Topic: Computer Vision for Underwater and Drone-based Sea-surface Imagery  

Abstract:

Underwater computer vision poses many challenges due to loss of contrast, low light, haziness, and color distortion in the captured images. Recovering a clean image and the corresponding 3D depth map from underwater observations is fundamental to high-level tasks involving scene understanding. Towards this end, we have devised a learning methodology that effectively utilizes both haze and geometry by harnessing the physical model for underwater image formation in conjunction with view-synthesis constraint. The proposed method is completely self supervised and simultaneously outputs the depth map and the restored image in real-time (55 fps). To facilitate self-supervision, we collected a Dataset of Real-world Underwater Videos of Artifacts (DRUVA) in shallow sea waters. DRUVA is the first UW video dataset that contains video sequences of 20 different submerged artifacts with almost full azimuthal coverage of each artifact. We are also involved in devising computer vision methods for analysing sea surface waters. Specifically, the talk will cover ongoing research being carried out in IPCV lab involving air drills over the ocean using drones with payload consisting of color as well as thermal cameras, and motion sensors for the tasks of geo-referencing and sea surface temperature analysis. Experimental results on real data will be discussed.

Biography:

Dr. A.N. Rajagopalan received Ph.D degree in Electrical Engineering from Indian Institute of Technology, Bombay. During the summer of 1998, he was a visiting scientist at the Image Communication Lab, University of Erlangen, Germany. He was with the Center for Automation Research, University of Maryland from 1998 till 2000 as a Research Scientist before joining the Department of Electrical Engineering at IIT Madras where he currently serves as Sterlite Technologies Chair Professor. His current research interests include deep learning, 3D recovery and novel view synthesis of dynamic scenes, audio-visual and multimodal learning, underwater imaging, computer vision for sports, and image restoration. He is a Fellow of Alexander von Humboldt Foundation, Germany, a Fellow of Indian National Academy of Engineering, and Fellow of Asia-Pacific Artificial Intelligence Association. He served as Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) from 2007 to 2011, Associate Editor of IEEE Transactions on Image Processing (TIP) from 2012 to 2016, and as Senior Area Editor for IEEE Transactions on Image Processing from 2016-2019 and 2021-2024. He has served as Area Chair for several A-star venues. He is a recipient of the DAE-SRC Outstanding Investigator award in 2012, the VASVIK award in 2013, the Mid-Career Research & Development award from IIT Madras in 2014, Google India AI/ML Research award for faculty in 2018, and Qualcomm Faculty award in 2022. His research has been supported with funding from national and international agencies. His collaboration with industries includes KLA-Tencor, Google, Qualcomm, Adobe, Dolby etc. He has co-authored two books.

Topic: Electronic Design of Remote Sensing Electro-Optical Payloads  

Abstract:

Indian Government has opened up space sector for Non-Government Entities. At present, India’s share in global space market is less and there is immense scope for expansion. More than 300 startups have come in space sector India in last 2-3 years. Lot of multi-disciplinary engineers / work force will be required in future for space sector. The topic provides a glimpse of electronic design of remote sensing electro-optical payloads for space. It covers Space based Remote Sensing, Electro-Optical Payloads, Basic Electronic blocks of Electro-optical payloads, Electronic design and challenges for space hardware realization and recent trends.

Biography:

Dr. Sanjeev Mehta is a Scientist at the Space Applications Centre of ISRO, Ahmedabad, where he has been contributing since joining the organization in 1992. He holds a B.E. in Electronics from Government Engineering College, Ujjain, and an M.Tech in Electronics Design & Technology from the Indian Institute of Science, Bangalore. He specializes in developing onboard electronics for IRS (Indian Remote Sensing) satellite payloads, focusing on compact, reliable instrumentation that enhances remote sensing capabilities.

Topic: From Bits to Bullets: Translating C.E.M.S for Atmanirbhar Bharat in Defence Technology  

Abstract:

To assist our tri-forces both DRDO and ISRO worked hand-in-hand for the past few years to give the latest equipments to our soldiers and support them with the accurate information to execute Operation Sindoor. But this is not the end; as we are working towards Atma-Nirbharta in state-of-the-art technologies such as AI-powered satellite imaging; Quantum-encrypted communications; Hypersonic drones or missiles. The Technology Perspective and Capability Roadmap (TPCR-2025) outlines India's long-term strategy for defense modernization, emphasizing indigenization, multi-domain readiness, and technological superiority through focused R&D in critical areas like AI, unmanned systems, and electronic warfare. The keynote address is based on the strategic themes in reference of the TPCR-2025. The talk will give insight to academia and start-up entrepreneurs highlighting opportunities in defence sector by mapping the requirement of our tri-forces in the areas of CEMS i.e Communication, Embedded Design, Machine Learning, and Signal Processing.

