Mysuru, July 21:- GSSS Institute of Engineering and Technology for Women, Mysuru, IEEE Student Branch and IEEE WIE Affinity Group in association with IEEE Bengaluru Section and IEEE Circuits and Systems (CAS) Society Bengaluru chapter, organised Webinar on “Deep learning-bases video analytics for surveillance IoT applications” by Dr Supavadee Aramvith, associate professor, Department of Electrical Engineering, Chulalongkorn University, Thailand and Candidate, 2021-2022 IEEE region 10 director-elect.
Dr Manjula G, associate professor, Department of TCE, welcomed the panel members, resource persons and participants.
The webinar was attended by convener Dr Parameshachari B D, professor and head, GSSSIETW, IEEE Student Branch Counsellor GSSSIETW.
The programme was coordinated by Keerthi Kumar M, assistant professor, Department of TCE, GSSSIETW, Mysuru.
Dr Aramvith initiated the webinar session on “Deep learning-bases video analytics for surveillance IoT applications. In her talk, she expressed that, main motivation for choosing video surveillance was to enhance public safety, and also discussed the major challenges faced to arrive at the solutions. She gave information about the distinct features of video analytics which includes person detection and tracking, image super-resolution, human feature extraction, face cataloging, monitoring and warning, person tracking through multiple cooperative cameras. She spoke about the research opportunities in the surveillance of video analytics. She explained with an example to train and test machine learning model for ‘Video analytics surveillance for IoT applications.’
Dr Aramvith discussed the current trends and researches in video analytics. As surveillance cameras have been widely installed worldwide, although the main purpose of those cameras is for monitoring, the most significant task is to be able to analyze video contents and extract useful information. Deep learning-based computer vision techniques utilizing a multi-layer neural network is drastically improving the performance of video analytics to a certain extent. Several on-going types of research on deep learning-based video analytics such as image super-resolution, real-time multiple face recognition systems, video anomaly detection and several implementations of embedded video analytic system on FPGA and ‘Single board computers’ were discussed. Some possible scenarios of utilising video analytics, IoT for Industries were also mentioned.
Dr Shivakumar M, principal, GSSSIETW, Mysuru, gave the concluding remarks for this webinar. Dr Jalaja S, IEEE CAS Bengaluru chapter, embraced as a panelist for this webinar series.
The participants expressed that this webinar gave valuable inputs and most of the doubts related to “Deep learning-bases video analytics for surveillance IoT applications” were cleared by the resource person. (MR)