WO2006055512A2 - Appareil et procede de traitement de donnees video - Google Patents

Appareil et procede de traitement de donnees video Download PDF

Info

Publication number
WO2006055512A2
WO2006055512A2 PCT/US2005/041253 US2005041253W WO2006055512A2 WO 2006055512 A2 WO2006055512 A2 WO 2006055512A2 US 2005041253 W US2005041253 W US 2005041253W WO 2006055512 A2 WO2006055512 A2 WO 2006055512A2
Authority
WO
WIPO (PCT)
Prior art keywords
data
video
pels
spatial
motion
Prior art date
Application number
PCT/US2005/041253
Other languages
English (en)
Other versions
WO2006055512A3 (fr
Inventor
John Weiss
Charles Paul Pace
Original Assignee
Euclid Discoveries, Llc
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 Euclid Discoveries, Llc filed Critical Euclid Discoveries, Llc
Priority to AU2005306599A priority Critical patent/AU2005306599C1/en
Priority to JP2007543165A priority patent/JP2008521347A/ja
Priority to CN2005800467624A priority patent/CN101103364B/zh
Priority to EP05822396A priority patent/EP1815397A4/fr
Publication of WO2006055512A2 publication Critical patent/WO2006055512A2/fr
Publication of WO2006055512A3 publication Critical patent/WO2006055512A3/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G06T9/001—Model-based coding, e.g. wire frame
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • 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
    • H04N19/20—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using video object coding

