Abstract：This paper proposes a bi-camera real-time tracking system which is composed of two cameras: one is a static camera,and the other is a removable camera.The system implements real-time tracking of moving object by making use of the respective advantages and overcoming the disadvantages of the two cameras in the system.The system structure and functional partition of the bi-camera system are presented.The object matching on two image planes of the two cameras is achieved by homography relation educed from an approximate camera projective model.In the system,a 2D motion model is established on the image plane of the static camera to predict the position of the object by Kalman filter,then by using homography relation,the predicted position of object can be obtained on the image plane of the dynamic camera.Then,the rotation angle of the dynamic camera platform is calculated,and the servo control of the dynamic camera is implemented.
[1] Krumm J,Harris S,Meyers B,et al.Multi-camera multi-person tracking for EasyLiving[A]. Proceedings of the 3rd IEEE International Workshop on Visual Surveillance[C]. Los Alamitos,CA,USA:IEEE Computer Society,2000.3-10.
[2] Fuentes L M,Velastin S A.People tracking in surveillance applications[A]. Proceedings of the 2nd IEEE International Workshop on Performance Evaluation on Tracking and Surveillance[C]. Piscataway,NJ,USA:IEEE,2001.http//www.cvg.rdg.ac.uk/PETS2001/PETSFINALPDF/fuentes.pdf.
[3] Cai Q,Aggarwal K.Tracking human motion using multiple cameras[A]. Proceedings of the International Conference on Pattern Recognition[C]. Los Alamitos,CA,USA:IEEE Computer Society,1996.68-72.
[4] Wei G,Petrushin V,Gershman A.Multiple-camera people localization in a cluttered environment[A]. Proceedings of the Fifth International Workshop on Multimedia Data Mining[C]. http://www.accenture.com/NR/rdonlyres/7B3E4EEE-2BCC-45EB-ADDF-0357F301 F1 C4/0/people localization.pdf.
[5] Shiao Y-S.Design and implementation of real-time tracking system based on vision servo control[J]. Tamkang Journal of Science and Engineering,2001,4(1):45-58.
[6] Weng J,Cohen P,Herniou M.Camera calibration with distortion models and accuracy evaluation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(10):965-980.
[7] Wren C,Azarbayejani A,Darrell T,et al.Pfinder:Real-time tracking of the human body[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):780-785.
[8] Stauffer C,Grimson W E L.Adaptive background mixture models for real-time tracking[A]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C]. Los Alamitos,CA,USA:IEEE,1999.246-252.
[9] Jain R,Kasturi R,Schunck B G.Machine Vision(英文版)[M]. 北京:机械工业出版社,2003.
[10] Chien Y,Huag Y,Jeng S,et al.Real-time surveillance system by use of the face understanding technologies[A]. Proceedings of the 7th Digital Image Computing:Techniques and Applications[C]. http://www.cmis.csiro.au/Hugues.Talbot/dicta2003/cdrom/pdf/0741.pdf.
[11] Ke Y,Sukthankar R,Hebert M.Efficient visual event detection using volumetric features[A]. Proceedings of the International Conference on Computer Vision[C]. Los Alamitos,CA,USA:IEEE Computer Society.2005.166-173.
[12] Visser R,Sebe N,Bakker E.Object recognition for video retrieval[A]. Proceedings of the International Conference on Image and Video Retrieval[C]. Bedin,Germany:Springer-Verlag,2002.250-259.
[13] Toreyin B U,Dedeoglu Y,Gudukbay U,et al.Computer vision based method for real-time fire and flame detection[J]. Pattern Recognition Letters,2006,27(1):49-58.
