Steel sample excitable point rotation detection method and system based on visual technology
Through the rotation detection method of steel sample excitable point based on vision technology, the defect detection of steel sample is detected using multi-angle rotation detection technology, which solves the data abnormalities and time-waste problems caused by the fixation of the excitation point of the spectrometer, and achieves the efficient and efficient steel sample detection accuracy.
Patent Information
- Application Number
- CN202410968004.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-03-25
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-08
AI Technical Summary
In the existing steel sample detection technology, the fixation of the spectrometer excitation point leads to data abnormalities and the excitation point does not meet the conditions and wastes time or even damages the spectrometer.
Using the rotation detection method of steel sample excitable point based on vision technology, the sample pictures are obtained through the upper computer control of the visual equipment, the reference position coordinates are analyzed and calculated, and the defect detection technology is used to detect the steel sample to screen out the areas that pass the inspection. , generate position data and upload it to the upper computer to provide offset position parameters for the robot system.
It efficiently solves the problem of data abnormalities caused by the fixation of the excitation point of the spectrometer and the problem of wasting time or even damaging the spectrometer due to the failure of the excitation point of the spectrometer, and realizes accurate detection and positioning of the excitation point of the steel sample.
Smart Images

Figure CN118914231A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of steel sample detection, and in particular to a method and system for detecting rotation of excitable points of steel samples based on vision technology. Background Art
[0002] Steel is an alloy mainly composed of iron and doped with other elements. It is one of the main materials used in construction today. Steel also comes in various types, and different usage scenarios require different types of steel. Therefore, testing the properties of steel is indispensable.
[0003] In the steel production process, it is crucial to analyze and test steel samples (i.e. samples taken from the steelmaking process). In particular, the accurate detection and positioning of excitable points (such as inclusions, defects, etc.) in steel samples is of great significance for product quality control. The excitation points of the spectrometer in the steel sample chemical composition inspection system are often fixed excitation points placed by the robot. Therefore, an efficient and accurate method is needed to detect and locate the excitable points of the steel sample. Summary of the invention
[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a method and system for detecting the rotation of an excitable point of a steel sample based on vision technology, so as to solve the problems existing in the above-mentioned background technology.
[0005] The present invention is implemented as follows: a method for detecting rotation of excitable points of steel samples based on visual technology, the method comprising the following steps: A sample image of the steel sample is obtained by controlling a visual device through a host computer, wherein the sample image is an image of a cross section of the steel sample on a layout platform; Analyze and calculate the sample image and obtain the reference position coordinates, where the reference position coordinates are the position of the steel sample in the sample image; Based on the reference position coordinates and using multi-angle rotation detection technology, the steel sample is inspected for defects to screen out qualified areas; The position data of the qualified detected area is obtained by coordinate calculation and uploaded to the host computer, so that the point coordinate information and related information of the sample image are displayed on the host computer interface.
[0006] As a further solution of the present invention: the step of obtaining a sample image of the steel sample by controlling the visual device through the host computer specifically includes: The feedback signal of the layout platform is detected by the upper computer end, and when the feedback signal is detected, the steel sample is placed on the layout platform; The lighting command is sent to the light source device through the upper computer, so that the light source device turns on the light and irradiates the steel sample on the layout platform; The photo taking instruction is sent to the camera device through the host computer to obtain sample pictures of the steel sample, and the visual device includes a light source device and a camera device.
[0007] As a further solution of the present invention: the step of performing defect detection on the steel sample based on the reference position coordinates and according to the multi-angle rotation detection technology specifically includes: Recognize the shape of the steel sample by a visual device to obtain shape information; According to the left side of the base position and using the visual capture algorithm, multiple detection areas are obtained, and the detection areas are circular areas generated by rotating the steel sample center at a specified angle; The detection area is subjected to defect analysis according to a visual program threshold judgment algorithm.
