WO2018120168A1 - 一种视觉检测方法及系统 - Google Patents

一种视觉检测方法及系统 Download PDF

Info

Publication number
WO2018120168A1
WO2018120168A1 PCT/CN2016/113840 CN2016113840W WO2018120168A1 WO 2018120168 A1 WO2018120168 A1 WO 2018120168A1 CN 2016113840 W CN2016113840 W CN 2016113840W WO 2018120168 A1 WO2018120168 A1 WO 2018120168A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
detection
detected
detecting surface
angle
Prior art date
Application number
PCT/CN2016/113840
Other languages
English (en)
French (fr)
Inventor
阳光
Original Assignee
深圳配天智能技术研究院有限公司
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 深圳配天智能技术研究院有限公司 filed Critical 深圳配天智能技术研究院有限公司
Priority to PCT/CN2016/113840 priority Critical patent/WO2018120168A1/zh
Priority to CN201680038377.3A priority patent/CN107820568A/zh
Publication of WO2018120168A1 publication Critical patent/WO2018120168A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8806—Specially adapted optical and illumination features
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/55—Specular reflectivity
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N2021/8411—Application to online plant, process monitoring
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques

Definitions

  • the present invention relates to the field of visual inspection technologies, and in particular, to a visual inspection method and system.
  • the object of the present invention is to provide a visual detection method and system, which solves the problem that the existing visual inspection requires multiple times of shooting the detection surface in multiple steps, resulting in a long detection time and low efficiency.
  • the present invention provides a visual detection method, including:
  • the collected images are subjected to detection and analysis to obtain analysis results.
  • the detecting and analyzing the collected image comprises:
  • the first detection image and the actual image are respectively detected and analyzed.
  • the determining the current reflection angle of the reflective device comprises:
  • the determining an angle between the plane of the second detecting surface and the first detecting surface includes:
  • a plane angle of the second detecting surface with respect to the first detecting surface is determined by a difference in distance variation of the object to be detected after moving relative to the reflecting device and a difference in movement variation of the object in the mirror.
  • the determining an angle between the plane of the second detecting surface and the first detecting surface includes:
  • An auxiliary light source is disposed, and a plane clip of the second detecting surface relative to the first detecting surface is determined by a difference in distance between the first detecting surface and the second detecting surface light spot of the auxiliary light source angle.
  • the dividing the collected image into the first detected image and the second detected image includes:
  • the object to be detected has a plurality of the second detecting surfaces
  • the reflecting device is a plurality of mirrors respectively corresponding to the second detecting surface.
  • the invention also provides a visual inspection system comprising:
  • a reflecting device a reflecting device, a camera device, and a processing device
  • the object to be detected has a first detecting surface located at a current photographing surface of the image capturing device and a second detecting surface at a certain angle with the first detecting surface;
  • the reflecting device is configured to perform reflection processing on the second detecting surface of the object to be detected, and Converting an image corresponding to the second detecting surface to the current shooting surface;
  • the camera device is configured to collect an image of the current shooting surface
  • the processing device is configured to perform detection analysis on the collected image to obtain an analysis result.
  • the processing device includes:
  • a dividing module configured to divide the collected image into a first detected image and a second detected image; wherein the first detected image corresponds to the first detecting surface, the second detected image and the second The second detection surface corresponds;
  • a plane angle determining module configured to determine a plane angle of the second detecting surface relative to the first detecting surface
  • a reflection angle determining module configured to determine a current reflection angle of the reflective device
  • An actual image determining module configured to determine an actual image of the second detecting surface corresponding to the second detected image according to the plane angle and the current reflection angle;
  • a detecting module configured to perform detection analysis on the first detection image and the actual image, respectively.
  • an identifier line for encoding is disposed on a mirror surface of the reflective device, and the processing device is configured to determine a current reflection angle of the reflective device according to a current length and an initial length of the identification line in the collected image.
  • the method further includes: an auxiliary light source; the processing device is configured to determine the second by a difference between a distance between the light points of the first detecting surface and the second detecting surface of the auxiliary light source The angle of the detection surface with respect to the plane of the first detection surface.
  • the dividing module is specifically configured to: divide the collected image into a first detection image and a second detection image according to a preset position; or match the collected image with a preset template, respectively determine The first detected image and the second detected image.
  • the object to be detected has a plurality of the second detecting surfaces
  • the reflecting device is a plurality of mirrors respectively corresponding to the second detecting surface.
  • the visual inspection method and system provided by the present invention moves the first detection surface of the object to be detected to the current imaging surface of the imaging device; the second detection surface of the object to be detected is reflected by the reflection device, and the second detection surface is correspondingly
  • the image is converted to the current shooting surface; the image of the current shooting surface is collected; the captured image is detected and analyzed to obtain an analysis result.
  • the visual inspection method and system can convert different detection surfaces at a certain angle to the current imaging surface of the imaging device through the reflection device, and can simultaneously detect the detection surfaces of different angles by only shooting the current imaging surface. , greatly reducing the process in the visual inspection process, saving the time required for testing and material resources, and improving the efficiency of visual inspection.
  • FIG. 1 is a flow chart of a specific embodiment of a visual inspection method provided by the present invention.
  • FIG. 2 is a flowchart of a process for detecting and analyzing the collected image in a visual detection method according to an embodiment of the present invention
  • FIG. 3 is a diagram 1 showing an example of determining spatial coordinates of an upper vertex in an embodiment of the present invention
  • FIG. 5 is a diagram showing an example of solving spatial coordinates of any point on the second detecting surface according to an embodiment of the present invention
  • Figure 6 is a schematic diagram of the classical structured light depth solution process.
  • FIG. 7 is a schematic diagram of an angle solution process of a visual detection method according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of another specific embodiment of a visual inspection method provided by the present invention.
  • FIG. 9 is a schematic diagram of an acquired image according to still another specific embodiment of the visual inspection method provided by the present invention.
  • FIG. 10 is a structural block diagram of a visual inspection system according to an embodiment of the present invention.
  • the embodiment of the invention provides a visual detection method, which can convert different detection surfaces at a certain angle to the current imaging surface of the imaging device, and can simultaneously perform detection of different angles on the current imaging surface.
  • the detection greatly reduces the flow in the visual inspection process, saves the time required for testing and material resources, and improves the detection efficiency. The details are described below separately.
  • FIG. 1 is a flow chart of a specific embodiment of a visual detection method provided by the present invention. As shown in FIG. 1, the method can include:
  • Step S101 moving the first detecting surface of the object to be detected to the current shooting surface of the imaging device;
  • the current shooting surface does not refer to a plane in the actual space, but a plane that the camera device can currently capture.
  • Step S102 performing a reflection process on the second detection surface of the object to be detected, and converting the image corresponding to the second detection surface to the current imaging surface;
  • the side information of the entire occlusion or partial occlusion can be reflected by using the reflection device, so that the information of the second detection surface can be collected simultaneously with the information of the second detection surface, so as to achieve one shot at a time.
  • the purpose of light detection is to avoid the workload caused by multiple acquisitions and the increase of detection time.
  • the reflecting device in this embodiment may be specifically a mirror, and may of course be other devices, and is not limited to this one.
  • Step S103 collecting an image of a current shooting surface
  • the image of the current shooting surface is collected by the image capturing device, and the captured image includes an image corresponding to the first detecting surface of the object to be detected, and an image of the second detecting surface that is reflected and displayed on the current shooting surface.
  • Step S104 Perform detection analysis on the collected image to obtain an analysis result.
  • the image corresponding to the first detecting surface and the reflected image of the second detecting surface may be respectively detected and analyzed according to the visual inspection standard, such as defect analysis, to obtain the surface quality of the current object to be detected, Generate the corresponding test results.
  • the visual inspection standard such as defect analysis
  • the visual detection method provided by the present invention moves the first detection surface of the object to be detected to the current imaging surface of the imaging device; the second detection surface of the object to be detected is reflected by the reflection device, and the image corresponding to the second detection surface is Convert to the current shooting surface; collect the image of the current shooting surface; perform detection and analysis on the captured image to obtain the analysis result.
  • different detection surfaces at a certain angle can be converted to the current imaging surface of the imaging device by the reflection device, and the detection surfaces of different angles can be simultaneously realized by only shooting the current imaging surface. The detection greatly reduces the flow in the visual inspection process, saves the time required for testing and material resources, and improves the efficiency of visual inspection.
  • the process of detecting and analyzing the collected images in the visual detection method provided by the embodiments of the present invention is further described in detail below.
  • the process may specifically include:
  • Step S201 The acquired image is divided into a first detection image and a second detection image; wherein the first detection image corresponds to the first detection surface, and the second detection image corresponds to the second detection surface.
  • the dividing process may divide the collected image into a first detection image and a second detection image according to the preset position; the preset position may be set by the user according to the actual situation, because the imaging device, the object to be detected, and the reflection device are In the case where the relative positions are not changed, the image positions of the first detection surface and the second detection surface are correspondingly within a certain range, and thus the first detection image and the second detection image can be distinguished according to the preset position.
  • the image positions corresponding to the first detecting surface and the second detecting surface It also remains relatively unchanged, so the position information of the first detection surface and the second detection surface can be determined in advance. In this way, for the acquired image of the shooting surface, it can be directly determined according to the obtained position information which is the first detecting surface and which is the second detecting surface.
  • Another way of dividing may be: matching the acquired image with a preset template, and determining the first detected image and the second detected image respectively.
  • the preset template may be pre-established image template information, and the first detected image and the second detected image are distinguished by comparing the acquired image with the image template information and matching the captured image with the image template information. When the left part of the acquired image matches the template image of the first detected image, the first detected image can be quickly distinguished.
  • feature extraction may be performed on the first detection image and the second detection image respectively, and image template information is included, where the image template information includes first feature information corresponding to the first detection image and second feature corresponding to the second detection image. information.
  • image template information includes first feature information corresponding to the first detection image and second feature corresponding to the second detection image. information.
  • feature extraction is also performed on the acquired image. After the portion of the image matches the first feature information, the corresponding portion is determined to be the first detected image; and when the portion of the image matches the second feature information, the corresponding portion is determined to be the second detected image.
  • Step S202 determining an angle between the second detecting surface and the plane of the first detecting surface
  • the angle between the plane of the second detecting surface and the plane of the first detecting surface can be obtained according to the existing method of measuring the angle between the two planes. This step can be obtained by real-time measurement.
  • the angle between the plane of the second detecting surface and the plane of the first detecting surface is kept constant, so that the plane angle can be measured in advance, and the plane angle can be directly obtained in this step. The corresponding value does not need to be measured every time. .
  • a specific acquisition manner for determining an angle between the second detection surface and the plane of the first detection surface may be: moving the object to be detected; changing the distance of the object to be detected after moving relative to the reflection device and the movement of the target in the mirror surface Poor, determining the angle between the second detecting surface and the plane of the first detecting surface.
  • the plane angle of the second detecting surface relative to the first detecting surface can be obtained by a two-point straight line equation or a plane equation of a multi-point male surface.
  • FIG. 3 corresponds to an example diagram before moving an object to be detected
  • FIG. 4 corresponds to an example diagram after the object to be detected is moved by an L distance.
  • the process of obtaining the spatial coordinates of the vertices of the B face can be specifically as follows:
  • the apex of the B plane obtained by the camera reflects the light to obtain an angle b, and the linear equation can be known;
  • Another specific acquisition manner may be: setting an auxiliary light source, and determining a plane angle of the second detecting surface relative to the first detecting surface by using a difference between the distances between the light points of the first detecting surface and the second detecting surface of the auxiliary light source .
  • the plane of the second detecting surface relative to the first detecting surface can be obtained by the two-point linear equation or the plane equation of the multi-point male surface. angle. Referring to Fig. 5, the process of solving the spatial coordinates of any point on the second detecting surface in the present embodiment will be described below.
  • the depth of the point can be determined from the incident reference light angle n and its imaging position on the imaging surface.
  • the spatial coordinates of the point After obtaining the depth of the above reference point and combining the xy position of the point (obtained from the calibrated image), the spatial coordinates of the point can be obtained.
  • the plane equation of the collecting surface B can be determined, and the angle between the collecting surface B and the collecting surface A can be further obtained.
  • Step S203 determining a current reflection angle of the reflecting device
  • the current reflection angle of the reflecting device can be determined by a preset setting by the user, for example, when the angle between the first detecting surface and the second detecting surface is 90°, the current reflection of the reflecting device is The angle of incidence is set to 45°.
  • a code can be added to the mirror surface of the reflecting device for calibrating the angle of the reflecting surface of the current mirror. For example, a two-dimensional code can be added at the corners of the mirror.
  • step S202 and step S203 can be reversed, which does not affect the implementation of the present invention.
  • Step S204 Determine an actual image of the second detection surface corresponding to the second detection image according to the plane angle and the current reflection angle.
  • FIG. 7 is an angle solution of the visual detection method according to the embodiment of the present invention. The process diagram is shown, where a is the angle between the side and the ground, and b is the angle between the mirror surface of the reflecting device and the ground. A-b is the angle between the side and the mirror. Due to the symmetry of the specular reflection, the angle between the corresponding image on the side and the mirror is also a-b. In this way, the angle between the image corresponding to the side and the ground can be obtained by the geometric relationship as a-2b.
  • the image of the angle a-2b can be mapped to the plane parallel to the ground or the upper surface by affine transformation, that is, the actual image of the second detection surface is obtained.
  • Step S205 Perform detection analysis on the first detection image and the actual image, respectively.
  • the object to be detected has a plurality of second detecting surfaces
  • the reflecting device is a plurality of mirrors respectively corresponding to the second detecting surface. That is, when the object to be detected has a plurality of side faces, different side faces can be simultaneously reflected to the current photographing surface by a plurality of reflecting devices, thereby simultaneously detecting the plurality of side faces, further reducing the number of detections and improving the detection efficiency.
  • the following object is to be detected as a notebook, and the process of detecting the defects on each side of the notebook by the visual inspection method provided by the present invention is further elaborated.
  • the first detection surface A surface and the second detection surface B surface can be detected by a mirror placed on a detection surface.
  • the angle between the A surface and the B surface is 90°, and the reflection angle of the mirror is 45°.
  • the camera captures the current picture, including the image information corresponding to the A side and the reflected image of the B side. As shown in FIG. 9, the left image is an image corresponding to the side B plane, and the right image is an image corresponding to the A side.
  • the process of calibrating the side image of the notebook after acquiring the image specifically includes:
  • the angle of the front side of the current notebook is calculated by the difference in the distance between the front and back and the difference in the movement of the target in the mirror.
  • the obtained side image is calibrated based on this angle and the position of the area of the reflected image.
  • a mirror can be placed on each side of the notebook to simultaneously acquire images of the four sides, further improving the efficiency of detection.
  • the visual inspection system provided by the embodiment of the present invention is introduced below, and the visual inspection system described below and the visual detection method described above can be referred to each other.
  • FIG. 10 is a schematic diagram of a visual inspection system according to an embodiment of the present invention.
  • the visual inspection system may include:
  • a reflecting device 1 an imaging device 2, and a processing device 3 (not shown);
  • the object to be detected 4 has a first detecting surface on the current imaging surface of the imaging device 2 and a second detecting surface at an angle to the first detecting surface;
  • the side information of the entire occlusion or partial occlusion can be reflected by using the reflection device, so that the information of the second detection surface can be collected simultaneously with the information of the second detection surface, so as to achieve one shot at a time.
  • the purpose of light detection is to avoid the workload caused by multiple acquisitions and the increase of detection time.
  • the reflecting device 1 is configured to reflect the second detecting surface of the object 4 to be detected, and convert the image corresponding to the second detecting surface to the current shooting surface;
  • the reflecting device in this embodiment may be specifically a mirror, and may of course be other devices, and is not limited to this one.
  • the camera device 2 is configured to collect an image of a current shooting surface
  • the image of the current imaging surface is acquired by the imaging device 2, and the acquired image includes an image corresponding to the first detection surface of the object 4 to be detected, and an image of the second detection surface after being reflected.
  • the processing device 3 is configured to perform detection analysis on the acquired image to obtain an analysis result.
  • the image corresponding to the first detecting surface and the reflected image of the second detecting surface may be respectively detected and analyzed according to the visual inspection standard, such as defect analysis, to obtain the surface quality of the current object to be detected, Generate the corresponding test results.
  • the visual inspection standard such as defect analysis
  • the processing device may specifically include:
  • a dividing module configured to divide the collected image into a first detected image and a second detected image; wherein the first detected image corresponds to the first detecting surface, and the second detected image corresponds to the second detecting surface;
  • a plane angle determining module configured to determine a plane angle of the second detecting surface relative to the first detecting surface
  • a reflection angle determining module for determining a current reflection angle of the reflecting device
  • An actual image determining module configured to determine an actual image of the second detecting surface corresponding to the second detected image according to the plane angle and the current reflection angle;
  • the detecting module is configured to perform detection analysis on the first detected image and the actual image respectively.
  • the mirror surface of the reflection device is provided with an identification line for encoding
  • the processing device is configured to determine the current reflection angle of the reflection device according to the current length and the initial length of the identification line in the acquired image.
  • the visual inspection system provided by the present invention may further include: an auxiliary light source; and the processing device is configured to use a difference between the distances between the light points of the first detecting surface and the second detecting surface by the auxiliary light source a value that determines an angle between the second detection surface and a plane of the first detection surface.
  • the dividing module may be specifically configured to: divide the collected image into a first detection image and a second detection image according to the preset position; or The template is matched to determine the first detected image and the second detected image, respectively.
  • the object to be detected has a plurality of second detecting surfaces
  • the reflecting device is a plurality of mirrors respectively corresponding to the second detecting surface
  • the visual inspection system uses an imaging device to capture a first detection surface of an object to be detected, the first detection surface is located on a current imaging surface of the imaging device; and the second detection surface of the object to be detected is reflected by the reflection device, The image corresponding to the second detecting surface is converted to the current shooting surface; the image of the current shooting surface is collected; and the collected image is detected and analyzed.
  • the visual inspection system provided by the invention can convert different detection surfaces at a certain angle to the current imaging surface of the imaging device through the reflection device, and can simultaneously perform detection surfaces of different angles by only shooting the current imaging surface. The detection greatly reduces the flow in the visual inspection process, saves the time required for testing and material resources, and improves the efficiency of visual inspection.
  • the steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented directly in hardware, a software module executed by a processor, or a combination of both.
  • the software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known.

Abstract

一种视觉检测方法及系统，将待检测物体(4)的第一检测面(A)移动至摄像装置(2)的当前拍摄面(S101)；通过反射装置(1)对待检测物体(4)的第二检测面(B)进行反射，将第二检测面(B)对应的图像转换到当前拍摄面(S102)；对当前拍摄面的图像进行采集(S103)；对采集的图像进行检测分析，以得到分析结果(S104)。视觉检测方法及系统，通过反射装置(1)能够将处于一定角度的不同检测面转换到摄像装置(2)的当前拍摄面上，只需对当前拍摄面进行拍摄即可实现对不同角度的检测面同时进行检测，大大减少了视觉检测过程中的流程，节省了检测所需的时间以及物料资源，提高了视觉检测的效率。

Description

一种视觉检测方法及系统 技术领域
本发明涉及视觉检测技术领域，特别是涉及一种视觉检测方法及系统。
背景技术
在流程化工业过程中，很多工序需要进行视觉检测，且在视觉检测过程中，很多情况需要对一个工件的很多面进行检测。若当前只有一台摄像机，则需要变换工件的位置以实现对不同的面进行检测，或者通过改变摄像机的位置以实现对不同的面进行检测，这就需要多次工序进行多次拍摄，增加了检测的流程，导致检测时间增加、效率降低。
发明内容
本发明的目的是提供一种视觉检测方法及系统，以解决现有视觉检测需多次工序多次拍摄检测面而导致检测时间较长、效率较低的问题。
为解决上述技术问题，本发明提供一种视觉检测方法，包括：
将待检测物体的第一检测面移动至摄像装置的当前拍摄面；
对所述待检测物体的第二检测面进行反射处理，以将所述第二检测面对应的图像转换到所述当前拍摄面；
对所述当前拍摄面的图像进行采集；
对采集的所述图像进行检测分析，以得到分析结果。
可选地，所述对采集的所述图像进行检测分析包括：
将采集的所述图像划分为第一检测图像以及第二检测图像；其中，所述第一检测图像与所述第一检测面相对应，所述第二检测图像与所述第二检测面相对应；
确定所述第二检测面相对所述第一检测面的平面夹角；
确定反射装置的当前反射角度；
根据所述平面夹角以及所述当前反射角度，确定所述第二检测图像对 应的第二检测面的实际图像；
分别对所述第一检测图像以及所述实际图像进行检测分析。
可选地，所述确定反射装置的当前反射角度包括：
获取所述反射装置的镜面上用于编码的标识线的当前长度，根据所述当前长度与初始长度确定所述反射装置的当前反射角度。
可选地，所述确定所述第二检测面相对所述第一检测面的平面夹角包括：
移动所述待检测物体；
通过所述待检测物体经移动后相对于所述反射装置的距离变化差以及镜面内目标的移动变化差，确定所述第二检测面相对所述第一检测面的平面夹角。
可选地，所述确定所述第二检测面相对所述第一检测面的平面夹角包括：
设置辅助光源，通过所述辅助光源在所述第一检测面以及所述第二检测面上光点之间距离的差值，确定所述第二检测面相对所述第一检测面的平面夹角。
可选地，所述将采集的所述图像划分为第一检测图像以及第二检测图像包括：
根据预设位置将采集的所述图像划分为第一检测图像以及第二检测图像；
或者将采集的所述图像与预设模板进行匹配，分别确定所述第一检测图像以及所述第二检测图像。
可选地，所述待检测物体具有多个所述第二检测面，所述反射装置为分别与所述第二检测面一一对应的多个反射镜。
本发明还提供了一种视觉检测系统，包括：
反射装置、摄像装置以及处理装置；
其中，待检测物体具有位于所述摄像装置的当前拍摄面的第一检测面以及与所述第一检测面呈一定角度的第二检测面；
所述反射装置用于对所述待检测物体的第二检测面进行反射处理，将 所述第二检测面对应的图像转换到所述当前拍摄面；
所述摄像装置用于对所述当前拍摄面的图像进行采集；
所述处理装置用于对采集的所述图像进行检测分析，以得到分析结果。
可选地，所述处理装置包括：
划分模块，用于将采集的所述图像划分为第一检测图像以及第二检测图像；其中，所述第一检测图像与所述第一检测面相对应，所述第二检测图像与所述第二检测面相对应；
平面夹角确定模块，用于确定所述第二检测面相对所述第一检测面的平面夹角；
反射角度确定模块，用于确定所述反射装置的当前反射角度；
实际图像确定模块，用于根据所述平面夹角以及所述当前反射角度，确定所述第二检测图像对应的第二检测面的实际图像；
检测模块，用于分别对所述第一检测图像以及所述实际图像进行检测分析。
可选地，所述反射装置的镜面上设置有用于编码的标识线，所述处理装置用于根据采集到图像中所述标识线的当前长度与初始长度确定所述反射装置的当前反射角度。
可选地，还包括：辅助光源；所述处理装置用于通过所述辅助光源在所述第一检测面以及所述第二检测面上光点之间距离的差值，确定所述第二检测面相对所述第一检测面的平面夹角。
可选地，所述划分模块具体用于：根据预设位置将采集的所述图像划分为第一检测图像以及第二检测图像；或者将采集的所述图像与预设模板进行匹配，分别确定所述第一检测图像以及所述第二检测图像。
可选地，所述待检测物体具有多个所述第二检测面，所述反射装置为分别与所述第二检测面一一对应的多个反射镜。
本发明所提供的视觉检测方法及系统，将待检测物体的第一检测面移动至摄像装置的当前拍摄面；通过反射装置对待检测物体的第二检测面进行反射，将第二检测面对应的图像转换到当前拍摄面；对当前拍摄面的图像进行采集；对采集的图像进行检测分析，以得到分析结果。本发明所提 供的视觉检测方法及系统，通过反射装置能够将处于一定角度的不同检测面转换到摄像装置的当前拍摄面上，只需对当前拍摄面进行拍摄即可实现对不同角度的检测面同时进行检测，大大减少了视觉检测过程中的流程，节省了检测所需的时间以及物料资源，提高了视觉检测的效率。
附图说明
为了更清楚的说明本发明实施例或现有技术的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单的介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明所提供的视觉检测方法的一种具体实施方式的流程图；
图2为本发明实施例所提供的视觉检测方法中对采集的所述图像进行检测分析的过程流程图；
图3为本发明实施例中确定上顶点的空间坐标的示例图一；
图4为本发明实施例中确定上顶点的空间坐标的示例图二；
图5为本发明实施例求解第二检测面上任一点的空间坐标的示例图；
图6为经典的结构光深度求解过程示意图
图7为本发明实施例所提供的视觉检测方法的角度求解过程示意图；
图8为本发明所提供的视觉检测方法的另一种具体实施方式的示意图；
图9为本发明所提供的视觉检测方法的又一种具体实施方式的采集图像示意图；
图10为本发明实施例提供的视觉检测系统的结构框图。
具体实施方式
为了使本技术领域的人员更好地理解本发明方案，下面结合附图和具体实施方式对本发明作进一步的详细说明。显然，所描述的实施例仅仅是本发明一部分实施例，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，都属于本发明保护的范围。
本发明实施例提供了一种视觉检测方法，能够将处于一定角度的不同检测面转换到摄像装置的当前拍摄面上，只需对当前拍摄面进行拍摄即可实现对不同角度的检测面同时进行检测，大大减少了视觉检测过程中的流程，节省了检测所需的时间以及物料资源，提高了检测效率。以下分别进行详细描述。
请参阅图1，图1为本发明所提供的视觉检测方法的一种具体实施方式的流程图。如图1所示，该方法可以包括：
步骤S101：将待检测物体的第一检测面移动至摄像装置的当前拍摄面；
其中，当前拍摄面并不是指实际空间中的一个平面，而是摄像装置当前可以拍摄到的平面。
步骤S102：对待检测物体的第二检测面进行反射处理，将第二检测面对应的图像转换到当前拍摄面；
需要指出的是，第二检测面与第一检测面之间存在一定的夹角，在当摄像装置对第一检测面进行拍摄时，由于第二检测面与第一检测面之间存在夹角，使得直接对第二检测面进行拍摄时，第二检测面上的信息存在全部或者部分遮挡的问题，导致不能获取得到第二检测面的全部信息。因此，本发明实施例采用反射装置，可以对被全部遮挡或部分遮挡的侧面信息进行反射，以将第二检测面的信息可以与第二检测面的信息同时进行采集，达到快速一次拍摄一次打光检测的目的，避免多次采集带来的工作量以及检测时间的增加。
本实施例中反射装置可以具体为反射镜，当然也可以为其他装置，并不限于这一种。
步骤S103：对当前拍摄面的图像进行采集；
通过摄像装置对当前拍摄面的图像进行采集，采集的图像中包括待检测物体的第一检测面对应的图像，以及第二检测面经反射后呈现在当前拍摄面的图像。
步骤S104：对采集的图像进行检测分析，以得到分析结果。
获取采集的图像后，可以根据视觉检测标准，分别对第一检测面对应的图像以及第二检测面经反射后的图像进行检测分析，如缺陷分析，获取当前待检测物体的表面质量情况，生成相应的检测结果。
本发明所提供的视觉检测方法，将待检测物体的第一检测面移动至摄像装置的当前拍摄面；通过反射装置对待检测物体的第二检测面进行反射，将第二检测面对应的图像转换到当前拍摄面；对当前拍摄面的图像进行采集；对采集的图像进行检测分析，以得到分析结果。本发明所提供的视觉检测方法，通过反射装置能够将处于一定角度的不同检测面转换到摄像装置的当前拍摄面上，只需对当前拍摄面进行拍摄即可实现对不同角度的检测面同时进行检测，大大减少了视觉检测过程中的流程，节省了检测所需的时间以及物料资源，提高了视觉检测的效率。
在上述实施例的基础上，下面对本发明实施例所提供的视觉检测方法中对采集的图像进行检测分析的过程进行进一步详细阐述，请参照图2，该过程可以具体包括：
步骤S201：将采集的图像划分为第一检测图像以及第二检测图像；其中，第一检测图像与第一检测面相对应，第二检测图像与第二检测面相对应。
具体地划分过程可以根据预设位置将采集的图像划分为第一检测图像以及第二检测图像；预设位置可以由用户根据实际情况自行设置，这是由于在摄像装置、待检测物体以及反射装置的相对位置不变的情况下，第一检测面以及第二检测面的图像位置也相应地在一定范围内，因此可以根据预设位置对第一检测图像以及第二检测图像进行区分。
在同一批次的物体视觉检测过程中，待检测物体、摄像装置以及反射装置的相对位置保持不变的情况下，在误差范围之内，第一检测面以及第二检测面对应的图像位置也相对保持不变，因此可以预先确定第一检测面以及第二检测面的位置信息。这样，对于采集到的拍摄面的图像来说，可以根据得到的位置信息直接确定哪个是第一检测面，哪个是第二检测面。 另一种划分的方式可以为：将采集的图像与预设模板进行匹配，分别确定第一检测图像以及第二检测图像。
预设模板可以为预先建立的图像模板信息，通过将采集的图像与图像模板信息进行比较，在采集的图像与图像模板信息匹配的情况下，对第一检测图像以及第二检测图像进行区分。如采集的图像左边部分与第一检测图像的模板图像匹配时，可以快速区分出第一检测图像。
例如，可分别对第一检测图像以及第二检测图像进行特征提取，建立图像模板信息，图像模板信息中包含对应于第一检测图像的第一特征信息以及对应于第二检测图像的第二特征信息。在实时采集到当前拍摄面的图像后，对采集到的图像同样进行特征提取。当图像中的部分与第一特征信息相匹配后，确定对应的部分为第一检测图像；当图像中的部分与第二特征信息相匹配后，确定对应的部分为第二检测图像。
步骤S202：确定第二检测面相对第一检测面的平面夹角；
第二检测面相对第一检测面的平面夹角可以根据现有的测量两个平面的夹角的方法获取得到。本步骤可以通过实时测量获取得到。当然，在对某一特定的待检测物体进行检测时，第二检测面相对于第一检测面的平面夹角保持恒定，因此可以预先测量得到平面夹角，本步骤中可以直接获取该平面夹角对应的数值，无需每次都进行测量。。
一种确定第二检测面相对第一检测面的平面夹角的具体获取方式可以为：移动待检测物体；通过待检测物体经移动后相对于反射装置的距离变化差以及镜面内目标的移动变化差，确定第二检测面相对第一检测面的平面夹角。
通过计算第二检测面上两个或多个点的空间坐标，通过两点直线方程或者多点公面的平面方程，即可求得第二检测面相对第一检测面的平面夹角。
两个点可以具体选定为第二检测面的上顶点以及下顶点。参照图3以及图4，下面以第二检测面(采集面B)的上顶点为例，确定上顶点的空间坐标，其他点的求取过程同理，在此不再赘述。图3对应移动待检测物体前的示例图，图4对应将待检测物体移动L距离后的示例图。
求取B面顶点的空间坐标的过程可以具体为：
由角度a以及平面上可标定的已知空间点P确定反射面的平面方程；
由相机得到的B面的顶点反射光求角度b，并可知该直线方程；
由相机得到的B面的顶点反射光直线方程以及反射面平面方程求公共解(交点)C；
由a得到反射面的法线，由b以及该法线得到B面顶点到C的角度或该直线的斜率K；
通过移动待检测物体，得到移位后另一组C’以及K’，并且可以通过图像知道待检测物理的移动位移量L；
将C’(K’)对应的直线反向移位L，得到新的方程，该方程与C(K)对应的方程的交点，即为B面上顶点的空间坐标。
另一种具体获取方式可以为：设置辅助光源，通过辅助光源在第一检测面以及第二检测面上光点之间距离的差值，确定第二检测面相对第一检测面的平面夹角。
同理，通过计算第二检测面上两个或多个点的空间坐标，通过两点直线方程或者多点公面的平面方程，即可求得第二检测面相对第一检测面的平面夹角。参照图5，下面对本实施例求解第二检测面上任一点的空间坐标的过程进行介绍。
根据入射参考光角度n以及其在成像面的成像位置，可以求得该点的深度。具体求解过程可以参照图6经典的结构光深度求解过程示意图所示，由图中的几何关系可以得到，d’＝tan(a2)*z1，d’＝tan(a1)*z2，z1+z2＝z；由这几个公式可以推导出深度d’＝z*tan(a2)*tan(a1)/[tan(a2)+tan(a1)]。
得到上述参考点的深度后再结合该点的xy位置(由标定过的图像获得)，即可得到该点的空间坐标。
根据两个或多个上述的参考点即可确定采集面B的平面方程，即可进一步得到采集面B与采集面A的夹角。
步骤S203：确定反射装置的当前反射角度；
具体地，反射装置的当前反射角度可以通过用户预先设置进行确定，例如在第一检测面与第二检测面之间夹角为90°时，将反射装置的当前反 射角度设置为45°。
另外，若反射装置的当前反射角度可随时调整变化时，可以在反射装置的镜面上增加编码，用于标定当前反射镜的反射面角度。例如，可以在镜面的边角处增加一个二维码。通过获取反射装置的镜面上用于编码的标识线的当前长度，根据当前长度与初始长度的对比，即可确定反射装置的当前反射角度。
需要指出的是，步骤S202以及步骤S203的顺序可以调换，这均不影响本发明的实现。
步骤S204：根据平面夹角以及当前反射角度，确定第二检测图像对应的第二检测面的实际图像；请一并参照图7，图7为本发明实施例所提供的视觉检测方法的角度求解过程示意图所示，其中，a为侧面与地面的夹角，b为反射装置的镜面与地面的夹角。a-b为侧面与镜面的夹角，由于镜面反射的对称性，侧面对应的像与镜面之间的夹角也为a-b。这样，由几何关系可以得到侧面对应的像与地面的夹角为a-2b。
在得到a-2b的数值后，可以通过仿射变换将a-2b这个角度的图像对应到地面或上表面平行的平面上，即得到第二检测面的实际图像。
步骤S205：分别对第一检测图像以及实际图像进行检测分析。
在上述任一实施例的基础上，本发明实施例所提供的检测方法中，待检测物体具有多个第二检测面，反射装置为分别与第二检测面一一对应的多个反射镜。即，在待检测物体具有多个侧面时，可以通过多个反射装置将不同的侧面同时反射至当前拍摄面上，从而对多个侧面进行同时检测，进一步降低检测次数，提高检测效率。
请参照图8，下面待检测物体为笔记本为例，对本发明所提供的视觉检测方法的具体对笔记本每个面的缺陷进行检测的过程进行进一步详细阐述。
将其第一检测面A面和第二检测面B面可通过反光镜放置在一个检测面检测。本实施例中，A面与B面的夹角为90°，反射镜的反射角度为45°。摄像机拍摄当前画面，包括A面对应的图像信息以及B面经反射后的图像 信息，如图9所示，左边图像为侧面B面对应的图像，右边图像为A面对应的图像。
采集到图像后标定笔记本侧面图像的过程具体包括：
首先对编码进行标定，获得当前镜面的角度。
然后移动笔记本，检测经过移动后的镜面与笔记本相对距离。通过前后的距离变化差及镜面内目标的移动变化差，计算当前笔记本侧面相对正面的角度。根据这个角度及反射图像的区域位置对获得的侧面图像进行标定。
在流程化处理时，有可能镜面与笔记本侧面的距离不能保持稳定一致的距离，存在一定的偏差。所以，通过对镜面目标及笔记本正面目标的查找可估算反射的侧面出现区域，可提高查找的效率。
在此过程中，可以在笔记本的四个侧面均设置一个反射镜，以同时对四个侧面的图像进行获取，进一步提高检测的效率。
下面对本发明实施例提供的视觉检测系统进行介绍，下文描述的视觉检测系统与上文描述的视觉检测方法可相互对应参照。
图10为本发明实施例提供的视觉检测系统的示意图，参照图10视觉检测系统可以包括：
反射装置1、摄像装置2以及处理装置3(图中未示出)；
其中，待检测物体4具有位于摄像装置2的当前拍摄面的第一检测面以及与第一检测面呈一定角度的第二检测面；
需要指出的是，第二检测面与第一检测面之间存在一定的夹角，在当摄像装置对第一检测面进行拍摄时，由于第二检测面与第一检测面之间存在夹角，使得直接对第二检测面进行拍摄时，第二检测面上的信息存在全部或者部分遮挡的问题，导致不能获取得到第二检测面的全部信息。因此，本发明实施例采用反射装置，可以对被全部遮挡或部分遮挡的侧面信息进行反射，以将第二检测面的信息可以与第二检测面的信息同时进行采集，达到快速一次拍摄一次打光检测的目的，避免多次采集带来的工作量以及检测时间的增加。
反射装置1用于对待检测物体4的第二检测面进行反射，将第二检测面对应的图像转换到当前拍摄面；
本实施例中反射装置可以具体为反射镜，当然也可以为其他装置，并不限于这一种。
摄像装置2用于对当前拍摄面的图像进行采集；
通过摄像装置2对当前拍摄面的图像进行采集，采集的图像中包括待检测物体4的第一检测面对应的图像，以及第二检测面经反射后的图像。
处理装置3用于对采集的图像进行检测分析，以得到分析结果。
获取采集的图像后，可以根据视觉检测标准，分别对第一检测面对应的图像以及第二检测面经反射后的图像进行检测分析，如缺陷分析，获取当前待检测物体的表面质量情况，生成相应的检测结果。
在上述实施例的基础上，本发明所提供的视觉检测系统中，处理装置可以具体包括：
划分模块，用于将采集的图像划分为第一检测图像以及第二检测图像；其中，第一检测图像与第一检测面相对应，第二检测图像与第二检测面相对应；
平面夹角确定模块，用于确定第二检测面相对第一检测面的平面夹角；
反射角度确定模块，用于确定反射装置的当前反射角度；
实际图像确定模块，用于根据平面夹角以及当前反射角度，确定第二检测图像对应的第二检测面的实际图像；
检测模块，用于分别对第一检测图像以及实际图像进行检测分析。
本发明所提供的视觉检测系统中，反射装置的镜面上设置有用于编码的标识线，处理装置用于根据采集到图像中标识线的当前长度与初始长度确定反射装置的当前反射角度。
在上述任一实施例的基础上，本发明所提供的视觉检测系统还可以包括：辅助光源；处理装置用于通过辅助光源在第一检测面以及第二检测面上光点之间距离的差值，确定第二检测面相对第一检测面的平面夹角。
作为一种具体实施方式，划分模块可以具体用于：根据预设位置将采集的图像划分为第一检测图像以及第二检测图像；或者将采集的图像与预 设模板进行匹配，分别确定第一检测图像以及第二检测图像。
在上述任一实施例的基础上，本发明所提供的视觉检测系统中，待检测物体具有多个第二检测面，反射装置为分别与第二检测面一一对应的多个反射镜。
本发明所提供的视觉检测系统，采用摄像装置对待检测物体的第一检测面进行拍摄，第一检测面位于摄像装置的当前拍摄面；通过反射装置对待检测物体的第二检测面进行反射，将第二检测面对应的图像转换到当前拍摄面；对当前拍摄面的图像进行采集；对采集的图像进行检测分析。本发明所提供的视觉检测系统，通过反射装置能够将处于一定角度的不同检测面转换到摄像装置的当前拍摄面上，只需对当前拍摄面进行拍摄即可实现对不同角度的检测面同时进行检测，大大减少了视觉检测过程中的流程，节省了检测所需的时间以及物料资源，提高了视觉检测的效率。
本说明书中各个实施例采用递进的方式描述，每个实施例重点说明的都是与其它实施例的不同之处，各个实施例之间相同或相似部分互相参见即可。对于实施例公开的装置而言，由于其与实施例公开的方法相对应，所以描述的比较简单，相关之处参见方法部分说明即可。
专业人员还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
结合本文中所公开的实施例描述的方法或算法的步骤可以直接用硬件、处理器执行的软件模块，或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。
以上对本发明所提供的视觉检测方法以及系统进行了详细介绍。本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想。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，还可以对本发明进行若干改进和修饰，这些改进和修饰也落入本发明权利要求的保护范围内。

Claims (13)

  1. 一种视觉检测方法，其特征在于，包括：
    将待检测物体的第一检测面移动至摄像装置的当前拍摄面；
    对所述待检测物体的第二检测面进行反射处理，以将所述第二检测面对应的图像转换到所述当前拍摄面；
    对所述当前拍摄面的图像进行采集；
    对采集的所述图像进行检测分析，以得到分析结果。
  2. 如权利要求1所述的视觉检测方法，其特征在于，所述对采集的所述图像进行检测分析，包括：
    将采集的所述图像划分为第一检测图像以及第二检测图像；其中，所述第一检测图像与所述第一检测面相对应，所述第二检测图像与所述第二检测面相对应；
    确定所述第二检测面相对所述第一检测面的平面夹角；
    确定反射装置的当前反射角度；
    根据所述平面夹角以及所述当前反射角度，确定所述第二检测图像对应的第二检测面的实际图像；
    分别对所述第一检测图像以及所述实际图像进行检测分析。
  3. 如权利要求2所述的视觉检测方法，其特征在于，所述确定反射装置的当前反射角度，包括：
    获取所述反射装置的镜面上用于编码的标识线的当前长度，根据所述当前长度与初始长度确定所述反射装置的当前反射角度。
  4. 如权利要求2所述的视觉检测方法，其特征在于，所述确定所述第二检测面相对所述第一检测面的平面夹角包括：
    移动所述待检测物体；
    通过所述待检测物体经移动后相对于所述反射装置的距离变化差以及镜面内目标的移动变化差，确定所述第二检测面相对所述第一检测面的平面夹角。
  5. 如权利要求2所述的视觉检测方法，其特征在于，所述确定所述第二检测面相对所述第一检测面的平面夹角包括：
    设置辅助光源，通过所述辅助光源在所述第一检测面以及所述第二检测面上光点之间距离的差值，确定所述第二检测面相对所述第一检测面的平面夹角。
  6. 如权利要求2至5任一项所述的视觉检测方法，其特征在于，所述将采集的所述图像划分为第一检测图像以及第二检测图像包括：
    根据预设位置将采集的所述图像划分为第一检测图像以及第二检测图像；
    或者将采集的所述图像与预设模板进行匹配，分别确定所述第一检测图像以及所述第二检测图像。
  7. 如权利要求6所述的视觉检测方法，其特征在于，所述待检测物体具有多个所述第二检测面，所述反射装置为分别与所述第二检测面一一对应的多个反射镜。
  8. 一种视觉检测系统，其特征在于，包括：
    反射装置、摄像装置以及处理装置；
    其中，待检测物体具有位于所述摄像装置的当前拍摄面的第一检测面以及与所述第一检测面呈一定角度的第二检测面；
    所述反射装置用于对所述待检测物体的第二检测面进行反射处理，将所述第二检测面对应的图像转换到所述当前拍摄面；
    所述摄像装置用于对所述当前拍摄面的图像进行采集；
    所述处理装置用于对采集的所述图像进行检测分析，以得到分析结果。
  9. 如权利要求8所述的视觉检测系统，其特征在于，所述处理装置包括：
    划分模块，用于将采集的所述图像划分为第一检测图像以及第二检测图像；其中，所述第一检测图像与所述第一检测面相对应，所述第二检测图像与所述第二检测面相对应；
    平面夹角确定模块，用于确定所述第二检测面相对所述第一检测面的平面夹角；
    反射角度确定模块，用于确定所述反射装置的当前反射角度；
    实际图像确定模块，用于根据所述平面夹角以及所述当前反射角度， 确定所述第二检测图像对应的第二检测面的实际图像；
    检测模块，用于分别对所述第一检测图像以及所述实际图像进行检测分析。
  10. 如权利要求9所述的视觉检测系统，其特征在于，所述反射装置的镜面上设置有用于编码的标识线，所述处理装置用于根据采集到图像中所述标识线的当前长度与初始长度确定所述反射装置的当前反射角度。
  11. 如权利要求9所述的视觉检测系统，其特征在于，还包括：辅助光源；所述处理装置用于通过所述辅助光源在所述第一检测面以及所述第二检测面上光点之间距离的差值，确定所述第二检测面相对所述第一检测面的平面夹角。
  12. 如权利要求9所述的视觉检测系统，其特征在于，所述划分模块具体用于：根据预设位置将采集的所述图像划分为第一检测图像以及第二检测图像；或者将采集的所述图像与预设模板进行匹配，分别确定所述第一检测图像以及所述第二检测图像。
  13. 如权利要求8至12任一项所述的视觉检测系统，其特征在于，所述待检测物体具有多个所述第二检测面，所述反射装置为分别与所述第二检测面一一对应的多个反射镜。
PCT/CN2016/113840 2016-12-30 2016-12-30 一种视觉检测方法及系统 WO2018120168A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2016/113840 WO2018120168A1 (zh) 2016-12-30 2016-12-30 一种视觉检测方法及系统
CN201680038377.3A CN107820568A (zh) 2016-12-30 2016-12-30 一种视觉检测方法及系统

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/113840 WO2018120168A1 (zh) 2016-12-30 2016-12-30 一种视觉检测方法及系统

Publications (1)

Publication Number Publication Date
WO2018120168A1 true WO2018120168A1 (zh) 2018-07-05

Family

ID=61600540

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/113840 WO2018120168A1 (zh) 2016-12-30 2016-12-30 一种视觉检测方法及系统

Country Status (2)

Country Link
CN (1) CN107820568A (zh)
WO (1) WO2018120168A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110595361A (zh) * 2019-09-27 2019-12-20 上海悦易网络信息技术有限公司 图像采集装置及图像检测设备
CN110657762A (zh) * 2019-09-25 2020-01-07 天津百利泰为科技有限公司 一种视觉检测片状物平整度系统的图像获取装置及方法
CN112710231A (zh) * 2020-12-15 2021-04-27 苏州光测视界智能科技有限公司 发光键盘的视觉检测系统和检测方法

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111150402A (zh) * 2020-01-02 2020-05-15 秒针信息技术有限公司 确定家畜形体参数的方法、装置、存储介质及电子装置
CN113513993B (zh) * 2021-05-14 2023-03-14 国网宁夏电力有限公司电力科学研究院 一种变压器绕组运动位移的测量方法、介质及系统
CN114138023A (zh) * 2021-11-30 2022-03-04 广东电网有限责任公司 一种变电站无人机自动巡检系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201641973U (zh) * 2009-02-19 2010-11-24 广州中科恺盛医疗科技有限公司 多角度成像装置
JP2010276433A (ja) * 2009-05-28 2010-12-09 Tokyo Institute Of Technology 撮像装置、画像処理装置及び距離計測装置
CN102928431A (zh) * 2012-10-24 2013-02-13 浙江工业大学 基于单目多视角机器视觉的珍珠大小形状在线自动分级装置
CN103063134A (zh) * 2012-12-26 2013-04-24 浙江大学 碎石几何特征采集系统及采集方法
CN103286081A (zh) * 2013-05-07 2013-09-11 浙江工业大学 基于单目多视角机器视觉的钢珠表面缺陷在线自动分选装置
JP2015105995A (ja) * 2013-11-29 2015-06-08 株式会社ニコン 反射ユニットおよび撮像装置
CN106226316A (zh) * 2016-08-31 2016-12-14 江苏大学 一种单摄像机宽视场视觉螺纹检测装置及其检测方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101949866B (zh) * 2010-09-01 2012-02-01 厦门大学 用于包装检测的单相机全向视觉传感器
CN102243185A (zh) * 2011-04-25 2011-11-16 苏州大学 一种多面成像测量装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201641973U (zh) * 2009-02-19 2010-11-24 广州中科恺盛医疗科技有限公司 多角度成像装置
JP2010276433A (ja) * 2009-05-28 2010-12-09 Tokyo Institute Of Technology 撮像装置、画像処理装置及び距離計測装置
CN102928431A (zh) * 2012-10-24 2013-02-13 浙江工业大学 基于单目多视角机器视觉的珍珠大小形状在线自动分级装置
CN103063134A (zh) * 2012-12-26 2013-04-24 浙江大学 碎石几何特征采集系统及采集方法
CN103286081A (zh) * 2013-05-07 2013-09-11 浙江工业大学 基于单目多视角机器视觉的钢珠表面缺陷在线自动分选装置
JP2015105995A (ja) * 2013-11-29 2015-06-08 株式会社ニコン 反射ユニットおよび撮像装置
CN106226316A (zh) * 2016-08-31 2016-12-14 江苏大学 一种单摄像机宽视场视觉螺纹检测装置及其检测方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110657762A (zh) * 2019-09-25 2020-01-07 天津百利泰为科技有限公司 一种视觉检测片状物平整度系统的图像获取装置及方法
CN110595361A (zh) * 2019-09-27 2019-12-20 上海悦易网络信息技术有限公司 图像采集装置及图像检测设备
CN112710231A (zh) * 2020-12-15 2021-04-27 苏州光测视界智能科技有限公司 发光键盘的视觉检测系统和检测方法

Also Published As

Publication number Publication date
CN107820568A (zh) 2018-03-20

Similar Documents

Publication Publication Date Title
WO2018120168A1 (zh) 一种视觉检测方法及系统
JP4896373B2 (ja) 立体３次元計測システムおよび方法
EP2339292A1 (en) Three-dimensional measurement apparatus and method thereof
JP6596433B2 (ja) ２つのカメラからの曲線の集合の構造化光整合
US10719740B2 (en) Method and a system for identifying reflective surfaces in a scene
JP2005514606A5 (zh)
CN108513121B (zh) 用于场景的景深图评估的方法和设备
JP2008039767A (ja) 反射性物体の表面の形状を検知する方法及びシステム
US8582824B2 (en) Cell feature extraction and labeling thereof
JP6282377B2 (ja) ３次元形状計測システムおよびその計測方法
CN111353997B (zh) 一种基于条纹投影的实时三维面型缺陷检测方法
TWI428569B (zh) 測距方法、測距系統與其處理軟體
US10462444B2 (en) Three-dimensional inspection
JP6580761B1 (ja) 偏光ステレオカメラによる深度取得装置及びその方法
US20220092345A1 (en) Detecting displacements and/or defects in a point cloud using cluster-based cloud-to-cloud comparison
CN106840035B (zh) 建立物件轮廓影像的扫描装置及方法
Xiao et al. A new three-dimensional laser scanner design and its performance analysis
TW201317587A (zh) 尺寸檢測裝置及方法
JP6550102B2 (ja) 光源方向推定装置
CN107084990B (zh) 一种单目视觉方钢管混凝土柱三面检测装置及检测方法
Randil et al. 3D Full-Field Deformation Measuring Technique with Optics-Based Measurements
KR20200032664A (ko) 사각형 그리드 투영을 이용한 3차원 영상 재구성 장치
TWI604261B (zh) 一種多維視覺圖像的獲取方法及系統
Khosravani et al. Coregistration of kinect point clouds based on image and object space observations
WO2023109960A1 (zh) 三维扫描的处理方法、装置和三维扫描设备

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: 16925883

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: 16925883

Country of ref document: EP

Kind code of ref document: A1