Special Issue for Computer Vision and Image Understanding on Background Models Comparison Call for Papers

Special Issue for Computer Vision and Image Understanding on Background Models Comparison Context and introduction The detection of moving objects in video sequence is an important task in many video-surveillance systems. As a matter of fact, the output of this very first stage, named background modeling or background subtraction, fundamentally determines the quality of the rest of pipelines developed for the detection, identification or tracking of persons, objects, etc. Background modeling is sometimes considered either as a trivial operation, carried out by computing a simple difference between the current frame and a single background image (or with the previous frame, etc.), or as a mastered technique that does not need any improvement or development nowadays. In the latter case, one cites in general very famous methods such as Gaussian Mixture Models introduced by Stauffer and Grimson in 1999, and thinks this is sufficient. Unfortunately, these kinds of algorithms are limited in outdoor environments, when used in long-term surveillance applications, because of many uncontrolled and damaging events: global variation of luminance, shadows of objects, bad weather, camera tilts, etc. Since this is a key-point of video-surveillance applications, background subtraction has become a popular topic, and many techniques have been proposed since the 90's. In BMC 2012 (1st ACCV Workshop Background Models Challenge), we proposed a new benchmark composed of almost 30 synthetic and real video sequences. Thanks to these datasets, we are able to propose very complex situations, in various surveillance contexts (human activities or traffic for example). We have also developed a free software (BMC Wizard) that computes relevant criteria that evaluate statistical, signal and structural information from a background subtraction algorithm. This Special Issue on Background Models Comparison (SI-BMC) is proposed directly in the continuity of this workshop. The main topics of SI-BMC are: . detection of moving objects, motion estimation ; . background modeling and maintenance, foreground detection ; . signal, image, video processing ; . image segmentation and classification ; . intelligent video-surveillance. Guest Editors Antoine Vacavant ISIT, CNRS/Université d'Auvergne, Clermont-Ferrand, France Laure Tougne LIRIS, CNRS/Université Lumière Lyon2, Lyon, France Lionel Robinault Foxstream company, Vaulx-en-Velin, France Thierry Chateau Pascal Institute, CNRS/UBP, Clermont-Ferrand, France Invited reviewers Guillaume Alexandre Ecole polytechnique de Montréal, Canada Najoua E. Ben Amara SAGE, Ecole polytechnique nationale de Sousse, Tunisia Domenico D. Bloisi Sapienza Univ. di Roma, Italy Thierry Bouwmans MIA, Univ. La Rochelle, France Larry Davis Institute for Advanced Computer Studies, MA, USA Pojala Chiranjeevi Indian Institute of Technology, Kharagpur, India Assaf Glazer Technion, Israel Institute of Technology, Israel Yann Goyat IFSTTAR, France Charles Guyon MIA, Univ. La Rochelle, France Benjamin Hoferlin Intelligent Systems Group - Univ. Stuttgart, Germany Karim Kalti SAGE, Ecole polytechnique nationale de Sousse, Tunisia Jean-Marc Lavest Pascal Institute, Univ. Blaise Pascal, France Jim Little Univ. of British Columbia, Vancouver, Canada Michael Lindenbaum Technion, Israel Institute of Technology, Israel Greg Mori Univ. of British Columbia, Vancouver, Canada Quoc-Cuong Pham CEA list, France Fatih Porikli Mitsubishi Electric Research Labs, Cambridge, MA, USA Esa Rahtu Center for Machine Vision and Research, Univ. of Oulu, Finland Nicolas Saunier Ecole polytechnique de Montréal, Canada Patrick Sayd CEA list, France Somnath Sengupta Indian Institute of Technology, Kharagpur, India Munir Shah Dep. of Information Science, Univ. of Otago, New Zealand Atsushi Shimada Kyushu Univ., Japan Hamed R. Tavakoli Center for Machine Vision and Research, Univ. of Oulu, Finland Rik van de Walle Multimedia Lab, Belgium Brendon Woodford Dep. of Information Science, Univ. of Otago, New Zealand Satoshi Yoshinaga Kyushu Univ., Japan Important dates First call for papers January, 25th 2013 EES system opens for submission February, 4th 2013 Submission of article, Excel file and code April, 1st 2013 Notification to authors July, 15th 2013 Submission of revised articles October, 14th 2013 Final decision December, 16th 2013 Submission guidelines This is an open call-for-papers from outside the BMC 2012 workshop, though participants of the workshop was invited to submit a paper of their contribution. All submitted papers will be reviewed according to the guidelines and standards of CVIU. Only original, high-quality papers, in-line with the CVIU standard guidelines, will be considered for publication in this special issue. Submissions will be judged by their contributions to the special issue topics, clarity of presentation, potential impact to the field, and suitability to publication in an archival journal. All articles must be submitted electronically through the Elsevier CVIU website (http://ees.elsevier.com/cviu/default.asp) by selecting "BMC" as the type of article, and authors must use the detailed guidelines for CVIU articles ( which are indicated on the page http://authors.elsevier.com/GuideForAuthors.html?PubID=622809&dc=GFA). Moreover, authors have to submit an Excel file gathering all the scores obtained thanks to the BMC workshop dataset (see http://bmc.univ-bpclermont.fr/?q=node/6 and http://bmc.univ-bpclermont.fr/?q=node/7), and binary images computed with their algorithm. The guest editors will choose which frames authors will have to present for the challenge. The evaluation of algorithms will be twofold: (1) objective evaluation thanks to the scores; (2) subjective evaluation by editors thanks to the images obtained from algorithms. Finally, we propose to authors to send an OpenCV program of their algorithm. The best techniques will be included into the OpenCV library. We will also be able to evaluate the execution time and memory requirement thanks to the code submitted. Documents required for a valid submission Here is a table summing up the set of files that are required for a submission to this BMC special issue: Name Mandatory? Comment Article Yes Must follow the Elsevier CVIU guidelines Scores Yes Must be indicated in a single Excel file, available on BMC website Images Yes Binary images obtained from the proposed algorithm Code No OpenCV-based program