Call for Papers
Special Issue on “Scene
Background Modeling and Initialization”
Pattern Recognition Letters
Motivations
In scene analysis, the availability of an initial background model
that describes the scene without foreground objects is the prerequisite, or at
least can be of help, for many applications, including video surveillance,
video segmentation, video compression, video inpainting (or video
completion), privacy protection for videos, and computational
photography.
Few methods for scene background modeling have specifically
addressed initialization, also referred to as bootstrapping, background
estimation, background reconstruction, initial background extraction, or background
generation, and many challenges still remain unsolved,
including handling sudden illumination changes, night videos, low framerate,
and videos taken by PTZ cameras; thus, model learning is highly required.
The
aim of this Special Issue is to bring together the works
of many experts in this multidisciplinary subject. The Special Issue serves to
highlight the advances from the perspective of the many fields involved, as
well as to further stimulate excellent fundamental and applied research on compiling the state of the art in this subject
from different application areas.
Manuscripts making
fundamental or practical contributions on scene background modeling and
initialization are solicited, including new or revisited models, e.g., statistical, neural, fuzzy/rough,
graphical, scale-space models, and modeling via deep learning, unsupervised
learning, subspace learning, active learning, as well as benchmarking datasets,
and performance evaluation.
Authors are encouraged to test their methods on the Scene Background
Initialization (SBI) dataset (http://sbmi2015.na.icar.cnr.it/SBIdataset.html)
for the evaluation of background initialization algorithms, that includes sequences
with corresponding reference background images and source code to compute
various performance metrics. It is strongly suggested that articles be
accompanied by online appendices containing data, demonstrations, and software.
Deadline for submission: |
April 15, 2016 |
First notification to authors (tentative): |
May 30, 2016 |
Deadline for submission of the revised papers (tentative): |
July 31, 2016 |
Second (final) notification to Authors (tentative): |
September 30, 2016 |
Submission
Format
Papers will be evaluated based on their originality, presentation,
relevance and novelty, as well as their suitability to the special issue, and for
their overall quality, giving preference to those with accompanying data, demo,
and software. All submitted papers will be strictly peer-reviewed; revised
papers that receive a major revision recommendation will be rejected. Author
guidelines for preparation of manuscript can be found at http://www.elsevier.com/journals/pattern-recognition-letters/0167-8655/guide-for-authors.
Manuscripts and any supplementary material
should be submitted through the Pattern Recognition Letters website (http://ees.elsevier.com/patrec). The
authors must select “SI:
SBMI” when they reach the “Article Type” step in the submission process.
Guest Editors
Professor, Department of Science and
Technology
Leader, Computer Vision and Pattern
Recognition Lab
University of Naples Parthenope, Naples,
Italy
alfredo.petrosino@uniparthenope.it
Researcher, Institute for
High-Performance Computing and Networking
National Research Council, Naples, Italy
Thierry
Bouwmans
Maitre de Conférences, Laboratoire
MIA
Université de
La Rochelle, La Rochelle, France