Name
Abstract | ||
|---|---|---|
In this paper, we present a framework for active contour-based visual tracking using level sets. The main components of our framework include contour-based tracking initialization, color-based contour evolution, adaptive shape-based contour evolution for non-periodic motions, dynamic shape-based contour evolution for periodic motions, and the handling of abrupt motions. For the initialization of contour-based tracking, we develop an optical flow-based algorithm for automatically initializing contours at the first frame. For the color-based contour evolution, Markov random field theory is used to measure correlations between values of neighboring pixels for posterior probability estimation. For adaptive shape-based contour evolution, the global shape information and the local color information are combined to hierarchically evolve the contour, and a flexible shape updating model is constructed. For the dynamic shape-based contour evolution, a shape mode transition matrix is learnt to characterize the temporal correlations of object shapes. For the handling of abrupt motions, particle swarm optimization is adopted to capture the global motion which is applied to the contour in the current frame to produce an initial contour in the next frame. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TIP.2012.2236340 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
adaptive shape model,level set,markov random field theory,local color information,color-based contour evolution,posterior probability estimation,adaptive signal processing,active contour-based visual tracking,particle swarm optimisation,matrix algebra,abrupt motion,set theory,optical flow-based algorithm,estimation theory,shape updating model,abrupt motion handling,markov processes,active contour-based tracking,shape mode transition matrix,temporal correlation,dynamic shape-based contour evolution,tracking,image sequences,adaptive shape-based contour evolution,nonperiodic motion,dynamic shape model,correlation methods,contour-based tracking initialization,image colour analysis,probability,particle swarm optimization,global shape information,image motion analysis,shape,optical imaging,computer vision | Active contour model,Computer vision,Active shape model,Pattern recognition,Markov random field,Level set,Adaptive filter,Pixel,Artificial intelligence,Initialization,Optical flow,Mathematics | Journal |
Volume | Issue | ISSN |
22 | 5 | 1941-0042 |
Citations | PageRank | References |
15 | 0.75 | 34 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weiming Hu | 1 | 5300 | 261.38 |
| Xue Zhou | 2 | 194 | 11.81 |
| Wei Li | 3 | 54 | 6.00 |
| Wenhan Luo | 4 | 214 | 19.48 |
| Xiaoqin Zhang | 5 | 952 | 72.31 |
| Stephen J. Maybank | 6 | 4105 | 493.12 |