# US 10,313,699 B2 · Method and apparatus for parallel video decoding based on multi-core system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,313,699 B2
- Document ID: US10313699B2
- Status: Granted
- Kind: B2
- Application number: 15/519,620
- Filed: 2015-10-07
- Published: 2017-08-31
- Granted: 2019-06-04
- Earliest claimed: 2014-10-17
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Hyung-ju Chun; Chan-sik Park; Ki-won Yoo; Jae-moon Kim
- Web page: https://patentgrep.com/patent/US10313699B2

## CPC

- H04N 19/513: Processing of motion vectors
- H04N 19/105: Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
- H04N 19/156: Availability of hardware or computational resources, e.g. encoding based on power-saving criteria
- H04N 19/172: the region being a picture, frame or field
- H04N 19/176: the region being a block, e.g. a macroblock
- H04N 19/436: using parallelised computational arrangements
- H04N 19/44: Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A video decoding method includes obtaining a motion vector of a current block belonging to a first picture from a bitstream, performed by a first decoding unit; determining whether a reference block indicated by the motion vector is decoded, performed by the first decoding unit; and decoding the current block, based on whether the reference block is decoded. The reference block is included in a second picture decoded by a second decoding unit. The first picture and the second picture are decoded in parallel.

## Claims

### Claim 1

A video decoding method comprising:
obtaining a motion vector of a current block belonging to a first picture from a bitstream, performed by a first decoding unit;
determining whether a reference block indicated by the motion vector is decoded, performed by the first decoding unit; and
when the reference block is not decoded, modifying the motion vector, performed by the first decoding unit; and
decoding the current block by using the modified motion vector, performed by the first decoding unit,
wherein the reference block is included in a second picture decoded by a second decoding unit, and
the first picture and the second picture are decoded in parallel.

### Claim 2 (depends on 1)

The video decoding method of claim 1, wherein the modifying of the motion vector comprises modifying the motion vector to indicate one of decoded blocks of the second picture.

### Claim 3 (depends on 1)

The video decoding method of claim 1, wherein the modifying of the motion vector comprises modifying a vertical component value of the motion vector to indicate a location on a decoded region of the second picture.

### Claim 4 (depends on 1)

The video decoding method of claim 1, wherein the modifying of the motion vector comprises modifying a reference picture value of the motion vector to indicate another decoded picture.

### Claim 5 (depends on 1)

The video decoding method of claim 1, wherein the modifying of the motion vector comprises:
determining at least one neighboring block belonging to the first picture and located near the current block; and
modifying the motion vector according to one of motion vectors of the at least one neighboring block.

### Claim 6 (depends on 1)

The video decoding method of claim 1, wherein the modifying the motion vector comprises:
when the reference block is not decoded, stopping the decoding of the current block;
when the reference block is decoded within a preset time, decoding the current block by using the reference block; and
decoding the current block by using the modified motion vector, performed by the first decoding unit.

### Claim 7

A video decoding apparatus for performing parallel-decoding, the video decoding apparatus comprising: a first decoding unit configured to obtain a motion vector of a current block belonging to a first picture from a bitstream, determine whether a reference block indicated by the motion vector is decoded, modifying the motion vector when the reference block is not decoded, and decode the current block based on whether the reference block is decoded by using the modified motion vector; and a second decoding unit configured to decode a second picture including the reference block, and the first picture and the second picture are decoded in parallel.

### Claim 8 (depends on 1)

A non-transitory computer-readable recording medium having recorded a computer program for performing the method of claim 1.