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

Très haute résolution multi-temporelle depuis l'espace : résultats du challenge de fusion de données de l'IEEE GRSS 2016

L. Mou (1) , X. Zhu (1) , M. Vakalopoulou (2) , K. Karantzalos (2) , N. Paragios (3) , B. Le Saux (4) , G. Moser (5) , D. Tuia (6)

1 IMF - DLR Institut für Methodik der Fernerkundung / DLR Remote Sensing Technology Institute
2 NTUA - National Technical University of Athens [Athens]
3 MICS - Mathématiques et Informatique pour la Complexité et les Systèmes
4 ONERA - The French Aerospace Lab [Palaiseau]
5 UniGe - Università degli studi di Genova = University of Genoa
6 UZH - Universität Zürich [Zürich] = University of Zurich

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.

Mots clés: VIDEO FROM SPACE; CONVOLUTIONAL NEURAL NETWORKS (CNN); CHANGE DETECTION; MULTISOURCE; IMAGE ANALYSIS AND DATA FUSION; TRACKING; DEEP LEARNING; RANDOM FIELDS; MULTIMODAL; MULTIRESOLUTION

Mots clés: DETECTION CHANGEMENT; RESEAU NEURONES; ANALYSE IMAGE; FUSION DONNEES

Domaines: Algorithme et structure de données [cs.DS]

L. Mou, X. Zhu, M. Vakalopoulou, K. Karantzalos, N. Paragios, et al.. Multitemporal Very High Resolution From Space: Outcome of the 2016 IEEE GRSS Data Fusion Contest. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10 (8), pp.3435-3447. ⟨10.1109/JSTARS.2017.2696823⟩. ⟨hal-01561333⟩