Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Flux optique de Lucas-Kanade× | Détection de blobs× | |
|---|---|---|
| Domaine | Vision par ordinateur | Vision par ordinateur |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 1981 | 1998 |
| Auteur d'origine≠ | Bruce Lucas and Takeo Kanade | Tony Lindeberg |
| Type≠ | Optical flow and tracking | Multi-scale feature 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 ↗ | Lindeberg, T. (1998). Feature detection with automatic scale selection. International Journal of Computer Vision, 30(2), 79–116. DOI ↗ |
| Alias | Lucas-Kanade method, Sparse optical flow | Connected component analysis, Region-based detection |
| 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. | Blob detection is a technique for identifying regions of interest (blobs)—connected, homogeneous areas that differ from their surroundings—at multiple scales. Introduced by Lindeberg in the context of scale-space theory, blob detection automatically finds and characterizes circular or elliptical objects without requiring a priori knowledge of their size. |
| ScholarGateJeu de données ↗ |
|
|