Title : Recent advances in Video Analysis For Film and Games Postproduction

Speaker :  

Prof. Ioannis Pitas, Professor,
Department of Informatics ,
University of Thessaloniki ,
Thessaloniki 54124, BOX 451,
Greece

Abstract : During the last two decades, we have witnessed an increasing research interest towards what one could call anthropocentric (human centered) video analysis , namely, algorithms that aim to extract, describe, and organize information regarding the basic element of most videos: humans. This diverse group of algorithms processes videos from various sources and extracts a wealth of useful information related to the state (presence, identity, body posture, emotional state, etc.) and state transitions (body parts movements, activities, etc.) of individuals, interactions or communication modes between two or more humans (dialogues, social signals, etc.) and physical characteristics of humans, such as 3D body models.

The interest of the scientific community for anthropocentric video analysis stems from the fact that the extracted information can be utilised in various important applications. One such application domain is film and games postproduction where anthropocentric video analysis results can be used in tasks such as indexing and retrieval or automatic semantic annotation. In this presentation we will review recent research results in a number of diverse areas such as face detection and tracking, eye detection, visual speech recognition, 3D face reconstruction, face clustering, face recognition, facial expression analysis, and activity recognition, either from a single or multiple visual (image/video) sources.

About the Speaker : Prof. I. Pitas received the Diploma of Electrical Engineering in 1980 and the PhD degree in Electrical Engineering in 1985, both from the University of Thessaloniki, Greece. Since 1994 he has been a Professor at the Department of Informatics, University of Thessaloniki, Greece. From 1980 to 1993 he served as Scientific Assistant, Lecturer, Assistant Professor, and Associate Professor in the Department of Electrical and Computer Engineering at the same University. He leads funded R&D projects in CERTH/ITI. He is an IEEE fellow. He served as Visiting Professor and ASI fellow at the University of British Columbia, Canada, as Visiting Professor at Ecole Polytechnique Federale de Lausanne, at Tampere University of Technology, Finland, as Visiting Assistant Professor at the University of Toronto and as a Visiting Research Associate at the University of Toronto, Canada and at the University of Erlangen-Nuernberg, Germany.

His current interests are in the areas of digital image processing, multimedia signal processing, multidimensional signal processing and computer vision. He has published over 640 papers, contributed in 32 books and authored, co-authored, edited, co-edited 8 books in his area of interest. He is the co-author of the books "Nonlinear Digital Filters: Principles and Applications" (Kluwer, 1990), ‘3D image processing algorithms’ (Wiley 2000). He is the author of the books ‘Digital Image Processing Algorithms’ (Prentice Hall, 1993), ‘Digital image processing algorithms and applications’ (Wiley 2000), ‘Digital image processing’ (in Greek, 1999). He is the editor of the book "Parallel Algorithms and Architectures for Digital Image Processing, Computer Vision and Neural Networks" (Wiley, 1993) and co-editor of the book ‘Nonlinear Model-Based Image/Video Processing and Analysis’ (Wiley 2000).

Dr. Pitas has been a member of the European Community ESPRIT Parallel Action Committee. He had 7 academical occupation and visits in universities abroad. He co-organized 11 special sessions in conferences, 7 special issues in scientific journals. He is/was editor in 22 journals. He gave 37 invited lectures, was member of the program committee of more than 214 scientific conferences and workshops and was chair of more than 36 conference sessions. He supervised 14 completed PhD theses. He was reviewer in 52 scientific journals, 150 conferences, 32 R&D funding agencies and 4 publishers. He participated in 16 national and international committees and he had a major role in the organization of 10 conferences. He participated in 50 R&D projects, is/was principal investigator/researcher in 39 competitive R&D projects and in 12 educational projects, all mostly funded by the European Union. He is/was Associate Editor of the IEEE Transactions on Circuits and Systems, IEEE Transactions on Neural Networks, IEEE Transactions on Image processing, IJIG Journal, IEICE, Circuits Systems and Signal Processing (CSSP), co-editor of Multidimensional Systems and Signal Processing, member of the editorial board of 6 journals and guest editor in 6 special journal issues. He was chair of the 1995 IEEE Workshop on Nonlinear Signal and Image Processing (NSIP95). He was technical chair of the 1998 European Signal Processing Conference. He was the general chair of IEEE ICIP2001. He was co-chair of the 2003 International workshop on Rich media content production. He was technical co-chair of the 2003 Greek Informatics conference (EPY). He was chair of the TC on Digital Signal Processing of the IEEE Circuits and Systems Society. He was vice-chair of the TC on image processing and multidimensional signal processing of the IEEE Signal Processing Society. He is member of the National Research Council of Greece. He has received the 2009 best cited author award by Aristotle University of Thessaloniki (8500+ citations). He has 11350+ citations to his work and H-index 53+.

