Within the context of the recently published Home Office Police Science and Technology Strategy , the strate-gic objective of the REVEAL project is to promote those key technologies which will enable automated extraction of evidence from CCTV archives, and to allow integration within existing HOLMES2 crime management sys-tems. These key issues can be summarised as the following scientific objectives:
- To develop models and algorithms for capturing the conceptual structure (i.e. the Visual Evidence Thesaurus) underpinning the work of surveillance expert's annotating video streams, based on corpus-based lexicography and terminology, and making explicit the link between linguistic and meta-data content.
- To develop methods of automatically characterising CCTV sequences (including distinguishing between in-door and outdoor scenes, near and far-fields, sparse and crowded scenes) and extracting the semantic land-scape (including spatio-temporal activity, geometric calibration, and the occlusion structure of the scene).
- To develop crowd models which can capture the global spatio-temporal motion characteristics of multi-directional people flows, and to develop the image processing algorithms that populate such models while op-erating in high levels of visual occlusion.
- To develop a rich Surveillance Meta-data Model for describing extracted image content including camera and scene descriptor, the spatio-temporal semantic landscape, crowd dynamics, as well as the more classical mov-ing object descriptors.
- To develop methods of integrating the linguistic structure (the Visual Evidence Thesaurus) and the visual-content (the Surveillance Meta-Data Model) through co-learning to enable the automatic annotation of video data streams, and facilitate the retrieval of video evidence from high-level queries.
 Police Science and Technology Strategy 2003-2008, Home Office Policy Unit, January 16. (2003)