Machine vision image recognition speed measurement device, method and system

By designing machine vision image recognition speed measurement equipment, using the central processing module to control the rotation of the turntable and display speed of the display screen, combined with the detection server, the problems of high complexity and uncontrollable stability are solved, and efficient image recognition speed measurement is achieved , and provides professional metering equipment traceability.

CN118488188BActive Publication Date: 2024-11-22NANJING PRODUCT QUALITY SUPERVISION & INSPECTION INSTITUTE (NANJING QUALITY DEVELOPMENT & ADVANCED TECHNOLOGY APPLICATION RESEARCH INSTITUTE)
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410949283.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-22
Estimated Expiration
2044-07-16

AI Technical Summary

Technical Problem

The existing machine vision image recognition speed measurement methods have problems with high detection operation complexity and uncontrollable stability, and lack professional metering equipment traceability.

Method used

A machine vision image recognition speed measurement device is designed, including fixtures, brackets, turntables, motors, central processing modules, display screens and magnetic workpieces. The central processing module controls the motor to drive the turntables to cooperate with the detection server and the image being tested to collect. The unit completes image recognition speed measurement, simplifying operation and improving stability.

Benefits of technology

It has achieved simplified detection operations, improved the controllability and accuracy of the measurement results, solved the problems of high complexity and uncontrollable stability in traditional methods, and provided professional metering equipment traceability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118488188B_ABST
    Figure CN118488188B_ABST
Patent Text Reader

Abstract

The present application relates to a machine vision image recognition speed measurement device, method and system. The device includes: a motor, a display screen and a central processing module are electrically connected, the motor and the central processing module are fixedly installed in the cavity of the base, a turntable is movably connected to the motor, the turntable is located on the upper surface of the base, a clamp is movably installed at one end of the bracket, the other end of the bracket is fixed on the base, and N magnetic workpieces are detachably adsorbed on the turntable; when measuring the machine vision image recognition speed, by fixing the image acquisition unit to be measured on the bracket through the clamp, when the central processing module receives the start measurement control instruction sent by the detection server, the motor drives the turntable to rotate at the set speed, and controls the display screen to display the speed of the turntable and the measurement operation countdown, cooperates with the detection server and the image acquisition unit to be measured to complete the image recognition speed measurement, and solves the problems of high complexity and uncontrollable stability of traditional detection operations.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a machine vision image recognition speed measurement device, method and system. Background Art

[0002] As an important branch of artificial intelligence, machine vision is an important component of new productivity. Its significance lies in using machine vision image processing to replace human eyes to achieve measurement and judgment. From a technical point of view, machine vision is an excellent comprehensive technology that cleverly integrates image processing, mechanical engineering technology, control theory, electric light source lighting, optical imaging, sensor technology, analog and digital video technology, and computer software and hardware technology.

[0003] There are two main methods for measuring the speed of machine vision image recognition: one is that during the R&D and production stage, the machine vision system R&D company uses technical means to import pre-collected image data code streams in the algorithm processing link, and makes judgments by obtaining the timestamp output in the analysis system log; the other is to record the number of workpieces processed by the system under test within n equal time periods T on the running assembly line. Method 1 lacks consideration of actual application scenarios, and its detection response speed is lower than the actual value. Although the test method of method 2 is tested in actual application scenarios, the actual operation is highly complex, and the speed and stability of the running assembly line are not highly controllable. Summary of the invention

[0004] Based on this, it is necessary to provide a machine vision image recognition speed measurement device, method and system that can solve the problems of high complexity and uncontrollable stability of traditional detection operations in response to the above technical problems.

[0005] A machine vision image recognition speed measuring device, the machine vision image recognition speed measuring device comprising: a fixture, a bracket, a turntable, a motor, a central processing module, a display screen, N magnetic workpieces with patterns attached thereto, and a base with an internal cavity;

[0006] The motor, the display screen and the central processing module are electrically connected, the motor and the central processing module are fixedly installed in the cavity of the base, the turntable is movably connected to the motor, the turntable is located on the upper surface of the base, the clamp is movably installed at one end of the bracket, the other end of the bracket is fixed on the base, and the N magnetic workpieces are detachably adsorbed on the turntable;

[0007] When measuring the machine vision image recognition speed, the image acquisition unit to be measured is fixed on the bracket by the clamp, and the focal length, aperture and distance between the image acquisition unit to be measured and the turntable are adjusted so that the shooting angle of the image acquisition unit to be measured is facing the magnetic workpiece. When the central processing module receives the start measurement control instruction sent by the detection server, it controls the motor to drive the turntable to rotate at the set speed, and controls the display screen to display the speed of the turntable and the measurement operation countdown, and cooperates with the detection server and the image acquisition unit to complete the machine vision image recognition speed measurement.

