CN111906043B - Pose detection method and system - Google Patents
Pose detection method and system Download PDFInfo
- Publication number
- CN111906043B CN111906043B CN202010686564.0A CN202010686564A CN111906043B CN 111906043 B CN111906043 B CN 111906043B CN 202010686564 A CN202010686564 A CN 202010686564A CN 111906043 B CN111906043 B CN 111906043B
- Authority
- CN
- China
- Prior art keywords
- detected
- dimensional
- information
- detection
- position information
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/04—Sorting according to size
- B07C5/10—Sorting according to size measured by light-responsive means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L22/00—Testing or measuring during manufacture or treatment; Reliability measurements, i.e. testing of parts without further processing to modify the parts as such; Structural arrangements therefor
- H01L22/10—Measuring as part of the manufacturing process
- H01L22/12—Measuring as part of the manufacturing process for structural parameters, e.g. thickness, line width, refractive index, temperature, warp, bond strength, defects, optical inspection, electrical measurement of structural dimensions, metallurgic measurement of diffusions
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Power Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a pose detection method and a pose detection system. The pose detection method comprises the following steps: detecting an element to be detected and generating a detection signal; triggering a two-dimensional detection device through the detection signal and detecting the position information and the posture information of the element to be detected; measuring the three-dimensional information of the element to be detected; judging whether the element to be detected is a bad element according to the posture information and the three-dimensional information, and generating position information of the bad element; and removing the bad elements according to the position information of the bad elements. The pose detection method effectively detects whether the semiconductor device meets the standard or not by detecting the parameters of the surface of the semiconductor device.
Description
Technical Field
The invention relates to the technical field of pose detection, in particular to a pose detection method and a pose detection system.
Background
In the manufacturing process of the semiconductor component, the semiconductor component is detected through the traditional two-dimensional machine vision so as to determine whether the component parameters meet the preset standard.
In the related art, the two-dimensional AOI detection equipment is used for analyzing the plane characteristics of the semiconductor device, and the space coordinate information of an object cannot be accurately acquired so as to measure parameters such as the flatness, the height difference and the bending degree of the semiconductor device.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a pose detection method which can effectively detect whether a semiconductor device meets the standard and quickly eliminate bad elements by detecting the parameters of the surface of the semiconductor device.
The invention further provides a pose detection system.
According to a first aspect embodiment of the present invention, a pose detection method includes:
detecting an element to be detected and generating a detection signal; triggering a two-dimensional detection device through the detection signal and detecting the position information and the posture information of the element to be detected; detecting the three-dimensional information of the element to be detected;
judging whether the element to be detected is a bad element or not according to the posture information and the three-dimensional information, and generating position information of the bad element; and removing the bad elements according to the position information of the bad elements.
The pose detection method provided by the embodiment of the invention at least has the following beneficial effects: by detecting the parameters of the surface of the semiconductor device, whether the semiconductor device meets the standard or not is effectively detected.
According to some embodiments of the present invention, the position of the three-dimensional detection device is adjusted according to the position information to detect the stereoscopic information of the element to be detected.
According to some embodiments of the invention, further comprising: the three-dimensional detection device detects the element to be detected and generates first plane point cloud data; extracting a plane correction matrix according to the first plane point cloud data; and carrying out plane correction on the first plane point cloud data through the plane correction matrix and generating second plane point cloud data.
According to some embodiments of the invention, a binary grayscale image is generated from the second planar point cloud data; performing region division on the binary gray level image to generate a plurality of single connected regions; traversing and analyzing the single connected regions and generating a deviation value of each single connected region; and comparing the deviation value with a preset threshold value to judge whether the element to be detected is a bad element.
According to some embodiments of the invention, the preset threshold comprises: a first coordinate error threshold, a second coordinate error threshold, an angle error threshold.
A pose detection system according to an embodiment of a second aspect of the present invention includes: the trigger sensor is used for detecting the element to be detected and generating a detection signal; the two-dimensional detection device receives the detection signal and detects the position information and the posture information of the element to be detected; the three-dimensional detection device is used for detecting the three-dimensional information of the element to be detected; the attitude analyzer is used for judging whether the element to be detected is a bad element or not according to the attitude information and the three-dimensional information and generating position information of the bad element; and the rejecting device rejects the defective element according to the position information of the defective element.
