Abstract | ||
---|---|---|
Tracking an object without any prior information regarding its appearance is a challenging problem. Modern tracking algorithms treat tracking as a binary classification problem between the object class and the background class. The binary classifier can be learned offline, if a specific object model is available, or online, if there is no prior information about the object's appearance. In this pa... |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/TCSVT.2011.2133970 | IEEE Transactions on Circuits and Systems for Video Technology |
Keywords | Field | DocType |
Classification algorithms,Feature extraction,Nearest neighbor searches,Image representation,Algorithm design and analysis,Tracking | k-nearest neighbors algorithm,Computer vision,Dimensionality reduction,Pattern recognition,Computer science,Object model,Metric (mathematics),Feature extraction,Video tracking,Artificial intelligence,Statistical classification,Contextual image classification | Journal |
Volume | Issue | ISSN |
21 | 12 | 1051-8215 |
Citations | PageRank | References |
38 | 1.02 | 15 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Grigorios Tsagkatakis | 1 | 122 | 21.53 |
Andreas Savakis | 2 | 377 | 41.10 |