a novel three-level (pixel-object-patch) framework for semantic classification of urban trees is proposed to categorize urban trees as park, roadside, and residential-institutional trees. These three categories are cognized and conceptualized by humans and serve as different ecological functions in urban areas. Park is important urban greenery accommodated within recreational and cultural facilities. Roadside and residential-institutional trees are distributed along streets or in neighborhoods. The framework for the semantic classification of urban trees includes the following steps: 1) vegetation information extraction at the pixel level utilizing a spectral vegetation index; 2) vegetation-type classification at the object level employing spectral and textural features; and 3) urban tree classification at the patch level, where a series of metrics related to area, shape, structure, and spatial relationship are considered. Two typical Chinese megacities, Shenzhen and Wuhan, were chosen to demonstrate the applicability and effectiveness of the proposed method. The results reveal that the proposed method can achieve a satisfactory performance, with the overall accuracy reaching 85{\%}. Moreover, the producer's and user's accuracies are generally high for most tree categories (>80{\%}). The further landscape analysis demonstrates some general characteristics of the natural landscape configuration: residential-institutional trees show greater fragmentation and spatial heterogeneity, and park trees show the maximum physical connectedness and aggregation.",
keywords = "natural landscape, very high resolution, urban, trees, semantic classification, vegetation mapping, remote sensing, image resolution, geophysical image processing",
author = "Dawei Wen and Xin Huang and Hui Liu and Wenzhi Liao and Liangpei Zhang",
year = "2017",
month = "1",
day = "20",
doi = "10.1109/JSTARS.2016.2645798",
language = "English",
volume = "10",
pages = "1413--1424",
journal = "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing",
issn = "1939-1404",
publisher = "IEEE",
number = "4",

}

Semantic classification of urban trees using very high resolution satellite imagery. / Wen, Dawei; Huang, Xin; Liu, Hui; Liao, Wenzhi; Zhang, Liangpei.

In: IEEE Journal of Selected Topics in Earth Observation and Remote Sensing, Vol. 10, No. 4, 20.01.2017, p. 1413-1424.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Semantic classification of urban trees using very high resolution satellite imagery

AU - Wen, Dawei

AU - Huang, Xin

AU - Liu, Hui

AU - Liao, Wenzhi

AU - Zhang, Liangpei

PY - 2017/1/20

Y1 - 2017/1/20

N2 - There is an urgent need for urban tree classification, in order to assist with ecological environment protection and provide sustainable development guidance for urban planners. While most of the existing studies have concentrated on tree crown extraction or tree species identification, only a few studies have attempted to conduct semantic classification of urban trees from an urban habitat perspective. The lack of semantic information means that it is difficult to meet the needs of ecological and environmental issues. As such, in this study, a novel three-level (pixel-object-patch) framework for semantic classification of urban trees is proposed to categorize urban trees as park, roadside, and residential-institutional trees. These three categories are cognized and conceptualized by humans and serve as different ecological functions in urban areas. Park is important urban greenery accommodated within recreational and cultural facilities. Roadside and residential-institutional trees are distributed along streets or in neighborhoods. The framework for the semantic classification of urban trees includes the following steps: 1) vegetation information extraction at the pixel level utilizing a spectral vegetation index; 2) vegetation-type classification at the object level employing spectral and textural features; and 3) urban tree classification at the patch level, where a series of metrics related to area, shape, structure, and spatial relationship are considered. Two typical Chinese megacities, Shenzhen and Wuhan, were chosen to demonstrate the applicability and effectiveness of the proposed method. The results reveal that the proposed method can achieve a satisfactory performance, with the overall accuracy reaching 85%. Moreover, the producer's and user's accuracies are generally high for most tree categories (>80%). The further landscape analysis demonstrates some general characteristics of the natural landscape configuration: residential-institutional trees show greater fragmentation and spatial heterogeneity, and park trees show the maximum physical connectedness and aggregation.

AB - There is an urgent need for urban tree classification, in order to assist with ecological environment protection and provide sustainable development guidance for urban planners. While most of the existing studies have concentrated on tree crown extraction or tree species identification, only a few studies have attempted to conduct semantic classification of urban trees from an urban habitat perspective. The lack of semantic information means that it is difficult to meet the needs of ecological and environmental issues. As such, in this study, a novel three-level (pixel-object-patch) framework for semantic classification of urban trees is proposed to categorize urban trees as park, roadside, and residential-institutional trees. These three categories are cognized and conceptualized by humans and serve as different ecological functions in urban areas. Park is important urban greenery accommodated within recreational and cultural facilities. Roadside and residential-institutional trees are distributed along streets or in neighborhoods. The framework for the semantic classification of urban trees includes the following steps: 1) vegetation information extraction at the pixel level utilizing a spectral vegetation index; 2) vegetation-type classification at the object level employing spectral and textural features; and 3) urban tree classification at the patch level, where a series of metrics related to area, shape, structure, and spatial relationship are considered. Two typical Chinese megacities, Shenzhen and Wuhan, were chosen to demonstrate the applicability and effectiveness of the proposed method. The results reveal that the proposed method can achieve a satisfactory performance, with the overall accuracy reaching 85%. Moreover, the producer's and user's accuracies are generally high for most tree categories (>80%). The further landscape analysis demonstrates some general characteristics of the natural landscape configuration: residential-institutional trees show greater fragmentation and spatial heterogeneity, and park trees show the maximum physical connectedness and aggregation.

KW - natural landscape

KW - very high resolution

KW - urban

KW - trees

KW - semantic classification

KW - vegetation mapping

KW - remote sensing

KW - image resolution

KW - geophysical image processing

UR - http://hdl.handle.net/1854/LU-8507926

U2 - 10.1109/JSTARS.2016.2645798

DO - 10.1109/JSTARS.2016.2645798

M3 - Article

VL - 10

SP - 1413

EP - 1424

JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

T2 - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

SN - 1939-1404

IS - 4

ER -