WO2023097913A1 - 体积测量方法和装置、计算机可读存储介质 - Google Patents

体积测量方法和装置、计算机可读存储介质 Download PDF

Info

Publication number
WO2023097913A1
WO2023097913A1 PCT/CN2022/078895 CN2022078895W WO2023097913A1 WO 2023097913 A1 WO2023097913 A1 WO 2023097913A1 CN 2022078895 W CN2022078895 W CN 2022078895W WO 2023097913 A1 WO2023097913 A1 WO 2023097913A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
point cloud
measured
reference plane
plane
Prior art date
Application number
PCT/CN2022/078895
Other languages
English (en)
French (fr)
Inventor
严斌龙
朱红军
刘长有
牛堃
周鹏
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2023097913A1 publication Critical patent/WO2023097913A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • G06T7/62Analysis of geometric attributes of area, perimeter, diameter or volume
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10028Range image; Depth image; 3D point clouds

Definitions

  • the present application relates to the technical field of computer vision, in particular to a volume measurement method and device, and a computer-readable storage medium.
  • volume detection targets such as conventional logistics package detection, generally requiring the package to be a rectangular parallelepiped with standard length, width and height. This method of volume measurement is not suitable for non-standard objects. In practical engineering applications, irregular objects are more common, and volume detection is more difficult.
  • Embodiments of the present application provide a volume measurement method, a volume measurement device, electronic equipment, and a computer-readable storage medium.
  • the embodiment of the present application provides a volume measurement method, the method comprising: acquiring the first original point cloud of the target to be measured; segmenting the first original point cloud to obtain the first target point cloud and the second A reference plane point cloud; fitting the first reference plane point cloud to obtain a first target reference plane; according to the first target reference plane, determine the relative position of each point in the first target point cloud relative to the target Measure the relative height of the background plane of the target; determine the number of voxels of the target to be measured according to the relative heights of all points; volume.
  • the embodiment of the present application provides a volume measurement device, the device includes: a measurement module, configured to obtain the first original point cloud of the target to be measured; a segmentation module, configured to obtain the first original point cloud The cloud is segmented to obtain the first target point cloud and the first reference plane point cloud; the fitting module is configured to fit the first reference plane point cloud to obtain the first target reference plane; the first processing module is set In order to determine the relative height of each point in the first target point cloud relative to the background plane of the target to be measured according to the first target reference plane; the second processing module is set to be based on the relative height of all points , determining the number of voxels of the target to be measured; the third processing module is configured to obtain the volume of the target to be measured according to the pre-calibrated voxel equivalent and the number of voxels of the target to be measured.
  • the embodiment of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and operable on the processor.
  • the processor executes the computer program, the above-mentioned
  • a volume measurement method When the processor executes the computer program, the above-mentioned
  • an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the volume measurement method provided in the first aspect above is realized.
  • Fig. 1 is a schematic flow chart of a volume measurement method provided in an embodiment of the present application
  • Fig. 2 is a schematic flow chart of a volume measurement method provided by an embodiment of the present application.
  • Fig. 3 is a schematic flow chart of a volume measurement method provided by an embodiment of the present application.
  • Fig. 4 is a schematic diagram of a spatial coordinate system provided by an embodiment of the present application.
  • Fig. 5 is a schematic diagram of the XOZ plane projection of the first target point cloud provided by the embodiment of the present application (omitting the internal point cloud);
  • FIG. 6 is a schematic diagram of the XOZ plane projection of the first target point cloud provided by the embodiment of the present application (omitting the internal point cloud);
  • Fig. 7 is a schematic structural diagram of a volume measuring device provided in an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • At least one of the following and similar expressions refer to any group of these items, including any group of single or plural items.
  • at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or, a and b and c, where a, b, c can be a single , or more than one.
  • Embodiments of the present application provide a volume measurement method, a volume measurement device, an electronic device, and a computer-readable storage medium, capable of accurately measuring the volume of a three-dimensional irregular object.
  • Fig. 1 is a schematic flow chart of a volume measurement method provided by an embodiment of the present application.
  • the volume measurement method provided by the embodiment of the present application includes the following steps:
  • Step S110 acquiring the first original point cloud of the target to be measured.
  • the object to be measured can be a regular three-dimensional or irregular three-dimensional, and the first original point cloud of the object to be measured can be captured by a 3D camera.
  • the information format of point cloud data is (x, y, z, B, G, R), wherein (x, y, z) represents three-dimensional space coordinate information; (B, G, R) represents the BGR color model information, B is the blue channel value (Blue), G is the green channel value (Green), and R is the red channel value (Red).
  • B, G, R represents the BGR color model information
  • B is the blue channel value (Blue)
  • G is the green channel value (Green)
  • R red channel value (Red).
  • BGR color model information (B, G, R) in the information format may be converted into channel values corresponding to other color models.
  • the BGR color model information (B, G, R) is converted into YUV color model information (Y, U, V), where Y represents brightness (Luminance or Luma), that is, the grayscale value, U and V means chroma (Chrominance or Chroma).
  • BGR color model information (B, G, R) is converted into HSV color model information (H, S, V), where H represents hue (Hue), S represents saturation (Saturation), and V represents lightness (Value).
  • Step S120 segment the first original point cloud to obtain a first target point cloud and a first reference plane point cloud.
  • the first target point cloud is a second target point cloud
  • the first target reference plane point cloud is a second target reference plane point cloud
  • the first original point cloud is segmented to obtain The first target point cloud and the first reference plane point cloud, including:
  • Segmenting the first original point cloud according to the spatial coordinate information to obtain an area point cloud including the target to be measured and a surrounding area of the target to be measured;
  • the region point cloud is segmented according to the color space model to obtain a second target point cloud and a second reference plane point cloud
  • the second target point cloud is the point cloud data of the target to be measured
  • the second reference point cloud is
  • the plane point cloud is the point cloud data of the background plane of the target to be measured.
  • the point cloud data of the point cloud data and the point cloud data of the background plane of the target to be measured, that is, the second target point cloud and the second reference plane point cloud are extracted.
  • the regional point cloud including the target to be measured and the surrounding area of the target to be measured can be initially segmented according to the spatial coordinate information, and then the regional point cloud is segmented according to the color model to obtain The second target point cloud and the second reference plane point cloud are used to reduce the calculation amount when segmenting the point cloud data according to the color model.
  • color space models include BGR color model, YUV color model, HSV color model and so on.
  • the point cloud data of the first original point cloud is expressed as (x, y, z, B, G, R), by setting the thresholds of the blue channel, the green channel and the red channel value to distinguish the point cloud data of the target to be measured and the background plane.
  • the point cloud data of the first original point cloud is expressed as (x, y, z, Y, U, V), and the threshold value of brightness and chroma is set to distinguish Point cloud data of the target and background planes to be measured.
  • the point cloud data of the first original point cloud is expressed as (x, y, z, H, S, V), by setting the threshold value of hue, saturation and lightness, with Distinguish the point cloud data of the target to be measured and the background plane.
  • the first target point cloud is a third target point cloud
  • the first target reference plane point cloud is a third target reference plane point cloud
  • the first original point cloud is segmented to obtain The first target point cloud and the first reference plane point cloud, including:
  • the point cloud data of the third reference plane, the plane where the point cloud is located is parallel to the background plane of the target to be measured.
  • the first original point cloud is segmented according to the difference of parameters in the spatial coordinate information, and the third target point cloud and the third reference plane point cloud are extracted.
  • the third target point cloud is the point cloud data of the target to be measured and the surrounding area of the target to be measured; the plane where the point cloud of the third reference plane is located is parallel to the background plane of the target to be measured.
  • Step S130 fitting the point cloud of the first reference plane to obtain a first target reference plane.
  • FIG. 5 is a schematic diagram of the XOZ plane projection of the first target point cloud provided by the embodiment of the present application (omitting the internal point cloud), and the first reference plane point cloud is the background of the target to be measured.