Biography:

Dr. Bharatbhushan Joshi is a Senior Defence-Scientist turned into Academician. He is BE (Hons.) in EEE from BITS, Pilani, and ME in Guided Missiles and Doctorate in MEMS Technology from University of Pune. He is presently working as Technology Advisor with few companies for indigenisation of armaments. He is Diploma in Business Management and Diploma in German Language from University of Pune. He is Master of Management Sciences degree in Finance. He is Fellow-IE, Fellow-IETE, Senior Member IEEE, Life Member SEMCI; ISSS; Vigyan Bharati; CEGR and Life Member at IDST He has total of 41 years of experience in design and development of Mechatronics systems for variety of armaments and weapon systems and has 14 years of experience in academics Management. Earlier he has worked as a Scientist and Group Director at DRDO. He has designed and developed various armament systems which now are in production. He has also worked as a consultant on operations, production, system design and strategic business development for defence industry & Defence PSUs. He was founder Principal at Maharshi Karve Stree Shikshan Samstha’s - Cummins College of Engineering for Women, Nagpur from 2011 to 2022. He has facilitated dozens of skill development courses for students which have benefited 300+ students during his tenure at Cummins college. He has introduced of 9 different Skill Development courses in the field of Defence and Aerospace sector at RTM Nagpur University. As a Director Technology and Innovation, he has developed a centre of Excellence in AI/ DS for Vidya Pratishthan at Pune. He contributed to form a Private University in Pune. He has more than 46 publications in various national/ international conferences and journals and has published 3 books.

Topic: Industry Academia Collaboration  

Biography:

Chandan Pramanik is the Director, Education at MathWorks based out of Bangalore. Chandan and his team help universities and institutions accelerate the pace of discovery, innovation, development, research and learning in engineering and science by accelerating the adoption and access of MATLAB & SIMULINK. Over the next few years, Chandan hopes to inculcate computational skills in the educational ecosystem as a fundamental skill for everyone so that students not only learn to code but also code to learn. Prior to joining MathWorks, Chandan was with Hewlett Packard Enterprise for 19 years where he helped customers be successful in their digital transformation journey.  He has experience in running complex business units, setting up and leading sales teams and channel teams. He has a Master’s in Business Administration in Operations Management from SP Jain Institute of Management, Mumbai and Bachelor’s in Mechanical Engineering from National Institute of Technology, Rourkela.

Topic: Connected Roads, Disconnected Future? Lessons from 25 Years of Vehicular Networking  

Abstract:

Over the past twenty-five years, the vision of connected vehicles has promised safer, smarter roads through networked communication. From DSRC to C-V2X, engineers have built increasingly capable systems, yet large-scale adoption remains elusive. This keynote traces the evolution of vehicular networking technologies, examines why technical success did not always translate into deployment, and argues that future progress must begin with application needs, not available technologies. Ultimately, it calls for a design philosophy where technology follows function, aligning connectivity, safety, and purpose in the next generation of intelligent transportation systems.

Biography:

Dr. Jeremy Blum is an associate professor of Computer Science and Chair of the Mathematics and Computer Science programs at the Pennsylvania State University (PSU), Harrisburg, PA, USA. Prior to joining Penn State Harrisburg, Dr. Blum worked as a research scientist at the Center for Intelligent Systems Research at the George Washington University. Dr. Blum received a D.Sc. in Computer Science and an M.S. in Computational Sciences, both from the George Washington University, as well as a B.A. in Economics from Washington University. Dr. Blum’s research interests include computer networks, computer security, and transportation safety. Dr. Blum’s previous work in this area includes work supported by the National Science Foundation, and the Washington State Department of Transportation. His paper on scalability and security challenges in inter-vehicle networks won the Top 10 Best Research Paper of the Decade Award from the IEEE Intelligent Transportation Systems Society.