CO2021016291A2 - Representación y extracción de movimiento en capas en videos de cámara fija monocular - Google Patents

Representación y extracción de movimiento en capas en videos de cámara fija monocular

Info

Publication number
CO2021016291A2
CO2021016291A2 CONC2021/0016291A CO2021016291A CO2021016291A2 CO 2021016291 A2 CO2021016291 A2 CO 2021016291A2 CO 2021016291 A CO2021016291 A CO 2021016291A CO 2021016291 A2 CO2021016291 A2 CO 2021016291A2
Authority
CO
Colombia
Prior art keywords
frame
segments
moving
picture
segmenting
Prior art date
Application number
CONC2021/0016291A
Other languages
English (en)
Inventor
Dan Pescaru
Vasile Gui
Cosmin Cernazanu-Glavan
Original Assignee
Everseen Ltd
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
Application filed by Everseen Ltd filed Critical Everseen Ltd
Publication of CO2021016291A2 publication Critical patent/CO2021016291A2/es

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/215—Motion-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/143—Segmentation; Edge detection involving probabilistic approaches, e.g. Markov random field [MRF] modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/174—Segmentation; Edge detection involving the use of two or more images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/254—Analysis of motion involving subtraction of images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/14—Picture signal circuitry for video frequency region
    • H04N5/144—Movement detection
    • H04N5/145—Movement estimation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Probability & Statistics with Applications (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Image Analysis (AREA)

Abstract

Un método para segmentar datos de movimiento e inferir el orden de capas en un video, incluye segmentar un primer cuadro de imagen del video usando una estimación de modo intra-cuadro, segmentar cuadros de imagen adicionales del video usando una coincidencia de modo entre-cuadros, generar un mapa de cambio de etiqueta para un cuadro de imagen segmentado actual, generar un mapa binario del cuadro de imagen segmentado actual, y luego marcar uno o más píxeles cuyas etiquetas han cambiado con respecto a un cuadro de imagen segmentado anterior, detectar uno o más segmentos de imagen no fijos del cuadro de imagen segmentado actual, detectar uno o más segmentos de imagen en movimiento en el uno o más segmentos de imagen no fijos, estimar un movimiento del uno o más segmentos de imagen en movimiento, representar cada segmento en movimiento como un vector de siete parámetros, y agrupar uno o más vectores de segmentos en movimiento similares en base a uno o más parámetros correspondientes.
CONC2021/0016291A 2019-07-01 2021-11-30 Representación y extracción de movimiento en capas en videos de cámara fija monocular CO2021016291A2 (es)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US16/458,291 US10803604B1 (en) 2019-07-01 2019-07-01 Layered motion representation and extraction in monocular still camera videos
PCT/IB2020/054687 WO2021001703A1 (en) 2019-07-01 2020-05-18 Layered motion representation and extraction in monocular still camera videos

Publications (1)

Publication Number Publication Date
CO2021016291A2 true CO2021016291A2 (es) 2021-12-10

Family

ID=70802897

Family Applications (1)

Application Number Title Priority Date Filing Date
CONC2021/0016291A CO2021016291A2 (es) 2019-07-01 2021-11-30 Representación y extracción de movimiento en capas en videos de cámara fija monocular

Country Status (11)