  • FIG. 6 is a schematic diagram of the XOZ plane projection of the first target point cloud provided by the embodiment of the present application (omitting the internal point cloud), the plane where the first reference plane point cloud is located and the plane of the target to be measured
  • the background plane is parallel, and by fitting the first reference plane, a first target reference plane parallel to the background plane of the target to be measured is obtained.
  • Step S140 according to the first target reference plane, determine the relative height of each point in the first target point cloud relative to the background plane of the target to be measured.
  • For each point in the first target point cloud refer to the first target reference plane, and calculate the height of each point relative to the background plane of the target to be measured.
  • step S140 in a volume measurement method provided in the embodiment of the present application includes:
  • the Z-direction projection point A'(xi , y i , axi + by i + c), according to the coordinate information of the projected point A', determine the relative height H of the point A, that is, determine the height H of the point A relative to the background plane of the target to be measured, H ax i +by i +cz i .
  • step S140 in a volume measurement method provided in the embodiment of the present application includes:
  • the Z-direction projection point and the parallel spacing determine the relative height of each point in the first target point cloud with respect to the background plane of the target to be measured.
  • Step S150 according to the relative heights of all points, determine the number of voxels of the target to be measured.
  • a voxel that is, a volume pixel
  • a volume pixel is the smallest unit of digital data in three-dimensional space division, and is a pixel in a 3D space.
  • the relative heights of all points in the point cloud of the first target are accumulated to obtain the number of voxels of the target to be measured.
  • step S160 the volume of the target to be measured is obtained according to the pre-calibrated voxel equivalent and the number of voxels of the target to be measured.
  • the voxel equivalent V e represents the actual volume represented by 1 unit voxel in real space, and the unit is cubic centimeter or cubic millimeter.
  • the micro-element volume i.e. voxel equivalent
  • the divided micro-element number i.e. voxel sum
  • Step 210 Obtain a second original point cloud of a calibration block of known volume.
  • Step 220 Segment the second original point cloud to obtain a fourth target point cloud and a fourth reference plane point cloud.
  • Step 230 Fitting the point cloud of the fourth reference plane to obtain a fourth target reference plane.
  • Step 240 According to the fourth target reference plane, calculate the relative height of each point in the fourth target point cloud relative to the background plane of the calibration block.
  • Step 250 Determine the voxel number of the calibration block according to the relative heights of all points.
  • Step 260 Obtain the voxel equivalent according to the voxel number and volume of the calibration block.
  • the same working conditions refer to the same working conditions as when acquiring the first original point cloud of the target to be measured, wherein the working conditions include the electronic device that captures the point cloud and the relative position of the electronic device to the target to be measured, etc. .
  • the voxel equivalent described in the embodiment of the present application can also be obtained in the following manner:
  • Step S310 Obtain a two-dimensional image of a calibration ruler of known length.
  • Step S320 Obtain the pixel equivalent according to the length of the two-dimensional image and the calibration ruler;
  • Step S330 Obtain the voxel equivalent according to the pre-calibrated Z-axis equivalent and the pixel equivalent.
  • the factory parameters of the electronic device that captures the third original point cloud including its Z-axis equivalent K, are acquired.
  • the same working conditions refer to the same working conditions as when acquiring the first original point cloud of the target to be measured, wherein the working conditions include the electronic device that captures the point cloud and the relative position of the electronic device to the target to be measured, etc. .
  • volume measurement method provided in the embodiment of the present application is described below through specific examples.
  • the volume of the object to be measured is measured according to the volume measurement method provided in the embodiment of the present application, and the specific process is as follows:
  • the volume of the object to be measured is measured, and the specific process is as follows:
  • the original point cloud of the target to be measured by obtaining the original point cloud of the target to be measured, the original point cloud is segmented to obtain the first target point cloud and the first reference plane point cloud including the target to be measured, and the first reference plane point cloud is fitted to obtain the second point cloud.
  • a target reference plane according to the first target reference plane, determine the relative height of each point in the first target point cloud relative to the background plane of the target to be measured, and then obtain the number of voxels of the target to be measured, according to the pre-calibrated voxel equivalent and the voxel number of the target to be measured to obtain the volume of the target to be measured.
  • the embodiment of the present application can accurately measure the volume of the object in the case of irregular stereo through the pre-calibrated voxel equivalent and the voxel number of the object to be measured.
  • FIG. 7 is a volume measuring device 100 provided in an embodiment of the present application. As shown in Figure 7, the volume measuring device 100 includes:
  • the measurement module 110 is configured to acquire the first original point cloud of the target to be measured
  • the segmentation module 120 is configured to segment the first original point cloud to obtain a first target point cloud and a first reference plane point cloud;
  • the fitting module 130 is configured to fit the first reference plane point cloud to obtain a first target reference plane
  • the first processing module 140 is configured to determine the relative height of each point in the first target point cloud relative to the background plane of the target to be measured according to the first target reference plane;
  • the second processing module 150 is configured to determine the number of voxels of the target to be measured according to the relative heights of all points;
  • the third processing module 160 is configured to obtain the volume of the target to be measured according to the pre-calibrated voxel equivalent and the number of voxels of the target to be measured.
  • FIG. 8 shows an electronic device 200 provided by an embodiment of the present application. As shown in FIG. 8, the electronic device 200 includes but is not limited to:
  • memory 210 configured to store programs
  • the processor 220 is configured to execute the program stored in the memory 210, and when the processor 220 executes the program stored in the memory 210, the processor 220 is configured to execute the above volume measurement method.
  • the processor 220 and the memory 210 may be connected through a bus or in other ways.
  • the memory 210 can be configured to store non-transitory software programs and non-transitory computer-executable programs, such as the volume measurement method described in any embodiment of the present application.
  • the processor 220 executes the non-transitory software programs and instructions stored in the memory 210 to implement the volume measurement method described above.
  • the memory 210 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store and execute the volume measurement method described above.
  • the memory 210 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices.
  • the memory 210 may include memory located remotely relative to the processor 220, and these remote memories may be connected to the processor 220 through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the non-transitory software programs and instructions required to implement the above volume measurement method are stored in the memory 210, and when executed by one or more processors 220, the volume measurement method provided by any embodiment of the present application is executed.
  • the embodiment of the present application also provides a storage medium storing computer-executable instructions, and the computer-executable instructions are configured to execute the above-mentioned volume measurement method.
  • the storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more control processors, for example, executed by one or more processors in the above-mentioned electronic device, so that the above-mentioned One or more processors execute the volume measurement method provided by any embodiment of the present application.
  • the original point cloud of the target to be measured by obtaining the original point cloud of the target to be measured, the original point cloud is segmented to obtain the first target point cloud and the first reference plane point cloud including the target to be measured, and the first reference plane point cloud is fitted to obtain the second point cloud.
  • a target reference plane according to the first target reference plane, determine the relative height of each point in the first target point cloud relative to the background plane of the target to be measured, and then obtain the number of voxels of the target to be measured, according to the pre-calibrated voxel equivalent and the voxel number of the target to be measured to obtain the volume of the target to be measured.
  • the embodiment of the present application can accurately measure the volume of the object in the case of irregular stereo through the pre-calibrated voxel equivalent and the voxel number of the object to be measured.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, tape, magnetic disk storage or other magnetic storage devices, or can Any other medium used to store desired information and which can be accessed by a computer.
  • communication media typically embody computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Image Processing (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

