IEEE ISM Invited Speakers
Jose C. Principe (IEEE Fellow)
Distinguished Professor, University of Florida, USA
Invited Position Talk Title: A Cognitive Architecture for Object Recognition in Video
Time: 17:00-17:30, Tuesday, Dec. 15, 2015
This talk describes our efforts to abstract from the animal visual system the computational principles to explain images in video. We develop a hierarchical, distributed architecture of dynamical systems that self-organizes to explain the input imagery using an empirical Bayes criterion with sparseness constraints and dual state estimation. The interpretation of the images is mediated through causes that flow top down and change the priors for the bottom up processing. We will present preliminary results in several data sets.
Jose C. Principe (M’83-SM’90-F’00) is a Distinguished Professor of Electrical and Computer Engineering and Biomedical Engineering at the University of Florida where he teaches advanced signal processing, machine learning and artificial neural networks (ANNs) modeling. He is BellSouth Professor and the Founder and Director of the University of Florida Computational NeuroEngineering Laboratory (CNEL) www.cnel.ufl.edu . His primary area of interest is processing of time varying signals with adaptive neural models. The CNEL Lab has been studying signal and pattern recognition principles based on information theoretic criteria (entropy and mutual information).
Dr. Principe is an IEEE Fellow. He was the past Chair of the Technical Committee on Neural Networks of the IEEE Signal Processing Society, Past-President of the International Neural Network Society, and Past-Editor in Chief of the IEEE Transactions on Biomedical Engineering. He is a member of the Advisory Board of the University of Florida Brain Institute. Dr. Principe has more than 600 publications. He directed 81 Ph.D. dissertations and 65 Master theses. He wrote in 2000 an interactive electronic book entitled “Neural and Adaptive Systems” published by John Wiley and Sons and more recently co-authored several books on “Brain Machine Interface Engineering” Morgan and Claypool, “Information Theoretic Learning”, Springer, and “Kernel Adaptive Filtering”, Wiley.
Dmitry Goldgof (IEEE/IAPR Fellow)
Professor, University of South Florida, USA
Invited Position Talk Title: Image Analysis in Radiomics: Challenges and Opportunities
Time: 16:30-17:00, Tuesday, Dec. 15, 2015
“Radiomics” refers to the extraction and analysis of large amounts of advanced quantitative imaging features with high throughput from medical images obtained with CT, PET or MRI. Importantly, these data are designed to be extracted from standard-of-care images, leading to a very large potential subject pool. Radiomics data are in a mineable form that can be used to build descriptive and predictive models relating image features to phenotypes or gene–protein signatures. The core hypothesis of radiomics is that these models, which can include biological or medical data, can provide valuable diagnostic, prognostic or predictive information.
Dmitry B. Goldgof is an educator and scientist working in the area of biomedical image analysis, video processing, pattern recognition and bioengineering. He is currently Professor in the Department of Computer Science and Engineering at the University of South Florida in Tampa. Dr. Goldgof has graduated 22 Ph.D. and 43 MS students, published over 80 journal and 200 conference papers, 20 books chapters and edited 5 books (citations impact: h-index 42, g-index 77). Professor Goldgof is a Fellow of IEEE and a Fellow of IAPR. He was recently elected to the Board of Governors of IEEE Systems, Man and Cybernetics Society and currently serving on the IEEE Press Editorial Board. Dr. Goldgof is an Associate Editor for IEEE Transactions on Systems, Man and Cybernetics and for International Journal of Pattern Recognition and Artificial Intelligence.
S.S. Iyengar (EAS Member, IEEE/ACM/AAAS Fellow)
Director and Ryder Professor, Florida International University, USA
Invited Position Talk Title: Content Based Retrieval Systems: Theory and Application
Time: 16:00-16:30, Tuesday, Dec. 15, 2015
The ability to organize and retrieve visual information such as images and video is becoming a crucial problem for specialists and general computer users alike. Because processing visual information requires perceptual abilities not yet known to exist in computational form, the ability to retrieve visual information without human assistance is a rich, complex, and interesting problem. This talk presents the problem from the point of view of real-world system construction, discusses the main feature extraction methods used in modern CBIR systems, and outlines several CBIR system implementations This is joint work with Dr.John Zachary, partially funded by NSF.