Title : Saliency-Guided Visualization of Very Large-Scale Datasets

Speaker :  

Prof. Amitabh Varshney, Professor,
Department of Computer Science,
4407 A. V. Williams Building,
University of Maryland,
College Park, MD 20742

Abstract : Scientific data is growing at an exponential rate due to advances in acquisition, modeling, and simulation technologies. Even as datasets have been growing at an exponential rate, the capabilities of the human visual system have remained unchanged. As a result, we have now reached a stage where the current generation datasets can easily overwhelm the limits of human comprehension. Visual scalability is thus rapidly emerging as one of the grand challenges in scientific data exploration. This has informed much of our recent research in developing saliency-guided techniques for large data visualization and analysis. Most of the time, most of the data is innocuous and unimportant and even considering it wastes precious time and resources. However, current visualization systems effectively assume a default, that every piece of data is equally important. In this talk I shall highlight some of the recent advances in building visualization systems for exploring gigapixel imagery and large molecular dynamics simulations that leverage the principles of perception of visual salience to address the data deluge challenge.

About the Speaker : Prof. Amitabh Varshney is the Director of the Institute for Advanced Computer Studies (UMIACS) and Professor of Computer Science at the University of Maryland at College Park. He received a B. Tech. in Computer Science from the Indian Institute of Technology, Delhi in 1989 and a M.S. and Ph.D. in Computer Science from the University of North Carolina at Chapel Hill in 1991 and 1994. During 1994 - 2000, he was an Assistant Professor in the Department of Computer Science at the State University of New York at Stony Brook.

Prof. Varshney's research focus is on exploring the applications of graphics and visualization in engineering, science, and medicine. He has worked on the design and implementation of virtual walkthroughs of proposed structures, such as buildings, automobiles, and submarines. In the process he has developed new algorithms for automatically generating multiresolution object hierarchies, image-based rendering, parallel computation and simplification of radiosity meshes, and fine gesture recognition for virtual environments.

Prof. Varshney's work on efficient and robust computation of smooth molecular surfaces is useful in the rational drug design process through the protein folding and docking problems. He is currently exploring applications in general-purpose high-performance parallel computing using clusters of CPUs and Graphics Processing Units (GPUs). He has also consulted and collaborated with the industry including Honda, IBM, Daimler Chrysler, General Dynamics, and Reuters.

Prof. Varshney received a NSF CAREER Award in 1995 and a Honda Research Initiation Award in 1997. He received the IEEE Visualization Technical Achievement Award in 2004. He is currently serving as the Chair of the IEEE Visualization and Graphics Technical Committee. He is a Fellow of IEEE.

Title : Motion Estimation in Image and Stereo Sequences: Accurate Models, Efficient Algorithms, and Recent Application

Speaker :  

Prof. Andres Bruhn,
Head of the Junior Research Group
"Vision and Image Processing"
Cluster of Excellence MMCI
Saarland University, Building E1.1
66041 Saarbruecken, Germany

Abstract : The estimation of motion information from two consecutive frames of an image sequence is one of the fundamental problems in computer vision. Since the seminal work of Horn and Schunck continuous optimization methods have been among the most popular techniques for solving this task. In the last three decades this popularity triggered a tremendous amount of research in the field. Nowadays continuous optimization methods belong to those methods that are best understood and that offer the best performance in terms of accuracy.

This talk addresses four important aspects of motion estimation with continuous optimization methods:
(i) First, it gives insights into the design of highly precise models that are among the most accurate approaches in the entire literature. This is done by discussing recent modeling concepts and embedding them into a general implementation framework.
(ii) Secondly, it presents efficient numerical algorithms both on sequential and parallel architectures. Despite the complexity of the underlying optimization problems, these algorithms allow to compute dense motion fields of excellent quality in real-time.
(iii) Furthermore, the talk shows the extensibility of the discussed models to other important areas in computer vision such as stereo reconstruction and scene flow. By jointly estimating the 3-D motion, the depth and the scene geometry, those methods are able to provide results that are significantly more accurate than those reported in the literature so far.
(iv) Finally, it comments on several applications for which motion information plays a key role. Such applications include video processing, image registration as well as audio-visual speech recognition.