一种体积测量方法、体积测量装置、电子设备和计算机可读存储介质。本申请实施例通过获取待测目标的原始点云(S110),对原始点云进行分割,得到包括待测目标的第一目标点云和第一参考平面点云(S120),拟合第一参考平面点云得到第一目标参考平面(S130),根据第一目标参考平面,得到第一目标点云中每个点相对于所述待测目标的背景平面的相对高度(S140),进而得到待测目标的体素数(S150),根据预先标定的体素当量和待测目标的体素数,得到待测目标的体积(S160)。

Description

体积测量方法和装置、计算机可读存储介质
相关申请的交叉引用
本申请基于申请号为202111470266.9,申请日为2021年12月03日的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及计算机视觉技术领域,特别是涉及一种体积测量方法和装置、计算机可读存储介质。
背景技术
随着现代工业技术、物流产业等的不断发展,各个行业领域为了降低人工负担、提高检测效率和精度,对于自动化视觉检测的需求越来越多,其中就包括对物体体积检测的需求,如物流包裹、PCB板焊锡或导热胶等。
由于物体和环境的多样性,物体体积检测难度较大,并且在多数体积测量方法中,对检测目标有限定要求,如常规的物流包裹检测,一般要求包裹是标准长、宽、高的长方体,这种体积测量方法对于非标准物体并不适用。而实际工程应用中,不规则物体更为常见,体积检测难度更大。
发明内容
本申请实施例提供一种体积测量方法、体积测量装置、电子设备和计算机可读存储介质。
第一方面,本申请实施例提供一种体积测量方法,所述方法包括:获取待测目标的第一原始点云;对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云;拟合所述第一参考平面点云,得到第一目标参考平面;根据所述第一目标参考平面,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度;根据所有点的相对高度,确定所述待测目标的体素数;根据预先标定的体素当量和所述待测目标的体素数,得到所述待测目标的体积。
第二方面,本申请实施例提供一种体积测量装置,所述装置包括:测量模块,被设置为获取待测目标的第一原始点云;分割模块,被设置为对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云;拟合模块,被设置为拟合所述第一参考平面点云,得到第一目标参考平面;第一处理模块,被设置为根据所述第一目标参考平面,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度;第二处理模块,被设置为根据所有点的相对高度,确定所述待测目标的体素数;第三处理模块,被设置为根据预先标定的体素当量和所述待测目标的体素数,得到所述待测目标的体积。
第三方面,本申请实施例提供一种电子设备,包括:存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述计算机程序时,实现如上第一方面提供的体积测量方法。
第四方面,本申请实施例提供一种计算机可读存储介质,存储有计算机程序,所述计算机程序被处理器执行时,实现如上第一方面提供的体积测量方法。
本申请的其它特征和优点将在随后的说明书中阐述,并且,部分地从说明书中变得显而易见,或者通过实施本申请而了解。本申请的目的和其他优点可通过在说明书、权利要求书以及附图中所特别指出的结构来实现和获得。
附图说明
附图用来提供对本申请技术方案的进一步理解,并且构成说明书的一部分,与本申请的实施例一起用于解释本申请的技术方案,并不构成对本申请技术方案的限制。
图1是本申请实施例提供的一种体积测量方法的流程示意图;
图2是本申请实施例提供的一种体积测量方法的流程示意图;
图3是本申请实施例提供的一种体积测量方法的流程示意图;
图4是本申请实施例提供的一种空间坐标系的示意图;
图5是本申请实施例提供的第一目标点云的XOZ面投影的示意图(省略内部点云);
图6是本申请实施例提供的第一目标点云的XOZ面投影的示意图(省略内部点云);
图7是本申请实施例提供的一种体积测量装置的结构示意图;
图8是本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅用以解释本申请,并不用于限定本申请。
应了解,在本申请实施例的描述中,如果有描述到“第一”、“第二”等只是用于区分技术特征为目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量或者隐含指明所指示的技术特征的先后关系。“至少一个”是指一个或者多个,“多个”是指两个或两个以上。“和/或”,描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示单独存在A、同时存在A和B、单独存在B的情况。其中A,B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项”及其类似表达,是指的这些项中的任意组,包括单项或复数项的任意组。例如,a、b和c中的至少一项可以表示:a,b,c,a和b,a和c,b和c,或者,a和b和c,其中a,b,c可以是单个,也可以是多个。
此外,下面所描述的本申请各个实施方式中所涉及到的技术特征只要彼此之间未构成冲突就可以相互组合。
本申请实施例提供了一种体积测量方法、体积测量装置、电子设备和计算机可读存储介质,能够精确测量立体不规则物体的体积。
图1是本申请实施例提供的一种体积测量方法的流程示意图。参见图1,本申请实施例提供的体积测量方法包括以下步骤:
步骤S110,获取待测目标的第一原始点云。
可以理解的是,待测目标可以是规则立体或不规则立体,待测目标的第一原始点云可以 由3D相机所拍取。