Dr. Iyengar, a computer scientist of international repute, is a pioneer in the field and has made fundamental contributions in the areas of information processing for sensor fusion networks, robotics and high performance algorithms, all relevant to critical event detection systems as seen in following:
Co-inventor of the Brooks–Iyengar algorithm for noise tolerant distributed control which bridges the gap between sensor fusion and Byzantine fault tolerance, providing an optimal solution to the fault-event disambiguation problem in sensor-networks (1996);
Co-inventor of a novel, paradigm shifting method for grid coverage of surveillance and target location in distributed sensor networks (2002);
Provided seminal work for automated analyses and interpretation of satellite imagery of the ocean and other unknown terrain (1994);
Co-invented the Cognitive Information Processing Shell, a complex event processing architecture and engine which recognizes and responds to complex patterns in mission critical, real-time applications (2010);
Solved an open problem in graph recognition, laying foundation for fast parallel computing for large scale data sets (1988);
The impact of his research contributions can be seen in places like Raytheon, Telecordia, Motorola, the United States Navy, DARPA agencies, etc. Details can be found in the following sections.
Iyengar is a Member of the European Academy of Sciences, the Lifetime Achievement Award from ISAM-IIT (BHU), a Fellow of the Institute of Electrical and Electronics Engineers (IEEE), a Fellow of the Association of Computing Machinery (ACM), a Fellow of the American Association for the Advancement of Science (AAAS), and Fellow of the Society for Design and Process Science (SDPS). He has also received the Distinguished Alumnus Award of the Indian Institute of Science. In 1998, he was awarded the IEEE Computer Society's Technical Achievement Award and is an IEEE Golden Core Member.He is also a Fellow of NAI, Professor Iyengar is an IEEE Distinguished Visitor, SIAM Distinguished Lecturer, and ACM National Lecturer. In 2006, his paper entitled, A Fast Parallel Thinning Algorithm for the Binary Image Skeletonization, was the most frequently read article in the month of January in the International Journal of High Performance Computing Applications. His innovative work called the Brooks-Iyengar algorithm along with the Prof. Richard Brooks from Clemson University is applied in industries and some real-world applications. Dr. Iyengar’s work has a big impact, contrary to popular belief, in 1988, we discovered “NC algorithms for Recognizing Chordal Graphs and K-trees” [IEEE Trans. On Computers 1988]. This breakthrough result led to the extension of designing fast parallel algorithms by researchers like J. Naor (Stanford), M. Naor (Berkeley), and A.A. Schaffer (AT&T Bell Labs). He has also published over 500 papers and 15 books (authored, co-authored, edited, etc.) in places like John Wiley & Sons, Prentice Hall, CRC Press, Springer Verlag, etc. These publications have been used in major universities all over the world.
Kien A. Hua (IEEE Fellow)
Pegasus Professor, University of Central Florida, USA
Invited Position Talk Title: Net Neutrality: New Regulations Require New Engineering Solutions
Time: 17:30-18:00, Tuesday, Dec. 15, 2015
In February of this year, the U.S. Federal Communications Commission voted to pass new net neutrality rules to regulate the Internet like a utility. The regulations ban Internet service providers from crafting deals to give preferential treatment, so called “Internet fast lanes,” to customers who could afford to pay more for the service. The proponents believe these rules will prevent larger conglomerates, like AT&T and Comcast, from controlling the flow of content online and therefore protect free expression and innovation on the Internet; while critics say it is a regulatory overreach and will make the Internet equitably slow and expensive for all of us. This controversy arises mainly because popularity of video streaming services has led to a surge in Internet traffic in recent years. Cisco forecasts that video will make up 84 percent of Internet traffic by 2018. The emerging Internet of Things (IoT) will add another significant percentage if they are not to be deployed responsibly. Unlike video streaming, mostly delivered on demand, many IoT applications rely on continuous data from Internet “things” to make real-time decisions. A recent study by the business consultancy firm Gartner anticipates 26 billion Internet-connected “things” by 2020. In this presentation, we discuss possible solutions for these important problems. More specifically, we examine traffic deduplication as a way to significantly reduce online video congestion. Although it may sound counterintuitive, creating temporary congestion is one effective solution to reducing congestion for video-on-demand services. To avoid non-stop streaming of IoT data, we consider ThingStore. Thing Providers may deploy “things” on Thing Servers, and advertise their smart services (thing operators for events detection) at ThingStore. Application developers can develop apps that query relevant thing operators using EQL (Event Query Language) much like the way traditional database applications are conveniently developed atop a standard database management system today. The advantage of this approach is twofold. First, EQL provides a unified abstraction to address the challenge associated with heterogeneity of devices; and second, decoupling of thing operators from the application logic allows pushing thing-specific computation closer to the live data source (e.g., pushing computer vision computation to the camera server) to avoid network traffic. The ThingStore architecture also enables applications to share Internet-connected “things” through EQL, an improvement over current intranet of things deployed in silos to support different IoT applications.
