|Résumé||Structure and objects in video images are often not known.
If we search for camera registration or focused areas of these
situations, some a priori knowledge was needed.
Now I present methods for finding geometrical structures in images or
videos without any preliminary object definition:
- First, a new motion-based method is presented for automatic registration
of images in multi-camera systems, to permit synthesis of wide-baseline
composite views by using an iterative Bayesian assignment of corresponding
image areas. Another application of this co-motion inference is to find the
vanishing-point position for planar reflected images or shadows.
- A new automatic solution for finding focused areas based on localized
blind deconvolution. This approach makes possible to determine the relative
blur of image areas without a priori knowledge about the images or the
shooting conditions. The method uses deconvolution based feature extraction
and a new residual error based classification for the discrimination of
image areas. We also show the method´s usability for applications in
content based indexing and video feature extraction.
- An MRF approach is also introduced for Bayesian Foreground and Shadow
Detection in Uncertain Frame Rate Surveillance Videos.