|go to week of Apr 28, 2013||28||29||30||1||2||3||4|
|go to week of May 5, 2013||5||6||7||8||9||10||11|
|go to week of May 12, 2013||12||13||14||15||16||17||18|
|go to week of May 19, 2013||19||20||21||22||23||24||25|
|go to week of May 26, 2013||26||27||28||29||30||31||1|
The ‘semantic analysis of video’ project at ADSC investigates and develops a computational framework suitable for the semantic analysis of complex activities present in video. The project contributes to the main vision of the Interactive Digital Media (IDM) subprogram of resolving the information overload problem by finding and modelling complex activities in video. In this talk I will talk about the research progress and contributions of the project. Our current primary application is sports video analysis where the goal is to detect important events and activities in sports videos. To test our framework we are developing AutoScout, our working sports video analysis prototype. Our new video analysis techniques are also used in the IDM Smart Office Integrative Project where we track moving person across multiple registered cameras installed in the ADSC office.
Indriyati Atmosukarto is a Research Scientist at the Advanced Digital Sciences Center (ADSC) in Singapore. Her research interest includes computer vision, machine learning, and medical image analysis. She is currently working on the “Semantic Analysis of Video” project at ADSC. Prior to joining ADSC, she was a Postdoctoral Senior Fellow at Seattle Children’s Research Institute. Her postdoctoral work was focused on developing ways to represent and quantify 3D facial shape deformation in children with craniofacial disorders. She earned her Ph.D. in Computer Science from the University of Washington, Seattle. Her dissertation work was on applying computer vision and machine learning techniques to analyse and quantify 3D shapes for similarity-based retrieval and classification for general computer vision and medical applications.