About the Speaker : Dr. Andres Bruhn is head of the research group "Vision and Image Processing" within the Cluster of Excellence "Multimodal Computing and Interaction" at Saarland University, Saarbruecken, Germany. Moreover, since 2007 he is associated as an adjunct assistant professor with the Mathematical Image Analysis Group at the same university. Dr. Bruhn received a diploma degree in Computer Engineering from the University of Mannheim, Mannheim, Germany, in 2001 and a Ph.D. degree in Computer Science from Saarland University, Saabruecken,Germany, in 2006. In 2009 he spent two months as a visiting reasearcher at the University of Las Palmas in Gran Canaria, Spain. His research interests include optical flow estimation, stereo reconstruction, diffusion filtering and fast numerical schemes for image processing and computer vision. In this field he published over 50 papers in peer-reviewed conference proceedings and journals.

Dr. Bruhn serves on the programme committee of ECCV, ICCV, ACCV, and CVPR and regularly reviews for all major computer vision journals. His publications received several awards, among them the 2004 Longuet-Higgins Best Paper Award of the European Conference on Computer Vision (ECCV), the 2006 Olympus Prize and the 2010 Main Prize of the German Pattern Recognition Society (DAGM), the 2006 Outstanding Dissertation Award of the German Society of Computer Science (GI), the Swiss Computer Science Society (SI), the Austrian Computer Society (OCG) and the German Chapters of the ACM (GChACM) as well as the 2007 Dr. Eduard Martin Prize of the Saarland University. Moreover, he was nominated as one of two national finalists for the 2008 Cor Baayen Award of the European Research Consortium for Informatics and Mathematics (ERCIM). Apart from that he received two Outstanding Reviewer awards: one at the European Conference on Computer Vision (ECCV) in 2008 and one at the Asian Conference on Computer Vision (ACCV) in 2010. Finally, Dr. Bruhn was also awarded for his teaching activities: In the summer term 2008 he received an Outstanding Teaching Award in Computer Science at Saarland University.

Title :Digital Watermarking: A Feasibile Signal Design Perspective

Speaker :  

Prof. Gaurav Sharma, Associate Professor,
University of Rochester
Hopeman 417, Box 270126
Rochester, NY 14627-0126,
USA

Abstract :Digital watermarking methods are designed to communicate information by imperceptibly hiding data within a multimedia host signal, without impacting the primary functionality of the host. Watermarking applications pose multiple constraints that must be simultaneously satisfied: sufficient watermarking strength, imperceptibility of embedding distortions, robustness to signal processing operations being the common requirements. In addition, applications often require multiple watermarks for different purposes: for example, for copyright protection, traitor tracing, and authentication. Traditional methods have addressed these scenarios through ad hoc modifications of the two main watermarking methods: spread-spectrum embedding and quantization index modulation. In this talk, we present a novel set theoretic methodology for watermarking that effectively addresses both of these scenarios in a common and principled framework. Multiple requirements across multiple watermarks, such as watermark embedding strength, imperceptibility, robustness to benign signal processing and fragility under malicious attacks, are described as constraint sets and a watermarked image is determined as a feasible solution satisfying these constraints. We illustrate that several constraints can be formulated as convex sets and develop a watermarking algorithm based on the method of projections onto convex sets. The framework allows flexible incorporation of different constraints including embedding strength requirements for multiple watermarks that share the same spatial context and different imperceptibility requirements based on frequency-weighted error and local texture perceptual models. Furthermore, it also allows for the optimization of one constraint while meeting other constraints. We present applications of the methodology to both spread-spectrum and quantization-index-modulation watermarks and demonstrate its effectiveness.

About the Speaker : Dr. Gaurav Sharma is with the University of Rochester, where he is an Associate Professor at the Department of Electrical and Computer Engineering with an adjunct appointment in the Department of Biostatistics and Computational Biology. He is also the Director for the Center for Emerging and Innovative Sciences (CEIS), a New York state supported center for promoting joint university-industry research and technology development, which is housed at the University of Rochester. From 1996 through 2003, he was with Xerox Research and Technology in Webster, NY first as a member of research and technology staff and then as a Principal Scientist and Project Leader. He received the Ph.D. in Electrical and Computer Engineering from North Carolina State University, Raleigh, NC, and masters degrees in Applied Mathematics from NCSU and in Electrical Communication Engineering from the Indian Institute of Science, Bangalore, India. He received his bachelor of engineering degree in Electronics and Communication Engineering from Indian Institute of Technology, Roorkee (formerly, Univ. of Roorkee).

Dr. Sharma is a senior member of the IEEE and a member of SPIE -- the international society for optics and photonics, the Society for Imaging Science and Technology (IS&T), and the IEEE Signal Processing and Communications Societies. He is also an elected member of Sigma Xi, the scientific research society and the Phi Kappa Phi and Pi Mu Epsilon honor societies.