参照图4,在一些实施例中,点云数据的信息格式为(x,y,z,B,G,R),其中(x,y,z)表示三维空间坐标信息;(B,G,R)表示BGR颜色模型信息,B为蓝色通道值(Blue),G为绿色通道值(Green),R为红色通道值(Red)。需要说明的是,在上述实施例中,根据实际需求,可以将信息格式中的BGR颜色模型信息(B,G,R),转化为其他颜色模型对应的通道值。
在一示例中,将BGR颜色模型信息(B,G,R)转化为YUV颜色模型信息(Y,U,V),其中Y表示明亮度(Luminance或Luma),也就是灰阶值,U和V表示是色度(Chrominance或Chroma)。
在一示例中,将BGR颜色模型信息(B,G,R)转化为HSV颜色模型信息(H,S,V),其中H表示色调(Hue),S表示饱和度(Saturation),V表示明度(Value)。
应了解,BGR颜色模型与YUV、HSV等颜色模型的转换方式为本领域技术人员所知,在此不再赘述。
步骤S120,对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云。
在一些实施例中,所述第一目标点云为第二目标点云,所述第一目标参考平面点云为第二目标参考平面点云,对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云,包括:
根据空间坐标信息对所述第一原始点云进行分割,得到包括所述待测目标以及所述待测目标周边区域的区域点云;
根据颜色空间模型对所述区域点云进行分割,得到第二目标点云和第二参考平面点云,所述第二目标点云为所述待测目标的点云数据,所述第二参考平面点云为所述待测目标的背景平面的点云数据。
利用空间坐标信息,对第一原始点云进行分割,得到包括带待测目标以及待测目标周边区域的区域点云,再根据颜色空间模型中参数的差异精确分割区域点云,得到待测目标的点云数据和待测目标的背景平面的点云数据,也就是提取第二目标点云和第二参考平面点云。
可以理解的是,在基于颜色模型进行分割之前,可以先根据空间坐标信息,初步分割出包含待测目标以及待测目标周边区域的区域点云,再根据颜色模型对区域点云进行分割,得到第二目标点云和第二参考平面点云,以此减少在根据颜色模型对点云数据进行分割时的计算量。
可以理解的是,颜色空间模型包括BGR颜色模型、YUV颜色模型和HSV颜色模型等。
在一示例中,基于BGR颜色模型,第一原始点云的点云数据表示为(x,y,z,B,G,R),通过设定蓝色通道、绿色通道和红色通道的门限值,以区分待测目标和背景平面的点云数据。
在一示例中,基于YUV颜色模型,第一原始点云的点云数据表示为(x,y,z,Y,U,V),通过设定明亮度和色度的门限值,以区分待测目标和背景平面的点云数据。
在一示例中,基于HSV颜色模型,第一原始点云的点云数据表示为(x,y,z,H,S,V),通过设定色调、饱和度和明度的门限值,以区分待测目标和背景平面的点云数据。
可以理解的是,上述根据三种颜色模型中参数的差异分割第一原始点云,不能理解为对本申请实施例所应用的颜色模型的限制,应用的颜色模型只要能区分待测目标和背景平面的点云数据即可。还需要说明的是,对于上述门限值,可以根据实际应用进行设定,在此不作 限制。
在一些实施例中,所述第一目标点云为第三目标点云,所述第一目标参考平面点云为第三目标参考平面点云,对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云,包括:
根据空间坐标信息对所述第一原始点云进行分割,得到第三目标点云和第三参考平面点云,所述第三目标点云为所述待测目标以及所述待测目标周边区域的点云数据,所述第三参考平面点云所在的平面与所述待测目标的背景平面平行。
根据空间坐标信息中参数的差异分割第一原始点云,提取第三目标点云和第三参考平面点云。第三目标点云为待测目标以及待测目标周边区域的点云数据;第三参考平面点云所在的平面与待测目标的背景平面平行。
步骤S130,拟合所述第一参考平面点云,得到第一目标参考平面。
可以理解的是,对于一个空间平面,其平面方程可以用ax+by+cz+d=0来表示,对于3D结构光采集的点云空间平面,c≠0,其平面方程则可以表示为:z=ax+by+c。
在一示例中,参照图5,图5是本申请实施例提供的第一目标点云的XOZ面投影的示意图(省略内部点云),第一参考平面点云为所述待测目标的背景平面的点云数据,通过拟合第一参考平面,即得到待测目标的背景平面,也就是得到第一目标参考平面,其平面方程可表示为z=ax+by+c。
在一示例中,参照图6,图6是本申请实施例提供的第一目标点云的XOZ面投影的示意图(省略内部点云),第一参考平面点云所在的平面与待测目标的背景平面平行,通过拟合第一参考平面,即得到与待测目标的背景平面平行的第一目标参考平面。
应了解,由离散点拟合平面的方法为本领域技术人员所知,在此不作赘述。
步骤S140,根据所述第一目标参考平面,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度。
对于第一目标点云中每个点,参考第一目标参考平面,计算每个点相对于待测目标的背景平面的高度。
在一些实施例中,本申请实施例提供的一种体积测量方法中的步骤S140包括:
确定所述第一目标点云中每个点在所述第一目标参考平面的Z向投影点;
根据所述Z向投影点,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度。
参照图5,图5是本申请实施例提供的第一目标点云的XOZ面投影的示意图(省略内部点云),如图5所示,第一目标参考平面与空间坐标系的XOY平面平行,第一目标参考平面为待测目标的背景平面,其中,第一目标参考平面的平面方程为z=ax+by+c。
在一示例中,确定第一目标点云中的点A(x i,y i,z i)到第一目标参考平面α的Z向投影点A'(x i,y i,ax i+by i+c),根据投影点A'的坐标信息,确定点A的相对高度H,也就是确定点A相对于待测目标的背景平面的高度H,H=ax i+by i+c-z i
在一些实施例中,本申请实施例提供的一种体积测量方法中的步骤S140包括:
获取所述第一目标参考平面与所述待测目标的背景平面之间的平行间距;
确定所述第一目标点云中每个点在所述第一目标参考平面上的Z向投影点;
根据所述Z向投影点和所述平行间距,确定所述第一目标点云中每个点相对于所述待测 目标的背景平面的相对高度。
参照图6,图6是本申请实施例提供的第一目标点云的XOZ面投影的示意图(省略内部点云),如图6所示,第一目标参考平面与待测目标的背景平面平行,第一目标参考平面的平面法线n与Z轴的夹角为θ,其中,第一目标参考平面的平面方程为z=ax+by+c。
在一示例中,根据第一目标参考平面的平面方程,确定第一目标参考平面与待测目标的背景平面之间的平行间距ΔH,确定第一目标点云中的点B(x i,y i,z i)到第一目标参考平面的Z向投影点B'(x i,y i,ax i+by i+c),根据点B和投影点B'的坐标信息,确定点B到投影点B'的距离:ax i+by i+c-z i,从而根据第一目标参考平面和待测目标的背景平面的平行间距ΔH,确定点B的相对高度H,也就是确定点H相对于待测目标的背景平面的高度H,H=ΔH/cosθ-(ax i+by i+c-z i)。
步骤S150,根据所有点的相对高度,确定所述待测目标的体素数。
应了解,体素,即体积像素,是数字数据于三维空间分割上的最小单位,是3D空间的像素。
累加第一目标点云中所有点的相对高度,得到待测目标的体素数。
步骤S160,根据预先标定的体素当量和所述待测目标的体素数,得到所述待测目标的体积。
应了解,参照图4,体素当量V e表示1单位体素在实际空间中代表的实际体积大小,单位为立方厘米或立方毫米等。
可以理解的是,利用微元积分法的方式,微元体积(即体素当量)为V e,划分的微元数(即体素和)为N,则待测目标的体积V=V e×N。
在一些实施例中,参照图2,本申请实施例所述体素当量通过以下方式得到:
步骤210:获取已知体积的校准块的第二原始点云。
步骤220:对所述第二原始点云进行分割,得到第四目标点云和第四参考平面点云。
步骤230:拟合所述第四参考平面点云,得到第四目标参考平面。
步骤240:根据所述第四目标参考平面,计算所述第四目标点云中每个点相对于所述校准块的背景平面的相对高度。
步骤250:根据所有点的相对高度,确定所述校准块的体素数。
应了解,步骤S210至S250的具体的实现过程可参见前面步骤S110至S150的相关描述,此处不再赘述。
步骤260:根据所述校准块的体素数和体积,得到所述体素当量。
利用已知体积的校准块,计算其体素数,并用体积除以体素数的计算方式得到相同工作条件下的体素当量。应了解,相同工作条件指的是与获取待测目标的第一原始点云时处于相同工作条件,其中,工作条件包括拍取点云的电子设备和该电子设备与待测目标的相对位置等。
在一些实施例中,参照图3,本申请实施例所述体素当量还可以通过以下方式得到:
步骤S310:获取已知长度的校准尺的二维图像。
获取长度为L的校准尺的二维图像。
步骤S320:根据所述二维图像和所述校准尺的长度,得到像素当量;
可以理解的是,通过获取二维图像中校准尺的起始像素点和终止像素点,得到校准尺的 像素值N,计算像素当量L e=L/N。
步骤S330:根据预先标定的Z轴当量和所述像素当量,得到所述体素当量。
可以理解的是,获取拍取第三原始点云的电子设备的出厂参数,包括其Z轴当量K。根据Z轴当量K和像素当量L e,得到相同工作条件下的体素当量V e=K×L e。应了解,相同工作条件指的是与获取待测目标的第一原始点云时处于相同工作条件,其中,工作条件包括拍取点云的电子设备和该电子设备与待测目标的相对位置等。
下面通过具体实施例描述本申请实施例提供的体积测量方法。
在一个具体实施例中,根据本申请实施例提供的体积测量方法对待测目标的体积进行测量,具体过程如下:
获取长度为L的校准尺的二维图像,从二维图像中获取校准尺的像素值N,根据像素值N和校准尺的长度L,得到像素当量L e,L e=L/N。根据拍取设备的出厂参数,包括其Z轴当量K,得到体素当量V e=K×L e
获取待测目标的原始点云,根据BGR颜色模型信息,将原始点云提取分割为目标点云和背景点云。拟合背景点云,得到目标背景平面,其空间平面方程为z=ax+by+c。目标点云中点的坐标为(x i,y i,z i),在目标背景平面的投影为(x i,y i,ax i+by i+c),确定目标点云中每个点相对于目标背景平面的高度H,H=ax i+by i+c-z i,累加每个点的相对高度H得到体素数N,计算待测目标的体积V=V e×N。
在另一个具体实施例中,根据本申请实施例提供的体积测量方法对待测目标的体积进行测量,具体过程如下:
获取体积为V的校准块的原始点云PointCloud00,根据空间坐标信息对原始点云PointCloud00进行分割,得到包含校准块及校准块周边区域的区域点云PointCloud01,通过颜色模型将区域点云分割为目标点云PointCloud03和背景点云PointCloud04,拟合背景点云PointCloud04,得到目标背景平面,其空间平面方程为z=ax+by+c。目标点云PointCloud03中点的坐标为(x i,y i,z i),在目标背景平面的投影为(x i,y i,ax i+by i+c),确定目标点云PointCloud03中每个点相对于目标背景平面的高度H,H=ax i+by i+c-z i,累加每个点的相对高度H得到体素数N,计算体素当量V e=V/N。
获取待测目标的原始点云PointCloud10,根据空间坐标信息,根据空间坐标信息对原始点云PointCloud10进行分割,得到与待测目标的背景平面平行,平行间距为ΔH的参考平面点云PointCloud11,拟合参考平面点云PointCloud11,得到目标参考平面,其空间平面方程为z=a 1x+b 1y+c 1,其平面法线与Z轴的夹角为θ。根据空间坐标信息对原始点云PointCloud10进行分割,得到待测目标以及待测目标周边区域的区域点云PointCloud12,区域点云PointCloud12中点的坐标为(x i,y i,z i),在目标背景平面的投影为(x i,y i,a 1x i+b 1y i+c 1),确定区域点云PointCloud12中每个点相对于目标背景平面的高度H,H=ΔH/cosθ-(a 1x i+b 1y i+c 1-z i),累加每个点的相对高度H得到体素数N,计算待测目标的体积V=V e×N。
