ONCCEE TEAM WINS CASCON People’s Choice Technology Showcase Award
Ocean Networks Canada’s Centre for Enterprise & Engagement (ONCCEE), in co-operation with IBM, is working to implement new software for real-time analysis of video data from the ocean. Phase 1 of the project developed the framework to allow scientists to define and create video analysis tools to help them in their research projects. The toolbox currently includes a video classifier, a particle detector, a motion detector and a contour detector tool. These tools will be used by researchers to help analyze the vast amounts of data being collected on the underwater networks. For example, the motion detector software was able to analyze two hours of video and identified 9 minutes of video with useful information for the scientists.
Future tools will be developed in collaboration with researchers on the VENUS and NEPTUNE Canada networks.
The results of this phase of the project was presented under the banner of “Ocean Networks Canada: Leveraging Parallelism in Deep Sea Video Analysis” in the poster section of CASCON 2011; the team won the People’s Choice Technology Showcase Award. They were competing with over 60 other research teams from across Canada. The Center for Advanced Studies (CAS) Canada Research was established at the IBM Toronto Lab in 1990. Its mission is to strengthen the links between research communities. Annual conferences bring together thousands of research participants from universities across North America. The theme for this year’s Conference was "Instrumented. Interconnected. Intelligent." Presenters at the conference were Maia Hoeberechts (NEPTUNE), Daniel Conti (ONC Coop student), Josh Erickson (ONC Coop student) and Aleya Gebali (UVic Master’s student).
Project Background:
NEPTUNE Canada and VENUS have gathered immense collections of image data through their cable-linked seafloor networks; however, analysis is slow because the vast amounts of data can only be observed by a person in small increments. The new system will allow more efficient access to this rich source of information about marine life on the seafloor.
Collaboration on this project encompasses the broader University of Victoria (UVic) and global community. UVic’s Dr. Alexandra Branzan-Albu (Assistant Professor of Computer Science and Engineering) and her graduate student Aleya Gebali (M.A.Sc. candidate) have developed an algorithm to detect salient events in large underwater video databases which meets the specific needs of NEPTUNE Canada and VENUS.
The ONCCEE software team developed a toolbox for automatic detection of movement and of objects-of-interest. Two UVic Co-op students, Josh Erickson and Daniel Conti, and Celina Gibbs, PhD. (UVic Computer Science Dept.) were responsible for adapting the algorithms to the Streams environment. They also worked with the Digital Management and Archive System (DMAS) group to properly integrate this new software with the existing database system.
