A fusion architecture based on TBM for camera motion classification

Mickaël Guironnet (1) , Denis Pellerin (1) , Michèle Rombaut (1)

1 GIPSA-GPIG - GIPSA - Géométrie, Perception, Images, Geste

We propose in this paper an original method of camera motion classification based on Transferable Belief Model (TBM). It consists in locating in a video the motions of translation and zoom, and the absence of camera motion (i.e static camera). The classification process is based on a rule-based system that is divided into three stages. From a parametric motion model, the first stage consists in combining data to obtain frame-level belief masses on camera motions. To ensure the temporal coherence of motions, a filtering of belief masses according to TBM is achieved. The second stage carries out a separation between static and dynamic frames. In the third stage, a temporal integration allows the motion to be studied on a set of frames and to preserve only those with significant magnitude and duration. Then, a more detailed description of each motion is given. Experimental results obtained show the effectiveness of the method.

Mots clés: camera motion classification

Mots clés: Transferable Belief Model; motion estimation; motion description; video indexing

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Mickaël Guironnet, Denis Pellerin, Michèle Rombaut. A fusion architecture based on TBM for camera motion classification. Image and Vision Computing, 2007, 25 (11), pp.1737-1747. ⟨10.1016/j.imavis.2007.01.001⟩. ⟨hal-00164601⟩