Video inpainting is the technique that can automatically restore damaged or partially removed image. It is also the unique tool for filling in the missing part in a video sequence. Exploration of more advanced concepts in video painting, we develop a new video algorithm based on temporal continuations and exemplar-based image inpainting techniques. This proposed algorithm involves the elements of removing the moving objects on stationary and non-stationary background. Therefore, the related experiments include a wide variety of temporal continuations of foreground and background. According to the results of our experiments, a motion-compensated inpainting procedure is successfully developed and it can be further extended toimplant into the inpainted background video. Ultimately, the inpainted video backgrounds are visually pleasant with smooth transitions.
