A strategy based on non-extensive statistics to improve frame-matching algorithms under large viewpoint changes.
Guilherme Alberto Wachs-LopesMiller HorvathGilson A. GiraldiPaulo Sergio RodriguesPublished in: Signal Process. Image Commun. (2019)
Keyphrases
- viewpoint
- data structure
- learning algorithm
- times faster
- matching algorithm
- machine learning
- recently developed
- benchmark datasets
- theoretical analysis
- optimization problems
- greedy strategy
- order statistics
- orders of magnitude
- d objects
- machine learning algorithms
- significant improvement
- computationally efficient
- pattern matching
- computational complexity
- image matching
- computational efficiency
- computer vision
- data sets
- graph matching
- feature points
- worst case