Video Analytics and Surveillance softwares for real-time analysis (intrusion, loitering, tracking) and post-mortem analysis (video search, summarization)
CORDS (COResets and Data Subset selection), DISTIL (Deep dIverSified inTeractIve Learning), SPEAR (Semi-suPervisEd dAta pRogramming), SUBMODLIB (SUBMODular optimization LIBrary)
Optical Character Recognition (OCR) and Scene text Recognition for Indian languages and Indian context
Video Analytics softwares for security applications includes real-time analysis such as intrusion, loitering, tracking (codenamed SurakshaVyuha, now being productized by SrivisifAI as 3rdAI) and post-mortem analysis - video search (Jigyasa), summarization (VideoSummy and VISIOCITY). These are ongoing projects, initiated by Prof. Ganesh Ramakrishnan in 2016, which got incorporated in 2017 as a part of the National Centre of Excellence in Technology for Internal Security (NCETIS). NCETIS has been strongly facilitating as well as promoting the work to the Indian Navy, Indian Army and Several state police forces. We also feature below video analytics for compliance and quality monitoring (Drishti), a work with the Ministry of Rural Development, Government of India.
Now being productized as 3rdAI, this CCTV Video Analytics solution includes real-time intrusion detection, perimeter monitoring, loitering detection, object tracking, etc.
Credentials to use the software can be provided upon acknowledgement/request.
Jigyasa is a Video Repository Indexing and Search platform with features like text search, face search, etc.
Credentials to use the software can be provided upon acknowledgement/request.
Videosummy can condense hours’ worth of video into a couple of minutes, by preserving key events and vignettes from your original video and removing repetitive visual information. Read in details, our VISIOCITY dataset and benchmark algorithms and evaluations for video summarization across different domains such as surveillance, TV shows, sports, education, events (birthdays and weddings), and different facets of summarization therein.
Drishti is an ongoing project with the Ministry of Rural Development (MoRD), Government of India to provide automated compliance and quality monitoring solution for their DDU-GKY skill development scheme (Deen Dayal Upadhyaya Gramina Kaushalya Yojana). It supports analytics like instructor face recognition, student count, uniform compliance, punctuality detection etc. on classroom videos.
Softwares and libraries for data efficient machine learning with less data.
CORDS (COResets and Data Subset selection)
DISTIL (Deep dIverSified inTeractIve Learning)
SPEAR (Semi-suPervisEd dAta pRogramming)
SUBMODLIB (SUBMODular optimization LIBrary)
Visit the project page https://decile.org
Optical Character Recognition (OCR) and Scene text Recognition for Indian languages and Indian context
End-to-end framework for Error Detection and Corrections in Indic-OCR. The system inputs a PDF file of a book, and obtains the OCR output using IndSenz OCR and Google OCR, and then corrects the OCRed text, and provides suggestions for words that probably have mistakes during the OCR method, hence any mistakes during the OCR process can be corrected by the user.
Selected publications related to the projects.
In Proceedings of The 11th IEEE Winter Conference on Applications of Computer Vision (WACV 2023).
Accepted paper at the Thirty-sixth Conference on Neural Information Processing Systems (Neurips 2022).
Accepted paper at the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi (Demo paper).
In Proceedings of The 36th AAAI Conference on Artificial Intelligence (AAAI 2022).
In Proceedings of The 35th AAAI Conference on Artificial Intelligence (AAAI 2021).
Accepted paper at the 38th International Conference on Machine Learning (ICML 2021).
Accepted paper at the 38th International Conference on Machine Learning (ICML 2021).
Accepted paper at the 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021 Findings).
Accepted at The 29th ACM International Conference on Multimedia (ACMM 2021)
Accepted at ICDAR 2021 Workshop on Camera-Based Document Analysis and Recognition (CBDAR 2021, 9TH EDITION)
Accepted paper at The 44th International ACM Conference on Research and Development in Information Retrieval (SIGIR), Resource Track, 2021.
In Proceedings of The 9th IEEE Winter Conference on Applications of Computer Vision (WACV 2021).
In Proceedings of The 28th ACM International Conference on Multimedia (ACMM 2020), Seattle, USA.
Accepted paper at the 21st INTERSPEECH Conference (Interspeech 2020), Shanghai, China
Accepted paper at the 7th IEEE Winter Conference on Applications of Computer Vision (WACV), 2019, Hawaii, USA.
Accepted paper at the 7th IEEE Winter Conference on Applications of Computer Vision (WACV), 2019, Hawaii, USA.
Accepted paper at the 7th IEEE Winter Conference on Applications of Computer Vision (WACV), 2019, Hawaii, USA.
Accepted paper at the 7th IEEE Winter Conference on Applications of Computer Vision (WACV), 2019, Hawaii, USA.
Best demo paper award. In Proceedings of the ACM India Joint International Conference on Data Science and Management of Data, CoDS-COMAD '19, Kolkota, India.
In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18), New Orleans, Louisiana, USA.
In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI-18), New Orleans, Louisiana, USA.
International Conference on Document Analysis and Recognition (ICDAR) 2017, Kyoto, Japan.
1st International Workshop on Open Services and Tools for Document Analysis (ICDAR- OST) 2017, Kyoto, Japan.
Proceedings of the 17th World Sanskrit Conference, Vancouver, 2018.
Research and Innovation Symposium in Computing (RISC) 2017 (Most Admiring Poster Presentation Award), IIT-Bombay, India.
In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Beijing, China, July - 2015
Official Facebook Post by Govt. of India
Ganesh Ramakrishnan, Faculty, CSE (Principal Investigator); Rishabh Iyer, Faculty, UT Dallas (Collaborator)
Vishal Kaushal (Research Scholar, Video Analytics); Rohit Saluja (Research Scholar, Document Analytics
Pankaj Singh, Aify (Collaborator)
SrivisifAI Technologies Pvt. Ltd. (Industry Partner)
For further details or if you are interested in using the softwares.