Country Link
US (1) US10803604B1 (es)
EP (1) EP3994664A1 (es)
JP (1) JP7282216B2 (es)
KR (1) KR20220007882A (es)
CN (1) CN114072839A (es)
AU (1) AU2020300067B2 (es)
BR (1) BR112021024268A2 (es)
CA (1) CA3141956A1 (es)
CO (1) CO2021016291A2 (es)
MX (1) MX2021015583A (es)
WO (1) WO2021001703A1 (es)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11200678B2 (en) * 2019-09-17 2021-12-14 Sony Corporation Image-based mask frame interpolation
US11748888B2 (en) * 2019-11-15 2023-09-05 L'oreal End-to-end merge for video object segmentation (VOS)
JP2022087914A (ja) * 2020-12-02 2022-06-14 本田技研工業株式会社 車両位置推定装置
CN114556419A (zh) * 2020-12-15 2022-05-27 深圳市大疆创新科技有限公司 三维点云分割方法和装置、可移动平台
CN113688951B (zh) * 2021-10-25 2022-01-21 腾讯科技（深圳）有限公司 视频数据处理方法以及装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120027091A1 (en) * 2010-07-28 2012-02-02 Wei-Lien Hsu Method and System for Encoding Video Frames Using a Plurality of Processors
US8335350B2 (en) * 2011-02-24 2012-12-18 Eastman Kodak Company Extracting motion information from digital video sequences
CN102263979B (zh) * 2011-08-05 2013-10-09 清华大学 一种平面视频立体化的深度图生成方法及装置
US9247136B2 (en) * 2013-08-21 2016-01-26 Xerox Corporation Automatic mobile photo capture using video analysis
US20190045193A1 (en) * 2018-06-29 2019-02-07 Intel Corporation Region-based motion estimation and modeling for accurate region-based motion compensation for efficient video processing or coding

Also Published As

Publication number Publication date
AU2020300067A1 (en) 2021-12-16
JP7282216B2 (ja) 2023-05-26
JP2022536524A (ja) 2022-08-17
CN114072839A (zh) 2022-02-18
EP3994664A1 (en) 2022-05-11
US10803604B1 (en) 2020-10-13
MX2021015583A (es) 2022-01-24
CA3141956A1 (en) 2021-01-07
AU2020300067B2 (en) 2023-02-23
BR112021024268A2 (pt) 2022-01-11
WO2021001703A1 (en) 2021-01-07
KR20220007882A (ko) 2022-01-19

Similar Documents

Publication Publication Date Title
CO2021016291A2 (es) Representación y extracción de movimiento en capas en videos de cámara fija monocular
MX2020010515A (es) Metodo de prediccion de imagen y aparato relacionado.
MX2020011278A (es) Metodo de codificacion de imagen de video, metodo de decodificacion de imagen de video, dispositivo de codificacion, y dispositivo de decodificacion.
MY196389A (en) Two-dimensional code and method and apparatus for recognizing two-dimensional code, and terminal
BR112017024275A2 (pt) determinação de região de busca para inter-codificação dentro de imagem específica de dados de vídeo
CL2019003677A1 (es) Predicción de vectores de movimiento.
KR101183781B1 (ko) 실시간 카메라 모션 추정을 이용한 물체 검출/추적 방법 및 단말
BR112021006152A2 (pt) método de codificação de imagem com base em histórico e aparelho do mesmo
MX2021003044A (es) Método y dispositivo de predicción de imagen.
MX2020003973A (es) Candidatos de predictor mejorados para compensacion de movimiento.
WO2017215899A8 (en) Augmented and virtual reality
CO2017009675A2 (es) Derivación del vector de movimiento en la codificación de video
US10412462B2 (en) Video frame rate conversion using streamed metadata
US10620826B2 (en) Object selection based on region of interest fusion
JP2014209762A5 (es)
WO2015105816A3 (en) Representing motion vectors in an encoded bitstream
EP4340356A3 (en) Image signal encoding/decoding method and apparatus therefor
WO2007092156A3 (en) Extracting key frame candidates from video clip
EP3023939A3 (en) Method and apparatus for tracking the motion of image content in a video frames sequence using sub-pixel resolution motion estimation
WO2019059575A3 (ko) 움직임 정보의 부호화 및 복호화 방법, 및 움직임 정보의 부호화 및 복호화 장치
DK3700216T3 (da) Billeddekodning, baseret på affin bevægelses-forudsigelse under anvendelse af affin MVP-kandidatliste
KR20090084460A (ko) 동영상의 객체 경계 추정 방법
CL2021000671A1 (es) Método de codificación/decodificación de señales de imagen y dispositivo para lo mismo
JP2015517239A5 (es)
US10403019B2 (en) Multi-channel tracking pattern