Most work in action recognition deals with sequences acquired by stationary cameras with fixed viewpoints. Due to the camera motion, the trajectories of the body parts contain not only the motion of the performing actor but also the motion of the camera. In addition to the camera motion, different viewpoints of the same action in different environments result in different trajectories, which can not be matched using standard approaches. In order to handle these problems, we propose to use the multi-view geometry between two actions. However, well known epipolar geometry of the static scenes where the cameras are stationary is not suitable for our task. Thus, we propose to extend the standard epipolar geometry to the geometry of dynamic scenes where the cameras are moving. We demonstrate the versatility of the proposed geometric approach for recognition of actions in a number of challenging sequences.
Recognizing human actions in videos acquired by uncalibrated moving cameras
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 1 ; 150-157 Vol. 1
2005-01-01
523997 byte
Conference paper
Electronic Resource
English
Recognizing Human Actions in Videos Acquired by Uncalibrated Moving Cameras
British Library Conference Proceedings | 2005
|Flexible 3D models from uncalibrated cameras
British Library Online Contents | 1996
|Free-Viewpoint Image Synthesis from Multiple-Viewimages Taken with Uncalibrated Moving Cameras
British Library Conference Proceedings | 2005
|Nondimensional star identification for uncalibrated star cameras
Springer Verlag | 2006
|