Method and system for encoding collections of images and videos

摘要

An input segment of an input video is encoded by first extracting and storing, for each segment of previously encoded videos, a set of reference features. The set of input features are matched with each set of the reference features to produce a set of scores. The reference segments having largest scores are selected to produce a first reduced set of reference segments. A rate-distortion cost for each reference segment in the first reduced set of reference segments is estimated. The reference segments in the first reduced set of reference segments is selected to produce a second reduced set of reference segments. Then, the input segment are encoded based on second reduced set of reference segments.

主权项

1. A method for encoding an input segment of an input video, comprising the steps of:
extracting and storing, for each segment of previously encoded videos, a set of reference features; extracting, for the input segment, a set of input features; matching the set of input feature with each set of the reference features to produce a set of scores; selecting the reference segments having largest scores to produce a first reduced set of reference segments; estimating a rate-distortion cost for each reference segment in the first reduced set of reference segments; selecting the reference segments in the first reduced set of reference segments to produce a second reduced set of reference segments; and encoding the input segment based on second reduced set of reference segments, wherein the segment is a group of pictures (GOP), wherein the matching is performed in a weighted manner by providing a higher factor for a first picture in the GOP, and wherein the set of features are only invariant to translation, wherein the steps are performed in a processor.