Inpainting or completion is used with the aim of restoring damaged regions in images and video frames using the safe regions. This paper introduces a novel approach based on LDS (Linear Dynamic Systems) for inpainting of corrupted video frames which include dynamic textures. In this work, a mask is defined for each frame corresponding to the damaged portion of the frame; the mask determines the target region that will be completed by the proposed method. Notice that the mask is moving. To verify whether corrupted frames are reconstructed correctly or not, a measure named MS-SSIM (Multi-Scale Structural Similarity) is used. The value close to one for this scale introduces more similarity between the two components that are going to be compared. The obtained value for the above mentioned measure is very close to one for our results and the generated video is pleasant.
Video inpainting is the process of reconstructing damaged regions of corrupted frames. In this research, we raise a few issues in existing video inpainting systems. They are usually not robust to the change in the object scale and cannot handle large missing regions behind the moving object. In this attempt, we will address the above issues as following: first, we extract moving objects from the background and construct two mosaic images for each object, a small mosaic and a large mosaic image. The small mosaic is used to detect the amount of scale changes in the moving objects and the large one is used to inpaint partially or completely corrupted objects. We next place the inpainted moving foreground in its location and rescale the objects to their original scale. Finally, we combine the inpainted moving foreground and the background to obtain the corrected video. To speed up the process, we have utilised a multiresolution approach so that the patch are initially matched in a coarse resolution and later are refined in a fine resolution. The results confirm the robustness of our method in handling the scale change of moving objects and large missing regions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.