需说明的是,在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述或记载的部分,可以参见其它实施例的相关描述。
本申请实施例通过获取待测目标的原始点云,对原始点云进行分割,得到包括待测目标的第一目标点云和第一参考平面点云,拟合第一参考平面点云得到第一目标参考平面,根据 第一目标参考平面,确定第一目标点云中每个点相对于待测目标的背景平面的相对高度,进而得到待测目标的体素数,根据预先标定的体素当量和待测目标的体素数,得到待测目标的体积。本申请实施例通过预先标定的体素当量和待测目标的体素数,能够在立体不规则的情况下精确测量物体体积。
参照图7,图7是本申请实施例提供的一种体积测量装置100。如图7所示,该体积测量装置100包括:
测量模块110,被设置为获取待测目标的第一原始点云;
分割模块120,被设置为对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云;
拟合模块130,被设置为拟合所述第一参考平面点云,得到第一目标参考平面;
第一处理模块140,被设置为根据所述第一目标参考平面,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度;
第二处理模块150,被设置为根据所有点的相对高度,确定所述待测目标的体素数;
第三处理模块160,被设置为根据预先标定的体素当量和所述待测目标的体素数,得到所述待测目标的体积。
需要说明的是,上述模块之间的信息交互、执行过程等内容,由于与本申请方法实施例基于同一构思,其具体功能及带来的技术效果,具体可参见方法实施例部分,此处不再赘述。
图8示出了本申请实施例提供的一种电子设备200。如图8所示,该电子设备200包括但不限于:
存储器210,被设置为存储程序;
处理器220,被设置为执行存储器210存储的程序,当处理器220执行存储器210存储的程序时,处理器220被设置为执行上述的体积测量方法。
处理器220和存储器210可以通过总线或者其他方式连接。
存储器210作为一种非暂态计算机可读存储介质,可被设置为存储非暂态软件程序以及非暂态性计算机可执行程序,如本申请任意实施例描述的体积测量方法。处理器220通过运行存储在存储器210中的非暂态软件程序以及指令,从而实现上述的体积测量方法。
存储器210可以包括存储程序区和存储数据区,其中,存储程序区可存储操作***、至少一个功能所需要的应用程序;存储数据区可存储执行上述的体积测量方法。此外,存储器210可以包括高速随机存取存储器,还可以包括非暂态存储器,比如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施方式中,存储器210可包括相对于处理器220远程设置的存储器,这些远程存储器可以通过网络连接至该处理器220。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
实现上述的体积测量方法所需的非暂态软件程序以及指令存储在存储器210中,当被一个或者多个处理器220执行时,执行本申请任意实施例提供的体积测量方法。
本申请实施例还提供了一种存储介质,存储有计算机可执行指令,计算机可执行指令被设置为执行上述的体积测量方法。
在一实施例中,该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控制处理器执行,比如,被上述电子设备中的一个或多个处理器执行,可使得上述一个或多个处理器执行本申请任意实施例提供的体积测量方法。
本申请实施例通过获取待测目标的原始点云,对原始点云进行分割,得到包括待测目标的第一目标点云和第一参考平面点云,拟合第一参考平面点云得到第一目标参考平面,根据第一目标参考平面,确定第一目标点云中每个点相对于待测目标的背景平面的相对高度,进而得到待测目标的体素数,根据预先标定的体素当量和待测目标的体素数,得到待测目标的体积。本申请实施例通过预先标定的体素当量和待测目标的体素数,能够在立体不规则的情况下精确测量物体体积。
以上所描述的实施例仅仅是示意性的,其中作为分离部件说明的单元可以是或者也可以不是物理上分开的,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
本领域普通技术人员可以理解,上文中所公开方法中的全部或某些步骤、***可以被实施为软件、固件、硬件及其适当的组合。某些物理组件或所有物理组件可以被实施为由处理器,如中央处理器、数字信号处理器或微处理器执行的软件,或者被实施为硬件,或者被实施为集成电路,如专用集成电路。这样的软件可以分布在计算机可读介质上,计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的,术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或其他磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质。此外,本领域普通技术人员公知的是,通信介质通常包括计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据,并且可包括任何信息递送介质。
以上是对本申请的若干实施方式进行了具体说明,但本申请并不局限于上述实施方式,熟悉本领域的技术人员在不违背本申请精神的。共享条件下还可作出种种等同的变形或替换,这些等同的变形或替换均包括在本申请权利要求所限定的范围内。

