Support vector tracking
Shai Avidan · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2004
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.
Cited by 1,040 works. doi:10.1109/tpami.2004.53
Authors
References
- The Nature of Statistical Learning Theory
- Support-Vector Networks
- Rapid object detection using a boosted cascade of simple features
- A Tutorial on Support Vector Machines for Pattern Recognition
- Example-based learning for view-based human face detection
- Training support vector machines: an application to face detection
- Efficient Pattern Recognition Using a New Transformation Distance
- Comparison of classifier methods: a case study in handwritten digit recognition
- A Trainable System for Object Detection
- Transductive Inference for Text Classification using Support Vector Machines