Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

Simon Fraser University

$31,000.00

Digital video analysis based on contexts

FY 2012-13

Summary
Digital video carries rich multimedia information and it involves insurmountable amount of data. In recent years, researchers have advocated that contextual information in the video is vital for understanding its content so its processing and retrieval can be more reliable. Because of its additional time dimension, digital video indeed facilitates contextual analysis. However, context itself is an elusive subject. Although simple visual features (color, texture, shape, etc.) and their geometric and temporal relationships can provide some contextual information, they are often limited and unreliable. We propose two novel concepts: Saliency Context and Activity Context, because they provide additional and essential cues for visual object-based video analysis. Research issues pertinent to their descriptions and matching will be investigated. This research is a continuation of our work in visual object extraction and reconstruction from Active Video, where videos are obtained with purposive camera movements and aimed at objects of interest. Multiple cues and descriptors at multiple scales will be incorporated to better represent the contextual information. Moreover, efficient matching algorithms based on convex programming and machine leaning will be explored. The long-term objective of my research is to advance the knowledge in visual object-based image and video processing and analysis. It is motivated by the cues from the intelligent human vision system. In this proposed research, projects in several application areas such as video summarization and context-aware visual tracking will be conducted to demonstrate the potential for more efficient and effective representation and matching of visual objects in digital video, and to seek possible technology transfer.
Program
Discovery Grants Program - Individual
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
36726-2010
Name nom
Li, ZeNian
Department département
Computing Science, School of
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2010
Award amount
31000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Partie
3
Nb partie
5
Application title
Digital video analysis based on contexts
Keyword
NSERC
Application summary
Digital video carries rich multimedia information and it involves insurmountable amount of data. In recent years, researchers have advocated that contextual information in the video is vital for understanding its content so its processing and retrieval can be more reliable. Because of its additional time dimension, digital video indeed facilitates contextual analysis. However, context itself is an elusive subject. Although simple visual features (color, texture, shape, etc.) and their geometric and temporal relationships can provide some contextual information, they are often limited and unreliable. We propose two novel concepts: Saliency Context and Activity Context, because they provide additional and essential cues for visual object-based video analysis. Research issues pertinent to their descriptions and matching will be investigated. This research is a continuation of our work in visual object extraction and reconstruction from Active Video, where videos are obtained with purposive camera movements and aimed at objects of interest. Multiple cues and descriptors at multiple scales will be incorporated to better represent the contextual information. Moreover, efficient matching algorithms based on convex programming and machine leaning will be explored. The long-term objective of my research is to advance the knowledge in visual object-based image and video processing and analysis. It is motivated by the cues from the intelligent human vision system. In this proposed research, projects in several application areas such as video summarization and context-aware visual tracking will be conducted to demonstrate the potential for more efficient and effective representation and matching of visual objects in digital video, and to seek possible technology transfer.