[0008] In one embodiment, the central processing module includes: a motor drive unit, a central processing unit and a communication unit;

[0009] The motor drive unit is connected to the motor, the motor drive unit and the communication unit are connected to the central processing unit, and the central processing unit is connected to the display screen;

[0010] The central processing unit communicates with the detection server through the communication unit to obtain a control instruction to start measurement, thereby controlling the motor drive unit to drive the motor to drive the turntable to rotate at a set speed, and controlling the display screen to display the speed of the turntable and the measurement operation countdown.

[0011] In one of the embodiments, the machine vision image recognition speed determination device further comprises: a speed knob;

[0012] The speed knob is connected to the central processing unit;

[0013] The speed knob is used to manually adjust the speed of the turntable.

[0014] In one of the embodiments, the diameter of the turntable is greater than or equal to 16 cm, and the turntable is made of stainless steel, so that the magnetic workpiece can be adsorbed on the surface of the turntable, and the clamp can adjust the position along the horizontal and vertical directions of the bracket, thereby adjusting the shooting angle of the image acquisition unit under test and the distance between it and the turntable.

[0015] A method for measuring machine vision image recognition speed, the method comprising:

[0016] According to the requirements or upper limit of the recognition speed of the image acquisition unit to be tested, N magnetic workpieces with patterns attached are selected and fixed on the turntable of the machine vision image recognition speed measurement device, and the stability of the turntable and the magnetic workpiece is evaluated;

[0017] Fix the image acquisition unit to be tested on the bracket of the machine vision image recognition speed measuring device by a clamp, adjust the focal length, aperture and distance between the image acquisition unit to be tested and the turntable of the machine vision image recognition speed measuring device, so that the shooting angle of the image acquisition unit to be tested faces the magnetic workpiece, and configure the clarity of the image acquisition of the image acquisition unit to be tested through the upper computer software interface of the detection server;

[0018] The rotation speed of the turntable of the machine vision image recognition speed measuring device and the measurement running countdown are configured through the upper computer software interface of the detection server, and the automatic measurement button is clicked to send a start measurement control instruction to the machine vision image recognition speed measuring device and the measured image acquisition unit to start the machine vision image recognition speed measurement;

[0019] After the countdown of the measurement operation ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test.

[0020] In one embodiment, after the countdown of the measurement operation ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test, including:

[0021] After the countdown of the measurement operation ends, the actual number of recognized images of the image acquisition unit under test is obtained;

[0022] Determine the theoretical number of recognized images this time according to the product of the number of the magnetically attracted workpieces, the rotation speed of the turntable and the countdown of the measurement operation;

[0023] The actual number of recognized images is compared with the theoretical number of recognized images, and the difference between the actual number of recognized images and the theoretical number of recognized images is less than or equal to 1% of the theoretical number of recognized images. If the difference is less than or equal to 1% of the theoretical number of recognized images, the machine vision image recognition speed measurement of the image acquisition unit under test passes; if the difference is greater than 1% of the theoretical number of recognized images, the machine vision image recognition speed measurement of the image acquisition unit under test fails.

[0024] In one of the embodiments, the value of N is determined based on the maximum speed requirement of the image acquisition unit under test and the maximum rotational speed of the turntable of the machine vision image recognition speed measuring device. If the maximum rotational speed of the turntable is greater than the maximum speed of the image acquisition unit under test, one magnetic workpiece is fixed on the turntable. If the maximum rotational speed of the turntable is less than or equal to the maximum speed of the image acquisition unit under test, more than two magnetic workpieces are fixed on the turntable.

[0025] In one of the embodiments, the host computer software of the detection server is written in C# and supports installation in operating systems of Windows XP or above. The host computer software interface of the detection server includes: acquisition image display, turntable speed configuration, measurement operation countdown configuration, measured image acquisition unit configuration, measurement result display and automatic measurement start button.

[0026] In one of the embodiments, the detection server communicates with the machine vision image recognition speed measurement device via an RS232 bus, and the function code 0x01 in the communication protocol represents a tachometer and 0x10 represents a timer.

[0027] A machine vision image recognition speed measurement system, the system comprising: a measured image acquisition unit, a machine vision image recognition speed measurement device and a detection server;

[0028] The image acquisition unit to be tested is connected to the detection server network, and the machine vision image recognition speed measuring device is connected to the detection server network;

[0029] According to the requirements or upper limit of the recognition speed of the image acquisition unit to be tested, N magnetic workpieces with patterns attached are selected and fixed on the turntable of the machine vision image recognition speed measurement device, and the stability of the turntable and the magnetic workpiece is evaluated;

[0030] Fix the image acquisition unit to be tested on the bracket of the machine vision image recognition speed measuring device by a clamp, adjust the focal length, aperture and distance between the image acquisition unit to be tested and the turntable of the machine vision image recognition speed measuring device, so that the shooting angle of the image acquisition unit to be tested faces the magnetic workpiece, and configure the clarity of the image acquisition of the image acquisition unit to be tested through the upper computer software interface of the detection server;

[0031] The rotation speed of the turntable of the machine vision image recognition speed measuring device and the measurement running countdown are configured through the upper computer software interface of the detection server, and the automatic measurement button is clicked to send a start measurement control instruction to the machine vision image recognition speed measuring device and the measured image acquisition unit to start the machine vision image recognition speed measurement;

[0032] After the countdown of the measurement operation ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test.

