CN113522770A - High-precision online detection system based on 3D vision - Google Patents
High-precision online detection system based on 3D vision Download PDFInfo
- Publication number
- CN113522770A CN113522770A CN202110832307.8A CN202110832307A CN113522770A CN 113522770 A CN113522770 A CN 113522770A CN 202110832307 A CN202110832307 A CN 202110832307A CN 113522770 A CN113522770 A CN 113522770A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- detection
- personal computer
- industrial personal
- area
- 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.)
- Withdrawn
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
- B07C5/36—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
-
- 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
- B07C5/38—Collecting or arranging articles in groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
- G01B11/12—Measuring arrangements characterised by the use of optical techniques for measuring diameters internal diameters
Abstract
The invention provides a high-precision online detection system based on 3D vision, which comprises: the industrial personal computer and the workpiece conveying mechanism; the workpiece conveying mechanism is provided with a workpiece conveying area, a workpiece detection area and a workpiece processing area which are connected in sequence; the workpiece placing sensor senses the workpiece placing information and transmits the workpiece placing information to the industrial personal computer for control; the industrial personal computer controls the work piece conveying mechanism to operate to convey the work piece to a work piece detection area, and triggers the detection in-place sensor to stop the work piece conveying mechanism from operating; the industrial personal computer controls the detection device to detect the workpiece, and after the detection is finished, the workpiece is transmitted to the workpiece processing area. Compared with the traditional manual detection, the system greatly improves the sorting accuracy and the detection efficiency and reduces the sorting cost.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a high-precision online detection system based on 3D vision.
Background
At present, an automatic production line is applied to a plurality of fields, and functions of automatic transmission, automatic picking and placing and the like of workpieces can be realized.
Although automatic material or work piece can be realized carrying by oneself to automation line, because the kind of work piece is many, and the size is not of uniform size, and the defect difference on the work piece is little moreover, and the naked eye resolution degree of difficulty is great, leads to artifical detection efficiency low, easily makes mistakes for traditional artifical detection obviously can not satisfy the detection demand under.
Disclosure of Invention
The invention provides a high-precision online detection system based on 3D vision, which greatly improves the sorting accuracy and detection efficiency and reduces the sorting cost compared with the traditional manual detection.
The system comprises: the industrial personal computer and the workpiece conveying mechanism;
the workpiece conveying mechanism is provided with a workpiece conveying area, a workpiece detection area and a workpiece processing area which are connected in sequence;
the workpiece conveying area is provided with a workpiece placing sensor;
the workpiece detection area is provided with an in-place detection sensor and a detection device;
the workpiece placing sensor, the workpiece conveying mechanism, the in-place detection sensor and the detection device are respectively connected with the industrial personal computer;
the workpiece placing sensor senses the workpiece placing information and transmits the workpiece placing information to the industrial personal computer for control;
the industrial personal computer controls the work piece conveying mechanism to operate to convey the work piece to a work piece detection area, and triggers the detection in-place sensor to stop the work piece conveying mechanism from operating;
the industrial personal computer controls the detection device to detect the workpiece, and after the detection is finished, the workpiece is transmitted to the workpiece processing area.
In a system according to the present invention, a detection device includes: a first detection camera and a second detection camera;
the first detection camera and the second detection camera are respectively in communication connection with the industrial personal computer,
the first detection camera captures panoramic information of the workpiece and sends the panoramic information to the industrial personal computer;
the second detection camera captures image information of the to-be-detected area of the workpiece and sends the image information of the to-be-detected area to the industrial personal computer;
the industrial personal computer compares the shot panoramic information with a preset panoramic model and judges whether the requirements are met;
and if so, identifying the image information of the to-be-detected region of the workpiece.
In the system related by the invention, a second detection camera acquires image information of a region to be detected in a focusing and amplifying mode;
the industrial personal computer compares the image information of the over-focused amplified region to be detected with a preset image model, judges whether the quality of the workpiece meets the requirement or not, and outputs the current detection information through the display screen.
