A visual query language for identifying temporal trends in video data

Video is becoming a popular medium for data collection. The challenge of analyzing video data is to abstract and conclude quantitative results from such a rich, qualitative medium. The focus of our research is to support video analysis by developing a user-friendly interactive visualization environment to query video data using spatio-temporal characteristics and to review visual results for trend analysis. We present our approach for identifying temporal trends in video data via querying for relationships between video annotations. Our approach allows users to analyze the video in terms of temporal relationships between events (e.g., events of type B frequently follow events of type A). We present a temporal visual query language for specifying relative temporal queries between sets of annotations. This query language builds on the notion of dynamic query filters and significantly extends them with temporal query support. It is tailored for temporal analysis-allowing users to pose queries as well as to browse the data in a temporally continuous manner, thereby aiding them in the discovery of temporal trends.