IEEE Geoscience and Remote Sensing Magazine - March 2014 - 21

◗ The Moon as a calibration site,
◗ Multi-sensor calibration concepts,
◗ In-Situ measurement requirements and instrumenta-

tion, and
◗ Linking ISIS and CEOS WGCV IVOS Subgroup with
focus on operational IS related calibration/validation
and institutional requirements.

◗ ISO standards and their relevance and linkage and ISIS

community's potential contribution.
Details on this workshop will be discussed before
IGARSS 2014 with the contributors to the calibration and validation session and iterated with all
participants at the planned ISIS discussion forum at
the conference.

Gabriele Moser, University of Genoa, Italy
Devis Tuia, Ecole Polytechnique Fédérale de Lausanne, Switzerland
Michal shiMoni, Royal Military Academy, Brussels, Belgium

2014 IEEE GRSS Data Fusion Contest: Multiresolution
Fusion of Thermal Hyperspectral and VIS Data
I. INTRODUCTION
he 2014 Data Fusion Contest, organized by the Image
Analysis and Data Fusion (IADF) Technical Committee of the IEEE Geoscience and Remote
Sensing Society (GRSS), aims at providing
a challenging image analysis opportunity,
including multiresolution and multisensor
fusion, very high resolution imagery, and
a type of remote sensing data source previously not seen in past Data Fusion Contests. The 2014 Contest involves two datasets acquired at different spectral ranges
and spatial resolutions: a coarser-resolution long-wave infrared (LWIR, thermal
infrared) hyperspectral data set and fineresolution data acquired in the visible (VIS) wavelength
range. The former is acquired by an 84-channel imager
that covers the wavelengths between 7.8 to 11.5 µm with
approximately one-meter spatial resolution. The latter is a
series of color images acquired during separate flight-lines
with approximately 20-cm spatial resolution. The two data
sources cover an urban area near Thetford Mines in Québec, Canada (see Fig. 1), and were acquired and were provided for the Contest by Telops Inc. (Canada).
The 2014 Data Fusion Contest has been framed as two
parallel competitions: the Classification Contest and the
Paper Contest. The Classification Contest took place in
the past weeks, while the Paper Contest is currently open
to the international community of remote sensing.

Digital Object Identifier 10.1109/MGRS.2014.2303201
Date of publication: 8 April 2014

march 2014

ieee Geoscience and remote sensing magazine

II. THE CLASSIFICATION CONTEST
The goal of the Classification Contest was to exploit coarser
resolution thermal hyperspectral data and finer resolution
color data to generate an accurate classification map at the finer of the two observed
resolutions. Ranking for the Classification
Contest was based on quantitative accuracy
parameters computed with respect to undisclosed test samples. In addition to accuracy,
another relevant aspect to assess a classification method is its computational burden,
given the provided amount of training samples. In the 2014 Classification Contest, participants were given a limited time period
to submit their classification maps after
the competition was started. To also allow participants to
effectively focus their methods on the proposed multiresolution task and type of input data, the Classification Contest
has consisted of two steps. In the first step, the participants
were provided with only a subset of the data endowed with
ground truth to train their algorithms. In the second step,
the participants received the whole data set and were asked
to submit their classification maps over the whole imaged
area in a short time period (two weeks). In parallel, they
submitted descriptions of their classification approaches.
III. HOW TO GET THE DATA
AND ENTER THE PAPER CONTEST
The Paper Contest aims at promoting novel synergetic uses
of multiresolution and multisensor data as well as of thermal hyperspectral imagery. Participants will submit 4-page
IEEE-style manuscripts using the aforementioned data for
21

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - March 2014