Adapting mode decisions in video encoder

A tangible, non-transitory, computer-readable medium configured to store instructions executable by one or more processors, wherein the instructions comprise instructions to:

• determine, using the one or more processors, a distortion measurement calculation based on operational parameters of image data, wherein the distortion measurement calculation comprises a higher-cost calculation when the one or more processors are capable of encoding the image data at or near real time, or comprises a low-cost calculation when the one or more processors are not capable of encoding the image data at or near real time;
• determine, using the one or more processors, rate distortion cost metrics of an inter-frame prediction mode and an intra-frame prediction mode using the distortion measurement calculation;
• select, using the one or more processors, the inter-frame prediction mode or the intra-frame prediction mode based on the rate distortion cost metrics;
• and
• encode, using the one or more processors, the image data using the inter-frame prediction mode or the intra-frame prediction mode selected by the one or more processors.

An encoding pipeline comprising:

• memory configured to store source image data corresponding with an image frame to be encoded by the encoding pipeline, wherein the source image data is divided into a plurality of prediction blocks;
• distortion measurement circuitry configured to select between a sum of squared differences calculation and a sum of absolute transformed differences calculation based at least in part on operational parameters of a display device and the source image data;
• mode selection circuitry configured to determine rate distortion cost metrics associated with at least two frame prediction modes using the sum of squared differences calculation when the encoding pipeline is capable of encoding the source image data at or near real time or the sum of absolute transformed differences calculation when the encoding pipeline is not capable of encoding the source image data at or near real time, and to select one of the at least two frame prediction modes based at least in part on the rate distortion cost metrics;
• encoding circuitry configured to encode the plurality of prediction blocks using the one of the at least two frame prediction modes selected by the mode selection circuitry;
• and
• an output configured to receive a plurality of encoded prediction blocks and to transmit the plurality of encoded prediction blocks in real-time or near real-time to the display device.