Claims (10)

  1. 一种体积测量方法,所述方法包括:
    获取待测目标的第一原始点云;
    对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云;
    拟合所述第一参考平面点云,得到第一目标参考平面;
    根据所述第一目标参考平面,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度;
    根据所有点的相对高度,确定所述待测目标的体素数;
    根据预先标定的体素当量和所述待测目标的体素数,得到所述待测目标的体积。
  2. 根据权利要求1所述的方法,其中,所述第一目标点云为第二目标点云,所述第一目标参考平面点云为第二目标参考平面点云,所述对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云,包括:
    根据空间坐标信息对所述第一原始点云进行分割,得到包括所述待测目标以及所述待测目标周边区域的区域点云;
    根据颜色空间模型对所述区域点云进行分割,得到第二目标点云和第二参考平面点云,所述第二目标点云为所述待测目标的点云数据,所述第二参考平面点云为所述待测目标的背景平面的点云数据。
  3. 根据权利要求2所述的方法,其中,所述根据所述第一目标参考平面,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度,包括:
    确定所述第一目标点云中每个点在所述第一目标参考平面的Z向投影点;
    根据所述Z向投影点,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度。
  4. 根据权利要求1所述的方法,其中,所述第一目标点云为第三目标点云,所述第一目标参考平面点云为第三目标参考平面点云,所述对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云,包括:
    根据空间坐标信息对所述第一原始点云进行分割,得到第三目标点云和第三参考平面点云,所述第三目标点云为所述待测目标以及所述待测目标周边区域的点云数据,所述第三参考平面点云所在的平面与所述待测目标的背景平面平行。
  5. 根据权利要求4所述的方法,其中,所述根据所述第一目标参考平面,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度,包括:
    获取所述第一目标参考平面与所述待测目标的背景平面之间的平行间距;
    确定所述第一目标点云中每个点在所述第一目标参考平面上的Z向投影点;
    根据所述Z向投影点和所述平行间距,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度。
  6. 根据权利要求1所述的方法,其中所述体素当量通过以下方式得到:
    获取已知体积的校准块的第二原始点云;
    对所述第二原始点云进行分割,得到第四目标点云和第四参考平面点云;
    拟合所述第四参考平面点云,得到第四目标参考平面;
    根据所述第四目标参考平面,计算所述第四目标点云中每个点相对于所述校准块的背景平面的相对高度;
    根据所有点的相对高度,确定所述校准块的体素数;
    根据所述校准块的体素数和体积,得到所述体素当量。
  7. 根据权利要求1所述的方法,其中所述体素当量通过以下方式得到:
    获取已知长度的校准尺的二维图像;
    根据所述二维图像和所述校准尺的长度,得到像素当量;
    根据预先标定的Z轴当量和所述像素当量,得到所述体素当量。
  8. 一种体积测量装置,包括:
    测量模块,被设置为获取待测目标的第一原始点云;
    分割模块,被设置为对所述第一原始点云进行分割,得到第一目标点云和第一参考平面点云;
    拟合模块,被设置为拟合所述第一参考平面点云,得到第一目标参考平面;
    第一处理模块,被设置为根据所述第一目标参考平面,确定所述第一目标点云中每个点相对于所述待测目标的背景平面的相对高度;
    第二处理模块,被设置为根据所有点的相对高度,确定所述待测目标的体素数;
    第三处理模块,被设置为根据预先标定的体素当量和所述待测目标的体素数,得到所述待测目标的体积。
  9. 一种电子设备,包括:存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序,其中,所述处理器执行所述计算机程序时,实现如权利要求1至7任一项所述的体积测量方法。
  10. 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时,实现如权利要求1至7任一项所述的体积测量方法。
PCT/CN2022/078895 2021-12-03 2022-03-02 体积测量方法和装置、计算机可读存储介质 WO2023097913A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111470266.9 2021-12-03
CN202111470266.9A CN116228841A (zh) 2021-12-03 2021-12-03 体积测量方法和装置、计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2023097913A1 true WO2023097913A1 (zh) 2023-06-08

