Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Flux optique de Lucas-Kanade× | Correspondance de modèle× | |
|---|---|---|
| Domaine | Vision par ordinateur | Vision par ordinateur |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 1981 | 1980s |
| Auteur d'origine≠ | Bruce Lucas and Takeo Kanade | Computer vision community |
| Type≠ | Optical flow and tracking | Pattern matching and detection |
| Source fondatrice≠ | Lucas, B. D., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. Proceedings of the Seventh International Joint Conference on Artificial Intelligence (IJCAI), 674–679. link ↗ | Lewis, J. P. (2004). Fast normalized cross-correlation. Vision Interface, 120–123. link ↗ |
| Alias | Lucas-Kanade method, Sparse optical flow | Correlation-based matching, Similarity matching |
| Apparentées | 5 | 5 |
| Résumé≠ | The Lucas-Kanade method, introduced by Bruce Lucas and Takeo Kanade in 1981, is a foundational technique for estimating optical flow—the apparent motion of objects in image sequences. By computing pixel-level motion vectors, the Lucas-Kanade algorithm tracks feature displacements between consecutive frames, enabling object tracking, motion estimation, and video analysis. | Template matching is a straightforward technique for locating a known pattern (template) within a larger image. By sliding a template image across the target image and computing a similarity measure at each position, template matching identifies locations where the template appears. It is effective for simple object detection when templates are well-defined and appearance variation is limited. |
| ScholarGateJeu de données ↗ |
|
|