Dr. Sharma currently serves as an associate editor for the SPIE/IS&T Journal of Electronic Imaging and the open-access Journal of Electrical and Computer Engineering. He has previously served as an associate editor for the IEEE Transactions on Information Forensics and Security, and for the IEEE Transactions on Image Processing and the open-access Research Letters in Signal Processing journal. He is the editor of the "Digital Color Imaging Handbook" published by CRC press.

Dr. Sharma serves as the chair for the Image, Video, and Multi-dimensional Signal Processing Technical Committee, of the IEEE Signal Processing Society and served as the 2007 Chair of the IEEE Rochester Section. He is also a member of the Information Forensics and Security Technical Committee , of the IEEE Signal Processing Society.

Speaker :  

Prof. R.K.Mittal,
Director,
BITS Pilani,
DUBAI

About the Speaker : Prof. Dr. R.K.Mittal has been deputed from BITS, Pilani-Rajasthan as the Director for BITS, Pilani-Dubai. Prof. Dr. R. K. Mittal is a B.E. (Hons.) , M.E. and Ph.D from BITS, Pilani. He commenced his academic career in BITS, Pilani in 1975 and has about 35 years of academic and administrative experience to his credit.

Prof. R.K.Mittal is an expert in the area of Robotics and has co-authored two textbooks and published over 40 articles in national and international journals. He is also the founding member of the Centre of Robotics and Intelligent systems at BITS, Pilani -Rajasthan. He was serving as the Deputy Director (Administration) at BITS before being deputed to the Dubai campus. He has led and been instrumental in computerization of the academic and administrative processes of the institute. He is the president of the BITS Alumni Association since its inception in 1989.

In 1975, he joined BITS, where he is currently a Professor of Computer Science. In 1990, he became an Associate Professor and, in 1995, a Professor. For the last 31 years, he has taught undergraduate and postgraduate courses, has guided several M. Tech. theses, and is currently guiding four Ph.D. students in Robotics and Software Engineering. He is the founding Member of the Centre for Robotics and Intelligent Systems (CRIS), BITS, which was established in 1992, and was its Coordinator until 2000. He is currently the Dean of the Academic Registration and Counselling Division, BITS. He coauthored the two textbooks Robotics & Control (New Delhi, India: McGraw-Hill, 2003) and Elements of Manufacturing Processes (New Delhi, India: Prentice-Hall, 2003). His research interests includes robust robotic designs, two-/three-dimensional robot-path planning, microelectromechanical systems (MEMS), microrobots and nanorobots, nanotechnology, software engineering, and software testing. Dr. R K Mittal is branch counselor for the IEEE Students Branch, BITS, and President of the BITS Alumni Association (BITSAA).

Title : Intelligent Video Analytics - A Visual Computing Tool

Speaker :  

Dr. Tinku Acharya,
Fellow IEEE, INAE, IETE
Founder & Managing Director
Videonetics Technology Pvt. Ltd., Kolkata

Abstract : We are in the midst of a visually enchanting world, which manifests itself with a variety of forms and shapes, colors and textures, motion and tranquility. The human perception (a natural biological) system has the capability to acquire, integrate, and interpret all this abundant visual information around us. It is challenging to impart such capabilities to a machine in order to interpret the visual information embedded in still images, graphics, and video or moving images in our sensory world. With the advent of today’s high speed computing platform, communication technology, and advancement of image understanding techniques, there is a paradigm shift in the concept of practical Machine Vision systems to achieve visual computing in a true sense. The computational and memory requirements for visual computing techniques and their applications with moving pictures in real-time is very high compared to traditional still imagery based techniques. Because of the huge computational requirements of underlying algorithms, most of the visual computing based computer or machine vision applications remained restricted to defense applications only (even in the last decade). Recently, concept of visual computing based machine vision systems started to get tremendous momentum for civilian applications due to the recent advancement of convergence of high speed computing and communication. Visual computing is no more a science fiction. This opened up many opportunities in the society to rethink traditional way of doing business to make our everyday lives more productive. One such new and emerging tool is Intelligent Video Analytics. This is an interdisciplinary domain of research and development that includes the expertise from image processing, computer vision, communication network, parallel and distributed computing, statistical analysis, and data mining technologies. The goal of Intelligent Video Analytics technology is to automatically generate actionable information from live video in Internet Protocol based digital video networks with far fetching implications of its future applications.

