[Legacy Report] IEEE Computer Society Distinguished Visitor Program On “Overview of Video Surveillance”

---

On Wednesday 22nd May 2013, IEEE and Computer Society Chapter, Hyderabad Section welcomed Dr. Sharath Pankanti of IBM research Division-Thomas J. Watson research Center, to deliver a lecture on Overview of Video Surveillance at Tata Consultancy Services, Khan Latif Khan Estate, Hyderabad. As an outstanding alumnus of Hyderabad Central University, Research member Dr. Sharath Pankanti has deep feelings towards Hyderabad. And this lecture was the first face-to-face communication with college students. The lecture commenced at 5:30 and lasted uptill7:30 PM.

About the speaker: Academician Dr. Pankanti is a Research Staff Member in the Software Research Department at the Thomas J. Watson Research Center. He received a B.S. degree in Electrical and Electronics Engineering from College of Engineering Pune in 1984, M.Tech in Computer Science from Hyderabad Central University in 1988 and Ph.D. degree in Computer Science from the Michigan State University in 1995. He joined IBM at the Thomas J. Watson Research Center in 1995 as a postdoctoral fellow and later in 1996 became Research Staff Member. He is manager of Exploratory Computer Vision Group at T J Watson Research Center since 2008. He has led a number of safety, productivity, and security focused projects involving biometrics-, multi-sensor surveillance, rail-safety, driver assistance technologies that entail object/event modeling, detection and recognition from information provided by static and moving sensors/cameras. He is an author or co-author of more than 50 patents and more than 70 technical papers. Dr. Pankanti is a fellow of the Institute of Electrical and Electronics Engineers (IEEE) and a member of the Association of Computing Machinery (ACM). Dr. Pankanti has co-edited the first comprehensive book on biometrics, “Biometrics: Personal Identification” Kluwer, 1999 and co-authored, “A Guide to Biometrics”, Springer 2004 which is being used in many undergraduate and graduate biometrics curricula.

Dr. Atul Negi Chairman IEEE Hyderabad Section, Maruthi Pathapati Chairman IEEE Computer Society Chapter Hyderabad Section, Gopalakrishna Kuppa Chairman Technology Management Council at IEEE Hyderabad Section, MGPL Narayana Vice President Tata Consultancy Services, Prof. Deekshitulu Senior member IEEE, few other eminent personalities and students from various Colleges in Hyderabad attended the lecture. Mohd. Safwanullah Shareef and Maimunah Fatima, Chairman and Secretary of IEEE Computer Society MJCET represented Muffakham Jah College of Engineering and Technology at the Distinguished Lecture.
At the beginning of the lecture, Dr. Pankanti explained briefly the various applications of Pattern Recognition, Machine Learning and Artificial Intelligence by presenting a slide of few pictures. The applications included Video Surveillance, Retail Production, Biometrics Rail Safety, and Driver assistance.
The next part of the lecture was when he detailed upon the topic of Video Surveillance.
He said, “Video Surveillance products can be used to provide real-time security in any situation” and “Statistical modeling, machine learning and pattern recognition are the key technologies to enable smart safety and security” and quoted a few examples of how crime-tracking becomes a lot easier because of the implementation of Video surveillance. Further, he explained the four main steps involved in video surveillance - Capture, Analyze, Detect and Act.
He threw light on the problem in video surveillance that arises when the scene is crowded. Usually, the current approaches assume that the observed scene is not crowded; therefore, these approaches (algorithms) are not extendable to more challenging surveillance videos of crowded environments like markets, subways, etc where tracking of individual objects is very hard. And therefore he acknowledged the problem and dealt with the research and technical challenges that occur while searching a vehicle in a crowded place by suggesting the “Finer grained analysis of objects”.

Later in the lecture, he explicated searching based on attributes. He enlightened the audience verbally as well as visually (by presenting videos) that if one’s searching objects based on their attributes, they can be detected by the following concepts step by step.
1. Background subtraction algorithm
2. Blob tracking algorithm 3. Object class
4. Color classification
As the lecture came to the closing stages, Maruthi Pathapati Chairman (IEEE Computer Society Chapter, Hyderabad Section) expressed the excitement and congratulations for Academician Dr. Sharath Pankanti by presenting a token of gratitude.

In sum, Dr. Sharath Pankanti concluded by saying that Video Surveillance is a very vigorous area of study in Computer Vision and is surely a good option for research since there’s no efficient algorithm for the same into practice yet. After the lecture, he clarified the queries and had a one-one talk with inquisitive audience members. As the Distinguished Visitor program ended, the audience was deeply impressed and greatly inspired.

---

---

---

---