Kien A. Hua is a Pegasus Professor and Director of the Data Systems Laboratory at University of Central Florida, U.S.A. He was the Associate Dean for Research of College of Engineering and Computer Science at UCF. Prior to joining UCF, he was a Lead Architect at IBM Mid-Hudson Laboratory, where he led a team of senior engineers to develop a highly parallel computer system, the precursor to the highly successful commercial parallel computer known as SP2.
Professor Hua received his Bachelor of Science in Computer Science, and Master of Science and PhD in Electrical Engineering, all from the University of Illinois at Urbana Champaign, USA. His diverse expertise includes image/video computing, network and wireless communications, Internet of Things, databases, medical imaging, mobile computing, sensor networks, and intelligent transportation systems. He has published widely with over 10 papers recognized as best/top papers at conferences and a journal. Many of his research have had significant impact. His Chaining technique started the peer-to-peer video streaming revolution. His Skyscraper Broadcasting, Patching, and Zigzag techniques have each been cited more than 700 times in the literature, and have inspired many commercial systems in use today.
In addition to being a successful researcher, Professor Hua is an effective teacher. He has won teaching awards four times. Pegasus Professorship is the highest honor any professor can achieve at UCF, who must exemplify excellence in all three areas: teaching, research, and service. Professor Hua’s teaching pedagogy includes service learning projects, in which he works with the students to develop applications for non-profit organizations. These projects offered his students a valuable environment to apply what they have learned in class to solve real-world problems while addressing the concerns and needs of their community.
Professor Hua has served as a Conference Chair, an Associate Chair, and a Technical Program Committee Member of numerous international conferences, and on the editorial boards of a number of professional journals. In particular, he was the General Chair of the ACM Multimedia Conference in 2014. Professor Hua is a Fellow of IEEE.
Paul Gader (IEEE Fellow)
UF Research Foundation Professor, University of Florida, USA
Invited Position Talk Title: Processing and integration of Massive hyperspectral and LiDAR imagery and ecological knowledge bases
Time: 10:00-10:30, Wednesday, Dec. 16, 2015
Several massive earth observation data collections are beginning that will take place over the course of several years. Hyperspectral imagery has 200 bands of light spread across the visible, Near-Infra-Red, and Short-Wave Infra-Red wavelengths. Continuous wave LiDar provides ranges as well as addition spectral information. The sizes of the data sets to be collected do not allow for the normal mode of operation thereby necessitating the need for integrating ecological knowledge into the processing chain to disambiguate classification information. The classification information is necessary for estimating ecological parameters useful in climate models.
Paul Gader received the Ph.D. from the University of Florida in 1986. He was a Research Scientist at Honeywell, Research Engineer/Manager at the Environmental Research Institute of Michigan, and Faculty Member at the Universities of Wisconsin, Oshkosh; Missouri; and Florida, where he was Chair of Computer and Information Science and Engineering from 2012 - 2015. He first performed image processing research in 1984 and has researched parallel, fast image and signal processing, applied linear algebra, mathematical morphology, fuzzy sets, Bayesian methods, handwriting and target recognition, landmine detection, and hyperspectral and biomedical image analysis. He is an IEEE Fellow and UF Research Foundation Professor.
