An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series

C. Pelletier; S. Valero; J. Inglada; G. Dedieu; N. Champion

doi:10.1109/IGARSS.2016.7729863

An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series

C. Pelletier, S. Valero, J. Inglada, G. Dedieu, N. Champion

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

8 Citations (Scopus)

Abstract

New high resolution Satellite Image Time Series (SITS) are becoming crucial to land cover mapping over large areas. Their high temporal resolution will allow to better depict scene dynamics. However, it will also increase the amount of data to process. The classification of these data involves therefore new challenges such as: (1) selecting the best feature set to use as input data, (2) dealing with data variability coming from landscape diversity, and (3) establishing the robustness of existing classifiers over large areas. This work aims at addressing these questions through three different studies. Experimental results are obtained by using SPOT-4 and Landsat-8 SITS.

Original language	English
Title of host publication	2016 IEEE International Geoscience and Remote Sensing Symposium - Proceedings
Subtitle of host publication	July 10–15, 2016 Beijing, China
Editors	Jiancheng Shi, Huadong Guo, Kun-shan Chen
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	3338-3341
Number of pages	4
ISBN (Electronic)	9781509033324
ISBN (Print)	9781509033331
DOIs	https://doi.org/10.1109/IGARSS.2016.7729863
Publication status	Published - 2016
Externally published	Yes
Event	IEEE International Geoscience and Remote Sensing Symposium 2016 - China National Convention Center, Beijing, China Duration: 10 Jul 2016 → 15 Jul 2016 Conference number: 36th https://www2.securecms.com/IGARSS2016/Default.asp http://www.igarss2016.org/ https://ieeexplore.ieee.org/xpl/conhome/7592514/proceeding (Proceedings)

Conference

Conference	IEEE International Geoscience and Remote Sensing Symposium 2016
Abbreviated title	IGARSS 2016
Country/Territory	China
City	Beijing
Period	10/07/16 → 15/07/16
Internet address	https://www2.securecms.com/IGARSS2016/Default.asp http://www.igarss2016.org/ https://ieeexplore.ieee.org/xpl/conhome/7592514/proceeding (Proceedings)

Keywords

Classification
High resolution
Land cover mapping
Random Forest
Satellite Image Time Series

UN SDGs

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

Access to Document

10.1109/IGARSS.2016.7729863

Cite this

Pelletier, C., Valero, S., Inglada, J., Dedieu, G., & Champion, N. (2016). An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series. In J. Shi, H. Guo, & K. Chen (Eds.), 2016 IEEE International Geoscience and Remote Sensing Symposium - Proceedings: July 10–15, 2016 Beijing, China (pp. 3338-3341). Article 7729863 IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IGARSS.2016.7729863

Pelletier, C. ; Valero, S. ; Inglada, J. et al. / An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series. 2016 IEEE International Geoscience and Remote Sensing Symposium - Proceedings: July 10–15, 2016 Beijing, China. editor / Jiancheng Shi ; Huadong Guo ; Kun-shan Chen. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2016. pp. 3338-3341

@inproceedings{334828588ae44ffa892eaa416a4da2e0,

title = "An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series",

abstract = "New high resolution Satellite Image Time Series (SITS) are becoming crucial to land cover mapping over large areas. Their high temporal resolution will allow to better depict scene dynamics. However, it will also increase the amount of data to process. The classification of these data involves therefore new challenges such as: (1) selecting the best feature set to use as input data, (2) dealing with data variability coming from landscape diversity, and (3) establishing the robustness of existing classifiers over large areas. This work aims at addressing these questions through three different studies. Experimental results are obtained by using SPOT-4 and Landsat-8 SITS.",

keywords = "Classification, High resolution, Land cover mapping, Random Forest, Satellite Image Time Series",

author = "C. Pelletier and S. Valero and J. Inglada and G. Dedieu and N. Champion",

year = "2016",

doi = "10.1109/IGARSS.2016.7729863",

language = "English",

isbn = "9781509033331",

pages = "3338--3341",

editor = "Shi, {Jiancheng } and Guo, {Huadong } and Chen, {Kun-shan }",

booktitle = "2016 IEEE International Geoscience and Remote Sensing Symposium - Proceedings",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE International Geoscience and Remote Sensing Symposium 2016, IGARSS 2016 ; Conference date: 10-07-2016 Through 15-07-2016",

url = "https://www2.securecms.com/IGARSS2016/Default.asp, http://www.igarss2016.org/, https://ieeexplore.ieee.org/xpl/conhome/7592514/proceeding",

}

Pelletier, C, Valero, S, Inglada, J, Dedieu, G & Champion, N 2016, An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series. in J Shi, H Guo & K Chen (eds), 2016 IEEE International Geoscience and Remote Sensing Symposium - Proceedings: July 10–15, 2016 Beijing, China., 7729863, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 3338-3341, IEEE International Geoscience and Remote Sensing Symposium 2016, Beijing, China, 10/07/16. https://doi.org/10.1109/IGARSS.2016.7729863

An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series. / Pelletier, C.; Valero, S.; Inglada, J. et al.
2016 IEEE International Geoscience and Remote Sensing Symposium - Proceedings: July 10–15, 2016 Beijing, China. ed. / Jiancheng Shi; Huadong Guo; Kun-shan Chen. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 3338-3341 7729863.

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

TY - GEN

T1 - An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series

AU - Pelletier, C.

AU - Valero, S.

AU - Inglada, J.

AU - Dedieu, G.

AU - Champion, N.

N1 - Conference code: 36th

PY - 2016

Y1 - 2016

N2 - New high resolution Satellite Image Time Series (SITS) are becoming crucial to land cover mapping over large areas. Their high temporal resolution will allow to better depict scene dynamics. However, it will also increase the amount of data to process. The classification of these data involves therefore new challenges such as: (1) selecting the best feature set to use as input data, (2) dealing with data variability coming from landscape diversity, and (3) establishing the robustness of existing classifiers over large areas. This work aims at addressing these questions through three different studies. Experimental results are obtained by using SPOT-4 and Landsat-8 SITS.

AB - New high resolution Satellite Image Time Series (SITS) are becoming crucial to land cover mapping over large areas. Their high temporal resolution will allow to better depict scene dynamics. However, it will also increase the amount of data to process. The classification of these data involves therefore new challenges such as: (1) selecting the best feature set to use as input data, (2) dealing with data variability coming from landscape diversity, and (3) establishing the robustness of existing classifiers over large areas. This work aims at addressing these questions through three different studies. Experimental results are obtained by using SPOT-4 and Landsat-8 SITS.

KW - Classification

KW - High resolution

KW - Land cover mapping

KW - Random Forest

KW - Satellite Image Time Series

UR - http://www.scopus.com/inward/record.url?scp=85007478149&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2016.7729863

DO - 10.1109/IGARSS.2016.7729863

M3 - Conference Paper

AN - SCOPUS:85007478149

SN - 9781509033331

SP - 3338

EP - 3341

BT - 2016 IEEE International Geoscience and Remote Sensing Symposium - Proceedings

A2 - Shi, Jiancheng

A2 - Guo, Huadong

A2 - Chen, Kun-shan

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE International Geoscience and Remote Sensing Symposium 2016

Y2 - 10 July 2016 through 15 July 2016

ER -

Pelletier C, Valero S, Inglada J, Dedieu G, Champion N. An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series. In Shi J, Guo H, Chen K, editors, 2016 IEEE International Geoscience and Remote Sensing Symposium - Proceedings: July 10–15, 2016 Beijing, China. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2016. p. 3338-3341. 7729863 doi: 10.1109/IGARSS.2016.7729863

An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series

Abstract

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Cite this