VIRTUAL RESEARCH SYMPOSIUM SERIES BY IEEE COMPUTATIONAL INTELLIGENCE SOCIETY - GUJARAT CHAPTER
About :
The IEEE Computational Intelligence Society Chapter - IEEE Gujarat Section brings in a Symposium series to foster exchange of ideas and experience by the young researchers. It provides a discussion forum for advancement of their research and gain feedback on research work in the domain of computational intelligence. This is an initiative by IEEE CIS chapter - IEEE Gujarat section to build community for intellectual exchange and support the budding researchers.
Intended Participants: Anyone interested in Computational Intelligence Domain
Details of the next Symposium talk
Topic: Person Retrieval from unconstrained surveillance videos
About Speaker: Hiren J Galiyawala is a PhD scholar at Ahmedabad University and working as a Data Scientist at Rydot Infotech Pvt. Ltd. He obtained a Bachelor's degree (ECE) in 2007 from VNSGU and a Master's degree (Digital Systems – Electronics) in 2010 from the College of Engineering Pune / University of Pune, India. He has 11+ years of experience including industry, research, and academic. His research interest is in computer vision, biometrics, and video analytics. His publications are in reputed conferences and journals with leading publishers – IEEE, Elsevier, and Springer. He also holds professional certifications like International Software Testing Qualifications Board (ISTQB) and IBM Certified Solution Designer – Rational Functional Tester for JAVA.
Registration: Interested may please register at https://forms.gle/6jHs8cy53cvrpu8Q8 and we will mail you the meeting details.
Abstract:
Recent advancement of research in biometrics, computer vision, and natural language processing has discovered opportunities for person retrieval from surveillance videos using a textual query. The prime objective of a surveillance system is to locate a person using a description, e.g., a tall man with a white t-shirt and blue jeans carrying a backpack. He has brown hair. Such a description contains attributes like gender, height, type of clothing, colour of clothing, hair colour, and accessories. Such attributes are formally known as soft biometrics. They help bridge the semantic gap between a human description and a machine as a textual query contains the person's soft biometric attributes. Traditional biometric (e.g., face) fails to locate a person in the surveillance video due to low resolution, distance, and unconstrained environment. In such cases, soft biometric attributes like gender, clothing colour, and type are still deducible. It is also not feasible to manually search through huge volumes of surveillance footage to retrieve a specific person. Hence, automatic person retrieval using vision and language-based algorithms is becoming popular.
Date: 26.07.2021
Time: 11.00 am to 11.50 am: 35 Mins talk + 15 Mins. Q&A
Speaker: Mr. Hiren Galiyawala, PhD Scholar, Ahmedabad University, India
Supervisor: Dr Mehul S Raval, Professor, Ahmedabad University, India
Date and Time
Location
Hosts
Registration
- Date: 26 Jul 2021
- Time: 11:00 AM to 11:50 AM
- All times are (GMT+05:30) Asia/Calcutta
-
Add Event to Calendar
- Ahmedabad, Gujarat
- India
Speakers
Hiren J Galiyawala
Person Retrieval from unconstrained surveillance videos
Recent advancement of research in biometrics, computer vision, and natural language processing has discovered opportunities for person retrieval from surveillance videos using a textual query. The prime objective of a surveillance system is to locate a person using a description, e.g., a tall man with a white t-shirt and blue jeans carrying a backpack. He has brown hair. Such a description contains attributes like gender, height, type of clothing, colour of clothing, hair colour, and accessories. Such attributes are formally known as soft biometrics. They help bridge the semantic gap between a human description and a machine as a textual query contains the person's soft biometric attributes. Traditional biometric (e.g., face) fails to locate a person in the surveillance video due to low resolution, distance, and unconstrained environment. In such cases, soft biometric attributes like gender, clothing colour, and type are still deducible. It is also not feasible to manually search through huge volumes of surveillance footage to retrieve a specific person. Hence, automatic person retrieval using vision and language-based algorithms is becoming popular.
Biography:
Hiren J Galiyawala is a PhD scholar at Ahmedabad University and working as a Data Scientist at Rydot Infotech Pvt. Ltd. He obtained a Bachelor's degree (ECE) in 2007 from VNSGU and a Master's degree (Digital Systems – Electronics) in 2010 from the College of Engineering Pune / University of Pune, India. He has 11+ years of experience including industry, research, and academic. His research interest is in computer vision, biometrics, and video analytics. His publications are in reputed conferences and journals with leading publishers – IEEE, Elsevier, and Springer. He also holds professional certifications like International Software Testing Qualifications Board (ISTQB) and IBM Certified Solution Designer – Rational Functional Tester for JAVA.