Segmenting, modeling and matching video clips containing multiple moving objects

Fred Rothganger (1) , Svetlana Lazebnik (1) , Cordelia Schmid (2) , Jean Ponce (1)

1 The Beckman Institute for Advanced Science and Technology
2 LEAR - Learning and recognition in vision

This paper presents a novel representation for dynamic scenes composed of multiple rigid objects that may undergo different motions and be observed by a moving camera. Multi-view constraints associated with groups of affine-invariant scene patches and a normalized description of their appearance are used to segment a scene into its rigid parts, construct three-dimensional protective, affine, and Euclidean models of these parts, and match instances of models recovered from different image sequences. The proposed approach has been implemented, and it is applied to the detection and recognition of moving objects in video sequences and the identification of shots that depict the same scene in a video clip (shot matching).

Mots clés: image matching; image motion analysis; image representation; image segmentation; image sequences; object detection; object recognition

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Fred Rothganger, Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. Segmenting, modeling and matching video clips containing multiple moving objects. IEEE Conference on Computer Vision and Pattern Recognition (CVPR '04), Jun 2004, Washington, United States. pp.914--921, ⟨10.1109/CVPR.2004.1315263⟩. ⟨inria-00548534⟩