[go: up one dir, main page]

WO2011072259A1 - Système et procédé de segmentation de données d'images tridimensionnelles - Google Patents

Système et procédé de segmentation de données d'images tridimensionnelles Download PDF

Info

Publication number
WO2011072259A1
WO2011072259A1 PCT/US2010/059955 US2010059955W WO2011072259A1 WO 2011072259 A1 WO2011072259 A1 WO 2011072259A1 US 2010059955 W US2010059955 W US 2010059955W WO 2011072259 A1 WO2011072259 A1 WO 2011072259A1
Authority
WO
WIPO (PCT)
Prior art keywords
class
slice
image data
identifiers
pixel
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.)
Ceased
Application number
PCT/US2010/059955
Other languages
English (en)
Inventor
Lauren Christopher
Yan Sun
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.)
Indiana University Research and Technology Corp
Original Assignee
Indiana University Research and Technology Corp
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 Indiana University Research and Technology Corp filed Critical Indiana University Research and Technology Corp
Priority to US13/514,768 priority Critical patent/US8897544B2/en
Publication of WO2011072259A1 publication Critical patent/WO2011072259A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G06F18/24155—Bayesian classification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects

Definitions

  • the system and method described below relate to a computing architecture and methods for manipulating image data in general, and more particularly to segmentation of three- dimensional image data.
  • Image data may be two-dimensional, such as image data corresponding to a photograph, or three- dimensional image data.
  • image data generated by various medical imaging devices including magnetic resonance imaging (MRI) devices.
  • MRI magnetic resonance imaging
  • These image data depict physical structures, such as organs of a subject undergoing an MRI, in a series of two-dimensional images taken at various locations along a third axis extending through the subject.
  • the third dimension in three-dimensional image data may also represent a temporal dimension instead of a spatial dimension.
  • a video recording includes a multiple frames, where each frame is a two-dimensional image taken at a particular time.
  • the three-dimensional image data represent multiple frames of the video taken at different times.
  • the three-dimensional image data are often analyzed as an arrangement of "pixel" values.
  • Each pixel contains image data corresponding to a single position in the three- dimensional space.
  • each pixel is assigned one or more values, typically numeric values, that represent information collected for the image at the location that the pixel represents.
  • image segmentation An operation to perform on an image is known as "image segmentation.”
  • An image segmentation operation groups various pixels in the image together into two or more segments. These pixels are grouped together based on some shared characteristic of the image data in the selected pixels.
  • Various segmentation techniques are known to the art, and one such technique is known as Bayesian Expectation Maximization / Maximization of Posterior Marginals (EM/MPM) segmentation.
  • EM/MPM technique includes two advantages over other segmentation techniques known in the art. First, EM/MPM generates estimates for Gaussian mean and variance for the Gaussian distributions of variations in the measured brightness values of image data corresponding to each pixel. This enables the technique to reduce inaccuracies introduced by noise present in image data. Second, the
  • EM/MPM technique analyzes image data for each pixel with respect to neighboring pixels in the three-dimensional image data.
  • a particular pixel has a high likelihood to have a brightness value that is the same or similar to the majority of its neighbors, and analyzing the neighbors reduces the effects of single-pixel errors in the image data.
  • the EM/MPM technique performs a statistical cost-minimization technique.
  • the "cost" is the estimated likelihood that a given class identifier for a group of pixels has errors.
  • the EM/MPM technique groups pixels into segments using segment distributions that are determined to have the lowest probability of errors. [0005] While various segmentation techniques are known to the art, many computational challenges limit the use of these techniques in practical applications.
  • image data may take a substantial amount of time to segment image data, particularly three-dimensional image data.
  • the size of image data representing a three-dimensional image expands as a cube of the number of pixels in each of the three dimensions.
  • a single three-dimensional image may grow to be many gigabytes in size, and the sizes of the images will continue to increase at a cubic rate with the development of higher resolution imaging devices.
  • Iterative image analysis techniques such as the MPM portion of the EM/MPM technique require multiple operations to be performed on each pixel in the image data.
  • Standard central processing units known in the art and even parallelized processors such as general-purpose graphical processing units (GPGPUs) may take a substantial amount of time to perform image analysis operations due to the need to exchange large amounts of data with memory, such as random access memory (RAM).
  • RAM random access memory
  • iterative techniques such as the MPM technique introduce data dependencies that reduce the effectiveness of parallel processing devices since one iteration must complete to provide the data used in the subsequent iteration.
  • the amount of time needed to load and store data and the difficulties in parallelizing image processing operations render conventional computing devices impractical for many time sensitive imaging applications. Consequently, improvements to computing architectures and methods of image analysis that reduce the time needed to perform image analysis operations on image data are beneficial.
  • a system for computing class identifiers for three-dimensional pixel data comprises a plurality of class identifying processors, and a data grouper operatively connected to a first memory.
  • Each class identifying processor has a plurality of inputs for at least one pixel value and a plurality of class identifiers for pixel values neighboring the at least one pixel value and each class identifying processor is configured to generate a class identifier for the at least one pixel value input with reference to the class identifiers for the neighboring pixel values.
  • the data grouper is configured to retrieve a plurality of pixel values from the first memory and a plurality of class identifiers for pixel values neighboring the retrieved pixel values.
  • a method for segmenting three-dimensional image data includes generating a class identifier for each pixel value in a first slice of three-dimensional image data with reference to a plurality of class identifiers
  • FIG. 1 is a view of pixels arranged in a three-dimensional space.
  • FIG. 2 is a view of a central pixel and six pixels surrounding the central pixel arranged for use in an MPM calculation.
  • FIG. 3 is a block flow diagram that depicts an EM/MPM image segmentation process.
  • FIG. 4 is a schematic diagram depicting an exemplary computing architecture for processing image data.
  • FIG. 5 is a block flow diagram that depicts memory operations for loading image slices during an iterative MPM calculation.
  • FIG. 6 is a schematic diagram depicting the computational block of FIG. 4 in more detail.
  • the term "three-dimensional image” refers to an image that includes two or more two- dimensional images arranged in a three-dimensional space. Each two-dimensional image includes a plurality of pixels arranged along an X axis and a Y axis. Each pixel includes image data, with typical image data for a single pixel being one or more numeric values that indicate image intensity, color levels, or other information generated at the position corresponding to the pixel.
  • the three-dimensional image includes multiple two-dimensional images arranged in a predetermined order along a Z axis.
  • the Z axis may form a three-dimensional image corresponding to a physical space, or may represent a logical dimension such as time where images taken at different times are arranged in a three-dimensional space.
  • image slice and “slice” refer to a two-dimensional plane of pixels taken through a three- dimensional image along the Z axis.
  • each slice includes a one-dimensional arrangement of pixels taken from each two-dimensional image in the three-dimensional image data.
  • FIG. 1 shows an example arrangement of pixels 100 in a three-dimensional space.
  • the forward facing pixels 104 arranged along the X and Y axes are one of the two-dimensional images that form the three-dimensional image data.
  • the shaded pixels 108 extending along the Z axis represent one image slice taken through the three-dimensional image data.
  • the selection of axes and the orientation of image slices depicted in FIG. 1 is merely exemplary of one set of three-dimensional image data, and various different coordinate systems as well as axis and slice orientations may also be used.
  • the words "calculate” and “identify” include the operation of a circuit comprised of hardware, software, or a combination of hardware and software that reaches a result based on one or more measurements of physical relationships with accuracy or precision suitable for a practical application.
  • FIG. 3 depicts a flow diagram of an EM/MPM image segmentation process 300.
  • the end result of process 300 is to assign a class identifier (k) to each pixel in the three-dimensional image data, where pixels sharing a common class identifier are considered to be in a single segment in the image data.
  • the number of classes, and consequently the number of segments, that the image data are divided into is provided a priori to the segmentation process.
  • the number of classes for image segmentation in a three-dimensional MRI image may match the number of tissue types for various organs or bodily structures present in the image data.
  • Process 300 begins by assigning class identifiers to each pixel in the three-dimensional image data (block 304).
  • the class identifiers are selected randomly from the predetermined classes.
  • An initial Expectation Maximization (EM) phase of process 300 generates estimated Gaussian parameters, including mean and variance parameters, that are associated with each class identifier and are used in the MPM calculations (block 308).
  • EM Expectation Maximization
  • Process 300 uses the assigned class identifiers and estimated parameters to perform a predetermined number of MPM iterations that calculate the class identifiers k having the minimum expected error rate (block 312).
  • the MPM technique uses a Bayesian probability distribution that includes both prior marginal probabilities and later, or posterior, marginal probabilities.
  • the prior marginal probability distribution p(x) is defined using the following equations: s)- ⁇ r ⁇ ec Yxr
  • FIG. 2 depicts one central pixel x s 204 with six (6) surrounding pixels x r 208, 212, 216, 220, 224, and 228.
  • the x s and x r data correspond to the class identifiers k associated with the central pixel x s and neighboring pixels x r .
  • neighbor pixels 208, 212, 220, and 224 are in the same slice as central pixel 204, pixel 216 is in the previous slice, and pixel 228 is in the next slice along the X axis.
  • the MPM maximized posterior distribution is generated using the results of each prior distribution p(x) according to the following equation that is calculated for each segment class identifier k:
  • logpost(k) ⁇ - ⁇ [r ⁇ ec Yx r ⁇
  • y s is the numeric value of the original central pixel
  • ⁇ and ⁇ are the mean and variance of the class assigned to the central pixel, respectively.
  • the logpost(k) equation generates a probability value associated with the cost of the class k using the mean and variance values associated with the class k. Since the cost represents the likelihood of the identifier k being inaccurate, the MPM techniques selects classes that generate logpost (k) probabilities with the smallest magnitudes. In an alternative embodiment known as simulated annealing, the logpost(k) values are compared to a random variable such as a uniformly random variable and the class is selected in response to the logpost(k) having a greater or smaller magnitude than the random variable.
  • the MPM values are generated using a predetermined number of iterations, as shown in more detail below.
  • a the MPM process iterates seven times. The iterations ensure that the calculated expected error value converges to the values having the smallest magnitude for the image data.
  • Process 300 generates segments for the three-dimensional image data by assigning each pixel having the same class identifier k to a common segment (block 316).
  • FIG. 4 depicts a hardware controller 404 that is configured to perform the EM/MPM segmentation process.
  • Controller 404 embodied in FIG. 4 as a Field Programmable Gate Array (FPGA) is configured with a parallel computational block 408, a first internal memory RAM A 412, second internal memory RAM B 416, a memory controller 424, a CPU block 420, and a pseudo-random number generator 430.
  • An external RAM 428 interfaces with the memory controller 424.
  • RAM A 412 and RAM B 416 are high-speed memory units communicatively coupled to the computational block 408.
  • RAM A 412 and RAM B 416 exchange intermediate results for the MPM calculations to enable computational block 408 to calculate MPM results for each pixel.
  • RAM A 412 and RAM B 416 each have the same storage capacity that is sufficient to hold image data for each pixel in a predetermined number of image slices.
  • Computational block 408 is further comprised of a predetermined number of computational units that are configured to perform MPM computations in parallel.
  • Memory controller 424 arbitrates reading and writing of data between the controller 404 and the external RAM 428.
  • External RAM 428 may be a dynamic RAM (DRAM) memory having a sufficient size to hold some or all of the three- dimensional image data, the results from intermediate MPM iterations, and the segmentation classifications for the image data.
  • the external ram 428 is substantially larger than RAM A 412 and RAM B 416, and has a substantially longer access latency than either RAM A 412 or RAM B 416.
  • CPU block 420 is responsible for the EM calculations. Since the EM calculation does not require the parallelism of the MPM calculations, CPU block 420 is implemented as a conventional "soft" CPU formed from various logic gates in the FPGA controller 404. In an alternative embodiment, CPU 420 may be an external processor device that is operatively coupled to the controller 404.
  • Pseudo-random number generator 430 provides random numbers to the computational block 408, CPU block 420, and to other components that utilize random numbers.
  • One use for the pseudo-random number generator 430 is to generate random class identifiers k for each of the pixels in the image data at the start of the MPM process.
  • Another use is to generate random numbers corresponding to a random variable for use in a simulated annealing process to generate class identifiers k from probabilities generated by the logpost(k) calculations.
  • the pixels begin with random class identifiers, and the MPM process modifies the class identifiers to converge on appropriate segment identifications.
  • FIG. 4 depicts controller 404 as an FPGA, various other hardware configurations including application specific integrated circuit (ASIC) systems may implement the components of FIG. 4.
  • ASIC application specific integrated circuit
  • FIG. 5 depicts a process 500 for computing the iterations of the MPM process using the system 400 of FIG. 4.
  • the process 500 begins by loading image data corresponding to a predetermined number of slices N of the three-dimensional image data from the external RAM 428 to one of RAM A 412 or RAM B 414 (block 504).
  • the data structure of each loaded slice includes two data elements corresponding to each pixel.
  • the first element is y s , the image data for the loaded pixel.
  • the second element is k ⁇ + i, meaning the class identifier for the
  • This arrangement of data items in the external memory simplifies references to adjacent class identifier values k that are used during calculation of the logpost (k) values.
  • N is eight (8) so the image data and corresponding class identifiers for eight slices are loaded from the external RAM to the internal memory.
  • the selected slices are adjacent to one another on either the X or Y axes as seen in FIG. 1, and typically the first slice loaded is at one end of either the X or Y axis.
  • the computational block 408 performs the calculations for each iteration in parallel on groups of central pixels and neighbor pixels in each slice.
  • the first iteration block calculates the logpost(k) functions recited above for all of the pixels in the first N - 1 slices of the image data.
  • the logpost(k) functions rely on the central pixel x s as well as all the neighbor pixels x r as seen in FIG. 2.
  • the logpost(k) function uses the image data y s for the central pixel, and the class identifiers k for each of the neighbor pixels. Only image data for the central pixel is needed, and the current classification k assigned to the central pixel is not needed. Two of the neighbor pixels 216 and 228 are in the slices immediately before and after the central pixel 204. Note that the classification k for pixel 228, in the next slice from pixel 204, is loaded from memory with the image data y s for pixel 204 as described above.
  • Process block 508 generates a class identifier k for each pixel in the N - 1 slices using the results of the logpost(k) calculations as described above with reference to FIG. 3.
  • the resulting class identifiers and corresponding image data from the first round of calculations are stored in the internal memory other than the internal memory in which the initial image data were stored (block 512). For example, if RAM A 512 stored the image data for the first N slices, then RAM B stores the first intermediate set of class identifiers generated by the MPM calculations. Moving the results between the internal RAM stores in this manner may be referred to as a "ping pong" memory management since results are moved back and forth between RAM A 412 and RAM B 416 in a manner similar to volleying a ping pong ball across a table. The results calculated from the previous round of calculations become the inputs to the next round of calculations.
  • each successive calculation iteration reduces the number of slices that are calculated by one (block 520).
  • the number of calculated slices reduces because each of the central pixels x s needs to calculate logpost(k) using the values of each of the neighboring pixels.
  • the pixels in slice N - 1 cannot be calculated since these pixels need to have the results of the previous round of calculations for all of the neighboring pixels.
  • Slice N - 1 lacks neighboring pixels in slice N that went through the previous round of calculations. In each subsequent round, one less slice is calculated until N - 1 iterations have been calculated (block 516).
  • the iterative process produces a series of partially calculated results that are transferred between RAM A 412 and RAM B 416.
  • the following table depicts the intermediate results where, the S x>y notation denotes that a slice number x has undergone y MPM calculation iterations.
  • Each iteration reads input data from selected from whichever of RAM A and RAM B holds the results of the previous round of calculations. The results are then stored in the remaining RAM.
  • the number of slices calculated drops until the first slice has completed seven iterations, seen as S 1>7 .
  • S 1>7 To minimize the amount of data exchanged between RAM A and RAM B, if an iteration generates no new results for a particular slice, then the contents of RAM A and RAM B for the slice remain unchanged.
  • the intermediate calculations for the other slices are retained in the internal memory.
  • the intermediate class identifiers are stored in the appropriate local RAM (block 540), and the calculated class identifiers for the completed slice are stored in the external RAM (block 544).
  • the second slice requires a single iteration to produce the complete the MPM calculation.
  • the subsequent iteration completes the second slice.
  • each subsequent iteration produces the calculated MPM result for pixels in an image slice.
  • the controller 404 and process 500 pipeline the MPM calculations with a depth of N - 1 since the controller performs one logpost(k) calculation for each of the N - 1 image slices that held in RAM A and RAM B for each iteration once the first slice has been calculated.
  • Process 500 concludes when no more image slices are available in the three- dimensional image data (block 548).
  • the remaining N - 1 slices cannot undergo all N - 1 iterations of the MPM calculation because there are an insufficient numbers of neighboring image slices to calculate logpost(k) for all iterations. Since these slices are near one edge of the image, they may be discarded, or may have classes assigned based on the number of MPM iterations that were performed.
  • a similar problem also occurs with the first slice loaded into memory since there is no preceding slice to use in performing the MPM calculation.
  • the first slice may have a clique number C of five (5) used in the logpost(k) calculations instead of the usual six (6) to enable the MPM calculations to proceed.
  • FIG. 6 depicts the computational block 408 in more detail.
  • the computational block 408 includes a plurality of computational units, exemplified here as computational units 604, and a data grouper 612. Typical embodiments of the computational block 408 include eight (8) or sixteen (16) computational units 604, but alternative embodiments may have greater or fewer computational units as needed.
  • Each of the computational units 604 is configured to receive image data for a single central pixel and class identifier data corresponding to the six (6) neighboring pixels.
  • the class identifier data for the neighboring pixels may be intermediate results from a previous iteration of the MPM calculation.
  • Each computational unit 604 is configured to generate a class identifier using the MPM calculations on image data and neighbor class identifiers.
  • the image data are read from RAM A 412, and the output of the computation units 604 is stored in RAM B 416, but RAM B 416 may be the source and RAM A 412 may be the destination as well.
  • the image data and class identifiers are arranged in RAM A to read out image data for N adjacent pixels, as well as the class identifiers for all of the pixels that neighbor each of the N adjacent pixels.
  • N matches the number of computational units 604, so if there are sixteen computational units, sixteen adjacent pixels along with class identifiers for all the neighboring pixels are read.
  • Data grouper 612 is a multiplexing unit that is configured to divide the image data read from RAM A 412 into appropriate groups of data for each of the computational units 604.
  • Data grouper 612 provides each of the computational units 604 with image data y s for one central pixel, as well as the class identifiers for the six surrounding pixels to enable the computational unit 604 to perform the MPM calculations. Once the computational units 604 have complete a single iteration of the MPM calculation, the computational units write the calculated class identifiers for each pixel to the destination RAM, seen here as RAM B 416. As seen above, RAM A 412 and RAM B 416alternate once all of the image data have been processed for a single iteration. RAM B 412 is also shown as operatively coupled to the data grouper 612 during operations where RAM B provides source data for the MPM calculations.
  • the controller 404 and process 500 calculate the class identifier k corresponding to the lowest cost for each pixel in the image data using parallelism and improved memory handling.
  • the plurality of control units 604 enable the controller 404 to calculate an iteration for multiple central pixels in parallel. Since the intermediate results for each iteration are held in the internal RAM A and RAM B during processing, the controller 404 only needs to access the slower external RAM to read in image data and to store the calculated class identifiers for each pixel. Thus, the controller 404 reads only one copy of the image data instead of reading the same image data multiple times during the iterative process.
  • the stored intermediate results enable the computational units 604 to perform iterative calculations in a pipelined manner that leads to efficient utilization of the computational units.
  • the intermediate results used in the iterations of the MPM calculations are retained in the internal RAM A and RAM B that provide fast access to the computational units 604.
  • the internal memory arrangement reduces the amount of time that the computational units spend waiting to receiving input data, and improves the utilization of the computational units and the performance of the MPM calculations.
  • the foregoing embodiments provide a faster and more efficient system for segmenting three- dimensional image data that benefits various fields that analyze the image data.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Probability & Statistics with Applications (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Processing (AREA)

Abstract

Dans un mode de réalisation, un système permettant de calculer des identificateurs de classes pour des données de pixels tridimensionnelles a été conçu. Le système comprend une pluralité de processeurs d'identification de classes, et un dispositif de groupage de données connecté de manière opérationnelle à une première mémoire. Chaque processeur d'identification de classe comprend une pluralité d'entrées pour au moins une valeur de pixel et une pluralité d'identificateurs de classes pour des valeurs de pixels avoisinant la ou les valeurs de pixels et chaque processeur d'identification de classe est configuré pour générer un identificateur de classe pour la ou les valeurs de pixels entrées avec référence aux identificateurs de classes pour les valeurs de pixels avoisinantes. Le dispositif de groupage de données est configuré pour récupérer une pluralité de valeurs de pixels à partir de la première mémoire et une pluralité d'identificateurs de classes pour les valeurs de pixels avoisinant les valeurs de pixels récupérées.
PCT/US2010/059955 2009-12-10 2010-12-10 Système et procédé de segmentation de données d'images tridimensionnelles Ceased WO2011072259A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US13/514,768 US8897544B2 (en) 2009-12-10 2010-12-10 System and method for segmentation of three-dimensional image data

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US28542909P 2009-12-10 2009-12-10
US61/285,429 2009-12-10

Publications (1)

Publication Number Publication Date
WO2011072259A1 true WO2011072259A1 (fr) 2011-06-16

Family

ID=44145946

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2010/059955 Ceased WO2011072259A1 (fr) 2009-12-10 2010-12-10 Système et procédé de segmentation de données d'images tridimensionnelles

Country Status (2)

Country Link
US (1) US8897544B2 (fr)
WO (1) WO2011072259A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112016592A (zh) * 2020-08-04 2020-12-01 杰创智能科技股份有限公司 基于交叉领域类别感知的领域适应语义分割方法及装置

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013040673A1 (fr) * 2011-09-19 2013-03-28 The University Of British Columbia Procédé et systèmes de segmentation d'image 3d interactive
US10241707B2 (en) 2013-05-23 2019-03-26 Intel Corporation Techniques for organizing three-dimensional array data
US10567635B2 (en) 2014-05-15 2020-02-18 Indiana University Research And Technology Corporation Three dimensional moving pictures with a single imager and microfluidic lens
US10043104B2 (en) 2015-01-05 2018-08-07 Avigilon Fortress Corporation Automatic moving object verification
JP7065038B2 (ja) 2016-02-08 2022-05-11 イマーゴ・システムズ，インコーポレーテッド 画像中の物体の視覚化および特徴づけのためのシステムおよび方法
US12175587B2 (en) * 2021-03-29 2024-12-24 Samsung Electronics Co., Ltd. Apparatus and method with graphics processing

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020028021A1 (en) * 1999-03-11 2002-03-07 Jonathan T. Foote Methods and apparatuses for video segmentation, classification, and retrieval using image class statistical models
US20040022438A1 (en) * 2002-08-02 2004-02-05 Hibbard Lyndon S. Method and apparatus for image segmentation using Jensen-Shannon divergence and Jensen-Renyi divergence
US7035467B2 (en) * 2002-01-09 2006-04-25 Eastman Kodak Company Method and system for processing images for themed imaging services
US20060202038A1 (en) * 2005-03-11 2006-09-14 Ynjiun Wang System and method to automatically focus an image reader
US20070206008A1 (en) * 2000-02-25 2007-09-06 The Research Foundation Of The State University Of New York Apparatus and Method for Real-Time Volume Processing and Universal Three-Dimensional Rendering
US20090276384A1 (en) * 2002-03-28 2009-11-05 Cole Coryell Harris Methods and Devices Relating to Estimating Classifier Performance
US20090274377A1 (en) * 2005-11-11 2009-11-05 Japan Advanced Institute Of Science And Technology Clustering System and Image Processing System Having the Same

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5859891A (en) * 1997-03-07 1999-01-12 Hibbard; Lyn Autosegmentation/autocontouring system and method for use with three-dimensional radiation therapy treatment planning
WO1998059213A1 (fr) * 1997-06-25 1998-12-30 Matsushita Electric Works, Ltd. Procede et dispositif de controle de motifs
US6185336B1 (en) * 1998-09-23 2001-02-06 Xerox Corporation Method and system for classifying a halftone pixel based on noise injected halftone frequency estimation
US7113185B2 (en) * 2002-11-14 2006-09-26 Microsoft Corporation System and method for automatically learning flexible sprites in video layers
US7653229B2 (en) * 2003-12-23 2010-01-26 General Electric Company Methods and apparatus for reconstruction of volume data from projection data
JP4556554B2 (ja) * 2004-08-25 2010-10-06 セイコーエプソン株式会社 画像処理を並列処理で実行する際の負荷の割り付け
US20080292194A1 (en) * 2005-04-27 2008-11-27 Mark Schmidt Method and System for Automatic Detection and Segmentation of Tumors and Associated Edema (Swelling) in Magnetic Resonance (Mri) Images
FR2886433B1 (fr) * 2005-05-30 2007-09-07 Commissariat Energie Atomique Methode de segmentation d'une sequence d'images tridimensionnelles, notamment en pharmaco-imagerie.
US7706610B2 (en) * 2005-11-29 2010-04-27 Microsoft Corporation Segmentation of objects by minimizing global-local variational energy

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020028021A1 (en) * 1999-03-11 2002-03-07 Jonathan T. Foote Methods and apparatuses for video segmentation, classification, and retrieval using image class statistical models
US20070206008A1 (en) * 2000-02-25 2007-09-06 The Research Foundation Of The State University Of New York Apparatus and Method for Real-Time Volume Processing and Universal Three-Dimensional Rendering
US7035467B2 (en) * 2002-01-09 2006-04-25 Eastman Kodak Company Method and system for processing images for themed imaging services
US20090276384A1 (en) * 2002-03-28 2009-11-05 Cole Coryell Harris Methods and Devices Relating to Estimating Classifier Performance
US20040022438A1 (en) * 2002-08-02 2004-02-05 Hibbard Lyndon S. Method and apparatus for image segmentation using Jensen-Shannon divergence and Jensen-Renyi divergence
US20060202038A1 (en) * 2005-03-11 2006-09-14 Ynjiun Wang System and method to automatically focus an image reader
US20090274377A1 (en) * 2005-11-11 2009-11-05 Japan Advanced Institute Of Science And Technology Clustering System and Image Processing System Having the Same

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112016592A (zh) * 2020-08-04 2020-12-01 杰创智能科技股份有限公司 基于交叉领域类别感知的领域适应语义分割方法及装置
CN112016592B (zh) * 2020-08-04 2024-01-26 杰创智能科技股份有限公司 基于交叉领域类别感知的领域适应语义分割方法及装置

Also Published As

Publication number Publication date
US20120243777A1 (en) 2012-09-27
US8897544B2 (en) 2014-11-25

Similar Documents

Publication Publication Date Title
You et al. GPU-accelerated Faster Mean Shift with euclidean distance metrics
US11816045B2 (en) Exploiting input data sparsity in neural network compute units
US8897544B2 (en) System and method for segmentation of three-dimensional image data
US9886377B2 (en) Pipelined convolutional operations for processing clusters
Catanzaro et al. Efficient, high-quality image contour detection
KR102838881B1 (ko) 팽창 컨볼루션 계산 가속화 방법 및 장치
US11995552B2 (en) Apparatus and method for multi-phase pruning for neural network with multi-sparsity levels
US20220083857A1 (en) Convolutional neural network operation method and device
US11544213B2 (en) Neural processor
US12361571B2 (en) Method and apparatus with convolution neural network processing using shared operand
JP2015197702A (ja) 情報処理装置、情報処理方法
US9058541B2 (en) Object detection method, object detector and object detection computer program
CN110837483B (zh) 张量维度变换的方法以及装置
US20210192315A1 (en) Method and apparatus with neural network convolution operation
CN112712457A (zh) 数据处理方法以及人工智能处理器
US12014505B2 (en) Method and apparatus with convolution neural network processing using shared operand
Chen et al. Flexible hardware architecture of hierarchical K-means clustering for large cluster number
CN116543161A (zh) 语义分割方法、装置、计算机设备和存储介质
Ali et al. GPU-based segmentation of dental x-ray images using active contours without edges
Song et al. SRender: Boosting Neural Radiance Field Efficiency via Sensitivity-Aware Dynamic Precision Rendering
Raina et al. An energy-scalable accelerator for blind image deblurring
CN112906728A (zh) 一种特征比对方法、装置及设备
Ruiz de Miras Fast differential box-counting algorithm on GPU
Lo et al. A high-performance architecture for training Viola-Jones object detectors
Li et al. A hardware architecture of feature extraction for real-time visual SLAM

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 10836778

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 13514768

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 10836778

Country of ref document: EP

Kind code of ref document: A1