WO2020173052A1 - 图像三维测量方法、电子设备、存储介质及程序产品 - Google Patents

图像三维测量方法、电子设备、存储介质及程序产品 Download PDF

Info

Publication number
WO2020173052A1
WO2020173052A1 PCT/CN2019/100738 CN2019100738W WO2020173052A1 WO 2020173052 A1 WO2020173052 A1 WO 2020173052A1 CN 2019100738 W CN2019100738 W CN 2019100738W WO 2020173052 A1 WO2020173052 A1 WO 2020173052A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
dimensional
dimensional image
medical images
measurement method
Prior art date
Application number
PCT/CN2019/100738
Other languages
English (en)
French (fr)
Inventor
李·戴维伟
李·斯图尔特平
Original Assignee
未艾医疗技术(深圳)有限公司
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 未艾医疗技术(深圳)有限公司 filed Critical 未艾医疗技术(深圳)有限公司
Priority to US17/433,240 priority Critical patent/US20220148222A1/en
Priority to EP19916823.8A priority patent/EP3933846A4/en
Priority to AU2019432052A priority patent/AU2019432052B2/en
Publication of WO2020173052A1 publication Critical patent/WO2020173052A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/003—Reconstruction from projections, e.g. tomography
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/003—Reconstruction from projections, e.g. tomography
    • G06T11/005—Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering
    • G06T15/005—General purpose rendering architectures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing

Definitions

  • the present invention relates to the field of medical imaging, in particular to image three-dimensional measurement methods, electronic equipment, storage media and program products.
  • VRDS refers to head-mounted displays (Set) used to present virtual reality (VR).
  • the 3D stereo vision of VRDS medical imaging is a comprehensive science involving mathematics, computer graphics, pattern recognition, digital image processing and digital signal processing.
  • the visual research goal of VRDS medical imaging is to make the VRDS system have the ability to recognize three-dimensional environmental information through two-dimensional images of medical Dicom volume data. Since the research results of medical imaging vision can be directly applied in the medical field to measure Dicom (Medical Digital Imaging and Communication) volume data, volume data recognition, virtual reality and other operations, the research on the three-dimensional visual digital image processing of medical images has been Become the hottest topic in the world today.
  • Dicom Medical Digital Imaging and Communication
  • the purpose of the present invention is to provide an image three-dimensional measurement method, electronic equipment, storage medium, and program product, so as to solve the problem that the prior art cannot achieve accurate measurement of three-dimensional medical images.
  • a three-dimensional image measurement method based on VRDS medical images which includes the following steps:
  • the three-dimensional image is projected onto the two-dimensional image, and the size of the target area is calculated according to the mapping relationship between the three-dimensional space point and the two-dimensional image point.
  • the three-dimensional image is projected onto the two-dimensional image by using a pinhole imaging model.
  • the three-dimensional image measurement method based on VRDS medical images wherein the three-dimensional image is projected onto the two-dimensional image, and the size of the target area is calculated according to the mapping relationship between the three-dimensional space point and the two-dimensional image point
  • the steps include:
  • the three-dimensional image measurement method based on VRDS medical images, wherein the three-dimensional image is projected onto the two-dimensional image, and the size of the target area is calculated according to the mapping relationship between the three-dimensional space point and the two-dimensional image point
  • the specific steps include:
  • the feature extraction is a feature extraction method based on contour lines or based on image gray values.
  • the image matching is an image matching method based on image gray information or image features.
  • the calibration adopts a calibration method based on an active vision system or a self-calibration method.
  • An electronic device which includes:
  • a processor suitable for implementing instructions
  • the storage device is adapted to store multiple instructions, and the instructions are adapted to be loaded and executed by the processor:
  • the three-dimensional image is projected onto the two-dimensional image, and the size of the target area is calculated according to the mapping relationship between the three-dimensional space point and the two-dimensional image point.
  • a non-volatile computer-readable storage medium wherein the non-volatile computer-readable storage medium stores computer-executable instructions that, when executed by one or more processors, can cause all The one or more processors execute the three-dimensional image measurement method based on VRDS medical images.
  • a computer program product wherein the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, and the computer program includes program instructions.
  • the program instructions When the program instructions are executed by a processor, the processor executes all The described three-dimensional image measurement method based on VRDS medical images.
  • the present invention realizes real-time measurement of three-dimensional images by extracting image feature information, image matching, calibration, reconstruction, and measurement. It has the characteristics of high accuracy, good stability, and non-contact measurement. It is a kind of automation A high degree of practical measurement method.
  • FIG. 1 is a schematic flowchart of a preferred embodiment of the image three-dimensional measurement method of the present invention.
  • Figures 2 to 4 are effect diagrams of the measurement method of the present invention during actual measurement.
  • Fig. 5 is a structural block diagram of a preferred embodiment of an electronic device of the present invention.
  • the present invention provides an image three-dimensional measurement method, electronic equipment, storage medium and program product.
  • the present invention provides an image three-dimensional measurement method, electronic equipment, storage medium and program product.
  • FIG. 1 is a schematic flowchart of a preferred embodiment of an image three-dimensional measurement method based on VRDS medical images of the present invention, which includes the steps:
  • the scanning device is preferably a CT (Computerized Tomography)/MRI (Nuclear Magnetic Resonance) scanning device.
  • CT Computerized Tomography
  • MRI Magnetic Resonance
  • DTI diffusion tensor imaging
  • PET-CT positron emission computed tomography
  • the feature extraction is performed to obtain the image features on which the matching is performed.
  • the image features obtained through feature extraction have distinguishability, invariance, stability, and the ability to effectively resolve ambiguity matching.
  • the image features used in the 3D measurement method of VRDS 4D medical images include feature points, feature lines, and feature regions.
  • feature points usually refer to points with sharp changes in gray level, including the intersection of straight lines, the point (corner or inflection point) with the largest curvature change on the contour of the object, and the isolated point on a monotonous background.
  • the characteristic line mainly refers to the curve and edge line segment of the image.
  • the edge in the image reflects the discontinuity of the change of the object structure, and this discontinuity contains rich information about the structure of the object.
  • the characteristic area is the area enclosed by characteristic lines.
  • the feature extraction in the present invention is a feature extraction method based on image gray values or contour lines.
  • the method first defines an operator, and extracts feature points by finding the extreme value of the operator on the grayscale image.
  • This operator can not only detect edges, but also Detect corners, and there are fewer parameters that need to be set manually, and the accuracy and robustness are very good.
  • the edge is first extracted from the image, and then the point of maximum curvature is searched on the chain of edges, or the edge is approximated by a polygon, and then the vertices of the polygon are calculated as feature points.
  • the present invention preferably introduces a multi-scale framework. A variety of functions are used to approximate the contour curve. The part where the curvature changes the most on the B-spline function is extracted from the contour line. These straight lines are grouped according to certain rules, and the intersection of the straight lines in each group is the feature point.
  • Image matching is the most important problem in computer binocular vision. According to different matching features and methods, the image matching is an image matching method based on image features or image gray information.
  • this matching method greatly reduces the amount of calculation in the matching process; at the same time, the matching metric value of the feature points is more sensitive to changes in position. Greatly improve the accuracy of matching; moreover, the feature point extraction process can reduce the influence of noise, so that the matching has better adaptability to grayscale changes, image deformation and occlusion.
  • image gray information is generally divided into gray information and gray statistical information.
  • the correlation operation is mainly performed on the gray values in the spatial domain of the two images, and the matching position is calculated according to the peak value of the correlation coefficient.
  • the methods used can be normalized cross-correlation, statistical correlation, average absolute difference, average square difference; frequency domain correlation based on FFT frequency domain, including phase correlation and power spectrum correlation; and invariant moment matching, amplitude sorting correlation algorithms, FFT related algorithms and sequence judgment algorithms for hierarchical search, etc.
  • Calibration is an essential step in the field of computer vision to obtain three-dimensional Euclidean information from two-dimensional images, because when the CT/MRI scanning equipment is not calibrated, the Euclidean information of the three-dimensional structure cannot be obtained, so only projective reconstruction can be achieved
  • the quality of the calibration result of CT scanning equipment directly determines the quality of the 3D reconstruction result.
  • There is a one-to-one correspondence between the three-dimensional space points and the image points in the image, and their positional relationship is determined by the imaging geometric model of the CT/MRI scanning equipment.
  • the parameters of the geometric model are called the parameters in the CT/MRI scanning equipment.
  • the calibration adopts a calibration method based on an active vision system or a self-calibration method.
  • traditional calibration methods can also be used.
  • the traditional calibration method uses the corresponding constraint relationship between a standard reference object and its image to determine the parameters of the CT/MRI scanning equipment, that is, placing an object of known shape and size in front of the CT/MRI scanning equipment, called the calibration object .
  • the CT/MRI scanning device obtains the image of the calibration object, and calculates the internal parameters of the camera (that is, the camera of the CT/MRI scanning device, the same below).