[0008] As a further solution of the present invention: the step of performing defect analysis on the detection area according to the visual program threshold judgment algorithm specifically includes: A predetermined threshold value is set in advance, and the threshold value is used to determine the defect condition of the detection area; identifying the currently selected detection area according to the threshold; When there is a defect in the detection area, it will be displayed that the area is below the specified threshold, and the next detection area will be identified according to the rotation order of the detection areas.
[0009] As a further solution of the present invention: the step of obtaining the position data of the qualified detected area by coordinate calculation and uploading it to the host computer terminal specifically includes: After obtaining the qualified detection area, the center coordinate value of the detection area is calculated according to the shape of the detection area and the reference position coordinates; The center coordinate value is converted into actual position data through transformation calculation; All position data are collated and sent to the host computer to provide offset position parameters for the robot system.
[0010] Another object of the present invention is to provide a steel sample excitable point rotation detection system based on vision technology, the system comprising: A picture acquisition module, used to acquire a sample picture of the steel sample by controlling the visual device through the host computer, wherein the sample picture is a picture of the cross section of the steel sample on the layout platform; A positioning analysis module is used to analyze and calculate the sample image and obtain reference position coordinates, where the reference position coordinates are the position of the steel sample in the sample image; The sample detection module detects defects on the steel sample based on the reference position coordinates and the multi-angle rotation detection technology, and is used to screen out qualified areas; The data sorting module is used to obtain the position data of the qualified detection area through coordinate calculation and upload it to the host computer end, so that the point coordinate information and related information of the sample image are displayed on the host computer end interface.
[0011] As a further solution of the present invention: the picture acquisition module includes: A signal detection unit, used for detecting a feedback signal of the layout platform through the host computer, and when the feedback signal is detected, the steel sample is placed on the layout platform; A light source control unit is used to send a light instruction to the light source device through the host computer, so that the light source device turns on the light and irradiates the steel sample on the layout platform; The camera control unit is used to send a photo command to a camera device through a host computer, so as to obtain a sample picture of the steel sample. The visual device includes a light source device and a camera device.
[0012] As a further solution of the present invention: the sample detection module includes: A steel sample recognition unit, used for recognizing the shape of the steel sample through a visual device to obtain shape information; A visual capture unit, used to obtain multiple detection areas according to the left side of the base position and using a visual capture algorithm, wherein the detection area is a circular area generated by rotating a specified angle around the center of the steel sample; The area judgment unit is used to perform defect analysis on the detection area according to a visual program threshold judgment algorithm.
[0013] As a further solution of the present invention: the data sorting module includes: A coordinate calculation unit, used to calculate the center coordinate value of the detection area according to the shape of the detection area and the reference position coordinates after obtaining the detection area that has passed the detection; A numerical conversion unit, used to convert the center coordinate value into actual position data through transformation calculation; The data transmission unit is used to organize all position data and send them to the host computer to provide offset position parameters for the robot system.
[0014] As a further embodiment of the present invention: Compared with the prior art, the present invention has the following beneficial effects: The present invention is that after the processed steel sample to be tested is placed on the layout platform, the host computer triggers the visual device to take a photo of the steel sample. After the visual processing software obtains the photo, the photo of the steel sample is analyzed. First, the reference position coordinates of the steel sample are obtained by the circle search method, and then the multi-angle rotation detection technology is used to perform rotation detection on multiple areas on the steel sample to determine whether there are defects in the currently selected area, and after finding a suitable number of defect-free areas. The corresponding regional position data is sorted and then transmitted to the host computer to provide the robot system with offset position parameters. In summary, the present invention efficiently solves the problems of data anomalies caused by the fixed excitation point of the spectrometer, wasting time due to the excitation point not meeting the conditions, and even damaging the spectrometer. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 The figure is a flow chart of a method for detecting rotation of excitable points of steel samples based on vision technology.
[0016] Figure 2 The present invention is a flow chart of a method for detecting the rotation of excitable points of steel samples based on vision technology, in which a host computer controls a visual device to obtain a sample image of the steel sample.
[0017] Figure 3 The present invention is a flow chart of defect detection of steel samples based on reference position coordinates and multi-angle rotation detection technology in a steel sample excitable point rotation detection method based on vision technology.
[0018] Figure 4 The present invention is a flow chart of a method for detecting rotation of excitable points of steel samples based on vision technology, in which defect analysis of the detection area is performed according to a visual program threshold judgment algorithm.
[0019] Figure 5 The present invention is a flow chart of a method for detecting rotation of excitable points of steel samples based on visual technology, in which the position data of the qualified detection area is obtained by coordinate calculation and uploaded to a host computer.
[0020] Figure 6 It is a structural schematic diagram of a steel sample excitable point rotation detection system based on vision technology.
[0021] Figure 7 The figure is a schematic diagram of the structure of the image acquisition module in a steel sample excitable point rotation detection system based on vision technology.
[0022] Figure 8 It is a structural schematic diagram of a sample detection module in a steel sample excitable point rotation detection system based on vision technology.
[0023] Fig. 9 The figure is a schematic diagram of the structure of the data sorting module in a steel sample excitable point rotation detection system based on vision technology.
[0024] Fig.10 A schematic diagram of the interface of the visual circle search algorithm software provided in an embodiment of the present invention.
[0025] Fig.11 A schematic diagram of the steel sample end surface detection area provided in an embodiment of the present invention.
[0026] Fig.12 A schematic diagram of the interface of the visual program threshold judgment algorithm software provided in an embodiment of the present invention.
[0027] Fig.13 A schematic diagram of the use of the coordinate calculation software provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0028] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0029] The specific implementation of the present invention is described in detail below in conjunction with specific embodiments.
[0030] like Figure 1 As shown, an embodiment of the present invention provides a method for detecting rotation of excitable points of a steel sample based on visual technology, the method comprising the following steps: S100, controlling a visual device through a host computer to obtain a sample image of the steel sample, wherein the sample image is an image of a cross section of the steel sample on a layout platform; S200, analyzing and calculating the sample image and obtaining reference position coordinates, wherein the reference position coordinates are the position of the steel sample in the sample image; S300, based on the reference position coordinates and using multi-angle rotation detection technology, performs defect detection on the steel sample to screen out qualified areas; S400, obtaining position data of the qualified detected area through coordinate calculation and uploading it to the host computer, so that the point coordinate information and related information of the sample image are displayed on the host computer interface.
[0031] It should be noted that if Fig.10 As shown, a schematic diagram of the interface of the visual circle search algorithm software is provided. The circle search visual algorithm is used to analyze and calculate the position of the processed steel sample, and coordinate information, namely the reference position coordinates, is provided for subsequent calculations and robot grasping. This step is mainly used to locate the steel sample to facilitate various identification processes.
[0032] In the embodiment of the present invention, after the processed steel sample to be tested is placed on the layout platform, the host computer triggers the visual device to take a photo of the steel sample, and after the visual processing software obtains the photo, the photo of the steel sample is analyzed. First, the reference position coordinates of the steel sample are obtained by the circle search method, and then the multi-angle rotation detection technology is used to perform rotation detection on multiple areas on the steel sample to determine whether there are defects in the currently selected area, and after finding a suitable number of defect-free areas. The corresponding regional position data is sorted and then transmitted to the host computer to provide the robot system with offset position parameters. In summary, the present invention efficiently solves the problems of data anomalies caused by the fixed excitation point of the spectrometer, wasting time due to the excitation point not meeting the conditions, and even damaging the spectrometer.
[0033] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of obtaining a sample image of a steel sample by controlling a visual device through a host computer specifically includes: S101, detecting a feedback signal of the layout platform through the host computer, and when the feedback signal is detected, the steel sample is placed on the layout platform; S102, sending a light instruction to the light source device through the host computer, so that the light source device turns on the light and illuminates the steel sample on the layout platform; S103, sending a photo taking instruction to a camera device through a host computer to obtain a sample picture of the steel sample, wherein the visual device includes a light source device and a camera device.
[0034] In the embodiments of the present invention, generally speaking, the end face of the steel sample needs to be processed and leveled before detection can be carried out. After the steel sample is placed on the layout platform, it needs to be fixed. Generally, a triangular clamp is used to fix the steel sample. The triangular clamp is a mechanical action, which means that relevant control instructions are generated. The feedback signal can be used to identify whether there is a steel sample on the layout platform. The light source device is used to fill in the light for the end face of the steel sample, so that the camera device can take clearer sample pictures.
[0035] like Figure 3 As shown, as a preferred embodiment of the present invention, the step of performing defect detection on the steel sample based on the reference position coordinates and according to the multi-angle rotation detection technology specifically includes: S301, identifying the shape of the steel sample by a visual device to obtain shape information; S302, obtaining a plurality of detection areas according to the reference position coordinates and using a visual capture algorithm, wherein the detection areas are circular areas generated by rotating a specified angle around the center of the steel sample; S303, performing defect analysis on the detection area according to a visual program threshold judgment algorithm.
[0036] In the embodiment of the present invention, Fig.11 This is a schematic diagram of the detection area of the steel sample end face, refer to Fig.11 The content shown is the visual program rotation grabbing algorithm, which can select the detection area at multiple positions and multiple rotation angles in the steel sample photo. According to the shape of the steel sample, multiple detection areas are generated by rotating the angle around the center of the circle inside, and the corresponding information data of the qualified area is obtained in the subsequent detection process.
[0037] like Figure 4 As shown, as a preferred embodiment of the present invention, the step of performing defect analysis on the detection area according to the visual program threshold judgment algorithm specifically includes: S3031, a preset threshold value, wherein the threshold value is used to determine the defect condition of the detection area; S3032, identifying the currently selected detection area according to the threshold; S3033, when there is a defect in the detection area, it will be displayed that the area is below the specified threshold, and the next detection area will be identified according to the rotation order of the detection area.
[0038] In the embodiment of the present invention, Fig.12 This is a schematic diagram of the interface of the visual program threshold judgment algorithm software, refer to Fig.12 Content, the visual program threshold judgment algorithm is to analyze the defects in the current detection area, set the debugged threshold, and identify the defects in the current detection area. If there are defects, the corresponding area will be displayed below the set threshold, which is regarded as a defect in the area, and automatically rotate to the next detection area until a suitable number of qualified areas are found.
[0039] like Figure 5 As shown, as a preferred embodiment of the present invention, the step of obtaining the position data of the qualified detected area by coordinate calculation and uploading it to the host computer specifically includes: S401, after obtaining a qualified detection area, calculating the center coordinate value of the detection area center according to the shape of the detection area and the reference position coordinates; S402, converting the center coordinate value into actual position data through transformation calculation; S403, sorting out all the position data and sending them to the host computer to provide offset position parameters for the robot system.
[0040] In the embodiment of the present invention, Fig.13 This is a schematic diagram of the use of coordinate calculation software, such as Fig.13As shown in the figure, the coordinate calculation is used to obtain the coordinates of the area after the inspection is qualified, and the coordinate value of the center of the circle in the selected area is calculated. The actual position value is calculated by transformation, and the final position value is sent to the host computer to provide the robot with offset position parameters.
[0041] like Figure 6 As shown, an embodiment of the present invention further provides a steel sample excitable point rotation detection system based on visual technology, the system comprising: The image acquisition module 100 is used to acquire a sample image of the steel sample by controlling the visual device through the host computer, wherein the sample image is an image of the cross section of the steel sample on the layout platform; Positioning analysis module 200, used to analyze and calculate according to the sample picture and obtain reference position coordinates, wherein the reference position coordinates are the position of the steel sample in the sample picture; The sample detection module 300 performs defect detection on the steel sample based on the reference position coordinates and according to the multi-angle rotation detection technology, so as to screen out the qualified areas; The data sorting module 400 is used to obtain the position data of the qualified detection area through coordinate calculation and upload it to the host computer end, so that the point coordinate information and related information of the sample image are displayed on the host computer end interface.
[0042] In the embodiment of the present invention, in the embodiment of the present invention, after the processed steel sample to be tested is placed on the layout platform, the host computer triggers the visual device to take a photo of the steel sample, and after the visual processing software obtains the photo, the photo of the steel sample is analyzed. First, the reference position coordinates of the steel sample are obtained by the circle search method, and then the multi-angle rotation detection technology is used to perform rotation detection on multiple areas on the steel sample to determine whether there are defects in the currently selected area, and after finding a suitable number of defect-free areas. The corresponding regional position data is sorted and then transmitted to the host computer to provide the robot system with offset position parameters. In summary, the present invention efficiently solves the problems of data anomalies caused by the fixed excitation point of the spectrometer, wasting time due to the excitation point not meeting the conditions, and even damaging the spectrometer.
[0043] like Figure 7 As shown, as a preferred embodiment of the present invention, the picture acquisition module includes: The signal detection unit 101 is used to detect the feedback signal of the layout platform through the host computer. When the feedback signal is detected, the steel sample is placed on the layout platform; The light source control unit 102 is used to send a light instruction to the light source device through the host computer, so that the light source device turns on the light and irradiates the steel sample on the layout platform; The camera control unit 103 is used to send a photo taking instruction to a camera device via a host computer, so as to obtain a sample image of the steel sample. The visual device includes a light source device and a camera device.
[0044] like Figure 8 As shown, as a preferred embodiment of the present invention, the sample detection module 300 includes: A steel sample recognition unit 300 is used to recognize the shape of the steel sample by a visual device to obtain shape information; A visual capture unit 301 is used to obtain multiple detection areas according to the left side of the base position and using a visual capture algorithm, wherein the detection area is a circular area generated by rotating a specified angle around the center of the steel sample; The area judgment unit 302 is used to perform defect analysis on the detection area according to the visual program threshold judgment algorithm.
[0045] like Fig. 9 As shown, as a preferred embodiment of the present invention, the data sorting module 400 includes: A coordinate calculation unit 401 is used to calculate the center coordinate value of the detection area according to the shape of the detection area and the reference position coordinates after obtaining the detection area that has passed the detection; A numerical conversion unit 402, used to convert the circular coordinate numerical value into actual position data through transformation calculation; The data transmission unit 403 is used to organize all the position data and send them to the host computer to provide offset position parameters for the robot system.
[0046] The above only describes in detail the preferred embodiments of the present invention, which is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
[0047] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.
[0048] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0049] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the disclosure in the specification and examples. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.
Claims
1. A method for detecting rotation of excitable points of steel samples based on visual technology, characterized in that: The method comprises the following steps: A sample image of the steel sample is obtained by controlling a visual device through a host computer, wherein the sample image is an image of a cross section of the steel sample on a layout platform; Analyze and calculate the sample image and obtain the reference position coordinates, where the reference position coordinates are the position of the steel sample in the sample image; Based on the reference position coordinates and using multi-angle rotation detection technology, the steel sample is inspected for defects to screen out qualified areas; The position data of the qualified detected area is obtained by coordinate calculation and uploaded to the host computer, so that the point coordinate information and related information of the sample image are displayed on the host computer interface.
2. The method for detecting rotation of excitable points of steel samples based on visual technology according to claim 1, characterized in that: The step of obtaining a sample image of the steel sample by controlling the visual device through the host computer specifically includes: The feedback signal of the layout platform is detected by the upper computer end, and when the feedback signal is detected, the steel sample is placed on the layout platform; The lighting command is sent to the light source device through the upper computer, so that the light source device turns on the light and irradiates the steel sample on the layout platform; The photo taking instruction is sent to the camera device through the host computer to obtain sample pictures of the steel sample, and the visual device includes a light source device and a camera device.
3. The method for detecting rotation of excitable points of steel samples based on visual technology according to claim 1, characterized in that: The step of performing defect detection on the steel sample based on the reference position coordinates and using the multi-angle rotation detection technology specifically includes: Recognize the shape of the steel sample by a visual device to obtain shape information; According to the left side of the base position and using the visual capture algorithm, multiple detection areas are obtained, and the detection areas are circular areas generated by rotating the steel sample center at a specified angle; The detection area is subjected to defect analysis according to a visual program threshold judgment algorithm.
4. The method for detecting rotation of excitable points of steel samples based on visual technology according to claim 3 is characterized in that: The step of performing defect analysis on the detection area according to the visual program threshold judgment algorithm specifically includes: A predetermined threshold value is set in advance, and the threshold value is used to determine the defect condition of the detection area; identifying the currently selected detection area according to the threshold; When there is a defect in the detection area, it will be displayed that the area is below the specified threshold, and the next detection area will be identified according to the rotation order of the detection areas.
5. The method for detecting rotation of excitable points of steel samples based on visual technology according to claim 1, characterized in that: The step of obtaining position data of the qualified detected area through coordinate calculation and uploading it to the host computer includes: After obtaining the qualified detection area, the center coordinate value of the detection area is calculated according to the shape of the detection area and the reference position coordinates; The center coordinate value is converted into actual position data through transformation calculation; All position data are collated and sent to the host computer to provide offset position parameters for the robot system.
6. A steel sample excitable point rotation detection system based on visual technology, characterized in that: The system comprises: A picture acquisition module, used to acquire a sample picture of the steel sample by controlling the visual device through the host computer, wherein the sample picture is a picture of the cross section of the steel sample on the layout platform; A positioning analysis module is used to analyze and calculate the sample image and obtain reference position coordinates, where the reference position coordinates are the position of the steel sample in the sample image; The sample detection module detects defects on the steel sample based on the reference position coordinates and the multi-angle rotation detection technology, and is used to screen out qualified areas; The data sorting module is used to obtain the position data of the qualified detection area through coordinate calculation and upload it to the host computer end, so that the point coordinate information and related information of the sample image are displayed on the host computer end interface.
7. The steel sample excitable point rotation detection system based on vision technology according to claim 6 is characterized in that: The picture acquisition module includes: A signal detection unit, used for detecting a feedback signal of the layout platform through the host computer, and when the feedback signal is detected, the steel sample is placed on the layout platform; A light source control unit is used to send a light instruction to the light source device through the host computer, so that the light source device turns on the light and irradiates the steel sample on the layout platform; The camera control unit is used to send a photo command to a camera device through a host computer, so as to obtain a sample picture of the steel sample. The visual device includes a light source device and a camera device.
8. The steel sample excitable point rotation detection system based on vision technology according to claim 6 is characterized in that: The sample detection module comprises: A steel sample recognition unit, used for recognizing the shape of the steel sample through a visual device to obtain shape information; A visual capture unit, used to obtain multiple detection areas according to the left side of the base position and using a visual capture algorithm, wherein the detection area is a circular area generated by rotating a specified angle around the center of the steel sample; The area judgment unit is used to perform defect analysis on the detection area according to a visual program threshold judgment algorithm.
9. The steel sample excitable point rotation detection system based on vision technology according to claim 6 is characterized in that: The data sorting module comprises: A coordinate calculation unit, used to calculate the center coordinate value of the detection area according to the shape of the detection area and the reference position coordinates after obtaining the detection area that has passed the detection; A numerical conversion unit, used to convert the center coordinate value into actual position data through transformation calculation; The data transmission unit is used to organize all position data and send them to the host computer to provide offset position parameters for the robot system.
