K-tangent spaces on Riemannian manifolds for improved pedestrian detection.
Andres SaninConrad SandersonMehrtash Tafazzoli HarandiBrian C. LovellPublished in: ICIP (2012)
Keyphrases
- pedestrian detection
- riemannian manifolds
- human body
- tangent space
- euclidean space
- object detection
- vector space
- mean shift
- benchmark datasets
- geometric structure
- geodesic distance
- detection rate
- multi class classification
- manifold learning
- feature space
- low dimensional
- computational cost
- reproducing kernel hilbert space
- parameter space
- shape analysis
- computational complexity
- covariance matrix
- covariance matrices
- machine learning
- high dimensional
- object recognition
- support vector