[0033] The above-mentioned machine vision image recognition speed measurement device, method and system are electrically connected to the central processing module through the motor and the display screen. The motor and the central processing module are fixedly installed in the cavity of the base. The turntable is movably connected to the motor. The turntable is located on the upper surface of the base. The clamp is movably installed at one end of the bracket, and the other end of the bracket is fixed on the base. N magnetic workpieces can be detachably adsorbed on the turntable. When measuring the machine vision image recognition speed, the image acquisition unit to be measured is fixed to the bracket through the clamp, and the focal length, aperture and distance between the image acquisition unit to be measured and the turntable are adjusted so that the image acquisition unit to be measured The shooting angle of the image acquisition unit is facing the magnetic workpiece. When the central processing module receives the start measurement control instruction sent by the detection server, it controls the motor to drive the turntable to rotate at the set speed, and controls the display screen to display the speed of the turntable and the measurement operation countdown, and cooperates with the detection server and the image acquisition unit to be tested to complete the machine vision image recognition speed measurement. Therefore, the machine vision image recognition speed measurement device is combined with the detection server to perform the machine vision image recognition speed measurement device on the image acquisition unit to be tested, thereby solving the problems of high complexity and uncontrollable stability of traditional detection operations. Furthermore, it also solves the problem of lack of traceability of professional measuring instruments. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of the front structure of a machine vision image recognition speed measurement device in one embodiment;

[0035] Figure 2 A schematic diagram of the reverse structure of a machine vision image recognition speed measurement device in one embodiment;

[0036] Figure 3 A schematic diagram of the structure of a central processing module in one embodiment;

[0037] Figure 4 A schematic diagram of a process of measuring a machine vision image recognition speed in one embodiment;

[0038] Figure 5 A schematic diagram of a host computer software interface in one embodiment;

[0039] Figure 6 A schematic diagram of RS232 communication protocol instructions in one embodiment;

[0040] Figure 7 A schematic diagram of a flow chart of a method for determining machine vision image recognition speed in another embodiment;

[0041] Figure 8 Schematic diagram of the structure of a machine vision image recognition speed measurement system in one embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] In one embodiment, Figure 1-3 As shown, a machine vision image recognition speed measuring device is provided, which includes: a fixture 1, a bracket 2, a turntable 3, a motor, a central processing module, a display screen, N magnetic workpieces 4 with patterns attached thereto, and a base 5 with an internal cavity; the motor, the display screen and the central processing module are electrically connected, the motor and the central processing module are fixedly installed in the cavity of the base 5, the turntable 3 is movably connected to the motor, the turntable 3 is located on the upper surface of the base 5, the fixture 1 is movably installed at one end of the bracket 2, and the other end of the bracket 2 is fixed on the base 5, and the N magnetic workpieces 4 are detachably adsorbed on the turntable 3.

[0044] Among them, when measuring the machine vision image recognition speed, the image acquisition unit to be measured is fixed on the bracket 2 by the clamp 1, and the focal length, aperture and distance between the image acquisition unit to be measured and the turntable 3 are adjusted, so that the shooting angle of the image acquisition unit to be measured is facing the magnetic workpiece 4. When the central processing module receives the start measurement control instruction sent by the detection server, it controls the motor to drive the turntable 3 to rotate at the set speed, and controls the display screen to display the speed of the turntable 3 and the measurement operation countdown, and cooperates with the detection server and the image acquisition unit to complete the machine vision image recognition speed measurement.

[0045] The image acquisition unit under test may include an industrial camera 61 and a lens 62 , and the industrial camera 61 is integrated with an image acquisition card; the image acquisition card may also be a separate device or integrated in other devices, and connected with the industrial camera 61 to complete image acquisition and recognition.

[0046] The image acquisition unit to be measured may further include a light source, and the installation position of the light source may be determined according to the imaging quality and clarity, etc., which is not limited here.

[0047] The fixture 1 can be moved up and down on the bracket 2, or can be moved left and right based on the bracket 2, so that the shooting angle of the image acquisition unit under test fixed on the fixture 1 and the distance between the turntable 3 are changed. When adjusted to the required position, the fixture 1 can be fixed on the bracket 2 by tightening the fixing knob.

[0048] One end of the fixture 1 is used to connect to the bracket 2, and the other end is used to fix the image acquisition unit to be tested.

[0049] The display screen may include a tachometer display screen 71 and a timer display screen 72 , wherein the tachometer display screen 71 is used to display the current rotation speed of the turntable 3 , and the timer display screen 72 is used to display the countdown of the measurement operation.

[0050] The outer surface of the base 5 is also affixed with a nameplate 8 to record equipment information such as the model and production date of the machine vision image recognition speed measurement equipment.

[0051] In one embodiment, the central processing module includes: a motor drive unit, a central processing unit and a communication unit; the motor drive unit is connected to the motor, the motor drive unit and the communication unit are connected to the central processing unit, and the central processing unit is connected to the display screen; the central processing unit communicates with the detection server through the communication unit to obtain a control instruction to start measuring, thereby controlling the motor drive unit to drive the motor to drive the turntable 3 to rotate at a set speed, and controlling the display screen to display the speed of the turntable 3 and the countdown of the measurement operation.

[0052] The central processing unit may be a single chip microcomputer that can control the rotation speed of the turntable, control the countdown of the turntable operation, and control data transmission.

[0053] In an example, the model of the single chip microcomputer may be STM32F103.

[0054] Among them, the communication unit can be an RJ45 network port 91 and / or an RS232 interface 92, which are fixed on the base 5 and connected to the detection server through the RJ45 network port 91 and / or the RS232 interface 92; it can also be connected to the laboratory management system through the RJ45 network port 91 to monitor and remotely control the working status of the machine vision image recognition speed measurement equipment.

[0055] In one example, one end of the RS232 bus is plugged into the RS232 interface 92 of the machine vision image recognition speed measurement device, and the other end of the RS232 bus is plugged into the RS232 interface of the detection server, so as to achieve communication between the machine vision image recognition speed measurement device and the detection server.

[0056] The central processing module further includes a power interface 10 , which is fixed on the base 5 . The power interface 10 is connected to the central processing unit for accessing power.

[0057] In one embodiment, the machine vision image recognition speed measurement device further includes: a speed knob 12 ; the speed knob 12 is connected to the central processing unit; the speed knob 12 is used to manually adjust the speed of the turntable 3 .

[0058] The rotating speed of the turntable can be manually adjusted by the rotating speed knob 12 .

[0059] Among them, by manually adjusting the turntable speed through the speed knob 12, the stability evaluation of the turntable 3 and the magnetic workpiece 4 of the machine vision image recognition speed measurement device can be performed separately without connecting to the detection server.

[0060] In one example, based on the number of magnetic workpieces placed on the turntable 3, by manually adjusting the turntable speed, it is evaluated whether the N magnetic workpieces 4 placed on the turntable 3 will move at the currently adjusted turntable speed. It is also possible to evaluate the maximum stable speed of the turntable 3 when different numbers of magnetic workpieces 4 are placed on the turntable 3.

[0061] In one embodiment, the rotating speed of the turntable is not less than 180 rpm / min.

[0062] In one embodiment, the diameter of the turntable 3 is greater than or equal to 16 cm, and the turntable 3 is made of stainless steel, so that the magnetic workpiece 4 can be adsorbed on the surface of the turntable 3, and the clamp 1 can adjust the position along the horizontal and vertical directions of the bracket 2, thereby adjusting the shooting angle of the image acquisition unit under test and the distance between it and the turntable 3.

[0063] In one embodiment, the machine vision image recognition speed measuring device further comprises a switch 13, which is connected to the central processing module and is used to control the start and stop of the machine vision image recognition speed measuring device.

[0064] The above-mentioned machine vision image recognition speed measuring device is electrically connected to the central processing module through a motor and a display screen. The motor and the central processing module are fixedly installed in the cavity of the base 5. The turntable 3 is movably connected to the motor. The turntable 3 is located on the upper surface of the base 5. The fixture 1 is movably installed at one end of the bracket 2, and the other end of the bracket 2 is fixed on the base 5. N magnetic workpieces 4 can be detachably adsorbed on the turntable 3. When measuring the machine vision image recognition speed, the image acquisition unit to be measured is fixed on the bracket 2 through the fixture 1, and the focal length, aperture and distance between the image acquisition unit to be measured and the turntable 3 are adjusted, so that the shooting speed of the image acquisition unit to be measured is adjusted. The viewing angle is facing the magnetic workpiece 4. When the central processing module receives the start measurement control instruction sent by the detection server, it controls the motor to drive the turntable 3 to rotate at the set speed, and controls the display screen to display the speed of the turntable 3 and the measurement operation countdown, and cooperates with the detection server and the image acquisition unit to complete the machine vision image recognition speed measurement. Therefore, the machine vision image recognition speed measurement device is combined with the detection server to perform the machine vision image recognition speed measurement device on the image acquisition unit to solve the problems of high complexity and uncontrollable stability of traditional detection operations. Furthermore, it also solves the problem of lack of traceability of professional measuring instruments.

[0065] In one embodiment, Figure 4 As shown, a method for determining the speed of machine vision image recognition is provided, comprising the following steps:

[0066] Step S220, according to the recognition speed requirement or upper limit of the image acquisition unit to be tested, select N magnetic workpieces with patterns attached and fix them on the turntable of the machine vision image recognition speed measurement device, and evaluate the stability of the turntable and the magnetic workpieces.

[0067] Step S240, fix the image acquisition unit under test on the bracket of the machine vision image recognition speed measuring device by a clamp, adjust the focal length, aperture and distance between the image acquisition unit under test and the turntable of the machine vision image recognition speed measuring device, so that the shooting angle of the image acquisition unit under test faces the magnetic workpiece, and configure the clarity of image acquisition of the image acquisition unit under test through the host computer software interface of the detection server.

[0068] Step S260, configuring the rotation speed of the turntable of the machine vision image recognition speed measuring device and the measurement running countdown through the host computer software interface of the detection server, and clicking the automatic measurement button to send a start measurement control instruction to the machine vision image recognition speed measuring device and the measured image acquisition unit to start the machine vision image recognition speed measurement;

[0069] Step S280, after the countdown of the measurement operation ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test.

[0070] Among them, the host computer software is installed on the detection server to control the machine vision image recognition speed measurement equipment and the image acquisition unit under test, so as to realize the automatic measurement of the recognition speed of the image acquisition unit under test.

[0071] Among them, the machine vision image recognition speed measurement equipment is composed of a hardware core layer and a software control layer. The hardware core layer mainly includes a central processing module, a fixture, a bracket, a turntable, a motor, a display screen, N magnetic workpieces with patterns attached and a base with an internal cavity. Among them, the central processing module is composed of a single-chip microcomputer, a motor drive unit, a memory, a communication unit, a tachometer and a timer; the software control layer mainly controls the turntable speed, controls the turntable operation countdown and controls data transmission through the single-chip microcomputer C program to realize communication with the detection server.

[0072] The machine vision image recognition speed measuring device and the detection server may communicate via an RS232 bus or an RJ45 network port.

[0073] The image acquisition unit under test and the detection server may communicate via an RS232 bus or an RJ45 network port.

[0074] The image acquisition unit under test can configure parameters of the image acquisition unit under test, and control the start and stop of image acquisition.

[0075] Among them, the host computer software configures the clarity of image acquisition of the image acquisition unit under test, which can be linked to the industrial camera configuration software of the image acquisition unit under test through the industrial camera configuration button on the host computer software interface to adjust the image, and all parameters are configured through the RJ45 network port.

[0076] In one embodiment, after the countdown of the measurement operation ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test, including:

[0077] After the countdown of the measurement operation ends, the actual number of recognized images of the image acquisition unit under test is obtained;

[0078] The theoretical number of images to be recognized is determined based on the product of the number of magnetically attracted workpieces, the rotation speed of the turntable, and the countdown of the measurement operation;

[0079] Compare the actual number of recognized images with the theoretical number of recognized images, and check whether the difference between the actual number of recognized images and the theoretical number of recognized images is less than or equal to 1% of the theoretical number of recognized images. If the difference is less than or equal to 1% of the theoretical number of recognized images, the machine vision image recognition speed measurement of the image acquisition unit under test passes; if the difference is greater than 1% of the theoretical number of recognized images, the machine vision image recognition speed measurement of the image acquisition unit under test fails.

[0080] Among them, in the host computer software interface of the detection server, configure the turntable speed and turntable running countdown time of the speed measurement device, click the automatic measurement button to start the test, and after the test, the host computer software will determine whether the test passes. If the test passes, the host computer software interface will display OK, and output the measured value of the image recognition speed on the host computer software interface. If the test fails, the host computer software interface will display NG.

[0081] In one example, the measurement passes and outputs the measurement result x fps, that is, the image recognition speed of the machine vision system of the image acquisition unit under test is x frames per second.

[0082] In one embodiment, the value of N is determined based on the maximum speed requirement of the image acquisition unit under test and the maximum rotational speed of the turntable of the machine vision image recognition speed measuring device. If the maximum rotational speed of the turntable is greater than the maximum speed of the image acquisition unit under test, one magnetic workpiece is fixed on the turntable. If the maximum rotational speed of the turntable is less than or equal to the maximum speed of the image acquisition unit under test, more than two magnetic workpieces are fixed on the turntable.

[0083] It should be understood that if the maximum rotation speed of the turntable is greater than the maximum speed of the image acquisition unit under test, one magnetic workpiece is fixed on the turntable; if the maximum rotation speed of the turntable is less than or equal to the maximum speed of the image acquisition unit under test, more than two magnetic workpieces are fixed on the turntable to meet the measurement requirements.

[0084] In one embodiment, the host computer software of the detection server is written in C# and supports installation on operating systems of Windows XP and above. The host computer software interface of the detection server includes: acquisition image display, turntable speed configuration, measurement operation countdown configuration, measured image acquisition unit configuration, measurement result display and automatic measurement start button.

[0085] The schematic diagram of the upper computer software interface is as follows: Figure 5 As shown, the upper computer software interface displays the rotation speed, countdown, measurement results, collected image display, industrial camera configuration button and automatic measurement button, etc.

[0086] In one embodiment, the detection server communicates with the machine vision image recognition speed measurement device via an RS232 bus, and the function code 0x01 in the communication protocol represents a tachometer and 0x10 represents a timer.

[0087] Among them, the RS232 communication protocol instruction diagram is as follows Figure 6 shown.

[0088] The above-mentioned machine vision image recognition speed measurement method selects N magnetic workpieces with patterns attached thereto and fixes them on the turntable of the machine vision image recognition speed measurement device according to the recognition speed requirement or upper limit of the image acquisition unit under test, and evaluates the stability of the turntable and the magnetic workpiece; fixes the image acquisition unit under test on the bracket of the machine vision image recognition speed measurement device through a fixture, adjusts the focal length, aperture and distance between the image acquisition unit under test and the turntable of the machine vision image recognition speed measurement device, so that the shooting angle of the image acquisition unit under test faces the magnetic workpiece, and configures the clarity of the image acquisition of the image acquisition unit under test through the host computer software interface of the detection server; configures the machine vision image recognition speed through the host computer software interface of the detection server. The speed of the turntable of the speed measuring device and the measurement running countdown are measured, and the automatic measurement button is clicked to send a start measurement control instruction to the machine vision image recognition speed measuring device and the image acquisition unit under test to start the machine vision image recognition speed measurement; after the measurement running countdown ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test. Thus, the machine vision image recognition speed measuring device is combined with the detection server to measure the image acquisition unit under test, thereby solving the problems of high complexity and uncontrollable stability of traditional detection operations, and further, solving the problems of lack of traceability of professional measuring instruments.

[0089] In one embodiment, Figure 7 As shown, a method for measuring machine vision image recognition speed is provided, which specifically includes:

[0090] Start the machine vision image recognition speed measurement equipment, adjust the positions of N magnetic workpieces to fix the magnetic workpieces, set the turntable speed of the machine vision image recognition speed measurement equipment, evaluate the turntable rotation stability until the rotation stability passes, start the host computer software of the detection server, start and configure the image acquisition unit, evaluate the static image recognition stability (the turntable does not move, adjust the industrial camera to focus on the magnetic workpiece, and the image is clear and recognizable from the host computer software interface) until it passes, the host computer software configures the turntable speed R and the measurement operation countdown T, and when the measurement operation countdown ends, the machine vision image recognition speed measurement equipment and the image acquisition unit stop working, and the host computer software records the actual number of images recognized by the image acquisition unit Q, whether N×R×T (that is, the theoretical number of recognized images) is approximately equal to Q (approximately equal to can be the difference between the actual number of recognized images and the theoretical number of recognized images is less than or equal to 1% of the theoretical number of recognized images), if yes, the measurement passes, otherwise, the measurement fails.

[0091] It should be understood that although Figure 4 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 4 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0092] In one embodiment, Figure 8 As shown, a machine vision image recognition speed measurement system is provided, the system includes: a measured image acquisition unit, a machine vision image recognition speed measurement device and a detection server; the measured image acquisition unit is connected to the detection server network, and the machine vision image recognition speed measurement device and the detection server are connected to the network.

[0093] According to the requirements or upper limit of the recognition speed of the image acquisition unit under test, N magnetic workpieces with patterns attached are selected and fixed on the turntable of the machine vision image recognition speed measurement device, and the stability of the turntable and the magnetic workpiece is evaluated; the image acquisition unit under test is fixed on the bracket of the machine vision image recognition speed measurement device through a clamp, and the focal length, aperture and distance between the image acquisition unit under test and the turntable of the machine vision image recognition speed measurement device are adjusted so that the shooting angle of the image acquisition unit under test faces the magnetic workpiece, and the clarity of the image acquisition of the image acquisition unit under test is configured through the host computer software interface of the detection server; the rotation speed of the turntable of the machine vision image recognition speed measurement device and the measurement countdown are configured through the host computer software interface of the detection server, and the automatic measurement button is clicked to send a start measurement control instruction to the machine vision image recognition speed measurement device and the image acquisition unit under test to start the machine vision image recognition speed measurement; after the measurement countdown ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test.

[0094] Among them, the machine vision image recognition speed measurement device and the detection server can be connected through an RS232 bus or through an RJ45 network port.

[0095] The image acquisition unit under test may include an industrial camera, an image acquisition card, a light source and a lens.

[0096] Among them, the machine vision image recognition speed measurement equipment is composed of a hardware core layer and a software control layer. The hardware core layer mainly includes a central processing module, a fixture, a bracket, a turntable, a motor, a display screen, N magnetic workpieces with patterns attached and a base with an internal cavity. Among them, the central processing module is composed of a single-chip microcomputer, a motor drive unit, a memory, a communication unit, a tachometer and a timer; the software control layer mainly controls the turntable speed, controls the turntable operation countdown and controls data transmission through the single-chip microcomputer C program to realize communication with the detection server.

[0097] The above-mentioned machine vision image recognition speed measurement system selects N magnetic workpieces with patterns attached thereto and fixes them on the turntable of the machine vision image recognition speed measurement device according to the recognition speed requirement or upper limit of the image acquisition unit under test, and evaluates the stability of the turntable and the magnetic workpiece; fixes the image acquisition unit under test on the bracket of the machine vision image recognition speed measurement device through a fixture, adjusts the focal length, aperture and distance between the image acquisition unit under test and the turntable of the machine vision image recognition speed measurement device so that the shooting angle of the image acquisition unit under test faces the magnetic workpiece, and configures the clarity of the image acquisition of the image acquisition unit under test through the host computer software interface of the detection server; configures the machine vision image recognition speed through the host computer software interface of the detection server. The speed of the turntable of the speed measuring device and the measurement running countdown are measured, and the automatic measurement button is clicked to send a start measurement control instruction to the machine vision image recognition speed measuring device and the image acquisition unit under test to start the machine vision image recognition speed measurement; after the measurement running countdown ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test. Thus, the machine vision image recognition speed measuring device is combined with the detection server to measure the image acquisition unit under test, thereby solving the problems of high complexity and uncontrollable stability of traditional detection operations, and further, solving the problems of lack of traceability of professional measuring instruments.

[0098] The specific definition of the machine vision image recognition speed measurement system can be found in the definition of the machine vision image recognition speed measurement method mentioned above, which will not be repeated here. Each module in the above-mentioned machine vision image recognition speed measurement system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A machine vision image recognition speed measurement device, characterized in that: The machine vision image recognition speed measurement device includes: a fixture, a bracket, a turntable, a motor, a central processing module, a display screen, N magnetic workpieces with patterns attached thereto, and a base with an internal cavity; The motor, the display screen and the central processing module are electrically connected, the motor and the central processing module are fixedly installed in the cavity of the base, the turntable is movably connected to the motor, the turntable is located on the upper surface of the base, the clamp is movably installed at one end of the bracket, the other end of the bracket is fixed on the base, and the N magnetic workpieces are detachably adsorbed on the turntable; When measuring the machine vision image recognition speed, the image acquisition unit to be measured is fixed on the bracket by the clamp, and the focal length, aperture and distance between the image acquisition unit to be measured and the turntable are adjusted so that the shooting angle of the image acquisition unit to be measured is facing the magnetic workpiece. When the central processing module receives the start measurement control instruction sent by the detection server, it controls the motor to drive the turntable to rotate at a set speed, and controls the display screen to display the speed of the turntable and the measurement countdown, and cooperates with the detection server and the image acquisition unit to complete the machine vision image recognition speed measurement, wherein the speed of the turntable and the measurement countdown of the machine vision image recognition speed measurement device are configured through the host computer software interface of the detection server, and the automatic measurement button is clicked to send the start measurement control instruction to the machine vision image recognition speed measurement device and the image acquisition unit to start the machine vision image recognition speed measurement; after the measurement countdown ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit to be measured according to the actual recognition image number and theoretical recognition image number of the image acquisition unit to be measured.

2. The machine vision image recognition speed measuring device according to claim 1, characterized in that: The central processing module includes: a motor drive unit, a central processing unit and a communication unit; The motor drive unit is connected to the motor, the motor drive unit and the communication unit are connected to the central processing unit, and the central processing unit is connected to the display screen; The central processing unit communicates with the detection server through the communication unit to obtain a control instruction to start measurement, thereby controlling the motor drive unit to drive the motor to drive the turntable to rotate at a set speed, and controlling the display screen to display the speed of the turntable and the measurement operation countdown.

3. The machine vision image recognition speed measuring device according to claim 2, characterized in that: The machine vision image recognition speed measurement device also includes: a speed knob; The speed knob is connected to the central processing unit; The speed knob is used to manually adjust the speed of the turntable.

4. The machine vision image recognition speed measuring device according to claim 1, characterized in that: The diameter of the turntable is greater than or equal to 16 cm. The turntable is made of stainless steel so that the magnetic workpiece can be adsorbed on the surface of the turntable. The clamp can adjust the position along the horizontal and vertical directions of the bracket to adjust the shooting angle of the image acquisition unit under test and the distance between it and the turntable.

5. A method for measuring machine vision image recognition speed, characterized in that: The machine vision image recognition speed determination method comprises: According to the requirements or upper limit of the recognition speed of the image acquisition unit to be tested, N magnetic workpieces with patterns attached are selected and fixed on the turntable of the machine vision image recognition speed measurement device, and the stability of the turntable and the magnetic workpiece is evaluated; Fix the image acquisition unit to be tested on the bracket of the machine vision image recognition speed measuring device by a clamp, adjust the focal length, aperture and distance between the image acquisition unit to be tested and the turntable of the machine vision image recognition speed measuring device, so that the shooting angle of the image acquisition unit to be tested faces the magnetic workpiece, and configure the clarity of the image acquisition of the image acquisition unit to be tested through the upper computer software interface of the detection server; The rotation speed of the turntable of the machine vision image recognition speed measuring device and the measurement running countdown are configured through the upper computer software interface of the detection server, and the automatic measurement button is clicked to send a start measurement control instruction to the machine vision image recognition speed measuring device and the measured image acquisition unit to start the machine vision image recognition speed measurement; After the countdown of the measurement operation ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test.

6. The method for measuring machine vision image recognition speed according to claim 5, characterized in that: After the countdown of the measurement operation ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test, including: After the countdown of the measurement operation ends, the actual number of recognized images of the image acquisition unit under test is obtained; Determine the theoretical number of recognized images this time according to the product of the number of the magnetically attracted workpieces, the rotation speed of the turntable and the countdown of the measurement operation; The actual number of recognized images is compared with the theoretical number of recognized images, and the difference between the actual number of recognized images and the theoretical number of recognized images is less than or equal to 1% of the theoretical number of recognized images. If the difference is less than or equal to 1% of the theoretical number of recognized images, the machine vision image recognition speed measurement of the image acquisition unit under test passes; if the difference is greater than 1% of the theoretical number of recognized images, the machine vision image recognition speed measurement of the image acquisition unit under test fails.

7. The method for measuring machine vision image recognition speed according to claim 5, characterized in that: The value of N is determined based on the maximum speed requirement of the image acquisition unit under test and the maximum rotational speed of the turntable of the machine vision image recognition speed measuring equipment. If the maximum rotational speed of the turntable is greater than the maximum speed of the image acquisition unit under test, one magnetic workpiece is fixed on the turntable. If the maximum rotational speed of the turntable is less than or equal to the maximum speed of the image acquisition unit under test, more than two magnetic workpieces are fixed on the turntable.

8. The method for measuring machine vision image recognition speed according to claim 5, characterized in that: The host computer software of the detection server is written in C# and supports installation in operating systems of Windows XP and above. The host computer software interface of the detection server includes: acquisition image display, turntable speed configuration, measurement operation countdown configuration, measured image acquisition unit configuration, measurement result display and automatic measurement start button.

9. The method for measuring machine vision image recognition speed according to claim 5, characterized in that: The detection server communicates with the machine vision image recognition speed measurement device via an RS232 bus, and the function code 0x01 in the communication protocol represents a tachometer and 0x10 represents a timer.

10. A machine vision image recognition speed measurement system, characterized in that: The machine vision image recognition speed measurement system comprises: a measured image acquisition unit, a machine vision image recognition speed measurement device and a detection server; The image acquisition unit to be tested is connected to the detection server network, and the machine vision image recognition speed measuring device is connected to the detection server network; According to the requirements or upper limit of the recognition speed of the image acquisition unit to be tested, N magnetic workpieces with patterns attached are selected and fixed on the turntable of the machine vision image recognition speed measurement device, and the stability of the turntable and the magnetic workpiece is evaluated; Fix the image acquisition unit to be tested on the bracket of the machine vision image recognition speed measuring device by a clamp, adjust the focal length, aperture and distance between the image acquisition unit to be tested and the turntable of the machine vision image recognition speed measuring device, so that the shooting angle of the image acquisition unit to be tested faces the magnetic workpiece, and configure the clarity of the image acquisition of the image acquisition unit to be tested through the upper computer software interface of the detection server; The rotation speed of the turntable of the machine vision image recognition speed measuring device and the measurement running countdown are configured through the upper computer software interface of the detection server, and the automatic measurement button is clicked to send a start measurement control instruction to the machine vision image recognition speed measuring device and the measured image acquisition unit to start the machine vision image recognition speed measurement; After the countdown of the measurement operation ends, the host computer software of the detection server determines the image recognition speed measurement result of the image acquisition unit under test according to the actual number of recognized images and the theoretical number of recognized images of the image acquisition unit under test.

Citation Information

Patent Citations

  • Machine vision teaching innovation experiment platform

    CN101174368A

  • Automobile instrument panel detection system and method based on machine vision

    CN111239158A

  • Novel image detection and identification intelligent device

    CN113102270A

  • Sand grading detection system based on machine vision and control method thereof

    CN117871372A

  • Computer vision-based adaptive measurement system and method for geometric parameters in assembly process

    WO2021179400A1