Title: DESCRIPTION LOGICS FOR CONTENT-BASED INDEXING AND RETRIEVAL OF VIDEO SURVEILLANCE

Year of Publication: 2012
Page Numbers: 294-305
Authors: Farhi Marir
Conference Name: The International Conference on Computing, Networking and Digital Technologies (ICCNDT2012)
- Bahrain

Abstract:


The paper presents The VIGILANT model which uses description logics to enhance object model for content and event-based indexing and retrieval of video surveillance. Annotations and indexes of video clips are captured in an underlying video-object model combining Object-Oriented (OO) modelling techniques and Description Logics (DLs) Knowledge representation. The OO technique model the static aspects of video clips and instances and their indexes will be stored in an Object-Oriented Database. The DLs model will extend the OO model to cater for the dynamic and incremental content descriptions of the video. The model is populated by automatic annotation and indexing of contents and events representing the extracted features and recognised objects from images captured by a video surveillance camera in a car park environment. The video knowledge is elicited using object-tracking technique, which automatically extracts moving objects such as cars and people and identifies their properties, then labels the events they are involved in e.g. a car entering the car park or a person getting off the car.