Name
Title | ||
|---|---|---|
Video object segmentation using Bayes-based temporal tracking and trajectory-based region merging |
Abstract | ||
|---|---|---|
A novel unsupervised video object segmentation algorithm is presented, aiming to segment a video sequence to objects: spatiotemporal regions representing a meaningful part of the sequence. The proposed algorithm consists of three stages: initial segmentation of the first frame using color, motion, and position information, based on a variant of the K-means-with-connectivity-constraint algorithm; a temporal tracking algorithm, using a Bayes classifier and rule-based processing to reassign changed pixels to existing regions and to efficiently handle the introduction of new regions; and a trajectory-based region merging procedure that employs the long-term trajectory of regions, rather than the motion at the frame level, so as to group them to objects with different motion. As shown by experimental evaluation, this scheme can efficiently segment video sequences with fast moving or newly appearing objects. A comparison with other methods shows segmentation results corresponding more accurately to the real objects appearing on the image sequence. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/TCSVT.2004.828341 | Circuits and Systems for Video Technology, IEEE Transactions |
Keywords | Field | DocType |
k-means-with-connectivity-constraint algorithm,bayes-based temporal tracking,segment video sequence,index terms—image sequence analysis,image sequence,video object segmentation algorithm,trajectory-based region,segmentation result,initial segmentation,temporal tracking,proposed algorithm,different motion,temporal tracking algorithm,tra- jectory-based merging,video segmentation.,video sequence,rule based,video compression,k means,image segmentation,bayes classifier,image classification,information retrieval,indexing terms,human interaction,indexation,merging,trajectory | Computer vision,Object detection,Block-matching algorithm,Scale-space segmentation,Pattern recognition,Computer science,Segmentation,Image segmentation,Video tracking,Artificial intelligence,Contextual image classification,Bayes classifier | Journal |
Volume | Issue | ISSN |
14 | 6 | 1051-8215 |
Citations | PageRank | References |
37 | 1.64 | 32 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| V. Mezaris | 1 | 293 | 16.26 |
| I. Kompatsiaris | 2 | 282 | 15.61 |
| michael g strintzis | 3 | 1095 | 79.71 |