An integrated motion analysis system guided by feedback information

The issues of using errorful data in motion estimation and of using feedback to improve feature extraction and matching in incremental analysis are addressed. Initial noisy correspondence data are continously refined by removing those parts that do not fit the estimated 3-D motion parameters. The extraction of a tracked region is guided by its expected properties obtained from the corresponding objects in the previous frames. The surfaces of objects are reconstructed from a sparse depth map.<
>