Distributed video encoding/decoding apparatus and method to achieve improved rate distortion performance

A distributed video encoding apparatus to achieve improved rate distortion performance, the distributed video encoding apparatus comprising:

• a processor;
• and
• a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which on execution, causes the processor to:
• receive at least one Group of Pictures (GOP) comprising a key frame and at least one Wyner-Ziv (WZ) frame, wherein the at least one GOP includes three or more frames;
• determine a first value that is indicative of a cumulative motion activity of a plurality of pixel values associated with a plurality of pixels between each of the adjacent frames in the at least one GOP;
• classify the at least one GOP into one of one or more high-motion WZ frames and one or more low-motion WZ frames based on the determined first value;
• encode the key frame from at least one GOP using predictive intra frame encoding;
• encode the one or more high-motion WZ frames using inter no-motion encoding wherein the inter no-motion encoding comprises an inter coding method that utilizes a combination of intra and bidirectional inter prediction to generate an IB construction where I corresponds to intra and B corresponds to bidirectional inter prediction;
• and
• encode the one or more low-motion WZ frames using Wyner-Ziv encoding, wherein the first value is determined based on one or more of a normalized histogram difference of a plurality of pixel values associated with a plurality of pixels between each of the adjacent frames in the at least one GOP, a normalized histogram difference between a set of pixel values of the adjacent frames within a pre-defined block size, or a normalized histogram variance difference between the set of pixel values of the adjacent frames within the pre-defined block size in each of the adjacent frames.

A non-transitory computer-readable storage medium having stored thereon, a set of computer-executable instructions for causing a computer comprising one or more processors to perform steps comprising:

• receiving, by a distributed video encoding apparatus, at least one Group of Pictures (GOP) comprising a key frame and at least one Wyner-Ziv (WZ) frame, wherein the at least one GOP includes three or more frames;
• determining, by the distributed video encoding apparatus, a first value that is indicative of a cumulative motion activity of a plurality of pixel values associated with a plurality of pixels between each of the adjacent frames in the at least one GOP;
• classifying, by the distributed video encoding apparatus, the at least one GOP into one of one or more high-motion WZ frames and one or more low-motion WZ frames based on the determined first value;
• encoding the key frame from at least one GOP using predictive intra frame encoding;
• encoding, by the distributed video encoding apparatus, the one or more high-motion WZ frames using inter no-motion encoding, wherein the inter no-motion encoding comprises an inter coding method that utilizes a combination of intra and bidirectional inter prediction to generate an IB construction where I corresponds to intra and B corresponds to bidirectional inter prediction;
• and
• encoding, by the distributed video encoding apparatus, the one or more low-motion WZ frames using Wyner-Ziv encoding, wherein the first value is determined based on one or more of a normalized histogram difference of a plurality of pixel values associated with a plurality of pixels between each of the adjacent frames in the at least one GOP, a normalized histogram difference between a set of pixel values of the adjacent frames within a pre-defined block size, or a normalized histogram variance difference between the set of pixel values of the adjacent frames within the pre-defined block size in each of the adjacent frames.