Guest editors' introduction: content-based access of image and video libraries
Computer Vision and Image Understanding - Special issue on content-based access for image and video libraries
Computer Vision
Everything You Wanted to Know About MPEG-7: Part 1
IEEE MultiMedia
Object Tracking and Event Recognition in Biological Microscopy Videos
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 4
Hi-index | 0.00 |
We present a system for extracting and organizing semantic content metadata from biological microscopy videos featuring living cells. The system uses image processing and understanding procedures to identify objects and events automatically within the digitized videos, thus leading to the generation of content information (semantic metadata) of high information value by automated analysis of their visual content. When such metadata are properly organized in a searchable database conformed with our proposed model, a content-based video query and retrieval system may be developed to locate particular objects, events or behaviours. Furthermore these metadata can be applied to find hidden semantic relationships such as correlations between behavioural alterations and changes in environmental conditions of cells. The suitability and functionality of the proposed metadata organizational model is demonstrated by the automated analysis of five different types of biological experiments, recording epithelial wound healing, bacterial multiplication, the rotations of tethered bacteria, and the swimming of motile bacteria and of human sperm. We have named our prototype analytical system VAMPORT (video automated metadata production by object recognition and tracking). We conclude that the use of an audiovisual content description standard such as MPEG7 will contribute valuably towards the interoperability of the system.