In this area of research, we focus on the semantic analysis and interpretation of videos and images. The aim is to provide more intuitive and enabling technologies for the wider community.

This research is currently focused on the analysis and mining of the visual content of video and image data. Other modalities such as audio and text are under investigation, in collaboration with the DCAPI research group. Scene classification and understanding, motion analysis, object detection, classification, and tracking are among the main tasks. Techniques to incorporate knowledge, ontology and spatio-temporal information in order to better interpret the scene are also under investigation.

Applications of this research include video segmentation, indexing, abstraction/skimming, classification/categorisation, scene understanding and event detection, semantic information extraction, and semantic-based video search and retrieval.

Investigators

• Amjad Altadmri
• Amr Ahmed
  

Representative Publications

Ahmed, A. (2008): Video representation and processing for multimedia data mining, book chapter in “Semantic Mining Technologies for Multimedia Databases”, IGI Global, To Appear.

Search Publications using ePrints: http://eprints.lincoln.ac.uk