Definitions

  • the present invention is generally related to the field of digital signal processing, and more particularly, to computer apparatus and computer-implemented methods for the efficient representation and processing of signal or image data, and most particularly, video data.
  • FIG. 1 a block diagram displays the typical prior art video processing system.
  • Such systems typically include the following stages: an input stage 102, a processing stage 104, an output stage 106, and one or more data storage mechanism(s) 108.
  • the input stage 102 may include elements such as camera sensors, camera sensor arrays, range finding sensors, or a means of retrieving data from a storage mechanism.
  • the input stage provides video data representing time correlated sequences of man-made and/or naturally occurring phenomena.
  • the salient component of the data may be masked or contaminated by noise or other unwanted signals.
  • the video data in the form of a data stream, array, or packet, may be presented to the processing stage 104 directly or through an intermediate storage element 108 in accordance with a predefined transfer protocol.
  • the processing stage 104 may take the form of dedicated analog or digital devices, or programmable devices such as central processing units (CPUs), digital signal processors (DSPs), or field programmable gate arrays (FPGAs) to execute a desired set of video data processing operations.
  • the processing stage 104 typically includes one or more CODECs (COder/DECcoders).
  • Output stage 106 produces a signal, display, or other response which is capable of affecting a user or external apparatus.
  • an output device is employed to generate an indicator signal, a display, a hardcopy, a representation of processed data in storage, or to initiate transmission of data to a remote site. It may also be employed to provide an intermediate signal or control parameter for use in subsequent processing operations.
  • storage element 108 may be either non- volatile, such as read-only storage media, or volatile, such as dynamic random access memory (RAM). It is not uncommon for a single video processing system to include several types of storage elements, with the elements having various relationships to the input, processing, and output stages. Examples of such storage elements include input buffers, output buffers, and processing caches.
  • the primary objective of the video processing system in Fig. 1 is to process input data to produce an output which is meaningful for a specific application.
  • processing operations including noise reduction or cancellation, feature extraction, object segmentation and/or normalization, data categorization, event detection, editing, data selection, data re-coding, and transcoding.
  • the design of a signal processing system is influenced by the intended use of the system and the expected characteristics of the source signal used as an input. In most cases, the performance efficiency required will also be a significant design factor. Performance efficiency, in turn, is affected by the amount of data to be processed compared with the data storage available as well as the computational complexity of the application compared with the computing power available.
  • An "optimal" video processing system is efficient, reliable, and robust in performing a desired set of processing operations.
  • Such operations may include the storage, transmission, display, compression, editing, encryption, enhancement, categorization, feature detection, and recognition of the data.
  • Secondary operations may include integration of such processed data with other information sources. Equally important, in the case of a video processing system, the outputs should be compatible with human vision by avoiding the introduction of perceptual artifacts.
  • a video processing system may be described as "robust” if its speed, efficiency, and quality do not depend strongly on the specifics of any particular characteristics of the input data. Robustness also is related to the ability to perform operations when some of the input is erroneous. Many video processing systems fail to be robust enough to allow for general classes of applications - providing only application to the same narrowly constrained data that was used in the development of the system.
  • Ensemble variability refers to any unpredictability in a class of data or information sources.
  • Data representative of visual information has a very large degree of ensemble variability because visual information is typically unconstrained.
  • Visual data may represent any spatial array sequence or spatio-temporal sequence that can be formed by light incident on a sensor array.
  • video processors hi modeling visual phenomena, video processors generally impose some set of constraints and/or structure on the manner in which the data is represented or interpreted. As a result, such methods can introduce systematic errors which would impact the quality of the output, the confidence with which the output may be regarded, and the type of subsequent processing tasks that can reliably be performed on the data.
  • Quantization methods reduce the precision of data in the video frames while attempting to retain the statistical variation of that data.
  • the video data is analyzed such that the distributions of data values are collected into probability distributions.
  • these quantization methods often result in perceptually implausible colors and can induce abrupt pixilation in originally smooth areas of the video frame.
  • Differential coding is also typically used to capitalize on the local spatial similarity of data.
  • Data in one part of the frame tend to be clustered around similar data in that frame, and also in a similar position in subsequent frames.
  • Representing the data in terms of its spatially adjacent data can then be combined with quantization and the net result is that, for a given precision, representing the differences is more accurate than using the absolute values of the data.
  • This assumption works well when the spectral resolution of the original video data is limited, such as in black and white video, or low- color video. As the spectral resolution of the video increases, the assumption of similarity breaks down significantly. The breakdown is due to the inability to selectively preserve the precision of the video data.
  • Residual coding is similar to differential encoding in that the error of the representation is further differentially encoded in order to restore the precision of the original data to a desired level of accuracy.
  • Variations of these methods attempt to transform the video data into alternate representations that expose data correlations in spatial phase and scale. Once the video data has been transformed in these ways, quantization and differential coding methods can then be applied to the transformed data resulting in an increase in the preservation of the salient image features.
  • Two of the most prevalent of these transform video compression techniques are the discrete cosine transform (DCT) and discrete wavelet transform (DWT). Error in the DCT transform manifests in a wide variation of video data values, and therefore, the DCT is typically used on blocks of video data in order to localize these false correlations. The artifacts from this localization often appear along the border of the blocks.
