An Annotation Engine for Supporting Video Database Population

AbstractÐWe propose a novel four-step hybrid approach for retrieval and composition of video newscasts based on information contained in different metadata sets. In the first step, we use conventional retrieval techniques to isolate video segments from the data universe using segment metadata. In the second step, retrieved segments are clustered into potential news items using a dynamic technique sensitive to the information contained in the segments. In the third step, we apply a transitive search technique to increase the recall of the retrieval system. In the final step, we increase recall performance by identifying segments possessing creation-time relationships. A quantitative analysis of the performance of the process on a newscast composition shows an increase in recall by 59 percent over the conventional keyword-based search technique used in the first step.

show abstract

Section: Methodsmentioning

confidence: 99%

Data semantics for improving retrieval performance of digital news video systems

Ahanger

Little

2001

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…The output of Vane, raw content metadata, are stored in a SGML compliant format. To make the raw metadata queryable, it is translated into a relational database specific schema (miniSQL) using the sgml2sql tool [11]. Queries are issued using the Web interface, which is implemented using HTML and the Java language.…”

Section: Methodsmentioning

confidence: 99%

Data Semantics for Improving Retrieval Performance of Digital News Video Systems

Ahanger

Little

1999

Database Semantics

View full text Add to dashboard Cite

Abstract-We propose a novel four-step hybrid approach for retrieval and composition of video newscasts based on information contained in different metadata sets. In the first step, we use conventional retrieval techniques to isolate video segments from the data universe using segment metadata. In the second step, retrieved segments are clustered into potential news items using a dynamic technique sensitive to the information contained in the segments.In the third step, we apply a transitive search technique to increase the recall of the retrieval system. In the final step, we increase recall performance by identifying segments possessing creation-time relationships.A quantitative analysis of the performance of the process on a newscast composition shows an increase in recall by 59% over the conventional keyword-based search technique used in the first step.

show abstract

“…Video annotation is a hot issue in the fields of multimedia [2], and sports annotation and analysis are one of the most important applications. Many previous works are done in this area, such as MIT's football match analysis system [3], basketball analysis system developed by Saur [4], tennis ball analysis system by Sudhir [5], soccer analysis system by Gong [6], and so on.…”

Section: Introductionmentioning

confidence: 99%

Novel rule-based soccer annotation system

et al. 2002

View full text Add to dashboard Cite

This paper presents an automatic soccer annotation system. The system consists of 3 modules: 3D reconstruction module, behavior analysis module and annotation module. The first module reconstructs the 3D model of the soccer scene, including positions, velocities and acceleration of each player, and the trajectory of ball. According to these parameters and domain knowledge, behavior analysis module will recognize each player's action with a finite state machine. Then, annotation module will convert key player's behavior into annotation words. The system proves to be robust when errors of 3D reconstruction results are small.

show abstract

An Annotation Engine for Supporting Video Database Population

Cited by 10 publications

References 19 publications

Data semantics for improving retrieval performance of digital news video systems

Data semantics for improving retrieval performance of digital news video systems

Data Semantics for Improving Retrieval Performance of Digital News Video Systems

Novel rule-based soccer annotation system

Contact Info

Product

Resources

About