The law and enforcement agencies need to take advantage of visual computing based Intelligent Video Analytics applications as a tool to enhance their operational excellence. One of them is to automate security and surveillance systems intelligently to reduce dependency on human observation and hence eliminate possible human errors, particularly in this era of global terrorism. In this presentation, we’ll present how Intelligent Video Analytics can be used for Intelligent Surveillance and Security application. Another area of application can be efficient traffic management and signal control system. Traffic management and smooth vehicle monitoring is a challenge in our great nation with such a high population density. The growth of urbanization and widening middle class population caused inorganic growth in the volute of traffic in the road. We need to adopt modern “Visual Computing” technology to cope up with such tremendous growth. Intelligent Video is one such technology. We’ll cover how we can take advantage of Intelligent Video Analytics towards solving such problems as well.

About the Speaker : Dr. Tinku Acharya is the Founder and Managing Director of Videonetics Technology Private Limited, Kolkata. He received his B.Sc. (Honors in Physics), B.Tech and M.Tech in Computer Science from University of Calcutta, and PhD in Computer Science from University of Central Florida, USA.

Dr. Acharya was elevated to IEEE Fellow in 2010 for his contributions to the advancement of very large scale integration algorithms and architectures for electronic image processing. He is also a Fellow of many institutions in India. He is recipient of “2009 NASI - Reliance Platinum Jubilee Award for innovation in Physical Sciences” from National Academy of Science in India and the first to receive this prestigious award from industry. He is recipient of the “1st Acharya P. C. Ray Memorial Award for distinguished achievements in Science and Entrepreneurship” from Institute of Pulmocare and Research (2010). He received the “Engineer of the Year” award from IEEE Phoenix, USA (2008), and “Outstanding Engineer” award from IEEE Southwest Region, USA (2008). He was recognized the ‘Most Prolific Inventor’ in Intel Corporation (worldwide) twice (1999 & 2001), and the ‘Most Prolific Inventor’ 5 times in Intel Arizona (1997-2001).

Dr. Acharya is inventor of 118 U.S. and 14 European patents in electronic imaging, data compression, multimedia computing, computer vision, and VLSI architectures. He contributed to over 100 technical papers published in international journals, conferences, and book chapters. He is author of 4 books - (i) Image Processing: Principles and Applications (Wiley, New Jersey, USA, 2005), (ii) JPEG2000 Standard for Image Compression: Concepts, Algorithms, and VLSI Architectures (Wiley, USA 2004), (iii) Information Technology: Principles and Applications (Prentice-Hall India, 2004), and (iv) Data Mining: Multimedia, Soft Computing and Bioinformatics (Wiley, USA, 2003).

Dr. Acharya equally contributed in academia and industry. As a Principal Engineer in Intel Corporation (USA), he lead several R&D teams to develop electronic imaging systems, digital camera (Intel’s first Webcam), reprographics architecture for color photo-copiers, high performance microprocessor, etc. He developed the key `image processing chain’ and related algorithms to pragmatically map them into a small footprint silicon for the first dual-mode digital camera (Intel’s WebCam). His works significantly influenced the design of digital cameras in early days and paved the successful transition of analog to digital photography today. His work was foundation of the MXP5800/5400 media processor from Intel, capable of processing 10 BOPS, and enabled successful implementation of a set of Internet capable photocopiers from Xerox and Fuji-Xerox. His pioneering works in VLSI mapping of Lifting based Discrete Wavelet Transformation with reduced computation and the versatile architectural framework to design the very first VLSI architecture for JPEG2000 standard for image compression is well known in the literature. His JPEG2000 book is the only book used as a reference in academia and industry worldwide for both software and VLSI implementation of this standard. His concept of the “coprocessor architecture for fast protein structure prediction” in bioinformatics is the first published VLSI architecture known in this domain.

He is a recognized expert in Intelligent Video Analytics and related technology across the industry. His innovative concept of intelligent security and surveillance has been adopted in 22 airports under Airports Authority of India. His concept of visual computing based dynamic traffic signal monitoring using real-time intelligent analysis of traffic flow patterns has been deployed in 37 busy intersections in Kolkata. He is currently developing many such real-life applications in his R&D Lab in Videonetics, Kolkata.

He was CTO of Avisere Inc (Arizona), engineer at AT&T Bell Lab (New Jersey), research faculty in UMIACS, University of Maryland at College Park, Adjunct Professor in Department of Electrical Engg., Arizona State University, visiting professor in Electronics and Communication Engineering Department, Indian Institute of Technology (Kharagpur). He collaborated with many institutions including Xerox Palo Alto Research Center, Eastman Kodak (New York), Calcutta University, Indian Statistical Institute, etc.

He served in US National Body of the ISO JPEG2000 standard committee (1998-2002) for definition of this scalable image compression standard. His current research interests are in intelligent video and image processing, computer vision, pattern recognition, multimedia computing, and VLSI architectures.