The pose detection system provided by the embodiment of the invention at least has the following beneficial effects: parameters such as flatness, height difference and curvature of the surface of the semiconductor device are detected, so that whether the semiconductor device meets the standard or not is effectively detected, and bad elements are quickly removed.
According to some embodiments of the invention, the two-dimensional detection device comprises: an annular light source for providing an illumination source; and the two-dimensional camera is used for acquiring the position information and the posture information of the element to be detected.
According to some embodiments of the invention, the three-dimensional inspection device comprises: the laser module is used for providing a detection light beam, and the detection light beam irradiates the surface of the element to be detected and is reflected; a three-dimensional camera for receiving the reflected detection beam; and the bracket is used for fixing the relative position of the laser module and the three-dimensional camera.
According to some embodiments of the invention, the three-dimensional inspection device further comprises: the first axial driving device is used for driving the three-dimensional detection device to move along a first axial direction; the second axial driving device is used for driving the three-dimensional detection device to move along the second axial direction; and the encoder is used for synchronously scanning data of the device to be detected.
According to some embodiments of the invention, the rejection device comprises: and the mechanical arm is used for positioning and removing the bad elements according to the position information of the bad elements.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a pose detection method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a pose detection system according to an embodiment of the present invention;
FIG. 3 is an enlarged partial view of portion A of FIG. 2;
fig. 4 is a partially enlarged schematic view of a portion B of fig. 2.
Reference numerals: 100. an element to be detected; 101. a trigger sensor; 200. a two-dimensional detection device; 201. a two-dimensional camera; 202. an annular light source; 300. a three-dimensional detection device; 301. a laser module; 302. a support; 303. a three-dimensional camera; 400. a rejecting device; 501. a first axial drive; 502. a second axial drive; 503. an encoder.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
The embodiment of the invention provides a pose detection method and a pose detection system, which can effectively detect whether a semiconductor device meets the standard or not by detecting parameters such as flatness, height difference, curvature and the like of the surface of the semiconductor device.
Referring to fig. 1, a pose detection method includes: step S100, detecting the element to be detected 100 through the trigger sensor 101 and generating a detection signal; step S200, triggering the two-dimensional detection device 200 through the detection signal and detecting the position information and the attitude information of the element to be detected 100; step S300, detecting the three-dimensional information of the element to be detected 100 through the three-dimensional detection device 300; step S400, the attitude analyzer judges whether the element 100 to be detected is a bad element according to the attitude information and the three-dimensional information, and transmits the position information of the bad element to the rejecting device 400; step S500, the rejecting device 400 rejects the defective component according to the position information of the defective component.
For example, the presence or absence of the component 100 to be detected on the conveyance path is detected by the trigger sensor 101 to generate a detection signal correspondingly. When the element 100 to be detected does not exist on the conveying path, the two-dimensional detection device 200 receives the detection signal and maintains a standby state; when the component 100 to be detected exists on the conveyance path, the two-dimensional detection device 200 receives the detection signal and enters a detection state to acquire position information and posture information of the component 100 to be detected, and transmits the posture information to the posture analyzer. The three-dimensional detection device 300 detects the three-dimensional information of the element 100 to be detected and transmits the three-dimensional information to the attitude analyzer, the attitude analyzer generates actual parameters of the element 100 to be detected according to the attitude information and the three-dimensional information, judges whether the element 100 to be detected is a defective element by comparing the actual parameters with preset reference parameters, and generates position information of the defective element. The rejecting device 400 rejects the defective components according to the position information of the defective components, so as to rapidly reject the defective components in the components 100 to be detected.
Wherein the actual parameters include at least: actual flatness, actual height difference and actual bending of the element; the preset reference parameters at least comprise: the method comprises the steps of presetting flatness, presetting height difference and presetting bending of elements.
The trigger sensor 101 may be a photoelectric switch sensor or a proximity switch sensor. The photoelectric switch sensor includes: an NPN type photoelectric switch sensor and a PNP type photoelectric switch sensor; the proximity switch sensor includes: NPN type proximity switch sensors and PNP type proximity switch sensors.
In some embodiments, the trigger sensor 101 is an NPN-type photoelectric switch sensor or an NPN-type proximity switch sensor.
