Multitemporal Very High Resolution From Space: Outcome of the 2016 IEEE GRSS Data Fusion Contest

L. Mou, X. Zhu, M. Vakalopoulou, K. Karantzalos, N. Paragios, B. Le Saux, G. Moser, D. Tuia

Research output: Contribution to journalArticleAcademicpeer-review

21 Citations (Scopus)

Abstract

In this paper, the scientific outcomes of the 2016 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society are discussed. The 2016 Contest was an open topic competition based on a multitemporal and multimodal dataset, which included a temporal pair of very high resolution panchromatic and multispectral Deimos-2 images and a video captured by the Iris camera on-board the International Space Station. The problems addressed and the techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and mixed ideas and methodologies from the remote sensing, video processing, and computer vision. In particular, the winning team developed a deep learning method to jointly address spatial scene labeling and temporal activity modeling using the available image and video data. The second place team proposed a random field model to simultaneously perform coregistration of multitemporal data, semantic segmentation, and change detection. The methodological key ideas of both these approaches and the main results of the corresponding experimental validation are discussed in this paper.
Original languageEnglish
Pages (from-to)3435-3447
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume10
Issue number8
DOIs
Publication statusPublished - 1 Aug 2017

Fingerprint

Data fusion
Remote sensing
Space stations
Labeling
Image analysis
Computer vision
Semantics
Cameras
remote sensing
computer vision
Processing
image analysis
segmentation
learning
methodology
modeling
video
Deep learning

Cite this

Mou, L. ; Zhu, X. ; Vakalopoulou, M. ; Karantzalos, K. ; Paragios, N. ; Le Saux, B. ; Moser, G. ; Tuia, D. / Multitemporal Very High Resolution From Space: Outcome of the 2016 IEEE GRSS Data Fusion Contest. In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2017 ; Vol. 10, No. 8. pp. 3435-3447.
@article{3400e2d4e67549b5a1c3567c3eb84f49,
title = "Multitemporal Very High Resolution From Space: Outcome of the 2016 IEEE GRSS Data Fusion Contest",
abstract = "In this paper, the scientific outcomes of the 2016 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society are discussed. The 2016 Contest was an open topic competition based on a multitemporal and multimodal dataset, which included a temporal pair of very high resolution panchromatic and multispectral Deimos-2 images and a video captured by the Iris camera on-board the International Space Station. The problems addressed and the techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and mixed ideas and methodologies from the remote sensing, video processing, and computer vision. In particular, the winning team developed a deep learning method to jointly address spatial scene labeling and temporal activity modeling using the available image and video data. The second place team proposed a random field model to simultaneously perform coregistration of multitemporal data, semantic segmentation, and change detection. The methodological key ideas of both these approaches and the main results of the corresponding experimental validation are discussed in this paper.",
author = "L. Mou and X. Zhu and M. Vakalopoulou and K. Karantzalos and N. Paragios and {Le Saux}, B. and G. Moser and D. Tuia",
year = "2017",
month = "8",
day = "1",
doi = "10.1109/JSTARS.2017.2696823",
language = "English",
volume = "10",
pages = "3435--3447",
journal = "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing",
issn = "1939-1404",
publisher = "Institute of Electrical and Electronics Engineers",
number = "8",

}

Multitemporal Very High Resolution From Space: Outcome of the 2016 IEEE GRSS Data Fusion Contest. / Mou, L.; Zhu, X.; Vakalopoulou, M.; Karantzalos, K.; Paragios, N.; Le Saux, B.; Moser, G.; Tuia, D.

In: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 10, No. 8, 01.08.2017, p. 3435-3447.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Multitemporal Very High Resolution From Space: Outcome of the 2016 IEEE GRSS Data Fusion Contest

AU - Mou, L.

AU - Zhu, X.

AU - Vakalopoulou, M.

AU - Karantzalos, K.

AU - Paragios, N.

AU - Le Saux, B.

AU - Moser, G.

AU - Tuia, D.

PY - 2017/8/1

Y1 - 2017/8/1

N2 - In this paper, the scientific outcomes of the 2016 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society are discussed. The 2016 Contest was an open topic competition based on a multitemporal and multimodal dataset, which included a temporal pair of very high resolution panchromatic and multispectral Deimos-2 images and a video captured by the Iris camera on-board the International Space Station. The problems addressed and the techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and mixed ideas and methodologies from the remote sensing, video processing, and computer vision. In particular, the winning team developed a deep learning method to jointly address spatial scene labeling and temporal activity modeling using the available image and video data. The second place team proposed a random field model to simultaneously perform coregistration of multitemporal data, semantic segmentation, and change detection. The methodological key ideas of both these approaches and the main results of the corresponding experimental validation are discussed in this paper.

AB - In this paper, the scientific outcomes of the 2016 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society are discussed. The 2016 Contest was an open topic competition based on a multitemporal and multimodal dataset, which included a temporal pair of very high resolution panchromatic and multispectral Deimos-2 images and a video captured by the Iris camera on-board the International Space Station. The problems addressed and the techniques proposed by the participants to the Contest spanned across a rather broad range of topics, and mixed ideas and methodologies from the remote sensing, video processing, and computer vision. In particular, the winning team developed a deep learning method to jointly address spatial scene labeling and temporal activity modeling using the available image and video data. The second place team proposed a random field model to simultaneously perform coregistration of multitemporal data, semantic segmentation, and change detection. The methodological key ideas of both these approaches and the main results of the corresponding experimental validation are discussed in this paper.

U2 - 10.1109/JSTARS.2017.2696823

DO - 10.1109/JSTARS.2017.2696823

M3 - Article

VL - 10

SP - 3435

EP - 3447

JO - 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 - 8

ER -