Video processing system and method for automatic enhancement of digital video
View Patent ↗An automatic video enhancement system and method for automatically enhancing video. The automated video enhancement method uses frame-to-frame motion estimation as the basis of the video enhancement. Motion estimation includes the computation of global motion (such as camera motion) and the computation of local motion (such as pixel motion). The automated video enhancement method includes generating global alignment transforms, generating optic flow vectors, and using these global alignment transforms and optic flow vectors to enhance the video. The invention also includes video processing and enhancement techniques that use the frame-to-frame motion estimation. These techniques include a deinterlace process, a denoise process, and a warp stabilization process that performs both damped and locked stabilization.
1. A method for decreasing a frame rate in a video having video frames to obtain a slow motion video, comprising:
determining an optic flow vector for each pixel within a first one of the video frames;
warping each pixel within the first one of the video frames forward in time by approximately 50 percent;
generating a new video frame using the warping immediately after in time the first one of the video frames; and
repeating the above process until all necessary new video frame have been generated.
2. The method as set forth in claim 1 , further comprising warping each pixel within a second one of the video frames backward in time by approximately 50 percent, the second one of the video frames being located after in time the first one of the video frames.
3. The method as set forth in claim 2 , further comprising continuing a forward and a backward warping until the first one of the video frames and the second one of the video frames converge.
4. The method as set forth in claim 1 further comprising performing denoising of the video using the optic flow vector and a temporal median filter having flow outlier rejection.
5. The method as set forth in claim 4 further comprising performing motion-compensated deinterlacing using the video and the optic flow vector.
6. The method as set forth in claim 5 further comprising performing warp stabilization using global alignment transforms.