Title :
3-D model-based people detection & tracking
Author :
Garibotto, Giovanni
Author_Institution :
Elsag spa, Genova
Abstract :
The paper describes a method for people detection and tracking from multi-camera views. The proposed approach is based on 3D models of the person shape, where motion tracking is carried out in 3D space with re-projection onto calibrated images to perform target validation according to a prediction-verification paradigm. Multiple cameras with partial overlap can be used to cover a much wider area. The referred examples are based on the data base from PETS 2006 video sequences and a data base from EU-ISCAPS demonstration environment.
Keywords :
image motion analysis; object detection; 3D model-based people detection; motion tracking; multicamera views; people tracking; prediction-verification paradigm; Calibration; Cameras; Humans; Layout; Object detection; Positron emission tomography; Robustness; Shape; Target tracking; Trajectory;
Conference_Titel :
Advanced Video and Signal Based Surveillance, 2007. AVSS 2007. IEEE Conference on
Conference_Location :
London
Print_ISBN :
978-1-4244-1696-7
Electronic_ISBN :
978-1-4244-1696-7
DOI :
10.1109/AVSS.2007.4425375