  • traditional calibration methods for CT/MRI scanning equipment can be divided into four categories: calibration methods using optimization algorithms, calibration methods using CT/MRI scanning equipment transformation matrix, two-step distortion compensation method, and CT /Biplane calibration method for imaging model of MRI scanning equipment.
  • the advantage of this traditional calibration method is that higher accuracy can be obtained.
  • the calibration method based on the active vision system it is to obtain multiple images by controlling the motion of the CT/MRI scanning equipment to calibrate the internal parameters of the camera.
  • the calibration method based on the active vision system is also a method that only uses the corresponding relationship between images for calibration, and does not require high-precision calibration objects. Because some motion information of CT/MRI scanning equipment is acquired during the calibration process, generally speaking, the internal parameters of CT/MRI scanning equipment can be solved linearly, and the calculation is simple and robust.
  • self-calibration method overcomes the shortcomings of the traditional method and the calibration method based on the active vision system. It does not require calibration objects or strict restrictions on the motion of the CT/MRI scanning equipment. It only relies on the geometry between the corresponding points of the multi-view The relationship is directly calibrated.
  • self-calibration methods mainly include self-calibration to directly solve the melting equation, layered stepwise calibration, self-calibration based on absolute quadric surface, modular constraint calibration, and layered stepwise calibration under variable internal parameters.
  • the self-calibration method is based on the absolute conic or dual absolute conic method.
  • the quasi-affine reconstruction is obtained from the constraint that all points on the image must be in front of the CT/MRI scanning equipment, and then this is used as the initial value
  • the calibration is obtained by minimizing the difference between the internal parameters of the CT/MRI scanning device and the internal parameters obtained by the CT/MRI scanning device projective matrix decomposition.
  • three-dimensional reconstruction is performed on the medical image according to the internal parameters of the scanning device to obtain a three-dimensional image.
  • the three-dimensional reconstruction is to restore the three-dimensional information of the object.
  • CT Dicom volume data can be performed, so the measurement method can also be referred to as a CT scanning measurement method.
  • the three-dimensional measurement system of VRDS medical imaging simulates the imaging geometry of the human eye to project a three-dimensional scene onto a two-dimensional image.
  • the three-dimensional measurement model of VRDS medical imaging describes the mapping relationship between 3D space points and 2D image points.
  • the most specific and simple camera model is the pinhole imaging model
  • projective geometry is the natural mathematical framework for describing this pinhole imaging model.
  • projective space both 3D space points and 2D image points can be represented by homogeneous coordinates.
  • the imaging principle from three-dimensional space to two-dimensional images and the pairing between two images can be described. Polar geometric relations and the calculation of three-dimensional object shapes reconstructed from images.
  • world coordinate system three-dimensional image coordinate system
  • VRDS4D medical imaging camera coordinate system three-dimensional image coordinate system
  • the world coordinate system Since the CT/MRI scanning equipment can be placed in any position in the hospital environment, the present invention selects the world coordinate system as the reference coordinate system to describe the position of the human body scanning in the CT/MRI scanning equipment environment. It is the world coordinate system, and the scale unit belongs to the physical unit.
  • Three-dimensional image coordinate system The images collected by CT/MRI scanning equipment are in the form of two-dimensional arrays. In order to be able to measure the coordinate points after three-dimensional imaging, define each of the M rows and N columns of the three-dimensional image in the three-dimensional image The element is a pixel, and its value is the brightness of the three-dimensional image point.
  • VRDS 4D medical imaging defines a three-dimensional rectangular coordinate system (u, v), which is called the number of columns and rows of the three-dimensional image in the array.
  • the coordinate system is based on a certain point in the human body three-dimensional image.
  • the x-axis and y-axis will be parallel to the u and v axes, respectively.
  • VRDS 4D medical image coordinate system In order to obtain the geometric relationship between the 2D and 3D imaging scanned by the CT/MRI scanning equipment, a medical image coordinate system is defined.
  • the x-axis and y-axis should be aligned with the x-axis and the three-dimensional image coordinate system.
  • the y-axis is parallel
  • z is the optical axis of the CT/MRI scanning device and is perpendicular to the plane of the center point of the 3D image.
  • the intersection of the optical axis and the 3D image plane is the origin of the VRDS4D medical image coordinate system.
  • the three-dimensional measurement of VRDS 4D medical images uses a pinhole imaging model to project the three-dimensional image onto the two-dimensional image.
  • the pinhole imaging model is simple and practical without losing accuracy.
  • the projection center of the 3D measurement of VRDS 4D medical images is called the CT/MRI scanning equipment center, also called the optical center.
  • the perpendicular line from the center of the CT/MRI scanning device to the image plane is called the main axis of the CT/MRI scanning device, and the intersection of the main axis and the two-dimensional image plane is called the principal point.
  • the method further includes:
  • the step of projecting the three-dimensional image onto the two-dimensional image and calculating the size of the target area according to the mapping relationship between the three-dimensional space point and the two-dimensional image point specifically includes:
  • the ratio of the above plane to the actual length is the actual physical scale of the plane.
  • the final measurement results are shown in Figure 2 to Figure 4.
  • the three-dimensional measurement of the VRDS 4D medical image of the present invention is mainly a measurement method that uses the image as a means of detecting and transmitting information. By extracting feature information of the image, etc., the actual information of the measured object is finally obtained from the image.
  • the VRDS 4D medical image three-dimensional measurement method of the present invention has strong adaptability in accuracy, speed, intelligence, etc., and has the characteristics of high accuracy, good stability, non-contact measurement, etc., combined with image processing technology, constitutes automation A practical measurement system with a higher degree.
  • the VRDS 4D medical image of the present invention realizes three-dimensional measurement in 3D and 4D real-time dynamic environments.
  • the three-dimensional measurement of VRDS 4D medical images can test the abnormal phenomena of the inner wall of the blood vessel, the inner diameter of the blood vessel, and the outer wall of the blood vessel.
  • the three-dimensional measurement of VRDS 4D medical images can perform three-dimensional measurement of the tumor in a real-time dynamic environment.
  • the three-dimensional measurement of VRDS 4D medical images can perform three-dimensional measurement in a real-time dynamic environment of the lesion organ and the remaining tissue after tumor resection.
  • the 3D measurement of the VRDS 4D medical image of the present invention can also perform 3D measurement of other targets in a real-time dynamic environment.
  • the present invention also provides an electronic device 10, as shown in FIG. 5, which includes:
  • the processor 110 is adapted to implement various instructions, and
  • the storage device 120 is adapted to store multiple instructions, and the instructions are adapted to be loaded and executed by the processor 110:
  • the three-dimensional image is projected onto the two-dimensional image, and the size of the target area is calculated according to the mapping relationship between the three-dimensional space point and the two-dimensional image point.
  • the processor 110 may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, Discrete gate or transistor logic, discrete hardware components, or any combination of these components.
  • the processor may also be any conventional processor, microprocessor or state machine.
  • the processor may also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP core, any other such configuration.
  • the storage device 120 can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the VRDS-based medical image in the embodiment of the present invention Program instructions corresponding to 3D measurement methods.
  • the processor executes various functional applications and data processing of the image three-dimensional measurement method based on VRDS medical images by running non-volatile software programs, instructions, and units stored in the storage device, thereby realizing the foregoing method embodiments.
  • the present invention also provides a non-volatile computer-readable storage medium that stores computer-executable instructions.
  • the computer-executable instructions are executed by one or more processors, they can The one or more processors are caused to execute the three-dimensional image measurement method based on VRDS medical images.
  • the present invention also provides a computer program product.
  • the computer program product includes a computer program stored on a non-volatile computer-readable storage medium.
  • the computer program includes program instructions. When the program instructions are executed by a processor, the processor Implement the three-dimensional image measurement method based on VRDS medical images.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Quality & Reliability (AREA)
  • Computer Graphics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Geometry (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)
  • Image Processing (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)

