CN113873258B - 光学流估计的图像处理系统和方法 - Google Patents

光学流估计的图像处理系统和方法 Download PDF

Info

Publication number
CN113873258B
CN113873258B CN202111171799.7A CN202111171799A CN113873258B CN 113873258 B CN113873258 B CN 113873258B CN 202111171799 A CN202111171799 A CN 202111171799A CN 113873258 B CN113873258 B CN 113873258B
Authority
CN
China
Prior art keywords
estimate
image
pixel
modified
pyramid
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202111171799.7A
Other languages
English (en)
Chinese (zh)
Other versions
CN113873258A (zh
Inventor
H·T·加吕达
马努·马修
S·N·纳戈尔里
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Texas Instruments Inc
Original Assignee
Texas Instruments 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
Application filed by Texas Instruments Inc filed Critical Texas Instruments Inc
Priority claimed from PCT/US2016/064982 external-priority patent/WO2017096384A1/en
Publication of CN113873258A publication Critical patent/CN113873258A/zh
Application granted granted Critical
Publication of CN113873258B publication Critical patent/CN113873258B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • H04N19/53—Multi-resolution motion estimation; Hierarchical motion estimation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/223—Analysis of motion using block-matching
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/223—Analysis of motion using block-matching
    • G06T7/238—Analysis of motion using block-matching using non-full search, e.g. three-step search
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/269—Analysis of motion using gradient-based methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/48—Matching video sequences
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G06T2207/20032—Median filtering

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Image Analysis (AREA)
  • Television Systems (AREA)
  • Geometry (AREA)
CN202111171799.7A 2015-12-04 2016-12-05 光学流估计的图像处理系统和方法 Active CN113873258B (zh)

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
IN6508CH2015 2015-12-04
IN6508/CHE/2015 2015-12-04
US15/081,118 US10268901B2 (en) 2015-12-04 2016-03-25 Quasi-parametric optical flow estimation
US15/081,118 2016-03-25
CN201680064214.2A CN108352074B (zh) 2015-12-04 2016-12-05 光学流估计的图像处理系统和方法
PCT/US2016/064982 WO2017096384A1 (en) 2015-12-04 2016-12-05 Quasi-parametric optical flow estimation

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201680064214.2A Division CN108352074B (zh) 2015-12-04 2016-12-05 光学流估计的图像处理系统和方法

Publications (2)

Publication Number Publication Date
CN113873258A CN113873258A (zh) 2021-12-31
CN113873258B true CN113873258B (zh) 2025-04-08

Family

ID=58799177

Family Applications (2)

Application Number Title Priority Date Filing Date
CN201680064214.2A Active CN108352074B (zh) 2015-12-04 2016-12-05 光学流估计的图像处理系统和方法
CN202111171799.7A Active CN113873258B (zh) 2015-12-04 2016-12-05 光学流估计的图像处理系统和方法

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN201680064214.2A Active CN108352074B (zh) 2015-12-04 2016-12-05 光学流估计的图像处理系统和方法

Country Status (4)

Country Link
US (2) US10268901B2 (enExample)
EP (1) EP3384466B1 (enExample)
JP (1) JP7004314B2 (enExample)
CN (2) CN108352074B (enExample)

