Application of LiDAR's multiple attributes for wetland classification

Qiong Ding; Shengyue Ji; Wu Chen

doi:10.1117/12.2234678

Application of LiDAR's multiple attributes for wetland classification

Qiong Ding, Shengyue Ji, Wu Chen

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

Wetlands have received intensive interdisciplinary attention as a unique ecosystem and valuable resources. As a new technology, the airborne LiDAR system has been applied in wetland research these years. However, most of the studies used only one or two LiDAR observations to extract either terrain or vegetation in wetlands. This research aims at integrating LiDAR's multiple attributes (DSM, DTM, off-ground features, Slop map, multiple pulse returns, and normalized intensity) to improve mapping and classification of wetlands based on a multi-level object-oriented classification method. By using this method, we are able to classify the Yellow River Delta wetland into eight classes with overall classification accuracy of 92.5%

Original language	English
Title of host publication	2nd ISPRS International Conference on Computer Vision in Remote Sensing, CVRS 2015
Publisher	SPIE
Volume	9901
ISBN (Electronic)	9781510601543
DOIs	https://doi.org/10.1117/12.2234678
Publication status	Published - 1 Jan 2016
Event	2nd ISPRS International Conference on Computer Vision in Remote Sensing, CVRS 2015 - Xiamen, China Duration: 28 Apr 2015 → 30 Apr 2015

Conference

Conference	2nd ISPRS International Conference on Computer Vision in Remote Sensing, CVRS 2015
Country/Territory	China
City	Xiamen
Period	28/04/15 → 30/04/15

Keywords

accuracy
classification
LiDAR
multiple attributes
wetlands

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

More information

10.1117/12.2234678

Cite this

@inproceedings{efd53cd47f754479857e4f43b3e2043d,

title = "Application of LiDAR's multiple attributes for wetland classification",

abstract = "Wetlands have received intensive interdisciplinary attention as a unique ecosystem and valuable resources. As a new technology, the airborne LiDAR system has been applied in wetland research these years. However, most of the studies used only one or two LiDAR observations to extract either terrain or vegetation in wetlands. This research aims at integrating LiDAR's multiple attributes (DSM, DTM, off-ground features, Slop map, multiple pulse returns, and normalized intensity) to improve mapping and classification of wetlands based on a multi-level object-oriented classification method. By using this method, we are able to classify the Yellow River Delta wetland into eight classes with overall classification accuracy of 92.5%",

keywords = "accuracy, classification, LiDAR, multiple attributes, wetlands",

author = "Qiong Ding and Shengyue Ji and Wu Chen",

year = "2016",

month = jan,

day = "1",

doi = "10.1117/12.2234678",

language = "English",

volume = "9901",

booktitle = "2nd ISPRS International Conference on Computer Vision in Remote Sensing, CVRS 2015",

publisher = "SPIE",

address = "United States",

note = "2nd ISPRS International Conference on Computer Vision in Remote Sensing, CVRS 2015 ; Conference date: 28-04-2015 Through 30-04-2015",

}

Application of LiDAR's multiple attributes for wetland classification. / Ding, Qiong; Ji, Shengyue; Chen, Wu.

2nd ISPRS International Conference on Computer Vision in Remote Sensing, CVRS 2015. Vol. 9901 SPIE, 2016. 990110.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Application of LiDAR's multiple attributes for wetland classification

AU - Ding, Qiong

AU - Ji, Shengyue

AU - Chen, Wu

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Wetlands have received intensive interdisciplinary attention as a unique ecosystem and valuable resources. As a new technology, the airborne LiDAR system has been applied in wetland research these years. However, most of the studies used only one or two LiDAR observations to extract either terrain or vegetation in wetlands. This research aims at integrating LiDAR's multiple attributes (DSM, DTM, off-ground features, Slop map, multiple pulse returns, and normalized intensity) to improve mapping and classification of wetlands based on a multi-level object-oriented classification method. By using this method, we are able to classify the Yellow River Delta wetland into eight classes with overall classification accuracy of 92.5%

AB - Wetlands have received intensive interdisciplinary attention as a unique ecosystem and valuable resources. As a new technology, the airborne LiDAR system has been applied in wetland research these years. However, most of the studies used only one or two LiDAR observations to extract either terrain or vegetation in wetlands. This research aims at integrating LiDAR's multiple attributes (DSM, DTM, off-ground features, Slop map, multiple pulse returns, and normalized intensity) to improve mapping and classification of wetlands based on a multi-level object-oriented classification method. By using this method, we are able to classify the Yellow River Delta wetland into eight classes with overall classification accuracy of 92.5%

KW - accuracy

KW - classification

KW - LiDAR

KW - multiple attributes

KW - wetlands

UR - http://www.scopus.com/inward/record.url?scp=84983372439&partnerID=8YFLogxK

U2 - 10.1117/12.2234678

DO - 10.1117/12.2234678

M3 - Conference article published in proceeding or book

VL - 9901

BT - 2nd ISPRS International Conference on Computer Vision in Remote Sensing, CVRS 2015

PB - SPIE

T2 - 2nd ISPRS International Conference on Computer Vision in Remote Sensing, CVRS 2015

Y2 - 28 April 2015 through 30 April 2015

ER -

Application of LiDAR's multiple attributes for wetland classification

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Cite this