Abstract

本发明公开图像三维测量方法、电子设备、存储介质及程序产品，其中，所述图像三维测量方法包括步骤：对扫描设备所扫描的医学图像进行特征提取；对特征提取后的医学图像进行图像匹配；对扫描设备进行标定，以确定扫描设备的内参数；根据所述扫描设备的内参数对医学图像进行三维重构获得三维图像；将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸。本发明通过提取图像的特征信息、图像匹配、标定、重构以及测量等，实现对三维图像的实时测量，具有精度高、稳定性好、非接触性测量等特点，是一种自动化程度较高的实用测量方法。

Description

图像三维测量方法、电子设备、存储介质及程序产品 技术领域
本发明涉及医学影像领域，尤其涉及图像三维测量方法、电子设备、存储介质及程序产品。
背景技术你
“VRDS”一词是指用于呈现虚拟现实(VR)的头盔式显示器(Head-mounted Displays Set)。VRDS医学影像的三维立体视觉是一门综合性科学，涉及到数学、计算机图形学、模式识别、数字图像处理和数字信号处理等。VRDS医学影像的视觉研究目标：是使VRDS系统具有通过医学Dicom体数据的二维图像认知三维环境信息的能力。由于医学影像的视觉的研究成果可以直接应用在医学领域中对Dicom(医学数字成像和通信)体数据进行测量、体数据识别、虚拟现实等操作，所以医学影像的三维视觉数字图像处理的研究已成为当今世界最热门的话题。
现有技术中，二维的医学图像虽能测量出病灶等目标区域的尺寸，但是对于三维的医学图像，则无法实现准确的测量功能。
因此，现有技术还有待于改进和发展。
发明内容
鉴于上述现有技术的不足，本发明的目的在于提供图像三维测量方法、电子设备、存储介质及程序产品，旨在解决现有技术无法实现对三维的医学图像进行准确的测量的问题。
本发明的技术方案如下：
一种基于VRDS医学影像的图像三维测量方法，其中，包括步骤：
对扫描设备所扫描的医学图像进行特征提取；
对特征提取后的医学图像进行图像匹配；
对扫描设备进行标定，以确定扫描设备的内参数；
根据所述扫描设备的内参数对医学图像进行三维重构获得三维图像；
将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸。
所述的基于VRDS医学影像的图像三维测量方法，其中，利用针孔成像模型将所述三维图像投影到二维图像上。
所述的基于VRDS医学影像的图像三维测量方法，其中，所述将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸的步骤之后还包括：
当接收到对所述三维图像的缩放指令时，对所述三维图像进行缩放，并且保持所计算出的尺寸大小。
所述的基于VRDS医学影像的图像三维测量方法，其中，所述将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸的步骤具体包括：
将目标区域的两个测量点投影到平面上得到相应的投影点；
计算平面上的两个投影点之间的测量长度；
根据所述测量长度与平面在实际长度的比例，得到两个投影点的实际长度；以及计算测量点与相应投影点之间的实际长度；
最后计算出目标区域的尺寸。
所述的基于VRDS医学影像的图像三维测量方法，其中，所述特征提取为基于轮廓线或基于图像灰度值的特征提取方法。
所述的基于VRDS医学影像的图像三维测量方法，其中，所述图像匹配为基于图像灰度信息或基于图像特征的图像匹配方法。
所述的基于VRDS医学影像的图像三维测量方法，其中，所述标定采 用基于主动视觉系统的标定方法或自标定方法。
一种电子设备，其中，包括：
处理器，适于实现各指令，以及
存储设备，适于存储多条指令，所述指令适于由处理器加载并执行：
对扫描设备所扫描的医学图像进行特征提取；
对特征提取后的医学图像进行图像匹配；
对扫描设备进行标定，以确定扫描设备的内参数；
根据所述扫描设备的内参数对医学图像进行三维重构获得三维图像；
将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸。
一种非易失性计算机可读存储介质，其中，所述非易失性计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行时，可使得所述一个或多个处理器执行所述的基于VRDS医学影像的图像三维测量方法。
一种计算机程序产品，其中，计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，计算机程序包括程序指令，当程序指令被处理器执行时，使所述处理器执行所述的基于VRDS医学影像的图像三维测量方法。
有益效果：本发明通过提取图像的特征信息、图像匹配、标定、重构以及测量等，实现对三维图像的实时测量，具有精度高、稳定性好、非接触性测量等特点，是一种自动化程度较高的实用测量方法。
附图说明
图1为本发明图像三维测量方法较佳实施例的流程示意图。
图2-图4为本发明的测量方法在实际测量时的效果图。
图5为本发明电子设备较佳实施例的结构框图。
具体实施方式
本发明提供图像三维测量方法、电子设备、存储介质及程序产品，为使本发明的目的、技术方案及效果更加清楚、明确，以下对本发明进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
请参阅图1，图1为本发明一种基于VRDS医学影像的图像三维测量方法较佳实施例的流程示意图，其包括步骤：
S1、对扫描设备所扫描的医学图像进行特征提取；
S2、对特征提取后的医学图像进行图像匹配；
S3、对扫描设备进行标定，以确定扫描设备的内参数；
S4、根据所述扫描设备的内参数对医学图像进行三维重构获得三维图像；
S5、将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸。
需说明的是，上述步骤的序号仅为方便说明，并不代表各步骤的执行顺序，根据情况和需求的不同，可以对步骤执行顺序做稍许调整，都应属于本发明的保护范围。
首先，对扫描设备所扫描的医学图像进行特征提取。
所述扫描设备优选为CT(电子计算机断层扫描)/MRI(核磁共振)扫描设备。当然还可以是DTI(弥散张量成像)或PET-CT(正电子发射型计算机断层显像)扫描设备。
本步骤S1中，进行特征提取是为了得到匹配赖以进行的图像特征，通过特征提取得到的图像特征具有可区分性、不变性、稳定性以及有效解决歧义匹配的能力。
在VRDS 4D医学影像的三维测量方法中所使用的图像特征有特征点、 特征线和特征区域等。其中，特征点通常是指灰度变化剧烈的点，包括直线的交点、物体轮廓上的曲率变化最大点(角点或拐点)、单调背景上的孤点等。特征线主要是指图像的曲线、边缘线段等，图像中的边缘反映了物体结构变化的不连续性，这种不连续性蕴含了有关物体结构的丰富信息。特征区域则是由特征线围成的区域。
进一步，本发明中的特征提取为基于图像灰度值或基于轮廓线的特征提取方法。
其中，对于基于图像灰度值的特征提取方法，该方法首先定义算子，通过在灰度化图像上寻找该算子的极值来提取特征点，这种算子不仅能检测边缘，也能检测角点，而且，需要人为设定的参数比较少，精确性和鲁棒性都很好。
其中，对于基于轮廓线的特征提取方法，首先从图像中提取边缘，再在边缘组成的链上搜索曲率最大点，或者将该边缘用多边形来逼近，再计算出多边形的各顶点作为特征点，从边缘轮廓线中提取特征点，为了得到鲁棒的结果，本发明优选引入了一个多尺度框架。利用多样条函数来逼进轮廓曲线，B样条函数上曲率变化最大的地方从轮廓线中提取出直线部分，这些直线以一定的规则被分组，而每组中直线的交点即为特征点。
图像匹配是计算机双眼视觉中最重要的问题。根据匹配特征和方式的不同，所述图像匹配为基于基于图像特征或图像灰度信息的图像匹配方法。
对于基于图像特征的匹配，由于图像的特征点比像素点要少的多，所以这种匹配方法大大减少了匹配过程的计算量；同时，特征点的匹配度量值对位置的变化比较敏感，可以大大提高匹配的精确度；而且，特征点的提取过程可以减少噪声的影响，使匹配对灰度变化、图像形变以及遮挡等都有较好的适应能力。
对于基于图像灰度信息的匹配，图像灰度信息一般分为灰度信息和灰度统计信息。本发明中，在VRDS在图像匹配算法中，主要是对两幅图像 空间域上的灰度值进行相关运算，根据相关系数的峰值，求出匹配位置。采用的方法可以是归一化互相关、统计相关、平均绝对差、平均平方差；基于FFT频率域的频域相关，包括相位相关和功率谱相关；以及不变矩匹配、幅度排序相关算法、FFT相关算法和分层搜索的序列判断算法等。
标定是计算机视觉领域中从二维图像获取三维欧氏信息必不可少的关键一步，因为在CT/MRI扫描设备未标定的情形下，无法得到三维结构的欧氏信息，从而只能实现射影重构，CT扫描设备标定结果的好坏直接决定着三维重构结果的好坏。三维空间点与其图像中的像点之间存在着一一对应的关系，它们的位置关系由CT/MRI扫描设备成像几何模型所决定。该几何模型的参数称为CT/MRI扫描设备内参数。
进一步，所述标定采用基于主动视觉系统的标定方法或自标定方法。除上述两种标定方法指纹，还可采用传统标定方法。
对于传统标定方法，其是利用一个标准参照物与其图像的对应约束关系来确定CT/MRI扫描设备内参数，即在CT/MRI扫描设备前放置一个己知形状和尺寸的物体，称为标定物，CT/MRI扫描设备获取该标定物的图像，并由此计算摄像机(即指CT/MRI扫描设备的摄像机，下同)的内参数。从计算思路的角度上看，传统的CT/MRI扫描设备标定方法可以分成四类：利用最优化算法的标定方法、利用CT/MRI扫描设备变换矩阵的标定方法、畸变补偿的两步法和CT/MRI扫描设备成像模型的双平面标定方法。这种传统的标定方法的优点在于可以获得较高的精度。
对于基于主动视觉系统的标定方法，其是通过控制CT/MRI扫描设备的运动获取多幅图像来标定摄像机内参数。与自标定方法一样，基于主动视觉系统的标定方法也是一种仅利用图像之间对应关系进行标定的方法，不需要高精度的标定物。由于在标定过程中获取了一些CT/MRI扫描设备的运动信息，所以一般来说，CT/MRI扫描设备的内参数可以线性求解，计算简单、鲁棒性比较好。
对于自标定方法，其克服了传统方法和基于主动视觉系统的标定方法的缺点，它不需要标定物也不需要对CT/MRI扫描设备运动作严格限制，仅仅依靠多视图对应点之间的几何关系直接进行标定。目前自标定方法主要有直接求解融方程的自标定、分层逐步标定、基于绝对二次曲面的自标定、的模约束标定以及可变内参数下的分层逐步标定等。
自标定方法是基于绝对二次曲线或者对偶绝对二次曲面的方法，由图像上的所有点都必须在CT/MRI扫描设备的前方这一约束获得准仿射重构，然后以此作为初值，通过最小化试图求解的CT/MRI扫描设备内参数和由CT/MRI扫描设备射影矩阵分解得到的内参数之间的差来获得标定。
然后根据所述扫描设备的内参数对医学图像进行三维重构获得三维图像。其中的三维重构，即恢复物体的三维信息。
最后在从图像得到景物的三维结构后，就可以根据实际的需要进行相关的应用。本发明中，可进行CT Dicom体数据的三维重建和测量，所以测量方法也可称为CT扫描测量法。
VRDS医学影像的三维测量系统模拟人眼成像几何把三维场景投影到二维图像上，VRDS医学影像的三维测量模型，描述的是3D空间点与2D图像点之间的映射关系。最具体、最简单的摄像机模型是针孔成像模型，而射影几何是描述这种针孔成像模型的自然数学框架。在射影空间中，3D空间点与2D图像点都可以用齐次坐标来表示，借助射影几何、矩眸等数学工具，可以描述三维空间到二维图像的成像原理、两幅图像之间的对极几何关系以及由图像重构三维空间物体形状的计算等。
首先定义几种不同类型的坐标系：世界坐标系、三维图像坐标系、VRDS4D医学影像摄像机坐标系。
其中，世界坐标系:由于CT/MRI扫描设备可以放在医院环境中的任何位置，所以，本发明选择世界坐标系作为基准坐标系，来描述CT/MRI扫描设备环境中人体扫描的位置，称为世界坐标系，刻度单位属于物理单位。
