Content-based medical video retrieval based on region motion trajectories - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès IFMBE 2011: proceedings of the 5th European Conference of the International Federation for Medical and Biological Engineering Année : 2011

Content-based medical video retrieval based on region motion trajectories

Résumé

In this paper, we address the problem of contentbased medical video retrieval. We propose the use of motion tracking to generate video features. First, we extract motion vectors derived from the 'MPEG-4 AVC/H.264' standard. Second, motion segmentation of the image sequence is performed by a combination of k-means clustering and motion consistency verification. Third, we used the well-known Kalman filter to track region motion between consecutive frames. This produced region's correspondences are concatenated to construct the region's motion trajectories. Finally, to compare videos, we adopted an extension of dynamic time warping (EDTW) to multidimensional time series. Results are promising: a retrieval precision at 5 of 62 % was achieved.

Dates et versions

hal-00945406 , version 1 (12-02-2014)

Identifiants

Citer

Mohammed Zakarya Droueche, Mathieu Lamard, Guy Cazuguel, Gwénolé Quellec, Christian Roux, et al.. Content-based medical video retrieval based on region motion trajectories. IFMBE 2011: proceedings of the 5th European Conference of the International Federation for Medical and Biological Engineering, Sep 2011, Budapest, Hungary. pp.622-635, ⟨10.1007/978-3-642-23508-5_161⟩. ⟨hal-00945406⟩
46 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More