In the system related by the invention, an industrial personal computer is configured with a coordinate system;
the method comprises the following steps that a first detection camera captures panoramic information of a workpiece based on a coordinate system, and at least four panoramic identification coordinate points are configured in the panoramic information;
the second detection camera captures image information of an area to be detected of the workpiece based on a coordinate system, and at least four image identification coordinate points are configured in the image information of the area to be detected;
the industrial personal computer verifies the panoramic identification coordinate point of the panoramic information and judges whether the requirements are met;
the industrial personal computer also verifies the image identification coordinate point of the image information of the region to be detected and judges whether the quality of the workpiece meets the requirement.
In the system related by the invention, an industrial personal computer is arranged in at least four panoramic identification coordinate points, and a connecting line of two panoramic identification coordinate points is configured as a first panoramic ratio pair line, and a connecting line of the other two panoramic identification coordinate points is configured as a second panoramic ratio pair line;
and associating the first panorama comparison line with the second panorama comparison line to form a panorama comparison graph line, comparing the panorama comparison graph line with a preset panorama comparison graph line, and judging whether the requirements are met.
In the system related by the invention, an industrial personal computer is arranged in at least four image identification coordinate points, a connecting line of two image identification coordinate points is configured as a first image comparison line, and a connecting line of the other two image identification coordinate points is configured as a second image comparison line;
and associating the first image comparison line with the second image comparison line to form an image comparison graph, comparing the image comparison graph with a preset image comparison graph, and judging whether the requirements are met.
In the invention, the method also comprises the following steps: a base station;
the workpiece conveying mechanism is arranged on the base platform;
a protective cover is covered outside the workpiece detection area; the bottom of protection casing and base station can be dismantled and be connected.
In the invention, the bottom of the base station is provided with a support frame, and the bottom of the support frame is provided with a support leg;
the industrial personal computer is placed in the rack and is provided with a wireless communication module, an audio/video input module, a user input module, a display screen, a memory, an interface module, a processor and a power supply module.
In the invention, the workpiece processing area is provided with an unqualified product processing area and a qualified product output area;
the unqualified product processing area is arranged between the workpiece detection area and the qualified product output area;
the reject handling area includes: the device comprises an unqualified position sensor, a stock stop and an electric push rod;
the material blocking mechanism is provided with a door-shaped frame, a material blocking plate is arranged on the door-shaped frame, and the material blocking plate is connected with a driving device;
the industrial personal computer senses a workpiece in-place signal through the unqualified position sensor, and controls the material baffle to block the workpiece if the workpiece is an unqualified product, and pushes the workpiece to an unqualified product box by controlling the electric push rod to operate.
In the invention, rollers are arranged at the base station positions of the unqualified product processing area and the qualified product output area;
the qualified product output area is provided with a material conveying frame arranged on the base platform, the material conveying frame extends out of the base platform, and a qualified product recovery box is arranged at the bottom of the material conveying frame.
According to the technical scheme, the invention has the following advantages:
the system has the functions of workpiece normalization belt transmission, visual detection, automatic distribution and the like. The size and the type of the workpiece and the defects are intelligently detected through 3D vision. The combined workpieces are sequentially placed on the workpiece conveying mechanism to detect the workpieces. During detection, the operation of the workpiece conveying mechanism is stopped, after the workpiece is detected to reach a detection area, the detection is started, after the detection is finished, the operation of the workpiece conveying mechanism is recovered, and the qualified workpieces are conveyed to a qualified product output area; and the unqualified workpiece is blocked and then pushed to an unqualified product box by controlling the electric push rod to operate. The workpiece sorting device is high in workpiece sorting efficiency. Is not influenced by a plurality of factors such as climate, time, human physical strength and the like. The detection accuracy is high, and the omission factor is low. Compared with the traditional manual detection, the method greatly improves the sorting accuracy and the detection efficiency and reduces the sorting cost.
The high-precision online detection system based on the 3D vision can realize artificial intelligence processing by using the computer vision technology and the artificial intelligence cloud service based on the artificial intelligence cloud service in the computer vision technology and the cloud technology, and can improve the accuracy of the artificial intelligence processing.
According to the invention, the coordinate points are configured on the key parts of the workpiece, and the industrial personal computer can judge the area of the coordinate points by taking the coordinate points as reference points when the industrial personal computer identifies and judges the panoramic information and the image information of the area to be detected of the workpiece. And the coordinate points can be used as positioning points to perform expansion comparison to judge whether the requirements are met, so that the quality of the workpiece can be judged by high-precision comparison.
The invention can form an image comparison graph by connecting the image identification coordinate points of the workpiece, and can detect the area related to the image comparison graph. The image information in the image comparison graph can be compared to judge whether the requirements are met, so that the comparison judgment is pointed, and the efficiency and the accuracy of the comparison judgment are improved.
In the invention, if the panoramic information does not meet the requirements, the matching judgment is not carried out on the image information of the area to be detected. Because the pixel information and the image definition information of the panoramic information are lower than the image information of the detection area, the industrial personal computer detects the panoramic information firstly, the data processing amount of the industrial personal computer can be reduced, the data processing efficiency is improved, and the detection efficiency is ensured.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings used in the description will be briefly introduced, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without creative efforts.
FIG. 1 is a schematic diagram of a high-precision online detection system based on 3D vision;
FIG. 2 is a perspective view of a high-precision online inspection system based on 3D vision;
fig. 3 is a schematic diagram of an embodiment of a high-precision online detection system based on 3D vision.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to fig. 1 to 3 in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The elements and algorithm steps of the various examples described in the embodiments disclosed in the 3D vision-based high-precision online inspection system provided by the present invention can be implemented in electronic hardware, computer software, or a combination of both, and in the above description, the components and steps of the various examples have been generally described in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The block diagram shown in the drawing of the high-precision online detection system based on 3D vision is only a functional entity and does not necessarily correspond to a physically independent entity. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
In the high-precision online detection system based on 3D vision provided by the invention, it should be understood that the disclosed system, apparatus and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The system of the invention specifically comprises: an industrial personal computer 11 and a workpiece conveying mechanism 1; the workpiece conveying mechanism 1 can adopt belt transmission, chain transmission, roller transmission and the like. The work conveying mechanism 1 may be driven by a motor. The industrial personal computer 11 may be a computer, a server, or the like.
The workpiece conveying mechanism 1 is provided with a workpiece conveying area 2, a workpiece detection area 3 and a workpiece processing area which are connected in sequence;
wherein, the system comprises a base station 4; the workpiece conveying mechanism 1 is arranged on the base 4; the bottom of the base station 4 is provided with a support frame 5, and the bottom of the support frame 5 is provided with a support leg 6; a protective cover 7 is covered outside the workpiece detection area 3; the bottom of the protective cover 7 is detachably connected with the base station 4. Can wrap up detection device inside the protection casing, play the guard action, can also reduce external interference to the testing process.
The workpiece conveying area 2 is provided with a workpiece placing sensor 12; the workpiece detection area 3 is provided with an in-place detection sensor 13 and a detection device;
the workpiece placing sensor 12, the workpiece conveying mechanism 1, the in-place detection sensor 13 and the detection device are respectively connected with the industrial personal computer 11; the workpiece placement sensor 12 senses workpiece placement information and transmits the information to the industrial personal computer 11 for control; the industrial personal computer 11 controls the work piece conveying mechanism 1 to operate, conveys work pieces to the work piece detection area 3, triggers the detection in-place sensor 13 and stops the work piece conveying mechanism 1 from operating; the industrial personal computer 11 controls the detection device to detect the workpiece, and transmits the workpiece to the workpiece processing area after the detection is finished.
The workpiece placing sensor 12 and the in-place detecting sensor 13 related to the present invention may be photoelectric sensors, infrared sensors, or the like, and the specific types are not limited. The sensor plays a role in sensing the position of workpiece transmission and transmitting the position to the industrial personal computer 11, so that the industrial personal computer 11 knows the position information of the workpiece and performs corresponding control.
The industrial personal computer 11 is placed in the rack 20, and the industrial personal computer 11 is provided with a wireless communication module, an audio/video input module, a user input module, a display screen, a memory, an interface module, a processor and a power supply module.
The industrial personal computer 11 and the electrical equipment of the system can adopt a wireless communication mode or a wired mode.
The present invention relates to a detection device comprising: a first detection camera 14 and a second detection camera 15; the first detection camera 14 and the second detection camera 15 are respectively in communication connection with the industrial personal computer 11, and the first detection camera 14 captures panoramic information of the workpiece and sends the panoramic information to the industrial personal computer 11; the second detection camera 15 captures image information of the to-be-detected area of the workpiece and sends the image information of the to-be-detected area to the industrial personal computer 11; the industrial personal computer 11 compares the shot panoramic information with a preset panoramic model and judges whether the requirements are met; and if so, identifying the image information of the to-be-detected region of the workpiece.
That is to say, the first detection camera 14 collects the whole image of the workpiece, and transmits the collected whole image information to the industrial personal computer 11, and the industrial personal computer 11 firstly judges the panoramic information of the workpiece to judge whether the requirement is met. Wherein the industrial computer 11 presets and has configured work piece panorama information image, and the work piece is fixed a position after carrying out the detection area, and the location can be fixed a position through positioning fixture, also can be based on location push rod location etc.. Of course, after the workpiece is placed in the workpiece conveying area 2, the position is fixed, and the detection shooting can be realized after the workpiece position is sensed by the in-place detection sensor 13.
The first detection camera 14 may be disposed on the side of the workpiece, or on the top, etc., and a 360 ° holographic camera may be used to capture panoramic information of the workpiece. In order to further detect important parts of the workpiece or a certain part of the workpiece, the second detection camera 15 captures image information of an area to be detected of the workpiece and sends the image information of the area to be detected to the industrial personal computer 11;
here, the second detection camera 15 acquires image information of the region to be inspected by means of focus enlargement; the industrial personal computer 11 compares the image information of the over-focused amplified region to be detected with a preset image model, judges whether the quality of the workpiece meets the requirement or not, and outputs the current detection information through the display screen.
The detection camera may be configured with a CMOS image sensor, a CCD image sensor, or the like, and the acquired workpiece image may be a color image, such as an RGB image, although not particularly limited thereto. The industrial personal computer 11 can perform image enhancement, format conversion and the like on the image.
The detection personnel can set the key detection area of the workpiece, and set a preset image model on the industrial personal computer 11, and the preset image model can be used as a standard graph for comparison processing of the collected images.
The industrial personal computer 11 also identifies the panoramic information of each workpiece and the image information of the area to be detected so as to facilitate the subsequent searching and use of a user. The encoding can be performed based on the detection time or the detection workpiece, so that a user can conveniently search the monitored workpiece.
The detection personnel can preset a mapping table of the image models on the industrial personal computer 11, and a plurality of preset image models are configured in the mapping table.
After receiving the detected image information of the area to be detected, the industrial personal computer 11 configures a corresponding preset image model from the mapping table, and compares the preset image model with the mapping table after matching is successful to judge whether the preset image model meets the requirements.
Of course, a mapping table of the panoramic information may be preset on the industrial personal computer 11, and a plurality of pieces of preset panoramic information may be configured in the mapping table.
The industrial personal computer 11 receives the panoramic information, configures corresponding preset panoramic information from the mapping table, and compares the panoramic information with the mapping table after matching is successful to judge whether the panoramic information meets the requirements. And if the requirements are met, matching the image information of the area to be detected.
The pixel information and the image definition information of the image information of the area to be detected can be higher than the panoramic information, so that the industrial personal computer 11 firstly performs matching judgment on the panoramic information and then performs matching judgment on the image information of the area to be detected.
And if the panoramic information does not meet the requirements, the image information of the area to be detected is not subjected to matching judgment. Because the pixel information and the image definition information of the panoramic information are lower than the image information of the detection area, the industrial personal computer 11 detects the panoramic information firstly, so that the data processing amount of the industrial personal computer 11 can be reduced, the data processing efficiency is improved, and the detection efficiency is ensured.
As an embodiment of the present invention, the industrial personal computer 11 configures a coordinate system;
the first detection camera 14 captures panoramic information of the workpiece based on a coordinate system, and at least four panoramic identification coordinate points are configured in the panoramic information; the second detection camera 15 captures image information of the to-be-detected area of the workpiece based on a coordinate system, and at least four image identification coordinate points are configured in the image information of the to-be-detected area; the industrial personal computer 11 verifies the panoramic identification coordinate point of the panoramic information and judges whether the panoramic identification coordinate point meets the requirements or not; the industrial personal computer 11 also verifies the image identification coordinate point of the image information of the region to be detected, and judges whether the quality of the workpiece meets the requirement.
Here, a coordinate point is configured at a key part of the workpiece, and the industrial personal computer 11 can judge the region of the coordinate point by using the coordinate point as a reference point when identifying and judging the panoramic information of the workpiece and the image information of the region to be detected. And the coordinate point can be used as a positioning point to perform expansion comparison to judge whether the requirement is met.
Further, the industrial personal computer 11 sets at least four panoramic identification coordinate points, and configures a connecting line of two panoramic identification coordinate points as a first panoramic ratio pair line, and a connecting line of the other two panoramic identification coordinate points as a second panoramic ratio pair line; and associating the first panorama comparison line with the second panorama comparison line to form a panorama comparison graph line, comparing the panorama comparison graph line with a preset panorama comparison graph line, and judging whether the requirements are met.
It can be understood that connecting the panorama identification coordinate points may form a panorama comparison graph, and of course, the area related to the panorama comparison graph may be detected. The image information in the panoramic comparison graph line can be compared to judge whether the requirements are met, so that the comparison judgment is pointed, and the efficiency and the accuracy of comparison judgment are improved.
Furthermore, the industrial personal computer 11 sets at least four image identification coordinate points, and configures a connection line of two image identification coordinate points as a first image comparison line, and a connection line of the other two image identification coordinate points as a second image comparison line; and associating the first image comparison line with the second image comparison line to form an image comparison graph, comparing the image comparison graph with a preset image comparison graph, and judging whether the requirements are met.
It will be appreciated that connecting the image identifier coordinates may form an image alignment map, although the regions to which the image alignment map relates may be detected. The image information in the image comparison graph can be compared to judge whether the requirements are met, so that the comparison judgment is pointed, and the efficiency and the accuracy of the comparison judgment are improved.
The high-precision online detection system based on the 3D vision can realize artificial intelligence processing by using the computer vision technology and the artificial intelligence cloud service based on the artificial intelligence cloud service in the computer vision technology and the cloud technology, and can improve the accuracy of the artificial intelligence processing.
The industrial personal computer 11 may use a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain theories, methods, techniques and application systems of optimal results. The industrial personal computer 11 may include technologies such as image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, synchronous positioning, map construction, and the like, and also include technologies of common biometric features such as face recognition, fingerprint recognition, and the like.
In the invention, a workpiece processing area is provided with an unqualified product processing area 8 and a qualified product output area 9; the unqualified product processing area 8 is arranged between the workpiece detection area 3 and the qualified product output area 9; the reject handling zone 8 includes: an unqualified position sensor 16, a stock stop and an electric push rod 17; the material blocking mechanism is provided with a door-shaped frame, a material blocking plate is arranged on the door-shaped frame, and the material blocking plate is connected with a driving device; the industrial personal computer 11 senses a workpiece in-place signal through the unqualified position sensor 16, and controls the material baffle to block the workpiece if the workpiece is an unqualified product, and pushes the workpiece to an unqualified product box by controlling the electric push rod 17 to operate.
Rollers are arranged at the positions of the base stations 4 of the unqualified product processing area 8 and the qualified product output area 9; the qualified product output area 9 is provided with a material conveying frame arranged on the base platform 4, the material conveying frame extends out of the base platform 4, and the bottom of the material conveying frame is provided with a qualified product recovery box 10.
In the system provided by the invention, the 3D intelligent camera can be used for identifying and capturing the workpiece, the image information is sent to the industrial personal computer 11, the industrial personal computer 11 processes the point location information of the captured image through an intelligent algorithm, the data of the inner diameter, the outer diameter and the height of the workpiece are analyzed, and then the data are compared with the standard workpiece size stored in the database to judge whether the detected workpiece is qualified. If the workpiece is detected to be qualified, the workpiece is automatically conveyed to a qualified product recovery box 10 of a qualified product output area 9, if the detected workpiece is unqualified, the industrial personal computer 11 controls the material baffle plate to stop the workpiece from conveying, and then the unqualified workpiece is pushed into an unqualified product box by the electric push rod 17. Compared with the traditional manual detection, the system greatly improves the sorting accuracy and the detection efficiency and reduces the sorting cost.
The system has the functions of workpiece normalization belt transmission, visual detection, automatic distribution and the like. The size and the type of the workpiece and the defects are intelligently detected through 3D vision. In the invention, the combined workpieces are sequentially placed on the workpiece conveying mechanism 1 to detect the workpieces. During detection, the operation of the workpiece conveying mechanism 1 is stopped, after the workpiece is detected to reach a detection area, the detection is started, after the detection is finished, the operation of the workpiece conveying mechanism 1 is recovered, and the qualified workpiece is conveyed to a qualified product output area 9; and the unqualified workpiece is blocked and then pushed to an unqualified product box by controlling the electric push rod 17 to operate. The workpiece sorting device is high in workpiece sorting efficiency. Is not influenced by a plurality of factors such as climate, time, human physical strength and the like. The detection accuracy is high, and the omission factor is low.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A high-precision online detection system based on 3D vision is characterized by comprising: the industrial personal computer and the workpiece conveying mechanism;
the workpiece conveying mechanism is provided with a workpiece conveying area, a workpiece detection area and a workpiece processing area which are connected in sequence;
the workpiece conveying area is provided with a workpiece placing sensor;
the workpiece detection area is provided with an in-place detection sensor and a detection device;
the workpiece placing sensor, the workpiece conveying mechanism, the in-place detection sensor and the detection device are respectively connected with the industrial personal computer;
the workpiece placing sensor senses the workpiece placing information and transmits the workpiece placing information to the industrial personal computer for control;
the industrial personal computer controls the work piece conveying mechanism to operate to convey the work piece to a work piece detection area, and triggers the detection in-place sensor to stop the work piece conveying mechanism from operating;
the industrial personal computer controls the detection device to detect the workpiece, and after the detection is finished, the workpiece is transmitted to the workpiece processing area.
2. The high-precision online detection system based on 3D vision according to claim 1,
the detection device comprises: a first detection camera and a second detection camera;
the first detection camera and the second detection camera are respectively in communication connection with the industrial personal computer,
the first detection camera captures panoramic information of the workpiece and sends the panoramic information to the industrial personal computer;
the second detection camera captures image information of the to-be-detected area of the workpiece and sends the image information of the to-be-detected area to the industrial personal computer;
the industrial personal computer compares the shot panoramic information with a preset panoramic model and judges whether the requirements are met;
and if so, identifying the image information of the to-be-detected region of the workpiece.
3. The 3D vision-based high-precision online detection system according to claim 2,
the second detection camera acquires image information of the area to be detected in a focusing and amplifying mode;
the industrial personal computer compares the image information of the over-focused amplified region to be detected with a preset image model, judges whether the quality of the workpiece meets the requirement or not, and outputs the current detection information through the display screen.
4. The 3D vision-based high-precision online detection system according to claim 3,
the industrial personal computer configures a coordinate system;
the method comprises the following steps that a first detection camera captures panoramic information of a workpiece based on a coordinate system, and at least four panoramic identification coordinate points are configured in the panoramic information;
the second detection camera captures image information of an area to be detected of the workpiece based on a coordinate system, and at least four image identification coordinate points are configured in the image information of the area to be detected;
the industrial personal computer verifies the panoramic identification coordinate point of the panoramic information and judges whether the requirements are met;
the industrial personal computer also verifies the image identification coordinate point of the image information of the region to be detected and judges whether the quality of the workpiece meets the requirement.
5. The 3D vision-based high-precision online detection system according to claim 4,
the industrial personal computer is arranged in at least four panoramic identification coordinate points, and a connecting line of two panoramic identification coordinate points is configured as a first panoramic ratio pair line, and a connecting line of the other two panoramic identification coordinate points is configured as a second panoramic ratio pair line;
and associating the first panorama comparison line with the second panorama comparison line to form a panorama comparison graph line, comparing the panorama comparison graph line with a preset panorama comparison graph line, and judging whether the requirements are met.
6. The 3D vision-based high-precision online detection system according to claim 4,
the industrial personal computer is arranged in at least four image identification coordinate points, and a connecting line of two image identification coordinate points is configured as a first image comparison line, and a connecting line of the other two image identification coordinate points is configured as a second image comparison line;
and associating the first image comparison line with the second image comparison line to form an image comparison graph, comparing the image comparison graph with a preset image comparison graph, and judging whether the requirements are met.
7. The 3D vision-based high-precision online detection system according to claim 1 or 2,
further comprising: a base station;
the workpiece conveying mechanism is arranged on the base platform;
a protective cover is covered outside the workpiece detection area; the bottom of protection casing and base station can be dismantled and be connected.
8. The 3D vision-based high-precision online detection system according to claim 7,
the bottom of the base station is provided with a support frame, and the bottom of the support frame is provided with a support leg;
the industrial personal computer is placed in the rack and is provided with a wireless communication module, an audio/video input module, a user input module, a display screen, a memory, an interface module, a processor and a power supply module.
9. The 3D vision-based high-precision online detection system according to claim 1 or 2,
the workpiece processing area is provided with an unqualified product processing area and a qualified product output area;
the unqualified product processing area is arranged between the workpiece detection area and the qualified product output area;
the reject handling area includes: the device comprises an unqualified position sensor, a stock stop and an electric push rod;
the material blocking mechanism is provided with a door-shaped frame, a material blocking plate is arranged on the door-shaped frame, and the material blocking plate is connected with a driving device;
the industrial personal computer senses a workpiece in-place signal through the unqualified position sensor, and controls the material baffle to block the workpiece if the workpiece is an unqualified product, and pushes the workpiece to an unqualified product box by controlling the electric push rod to operate.
10. The high-precision online detection system based on 3D vision according to claim 9,
rollers are arranged at the positions of the base stations of the unqualified product processing area and the qualified product output area;
the qualified product output area is provided with a material conveying frame arranged on the base platform, the material conveying frame extends out of the base platform, and a qualified product recovery box is arranged at the bottom of the material conveying frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110832307.8A CN113522770A (en) | 2021-07-22 | 2021-07-22 | High-precision online detection system based on 3D vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110832307.8A CN113522770A (en) | 2021-07-22 | 2021-07-22 | High-precision online detection system based on 3D vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113522770A true CN113522770A (en) | 2021-10-22 |
Family
ID=78120525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110832307.8A Withdrawn CN113522770A (en) | 2021-07-22 | 2021-07-22 | High-precision online detection system based on 3D vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113522770A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115366118A (en) * | 2022-08-09 | 2022-11-22 | 广东机电职业技术学院 | Relay detection system and method based on robot and vision technology |
| CN115771740A (en) * | 2023-02-10 | 2023-03-10 | 苏州梅曼智能科技有限公司 | Hydrogen fuel cell 3D visual detection machine |
| CN117602320A (en) * | 2024-01-24 | 2024-02-27 | 歌尔股份有限公司 | Material cavity dividing device and material cavity dividing method |
| EP4345720A1 (en) * | 2022-08-31 | 2024-04-03 | Siemens Aktiengesellschaft | System and method for managing end-of-life products |
-
2021
- 2021-07-22 CN CN202110832307.8A patent/CN113522770A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115366118A (en) * | 2022-08-09 | 2022-11-22 | 广东机电职业技术学院 | Relay detection system and method based on robot and vision technology |
| EP4345720A1 (en) * | 2022-08-31 | 2024-04-03 | Siemens Aktiengesellschaft | System and method for managing end-of-life products |
| CN115771740A (en) * | 2023-02-10 | 2023-03-10 | 苏州梅曼智能科技有限公司 | Hydrogen fuel cell 3D visual detection machine |
| CN115771740B (en) * | 2023-02-10 | 2024-01-09 | 苏州梅曼智能科技有限公司 | Hydrogen fuel cell 3D visual inspection machine |
| CN117602320A (en) * | 2024-01-24 | 2024-02-27 | 歌尔股份有限公司 | Material cavity dividing device and material cavity dividing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113522770A (en) | High-precision online detection system based on 3D vision | |
| US20190362480A1 (en) | Methods and system for improved quality inspection | |
| KR20180106856A (en) | Automatic optical inspection system and operating method thereof | |
| CN104690007A (en) | Human-machine combined magnetic core on-line detection system and detection method | |
| CN103776841A (en) | Automatic detection device and method of synthetic leather defect | |
| CN110560376B (en) | Product surface defect detection method and device | |
| CN108872265A (en) | Detection method, apparatus and system | |
| CN105690393A (en) | Four-axle parallel robot sorting system based on machine vision and sorting method thereof | |
| CN110672626B (en) | Method for detecting particle defects on surface of middle frame of mobile phone shell | |
| CN113066195A (en) | Power equipment inspection method and device, AR glasses and storage medium | |
| CN112070000A (en) | Intelligent recognition algorithm training method and device, terminal server and storage medium | |
| CN112084964A (en) | Product identification apparatus, method and storage medium | |
| CN110160587B (en) | Capacitance detection method and system | |
| CN110044921A (en) | Lithium battery open defect detection system and method | |
| CN116593479A (en) | Method, device, equipment and storage medium for detecting appearance quality of battery cover plate | |
| CN109240069B (en) | Automatic detection system for production of liquid crystal display clock products | |
| CN112304965A (en) | Multi-scene fuse box visual detection system | |
| CN105548210A (en) | Detection method for American-standard power source extension wire based on machine vision | |
| CN106846302B (en) | Detection method for correctly taking tool and examination table based on method | |
| CN115661091A (en) | High-precision intelligent control system for gear box machining based on machine vision detection technology | |
| CN113182205B (en) | Full-automatic robot photoelectric detection method for mobile phone parts based on Internet | |
| CN115330751A (en) | Bolt detection and positioning method based on YOLOv5 and Realsense | |
| CN111942426B (en) | Hot infrared-based axle temperature measurement method for molten iron transportation locomotive | |
| CN210513211U (en) | Capacitance detection device | |
| CN205552536U (en) | Four -axis parallel robot letter sorting system based on machine vision |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20211022 |
|
| WW01 | Invention patent application withdrawn after publication |