When the element 100 to be detected does not exist on the transmission path, the NPN-type photoelectric switch sensor or the NPN-type proximity switch sensor outputs a low-level signal; when the element 100 to be detected is present on the transmission path, the NPN-type photoelectric switch sensor or the NPN-type proximity switch sensor outputs a high-level signal. The two-dimensional detection device 200 switches the two-dimensional detection device 200 to a standby state or a detection state by determining whether the detection signal is a low level signal or a high level signal. The operating state of the two-dimensional inspection device 200 is switched by detecting whether or not the component 100 to be inspected exists on the conveyance path, thereby preventing the two-dimensional inspection device 200 from being in the operating state for a long time without the component to be inspected. I.e. by automatically switching the operating state of the two-dimensional detection device 200, to reduce power consumption.
In some embodiments, the trigger sensor 101 is a PNP-type photoelectric switch sensor or a PNP-type proximity switch sensor.
When the element 100 to be detected does not exist on the transmission path, the PNP type photoelectric switch sensor or the PNP type proximity switch sensor outputs a high level signal; when the element 100 to be detected exists on the transmission path, the PNP type photoelectric switch sensor or the PNP type proximity switch sensor outputs a low level signal. The operating state of the two-dimensional inspection device 200 is switched by detecting whether or not the component 100 to be inspected exists on the conveyance path, thereby preventing the two-dimensional inspection device 200 from being in the operating state for a long time without the component to be inspected. I.e. by automatically switching the operating state of the two-dimensional detection device 200, to reduce power consumption.
In some embodiments, the pose detection method further includes: step S201, adjusting the position of the three-dimensional detection device 300 according to the position information to detect the three-dimensional information of the element 100 to be detected.
The position of the device to be detected on the conveying path is detected by the two-dimensional detection device 200 and corresponding position information is generated, and the three-dimensional detection device 300 receives the position information and adjusts the position of the three-dimensional detection device 300 according to the position information.
For example, the placement positions of the devices to be detected on the conveying path are irregular curves, the specific positions of the devices to be detected are detected by the two-dimensional detection device 200, position information is generated, and the detection path of the three-dimensional detection device 300 is generated according to the position information.
The position of the three-dimensional inspection device 300 is adjusted according to the inspection path. For example, the relative position of the three-dimensional inspection device 300 is adjusted by the axial driving device, so that the device to be inspected is completely within the inspection range of the three-dimensional inspection device 300, thereby avoiding the condition of missing inspection or error inspection.
In some embodiments, the pose detection method further includes: step S301, detecting the element to be detected 100 by the three-dimensional detection device 300 and generating first plane point cloud data; step S302, extracting a plane correction matrix according to the first plane point cloud data; and carrying out plane correction on the first plane point cloud data through the plane correction matrix and generating second plane point cloud data.
For example, the element to be inspected 100 is inspected by the three-dimensional inspection device 300, and first plane point cloud data is generated with reference to the initial coordinate system. And acquiring a flag bit variable through the first plane point cloud data to judge whether the element 100 to be detected of the current type is primarily detected. If the element 100 to be detected of the current type is detected for the first time, extracting a plane correction matrix from the first plane point cloud data; if the current type of element 100 to be detected is not the primary detection, the corresponding planar rectification matrix is obtained from the system. And carrying out plane correction processing on the first plane point cloud data through the plane correction matrix, and generating second plane point cloud data. For example, the first plane point cloud data is subjected to coordinate system conversion by the plane rectification matrix and the second plane point cloud data is generated.
For example, the three-dimensional inspection device 300 inspects the element 100 to be inspected to obtain the first plane point cloud data Pn[xn，yn，zn]And the coordinate system of the first plane point cloud data is XYZ.
Wherein x isnIs the first plane point cloud data PnPosition on the X-axis, ynIs the first plane point cloud data PnPosition on the Y axis, znIs the first plane point cloud data PnPosition on the Z axis, i.e. height value.
The three-dimensional inspection device 300 performs inspection on the element to be inspected 100And detecting and collecting a three-dimensional image, and judging whether the element 100 to be detected of the current type is primarily detected or not through the flag bit variable FT. If the flag bit variable FT is 0, the current type of element to be detected 100 is subjected to primary detection, a correction matrix of a first plane point cloud data plane with the same height is extracted, and the plane correction matrix is encoded and stored in a memory; if the flag variable FT is 1, the current type of element 100 to be detected is non-primary detection, and a corresponding plane correction matrix is obtained from the system. Performing plane correction processing on the first plane point cloud data through the plane correction matrix to perform coordinate system conversion and generate second plane point cloud data Pn’[xn’，yn’，zn’]。
And carrying out plane correction processing on the first plane point cloud data through the plane correction matrix so as to eliminate the influence of the height difference formed by uneven placement of the element 100 to be detected on the detection result. For example, the element 100 to be detected is placed unevenly and forms a certain height difference, a binary gray image is generated from the first plane point cloud data, the binary gray image is divided, and the deviation value is calculated. Due to the fact that the height difference generated by uneven placement causes a large error value in the deviation value, qualified products to be detected may be judged as bad elements by mistake, and unqualified products to be detected may be judged as qualified elements by mistake. And carrying out plane correction processing on the first plane point cloud data through the plane correction matrix, and carrying out coordinate system conversion to generate second plane point cloud data. And generating a binary gray image through the second plane point cloud data to eliminate an error value caused by height difference, thereby improving the detection precision.
In some embodiments, the pose detection method further includes: step S303, according to the second plane point cloud data Pn’[xn’，yn’，zn’]Generating a binary gray level image; step S304, carrying out region division on the binary gray level image to generate a plurality of single connected regions; s305, performing traversal analysis on a plurality of single connected regions and generating a deviation value of each single connected region; step S306, comparing the deviation value with a predetermined threshold value to determine whether the device 100 to be tested is defectiveAnd (3) a component.
By second plane point cloud data Pn’[xn’，yn’，zn’]A binary gray image is generated for region division. Comparing the deviation value of each region with a preset threshold value to judge whether the current element 100 to be detected meets a preset standard, and marking the element 100 to be detected with the deviation value exceeding the preset threshold value as a bad element.
The position information of the bad elements is sent to the removing device 400, and the removing device 400 removes the bad elements on the transmission path rapidly according to the position information of the bad elements, so that the product detection efficiency and the product accuracy are improved.
The preset threshold includes: a first coordinate error threshold, a second coordinate error threshold, an angle error threshold. Through comparing a plurality of errors, the detection accuracy of the product is improved.
For example, the first plane point cloud data is subjected to plane rectification processing by the plane rectification matrix to perform coordinate system conversion and generate the second plane point cloud data Pn’[xn’，yn’，zn’]. Second plane point cloud data Pn’[xn’，yn’，zn’]Is X ' Y ' Z '. By spotting the second plane with cloud data Pn’[xn’，yn’，zn’]Projected onto the X 'O' Y 'plane and a scanned image I (u, v, z' n) of the element 100 to be inspected is obtained.
Wherein u is the abscissa of the corresponding pixel point, v is the abscissa of the corresponding pixel point, and z' n is the gray value of the corresponding pixel point.
And D, performing Dice area division on the scanned image I (u, v, z 'n) according to the gray value z' n of the pixel point to form a plurality of single connected areas InDn (un, vn). The variable Dn represents that the current region is the nth block region, the variable In represents that the current region has n pixel points, un represents the abscissa position of the pixel In the current region, and vn represents the ordinate position of the pixel In the current region.
And performing Blob analysis on each connected region InDn to calculate the pose InDnPn (an, bn, theta n) of each Dice region. And calculating a deviation value delta Vn (delta an, delta bn and delta theta n) through a reference point Pstandart (as, bs and theta s) and the pose InDnPn (an, bn and theta n).
Wherein, the variable Δ an is an-as, the variable Δ bn is bn-bs, the variable Δ θ n is θ n- θ s, and n represents the nth Dice region of the scanned image I. an is an actual detection abscissa, bn is an actual detection ordinate, and θ n is an actual detection angle value. as is the reference abscissa, bs is the reference ordinate, and θ s is the reference angle value.
Whether the position deviation occurs on the theoretical position is judged by comparing the preset threshold value TH (TH1, TH2, TH3) and the deviation value delta Vn (delta an, delta bn, delta theta n) of each Dice area.
Where th1 represents an allowable error value on the abscissa, th2 represents an allowable error value on the ordinate, and th3 represents an allowable angle error value for the Dice attitude.
If any parameter in the deviation value delta Vn in the Dice area is larger than the corresponding parameter in the preset threshold TH, judging that the current element 100 to be detected is unqualified, and outputting an NG label; if any parameter of the deviation value delta Vn in the Dice area is smaller than or equal to the corresponding parameter of the preset threshold TH, the current element 100 to be detected is judged to be qualified, and an OK label is output.
The specific comparison method is as follows:
all the detection data are stored in the data server, the position information of the bad elements is sent to the removing device 400, and the removing device 400 removes the bad elements on the transmission path quickly according to the position information of the bad elements, so that the product detection efficiency and the product accuracy are improved.
In some embodiments, an embodiment of the present invention further provides a pose detection system, including: a trigger sensor 101 for detecting the element to be detected 100 and generating a detection signal; a two-dimensional detection device 200 that receives the detection signal and detects position information and posture information of the element 100 to be detected; a three-dimensional detection device 300 that detects stereoscopic information of the element to be detected 100; the attitude analyzer is used for judging whether the element 100 to be detected is a bad element according to the attitude information and the three-dimensional information and generating the position information of the bad element; the removing device 400 removes defective components based on the positional information of the defective components.
For example, the presence or absence of the component 100 to be detected on the conveyance path is detected by the trigger sensor 101 to generate a detection signal correspondingly. When the element 100 to be detected does not exist on the conveying path, the two-dimensional detection device 200 receives the detection signal and maintains a standby state; when the component 100 to be detected exists on the conveyance path, the two-dimensional detection device 200 receives the detection signal and enters a detection state to acquire position information and posture information of the component 100 to be detected, and transmits the posture information to the posture analyzer. The three-dimensional detection device 300 detects the three-dimensional information of the element 100 to be detected and transmits the three-dimensional information to the attitude analyzer, the attitude analyzer generates actual parameters of the element 100 to be detected according to the attitude information and the three-dimensional information, judges whether the element 100 to be detected is a defective element by comparing the actual parameters with preset reference parameters, and generates position information of the defective element. The rejecting device 400 rejects the defective components according to the position information of the defective components, so as to rapidly reject the defective components in the components 100 to be detected.
The two-dimensional detection device 200 includes: an annular light source 202 for providing an illumination source; the two-dimensional camera 201 is configured to acquire position information and posture information of the element 100 to be detected.
The annular light source 202 is used as an illumination light source to stably illuminate the element 100 to be detected, so that large errors of position information and posture information of the element 100 to be detected caused by uneven light are avoided.
The two-dimensional camera 201 is disposed in a central region of the annular light source 202, that is, a receiving end of the two-dimensional camera 201 is located at the center of the annular light source 202.
The three-dimensional inspection device 300 includes: the laser module 301 is used for providing a detection light beam, and the detection light beam irradiates the surface of the element 100 to be detected and is reflected; a three-dimensional camera 303 for receiving the reflected detection beam; and the bracket 302 is used for fixing the relative positions of the laser module 301 and the three-dimensional camera 303.
For example, the component 100 to be inspected, the laser module 301 and the three-dimensional camera 303 form a triangular relationship, the laser module 301 emits a detection beam, and the detection beam is on the surface of the component 100 to be inspected and reflected to the three-dimensional camera 303. The relative positions of the laser module 301 and the three-dimensional camera 303 are fixed by a bracket 302. The depth information of the point to be detected in the element 100 to be detected is calculated by the angle change generated by the deviation of the point to be detected relative to the optical reference line. The first plane point cloud data is obtained by detecting the depth information of all the points on the surface of the element 100 to be detected. And carrying out plane correction processing on the first plane point cloud data through the plane correction matrix to generate second plane point cloud data. Generating a binary gray image according to the second plane point cloud data; performing region division on the binary gray level image to generate a plurality of single connected regions; traversing and analyzing the plurality of single connected regions and generating a deviation value of each single connected region; the deviation value is compared with a preset threshold value to determine whether the device 100 to be detected is a bad device.
In some embodiments, the three-dimensional inspection device 300 further comprises: a first axial driving device 501 for driving the three-dimensional detection device 300 to move along a first axial direction; a second axial driving means 502 for driving the three-dimensional detection device 300 to move in the second axial direction; the encoder 503 is used for performing synchronous data encoding scanning on the device to be detected to generate encoded information.
The three-dimensional detection device 300 is driven by the first axial driving device 501 to move along the first axial direction so as to adjust the working object distance of the laser module 301, so that the belt detection element 100 is located in the effective detection area of the three-dimensional detection device 300. The three-dimensional inspection device 300 is driven by the second axial driving means 502 to move in the second axial direction so that the inspection range of the three-dimensional camera 303 can completely cover the device to be inspected.
For example, the first axial drive 501 is a longitudinally moving screw; the second axial drive 502 is a laterally moving lead screw. The height of the three-dimensional detection device 300 relative to the transmission path is adjusted by moving the lead screw longitudinally to focus the lens of the three-dimensional camera 303, so that the device to be detected is located at the focal plane of the three-dimensional camera 303.
The position of the three-dimensional inspection device 300 is laterally adjusted by laterally moving the lead screw so that the inspection area of the three-dimensional inspection device 300 completely covers the device to be inspected. For example, the relative position of the three-dimensional inspection device 300 and the conveyance path is adjusted by moving the lead screw laterally so that the photographing range of the three-dimensional camera 303 can completely cover the device to be inspected.
The laser generated by the laser module 301 may be a red line laser. The three-dimensional camera 303 and the encoder 503 perform synchronous data scanning on the device to be detected to generate first point cloud data.
The processor judges whether the component 100 to be detected is a bad component according to the posture information and the three-dimensional information of the component to be detected, and transmits the position information of the bad component to the rejecting device 400.
In some embodiments, the culling apparatus 400 includes: and the mechanical arm is used for positioning and removing the defective element according to the position information of the defective element. The mechanical arm places the bad elements in the bearing table, rejects the bad patches in the bad elements, and puts the rejected bad elements back to the conveying path again.
A pose detection system in a specific embodiment will be described below with reference to the above embodiments.
In some specific embodiments, an embodiment of the present invention further provides a pose detection system, including: the device comprises a trigger sensor 101, a two-dimensional detection device 200, a three-dimensional detection device 300, a posture analyzer and a rejection device 400;
the trigger sensor 101 detects the element to be detected 100 and generates a detection signal; the two-dimensional detection device 200 receives the detection signal and detects position information and posture information of the element 100 to be detected.
Wherein the two-dimensional detection device 200 comprises: an annular light source 202 for providing an illumination source; the two-dimensional camera 201 is configured to acquire position information and posture information of the element 100 to be detected. The three-dimensional inspection device 300 includes: the laser module 301 is used for providing a detection light beam, and the detection light beam irradiates the surface of the element 100 to be detected and is reflected; a three-dimensional camera 303 for receiving the reflected detection beam; and the bracket 302 is used for fixing the relative positions of the laser module 301 and the three-dimensional camera 303.
The three-dimensional inspection device 300 is used to inspect the stereoscopic information of the element to be inspected 100. Wherein, the three-dimensional detection device 300 further comprises: a first axial driving device 501 for driving the three-dimensional detection device 300 to move along a first axial direction; a second axial driving means 502 for driving the three-dimensional detection device 300 to move in the second axial direction; the encoder 503 is used for performing synchronous data encoding scanning on the device to be detected to generate encoded information.
The attitude analyzer judges whether the element 100 to be detected is a bad element according to the attitude information and the three-dimensional information, and generates position information of the bad element; the rejecting device 400 rejects the defective component according to the position information of the defective component.
The removing device 400 may be embodied as a mechanical arm, which performs positioning removal on the defective component according to the position information of the defective component.
Specifically, the presence or absence of the component 100 to be detected on the conveyance path is detected by the trigger sensor 101 to generate a detection signal correspondingly. When the element 100 to be detected does not exist on the conveying path, the two-dimensional detection device 200 receives the detection signal and maintains a standby state; when the component 100 to be detected exists on the conveyance path, the two-dimensional detection device 200 receives the detection signal and enters a detection state to acquire position information and posture information of the component 100 to be detected, and transmits the posture information to the posture analyzer. The three-dimensional detection device 300 detects the three-dimensional information of the element 100 to be detected and transmits the three-dimensional information to the attitude analyzer, the attitude analyzer generates actual parameters of the element 100 to be detected according to the attitude information and the three-dimensional information, judges whether the element 100 to be detected is a defective element by comparing the actual parameters with preset reference parameters, and generates position information of the defective element. The rejecting device 400 rejects the defective components according to the position information of the defective components, so as to rapidly reject the defective components in the components 100 to be detected.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (9)
1. A pose detection method is characterized by comprising:
detecting an element to be detected and generating a detection signal;
triggering a two-dimensional detection device through the detection signal and detecting the position information and the posture information of the element to be detected;
adjusting the position of a three-dimensional detection device according to the position information to detect the three-dimensional information of the element to be detected;
judging whether the element to be detected is a bad element or not according to the posture information and the three-dimensional information, and generating position information of the bad element;
and removing the bad elements according to the position information of the bad elements.
2. The pose detection method according to claim 1, further comprising:
detecting the element to be detected and generating first plane point cloud data;
extracting a plane correction matrix according to the first plane point cloud data;
and carrying out plane correction on the first plane point cloud data through the plane correction matrix and generating second plane point cloud data.
3. The pose detection method according to claim 2, further comprising:
generating a binary gray image according to the second plane point cloud data;
performing region division on the binary gray level image to generate a plurality of single connected regions;
traversing and analyzing the single connected regions and generating a deviation value of each single connected region;
and comparing the deviation value with a preset threshold value to judge whether the element to be detected is a bad element.
4. The pose detection method according to claim 3, wherein the preset threshold value includes:
a first coordinate error threshold, a second coordinate error threshold, an angle error threshold;
the first coordinate error threshold value represents an allowable error value under an abscissa, the second coordinate error threshold value represents an allowable error value under an ordinate, and the angle error threshold value represents an allowable angle error value of a Dice attitude.
5. A pose detection system characterized by comprising:
the trigger sensor is used for detecting the element to be detected and generating a detection signal;
the two-dimensional detection device receives the detection signal and detects the position information and the posture information of the element to be detected;
the three-dimensional detection device is used for detecting the three-dimensional information of the element to be detected;
the attitude analyzer is used for judging whether the element to be detected is a bad element or not according to the attitude information and the three-dimensional information and generating position information of the bad element;
and the rejecting device rejects the defective element according to the position information of the defective element.
6. The pose detection system according to claim 5, characterized in that the two-dimensional detection means includes:
an annular light source for providing an illumination source;
and the two-dimensional camera is used for acquiring the position information and the posture information of the element to be detected.
7. The pose detection system according to claim 5, characterized in that the three-dimensional detection means includes:
the laser module is used for providing a detection light beam, and the detection light beam irradiates the surface of the element to be detected and is reflected; a three-dimensional camera for receiving the reflected detection beam;
and the bracket is used for fixing the relative position of the laser module and the three-dimensional camera.
8. The pose detection system according to claim 7, wherein the three-dimensional detection means further includes:
the first axial driving device is used for driving the three-dimensional detection device to move along a first axial direction;
the second axial driving device is used for driving the three-dimensional detection device to move along the second axial direction;
and the encoder is used for synchronously scanning data of the device to be detected.
9. The pose detection system according to claim 5, wherein the eliminating means includes:
and the mechanical arm is used for positioning and removing the bad elements according to the position information of the bad elements.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010686564.0A CN111906043B (en) | 2020-07-16 | 2020-07-16 | Pose detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010686564.0A CN111906043B (en) | 2020-07-16 | 2020-07-16 | Pose detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111906043A CN111906043A (en) | 2020-11-10 |
| CN111906043B true CN111906043B (en) | 2022-03-29 |
Family
ID=73280404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010686564.0A Active CN111906043B (en) | 2020-07-16 | 2020-07-16 | Pose detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111906043B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102589530A (en) * | 2012-02-24 | 2012-07-18 | 合肥工业大学 | Method for measuring position and gesture of non-cooperative target based on fusion of two dimension camera and three dimension camera |
| CN105115972A (en) * | 2015-08-24 | 2015-12-02 | 北京慧眼智行科技有限公司 | Printing detection system and method |
| CN106842216A (en) * | 2017-02-13 | 2017-06-13 | 大连理工大学 | A kind of workpiece pose online test method cooperateed with three-dimensional laser based on Kinect |
| CN107578400A (en) * | 2017-07-26 | 2018-01-12 | 西南交通大学 | A kind of contact net device parameter detection method of BIM and three-dimensional point cloud fusion |
| CN107597600A (en) * | 2017-09-26 | 2018-01-19 | 北京京东尚科信息技术有限公司 | Sorting system and method for sorting |
| CN107649406A (en) * | 2017-09-30 | 2018-02-02 | 南京航空航天大学 | A kind of efficient more material picking up system of binocular vision and method |
| CN109520436A (en) * | 2018-11-28 | 2019-03-26 | 扬州市职业大学 | A kind of butterfly spring three-dimensional dimension automatic measurement system and its measurement method based on machine vision |
| CN109719042A (en) * | 2017-10-27 | 2019-05-07 | 北京京东尚科信息技术有限公司 | Piece supplying method, apparatus, electronic equipment and the storage medium of package |
| CN109924994A (en) * | 2019-04-02 | 2019-06-25 | 晓智科技（成都）有限公司 | A kind of x photo-beat take the photograph during detection position automatic calibrating method and system |
| CN209393575U (en) * | 2018-12-06 | 2019-09-17 | 苏州英士派克光电科技有限公司 | A kind of magnetic core detection device |
-
2020
- 2020-07-16 CN CN202010686564.0A patent/CN111906043B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102589530A (en) * | 2012-02-24 | 2012-07-18 | 合肥工业大学 | Method for measuring position and gesture of non-cooperative target based on fusion of two dimension camera and three dimension camera |
| CN105115972A (en) * | 2015-08-24 | 2015-12-02 | 北京慧眼智行科技有限公司 | Printing detection system and method |
| CN106842216A (en) * | 2017-02-13 | 2017-06-13 | 大连理工大学 | A kind of workpiece pose online test method cooperateed with three-dimensional laser based on Kinect |
| CN107578400A (en) * | 2017-07-26 | 2018-01-12 | 西南交通大学 | A kind of contact net device parameter detection method of BIM and three-dimensional point cloud fusion |
| CN107597600A (en) * | 2017-09-26 | 2018-01-19 | 北京京东尚科信息技术有限公司 | Sorting system and method for sorting |
| CN107649406A (en) * | 2017-09-30 | 2018-02-02 | 南京航空航天大学 | A kind of efficient more material picking up system of binocular vision and method |
| CN109719042A (en) * | 2017-10-27 | 2019-05-07 | 北京京东尚科信息技术有限公司 | Piece supplying method, apparatus, electronic equipment and the storage medium of package |
| CN109520436A (en) * | 2018-11-28 | 2019-03-26 | 扬州市职业大学 | A kind of butterfly spring three-dimensional dimension automatic measurement system and its measurement method based on machine vision |
| CN209393575U (en) * | 2018-12-06 | 2019-09-17 | 苏州英士派克光电科技有限公司 | A kind of magnetic core detection device |
| CN109924994A (en) * | 2019-04-02 | 2019-06-25 | 晓智科技（成都）有限公司 | A kind of x photo-beat take the photograph during detection position automatic calibrating method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111906043A (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102102874B1 (en) | Automatic optical inspection system and operating method thereof | |
| TWI661495B (en) | Work piece processing device, work piece conveying system | |
| US11300521B2 (en) | Automatic defect classification | |
| WO2010090605A1 (en) | Methods for examining a bonding structure of a substrate and bonding structure inspection devices | |
| US20080175466A1 (en) | Inspection apparatus and inspection method | |
| US10360684B2 (en) | Method and apparatus for edge determination of a measurement object in optical metrology | |
| US20120300039A1 (en) | Apparatus and method for three dimensional inspection of wafer saw marks | |
| CN113379837B (en) | Angle correction method and device for detection device and computer readable storage medium | |
| CN110739240A (en) | Substrate inspection method and substrate inspection apparatus | |
| JP2001266127A (en) | Device for inspecting printed wiring board | |
| CN116256366A (en) | Chip defect detection method, detection system and storage medium | |
| CN115127483A (en) | Detection method for measuring coaxiality and system for detecting coaxiality | |
| US20080205746A1 (en) | Method of inspecting an identification mark, method of inspecting a wafer using the same, and apparatus for performing the method | |
| CN111220621B (en) | Chip inclined surface detection method | |
| CN111906043B (en) | Pose detection method and system | |
| CN114608458B (en) | Device and method for detecting thickness of die attach adhesive | |
| JP2017181136A (en) | Surface defect detection method and surface defect detection device | |
| JP3272998B2 (en) | Bump height pass / fail judgment device | |
| JP2012190935A (en) | Chip position specification system, chip position specification device, chip position specification program, and chip position specification method | |
| JP4369276B2 (en) | Chip shape inspection apparatus and chip inspection method for disk-shaped parts | |
| JP4563184B2 (en) | Method and apparatus for inspecting mura defect | |
| JPH10253547A (en) | Visual inspection system for board | |
| JPH10253543A (en) | Instrument and method for visual examination of substrate | |
| TWM425273U (en) | Re-inspection machine for visual inspection | |
| WO2021261302A1 (en) | Defect inspection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |