Support vector tracking.IEEE Trans Pattern Anal Mach Intell. 2004 Aug; 26(8):1064-72.IT
Abstract
Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow-based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using SVT for vehicle tracking in image sequences.
MeSH
AlgorithmsArtificial IntelligenceComputer GraphicsImage EnhancementImage Interpretation, Computer-AssistedImaging, Three-DimensionalInformation Storage and RetrievalMovementNumerical Analysis, Computer-AssistedPattern Recognition, AutomatedReproducibility of ResultsSensitivity and SpecificitySignal Processing, Computer-AssistedSubtraction TechniqueVideo Recording
Pub Type(s)
Comparative Study
Evaluation Study
Journal Article
Validation Study
Language
eng
PubMed ID
15641735
Citation
Avidan, Shai. "Support Vector Tracking." IEEE Transactions On Pattern Analysis and Machine Intelligence, vol. 26, no. 8, 2004, pp. 1064-72.
Avidan S. Support vector tracking. IEEE Trans Pattern Anal Mach Intell. 2004;26(8):1064-72.
Avidan, S. (2004). Support vector tracking. IEEE Transactions On Pattern Analysis and Machine Intelligence, 26(8), 1064-72.
Avidan S. Support Vector Tracking. IEEE Trans Pattern Anal Mach Intell. 2004;26(8):1064-72. PubMed PMID: 15641735.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR
T1 - Support vector tracking.
A1 - Avidan,Shai,
PY - 2005/1/12/pubmed
PY - 2005/2/11/medline
PY - 2005/1/12/entrez
SP - 1064
EP - 72
JF - IEEE transactions on pattern analysis and machine intelligence
JO - IEEE Trans Pattern Anal Mach Intell
VL - 26
IS - 8
N2 - Support Vector Tracking (SVT) integrates the Support Vector Machine (SVM) classifier into an optic-flow-based tracker. Instead of minimizing an intensity difference function between successive frames, SVT maximizes the SVM classification score. To account for large motions between successive frames, we build pyramids from the support vectors and use a coarse-to-fine approach in the classification stage. We show results of using SVT for vehicle tracking in image sequences.
SN - 0162-8828
UR - https://www.unboundmedicine.com/medline/citation/15641735/Support_vector_tracking_
DB - PRIME
DP - Unbound Medicine
ER -