Families Citing this family (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9311690B2 (en) * 2014-03-11 2016-04-12 Adobe Systems Incorporated Video denoising using optical flow
US10268901B2 (en) * 2015-12-04 2019-04-23 Texas Instruments Incorporated Quasi-parametric optical flow estimation
US10715818B2 (en) * 2016-08-04 2020-07-14 Intel Corporation Techniques for hardware video encoding
US10621446B2 (en) * 2016-12-22 2020-04-14 Texas Instruments Incorporated Handling perspective magnification in optical flow processing
US10229534B2 (en) * 2017-01-10 2019-03-12 Ditto Technologies, Inc. Modeling of a user's face
US10824877B2 (en) * 2017-06-29 2020-11-03 Texas Instruments Incorporated Hierarchical data organization for dense optical flow processing in a computer vision system
US10467765B2 (en) * 2017-06-29 2019-11-05 Texas Instruments Incorporated Dense optical flow processing in a computer vision system
US11070796B2 (en) * 2018-09-28 2021-07-20 Qualcomm Incorporated Ultimate motion vector expression based pruning for video coding
CN111083492B (zh) 2018-10-22 2024-01-12 北京字节跳动网络技术有限公司 双向光流中的梯度计算
WO2020084476A1 (en) 2018-10-22 2020-04-30 Beijing Bytedance Network Technology Co., Ltd. Sub-block based prediction
CN109544520B (zh) * 2018-11-09 2023-08-18 福建和盛高科技产业有限公司 一种视频图像扭曲自动检测方法
WO2020098648A1 (en) 2018-11-12 2020-05-22 Beijing Bytedance Network Technology Co., Ltd. Using combined inter intra prediction in video processing
CN117319644A (zh) 2018-11-20 2023-12-29 北京字节跳动网络技术有限公司 基于部分位置的差计算
WO2020103870A1 (en) 2018-11-20 2020-05-28 Beijing Bytedance Network Technology Co., Ltd. Inter prediction with refinement in video processing
CN109598744B (zh) * 2018-11-29 2020-12-08 广州市百果园信息技术有限公司 一种视频跟踪的方法、装置、设备和存储介质
US11531110B2 (en) * 2019-01-30 2022-12-20 Baidu Usa Llc LiDAR localization using 3D CNN network for solution inference in autonomous driving vehicles
WO2020177756A1 (en) 2019-03-06 2020-09-10 Beijing Bytedance Network Technology Co., Ltd. Size dependent inter coding
KR102610709B1 (ko) * 2019-04-02 2023-12-05 베이징 바이트댄스 네트워크 테크놀로지 컴퍼니, 리미티드 디코더 측 움직임 벡터 유도
WO2020224613A1 (en) * 2019-05-07 2020-11-12 Beijing Bytedance Network Technology Co., Ltd. Unified calculation method for inter prediction with refinement
US11430134B2 (en) * 2019-09-03 2022-08-30 Nvidia Corporation Hardware-based optical flow acceleration
US11176682B2 (en) * 2019-11-27 2021-11-16 Nvidia Corporation Enhanced optical flow estimation using a varied scan order
US11694341B2 (en) 2019-12-23 2023-07-04 Texas Instmments Incorporated Cascaded architecture for disparity and motion prediction with block matching and convolutional neural network (CNN)
CN113538525B (zh) * 2021-05-28 2023-12-05 北京旷视科技有限公司 光流估计方法、模型训练方法及对应装置
US20220392116A1 (en) * 2021-06-03 2022-12-08 Intel Corporation Neural frame extrapolation rendering mechanism
CN113379808B (zh) * 2021-06-21 2022-08-12 昆明理工大学 一种多波段太阳图像配准的方法
CN114363703B (zh) * 2022-01-04 2024-01-23 上海哔哩哔哩科技有限公司 视频处理方法、装置及系统
CN119854521B (zh) * 2024-12-30 2025-10-28 上海富瀚微电子股份有限公司 运动矢量估计方法、系统及可读存储介质

Family Cites Families (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0026846D0 (en) 2000-11-03 2000-12-20 Clayton John C Motion compensation of images
JP3776094B2 (ja) 2002-05-09 2006-05-17 松下電器産業株式会社 監視装置、監視方法および監視用プログラム
US7558320B2 (en) * 2003-06-13 2009-07-07 Microsoft Corporation Quality control in frame interpolation with motion analysis
US7831088B2 (en) * 2003-06-13 2010-11-09 Georgia Tech Research Corporation Data reconstruction using directional interpolation techniques
US7778466B1 (en) * 2003-12-02 2010-08-17 Hrl Laboratories, Llc System and method for processing imagery using optical flow histograms
US20050162565A1 (en) 2003-12-29 2005-07-28 Arcsoft, Inc. Slow motion processing of digital video data
KR100995398B1 (ko) * 2004-01-20 2010-11-19 삼성전자주식회사 수직 및 수평 방향의 패턴을 고려한 전역 움직임 보상순차주사화 방법
DE102004026782A1 (de) * 2004-06-02 2005-12-29 Infineon Technologies Ag Verfahren und Vorrichtung zur rechnergestützten Bewegungsschätzung in mindestens zwei zeitlich aufeinander folgenden digitalen Bildern, computerlesbares Speichermedium und Computerprogramm-Element
US7440008B2 (en) * 2004-06-15 2008-10-21 Corel Tw Corp. Video stabilization method
GB0500174D0 (en) * 2005-01-06 2005-02-16 Kokaram Anil Method for estimating motion and occlusion
JP4774857B2 (ja) 2005-08-11 2011-09-14 カシオ計算機株式会社 画像処理装置及びプログラム
WO2008034164A1 (en) * 2006-09-22 2008-03-27 Adelaide Research & Innovation Pty Ltd Flow analysis
GB2510709B (en) * 2008-10-15 2015-02-11 Spinella Ip Holdings Inc Digital processing method and system for determination of optical flow
GB2476397B (en) * 2008-10-15 2014-04-30 Spinella Ip Holdings Inc Digital processing method and system for determination of optical flow
US8315434B2 (en) * 2009-01-06 2012-11-20 Avago Technologies Ecbu Ip (Singapore) Pte. Ltd. Absolute tracking in a sub-pixel range
US8259809B2 (en) * 2009-01-12 2012-09-04 Mediatek Singapore Pte Ltd. One step sub-pixel motion estimation
US8896715B2 (en) * 2010-02-11 2014-11-25 Microsoft Corporation Generic platform video image stabilization
US20110255599A1 (en) * 2010-04-15 2011-10-20 Sony Corporation Apparatus and method for motion estimation
US9014421B2 (en) * 2011-09-28 2015-04-21 Qualcomm Incorporated Framework for reference-free drift-corrected planar tracking using Lucas-Kanade optical flow
DE102012023060A1 (de) 2012-11-24 2014-06-12 Connaught Electronics Ltd. Verfahren zum Detektieren eines beweglichen Objekts mithilfe eines Histogramms anhand von Bildern einer Kamera und Kamerasystem für ein Kraftfahrzeug
US9129399B2 (en) * 2013-03-11 2015-09-08 Adobe Systems Incorporated Optical flow with nearest neighbor field fusion
CN103400346B (zh) * 2013-07-18 2016-12-28 天津大学 基于自适应的超像素导向自回归模型的视频超分辨率方法
CN103646421B (zh) * 2013-12-13 2016-08-17 贾金原 基于增强型PyrLK光流法的树木轻量化3D重建方法
CN104978728B (zh) * 2014-04-08 2017-11-14 南京理工大学 一种光流法的图像匹配系统
US9681150B2 (en) 2014-06-13 2017-06-13 Texas Instruments Incorporated Optical flow determination using pyramidal block matching
CN104239867B (zh) * 2014-09-17 2017-12-01 深圳市捷顺科技实业股份有限公司 车牌定位方法及系统
CN104331151B (zh) * 2014-10-11 2018-02-23 中国传媒大学 基于光流法的手势运动方向识别方法
EP3023938A1 (en) * 2014-11-21 2016-05-25 Thomson Licensing Method and apparatus for tracking the motion of image content in a video frames sequence using sub-pixel resolution motion estimation
CN104376741B (zh) * 2014-12-02 2017-03-22 深圳市捷顺科技实业股份有限公司 一种车位状态检测方法与系统
CN105100546A (zh) * 2014-12-31 2015-11-25 天津航天中为数据系统科技有限公司 运动估计方法及装置
CN104869387B (zh) * 2015-04-19 2017-01-11 中国传媒大学 基于光流法的双目图像最大视差获取方法
US10268901B2 (en) * 2015-12-04 2019-04-23 Texas Instruments Incorporated Quasi-parametric optical flow estimation
US10108864B2 (en) * 2015-12-29 2018-10-23 Texas Instruments Incorporated Stationary-vehicle structure from motion

Also Published As

Publication number Publication date
US20170161565A1 (en) 2017-06-08
JP2019504394A (ja) 2019-02-14
EP3384466A1 (en) 2018-10-10
CN108352074A (zh) 2018-07-31
JP7004314B2 (ja) 2022-01-21
US11341750B2 (en) 2022-05-24
CN108352074B (zh) 2021-11-26
CN113873258A (zh) 2021-12-31
US20190244036A1 (en) 2019-08-08
US10268901B2 (en) 2019-04-23
EP3384466A4 (en) 2018-12-05
EP3384466B1 (en) 2020-09-16

Similar Documents

Publication Publication Date Title
CN113873258B (zh) 光学流估计的图像处理系统和方法
US9681150B2 (en) Optical flow determination using pyramidal block matching
AU2017324923B2 (en) Predicting depth from image data using a statistical model
US8705877B1 (en) Method and apparatus for fast computational stereo
US8416989B2 (en) Image processing apparatus, image capture apparatus, image processing method, and program
CN101996399A (zh) 在左图像与右图像之间估计视差的设备和方法
US8867826B2 (en) Disparity estimation for misaligned stereo image pairs
WO2010080168A1 (en) One step sub-pixel motion estimation
US20060165315A1 (en) Method and apparatus for depth ordering of digital images
WO2017096384A1 (en) Quasi-parametric optical flow estimation
WO2013107833A1 (en) Method and device for generating a motion field for a video sequence
Zhang et al. Neuflow: Real-time, high-accuracy optical flow estimation on robots using edge devices
Yang et al. Depth-aware unpaired video dehazing
JP2001520781A (ja) 動き又はデプス推定
CN111526369B (zh) 视频的运动估计方法、装置、电子设备和存储介质
JP2004356747A (ja) 画像のマッチング方法および装置
US9100573B2 (en) Low-cost roto-translational video stabilization
Hou et al. F3DsCNN: A fast two-branch 3D separable CNN for moving object detection
KR101920159B1 (ko) 지원점 보간법을 이용한 스테레오 매칭 방법 및 장치
JP6349774B2 (ja) 画像処理装置、画像処理システム、画像処理方法
KR20180051241A (ko) 직사각형 윈도우를 이용한 스테레오 정합 방법 및 스테레오 정합 시스템
CN112184833B (zh) 一种双目立体匹配算法的硬件实现系统和方法
Fedak et al. Image and video super-resolution via accurate motion estimation
JP2025165222A (ja) 画像処理装置
Phan et al. Edge-aware temporally consistent SimpleFlow: Optical flow without global optimization

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant