Abstract | ||
---|---|---|
This paper describes a method for tracking regions in image sequences. Regions segmented from each frame by a motion segmentation technique are matched by using a relaxation procedure. Matching is based on measuring the similarity of the regions from the current frame and a list of regions corresponding to objects. A Kalman filter is used in order to estimate motion parameters. This filter uses a kinematic model which considers varying acceleration. This assumption allows the system to model the movement when objects are approaching the camera. The tracking method presented here has been successfully applied to traffic monitoring tasks, where it connects to other two computer vision based modules: motion segmentation and temporal integration |
Year | DOI | Venue |
---|---|---|
2000 | 10.1109/ICPR.2000.903743 | ICPR |
Keywords | Field | DocType |
traffic monitoring sequences,temporal integration,kalman filter,tracking regions,dynamic range,kalman filters,image matching,traffic engineering computing,computer vision based modules,relaxation theory,image segmentation,relaxation procedure,computerised monitoring,color image,kinematic model,motion estimation,optical tracking,inherent physical limitation,region similarity measurement,image sequences,image sequence region tracking,computer vision,kinematics,filtering theory,road traffic,motion segmentation,acquisition process,motion parameter estimation,pattern-selective image fusion,varying acceleration,kalman filtering,vehicle dynamics,parameter estimation,acceleration | Computer vision,Kinematics,Pattern recognition,Computer science,Segmentation,Kalman filter,Image segmentation,Vehicle dynamics,Acceleration,Artificial intelligence,Estimation theory,Motion estimation | Conference |
Volume | ISSN | ISBN |
3 | 1051-4651 | 0-7695-0750-6 |
Citations | PageRank | References |
7 | 0.65 | 9 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Badenas, J. | 1 | 7 | 0.65 |
Sanchiz, J.M. | 2 | 7 | 0.98 |
Pla, F. | 3 | 7 | 0.65 |