WO2021093111A1 - 面向结构光3d视觉系统的全自动标定方法及装置 - Google Patents

面向结构光3d视觉系统的全自动标定方法及装置 Download PDF

Info

Publication number
WO2021093111A1
WO2021093111A1 PCT/CN2019/128962 CN2019128962W WO2021093111A1 WO 2021093111 A1 WO2021093111 A1 WO 2021093111A1 CN 2019128962 W CN2019128962 W CN 2019128962W WO 2021093111 A1 WO2021093111 A1 WO 2021093111A1
Authority
WO
WIPO (PCT)
Prior art keywords
automatic calibration
structured light
vision system
calibration
pictures
Prior art date
Application number
PCT/CN2019/128962
Other languages
English (en)
French (fr)
Inventor
邱天
张昕
吴佩雯
Original Assignee
五邑大学
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 五邑大学 filed Critical 五邑大学
Priority to US17/622,604 priority Critical patent/US12002241B2/en
Publication of WO2021093111A1 publication Critical patent/WO2021093111A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/80Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G06T7/85Stereo camera calibration
    • 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
    • G06T2207/10141Special mode during image acquisition
    • G06T2207/10152Varying illumination
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30204Marker
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02BCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40Control techniques providing energy savings, e.g. smart controller or presence detection

Definitions

  • the invention relates to the technical field of visual recognition, in particular to a fully automatic calibration method and device for structured light 3D vision systems.
  • the upgrade of current mobile optical equipment has always been at the two-dimensional level of pixels and photosensitivity, and it is also the main driving force of the smartphone innovation cycle.
  • the 3D imaging system realizes the superposition of pixel depth of field, and records the three-dimensional information of the object while taking pictures. In the future, it will promote the realization of face recognition and remote gesture control, which will be the innovation of imaging equipment in the future. focus.
  • structured light-based stereo imaging has always occupied an important position. It has the advantages of fast speed and high precision.
  • Structured light is a light field with a special organization structure, such as light spot, fringe light, coded structured light, etc.
  • the two-dimensional structured light image is projected onto the measured object, and the depth information of the surface of the measured object can be calculated using the trigonometric function according to the distortion of the image. Based on this principle, a series of 3D imaging systems based on structured light have been produced.
  • a 3D imaging system based on structured light requires a projection system and an imaging system, and the two systems are in different 3D coordinate systems. If the 3D coordinate systems of the two are to come together, a complicated calibration process is required.
  • the calibration process of the 3D vision system is complicated. Since the total number of 3D vision systems is not large at present, the calibration of the 3D vision system is mainly carried out manually in the laboratory or factory. It includes a series of manual photography and program calculation process. Even professionals in optics or imaging need to perform precise operations in accordance with the operating instructions to complete a calibration process.
  • the 3D imaging system based on structured light not only needs to be calibrated when it leaves the factory, but also may need to be re-calibrated when the system is subjected to collision, vibration or large external forces. Even ordinary maintenance technicians cannot easily complete the calibration process accurately.
  • the purpose of the present invention is to provide a fully automatic calibration method and device for structured light 3D vision system, which is convenient to operate, so that non-professionals can also use this calibration method to easily complete the calibration of structured light 3D imaging;
  • the 3D vision system can also be calibrated in batches according to this calibration method.
  • an embodiment of the present invention proposes a fully automatic calibration method for a structured light 3D vision system, including:
  • the running automatic calibration system includes:
  • step 4 If the number of groups of "recorded results" is less than 2, go back to step 1), otherwise, go to step 5);
  • step 7 If the result difference is less than the set threshold, go to step 7), otherwise, go back to step 1);
  • the photographing includes:
  • the running automatic calibration system performs 2 or 3 calibrations.
  • the embodiment of the present invention also proposes a fully automatic calibration device for structured light 3D vision system, including:
  • Erection module used to set up 3D vision system and robotic arm
  • Installation module used to install the calibration board and controllable lighting system on the robot arm
  • Initialization module used to initialize the position of the robotic arm
  • the calibration module is used to run the automatic calibration system and output the calibration results.
  • the embodiment of the present invention also proposes a fully automatic calibration device for structured light 3D vision system, including:
  • At least one processor and,
  • a memory communicatively connected with the at least one processor; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the method according to the first aspect of the present invention.
  • the embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to cause a computer to execute the method described in the first aspect of the present invention. The method described.
  • the one or more technical solutions provided in the embodiments of the present invention have at least the following beneficial effects:
  • the present invention provides a fully automatic calibration method and device for structured light 3D vision systems, which does not need to be used for a built-in 3D vision system. It can be moved to complete automatic calibration; for unfixed 3D vision systems, automatic calibration can also be completed without manual operation. Using this calibration method, on the one hand, non-professionals can easily complete the calibration of structured light 3D imaging; on the other hand, it can also solve the problem of calibrating large quantities of 3D cameras.