  • the present invention is a computer-implemented video processing method that provides both computational and analytical advantages over existing state-of-the-art methods.
  • the principle inventive method is the integration of a linear decompositional method, a spatial segmentation method, and a spatial normalization method. Spatially constraining video data greatly increases the robustness and applicability of linear decompositional methods. Additionally, spatial segmentation of the data corresponding to the spatial normalization, can further serve to increase the benefits derived from spatial normalization alone.
  • the present invention provides a means by which signal data can be efficiently processed into one or more beneficial representations.
  • the present invention is efficient at processing many commonly occurring data sets and is particularly efficient at processing video and image data.
  • the inventive method analyzes the data and provides one or more concise representations of that data to facilitate its processing and encoding.
  • Each new, more concise data representation allows reduction in computational processing, transmission bandwidth, and storage requirements for many applications, including, but not limited to: encoding, compression, transmission, analysis, storage, and display of the video data.
  • the invention includes methods for identification and extraction of salient components of the video data, allowing a prioritization in the processing and representation of the data. Noise and other unwanted parts of the signal are identified as lower priority so that further processing can be focused on analyzing and representing the higher priority parts of the video signal. As a result, the video signal is represented more concisely than was previously possible. And the loss in accuracy is concentrated in the parts of the video signal that are perceptually unimportant.
  • Fig. 1 is a block diagram illustrating a prior art video processing system.
  • Fig. 2 is a block diagram providing an overview of the invention that shows the major modules for processing video.
  • Fig. 3 is a block diagram illustrating the motion estimation method of the invention.
  • Fig. 4 is a block diagram illustrating the global registration method of the invention.
  • Fig. 5 is a block diagram illustrating the normalization method of the invention.
  • Fig. 6 is a block diagram illustrating the hybrid spatial normalization compression method.
  • Fig. 7 is a block diagram illustrating the mesh generation method of the invention employed in local normalization.
  • Fig. 8 is a block diagram illustrating the mesh based normalization method of the invention employed in local normalization.
  • Fig. 9 is a block diagram illustrating the combined global and local normalization method of the invention.
  • Fig. 10 is a block diagram illustrating the GPCA - basic polynomial fitting and differentiation method of the invention.
  • Fig. 11 is a block diagram illustrating the recursive GPCA refinement method of the invention.
  • the present invention as illustrated in Fig. 2 analyzes signal data and identifies the salient components.
  • the signal is comprised of video data
  • analysis of the spatiotemporal stream reveals salient components that are often specific objects, such as faces.
  • the identification process qualifies the existence and significance of the salient components, and chooses one or more of the most significant of those qualified salient components. This does not limit the identification and processing of other less salient components after or concurrently with the presently described processing.
  • the aforementioned salient components are then further analyzed, identifying the variant and invariant subcomponents.
  • the identification of invariant subcomponents is the process of modeling some aspect of the component, thereby revealing a parameterization of the model that allows the component to be synthesized to a desired level of accuracy.
  • a preferred embodiment of the present invention details the linear decomposition of a foreground video object.
  • the object is normalized spatially, thereby yielding a compact linear appearance model.
  • a further preferred embodiment additionally segments the foreground object from the background of the video frame prior to spatial normalization.
  • a preferred embodiment of the invention applies the present invention to a video of a person speaking into a camera while undergoing a small amount of motion.
  • a preferred embodiment of the invention applies the present invention to any object in a video that can be represented well through spatial transformations.
  • a preferred embodiment of the invention specifically employs block-based motion estimation to determine finite differences between two or more frames of video.
  • a higher order motion model is factored from the finite differences in order to provide a more effective linear decomposition.
  • the constituent salient components of the signal may be retained, and all other signal components may be diminished or removed.
  • the process of detecting the salient component is shown in Fig.2, where the Video Frame (202) is processed by one or more Detect Object (206) processes, resulting in one or more objects being identified, and subsequently tracked.
  • the retained components represent the intermediate form of the video data.
  • This intermediate data can then be encoded using techniques that are typically not available to existing video processing methods. As the intermediate data exists in several forms, standard video encoding techniques can also be used to encode several of these intermediate forms. For each instance, the present invention determines and then employs the encoding technique that is most efficient.
  • a saliency analysis process detects and classifies salient signal modes.
  • This process employs a combination of spatial filters specifically designed to generate a response signal whose strength is relative to the detected saliency of an object in the video frame.
  • the classifier is applied at differing spatial scales and in different positions of the video frame. The strength of the response from the classifier indicates the likelihood of the presence of a salient signal mode.
  • the process classifies it with a correspondingly strong response.
  • the detection of the salient signal mode distinguishes the present invention by enabling the subsequent processing and analysis on the salient information in the video sequence.
  • the present invention Given the detection location of a salient signal mode in one or more frames of video, the present invention analyzes the salient signal mode's invariant features. Additionally, the invention analyzes the residual of the signal, the "less-salient" signal modes, for invariant features. Identification of invariant features provides a basis for reducing redundant information and segmenting (i.e. separating) signal modes.
  • spatial positions in one or more frames are determined through spatial intensity field gradient analysis. These features correspond to some intersection of "lines” which can be described loosely as a "corner”. Such an embodiment further selects a set of such corners that are both strong corners and spatially disparate from each other, herein referred to as the feature points. Further, employing a hierarchical multi-resolution estimation of the optical flow allows the determination of the translational displacement of the feature points over time.
