APPARATUS AND METHOD FOR ENCODING VIDEO USING DIFFERENT SECOND-STAGE TRANSFORM

Patent №

US 9,106,933

Granted

2015-08-11

Filed 2011

Owner

GOOGLE INC.

AI components

1

vision

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

13110278

A system, apparatus, and method of encoding a video stream having a plurality of frames, each frame having a plurality of blocks is disclosed. The method includes selecting a group of blocks from a current frame of the plurality of frames, determining a plurality of first stage transform coefficient matrices for the group of blocks using a first transform technique, determining a DC second stage transform coefficient matrix for the group of blocks based on at least some of the plurality of first stage transform coefficient matrices and using a second transform technique on a processor, and encoding the group of blocks into an encoding format using the DC second stage coefficient matrix and the first stage coefficient matrices.

VisionH04N 19/94H04N 19/117H04N 19/124H04N 19/14H04N 19/176H04N 19/86H04N 19/82

AI classification

Vision1.00
Natural language0.00
Evolutionary computation0.00
AI hardware0.00
Knowledge representation0.00
Machine learning0.00
Speech0.00
Planning0.00

Ownership

GOOGLE INC.

assignment · 263000864

Assignors

BANKOSKI, JAMES, WILKINS, PAUL, XU, YAOWU

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC