WO2020063987A1

WO2020063987A1 - Three-dimensional scanning method and apparatus and storage medium and processor

Info

Publication number: WO2020063987A1
Application number: PCT/CN2019/109203
Authority: WO
Inventors: 黄磊杰
Original assignee: 先临三维科技股份有限公司
Priority date: 2018-09-30
Filing date: 2019-09-29
Publication date: 2020-04-02
Also published as: CN109357633B; CN109357633A

Abstract

Disclosed are a three-dimensional scanning method and apparatus, a storage medium and a processor. The method comprises: acquiring a first image collected by a predetermined camera for the first time, wherein the first image is the image, of an object to be scanned, collected by the predetermined camera in a first position (S102); acquiring a second image collected by the predetermined camera for the second time, wherein the second image is the image, of the object to be scanned, collected by the predetermined camera in a second position (S104); and determining three-dimensional point cloud coordinates of the object to be scanned according to the first image and the second image (S106).

Description

三维扫描方法、装置、存储介质和处理器Three-dimensional scanning method, device, storage medium and processor

本申请要求于2018年09月30日提交中国专利局、申请号为201811161684.8发明名称“三维扫描方法、装置、存储介质和处理器”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on September 30, 2018, with the application number of 201811161684.8, and the invention name "three-dimensional scanning method, device, storage medium and processor", the entire contents of which are incorporated herein by reference. Applying.

技术领域Technical field

本发明涉及三维扫描领域，具体而言，涉及一种三维扫描方法、装置、存储介质和处理器。The present invention relates to the field of three-dimensional scanning, and in particular, to a three-dimensional scanning method, device, storage medium, and processor.

背景技术Background technique

一个位置被两个相机同时采集到，是双目视觉测量***实现测量的一个前提。其中，一套双目视觉测量***由两个完成内外参标定的相机组成，通过匹配算法找到空间中一点在两个相平面上的成像位置，通过三角测量法便能够测量计算出空间中点在相机坐标系下的三维点云坐标。One position is acquired by two cameras at the same time, which is a prerequisite for the binocular vision measurement system to achieve measurement. Among them, a set of binocular vision measurement system consists of two cameras that complete the calibration of internal and external parameters. The matching position is used to find the imaging position of a point on two phase planes. The triangulation method can be used to measure and calculate the midpoint of the space. The 3D point cloud coordinates in the camera coordinate system.

但是，在一些比较复杂的扫描环境下，常常会因为遮挡，致使某个位置只有一个相机采集到，导致针对该位置的测量失败。并且当测量环境比较狭窄，无法变换视角使某个位置被两个相机同时采集到，这将使该位置数据始终无法采集，导致扫描数据不完整。However, in some more complicated scanning environments, it is often caused by occlusion that only one camera can collect at a certain position, which causes the measurement of that position to fail. And when the measurement environment is relatively narrow, it is impossible to change the angle of view so that a position is captured by two cameras at the same time, which will make the position data always impossible to collect, resulting in incomplete scan data.

针对上述无法对狭窄位置进行双目扫描的问题，目前尚未提出有效的解决方案。Aiming at the problem that the binocular scan cannot be performed on the narrow position, an effective solution has not been proposed at present.

发明内容Summary of the Invention

本发明实施例提供了一种三维扫描方法、装置、存储介质和处理器，以至少解决无法对狭窄位置进行双目扫描的技术问题。Embodiments of the present invention provide a three-dimensional scanning method, device, storage medium, and processor, so as to at least solve a technical problem that binocular scanning cannot be performed on a narrow position.

根据本发明实施例的一个方面，提供了一种三维扫描方法，包括：获取预定相机在第一次采集的第一图像，其中，所述第一图像为所述预定相机在第一位置采集的待扫描物体的图像；获取所述预定相机在第二次位置采集的第二图像，其中，所述第二图像为所述预定相机在第二位置采集的所述待扫描物体的图像；根据所述第一图像和所述第二图像确定所述待扫描物体的三维点云坐标。According to an aspect of the embodiment of the present invention, a three-dimensional scanning method is provided, including: acquiring a first image acquired by a predetermined camera for the first time, wherein the first image is acquired by the predetermined camera at a first position. An image of the object to be scanned; acquiring a second image acquired by the predetermined camera at a second position, wherein the second image is an image of the object to be scanned acquired by the predetermined camera at the second position; The first image and the second image determine the three-dimensional point cloud coordinates of the object to be scanned.

进一步地，所述待扫描物体包括标识信息，根据所述第一图像和所述第二图像确定所述待扫描物体的三维点云坐标包括：在所述第一图像中确定所述标识信息为第一标识信息；在所述第二图像中确定所述标识信息为第二标识信息；根据所述第一标识信息和所述第二标识信息，确定所述预定相机在所述第一位置和所述第二位置之间坐标系的变换关系；依据变换关系确定所述第一图像和所述第二图像中的所述待扫描物体的三维点云坐标。Further, the object to be scanned includes identification information, and determining the three-dimensional point cloud coordinates of the object to be scanned according to the first image and the second image includes: determining the identification information in the first image as First identification information; determining that the identification information is second identification information in the second image; and determining, according to the first identification information and the second identification information, that the predetermined camera is at the first position and A transformation relationship of a coordinate system between the second positions; and determining a three-dimensional point cloud coordinate of the object to be scanned in the first image and the second image according to the transformation relationship.

进一步地，依据变换关系确定所述待扫描物体的三维点云坐标包括：根据所述变换关系确定预定相机外参，其中，所述预定相机外参用于确定所述预定相机在所述第一位置和所述第二位置构成的双目视觉测量***，所述第一图像为所述双目视觉测量***中第一目采集的图像，所述第二图像为所述双目视觉测量***中第二目采集的图像；依据所述双目视觉测量***确定所述第一图像和所述第二图像中的所述待扫描物体的三维点云坐标。Further, determining the three-dimensional point cloud coordinates of the object to be scanned according to a transformation relationship includes: determining a predetermined camera external parameter according to the transformation relationship, wherein the predetermined camera external parameter is used to determine that the predetermined camera is in the first The binocular vision measurement system formed by the position and the second position, the first image is an image acquired by the first binocular in the binocular vision measurement system, and the second image is the binocular vision measurement system An image acquired by the second eye; and a three-dimensional point cloud coordinate of the object to be scanned in the first image and the second image is determined according to the binocular vision measurement system.

进一步地，所述标识信息至少包括：所述待扫描物体的纹理特征，和所述待扫描物体的几何特征。Further, the identification information includes at least: a texture feature of the object to be scanned, and a geometric feature of the object to be scanned.

进一步地，所述预定相机包括双目相机，其中，所述双目相机包括第一镜头和第二镜头，获取预定相机在第一次采集的第一图像包括：获取所述双目相机在所述第一位置采集的第一双目图像，其中，所述第一双目图像包括：所述第一镜头采集的第一预定图像和所述第二镜头采集的第二预定图像；确定所述第一预定图像和所述第二预定图像中存在所述标识信息的图像为所述第一图像；获取预定相机在第二次采集的第二图像包括：获取所述双目相机在所述第二位置采集的第二双目图像，其中，所述第二双目图像包括：所述第一镜头采集的第三预定图像和所述第二镜头采集的第四预定图像；确定所述第三预定图像和所述第四预定图像中存在所述标识信息的图像为所述第二图像。Further, the predetermined camera includes a binocular camera, wherein the binocular camera includes a first lens and a second lens, and acquiring the first image acquired by the predetermined camera for the first time includes: acquiring the binocular camera at all locations. The first binocular image acquired at the first position, wherein the first binocular image includes: a first predetermined image acquired by the first lens and a second predetermined image acquired by the second lens; determining the An image in which the identification information exists in the first predetermined image and the second predetermined image is the first image; acquiring a second image acquired by a predetermined camera for a second time includes: acquiring the binocular camera in the first The second binocular image acquired at two positions, wherein the second binocular image includes: a third predetermined image acquired by the first lens and a fourth predetermined image acquired by the second lens; determining the third An image in which the identification information exists in the predetermined image and the fourth predetermined image is the second image.

根据本发明实施例的另一方面，还提供了一种三维扫描装置，包括：第一获取单元，被设置为获取预定相机在第一次采集的第一图像，其中，所述第一图像为所述预定相机在第一位置采集的待扫描物体的图像；第二获取单元，被设置为获取所述预定相机在第二次位置采集的第二图像，其中，所述第二图像为所述预定相机在第二位置采集的所述待扫描物体的图像；确定单元，被设置为根据所述第一图像和所述第二图像确定所述待扫描物体的三维点云坐标。According to another aspect of the embodiments of the present invention, a three-dimensional scanning device is further provided, including: a first acquisition unit configured to acquire a first image acquired by a predetermined camera for the first time, wherein the first image is An image of an object to be scanned acquired by the predetermined camera at a first position; a second acquisition unit configured to acquire a second image acquired by the predetermined camera at a second position, wherein the second image is the An image of the object to be scanned collected by a predetermined camera at a second position; a determining unit configured to determine a three-dimensional point cloud coordinate of the object to be scanned according to the first image and the second image.

进一步地，所述待扫描物体包括标识信息，所述确定单元，包括：第一确定模块，被设置为在所述第一图像中确定所述标识信息为第一标识信息；第二确定模块，被设置为在所述第二图像中确定所述标识信息为第二标识信息；第三确定模块，被设置为根据所述第一标识信息和所述第二标识信息，确定所述预定相机在所述第一位置和所述第二位置之间坐标系的变换关系；第四确定模块，被设置为依据变换关系确定所述第一图像和所述第二图像中的所述待扫描物体的三维点云坐标。Further, the object to be scanned includes identification information, and the determination unit includes: a first determination module configured to determine the identification information as the first identification information in the first image; a second determination module, And configured to determine that the identification information is second identification information in the second image; a third determination module is configured to determine, based on the first identification information and the second identification information, that the predetermined camera is in A transformation relationship of a coordinate system between the first position and the second position; a fourth determination module is configured to determine, based on the transformation relationship, a position of the object to be scanned in the first image and the second image 3D point cloud coordinates.

进一步地，所述第四确定模块包括：第五确定模块，被设置为根据所述变换关系确定预定相机外参，其中，所述预定相机外参用于确定所述预定相机在所述第一位置和所述第二位置构成的双目视觉测量***，所述第一图像为所述双目视觉测量***中第一目采集的图像，所述第二图像为所述双目视觉测量***中第二目采集的图像；第六确定模块，被设置为依据所述双目视觉测量***确定所述第一图像和所述第二图像中的所述待扫描物体的三维点云坐标。Further, the fourth determining module includes a fifth determining module configured to determine a predetermined camera external parameter according to the transformation relationship, wherein the predetermined camera external parameter is used to determine that the predetermined camera is in the first The binocular vision measurement system formed by the position and the second position, the first image is an image acquired by the first binocular in the binocular vision measurement system, and the second image is the binocular vision measurement system An image acquired by the second eye; a sixth determination module configured to determine the three-dimensional point cloud coordinates of the object to be scanned in the first image and the second image according to the binocular vision measurement system.

根据本发明实施例的另一个方面，还提供了一种存储介质，所述存储介质包括存储的程序，其中，在所述程序运行时控制所述存储介质所在设备执行上述所述的三维扫描方法。According to another aspect of the embodiments of the present invention, there is also provided a storage medium including a stored program, wherein when the program runs, the device where the storage medium is located is controlled to perform the three-dimensional scanning method described above. .

根据本发明实施例的又一个方面，还提供了一种处理器，所述处理器被设置为运行程序，其中，所述程序运行时执行上述所述的三维扫描方法。According to yet another aspect of the embodiments of the present invention, there is also provided a processor configured to run a program, wherein the three-dimensional scanning method described above is executed when the program runs.

在本发明实施例中，预定相机第一次在第一预定位置采集待扫描物体的第一图像，然后预定相机第二次在第二预定位置采集待扫描物体的第二图像，可以根据两次采集的图像对待扫描物体进行三维建模，得到待扫描物体的三维点云坐标，从而在无法直接使用双目视觉测量***的狭窄位置，可以根据预定相机先后采集的两个图像确定待扫描物体的三维扫描，从而实现了对狭窄位置的物体进行三维扫描的技术效果，进而解决了无法对狭窄位置进行双目扫描的技术问题。In the embodiment of the present invention, the predetermined camera acquires the first image of the object to be scanned for the first time at the first predetermined position, and then the predetermined camera acquires the second image of the object to be scanned for the second time at the second predetermined position. The acquired image is three-dimensionally modeled to be scanned, and the three-dimensional point cloud coordinates of the object to be scanned are obtained. Therefore, in a narrow position where the binocular vision measurement system cannot be directly used, the two images acquired by a predetermined camera can be used to determine the object to be scanned. Three-dimensional scanning, thereby realizing the technical effect of three-dimensional scanning on objects in narrow positions, and further solving the technical problem that binocular scanning cannot be performed on narrow positions.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

此处所说明的附图用来提供对本发明的进一步理解，构成本申请的一部分，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：The drawings described here are used to provide a further understanding of the present invention and constitute a part of the present application. The schematic embodiments of the present invention and the descriptions thereof are used to explain the present invention, and do not constitute an improper limitation on the present invention. In the drawings:

图1是根据本发明实施例的一种三维扫描方法的流程图；FIG. 1 is a flowchart of a three-dimensional scanning method according to an embodiment of the present invention;

图2是根据本发明实施例的一种三维扫描装置的示意图。FIG. 2 is a schematic diagram of a three-dimensional scanning device according to an embodiment of the present invention.

具体实施方式detailed description

为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分的实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本发明保护的范围。In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only The embodiments are part of the present invention, but not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative efforts should fall within the protection scope of the present invention.

需要说明的是，本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本发明的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、***、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。It should be noted that the terms “first” and “second” in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data so used may be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in an order other than those illustrated or described herein. Furthermore, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units need not be limited to those explicitly listed Those steps or units may instead include other steps or units not explicitly listed or inherent to these processes, methods, products or equipment.

根据本发明实施例，提供了一种三维扫描方法实施例，需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机***中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。According to an embodiment of the present invention, an embodiment of a three-dimensional scanning method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. The logical order is shown in the flowchart, but in some cases, the steps shown or described may be performed in a different order than here.

图1是根据本发明实施例的一种三维扫描方法的流程图，如图1所示，该方法包括如下步骤：FIG. 1 is a flowchart of a three-dimensional scanning method according to an embodiment of the present invention. As shown in FIG. 1, the method includes the following steps:

步骤S102，获取预定相机在第一次采集的第一图像，其中，第一图像为预定相机在第一位置采集的待扫描物体的图像；Step S102, acquiring a first image acquired by a predetermined camera for the first time, where the first image is an image of an object to be scanned acquired by the predetermined camera at a first position;

步骤S104，获取预定相机在第二次采集的第二图像，其中，第二图像为预定相机在第二位置采集的待扫描物体的图像；Step S104: Acquire a second image acquired by the predetermined camera at the second time, where the second image is an image of the object to be scanned acquired by the predetermined camera at the second position;

步骤S106，根据第一图像和第二图像确定待扫描物体的三维点云坐标。Step S106: Determine the three-dimensional point cloud coordinates of the object to be scanned according to the first image and the second image.

通过上述步骤，预定相机第一次在第一预定位置采集待扫描物体的第一图像，然后预定相机第二次在第二预定位置采集待扫描物体的第二图像，可以根据两次采集的图像对待扫描物体进行三维建模，得到待扫描物体的三维点云坐标，从而在无法直接使用双目视觉测量***的狭窄位置，可以根据预定相机先后采集的两个图像确定待扫描物体的三维扫描，从而实现了对狭窄位置的物体进行三维扫描的技术效果，进而解决了无法对狭窄位置进行双目扫描的技术问题。Through the above steps, the scheduled camera collects the first image of the object to be scanned for the first time at the first predetermined position, and then the scheduled camera acquires the second image of the object to be scanned for the second time at the second predetermined position. 3D modeling of the object to be scanned to obtain the 3D point cloud coordinates of the object to be scanned, so that in a narrow position where the binocular vision measurement system cannot be used directly, a 3D scan of the object to be scanned can be determined according to two images acquired by a predetermined camera successively. Therefore, the technical effect of three-dimensional scanning of objects in a narrow position is realized, and the technical problem that binocular scanning cannot be performed in a narrow position is solved.

在上述步骤S106中，可以将第一图像和第二图像作为双目视觉测量***中的双目镜头采集的两个图像，从而可以根据第一图像和第二图像确定待扫描物体的三维点云坐标。In the above step S106, the first image and the second image may be used as the two images collected by the binocular lens in the binocular vision measurement system, so that the three-dimensional point cloud of the object to be scanned can be determined according to the first image and the second image. coordinate.

在上述步骤S106中，待扫描物体的三维点云坐标用于描述待扫描物体的三维轮廓。In step S106, the three-dimensional point cloud coordinates of the object to be scanned are used to describe the three-dimensional contour of the object to be scanned.

但是，若使用第一图像和第二图像作为双目视觉测量***中的双目镜头采集的两个图像，则需要确定第一图像和第二图像之间某些用于构建第一图像和第二图像作为双目视觉测量***中的双目镜头采集的两个图像的特定参数。例如，需要确定预定相机采集第一图像的第一位置与采集第二图像的第二位置之间坐标系的变换关系。又例如，需要根据预定相机在第一位置和第二位置构成的双目视觉测量***的相机外参。However, if the first image and the second image are used as the two images collected by the binocular lens in the binocular vision measurement system, it is necessary to determine that some of the first image and the second image are used to construct the first image and the second image. Two images are specific parameters of two images acquired by a binocular lens in a binocular vision measurement system. For example, it is necessary to determine a transformation relationship of a coordinate system between a first position where a predetermined camera acquires a first image and a second position where a second image is acquired. As another example, a camera external reference of a binocular vision measurement system formed by a predetermined camera at a first position and a second position is required.

需要说明的是，在双目视觉测量***中，可以根据双目相机中双目镜头的相机外参和双目镜头中分别采集的待扫描物体的图像，完成对待扫描物体的三维扫描，得到待扫描物体的三维点云坐标。It should be noted that, in the binocular vision measurement system, the three-dimensional scanning of the object to be scanned can be completed according to the external parameters of the camera of the binocular lens in the binocular camera and the images of the object to be scanned, respectively, to obtain The 3D point cloud coordinates of the scanned object.

可选地，可以根据第一图像和第二图像中的待扫描物体的标识信息确定上述特定参数。Optionally, the specific parameter may be determined according to identification information of an object to be scanned in the first image and the second image.

作为一种可选的实施例，待扫描物体包括标识信息，根据第一图像和第二图像确定待扫描物体的三维点云坐标包括：在第一图像中确定标识信息为第一标识信息；在第二图像中确定标识信息为第二标识信息；根据第一标识信息和第二标识信息，确定预定相机在第一位置和第二位置之间坐标系的变换关系；依据变换关系确定第一图像和第二图像中的待扫描物体的三维点云坐标。As an optional embodiment, the object to be scanned includes identification information, and determining the three-dimensional point cloud coordinates of the object to be scanned according to the first image and the second image includes: determining the identification information in the first image as the first identification information; Determine the identification information in the second image as the second identification information; determine the transformation relationship of the coordinate system of the predetermined camera between the first position and the second position according to the first identification information and the second identification information; determine the first image according to the transformation relationship And the three-dimensional point cloud coordinates of the object to be scanned in the second image.

采用本发明上述实施例，将第一图像中待扫描物体上的标识信息作为第一标识信息，将第二图像中待扫描物体上的标识信息作为第二标识信息，则根据第一标识信息和第二标识信息可以确定采集第一图像和第二图像的预定相机在第一位置和第二位置之间坐标系的变化关系，进而根据该变换关系结合第一图像和第二图像即可确定待扫描物体的三维点云坐标，完成对待扫描物体的三维扫描。With the above embodiment of the present invention, if the identification information on the object to be scanned in the first image is used as the first identification information, and the identification information on the object to be scanned in the second image is used as the second identification information, then according to the first identification information and The second identification information can determine a change relationship of a coordinate system between a first position and a second position of a predetermined camera that collects the first image and the second image, and then the first image and the second image are combined according to the transformation relationship to determine the Scan the 3D point cloud coordinates of the object to complete the 3D scan of the object to be scanned.

作为一种可选的实施例，依据变换关系确定待扫描物体的三维点云坐标包括：根据变换关系确定预定相机外参，其中，预定相机外参用于确定预定相机在第一位置和第二位置构成的双目视觉测量***，第一图像为双目视觉测量***中第一目采集的图像，第二图像为双目视觉测量***中第二目采集的图像；依据双目视觉测量***确定第一图像和第二图像中的待扫描物体的三维点云坐标。As an optional embodiment, determining the three-dimensional point cloud coordinates of the object to be scanned according to the transformation relationship includes: determining a predetermined camera external parameter according to the transformation relationship, wherein the predetermined camera external parameter is used to determine that the predetermined camera is at the first position and the second A binocular vision measurement system composed of positions. The first image is an image acquired by the first eye in the binocular vision measurement system, and the second image is an image acquired by the second eye in the binocular vision measurement system. It is determined according to the binocular vision measurement system. The three-dimensional point cloud coordinates of the object to be scanned in the first image and the second image.

采用本发明上述实施例，根据预定相机在第一位置和第二位置之间坐标系的变化关系，可以确定预定相机在第一位置和第二位置构成的双目视觉测量***的中的预定相机外参，从而可以根据双目视觉测量***进行三维扫描的原理，完成对待扫描物体的三维扫描。According to the above embodiments of the present invention, according to the change relationship of the coordinate system of the predetermined camera between the first position and the second position, the predetermined camera in the binocular vision measurement system formed by the predetermined camera at the first position and the second position can be determined. External parameters, so that the three-dimensional scanning of the object to be scanned can be completed according to the principle of three-dimensional scanning of the binocular vision measurement system.

需要说明的是，直接使用双目相机构成的双目视觉测量***中，双目相机的两个镜头的位置固定，也即两个镜头之间的距离固定，从而无法在狭窄位置灵活配置双目相机的镜头位置、两个镜头的夹角，以及两个镜头的基线等相机外参。而根据预定相机的第一位置和第二位置构成的双目视觉测量***中，通过调整第一位置和第二位置，可以灵活地配置相机外参，使重构的双目视觉测量***可以更加灵活。It should be noted that in a binocular vision measurement system constructed by directly using a binocular camera, the positions of the two lenses of the binocular camera are fixed, that is, the distance between the two lenses is fixed, so that the binocular cannot be flexibly configured in a narrow position. Camera external parameters such as the lens position of the camera, the angle between the two lenses, and the baseline of the two lenses. In the binocular vision measurement system based on the first and second positions of the predetermined camera, by adjusting the first position and the second position, the external parameters of the camera can be flexibly configured, so that the reconstructed binocular vision measurement system can be more flexible.

作为一种可选的实施例，标识信息包括：待扫描物体的纹理特征，或待扫描物体的几何特征，或待扫描物体的表面上预设的标识点。As an optional embodiment, the identification information includes: a texture feature of an object to be scanned, a geometric feature of the object to be scanned, or a preset identification point on a surface of the object to be scanned.

可选地，若直接对待扫描物体进行扫描，待扫描物体的表面纹理不会被覆盖，则可以从表面纹理中提取纹理特征作为标识信息。Optionally, if the object to be scanned is scanned directly, the surface texture of the object to be scanned will not be covered, and texture features may be extracted from the surface texture as identification information.

可选地，在对待扫描物体进行扫描的过程中，可能需要向待扫描物体的表面投射图案，则无法从待扫描物体的表面纹理中提取纹理特征，则可以将待扫描物体表面的几何特征作为标识信息。Optionally, in the process of scanning the object to be scanned, it may be necessary to project a pattern onto the surface of the object to be scanned, and then it is not possible to extract texture features from the surface texture of the object to be scanned, and the geometric feature of the surface of the object to be scanned may be used as Identification information.

可选地，待扫描物体的几何特征可以是待扫描物体表面的预设图案，如投影在待扫描物体的图案。Optionally, the geometric feature of the object to be scanned may be a preset pattern on the surface of the object to be scanned, such as a pattern projected on the object to be scanned.

可选地，预定相机可以是单目相机，也可以是双目相机。Optionally, the predetermined camera may be a monocular camera or a binocular camera.

作为一种可选的实施例，预定相机包括双目相机，其中，双目相机包括第一镜头和第二镜头，获取预定相机在第一次采集的第一图像包括：获取双目相机在第一位置采集的第一双目图像，其中，第一双目图像包括：第一镜头采集的第一预定图像和第二镜头采集的第二预定图像；确定第一预定图像和第二预定图像中存在标识信息的图像为第一图像；获取预定相机在第一次采集的第一图像包括：获取双目相机在第二位置采集的第二双目图像，其中，第二双目图像包括：第一镜头采集的第三预定图像和第二镜头采集的第四预定图像；确定第三预定图像和第四预定图像中存在标识信息的图像为第二图像。As an optional embodiment, the predetermined camera includes a binocular camera, wherein the binocular camera includes a first lens and a second lens, and acquiring the first image acquired by the predetermined camera for the first time includes: acquiring the binocular camera at the first A first binocular image collected at one location, where the first binocular image includes: a first predetermined image collected by a first lens and a second predetermined image collected by a second lens; determining the first predetermined image and the second predetermined image The image with the identification information is the first image; acquiring the first image acquired by the predetermined camera for the first time includes: acquiring the second binocular image acquired by the binocular camera at the second position, where the second binocular image includes: the first The third predetermined image collected by one lens and the fourth predetermined image collected by the second lens; it is determined that the image having identification information in the third predetermined image and the fourth predetermined image is the second image.

采用本发明上述实施例，在预定相机为双目相机的情况下，对于待扫描物体的狭窄位置，双目相机的两个镜头无法同时采集到待扫描物体的图像，即双目相机中仅有一个镜头能够采集到待扫描物体的图像，则可以使用双目相机中的任意一目镜头在采集待扫描物体的图像，得到第一图像，然后更换双目相机的位置，再一次通过任意一目镜头在采集待扫描物体的图像，得到第二图像。With the above embodiment of the present invention, when the predetermined camera is a binocular camera, for the narrow position of the object to be scanned, the two lenses of the binocular camera cannot simultaneously capture images of the object to be scanned, that is, only One lens can capture the image of the object to be scanned. You can use any of the binocular cameras to capture the image of the object to be scanned to obtain the first image, and then change the position of the binocular camera. An image of the object to be scanned is acquired to obtain a second image.

本发明还提供了一种优选实施例，该优选实施例提供了一种小范围，复杂环境下的单双目结合扫描方法。The present invention also provides a preferred embodiment, which provides a single-binocular and binocular combined scanning method in a small-scale and complex environment.

本发明提供的技术方案，在有一套双目视觉扫描***的基础上，分别利用两个相机在时序上的对应关系构成单套或者多套扫描***实现对待扫描物体的三维扫描。The technical solution provided by the present invention is based on a set of binocular vision scanning systems, and uses a corresponding relationship between two cameras in time sequence to form a single or multiple scanning systems to realize three-dimensional scanning of an object to be scanned.

可选地，在扫描过程中，分别在第一位置和第二位置完成两次扫描，利用这两次扫描的数据(或图像)，可以通过深度图之间的匹配，计算两次扫描过程中第一次扫描时的左(右)相机和第二次扫描时的左(右)相机之间坐标系的变换关系。Optionally, during the scanning process, two scans are completed at the first position and the second position respectively. Using the data (or images) from the two scans, the depth map can be used to calculate the two scans. The transformation relationship of the coordinate system between the left (right) camera at the first scan and the left (right) camera at the second scan.

可选地，通过深度图之间的匹配，可以是匹配待扫描物体表面的纹理特征或几何特征。Optionally, by matching between the depth maps, the texture features or geometric features of the surface of the object to be scanned can be matched.

可选地，在扫描过程中，分别在第一位置和第二位置完成两次扫描，利用这两次扫描的数据(或图像)，还可以通过提前放在扫描环境下的标志位物体(即标识点)，计算两次扫描过程中第一次扫描时的左(右)相机和第二次扫描时的左(右)相机之间坐标系的变换关系。Optionally, during the scanning process, two scans are completed at the first position and the second position respectively. Using the data (or images) from the two scans, it is also possible to mark objects (i.e. (Identification point), and calculate the transformation relationship of the coordinate system between the left (right) camera at the first scan and the left (right) camera at the second scan during two scans.

由于在扫描过程中，相机是固定的，即两次扫描中相机的内参是不变的。因此，根据相机在两次扫描的变换关系，即可确定两次扫描过程左(右)相机之间构成的相机外参。During the scanning process, the camera is fixed, that is, the internal parameters of the camera are unchanged during the two scans. Therefore, according to the transformation relationship between the two scans of the camera, the external camera parameters formed between the left (right) cameras during the two scans can be determined.

可选地，所谓相机的外参指的是确定两个相机坐标系之间的变换，而相机外参的获取，在主动式扫描和被动式扫描中是不同的。Optionally, the so-called external parameter of the camera refers to determining a transformation between two camera coordinate systems, and the acquisition of the external parameter of the camera is different in active scanning and passive scanning.

可选地，在被动式扫描的方法中，扫描设备一般不向待扫描物体表面投射图案，相机可以直接获取待扫描物体的表面纹理，从纹理中提取特征点，其中，该特征点可以是物体表面天然的纹理特征，也可以是为了提高匹配稳定性认为后续添加的一些特征。Optionally, in the passive scanning method, the scanning device generally does not project a pattern onto the surface of the object to be scanned, and the camera can directly obtain the surface texture of the object to be scanned and extract feature points from the texture, where the feature points may be the surface of the object Natural texture features can also be some features that are added later in order to improve matching stability.

可选地，双目相机中的任意一目相机可以在提取待扫描物体图像的二维特征点之后，再映射到该图像重建得到的三维数据中，通过对得到的三维数据进行插值便能得到这些二维特征点对应的空间三维坐标。Optionally, any one of the binocular cameras can extract the two-dimensional feature points of the image of the object to be scanned and then map them to the three-dimensional data obtained from the reconstruction of the image. These values can be obtained by interpolating the obtained three-dimensional data. The spatial three-dimensional coordinates corresponding to the two-dimensional feature points.

可选地，可以对第一次采集的第一图像求得的特征点的三维坐标和第二次采集的第一图像求得的特征点三维坐标进行匹配之后，可以求取一个刚体变换，进而便能得到采集第一图像的相机与采集第二图像的相机之间的外参。Optionally, after matching the three-dimensional coordinates of the feature points obtained in the first image acquired the first time and the three-dimensional coordinates of the feature points obtained in the second image acquired the second time, a rigid body transformation may be obtained, and An external parameter can be obtained between the camera collecting the first image and the camera collecting the second image.

可选地，在主动式扫描的方法中，扫描设备一般会向待扫描物体表面投射预定图案，这个时候无法获取物体表面的纹理特征，只能获取物体表面的几何特征，利用一些跟踪技术，将这两帧三维数据进行配准也能获取这两个位置相机的外参。Optionally, in the active scanning method, the scanning device generally projects a predetermined pattern on the surface of the object to be scanned. At this time, the texture features of the object surface cannot be obtained, and only the geometric features of the object surface can be obtained. Using some tracking technologies, The registration of these two frames of three-dimensional data can also obtain the external parameters of the two position cameras.

本发明上述实施例，利用一套双目视觉扫描***在完成两次扫描时，实际上能够得到多套双目视觉扫描***的四次扫描结果。In the above embodiment of the present invention, when a set of binocular vision scanning system is used to complete two scans, the four scanning results of multiple sets of binocular vision scanning system can actually be obtained.

需要说明的是，多套扫描***分别为：It should be noted that the multiple scanning systems are:

(1)双目相机的左右相机构成的双目视觉扫描***。(1) Binocular vision scanning system consisting of left and right cameras of the binocular camera.

(2)第一次扫描时的左相机和第二次扫描时的左相机构成的双目视觉扫描***。(2) Binocular vision scanning system consisting of the left camera during the first scan and the left camera during the second scan.

(3)第一次扫描时的右相机和第二次扫描时的右相机构成的双目视觉扫描***。(3) Binocular vision scanning system consisting of the right camera at the first scan and the right camera at the second scan.

(4)第一次扫描时的右相机和第二次扫描时的左相机构成的双目视觉扫描***。(4) Binocular vision scanning system consisting of the right camera in the first scan and the left camera in the second scan.

(5)第一次扫描时的左相机和第二次扫描时的右相机构成的双目视觉扫描***。(5) Binocular vision scanning system consisting of the left camera at the first scan and the right camera at the second scan.

需要说明的是，四次扫描结果包括：It should be noted that the results of the four scans include:

(1)双目相机第一位置的扫描结果。(1) Scanning result of the first position of the binocular camera.

(2)双目相机第二位置的扫描结果。(2) The scanning result of the second position of the binocular camera.

(3)第一位置左相机与第二位置左相机的扫描结果。(3) Scan results of the left camera at the first position and the left camera at the second position.

(4)第一位置右相机与第二位置右相机的扫描结果。(4) Scanning results of the first position right camera and the second position right camera.

本发明上述实施例，通过这三套测量***之间的互补基本上能够保证对待扫描物体表面进行过更完整的扫描。The above embodiments of the present invention can basically ensure that a more complete scan is performed on the surface of the object to be scanned by complementarity between the three sets of measurement systems.

本发明提供的技术方案，从结构上来说，无需改变现有的双目相机，可以保证较大的相机夹角和基线，保证扫描的精度和对噪声的控制，同时利用时序的方式相当于在测量过程中又增加了两个扫描头，两个扫描头的夹角通过第一位置和第二位置确定，通过调整第一位置和第二位置，可以灵活地配置两个测头的夹角和基线，配置较小的夹角和基线，减小测量死角的同时也提升了扫描效率。The technical solution provided by the present invention, from a structural point of view, does not need to change the existing binocular camera, can ensure a larger camera angle and baseline, ensure scanning accuracy and control of noise, while using the timing method is equivalent to During the measurement process, two scanning heads were added. The angle between the two scanning heads was determined by the first position and the second position. By adjusting the first position and the second position, the angle between the two scanning heads can be flexibly configured. Baseline, with smaller included angles and baselines, which reduces the measurement dead angle and improves scanning efficiency.

根据本发明的又一个实施例，还提供了一种存储介质，所述存储介质包括存储的程序，其中，所述程序运行时执行上述任一项所述的三维扫描方法。According to yet another embodiment of the present invention, a storage medium is further provided. The storage medium includes a stored program, and when the program runs, the three-dimensional scanning method according to any one of the foregoing is performed.

根据本发明的又一个实施例，还提供了一种处理器，所述处理器被设置为运行程序，其中，所述程序运行时执行上述任一项所述的三维扫描方法。According to yet another embodiment of the present invention, a processor is further provided, the processor is configured to run a program, and when the program runs, the three-dimensional scanning method according to any one of the foregoing is performed.

根据本发明实施例，还提供了一种三维扫描的装置实施例，需要说明的是，该三维扫描装置可以被设置为执行本发明实施例中的三维扫描方法，本发明实施例中的三维扫描方法可以在该三维扫描装置中执行。According to the embodiment of the present invention, an embodiment of a three-dimensional scanning device is also provided. It should be noted that the three-dimensional scanning device may be configured to perform the three-dimensional scanning method in the embodiment of the present invention, and the three-dimensional scanning in the embodiment of the present invention. The method can be performed in the three-dimensional scanning device.

图2是根据本发明实施例的一种三维扫描装置的示意图，如图2所示，该装置可以包括：第一获取单元21，被设置为获取预定相机在第一次采集的第一图像，其中，第一图像为预定相机在第一位置采集的待扫描物体的图像；第二获取单元23，被设置为获取预定相机在第二次位置采集的第二图像，其中，第二图像为预定相机在第二位置采集的待扫描物体的图像；确定单元25，被设置为根据第一图像和第二图像确定待扫描物体的三维点云坐标。FIG. 2 is a schematic diagram of a three-dimensional scanning device according to an embodiment of the present invention. As shown in FIG. 2, the device may include a first acquisition unit 21 configured to acquire a first image acquired by a predetermined camera for the first time, The first image is an image of the object to be scanned acquired by the predetermined camera at the first position; the second acquisition unit 23 is configured to acquire the second image acquired by the predetermined camera at the second position, where the second image is the predetermined The image of the object to be scanned collected by the camera at the second position; the determining unit 25 is configured to determine the three-dimensional point cloud coordinates of the object to be scanned according to the first image and the second image.

需要说明的是，该实施例中的第一获取单元21可以被设置为执行本申请实施例中的步骤S102，该实施例中的第二获取单元23可以被设置为执行本申请实施例中的步骤S104，该实施例中的确定单元25可以被设置为执行本申请实施例中的步骤S106。上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例所公开的内容。It should be noted that the first obtaining unit 21 in this embodiment may be configured to perform step S102 in the embodiment of the present application, and the second obtaining unit 23 in this embodiment may be configured to execute the step S102 in the embodiment of the present application. Step S104. The determining unit 25 in this embodiment may be configured to execute step S106 in the embodiment of the present application. The examples and application scenarios implemented by the foregoing modules are the same as the corresponding steps, but are not limited to the content disclosed in the foregoing embodiments.

在本发明实施例中，预定相机第一次在第一预定位置采集待扫描物体的第一图像，然后预定相机第二次在第二预定位置采集待扫描物体的第二图像，可以根据两次采集的图像对待扫描物体进行三维建模，得到待扫描物体的三维点云坐标，从而在无法直接使用双目视觉测量***的狭窄位置，可以根据预定相机先后采集的两个图像确定待扫描物体的三维扫描，从而实现了对狭窄位置的物体进行三维扫描的技术效果，进而解决了无法对狭窄位置进行双目扫描的技术问题。In the embodiment of the present invention, the predetermined camera acquires the first image of the object to be scanned for the first time at the first predetermined position, and then the predetermined camera acquires the second image of the object to be scanned for the second time at the second predetermined position. The acquired image is three-dimensionally modeled to be scanned, and the three-dimensional point cloud coordinates of the object to be scanned are obtained. Therefore, in a narrow position where the binocular vision measurement system cannot be used directly, the two images acquired by a predetermined camera can be used to determine the Three-dimensional scanning, thereby realizing the technical effect of three-dimensional scanning on objects in narrow positions, and further solving the technical problem that binocular scanning cannot be performed on narrow positions.

作为一种可选的实施例，待扫描物体包括标识信息，确定单元，包括：第一确定模块，被设置为在第一图像中确定标识信息为第一标识信息；第二确定模块，被设置为在第二图像中确定标识信息为第二标识信息；第三确定模块，被设置为根据第一标识信息和第二标识信息，确定预定相机在第一位置和第二位置之间坐标系的变换关系；第四确定模块，被设置为依据变换关系确定第一图像和第二图像中的待扫描物体的三维点云坐标。As an optional embodiment, the object to be scanned includes identification information, and a determining unit includes: a first determination module configured to determine the identification information in the first image as the first identification information; and a second determination module configured to be set In order to determine the identification information in the second image as the second identification information; the third determination module is configured to determine, based on the first identification information and the second identification information, the coordinate system of the predetermined camera between the first position and the second position. A transformation relationship; a fourth determination module configured to determine the three-dimensional point cloud coordinates of the object to be scanned in the first image and the second image according to the transformation relationship.

作为一种可选的实施例，第四确定模块包括：第五确定模块，被设置为根据变换关系确定预定相机外参，其中，预定相机外参用于确定预定相机在第一位置和第二位置构成的双目视觉测量***，第一图像为双目视觉测量***中第一目采集的图像，第二图像为双目视觉测量***中第二目采集的图像；第六确定模块，被设置为依据双目视觉测量***确定第一图像和第二图像中的待扫描物体的三维点云坐标。As an optional embodiment, the fourth determining module includes a fifth determining module configured to determine a predetermined camera external parameter according to a transformation relationship, wherein the predetermined camera external parameter is used to determine that the predetermined camera is at the first position and the second camera. The binocular vision measurement system composed of positions, the first image is an image acquired by the first eye in the binocular vision measurement system, and the second image is an image acquired by the second eye in the binocular vision measurement system; a sixth determination module is set To determine the three-dimensional point cloud coordinates of the object to be scanned in the first image and the second image according to the binocular vision measurement system.

作为一种可选的实施例，所述标识信息包括：待扫描物体的纹理特征，或待扫描物体的几何特征，或待扫描物体的表面上预设的标识点。As an optional embodiment, the identification information includes: a texture feature of an object to be scanned, a geometric feature of the object to be scanned, or a preset identification point on a surface of the object to be scanned.

作为一种可选的实施例，所述预定相机包括双目相机，其中，所述双目相机包括第一镜头和第二镜头，第一获取单元包括：第一获取模块，被设置为获取所述双目相机在所述第一位置采集的第一双目图像，其中，所述第一双目图像包括：所述第一镜头采集的第一预定图像和所述第二镜头采集的第二预定图像；第七确定模块，被设置为确定所述第一预定图像和所述第二预定图像中存在所述标识信息的图像为所述第一图像；第二获取单元包括：第二获取模块，被设置为获取所述双目相机在所述第二位置采集的第二双目图像，其中，所述第二双目图像包括：所述第一镜头采集的第三预定图像和所述第二镜头采集的第四预定图像；第八确定模块，被设置为确定所述第三预定图像和所述第四预定图像中存在所述标识信息的图像为所述第二图像。As an optional embodiment, the predetermined camera includes a binocular camera, wherein the binocular camera includes a first lens and a second lens, and the first acquisition unit includes a first acquisition module configured to acquire all cameras. The first binocular image acquired by the binocular camera at the first position, wherein the first binocular image includes: a first predetermined image acquired by the first lens and a second image acquired by the second lens A predetermined image; a seventh determination module configured to determine that an image in which the identification information exists in the first predetermined image and the second predetermined image is the first image; the second obtaining unit includes a second obtaining module Is configured to obtain a second binocular image collected by the binocular camera at the second position, wherein the second binocular image includes: a third predetermined image collected by the first lens and the first A fourth predetermined image collected by two lenses; an eighth determination module is configured to determine that the image in which the identification information exists in the third predetermined image and the fourth predetermined image is the second image.

上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。The sequence numbers of the foregoing embodiments of the present invention are only for description, and do not represent the superiority or inferiority of the embodiments.

在本发明的上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For a part that is not described in detail in an embodiment, reference may be made to the description of other embodiments.

在本申请所提供的几个实施例中，应该理解到，所揭露的技术内容，可通过其它的方式实现。其中，以上所描述的装置实施例仅仅是示意性的，例如所述单元的划分，可以为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，单元或模块的间接耦合或通信连接，可以是电性或其它的形式。In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the unit may be a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or may be combined. Integration into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, units or modules, and may be electrical or other forms.

所述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，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the objective of the solution of this embodiment.

另外，在本发明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，也可以采用软件功能单元的形式实现。In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional unit.

所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention essentially or part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium Including a plurality of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The foregoing storage media include: U disks, Read-Only Memory (ROM), Random Access Memory (RAM), mobile hard disks, magnetic disks, or optical disks, and other media that can store program codes .

以上所述仅是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。The above is only a preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principles of the present invention, several improvements and retouches can be made. These improvements and retouches also It should be regarded as the protection scope of the present invention.

工业实用性Industrial applicability

本发明实施例提供的方案，可以应用于三维扫描过程中。通过本发明实施例解决了无法对狭窄位置进行双目扫描的技术问题，实现了对狭窄位置的物体进行三维扫描的技术效果。The solution provided by the embodiment of the present invention can be applied to a three-dimensional scanning process. The embodiment of the present invention solves the technical problem that binocular scanning cannot be performed on a narrow position, and realizes the technical effect of three-dimensional scanning on an object in a narrow position.

Claims

一种三维扫描方法，包括：A three-dimensional scanning method includes:

获取预定相机在第一次采集的第一图像，其中，所述第一图像为所述预定相机在第一位置采集的待扫描物体的图像；Acquiring a first image acquired by a predetermined camera for the first time, wherein the first image is an image of an object to be scanned acquired by the predetermined camera at a first position;

获取所述预定相机在第二次采集的第二图像，其中，所述第二图像为所述预定相机在第二位置采集的所述待扫描物体的图像；Acquiring a second image acquired by the predetermined camera at a second time, wherein the second image is an image of the object to be scanned acquired by the predetermined camera at a second position;

根据所述第一图像和所述第二图像确定所述待扫描物体的三维点云坐标。The three-dimensional point cloud coordinates of the object to be scanned are determined according to the first image and the second image.
根据权利要求1所述的方法，其中，所述待扫描物体包括标识信息，根据所述第一图像和所述第二图像确定所述待扫描物体的三维点云坐标包括：The method according to claim 1, wherein the object to be scanned includes identification information, and determining the three-dimensional point cloud coordinates of the object to be scanned according to the first image and the second image comprises:

在所述第一图像中确定所述标识信息为第一标识信息；Determining that the identification information is the first identification information in the first image;

在所述第二图像中确定所述标识信息为第二标识信息；Determining the identification information in the second image as second identification information;

根据所述第一标识信息和所述第二标识信息，确定所述预定相机在所述第一位置和所述第二位置之间坐标系的变换关系；Determining a transformation relationship of the coordinate system of the predetermined camera between the first position and the second position according to the first identification information and the second identification information;

依据变换关系确定所述第一图像和所述第二图像中的所述待扫描物体的三维点云坐标。The three-dimensional point cloud coordinates of the object to be scanned in the first image and the second image are determined according to a transformation relationship.
根据权利要求2述的方法，其中，依据变换关系确定所述待扫描物体的三维点云坐标包括：The method according to claim 2, wherein determining the three-dimensional point cloud coordinates of the object to be scanned according to a transformation relationship comprises:

根据所述变换关系确定预定相机外参，其中，所述预定相机外参用于确定所述预定相机在所述第一位置和所述第二位置构成的双目视觉测量***，所述第一图像为所述双目视觉测量***中第一目采集的图像，所述第二图像为所述双目视觉测量***中第二目采集的图像；Determining a predetermined camera external parameter according to the transformation relationship, wherein the predetermined camera external parameter is used to determine a binocular vision measurement system formed by the predetermined camera at the first position and the second position, and the first The image is an image acquired by a first eye in the binocular vision measurement system, and the second image is an image acquired by a second eye in the binocular vision measurement system;

依据所述双目视觉测量***确定所述第一图像和所述第二图像中的所述待扫描物体的三维点云坐标。The three-dimensional point cloud coordinates of the object to be scanned in the first image and the second image are determined according to the binocular vision measurement system.
根据权利要求2所述的方法，其中，所述标识信息包括：所述待扫描物体的纹理特征，或所述待扫描物体的几何特征，或所述待扫描物体的表面上预设的标识点。The method according to claim 2, wherein the identification information comprises: a texture feature of the object to be scanned, or a geometric feature of the object to be scanned, or a preset identification point on a surface of the object to be scanned .
根据权利要求2所述的方法，其中，所述预定相机包括双目相机，其中，所述双目相机包括第一镜头和第二镜头，The method according to claim 2, wherein the predetermined camera includes a binocular camera, and wherein the binocular camera includes a first lens and a second lens,

获取预定相机在第一次采集的第一图像包括：获取所述双目相机在所述第一位置采集的第一双目图像，其中，所述第一双目图像包括：所述第一镜头采集的第一预定图像和所述第二镜头采集的第二预定图像；确定所述第一预定图像和所述第二预定图像中存在所述标识信息的图像为所述第一图像；Acquiring a first image acquired by a predetermined camera for the first time includes: acquiring a first binocular image acquired by the binocular camera at the first position, wherein the first binocular image includes: the first lens A first predetermined image acquired and a second predetermined image acquired by the second lens; determining that an image in which the identification information exists in the first predetermined image and the second predetermined image is the first image;

获取预定相机在第二次采集的第二图像包括：获取所述双目相机在所述第二位置采集的第二双目图像，其中，所述第二双目图像包括：所述第一镜头采集的第三预定图像和所述第二镜头采集的第四预定图像；确定所述第三预定图像和所述第四预定图像中存在所述标识信息的图像为所述第二图像。Acquiring a second image acquired by a predetermined camera at a second time includes: acquiring a second binocular image acquired by the binocular camera at the second position, wherein the second binocular image includes: the first lens A third predetermined image collected and a fourth predetermined image collected by the second lens; and it is determined that an image in which the identification information exists in the third predetermined image and the fourth predetermined image is the second image.
一种三维扫描装置，包括：A three-dimensional scanning device includes:

第一获取单元，被设置为获取预定相机在第一次采集的第一图像，其中，所述第一图像为所述预定相机在第一位置采集的待扫描物体的图像；A first acquiring unit configured to acquire a first image acquired by a predetermined camera for the first time, wherein the first image is an image of an object to be scanned acquired by the predetermined camera at a first position;

第二获取单元，被设置为获取所述预定相机在第二次采集的第二图像，其中，所述第二图像为所述预定相机在第二位置采集的所述待扫描物体的图像；A second acquisition unit configured to acquire a second image acquired by the predetermined camera at a second time, where the second image is an image of the object to be scanned acquired by the predetermined camera at a second position;

确定单元，被设置为根据所述第一图像和所述第二图像确定所述待扫描物体的三维点云坐标。The determining unit is configured to determine the three-dimensional point cloud coordinates of the object to be scanned according to the first image and the second image.
根据权利要求6所述的装置，其中，所述待扫描物体包括标识信息，所述确定单元，包括：The apparatus according to claim 6, wherein the object to be scanned includes identification information, and the determining unit comprises:

第一确定模块，被设置为在所述第一图像中确定所述标识信息为第一标识信息；A first determining module configured to determine the identification information in the first image as the first identification information;

第二确定模块，被设置为在所述第二图像中确定所述标识信息为第二标识信息；A second determining module configured to determine the identification information in the second image as second identification information;

第三确定模块，被设置为根据所述第一标识信息和所述第二标识信息，确定所述预定相机在所述第一位置和所述第二位置之间坐标系的变换关系；A third determining module configured to determine a transformation relationship of a coordinate system of the predetermined camera between the first position and the second position according to the first identification information and the second identification information;

第四确定模块，被设置为依据变换关系确定所述第一图像和所述第二图像中的所述待扫描物体的三维点云坐标。A fourth determining module is configured to determine a three-dimensional point cloud coordinate of the object to be scanned in the first image and the second image according to a transformation relationship.
根据权利要求7述的装置，其中，所述第四确定模块包括：The apparatus according to claim 7, wherein the fourth determining module comprises:

第五确定模块，被设置为根据所述变换关系确定预定相机外参，其中，所述预定相机外参被设置为确定所述预定相机在所述第一位置和所述第二位置构成的双目视觉测量***，所述第一图像为所述双目视觉测量***中第一目采集的图像，所述第二图像为所述双目视觉测量***中第二目采集的图像；A fifth determination module is configured to determine a predetermined camera external parameter according to the transformation relationship, wherein the predetermined camera external parameter is configured to determine a dual camera formed by the predetermined camera at the first position and the second position. A visual measurement system, the first image is an image acquired by a first eye in the binocular vision measurement system, and the second image is an image acquired by a second eye in the binocular vision measurement system;

第六确定模块，被设置为依据所述双目视觉测量***确定所述第一图像和所述第二图像中的所述待扫描物体的三维点云坐标。A sixth determination module is configured to determine the three-dimensional point cloud coordinates of the object to be scanned in the first image and the second image according to the binocular vision measurement system.
一种存储介质，所述存储介质包括存储的程序，其中，所述程序执行权利要求1至5中任意一项所述的三维扫描方法。A storage medium comprising a stored program, wherein the program executes the three-dimensional scanning method according to any one of claims 1 to 5.
一种处理器，所述处理器被设置为运行程序，其中，所述程序运行时执行权利要求1至5中任意一项所述的三维扫描方法。A processor configured to run a program, wherein when the program runs, the three-dimensional scanning method according to any one of claims 1 to 5 is executed.