Wetland mapping by fusion of airborne laser scanning and multi-temporal multispectral satellite imagery

Maha Shadaydeh, András Zlinszky, Andrea Manno-Kovacs, T. Szirányi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Wetlands play a major role in Europe’s biodiversity. Despite their importance, wetlands are suffering from constant degradation and loss, therefore, they require constant monitoring. This article presents an automatic method for the mapping and monitoring of wetlands based on the fused processing of laser scans and multispectral satellite imagery, with validations and evaluations performed over an area of Lake Balaton in Hungary. Markov Random Field models have already been shown to successfully integrate various image properties in several remote sensing applications. In this article, we propose the multi-layer fusion Markov Random Field model for classifying wetland areas, built into an automatic classification process that combines multi-temporal multispectral images with a wetland classification reference map derived from airborne laser scanning (ALS) data acquired in an earlier year. Using an ALS-based wetland classification map that relied on a limited amount of ground truthing proved to improve the discrimination of land-cover classes with similar spectral characteristics. Based on the produced classifications, we also present an unsupervised method to track temporal changes of wetland areas by comparing the class labellings of different time layers. During the evaluations, the classification model is validated against manually interpreted independent aerial orthoimages. The results show that the proposed fusion model performs better than solely image-based processing, producing a non-supervised/semi-supervised wetland classification accuracy of 81–93% observed over different years.

Original languageEnglish
Pages (from-to)7422-7440
Number of pages19
JournalInternational Journal of Remote Sensing
Volume38
Issue number23
DOIs
Publication statusPublished - Dec 2 2017

Fingerprint

satellite imagery
laser
wetland
multispectral image
monitoring
land cover
biodiversity
remote sensing
lake

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)

Cite this

Wetland mapping by fusion of airborne laser scanning and multi-temporal multispectral satellite imagery. / Shadaydeh, Maha; Zlinszky, András; Manno-Kovacs, Andrea; Szirányi, T.

In: International Journal of Remote Sensing, Vol. 38, No. 23, 02.12.2017, p. 7422-7440.

Research output: Contribution to journalArticle

Shadaydeh, Maha ; Zlinszky, András ; Manno-Kovacs, Andrea ; Szirányi, T. / Wetland mapping by fusion of airborne laser scanning and multi-temporal multispectral satellite imagery. In: International Journal of Remote Sensing. 2017 ; Vol. 38, No. 23. pp. 7422-7440.
@article{7defff619b2b4b3285edca63599a3cd1,
title = "Wetland mapping by fusion of airborne laser scanning and multi-temporal multispectral satellite imagery",
abstract = "Wetlands play a major role in Europe’s biodiversity. Despite their importance, wetlands are suffering from constant degradation and loss, therefore, they require constant monitoring. This article presents an automatic method for the mapping and monitoring of wetlands based on the fused processing of laser scans and multispectral satellite imagery, with validations and evaluations performed over an area of Lake Balaton in Hungary. Markov Random Field models have already been shown to successfully integrate various image properties in several remote sensing applications. In this article, we propose the multi-layer fusion Markov Random Field model for classifying wetland areas, built into an automatic classification process that combines multi-temporal multispectral images with a wetland classification reference map derived from airborne laser scanning (ALS) data acquired in an earlier year. Using an ALS-based wetland classification map that relied on a limited amount of ground truthing proved to improve the discrimination of land-cover classes with similar spectral characteristics. Based on the produced classifications, we also present an unsupervised method to track temporal changes of wetland areas by comparing the class labellings of different time layers. During the evaluations, the classification model is validated against manually interpreted independent aerial orthoimages. The results show that the proposed fusion model performs better than solely image-based processing, producing a non-supervised/semi-supervised wetland classification accuracy of 81–93{\%} observed over different years.",
author = "Maha Shadaydeh and Andr{\'a}s Zlinszky and Andrea Manno-Kovacs and T. Szir{\'a}nyi",
year = "2017",
month = "12",
day = "2",
doi = "10.1080/01431161.2017.1375614",
language = "English",
volume = "38",
pages = "7422--7440",
journal = "International Joural of Remote Sensing",
issn = "0143-1161",
publisher = "Taylor and Francis Ltd.",
number = "23",

}

TY - JOUR

T1 - Wetland mapping by fusion of airborne laser scanning and multi-temporal multispectral satellite imagery

AU - Shadaydeh, Maha

AU - Zlinszky, András

AU - Manno-Kovacs, Andrea

AU - Szirányi, T.

PY - 2017/12/2

Y1 - 2017/12/2

N2 - Wetlands play a major role in Europe’s biodiversity. Despite their importance, wetlands are suffering from constant degradation and loss, therefore, they require constant monitoring. This article presents an automatic method for the mapping and monitoring of wetlands based on the fused processing of laser scans and multispectral satellite imagery, with validations and evaluations performed over an area of Lake Balaton in Hungary. Markov Random Field models have already been shown to successfully integrate various image properties in several remote sensing applications. In this article, we propose the multi-layer fusion Markov Random Field model for classifying wetland areas, built into an automatic classification process that combines multi-temporal multispectral images with a wetland classification reference map derived from airborne laser scanning (ALS) data acquired in an earlier year. Using an ALS-based wetland classification map that relied on a limited amount of ground truthing proved to improve the discrimination of land-cover classes with similar spectral characteristics. Based on the produced classifications, we also present an unsupervised method to track temporal changes of wetland areas by comparing the class labellings of different time layers. During the evaluations, the classification model is validated against manually interpreted independent aerial orthoimages. The results show that the proposed fusion model performs better than solely image-based processing, producing a non-supervised/semi-supervised wetland classification accuracy of 81–93% observed over different years.

AB - Wetlands play a major role in Europe’s biodiversity. Despite their importance, wetlands are suffering from constant degradation and loss, therefore, they require constant monitoring. This article presents an automatic method for the mapping and monitoring of wetlands based on the fused processing of laser scans and multispectral satellite imagery, with validations and evaluations performed over an area of Lake Balaton in Hungary. Markov Random Field models have already been shown to successfully integrate various image properties in several remote sensing applications. In this article, we propose the multi-layer fusion Markov Random Field model for classifying wetland areas, built into an automatic classification process that combines multi-temporal multispectral images with a wetland classification reference map derived from airborne laser scanning (ALS) data acquired in an earlier year. Using an ALS-based wetland classification map that relied on a limited amount of ground truthing proved to improve the discrimination of land-cover classes with similar spectral characteristics. Based on the produced classifications, we also present an unsupervised method to track temporal changes of wetland areas by comparing the class labellings of different time layers. During the evaluations, the classification model is validated against manually interpreted independent aerial orthoimages. The results show that the proposed fusion model performs better than solely image-based processing, producing a non-supervised/semi-supervised wetland classification accuracy of 81–93% observed over different years.

UR - http://www.scopus.com/inward/record.url?scp=85050700739&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050700739&partnerID=8YFLogxK

U2 - 10.1080/01431161.2017.1375614

DO - 10.1080/01431161.2017.1375614

M3 - Article

AN - SCOPUS:85050700739

VL - 38

SP - 7422

EP - 7440

JO - International Joural of Remote Sensing

JF - International Joural of Remote Sensing

SN - 0143-1161

IS - 23

ER -