摘要 |
Video data compression performance is improved through the use of multiple processors operating in parallel. The parallel processors perform motion or spatial estimation, where portions of a video frame are found to be similar to portions in reference frames. Because this estimation operation can be very time consuming, the use of multiple processors can reduce the overall time required, or they can enable higher-performing algorithms that might otherwise require a prohibitively long processing time. The motion or spatial estimation results are applied to reconstructed versions of the video frame data to enable high levels of video data compression.
|