Semantic segmentation applied to image interpolation in the case of camera panning and zooming

In this paper we describe an algorithm for image interpolation that takes into account both the motion of the camera and the motion of the imaged objects. First the estimated global motion parameters are employed to compensate the camera motion. After that the missing images are interpolated by using the local motion field. Last of all these images are reconstructed in their correct dimension considering the global motion information. Good performance is obtained by the proposed algorithm. Moreover some experiments have been carried out in order to extend the concept of object-background segmentation developed for fixed camera sequences to the case of camera zooming or panning. The simulations show that in order to obtain an effective semantic segmentation is necessary to take into account a very accurate model of the camera lens system.