三维图像坐标系：CT/MRI扫描设备采集到的图像是以二维数组的形式存在的，为了能够测量到三维成像后的坐标点，定义三维图像的M行N列在三维图像中的每一个元素为像素，其数值为三维图像点的亮度。VRDS 4D医学影像中定义了三维直角坐标系(u，v)，其称为三维图像在数组中的列数和行数。VRDS 4D医学影像创建的物理单位(如毫米)表示的三维图像坐标系，该坐标系以人体三维图像内某一点为基础原点，x轴和y轴将分别与u和v轴平行。
VRDS 4D医学影像坐标系：为了获取CT/MRI扫描设备扫描后的2D与三维成像的几何关系，定义一个医学影像坐标系，x轴和y轴分别要与三维图像的坐标系中的x轴和y轴平行，z为CT/MRI扫描设备的光轴，并与三维图像中心点平面垂直，光轴与三维图像平面的交点，为VRDS4D医学影像坐标系的原点。
进一步，VRDS 4D医学影像的三维测量利用针孔成像模型将所述三维图像投影到二维图像上。针孔成像模型简单实用而不失准确性。在VRDS 4D医学影像的三维测量中，三维图像中的空间坐标为x＝(x,y,z)t的点x被映射到二维图像平面的点x，它是连接点x和投影中心c的直线与图像平面的交点。VRDS 4D医学影像的三维测量的投影中心称为CT/MRI扫描设备中心，也称为光心。CT/MRI扫描设备中心到图像平面的垂线称为CT/MRI扫描设备的主轴，而主轴与二维图像平面的交点称为主点。
进一步，所述将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸的步骤之后还包括：
当接收到对所述三维图像的缩放指令时，对所述三维图像进行缩放，并且保持所计算出的尺寸大小。
在VRDS 4D医学影像的三维测量中，当缩放比例改变时，所测量的目标区域的尺寸不改变，目标区域的尺寸记录的是物体的原始尺寸。也就是说，利用VRDS 4D医学影像进行实时动态环境下的三维测量时，即使进行 缩放和移动等操作，三维测量得到的真实尺寸也不会发生变化。
进一步，所述将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸的步骤具体包括：
将目标区域的两个测量点投影到平面上得到相应的投影点；
计算平面上的两个投影点之间的测量长度；
根据所述测量长度与平面在实际长度的比例，得到两个投影点的实际长度；以及计算测量点与相应投影点之间的实际长度；
最后计算出目标区域的尺寸。
上述平面在实际长度的比例也就是平面的实际物理刻度。
举例来说，假设A1和A2两点为三维图像中的待测量的点
1.将三维图像中待测量的两个点A1和A2投影到二维图像的平面上得到相应的投影点V1和V2，通过V1在二维图像的平面的坐标(X1,Y1)和V2在平面(X2,Y2)的坐标计算出V1和V2之间的测量长度；
2.再将V1和V2之间的长度与平面在实际长度中的比例进行计算，得出V1和V2之间的实际长度；
3.计算A1和V1之间的测量长度，以及A2和V2之间的测量长度；
4.通过直角三角形的勾股定理得出A1和A2两点之间的测量长度。
最终测量的效果如图2至图4所示。本发明VRDS 4D医学影像的三维测量主要是把图像当作检测和传递信息的手段而加以利用的测量方法，通过提取图像的特征信息等，最终从图像中获取被测对象的实际信息。本发明的VRDS 4D医学影像的三维测量方法在精度、速度、智能化等方面具有很强的适应性，并具有精度高、稳定性好、非接触性测量等特点，结合图像处理技术，构成自动化程度较高的实用测量系统。
本发明的VRDS 4D医学影像在3D及4D的实时动态的环境下实现了三维测量。并且VRDS 4D医学影像的三维测量可以对血管内壁、血管内径、血管外壁的异常现象进行测试。同时，VRDS 4D医学影像的三维测量可以 对病灶肿瘤进行实时动态环境下的三维测量。另外，VRDS 4D医学影像的三维测量可以对病灶器官、肿瘤切除后的剩余组织进行实时动态环境下的三维测量。
另外，根据需要，本发明的VRDS 4D医学影像的三维测量还可以对其他目标进行实时动态环境下的三维测量。
本发明还提供一种电子设备10，如图5所示，其包括：
处理器110，适于实现各指令，以及
存储设备120，适于存储多条指令，所述指令适于由处理器110加载并执行：
对扫描设备所扫描的医学图像进行特征提取；
对特征提取后的医学图像进行图像匹配；
对扫描设备进行标定，以确定扫描设备的内参数；
根据所述扫描设备的内参数对医学图像进行三维重构获得三维图像；
将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸。
所述处理器110可以为通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)、单片机、ARM(Acorn RISC Machine)或其它可编程逻辑器件、分立门或晶体管逻辑、分立的硬件组件或者这些部件的任何组合。还有，处理器还可以是任何传统处理器、微处理器或状态机。处理器也可以被实现为计算设备的组合，例如，DSP和微处理器的组合、多个微处理器、一个或多个微处理器结合DSP核、任何其它这种配置。
存储设备120作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本发明实施例中的基于VRDS医学影像的图像三维测量方法对应的程序指令。处理器通过运行存储在存储设备中的非易失性软件程序、指令以及单元，从而执行 基于VRDS医学影像的图像三维测量方法的各种功能应用以及数据处理，即实现上述方法实施例。
关于上述电子设备10的具体技术细节在前面的方法中已有详述，故不再赘述。
本发明还提供一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行时，可使得所述一个或多个处理器执行所述的基于VRDS医学影像的图像三维测量方法。
本发明还提供一种计算机程序产品，计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，计算机程序包括程序指令，当程序指令被处理器执行时，使所述处理器执行所述的基于VRDS医学影像的图像三维测量方法。
应当理解的是，本发明的应用不限于上述的举例，对本领域普通技术人员来说，可以根据上述说明加以改进或变换，所有这些改进和变换都应属于本发明所附权利要求的保护范围。

Claims (10)

  1. 一种基于VRDS医学影像的图像三维测量方法，其特征在于，包括步骤：
    对扫描设备所扫描的医学图像进行特征提取；
    对特征提取后的医学图像进行图像匹配；
    对扫描设备进行标定，以确定扫描设备的内参数；
    根据所述扫描设备的内参数对医学图像进行三维重构获得三维图像；
    将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸。
  2. 根据权利要求1所述的基于VRDS医学影像的图像三维测量方法，其特征在于，利用针孔成像模型将所述三维图像投影到二维图像上。
  3. 根据权利要求1所述的基于VRDS医学影像的图像三维测量方法，其特征在于，所述将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸的步骤之后还包括：
    当接收到对所述三维图像的缩放指令时，对所述三维图像进行缩放，并且保持所计算出的尺寸大小。
  4. 根据权利要求1所述的基于VRDS医学影像的图像三维测量方法，其特征在于，所述将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸的步骤具体包括：
    将目标区域的两个测量点投影到平面上得到相应的投影点；
    计算平面上的两个投影点之间的测量长度；
    根据所述测量长度与平面在实际长度的比例，得到两个投影点的实际长度；以及计算测量点与相应投影点之间的实际长度；
    最后计算出目标区域的尺寸。
  5. 根据权利要求1所述的基于VRDS医学影像的图像三维测量方法，其特征在于，所述特征提取为基于轮廓线或基于图像灰度值的特征提取方 法。
  6. 根据权利要求1所述的基于VRDS医学影像的图像三维测量方法，其特征在于，所述图像匹配为基于图像灰度信息或基于图像特征的图像匹配方法。
  7. 根据权利要求1所述的基于VRDS医学影像的图像三维测量方法，其特征在于，所述标定采用基于主动视觉系统的标定方法或自标定方法。
  8. 一种电子设备，其特征在于，包括：
    处理器，适于实现各指令，以及
    存储设备，适于存储多条指令，所述指令适于由处理器加载并执行：
    对扫描设备所扫描的医学图像进行特征提取；
    对特征提取后的医学图像进行图像匹配；
    对扫描设备进行标定，以确定扫描设备的内参数；
    根据所述扫描设备的内参数对医学图像进行三维重构获得三维图像；
    将所述三维图像投影到二维图像上，根据三维空间点与二维图像点之间的映射关系计算出目标区域的尺寸。
  9. 一种非易失性计算机可读存储介质，其特征在于，所述非易失性计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行时，可使得所述一个或多个处理器执行权利要求1-7任一项所述的基于VRDS医学影像的图像三维测量方法。
  10. 一种计算机程序产品，其特征在于，计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，计算机程序包括程序指令，当程序指令被处理器执行时，使所述处理器执行权利要求1-7任一项所述的基于VRDS医学影像的图像三维测量方法。
PCT/CN2019/100738 2019-02-28 2019-08-15 图像三维测量方法、电子设备、存储介质及程序产品 WO2020173052A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/433,240 US20220148222A1 (en) 2019-02-28 2019-08-15 Image three-dimensional measurement method, electronic device, storage medium and program product
EP19916823.8A EP3933846A4 (en) 2019-02-28 2019-08-15 THREE-DIMENSIONAL IMAGE MEASUREMENT METHOD, ELECTRONIC DEVICE, STORAGE MEDIUM AND PROGRAM PRODUCT
AU2019432052A AU2019432052B2 (en) 2019-02-28 2019-08-15 Three-dimensional image measurement method, electronic device, storage medium, and program product

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910151898.5A CN109949899B (zh) 2019-02-28 2019-02-28 图像三维测量方法、电子设备、存储介质及程序产品
CN201910151898.5 2019-02-28

Publications (1)

Publication Number Publication Date
WO2020173052A1 true WO2020173052A1 (zh) 2020-09-03

Family

ID=67006525

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/100738 WO2020173052A1 (zh) 2019-02-28 2019-08-15 图像三维测量方法、电子设备、存储介质及程序产品

Country Status (5)

Country Link
US (1) US20220148222A1 (zh)
EP (1) EP3933846A4 (zh)
CN (1) CN109949899B (zh)
AU (1) AU2019432052B2 (zh)
WO (1) WO2020173052A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112907727A (zh) * 2021-01-25 2021-06-04 中国科学院空天信息创新研究院 相对变换矩阵的标定方法、装置及系统
CN113140022A (zh) * 2020-12-25 2021-07-20 杭州今奥信息科技股份有限公司 数字测图方法、系统及计算机可读存储介质
CN114863017A (zh) * 2022-04-27 2022-08-05 青岛海信医疗设备股份有限公司 一种数据处理方法、设备及装置

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109949899B (zh) * 2019-02-28 2021-05-28 未艾医疗技术(深圳)有限公司 图像三维测量方法、电子设备、存储介质及程序产品
WO2021030995A1 (zh) * 2019-08-16 2021-02-25 未艾医疗技术(深圳)有限公司 基于vrds ai下腔静脉影像的分析方法及产品
CN112489105B (zh) * 2019-08-24 2024-03-15 北京地平线机器人技术研发有限公司 一种结构化参数表示获取方法及装置
WO2021081772A1 (zh) * 2019-10-29 2021-05-06 未艾医疗技术(深圳)有限公司 基于vrds ai脑部影像的分析方法和相关装置
WO2021081771A1 (zh) * 2019-10-29 2021-05-06 未艾医疗技术(深圳)有限公司 基于vrds ai医学影像的心脏冠脉的分析方法和相关装置
WO2021081841A1 (zh) * 2019-10-30 2021-05-06 未艾医疗技术(深圳)有限公司 基于vrds 4d医学影像的脾脏肿瘤识别方法及相关装置
WO2021081846A1 (zh) * 2019-10-30 2021-05-06 未艾医疗技术(深圳)有限公司 静脉血管肿瘤影像处理方法及相关产品
WO2021081842A1 (zh) * 2019-10-30 2021-05-06 未艾医疗技术(深圳)有限公司 基于vrds ai医学影像的肠肿瘤与血管分析方法和相关装置
CN114341996A (zh) * 2019-10-30 2022-04-12 未艾医疗技术(深圳)有限公司 基于vrds 4d的病情分析方法及相关产品
WO2021081836A1 (zh) * 2019-10-30 2021-05-06 未艾医疗技术(深圳)有限公司 基于vrds 4d医学影像的胃肿瘤识别方法及相关产品
CN113344611B (zh) * 2021-05-19 2023-04-18 天津旗滨节能玻璃有限公司 成本确定方法、智能设备和存储介质
CN113470003A (zh) * 2021-07-22 2021-10-01 北京爱康宜诚医疗器材有限公司 工具的确定方法、装置、计算机可读存储介质及处理器
CN114708230B (zh) * 2022-04-07 2022-12-16 深圳市精明检测设备有限公司 基于图像分析的车架质量检测方法、装置、设备及介质
CN114862850B (zh) * 2022-07-06 2022-09-20 深圳科亚医疗科技有限公司 一种血管医学图像的目标检测方法、装置及介质
CN115289974B (zh) * 2022-10-09 2023-01-31 思看科技(杭州)股份有限公司 孔位测量方法、装置、计算机设备和存储介质
CN116592776B (zh) * 2023-07-19 2023-12-01 浙江视觉智能创新中心有限公司 一种基于三维点云的管径尺寸检测方法、装置及电子设备
CN116758205B (zh) * 2023-08-24 2024-01-26 先临三维科技股份有限公司 数据处理方法、装置、设备及介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150332498A1 (en) * 2014-05-14 2015-11-19 Nuctech Company Limited Image display methods
CN105894574A (zh) * 2016-03-30 2016-08-24 清华大学深圳研究生院 一种双目三维重建方法
CN106447764A (zh) * 2016-09-08 2017-02-22 福州大学 一种三维可视化的人体骨盆参数自动测量方法
CN108742519A (zh) * 2018-04-02 2018-11-06 上海中医药大学附属岳阳中西医结合医院 机器视觉三维重建技术皮肤溃疡创面智能辅助诊断系统
CN109949899A (zh) * 2019-02-28 2019-06-28 未艾医疗技术(深圳)有限公司 图像三维测量方法、电子设备、存储介质及程序产品