  • the Track Object (220) process is shown to pull together the detection instances from the Detect Object processes (208) and further Identify Correspondences (222) of features of one or more of the detected objects over a multitude of Video Frames (202 & 204).
  • a non-limiting embodiment of feature tracking can be employed such that the features are used to qualify a more regular gradient analysis method such as block-based motion estimation.
  • Another embodiment anticipates the prediction of motion estimates based on feature tracking.
  • a robust object classifier is employed to track faces in frames of video.
  • Such a classifier is based on a cascaded response to oriented edges that has been trained on faces.
  • the edges are defined as a set of basic Haar features and the rotation of those features by 45 degrees.
  • the cascaded classifier is a variant of the AdaBoost algorithm. Additionally, response calculations can be optimized through the use of summed area tables.
  • Registration involves the assignment of correspondences between elements of identified objects in two or more video frames. These correspondences become the basis for modeling the spatial relationships between video data at temporally distinct points in the video data.
  • One means of modeling the apparent optical flow in a spatio-temporal sequence can be achieved through generation of a finite difference field from two or more frames of the video data.
  • Optical flow field can be sparsely estimated if the correspondences conform to certain constancy constraints in both a spatial and an intensity sense.
  • a Frame (302 or 304) is sub-sampled spatially, possibly through a decimation process (306), or some other sub-sampling process (e.g. low pass filter).
  • These spatially reduced images (310 & 312) can be further sub-sampled as well.
  • FSBB full search block-based
  • DSBB diamond search block- based
  • phase-based normalized cross correlation as illustrated in Fig. 3 transforms a block from the current frame and the previous frame into "phase space” and finds the cross correlation of those two blocks.
  • the cross correlation is represented as a field of values whose positions correspond to the 'phase shifts' of edges between the two blocks. These positions are isolated through thresholding and then transformed back into spatial coordinates.
  • the spatial coordinates are distinct edge displacements, and correspond to motion vectors.
  • feature points are used to generate a mesh constituted of triangular elements whose vertices correspond to the feature points.
  • the corresponding feature points is other frames imply an interpolated "warping" of the triangles, and correspondingly the pels, to generate a local deformation model.
  • a spatial density model termination condition is employed to optimize the processing of the mesh vertices.
  • the processing can be terminated.
  • the termination generates a score. Vertex and feature points entering the processing are sorted by this score. If the point is too spatially close to an existing point, or if the point does not correspond to an edge in the image gradient, then it is discarded. Otherwise, the image gradient in the neighborhood of the point is descended, and if the residual of the gradient exceeds a limit, then that point is also discarded.
  • the present invention may utilize spatial segmentation based on spectral classification to segment pels in frames of the video. Further, correspondence between regions may be determined based on overlap of spectral regions with regions in previous segmentations. It is observed that when video frames are roughly made up of continuous color regions that are spatially connected into larger regions that correspond to objects in the video frame, identification and tracking of the colored (or spectral) regions can facilitate the subsequent segmentation of objects in a video sequence.
  • the current frame is constructed by motion compensating the previous frame using motion vectors, followed by application of a residual update for the compensation blocks, and finally, any blocks that do not have a sufficient match are encoded as new blocks.
  • Sub-band decomposition reduces the spatial variance in any one decomposition video.
  • the decomposition coefficients for any one sub-band are arranged spatially into a sub-band video. For instance, the DC coefficients are taken from each block and arranged into a sub-band video that looks like a postage stamp version of the original video. This is repeated for all the other sub-bands, and the resulting sub-band videos are each processed using PCA.
  • the sub-bands are already arranged in the manner described for DCT.
  • discretely sampled phenomena data and derivative data can be represented as a set of data vectors corresponding to an algebraic vector space.
  • These data vectors include, in a non-limiting way, the pels in the normalized appearance of the segmented object, the motion parameters, and any structural positions of features or vertices in two or three dimensions.
  • Each of these vectors exists in a vector space, and the analysis of the geometry of the space can be used to yield concise representations of the sampled, or parameter, vectors.
  • Beneficial geometric conditions are typified by parameter vectors that form compact subspaces. When one or more subspaces are mixed, creating a seemingly more complex single subspace, the constituent subspaces can be difficult to discern.
  • There are several methods of segmentation that allow for the separation of such subspaces through examining the data in a higher dimensional vector space that is created through some interaction of the original vectors (such as inner product).
  • One method of segmenting the vector space involves the projection of the vectors into a Veronese vector space representing polynomials. This method is well known in the prior art as the Generalized PCA or GPCA technique. Through such a projection, the normals to the polynomials are found, grouped, and the original vectors associated with those normals can be grouped together.
  • An example of the utility of this technique is in the factoring of two dimensional spatial point correspondences tracked over time into a three dimensional structure model and the motion of that three dimensional model.
  • the inventive extension to the GPCA technique has greater advantages in cases where there are multiple roots in the Veronese polynomial vector space. Additionally, when the prior art technique encounters the degenerate case when normals in the Veronese map are parallel to a vector space axis, the present method is not degenerate.
  • the new videos of object and the non-object, having their pels spatially normalized, are provided as input to a conventional block-based compression algorithm.
  • the global motion model parameters are used to de- normalize those decoded frames, and the object pels are composited together and onto the non-object pels to yield an approximation of the original video stream.
  • the primary data structures include global spatial deformation parameters and object segmentation specification masks.
  • the primary communication protocols are layers that include the transmission of the global spatial deformation parameters and object segmentation specification masks.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

