摘要 |
The invention relates to a method of estimation of the motion parameters of a camera. It is applied to a sequence of successive video frames subdivided into blocks and includes the following steps of extracting from the sequence vectors corresponding to the motion between two frames, motion vectors forming the camera velocity field, preprocessing the camera velocity field thus obtained, in order to reduce the amount of data and the heterogeneousness of the extracted motion vectors, estimating for each pair of frames, from the preprocessed field, camera features between the two considered frames, and undertaking, on the basis of said estimation, a long term motion analysis to obtain motion descriptors corresponding to the estimated camera motion parameters.
|