IEEE Geoscience and Remote Sensing Magazine - September 2021 - 165

TECHNICAL COMMITTEES
MICHAEL SCHMITT, CLAUDIO PERSELLO, GEMINE VIVONE, DALTON LUNGA, WENZHI LIAO,
NAOTO YOKOYA, PEDRAM GHAMISI, AND RONNY HÄNSCH
The New Working Groups of the GRSS Technical
Committee on Image Analysis and Data Fusion
T
he Image Analysis and Data Fusion Technical Committee
(IADF TC) of the IEEE Geoscience and Remote
Sensing Society (GRSS) serves as a global, multidisciplinary
network for geospatial image analysis (IA), e.g., machine
learning (ML), deep learning (DL), image and signal processing,
and big data and data fusion (DF), e.g., multisensor,
multiscale, and multitemporal data integration.
The wide scope of IADF broadened further with the recent
advances of IA and DF. The increasing availability of space
or airborne remote sensing data requires advanced methods
for multimodal DF, including image alignment, low-level
preprocessing, feature extraction, and image fusion. It also
allows for new opportunities for IA such as sensor transcoding,
cross-modal image interpretation, and domain adaptation.
Many of these advancements are achieved by ML
approaches. In particular, DL has been extremely successful
at all levels of the processing chain to automatically interpret
remote sensing images including image compression, cloud
removal, noise suppression, image registration and normalization,
feature extraction, and representation learning as
well as semantic analysis and extraction of bio-/geophysical
parameters. One of the main causes for the recent success
of ML and DL is the increasing availability of large-scale
benchmark data sets, i.e., data that contains reference data
additionally to the input images, which allows the proper
training and evaluation of learning-based approaches.
To ensure that these diverse aspects are well represented
by IADF, three working groups (WGs) were created that are
dedicated to distinct fields within the scope of IA and DF,
namely benchmarking (WG-BEN; Figure 1), image and
signal processing (WG-ISP; Figure 2), and ML/DL for IA
(WG-MIA; Figure 3).
WG-BEN
Data sets have always been important for research on
novel remote sensing methodologies, as they are needDigital
Object Identifier 10.1109/MGRS.2021.3100654
Date of current version: 28 September 2021
SEPTEMBER 2021 IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE
ed for the development and evaluation of new algorithms.
In today's era of big data and DL, data sets have
become even more important than before: large, wellcurated,
and annotated data sets are of crucial importance
for the training and validation of state-of-the-art
models for information extraction from increasingly
versatile multisensor remote sensing data. In addition,
due to the increasing number of new methods being
proposed by scientists and engineers, the possibility
to compare these methods in a fair and transparent
manner has become more and more important.
The WG-BEN addresses these challenges and provides
input with respect to evaluation methods, data sets,
benchmarks, competitions, and tools for the creation of
reference data. Furthermore, we contribute to evaluation
sites, databases, and standardization endeavors.
WG-ISP
The WG-ISP promotes advances in signal and image
processing relying upon the use of remote sensing data.
It serves as a global multidisciplinary network for both
DF and IA, supporting activities about several specific
topics under the umbrella of the GRSS IADF TC. It
aims at connecting people, supporting educational initiatives
for both students and professionals. The WGISP
encloses different topics, such as pansharpening,
superresolution, multimodal image registration, DF,
165
IEEE Geoscience and Remote Sensing Magazine - September 2021

Table of Contents for the Digital Edition of IEEE Geoscience and Remote Sensing Magazine - September 2021