Bhavani Thuraisingham (IEEE/AAAS/SPDS Fellow)
Louis A. Beecherl, Jr. Distinguished Professor, University of Texas at Dallas, USA
Invited Position Talk Title: Analyzing and Securing Geospatial data
Time: 10:30-11:00, Wednesday, Dec. 16, 2015
Dr. Bhavani Thuraisingham is the Louis A. Beecherl, Jr. Distinguished Professor of Computer Science and the Executive Director of the Cyber Security Research and Education Institute (CSI) at The University of Texas at Dallas. She is an elected Fellow of IEEE, the AAAS, the British Computer Society, and the SPDS (Society for Design and Process Science). She received several prestigious award including IEEE Computer Society's 1997 Technical Achievement Award for “outstanding and innovative contributions to secure data management”, the 2010 ACM SIGSAC (Association for Computing Machinery, Special Interest Group on Security, Audit and Control) Outstanding Contributions Award for “seminal research contributions and leadership in data and applications security for over 25 years” and the SDPS Transformative Achievement Gold Medal for her contributions to interdisciplinary research. She has unique experience working in the commercial industry (Honeywell), federal research laboratory (MITRE), US government (NSF) and academia and her 34+ year career includes research and development, technology transfer, product development, program management, and consulting for the federal government. Her work has resulted in 100+ journal articles, 200+ conference papers, 100+ keynote and featured addresses, eight US patents (three pending) and fifteen books (two pending). She received the prestigious earned higher doctorate degree (DEng) from the University of Bristol England in 2011 for her published work in secure data management since her PhD.
Mubarak Shah (IEEE/AAAS/IAPR/SPIE Fellow)
Trustee Chair Professor, University of Central Florida, USA
Invited Position Talk Title: TBA
Time: 11:00-11:30, Wednesday, Dec. 16, 2015
Dr. Mubarak Shah, Trustee Chair Professor of Computer Science, is the founding director of the Center for Research in Computer Vision at UCF. His research interests include: video surveillance, visual tracking, human activity recognition, visual analysis of crowded scenes, video registration, UAV video analysis, etc. Dr. Shah is a fellow of IEEE, AAAS, IAPR and SPIE. In 2006, he was awarded a Pegasus Professor award, the highest award at UCF. He is ACM distinguished speaker. He was an IEEE Distinguished Visitor speaker for 1997-2000 and received IEEE Outstanding Engineering Educator Award in 1997. He received the Harris Corporation's Engineering Achievement Award in 1999, the TOKTEN awards from UNDP in 1995, 1997, and 2000; Teaching Incentive Program award in 1995 and 2003, Research Incentive Award in 2003 and 2009, Millionaires' Club awards in 2005 and 2006, University Distinguished Researcher award in 2007, honorable mention for the ICCV 2005 Where Am I? Challenge Problem, and was nominated for the best paper award in ACM Multimedia Conference in 2005. He is an editor of international book series on Video Computing; editor in chief of Machine Vision and Applications journal, and an associate editor of ACM Computing Surveys journal. He was an associate editor of the IEEE Transactions on PAMI, and a guest editor of the special issue of International Journal of Computer Vision on Video Computing.
Rangachar Kasturi (IEEE/IAPR Fellow)
Douglas W. Hood Professor, University of South Florida, USA
Invited Position Talk Title: Person Reidentification and Recognition in Video
Time: 11:30-12:00, Wednesday, Dec. 16, 2015
Person recognition has been a challenging research problem for computer vision researchers for many years. A variation of this generic problem is that of identifying the reappearance of the same person in different segments to tag people in a family video. Often we are asked to answer seemingly simple queries such as ‘how many different people are in this video?’ or ‘find all instances of this person in these videos’. The complexity of the task grows quickly if the video in question includes segments taken at different times, places, lighting conditions, camera settings and distances since these could include substantial variations in resolution, pose, appearance, illumination, background, occlusions, etc. In some scenarios (airports, shopping centers, and city streets) we may have video feeds from multiple cameras with partially overlapping views operating under widely varying lighting and visibility conditions. Yet computer vision systems are challenged to find and track a person of interest as data from such systems have become ubiquitous and concern for security in public spaces has become a growing concern. While this is yet an unsolved challenge, much progress has been made in recent years in developing computer vision algorithms which are the building blocks for person detection, tracking and recognition. We consider several video capture scenarios, discuss the challenges they present for person re-identification and recognition as the complexity of the scene changes, and present pointers to recent research work in relevant computer vision areas in this paper.
Rangachar Kasturi has been the Douglas W. Hood Professor of Computer Science and Engineering at the University of South Florida since 2003. He was a Professor at the Pennsylvania State University during 1982-2003. He received his Ph.D. from Texas Tech University in 1982. His research interests are in computer vision, pattern recognition, and document image analysis. He is an author of the textbook, Machine Vision, McGraw-Hill, 1995. He has served as the Editor in Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence (1995-98), a Fulbright Scholar (1999), the President of the International Association for Pattern Recognition (IAPR) (2002-04), and the President of the IEEE Computer Society (2008). He is a Fellow of the IEEE and IAPR.