  • FIG. 1 is a schematic flow chart of a fully automatic calibration method for a structured light 3D vision system in the first embodiment of the present invention
  • Figure 2 is a flow chart of the running automatic calibration system in the automatic calibration method for structured light 3D vision system in the first embodiment of the present invention
  • FIG. 3 is a flowchart of a picture taking in the automatic calibration method for a structured light 3D vision system in the first embodiment of the present invention
  • FIG. 4 is a schematic structural diagram of a fully automatic calibration device for a structured light 3D vision system in a second embodiment of the present invention
  • Fig. 5 is a schematic structural diagram of a fully automatic calibration device for a structured light 3D vision system in the third embodiment of the present invention.
  • the first embodiment of the present invention provides a fully automatic calibration method for a structured light 3D vision system, including but not limited to the following steps:
  • step S400 the specific steps of running the automatic calibration system are as follows:
  • step 4 If the number of groups of "recorded results" is less than 2, go back to step 1), otherwise, go to step 5);
  • step 7 If the result difference is less than the set threshold, go to step 7), otherwise, go back to step 1);
  • the 3D vision system sends out patterns when the camera captures. Each time a group of 45 images should be captured, the 45 pictures should be stored in the folder of the specified path, and 15 to 20 groups of images should be taken for one calibration. Perform 2 to 3 calibrations.
  • Step 1 Rotate the calibration plate in a small range
  • Step 2 Find the front
  • Step 3 Change in distance
  • Step 5 Calibration attempt
  • Step 7 Output the calibration file.
  • the advantages of this automatic calibration method for structured light 3D vision systems are: for the already installed 3D vision system, it can complete automatic calibration without moving it; for unfixed The 3D vision system can also complete automatic calibration without manual operation.
  • this calibration method on the one hand, non-professionals can easily complete the calibration of structured light 3D imaging; on the other hand, it can also solve the problem of calibrating large quantities of 3D cameras.
  • the second embodiment of the present invention provides a fully automatic calibration device for structured light 3D vision system, including:
  • the erection module 110 is used to erect the three-dimensional vision system and the robotic arm;
  • the installation module 120 is used to install a calibration board and a controllable lighting system on the robotic arm;
  • the initialization module 130 is used to initialize the position of the robotic arm
  • the calibration module 140 is used to run the automatic calibration system and output the calibration result.
  • the automatic calibration device for structured light 3D vision system in this embodiment and the automatic calibration method for structured light 3D vision system in the first embodiment are based on the same inventive concept. Therefore, the structured light-oriented system in this embodiment
  • the automatic calibration system of the 3D vision system has the same beneficial effects: for the already installed 3D vision system, it can be fully automated without moving it; for the unfixed 3D vision system, it can also be completed without manual operation. Automatic calibration. Using this device, on the one hand, non-professionals can easily complete the calibration of structured light 3D imaging; on the other hand, it can also solve the problem of calibrating large quantities of 3D cameras.
  • the third embodiment of the present invention also provides a fully automatic calibration device for structured light 3D vision system, including:
  • At least one processor At least one processor
  • the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute any one of the instructions in the first embodiment.
  • the memory can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the virtual image control method in the embodiment of the present invention .
  • the processor executes various functional applications and data processing of the stereo imaging processing device by running non-transitory software programs, instructions and modules stored in the memory, that is, realizing the structured light-oriented 3D vision system of any of the above-mentioned method embodiments Fully automatic calibration method.
  • the memory may include a storage program area and a storage data area, where the storage program area can store an operating system and an application program required by at least one function; the storage data area can store data created according to the use of the stereo imaging processing device, and the like.
  • the memory 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 may optionally include a memory remotely provided with respect to the processor, and these remote memories may be connected to the stereoscopic projection apparatus via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the one or more modules are stored in the memory, and when executed by the one or more processors, the automatic calibration method for structured light 3D vision system in any of the foregoing method embodiments is executed, for example, the first The method in the embodiment includes steps S100 to S400.
  • the fourth embodiment of the present invention also provides a computer-readable storage medium that stores computer-executable instructions that are executed by one or more control processors to enable the foregoing One or more processors execute an automatic calibration method for a structured light 3D vision system in the foregoing method embodiments, for example, the method steps S100 to S400 in the first embodiment.
  • the device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • each implementation manner can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware.
  • a person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by a computer program instructing relevant hardware.
  • the program can be stored in a computer readable storage medium, and the program can be stored in a computer readable storage medium. When executed, it may include the procedures of the above-mentioned method embodiments.
  • the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.

Landscapes

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

Abstract

一种面向结构光3D视觉系统的全自动标定方法及装置,对于已经架设好的三维视觉系统,无需移动就可以完成全自动标定;对于未固定的三维视觉系统,也可以无需人工操作就可以完成全自动标定。利用面向结构光3D视觉系统的全自动标定方法,一方面使得非专业人士可以轻松完成结构光3D成像的标定;另一方面也可以解决对大批量3D相机进行标定的问题。

Description

面向结构光3D视觉系统的全自动标定方法及装置 技术领域
本发明涉及视觉识别技术领域,尤其是一种面向结构光3D视觉系统的全自动标定方法及装置。
背景技术
目前的移动式光学设备(比如搭载在手机上的摄像头)升级一直停留在像素、感光等二维层面,也是智能手机创新周期的主驱动力。3D成像系统在二维的基础上,实现了像素景深的叠加,拍照的同时记录下对象的立体信息,未来将可以推动人脸识别、远程手势控制等变为现实,将是未来成像设备的创新焦点。
在三维成像方面,基于结构光的立体成像一直占据重要的地位,它具有速度快、精度高的优点。结构光是有特殊组织结构的光场,比如光斑、条纹光、编码结构光等。将二维结构光图像投影至被测物上,根据图像的畸变大小,利用三角函数可以计算出被测物的表面的深度信息。根据这个原理产生出了一系列的基于结构光的3D成像系统。
基于结构光的3D成像系统需要一个投影系统和一个取像系统,这两个系统处于不同的3D坐标系中。如果要使二者的3D坐标系统一起来,就需要一个复杂的标定流程。
对3D视觉系统的标定过程复杂,由于目前3D视觉系统的总数量不多,对于3D视觉系统的标定主要是在实验室或者工厂里手动进行 的。它包括一系列的手动拍照和程序运算过程。即使是光学或者成像方面的专业人士,也需要对照操作说明书进行精密的操作才可以完成一次标定过程。
随着3D视觉系统的广泛应用,比如一种说法是未来的每个手机上都可能搭载一套3D视觉系统,这意味着3D视觉系统的出货量将会增加甚至急剧增加。但是目前为止,在实验室和车间中一般都是由手动标定的。目前的方式无法完成3D相机的批量标定。
基于结构光的3D成像系统不仅在出厂时需要标定,当系统受到碰撞、振动或较大外力时,都可能需要重新标定,即使是一般的维修技术人员,也不容易精确的完成标定过程。
发明内容
为解决上述问题,本发明的目的在于提供一种面向结构光3D视觉系统的全自动标定方法及装置,其操作便捷,使得非专业人士也可以利用此标定方法轻松完成结构光3D成像的标定;对于3D相机的生产方和批量使用方,同样可以依据此标定方法进行批量标定3D视觉系统。
本发明解决其问题所采用的技术方案是:
第一方面,本发明实施例提出了一种面向结构光3D视觉系统的全自动标定方法,包括:
架设三维视觉系统和机械手臂;
在机器手臂上安装标定板和可控照明系统;
初始化机器手臂的位置;
运行自动标定系统,输出标定结果。
进一步,所述运行自动标定系统包括:
1)拍图20组,每组45个图像;
2)把20组图输入到张氏标定法,检测结果;
3)增加一组记录结果;
4)如果“已记录结果”的组数<2,回到步骤1),否则,进入步骤5);
5)如果“已记录结果”的组数=2,进入步骤6);
6)如果结果差小于设定阈值,进入步骤7),否则,回到步骤1);
7)求平均,输出结果。
进一步,所述拍图包括:
1)启动单幅拍照;
2)如果有图,则继续;如果没有,则查找;
3)在Z平面内做六角形移位,在每一个位置拍照取像,判断角点个数并排序;
4)如果没有,扩大搜索范围;
5)如果还没有,回复到原点,调整Z平面的方向,45度角,重复;
6)如果有找到最大角点位置,调整三维视觉系统的方向和亮度,得到第一个完整的正面图,记录位置;
7)调整角度,得到一组图;
8)调整距离,得到一组图;
9)共得到20组,每组50幅图。
进一步,所述运行自动标定系统进行2次或3次标定。
第二方面,本发明实施例还提出了一种面向结构光3D视觉系统的全自动标定装置,包括:
架设模块,用于架设三维视觉系统和机械手臂;
安装模块,用于在机器手臂上安装标定板和可控照明系统;
初始化模块,用于初始化机器手臂的位置;
标定模块,用于运行自动标定系统,输出标定结果。
第三方面,本发明实施例还提出了一种面向结构光3D视觉系统的全自动标定设备,包括:
至少一个处理器;以及,
与所述至少一个处理器通信连接的存储器;其中,
所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行本发明第一方面所述的方法。
第四方面,本发明实施例还提出了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可执行指令,所述计算机可执行指令用于使计算机执行本发明第一方面所述的方法。
本发明实施例中提供的一个或多个技术方案,至少具有如下有益 效果:本发明提供的一种面向结构光3D视觉系统的全自动标定方法及装置,对于已经架设好的三维视觉系统,无需移动它就可以完成全自动标定;对于未固定的三维视觉系统,也可以无需人工操作就可以完成全自动标定。利用本标定方法,一方面使得非专业人士可以轻松完成结构光3D成像的标定;另一方面也可以解决对大批量3D相机进行标定的问题。
附图说明
下面结合附图和实例对本发明作进一步说明。
图1是本发明第一实施例中面向结构光3D视觉系统的全自动标定方法的流程简图;
图2是本发明第一实施例中面向结构光3D视觉系统的全自动标定方法中的运行自动标定系统流程图;
图3是本发明第一实施例中面向结构光3D视觉系统的全自动标定方法中的拍图流程图;
图4是本发明第二实施例中面向结构光3D视觉系统的全自动标定装置的结构简图;
图5是本发明第三实施例中面向结构光3D视觉系统的全自动标定设备的结构简图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明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发明,并不用于限定本发明。
需要说明的是,如果不冲突,本发明实施例中的各个特征可以相互结合,均在本发明的保护范围之内。另外,虽然在装置示意图中进行了功能模块划分,在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于装置中的模块划分,或流程图中的顺序执行所示出或描述的步骤。
下面结合附图,对本发明实施例作进一步阐述。
如图1所示,本发明的第一实施例提供了一种面向结构光3D视觉系统的全自动标定方法,包括但不限于以下步骤:
S100:架设三维视觉系统和机械手臂;
S200:在机器手臂上安装标定板和可控照明系统;
S300:初始化机器手臂的位置;
S400:运行自动标定系统,输出标定结果。
需要指出的是,对于已经架设好的三维视觉系统,无需移动此三维视觉系统就可以完成全自动标定;对于未固定的三维视觉系统,可以无需人工操作就可以完成全自动标定。上述两种情形都要先把三维视觉系统架设好实现位置固定,再由机械手臂带动标定板按照自动标定系统设定的步骤运行。
如图2所示,在步骤S400中,运行自动标定系统具体步骤如下:
1)拍图20组,每组45个图像,把这些图存放到指定路径的文件夹内;
2)把20组图输入到张氏标定法,检测结果;
3)增加一组记录结果;
4)如果“已记录结果”的组数<2,回到步骤1),否则,进入步骤5);
5)如果“已记录结果”的组数=2,进入步骤6);
6)如果结果差小于设定阈值,进入步骤7),否则,回到步骤1);
7)求平均,输出结果。
其中,如图3所示,拍图具体步骤如下:
1)启动单幅拍照;
2)如果有图,则继续;如果没有,则查找;
3)在Z平面内做六角形移位,在每一个位置拍照取像,判断角点个数并排序;
4)如果没有,扩大搜索范围;
5)如果还没有,回复到原点,调整Z平面的方向,45度角,重复;
6)如果有找到最大角点位置,调整三维视觉系统中照明相机的方向和亮度,得到第一个完整的正面图,记录位置。
7)调整角度,得到一组图;
8)调整距离,得到一组图;
9)共得到20组,每组50幅图。
整个拍图过程三维视觉系统在相机捕捉时发出图案,每次应捕获 一组45个图像,把45幅图存放到指定路径的文件夹内,拍摄15到20组图像进行一次标定,总共要进行2次到3次标定。
另外,对于非专业人士可以执行如下步骤来进行标定:
步骤一:小范围旋转标定板;
步骤二:查找正面;
步骤三:远近变化;
步骤四:旋转;
步骤五:标定尝试;
步骤六:循环;
步骤七:输出标定文件。
通过上述步骤,这样非专业人士也可以迅速得到高质量的标定结果。
综上所述,与现有技术相比,本面向结构光3D视觉系统的全自动标定方法的优点在于:对于已经架设好的三维视觉系统,无需移动它就可以完成全自动标定;对于未固定的三维视觉系统,也可以无需人工操作就可以完成全自动标定。利用本标定方法,一方面使得非专业人士可以轻松完成结构光3D成像的标定;另一方面也可以解决对大批量3D相机进行标定的问题。
另外,如图4所示,本发明的第二实施例提供了一种面向结构光3D视觉系统的全自动标定装置,包括:
架设模块110,用于架设三维视觉系统和机械手臂;
安装模块120,用于在机器手臂上安装标定板和可控照明系统;
初始化模块130,用于初始化机器手臂的位置;
标定模块140,用于运行自动标定系统,输出标定结果。
本实施例中的面向结构光3D视觉系统的全自动标定装置与第一实施例中的面向结构光3D视觉系统的全自动标定方法基于相同的发明构思,因此,本实施例中的面向结构光3D视觉系统的全自动标定系统具有相同的有益效果:对于已经架设好的三维视觉系统,无需移动它就可以完成全自动标定;对于未固定的三维视觉系统,也可以无需人工操作就可以完成全自动标定。利用本装置,一方面使得非专业人士可以轻松完成结构光3D成像的标定;另一方面也可以解决对大批量3D相机进行标定的问题。
如图5所示,本发明的第三实施例还提供了一种面向结构光3D视觉系统的全自动标定设备,包括:
至少一个处理器;
以及与所述至少一个处理器通信连接的存储器;
其中,所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如上述第一实施例中任意一种面向结构光3D视觉系统的全自动标定方法。
存储器作为一种非暂态计算机可读存储介质,可用于存储非暂态软件程序、非暂态性计算机可执行程序以及模块,如本发明实施例中 的虚拟影像控制方法对应的程序指令/模块。处理器通过运行存储在存储器中的非暂态软件程序、指令以及模块,从而执行立体成像处理装置的各种功能应用以及数据处理,即实现上述任一方法实施例的面向结构光3D视觉系统的全自动标定方法。
存储器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系统、至少一个功能所需要的应用程序;存储数据区可存储根据立体成像处理装置的使用所创建的数据等。此外,存储器可以包括高速随机存取存储器,还可以包括非暂态存储器,例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。在一些实施例中,存储器可选包括相对于处理器远程设置的存储器,这些远程存储器可以通过网络连接至该立体投影装置。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。
所述一个或者多个模块存储在所述存储器中,当被所述一个或者多个处理器执行时,执行上述任意方法实施例中的面向结构光3D视觉系统的全自动标定方法,例如第一实施例中的方法步骤S100至S400。
本发明的第四实施例还提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机可执行指令,该计算机可执行指令被一个或多个控制处理器执行,可使得上述一个或多个处理器执行上述方法实施例中的一种面向结构光3D视觉系统的全自动标定方法,例如第一实施例中的方法步骤S100至S400。
以上所描述的装置实施例仅仅是示意性的,其中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,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。
通过以上的实施方式的描述,本领域普通技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现,当然也可以通过硬件。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序来指令相关的硬件来完成,所述的程序可存储于一计算机可读取存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
以上是对本发明的较佳实施进行了具体说明,但本发明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发明精神的前提下还可作出种种的等同变形或替换,这些等同的变形或替换均包含在本申请权利要求所限定的范围内。

Claims (7)

  1. 一种面向结构光3D视觉系统的全自动标定方法,其特征在于,包括:
    架设三维视觉系统和机械手臂;
    在机器手臂上安装标定板和可控照明系统;
    初始化机器手臂的位置;
    运行自动标定系统,输出标定结果。
  2. 根据权利要求1所述的一种面向结构光3D视觉系统的全自动标定方法,其特征在于,所述运行自动标定系统包括:
    1)拍图20组,每组45个图像;
    2)把20组图输入到张氏标定法,检测结果;
    3)增加一组记录结果;
    4)如果“已记录结果”的组数<2,回到步骤1),否则,进入步骤5);
    5)如果“已记录结果”的组数=2,进入步骤6);
    6)如果结果差小于设定阈值,进入步骤7),否则,回到步骤1);
    7)求平均,输出结果。
  3. 根据权利要求2所述的一种面向结构光3D视觉系统的全自动标定方法,其特征在于,所述拍图包括:
    1)启动单幅拍照;
    2)如果有图,则继续;如果没有,则查找;
    3)在Z平面内做六角形移位,在每一个位置拍照取像,判断角点个数并排序;
    4)如果没有,扩大搜索范围;
    5)如果还没有,回复到原点,调整Z平面的方向,45度角,重复;
    6)如果有找到最大角点位置,调整三维视觉系统的方向和亮度,得到第一个完整的正面图,记录位置;
    7)调整角度,得到一组图;
    8)调整距离,得到一组图;
    9)共得到20组,每组50幅图。
  4. 根据权利要求1所述的一种面向结构光3D视觉系统的全自动标定方法,其特征在于,所述运行自动标定系统进行2次或3次标定。
  5. 一种面向结构光3D视觉系统的全自动标定装置,其特征在于,包括:
    架设模块,用于架设三维视觉系统和机械手臂;
    安装模块,用于在机器手臂上安装标定板和可控照明系统;
    初始化模块,用于初始化机器手臂的位置;
    标定模块,用于运行自动标定系统,输出标定结果。
  6. 一种面向结构光3D视觉系统的全自动标定设备,其特征在于,包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如权利要求1-4任一项所述的方法。
  7. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质存储有计算机可执行指令,所述计算机可执行指令用于使计算机执行如权利要求1-4任一项所述的方法。
PCT/CN2019/128962 2019-11-15 2019-12-27 面向结构光3d视觉系统的全自动标定方法及装置 WO2021093111A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/622,604 US12002241B2 (en) 2019-11-15 2019-12-27 Full-automatic calibration method and apparatus oriented to structured light 3D vision system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911116903.5 2019-11-15
CN201911116903.5A CN110930460B (zh) 2019-11-15 2019-11-15 面向结构光3d视觉系统的全自动标定方法及装置

Publications (1)

Publication Number Publication Date
WO2021093111A1 true WO2021093111A1 (zh) 2021-05-20

Family

ID=69853050

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/128962 WO2021093111A1 (zh) 2019-11-15 2019-12-27 面向结构光3d视觉系统的全自动标定方法及装置

Country Status (3)

Country Link
US (1) US12002241B2 (zh)
CN (1) CN110930460B (zh)
WO (1) WO2021093111A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101814185A (zh) * 2010-04-14 2010-08-25 天津大学 用于微小尺寸测量的线结构光视觉传感器标定方法
CN106017312A (zh) * 2016-03-22 2016-10-12 武汉武大卓越科技有限责任公司 结构光三角测量自动标定系统及标定方法
CN106441099A (zh) * 2016-10-13 2017-02-22 北京交通大学 多线结构光传感器的标定方法
CN108709499A (zh) * 2018-04-28 2018-10-26 天津大学 一种结构光视觉传感器及其快速标定方法
KR20190050819A (ko) * 2017-04-05 2019-05-13 (주)칼리온 가정된 캘리브레이션 모델 없이 측정된 데이터를 이용하여 캘리브레이션을 수행하는 방법 및 상기 방법을 수행하는 3차원 스캐너 캘리브레이션 시스템
CN110111394A (zh) * 2019-05-16 2019-08-09 湖南三一快而居住宅工业有限公司 基于机械手特征对摄像机自动标定的方法及装置

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4877891B2 (ja) * 2001-08-03 2012-02-15 株式会社トプコン 校正用被写体
CN107003109B (zh) * 2014-11-13 2019-11-05 奥林巴斯株式会社 校准装置、校准方法、光学装置、摄影装置、投影装置、测量系统以及测量方法
JP6396516B2 (ja) * 2017-01-12 2018-09-26 ファナック株式会社 視覚センサのキャリブレーション装置、方法及びプログラム
US10366531B2 (en) * 2017-10-24 2019-07-30 Lowe's Companies, Inc. Robot motion planning for photogrammetry
CN108830906B (zh) * 2018-05-31 2023-10-24 福州大学 一种基于虚拟双目视觉原理的摄像机参数自动标定方法
CN109754433B (zh) * 2018-12-27 2023-10-03 中国科学院长春光学精密机械与物理研究所 一种标定图像采集方法、装置、设备及存储介质
US10369698B1 (en) * 2019-03-07 2019-08-06 Mujin, Inc. Method and system for performing automatic camera calibration for robot control
CN110095136B (zh) * 2019-03-27 2023-12-01 苏州德沃物流科技有限公司 融合imu位姿修正的双目视觉三维重建标定装置和方法
CN110163918B (zh) * 2019-04-24 2023-03-28 华南理工大学 一种基于射影几何的线结构光标定方法
CN110136208B (zh) * 2019-05-20 2020-03-17 北京无远弗届科技有限公司 一种机器人视觉伺服系统的联合自动标定方法及装置
US10565737B1 (en) * 2019-07-09 2020-02-18 Mujin, Inc. Method and system for performing automatic camera calibration for a scanning system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101814185A (zh) * 2010-04-14 2010-08-25 天津大学 用于微小尺寸测量的线结构光视觉传感器标定方法
CN106017312A (zh) * 2016-03-22 2016-10-12 武汉武大卓越科技有限责任公司 结构光三角测量自动标定系统及标定方法
CN106441099A (zh) * 2016-10-13 2017-02-22 北京交通大学 多线结构光传感器的标定方法
KR20190050819A (ko) * 2017-04-05 2019-05-13 (주)칼리온 가정된 캘리브레이션 모델 없이 측정된 데이터를 이용하여 캘리브레이션을 수행하는 방법 및 상기 방법을 수행하는 3차원 스캐너 캘리브레이션 시스템
CN108709499A (zh) * 2018-04-28 2018-10-26 天津大学 一种结构光视觉传感器及其快速标定方法
CN110111394A (zh) * 2019-05-16 2019-08-09 湖南三一快而居住宅工业有限公司 基于机械手特征对摄像机自动标定的方法及装置

Also Published As

Publication number Publication date
US12002241B2 (en) 2024-06-04
CN110930460A (zh) 2020-03-27
CN110930460B (zh) 2024-02-23
US20220358680A1 (en) 2022-11-10

Similar Documents

Publication Publication Date Title
US8662676B1 (en) Automatic projector calibration
US8619144B1 (en) Automatic camera calibration
KR102143456B1 (ko) 심도 정보 취득 방법 및 장치, 그리고 이미지 수집 디바이스
KR101854461B1 (ko) 카메라 시스템 및 이의 객체 인식 방법
US9338447B1 (en) Calibrating devices by selecting images having a target having fiducial features
CN109922251A (zh) 快速抓拍的方法、装置及系统
JP2017112602A (ja) パノラマ魚眼カメラの画像較正、スティッチ、および深さ再構成方法、ならびにそのシステム
CN109712193B (zh) 一种球机视场角的确定方法及装置
TWI736091B (zh) 攝像模組自動對焦測試方法及裝置
US20170171456A1 (en) Stereo Autofocus
CN108340405B (zh) 一种机器人三维扫描系统及方法
CN207766424U (zh) 一种拍摄装置及成像设备
CN106226976A (zh) 一种双摄像头拍摄方法、系统及终端
CN110213491B (zh) 一种对焦方法、装置及存储介质
CN104092955A (zh) 闪光控制方法及控制装置、图像采集方法及采集设备
WO2020181409A1 (zh) 拍摄装置参数标定方法、设备及存储介质
EP3067860B1 (en) Hybrid depth estimation
US20200267297A1 (en) Image processing method and apparatus
EP3547024B1 (en) Mass production method and system for panorama camera
CN114363522A (zh) 拍照方法及相关装置
CN112598719B (zh) 深度成像系统及其标定方法、深度成像方法、存储介质
WO2022057043A1 (zh) 一种目标跟踪动向投影方法和动向投影设备
WO2021093111A1 (zh) 面向结构光3d视觉系统的全自动标定方法及装置
US20150077583A1 (en) Systems and methods for digital correction of aberrations produced by tilted plane-parallel plates or optical wedges
WO2021145913A1 (en) Estimating depth based on iris size

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: 19952490

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19952490

Country of ref document: EP

Kind code of ref document: A1