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1259093A3 (de) * 2001-05-16 2005-12-14 ELMEG Communication Systems GmbH Netzabschlussgerät für ein Telefonnetz
CN101371786B (zh) * 2007-08-24 2011-01-12 北京师范大学珠海分校 一种x射线图像三维重构的方法及系统
CN101271469B (zh) * 2008-05-10 2013-08-21 深圳先进技术研究院 一种基于三维模型库下二维图像的识别和物体的重建方法
CN101639947A (zh) * 2009-08-26 2010-02-03 北京农业信息技术研究中心 基于图像的植物三维形态测量与重建方法及系统
CN201983758U (zh) * 2011-01-25 2011-09-21 余韵致 基于小孔成像原理的三维物体空间测量装置
JP5950619B2 (ja) * 2011-04-06 2016-07-13 キヤノン株式会社 情報処理装置
TWI439854B (zh) * 2011-11-25 2014-06-01 Inventec Corp 開機錯誤處理方法
US10360673B2 (en) * 2015-03-26 2019-07-23 Eyekor, Llc Image analysis
CN105678746B (zh) * 2015-12-30 2018-04-03 上海联影医疗科技有限公司 一种医学图像中肝脏范围的定位方法及装置
CN107907048A (zh) * 2017-06-30 2018-04-13 长沙湘计海盾科技有限公司 一种基于线结构光扫描的双目立体视觉三维测量方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150332498A1 (en) * 2014-05-14 2015-11-19 Nuctech Company Limited Image display methods
CN105894574A (zh) * 2016-03-30 2016-08-24 清华大学深圳研究生院 一种双目三维重建方法
CN106447764A (zh) * 2016-09-08 2017-02-22 福州大学 一种三维可视化的人体骨盆参数自动测量方法
CN108742519A (zh) * 2018-04-02 2018-11-06 上海中医药大学附属岳阳中西医结合医院 机器视觉三维重建技术皮肤溃疡创面智能辅助诊断系统
CN109949899A (zh) * 2019-02-28 2019-06-28 未艾医疗技术(深圳)有限公司 图像三维测量方法、电子设备、存储介质及程序产品

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3933846A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113140022A (zh) * 2020-12-25 2021-07-20 杭州今奥信息科技股份有限公司 数字测图方法、系统及计算机可读存储介质
CN112907727A (zh) * 2021-01-25 2021-06-04 中国科学院空天信息创新研究院 相对变换矩阵的标定方法、装置及系统
CN112907727B (zh) * 2021-01-25 2023-09-01 中国科学院空天信息创新研究院 相对变换矩阵的标定方法、装置及系统
CN114863017A (zh) * 2022-04-27 2022-08-05 青岛海信医疗设备股份有限公司 一种数据处理方法、设备及装置

Also Published As

Publication number Publication date
EP3933846A1 (en) 2022-01-05
AU2019432052A1 (en) 2021-09-16
CN109949899B (zh) 2021-05-28
AU2019432052B2 (en) 2023-06-01
CN109949899A (zh) 2019-06-28
EP3933846A4 (en) 2022-11-09
US20220148222A1 (en) 2022-05-12

Similar Documents

Publication Publication Date Title
WO2020173052A1 (zh) 图像三维测量方法、电子设备、存储介质及程序产品
Keller et al. Real-time 3d reconstruction in dynamic scenes using point-based fusion
Wang et al. Conformal geometry and its applications on 3D shape matching, recognition, and stitching
JP4785880B2 (ja) 三次元オブジェクト認識のためのシステムおよび方法
CN108052942B (zh) 一种飞机飞行姿态的视觉图像识别方法
Yuan et al. 3D point cloud matching based on principal component analysis and iterative closest point algorithm
WO2019050417A1 (en) METHOD FOR CALIBRATING STEREOSCOPIC SYSTEM
CN109544606B (zh) 基于多个Kinect的快速自动配准方法及系统
CN102980513B (zh) 以物为中心的单目全景立体视觉传感器
CN116129037B (zh) 视触觉传感器及其三维重建方法、系统、设备及存储介质
CN116309880A (zh) 基于三维重建的物体位姿确定方法、装置、设备及介质
CN113362446B (zh) 基于点云数据重建对象的方法及装置
CN106500625A (zh) 一种远心立体视觉测量装置及其应用于物体三维形貌微米级精度测量的方法
Fan et al. Convex hull aided registration method (CHARM)
CN101996415B (zh) 眼球的三维建模方法
Lim et al. Camera-based hand tracking using a mirror-based multi-view setup
Li et al. A vision-based navigation system with markerless image registration and position-sensing localization for oral and maxillofacial surgery
CN108629840A (zh) 一种建立logo三维轮廓的方法、装置和设备
CN111915666A (zh) 基于移动终端的体积测量方法及装置
CN115131442A (zh) 一种标定方法及装置、计算机可读存储介质
Balzer et al. Volumetric reconstruction applied to perceptual studies of size and weight
Villa-Uriol et al. Automatic creation of three-dimensional avatars
CN113689397A (zh) 工件圆孔特征检测方法和工件圆孔特征检测装置
Xu et al. Fast 3d-object modeling with kinect and rotation platform
CN111462199A (zh) 基于gpu的快速散斑图像匹配方法

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: 19916823

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019432052

Country of ref document: AU

Date of ref document: 20190815

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2019916823

Country of ref document: EP

Effective date: 20210928