The concept of automated incident detection is based on the idea of finding suitable image cues that can represent the specific event of interest with minimum overlapping with other classes. In this paper motion is adopted as the main cue for abnormal incident detection. First, scene motion information is extracted by a hardware implemented exhaustive block matching motion detector, followed by a stage of motion segmentation and filtering. The extracted motion information from sequences with normal events is fed to a neural network as training data. Hence, the system is first set to learn the usual motion patterns in the scene as a means of detecting abnormal motion patterns as they arise. Some of the previous work in this field is presented. The neural network model, the run-time techniques employed to detect the abnormal agents and a typical example of implementation, are described.
Image processing system for pedestrian monitoring using neural classification of normal motion patterns
Measurement and Control ; 32 , 9 ; 261-264
1999
4 Seiten, 11 Quellen
Aufsatz (Zeitschrift)
Englisch
Pedestrian Detection Using Global-Local Motion Patterns
Springer Verlag | 2007
|Image Monitoring Motorway: Pedestrian Detection Using Image Processing
British Library Conference Proceedings | 1996
|Pedestrian Classification from Moving Platforms using Cyclic Motion Pattern
British Library Conference Proceedings | 2005
|