L'invention concerne un appareil et des procédés permettant de traiter des données vidéo. Elle concerne également une représentation de données vidéo pouvant servir à évaluer la concordance entre les données et un modèle approprié pour une paramétrisation particulière des données, ce qui permet de comparer diverses techniques de paramétrisation et de sélectionner la technique optimale pour un traitement vidéo continu desdites données. La représentation peut servir, dans une forme intermédiaire, comme partie d'un processus plus vaste ou comme mécanisme de rétroaction en matière de traitement de données vidéo. Dans sa forme intermédiaire, la représentation peut être utilisée dans des processus de stockage, d'amélioration, d'affinement, d'extraction d'attributs, de compression, de codage, et de transmission de données vidéo. L'invention concerne l'extraction d'informations importantes d'une manière robuste et efficace parallèlement au traitement des problèmes d'ordinaire associés aux sources de données vidéo.
PCT/US2005/041253 2004-11-17 2005-11-16 Appareil et procede de traitement de donnees video WO2006055512A2 (fr)

Priority Applications (4)

Application Number Priority Date Filing Date Title
AU2005306599A AU2005306599C1 (en) 2004-11-17 2005-11-16 Apparatus and method for processing video data
JP2007543165A JP2008521347A (ja) 2004-11-17 2005-11-16 ビデオデータを処理する装置および方法
CN2005800467624A CN101103364B (zh) 2004-11-17 2005-11-16 用来处理视频数据的装置和方法
EP05822396A EP1815397A4 (fr) 2004-11-17 2005-11-16 Appareil et procede de traitement de donnees video

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US62881904P 2004-11-17 2004-11-17
US62886104P 2004-11-17 2004-11-17
US60/628,861 2004-11-17
US60/628,819 2004-11-17

Publications (2)

Publication Number Publication Date
WO2006055512A2 true WO2006055512A2 (fr) 2006-05-26
WO2006055512A3 WO2006055512A3 (fr) 2007-03-15

Family

ID=36407676

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2005/041253 WO2006055512A2 (fr) 2004-11-17 2005-11-16 Appareil et procede de traitement de donnees video

Country Status (6)

Country Link
EP (1) EP1815397A4 (fr)
JP (1) JP2008521347A (fr)
KR (1) KR20070086350A (fr)
CN (1) CN101103364B (fr)
AU (1) AU2005306599C1 (fr)
WO (1) WO2006055512A2 (fr)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1846892A1 (fr) * 2005-01-28 2007-10-24 Euclid Discoveries, LLC Dispositifs et procedes pour le traitement de donnees video
EP1878256A1 (fr) * 2005-03-31 2008-01-16 Euclid Discoveries, LLC Dispositif et procede pour le traitement de donnees video
JP2009540675A (ja) * 2006-06-08 2009-11-19 ユークリッド・ディスカバリーズ・エルエルシー ビデオデータを処理する装置および方法
WO2009151755A2 (fr) * 2008-05-16 2009-12-17 Microsoft Corporation Traitement vidéo
JP2012505600A (ja) * 2008-10-07 2012-03-01 ユークリッド・ディスカバリーズ・エルエルシー 特徴を基礎とするビデオ圧縮
US8243118B2 (en) 2007-01-23 2012-08-14 Euclid Discoveries, Llc Systems and methods for providing personal video services
US8553782B2 (en) 2007-01-23 2013-10-08 Euclid Discoveries, Llc Object archival systems and methods
US8908766B2 (en) 2005-03-31 2014-12-09 Euclid Discoveries, Llc Computer method and apparatus for processing image data
US9578345B2 (en) 2005-03-31 2017-02-21 Euclid Discoveries, Llc Model-based video encoding and decoding
US9621917B2 (en) 2014-03-10 2017-04-11 Euclid Discoveries, Llc Continuous block tracking for temporal prediction in video encoding
US9743078B2 (en) 2004-07-30 2017-08-22 Euclid Discoveries, Llc Standards-compliant model-based video encoding and decoding
US10091507B2 (en) 2014-03-10 2018-10-02 Euclid Discoveries, Llc Perceptual optimization for model-based video encoding
US10097851B2 (en) 2014-03-10 2018-10-09 Euclid Discoveries, Llc Perceptual optimization for model-based video encoding

