Name
Abstract | ||
|---|---|---|
In this paper we propose a novel implementation of the level set method that achieves real-time level-set-based video tracking. In our fast algorithm, the evolution of the curve is realized by simple operations such as switching elements between two linked lists and there is no need to solve any partial differential equations. Furthermore, a novel procedure based on Gaussian filtering is introduced to incorporate boundary smoothness regularization. By replacing the standard curve length penalty with this new smoothing procedure, further speedups are obtained. Another advantage of our fast algorithm is that the topology of the curves can be controlled easily. For the tracking of multiple objects, we extend our fast algorithm to maintain the desired topology for multiple object boundaries based on ideas from discrete topology. With our fast algorithm, a real-time system has been implemented on a standard PC and only a small fraction of the CPU power is used for tracking. Results from standard test sequences and our realtime system are presented. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/CVPR.2005.294 | CVPR (2) |
Keywords | Field | DocType |
video tracking,video signal processing,real-time level-set-based video tracking,curve evolution,discrete topology,curve fitting,linked lists,multiple object boundary,real-time system,partial differential equation,multiple object,standard curve length penalty,fast algorithm,standard test sequence,tracking,gaussian processes,object detection,computer vision,partial differential equations,boundary smoothness regularization,filtering theory,multiple object tracking,real-time tracking,standard pc,level set method,real-time systems,gaussian filtering process,new smoothing procedure,curve topology,level sets,filtering,real time,level set,real time system,system testing,videoconference,real time systems,topology | Computer vision,Curve fitting,Computer science,Level set method,Level set,Filter (signal processing),Smoothing,Video tracking,Gaussian process,Artificial intelligence,Discrete space | Conference |
Volume | ISSN | ISBN |
2 | 1063-6919 | 0-7695-2372-2 |
Citations | PageRank | References |
83 | 4.49 | 15 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yonggang Shi | 1 | 598 | 54.47 |
| W. Clem Karl | 2 | 224 | 35.45 |