BR112023016294A2 - Determinação de fluxo para codificação de vídeo com base em aprendizado de máquina - Google Patents

Determinação de fluxo para codificação de vídeo com base em aprendizado de máquina

Info

Publication number
BR112023016294A2
BR112023016294A2 BR112023016294A BR112023016294A BR112023016294A2 BR 112023016294 A2 BR112023016294 A2 BR 112023016294A2 BR 112023016294 A BR112023016294 A BR 112023016294A BR 112023016294 A BR112023016294 A BR 112023016294A BR 112023016294 A2 BR112023016294 A2 BR 112023016294A2
Authority
BR
Brazil
Prior art keywords
machine learning
current frame
motion information
component
video coding
Prior art date
Application number
BR112023016294A
Other languages
English (en)
Inventor
Kumar Singh Ankitesh
Enes Egilmez Hilmi
Marta Karczewicz
Zeyd Coban Muhammed
Original Assignee
Qualcomm Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US17/676,510 external-priority patent/US20220272355A1/en
Application filed by Qualcomm Inc filed Critical Qualcomm Inc
Publication of BR112023016294A2 publication Critical patent/BR112023016294A2/pt

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
    • H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal prediction
    • H04N19/51—Motion estimation or motion compensation
    • H04N19/537—Motion estimation other than block-based
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
    • H04N19/132—Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
    • H04N19/157—Assigned coding mode, i.e. the coding mode being predefined or preselected to be further used for selection of another element or parameter
    • H04N19/159—Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
    • H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal prediction
    • H04N19/51—Motion estimation or motion compensation
    • H04N19/513—Processing of motion vectors
    • H04N19/517—Processing of motion vectors by encoding
    • H04N19/52—Processing of motion vectors by encoding by predictive encoding
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
    • H04N19/587—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal sub-sampling or interpolation, e.g. decimation or subsequent interpolation of pictures in a video sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
    • H04N19/186—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being a colour or a chrominance component

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)

Abstract

determinação de fluxo para codificação de vídeo com base em aprendizado de máquina. sistemas e técnicas são descritos no presente documento para processar dados de vídeo. em alguns aspectos, um método pode incluir obter, por um sistema de aprendizado de máquina, dados de vídeo inseridos. os dados de vídeo inseridos incluem um ou mais componentes de luminância para um quadro atual. o método pode incluir determinar, pelo sistema de aprendizado de máquina, informações de movimento para o(s) componente(s) de luminância(s) do quadro atual e informações de movimento para um ou mais componentes de crominância do quadro atual usando o(s) componente(s) de luminância(s) para o quadro atual. em alguns casos, o método pode incluir determinar as informações de movimento para o(s) componente(s) de luminância(s) com base no(s) componente(s) de luma(s) do quadro atual e pelo menos um componente de luma reconstruído de um quadro anterior. em alguns casos, o método pode incluir adicionalmente determinar as informações de movimento para o(s) componente(s) de crominância do quadro atual usando as informações de movimento determinadas para o(s) componente(s) de luminância(s) do quadro atual.
BR112023016294A 2021-02-25 2022-02-22 Determinação de fluxo para codificação de vídeo com base em aprendizado de máquina BR112023016294A2 (pt)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US202163153475P 2021-02-25 2021-02-25
US17/676,510 US20220272355A1 (en) 2021-02-25 2022-02-21 Machine learning based flow determination for video coding
PCT/US2022/017296 WO2022182651A1 (en) 2021-02-25 2022-02-22 Machine learning based flow determination for video coding

Publications (1)

Publication Number Publication Date
BR112023016294A2 true BR112023016294A2 (pt) 2023-11-07

Family

ID=80683155

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112023016294A BR112023016294A2 (pt) 2021-02-25 2022-02-22 Determinação de fluxo para codificação de vídeo com base em aprendizado de máquina

Country Status (5)

Country Link
EP (1) EP4298795A1 (pt)
JP (1) JP2024508772A (pt)
KR (1) KR20230150274A (pt)
BR (1) BR112023016294A2 (pt)
WO (1) WO2022182651A1 (pt)

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7724827B2 (en) * 2003-09-07 2010-05-25 Microsoft Corporation Multi-layer run level encoding and decoding

Also Published As

Publication number Publication date
WO2022182651A1 (en) 2022-09-01
JP2024508772A (ja) 2024-02-28
EP4298795A1 (en) 2024-01-03
KR20230150274A (ko) 2023-10-30

Similar Documents

Publication Publication Date Title
BR112022016793A2 (pt) Compressão de vídeo usando sistemas de aprendizado de máquina de base recorrente
BR112018077230A2 (pt) sistemas e métodos para identificar conteúdo correspondente
BR112019013832A8 (pt) Restauração de vetor de movimento de lado de decodificador para codificação de vídeo
US10984538B2 (en) Image-processing device, image-processing method, and recording medium
BR112021024288A2 (pt) Sistemas casx modificados
US11423265B1 (en) Content moderation using object detection and image classification
BR112017024275A2 (pt) determinação de região de busca para inter-codificação dentro de imagem específica de dados de vídeo
BRPI0501286A (pt) Localização de traços pela decodificação de matriz-m e correspondência rápida de imagem
US20080231709A1 (en) System and method for managing the interaction of object detection and tracking systems in video surveillance
CN106651797B (zh) 一种信号灯有效区域的确定方法和装置
BR112023003932A2 (pt) Codificação de vídeo baseada em rede neural de ponta a ponta
CN112640426B (zh) 用于缓解led闪烁的图像处理系统
MY137026A (en) A system and process for generating high dynamic range images from multiple exposures of a moving scene
DE602006017977D1 (de) Verfolgen von objekten in einer videosequenz
ATE486332T1 (de) Verfahren zur verfolgung von objekten in einer videosequenz
JP2014157452A (ja) 画像処理装置、画像処理方法、および画像処理プログラム
BR112021026284A2 (pt) Aparelho para decodificar ou codificar um bloco predeterminado de uma imagem, métodos e fluxo de dados
BR112023005338A2 (pt) Segmentação para efeitos de imagem
CN111079613B (zh) 姿势识别方法和装置、电子设备及存储介质
US9762856B2 (en) Videoconferencing server with camera shake detection
BR112022018884A2 (pt) Método de processamento de vídeo, aparelho para processamento de dados de vídeo, meios de armazenamento e de gravação não transitórios legíveis por computador
BR112023005822A2 (pt) Métodos e aparelhos para mapeamento de tom adaptivo e baseado em histograma utilizando uma pluralidade de quadros
BR112022016529A2 (pt) Método de processamento de vídeo, aparelho para processar dados de vídeo e meios legíveis por computador
BR112023014810A2 (pt) Otimizador de distorção de taxa com base em aprendizagem de máquina para compactação de vídeo
BR112023005770A2 (pt) Estimativa de movimento em compressão para geometria de nuvem de pontos