Family

ID=86581093

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/078895 WO2023097913A1 (zh) 2021-12-03 2022-03-02 体积测量方法和装置、计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN116228841A (zh)
WO (1) WO2023097913A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110095062A (zh) * 2019-04-17 2019-08-06 北京华捷艾米科技有限公司 一种物体体积参数测量方法、装置及设备
CN112270702A (zh) * 2020-11-12 2021-01-26 Oppo广东移动通信有限公司 体积测量方法及装置、计算机可读介质和电子设备
CN112419505A (zh) * 2020-12-07 2021-02-26 苏州工业园区测绘地理信息有限公司 一种结合语义规则和模型匹配的车载点云道路杆状物自动提取方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110095062A (zh) * 2019-04-17 2019-08-06 北京华捷艾米科技有限公司 一种物体体积参数测量方法、装置及设备
CN112270702A (zh) * 2020-11-12 2021-01-26 Oppo广东移动通信有限公司 体积测量方法及装置、计算机可读介质和电子设备
CN112419505A (zh) * 2020-12-07 2021-02-26 苏州工业园区测绘地理信息有限公司 一种结合语义规则和模型匹配的车载点云道路杆状物自动提取方法

Also Published As

Publication number Publication date
CN116228841A (zh) 2023-06-06

Similar Documents

Publication Publication Date Title
JP6363863B2 (ja) 情報処理装置および情報処理方法
CN112634374B (zh) 双目相机的立体标定方法、装置、***及双目相机
US9007602B2 (en) Three-dimensional measurement apparatus, three-dimensional measurement method, and computer-readable medium storing control program
US10452949B2 (en) System and method for scoring clutter for use in 3D point cloud matching in a vision system
US9013559B2 (en) System, method and program for capturing images from a virtual viewpoint
US11042966B2 (en) Method, electronic device, and storage medium for obtaining depth image
JP6566768B2 (ja) 情報処理装置、情報処理方法、プログラム
JP5633058B1 (ja) 3次元計測装置及び3次元計測方法
CN109163775B (zh) 一种基于带式运输机的质量测量方法及装置
US11132802B2 (en) Method of detecting moving objects from a temporal sequence of images
US20180367709A1 (en) Image processing apparatus, object shape estimation method, and storage medium
CN112378333B (zh) 仓储货物测量方法和装置
KR102023087B1 (ko) 카메라 캘리브레이션 방법
WO2023097913A1 (zh) 体积测量方法和装置、计算机可读存储介质
US20240005548A1 (en) Information processing apparatus, three-dimensional position estimation method, and a non-transitory computer-readable medium
CN115690469A (zh) 一种双目图像匹配方法、装置、设备和存储介质
KR101574195B1 (ko) 모바일 플랫폼에 기반한 가상 카메라의 자동 캘리브레이션 방법
JP2007315777A (ja) 三次元形状計測システム
KR101314101B1 (ko) 3차원 계측 시스템 및 그 방법
CN112734721B (zh) 一种光轴偏转角度检测方法、装置、设备和介质
CN112262411B (zh) 图像关联方法、***和装置
CN113347402A (zh) 基于Unity的渲染沉浸式内容的改良方法、装置和存储介质
KR101980899B1 (ko) 직교 소실점을 이용한 단일 영상의 내벽 구조 검출 장치 및 방법
KR20210084339A (ko) 이미지 연관 방법, 시스템 및 장치
EP2953096B1 (en) Information processing device, information processing method, system and carrier means

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: 22899736

Country of ref document: EP

Kind code of ref document: A1