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9532069B2 (en) 2004-07-30 2016-12-27 Euclid Discoveries, Llc Video compression repository and model reuse
US8902971B2 (en) 2004-07-30 2014-12-02 Euclid Discoveries, Llc Video compression repository and model reuse
EP2328124B1 (fr) * 2009-11-25 2019-05-15 Agfa Nv Procédé d'amélioration du contraste de phénomènes localisés dans l'espace dans une image
US9258525B2 (en) * 2014-02-25 2016-02-09 Alcatel Lucent System and method for reducing latency in video delivery

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5592228A (en) * 1993-03-04 1997-01-07 Kabushiki Kaisha Toshiba Video encoder using global motion estimation and polygonal patch motion estimation
KR100235343B1 (ko) * 1994-12-29 1999-12-15 전주범 영역분할 기법을 이용한 동영상신호 부호화기의 움직임 벡터 측정장치
US6037988A (en) * 1996-03-22 2000-03-14 Microsoft Corp Method for generating sprites for object-based coding sytems using masks and rounding average
US6711278B1 (en) * 1998-09-10 2004-03-23 Microsoft Corporation Tracking semantic objects in vector image sequences
US7124065B2 (en) * 1998-10-26 2006-10-17 Speech Technology And Applied Research Corporation Determining a tangent space and filtering data onto a manifold
KR100611999B1 (ko) * 1999-08-27 2006-08-11 삼성전자주식회사 그리디 알고리듬을 이용한 객체 기반 콰드 트리 메쉬 움직임 보상방법
US6661004B2 (en) * 2000-02-24 2003-12-09 Massachusetts Institute Of Technology Image deconvolution techniques for probe scanning apparatus
US20040135788A1 (en) * 2000-12-22 2004-07-15 Davidson Colin Bruce Image processing system
US7136505B2 (en) * 2002-04-10 2006-11-14 National Instruments Corporation Generating a curve matching mapping operator by analyzing objects of interest and background information
US7203356B2 (en) * 2002-04-11 2007-04-10 Canesta, Inc. Subject segmentation and tracking using 3D sensing technology for video compression in multimedia applications
FR2852773A1 (fr) * 2003-03-20 2004-09-24 France Telecom Procedes et dispositifs de codage et de decodage d'une sequence d'images par decomposition mouvement/texture et codage par ondelettes
EP2602742A1 (fr) * 2004-07-30 2013-06-12 Euclid Discoveries, LLC Appareil et procédé de traitement de données vidéo
CN101061489B (zh) * 2004-09-21 2011-09-07 欧几里得发现有限责任公司 用来处理视频数据的装置和方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of EP1815397A4 *

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9743078B2 (en) 2004-07-30 2017-08-22 Euclid Discoveries, Llc Standards-compliant model-based video encoding and decoding
EP1846892A1 (fr) * 2005-01-28 2007-10-24 Euclid Discoveries, LLC Dispositifs et procedes pour le traitement de donnees video
EP1846892A4 (fr) * 2005-01-28 2011-04-06 Euclid Discoveries Llc Dispositifs et procedes pour le traitement de donnees video
US8908766B2 (en) 2005-03-31 2014-12-09 Euclid Discoveries, Llc Computer method and apparatus for processing image data
EP1878256A1 (fr) * 2005-03-31 2008-01-16 Euclid Discoveries, LLC Dispositif et procede pour le traitement de donnees video
US9578345B2 (en) 2005-03-31 2017-02-21 Euclid Discoveries, Llc Model-based video encoding and decoding
EP1878256A4 (fr) * 2005-03-31 2011-06-08 Euclid Discoveries Llc Dispositif et procede pour le traitement de donnees video
US8964835B2 (en) 2005-03-31 2015-02-24 Euclid Discoveries, Llc Feature-based video compression
US8942283B2 (en) 2005-03-31 2015-01-27 Euclid Discoveries, Llc Feature-based hybrid video codec comparing compression efficiency of encodings
US9106977B2 (en) 2006-06-08 2015-08-11 Euclid Discoveries, Llc Object archival systems and methods
JP2009540675A (ja) * 2006-06-08 2009-11-19 ユークリッド・ディスカバリーズ・エルエルシー ビデオデータを処理する装置および方法
US8842154B2 (en) 2007-01-23 2014-09-23 Euclid Discoveries, Llc Systems and methods for providing personal video services
US8553782B2 (en) 2007-01-23 2013-10-08 Euclid Discoveries, Llc Object archival systems and methods
US8243118B2 (en) 2007-01-23 2012-08-14 Euclid Discoveries, Llc Systems and methods for providing personal video services
US8824801B2 (en) 2008-05-16 2014-09-02 Microsoft Corporation Video processing
WO2009151755A3 (fr) * 2008-05-16 2010-02-25 Microsoft Corporation Traitement vidéo
WO2009151755A2 (fr) * 2008-05-16 2009-12-17 Microsoft Corporation Traitement vidéo
JP2012505600A (ja) * 2008-10-07 2012-03-01 ユークリッド・ディスカバリーズ・エルエルシー 特徴を基礎とするビデオ圧縮
US9621917B2 (en) 2014-03-10 2017-04-11 Euclid Discoveries, Llc Continuous block tracking for temporal prediction in video encoding
US10091507B2 (en) 2014-03-10 2018-10-02 Euclid Discoveries, Llc Perceptual optimization for model-based video encoding
US10097851B2 (en) 2014-03-10 2018-10-09 Euclid Discoveries, Llc Perceptual optimization for model-based video encoding

Also Published As

Publication number Publication date
WO2006055512A3 (fr) 2007-03-15
CN101103364B (zh) 2010-05-12
AU2005306599A1 (en) 2006-05-26
EP1815397A2 (fr) 2007-08-08
JP2008521347A (ja) 2008-06-19
AU2005306599B2 (en) 2010-02-18
KR20070086350A (ko) 2007-08-27
CN101103364A (zh) 2008-01-09
EP1815397A4 (fr) 2012-03-28
AU2005306599C1 (en) 2010-06-03

Similar Documents

Publication Publication Date Title
US7457435B2 (en) Apparatus and method for processing video data
US7436981B2 (en) Apparatus and method for processing video data
US7457472B2 (en) Apparatus and method for processing video data
AU2006230545B2 (en) Apparatus and method for processing video data
AU2005306599B2 (en) Apparatus and method for processing video data
US7426285B2 (en) Apparatus and method for processing video data
US7508990B2 (en) Apparatus and method for processing video data
CA2575211C (fr) Dispositif et procede permettant de traiter des donnees video
WO2006083567A1 (fr) Dispositifs et procedes pour le traitement de donnees video
WO2007146102A2 (fr) Appareil et procédé pour traiter des données vidéo
AU2006211563B2 (en) Apparatus and method for processing video data

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KM KN KP KR KZ LC LK LR LS LT LU LV LY MA MD MG MK MN MW MX MZ NA NG NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU LV MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
WWE Wipo information: entry into national phase

Ref document number: 2005306599

Country of ref document: AU

Ref document number: 2007543165

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2005306599

Country of ref document: AU

Date of ref document: 20051116

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2005822396

Country of ref document: EP

WWP Wipo information: published in national office

Ref document number: 2005306599

Country of ref document: AU

WWE Wipo information: entry into national phase

Ref document number: 2614/CHENP/2007

Country of ref document: IN

Ref document number: 1020077013724

Country of ref document: KR

WWE Wipo information: entry into national phase

Ref document number: 200580046762.4

Country of ref document: CN

WWP Wipo information: published in national office

Ref document number: 2005822396

Country of ref document: EP