A mobile electronic training platform experimental instrument position recognition and determination method

Abstract

The application discloses a kind of mobile electronic practical training platform experimental appliance position recognition determination method, this method includes the following steps: S1, based on radio frequency identification technology realizes the control of the opening and closing state of electronic equipment on electronic practical training platform;S2, the position image of experimental appliance on electronic practical training platform is obtained using the preset image acquisition device, and pre-processing is carried out;S3, the placement position of experimental appliance on electronic practical training platform is identified and judged using image recognition technology.The application can realize the identification and judgment of the placement position of experimental appliance on practical training platform, distinguish whether the placement position of each experimental appliance is located in the standard area, compared with the traditional artificial one-by-one checking mode, effectively reduce the workload of staff, can better satisfy the use demand of enterprise.

Description

Technical Field

[0001] This invention relates to the field of location recognition technology, and more specifically, to a method for location recognition and judgment of a mobile electronic training platform experimental tool. Background Technology

[0002] With the development of intelligent and digital technologies, various emerging technologies have been integrated into campus education. Electronic technology courses are important technical foundation courses for electrical engineering and some non-electrical engineering majors. Electronic technology is a highly practical and widely applicable discipline. To master electronic technology, it is essential to focus on practical teaching components, such as experiments and training, which are closely related to theoretical courses. The main content of electronic technology training includes familiarizing oneself with circuit components, checking and familiarizing oneself with the use of various tools, soldering components on circuit boards, and completing analog and digital electronic technology experiments. Therefore, electronic training platforms have been widely used.

[0003] Currently, in order to enable users to better utilize electronic training platforms in the future, users often need to properly place the experimental equipment on the platform after training. However, due to some users' unintentional or random placement, the experimental equipment is often not placed correctly in the designated area. As a result, after each training session, staff need to check the placement of each piece of equipment on the platform one by one, which greatly increases the workload of the staff and cannot adequately meet the needs of users. Therefore, this invention proposes a method for identifying and judging the position of experimental equipment on a mobile electronic training platform. Summary of the Invention

[0004] To address the problems in related technologies, this invention proposes a method for identifying and determining the location of experimental equipment on a mobile electronic training platform, thereby overcoming the aforementioned technical problems existing in the prior art.

[0005] Therefore, the specific technical solution adopted by the present invention is as follows:

[0006] A method for identifying and determining the position of a mobile electronic training platform, comprising the following steps:

[0007] S1. Controlling the on / off status of electronic equipment on the electronic training platform based on radio frequency identification technology;

[0008] S2. Use the preset image acquisition device to acquire the position images of the experimental equipment on the electronic training platform, and perform preprocessing.

[0009] S3. Use image recognition technology to identify and determine the placement of experimental equipment on the electronic training platform.

[0010] Furthermore, the electronic training platform is equipped with a hardware control group, which includes a control chip, relays, photoresistors, an RFID module, and electrical controlled terminals.

[0011] Furthermore, the control of the on / off state of electronic equipment on the electronic training platform based on radio frequency identification technology includes the following steps:

[0012] S11. Use the RFID module to identify the pre-recorded ID signal, and use the control chip to control the relay to start the computer and monitor on the electronic training platform.

[0013] S12. Use the RFID module again to identify the pre-recorded ID signal, and use the control chip to control the relay to turn off the computer and monitor on the electronic training platform.

[0014] Furthermore, the control of the on / off state of electronic equipment on the electronic training platform based on radio frequency identification technology also includes the following steps:

[0015] The control chip is used to acquire real-time data from the photoresistor, and the optimal brightness is obtained through analysis and calculation.

[0016] The optimal brightness obtained through analysis and calculation is used to adaptively adjust the brightness of the energy-saving lamps on the electronic training platform.

[0017] Furthermore, before acquiring the positional image of the experimental equipment on the electronic training platform using a preset image acquisition device and performing preprocessing, the following steps are also included:

[0018] The preset positions of each experimental tool on the electronic training platform are calibrated to obtain several calibration areas, wherein the area of ​​the calibration area is larger than the area of ​​the experimental tool.

[0019] Several calibrated areas were coated with different colors, and a correspondence table between experimental equipment and colors was established.

[0020] Furthermore, the step of acquiring positional images of the experimental equipment on the electronic training platform using a preset image acquisition device and performing preprocessing includes the following steps:

[0021] S21. Use a camera pre-installed on the top of the electronic training platform to obtain real-time images of the position of the experimental equipment on the surface of the electronic training platform;

[0022] S22. Median filtering is used to remove noise from the surface of the location image, and super-resolution is used to reconstruct the location image.

[0023] Furthermore, the step of removing noise from the surface of the location image using median filtering and performing super-resolution reconstruction of the location image using image super-resolution includes the following steps:

[0024] S221. Use median filtering to remove noise from the surface of the location image and determine whether the resolution of the location image is lower than a preset threshold.

[0025] S222. Import the image at a position below the preset threshold into the SRGAN network for processing, and set the core operating parameters of the SRGAN network, such as magnification, learning rate and number of iterations.

[0026] S223. The high-resolution location image is generated by progressively processing the data through three convolutional layers in the SRGAN network.

[0027] Furthermore, the process of using image recognition technology to identify and determine the placement of experimental equipment on the electronic training platform includes the following steps:

[0028] S31. Obtain the location image after super-resolution reconstruction, and use the object detection algorithm based on convolutional neural network to obtain the location and category of the experimental equipment in the location image;

[0029] S32. Use the target color recognition method to identify the color of the marked area in the location image;

[0030] S33. Based on the correspondence table between experimental equipment and color, determine whether the position of the experimental equipment in the position image is correct. If yes, issue a prompt that the experimental equipment is correctly placed; otherwise, issue a prompt that the experimental equipment is incorrectly placed.

[0031] Furthermore, the step of obtaining the location image after super-resolution reconstruction and using a target detection algorithm based on a convolutional neural network to obtain the location and category of the experimental equipment in the location image includes the following steps:

[0032] S311. Obtain the location image after super-resolution reconstruction, and extract a preset number of boxes as candidate regions from top to bottom using a selective search method.

[0033] S312. Expand the edges of the selected candidate regions to a size of 227x227, and use a convolutional neural network to extract features from each candidate region.

[0034] S313. Use a preset linear SVM classifier to classify each candidate region, and perform coordinate regression on the classified candidate region boxes to obtain the location and category of the experimental equipment.

[0035] Furthermore, the method of identifying the color of a designated area in a location image using target color recognition includes the following steps:

[0036] S321. Calculate the sum of the color membership values ​​of all pixels in the calibration region, Sum(k), where k is an integer and 0 < k < k. <k<12;

[0037] S322. Sort the sum of color membership Sum(k) in descending order;

[0038] S323, Find the satisfying The minimum value of m, where T is the threshold, 0.2 <T<0.95;

[0039] S324. Output the first m colors corresponding to the sum of the color membership degree Sum(k), which are the colors of the calibrated areas in the location image.

[0040] The beneficial effects of this invention are as follows: By controlling the on / off state of electronic devices on the electronic training platform based on radio frequency identification (RFID) technology, not only can intelligent control of the electronic training platform be achieved, but also user information can be intelligently recorded, facilitating the management of the training classroom; by using a preset image acquisition device to acquire and preprocess images of the positions of experimental tools on the electronic training platform, and using image recognition technology to identify and judge the placement of experimental tools on the electronic training platform, it is possible to identify and judge the placement of experimental tools on the training platform, and determine whether the placement of each experimental tool is within the standard area. Compared with the traditional method of manual inspection, this effectively reduces the workload of staff and can better meet the needs of enterprises. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart illustrating a method for identifying and determining the position of a mobile electronic training platform experimental tool according to an embodiment of the present invention. Detailed Implementation

[0043] To further illustrate the various embodiments, the present invention provides accompanying drawings, which are part of the disclosure of the present invention. These drawings are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementation methods and the advantages of the present invention. The components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0044] According to an embodiment of the present invention, a method for identifying and determining the location of experimental equipment on a mobile electronic training platform is provided.

[0045] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, a method for identifying and determining the location of a mobile electronic training platform experimental apparatus according to an embodiment of the present invention includes the following steps:

[0046] S1. Controlling the on / off status of electronic equipment on the electronic training platform based on radio frequency identification technology;

[0047] The electronic training platform consists of an aluminum frame, a display, a hardware control group, a computer, casters, a camera, and energy-saving lamps. The electronic training platform is equipped with a hardware control group, which contains a control chip, relays, photoresistors, an RFID module, and electrical controlled terminals.

[0048] Specifically, the control of the on / off state of electronic devices on the electronic training platform based on radio frequency identification technology includes the following steps:

[0049] S11. Use the RFID module to identify the pre-recorded ID signal, and use the control chip to control the relay to start the computer and monitor on the electronic training platform.

[0050] S12. Use the RFID module again to identify the pre-recorded ID signal, and use the control chip to control the relay to turn off the computer and monitor on the electronic training platform.

[0051] In addition, the control of the on / off state of electronic equipment on the electronic training platform based on radio frequency identification technology also includes the following steps:

[0052] The system uses a control chip to acquire real-time data from the photoresistor and analyzes and calculates the optimal brightness. The optimal brightness is then used to adaptively adjust the brightness of the energy-saving lamp on the electronic training platform.

[0053] S2. Use the preset image acquisition device to acquire the position images of the experimental equipment on the electronic training platform, and perform preprocessing.

[0054] The step of acquiring the positional image of the experimental equipment on the electronic training platform using a preset image acquisition device and performing preprocessing includes the following steps:

[0055] The preset positions of each experimental tool on the electronic training platform are calibrated to obtain several calibration areas, where the area of ​​the calibration area is larger than the area of ​​the experimental tool. The calibration areas are then coated with different colors, and a correspondence table between the experimental tools and the colors is established.

[0056] Specifically, the step of acquiring positional images of experimental equipment on the electronic training platform using a preset image acquisition device and performing preprocessing includes the following steps:

[0057] S21. Use a camera pre-installed on the top of the electronic training platform to obtain real-time images of the position of the experimental equipment on the surface of the electronic training platform;

[0058] S22. Median filtering is used to remove noise from the surface of the location image, and super-resolution is used to reconstruct the location image.

[0059] The method of removing noise from the surface of the location image using median filtering and performing super-resolution reconstruction of the location image using image super-resolution includes the following steps:

[0060] S221. The median filtering method is used to remove noise from the surface of the location image, and it is determined whether the resolution of the location image is lower than a preset threshold. Specifically, in this embodiment, the threshold is 480*480, and the preset threshold can be manually modified.

[0061] S222. Import the image at a position below the preset threshold into the SRGAN network for processing, and set the core operating parameters of the SRGAN network, such as magnification, learning rate and number of iterations.

[0062] S223. A high-resolution location image is generated through progressive processing using three convolutional layers in the SRGAN network, specifically including the following steps:

[0063] The first convolutional layer extracts feature points from the original real-time image; the second convolutional layer performs non-linear mapping on the feature points to predict the missing details of each feature point; and the third convolutional layer combines the mapped images to generate a high-resolution image.

[0064] S3. Use image recognition technology to identify and determine the placement of experimental equipment on the electronic training platform.

[0065] The process of identifying and determining the placement of experimental equipment on the electronic training platform using image recognition technology includes the following steps:

[0066] S31. Obtain the location image after super-resolution reconstruction, and use the object detection algorithm based on convolutional neural network to obtain the location and category of the experimental equipment in the location image;

[0067] Specifically, the process of obtaining the location image after super-resolution reconstruction and using a target detection algorithm based on a convolutional neural network to obtain the location and category of the experimental equipment in the location image includes the following steps:

[0068] S311. Obtain the location image after super-resolution reconstruction, and extract a preset number of boxes as candidate regions from top to bottom using a selective search method.

[0069] S312. Expand the edges of the selected candidate regions to a size of 227x227, and use a convolutional neural network to extract features from each candidate region.

[0070] S313. Use a preset linear SVM classifier to classify each candidate region, and perform coordinate regression on the classified candidate region boxes to obtain the location and category of the experimental equipment.

[0071] S32. Use the target color recognition method to identify the color of the marked area in the location image;

[0072] Specifically, the method of identifying the color of a designated area in a location image using target color recognition includes the following steps:

[0073] S321. Calculate the sum of the color membership values ​​of all pixels in the calibration region, Sum(k), where k is an integer and 0 < k < k. <k<12;

[0074] S322. Sort the sum of color membership Sum(k) in descending order;

[0075] S323, Find the satisfying The minimum value of m, where T is the threshold, 0.2 <T<0.95;

[0076] S324. Output the first m colors corresponding to the sum of the color membership degree Sum(k), which are the colors of the calibrated areas in the location image.

[0077] S33. Based on the correspondence table between experimental equipment and color, determine whether the position of the experimental equipment in the position image is correct. If yes, issue a prompt that the experimental equipment is correctly placed; otherwise, issue a prompt that the experimental equipment is incorrectly placed.

[0078] In summary, by utilizing the above-mentioned technical solution of this invention, the on / off state of electronic equipment on the electronic training platform can be controlled based on radio frequency identification (RFID) technology. This not only enables intelligent control of the electronic training platform but also allows for intelligent recording of user information, facilitating the management of the training classroom. By using a pre-set image acquisition device to acquire and preprocess images of the experimental equipment positions on the electronic training platform, and then using image recognition technology to identify and judge the placement of the experimental equipment, the system can identify whether each piece of equipment is within the designated area. Compared to the traditional method of manual inspection, this effectively reduces the workload of staff and better meets the needs of enterprises.

[0079] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A mobile electronic training platform experiment tool position recognition determination method, characterized in that, The method comprises the following steps: S1, based on radio frequency identification technology to realize the control of the opening and closing state of the electronic equipment on the electronic training platform; S2, using a pre-set image acquisition device to obtain the position image of the experimental tools on the electronic training platform, and pre-processing; S3, using image recognition technology to identify and judge the placement position of the experimental tools on the electronic training platform; Wherein, the step of using image recognition technology to identify and judge the placement position of the experimental tools on the electronic training platform comprises the following steps: S31, obtaining the position image after super-resolution reconstruction, and using a target detection algorithm based on convolutional neural network to obtain the position and category of the experimental tools in the position image; S32, using target color recognition method to identify the color of the calibration area in the position image; The step of using target color recognition method to identify the color of the calibration area in the position image comprises the following steps: S321, calculating the sum of color membership of all pixel points in the calibration area Sum(k), k is an integer, and 0<k<12; S322, sorting the sum of color membership Sum(k) in descending order; S323、find the minimum m value satisfying T is a threshold value, 0.2 < T < 0.

95. S324, outputting the color corresponding to the sum of color membership Sum(k) in the first m, which is the color of the calibration area in the position image; S33, judging whether the position of the experimental tools in the position image is placed correctly based on the correspondence table of the relationship between the experimental tools and the color, if yes, issuing a prompt that the experimental tools are placed correctly, if not, issuing a prompt that the experimental tools are placed incorrectly.

2. The method of claim 1, wherein the method further comprises: The internal part of the electronic training platform is provided with a hardware control group, and the internal part of the hardware control group is provided with a control chip, a relay, a photosensitive resistance, an RFID module and an electrically controlled end.

3. The method of claim 2, wherein the method further comprises: determining the position of the experimental apparatus based on the position of the mobile electronic training platform. The step of using RFID module to identify the pre-recorded ID signal, and using the control chip to control the relay to start the computer and display on the electronic training platform; S12, using RFID module to identify the pre-recorded ID signal again, and using the control chip to control the relay to turn off the computer and display on the electronic training platform. The step of using RFID module to identify the pre-recorded ID signal, and using the control chip to control the relay to start the computer and display on the electronic training platform; 4. The method of claim 3, wherein the method further comprises: Using the control chip to obtain the real-time acquisition data of the photosensitive resistance, and analyzing and calculating the optimal brightness; Using the optimal brightness obtained by analysis and calculation to adaptively adjust the brightness of the energy-saving lamp on the electronic training platform. Before the step of using the pre-set image acquisition device to obtain the position image of the experimental tools on the electronic training platform and pre-processing, the following steps are further included:

5. The method for identifying and determining the position of a mobile electronic training platform experimental tool according to claim 1, characterized in that, Calibrating the pre-set position of each experimental tool on the electronic training platform to obtain a plurality of calibration areas, wherein the area of the calibration area is larger than the area of the experimental tool; Coating different colors on the plurality of calibration areas respectively, and establishing a correspondence table of the relationship between the experimental tools and the colors. The step of using the pre-set image acquisition device to obtain the position image of the experimental tools on the electronic training platform and pre-processing comprises the following steps:

6. The method of claim 5, wherein the method further comprises: ​ S21, real-time acquisition of the position image of the experimental instrument on the surface of the electronic training platform by using the camera pre-installed on the top of the electronic training platform; S22, removing the noise on the surface of the position image by using the median filtering method, and super-resolution reconstruction of the position image by using the image super-resolution method.

7. The method of claim 6, wherein the method further comprises: determining the position of the experimental apparatus based on the position of the mobile electronic training platform. The step of removing the noise on the surface of the position image by using the median filtering method, and super-resolution reconstruction of the position image by using the image super-resolution method comprises the following steps: S221, removing the noise on the surface of the position image by using the median filtering method, and judging whether the resolution of the position image is lower than a preset threshold value; S222, importing the position image lower than the preset threshold value into the SRGAN network for processing, and setting the core operation parameters of the magnification, learning rate and iteration number in the SRGAN network; S223, step-by-step processing by three convolutional layers in the SRGAN network to generate a high-resolution position image.

8. The method for identifying and determining the position of a mobile electronic training platform experimental apparatus according to claim 1, characterized in that, The step of acquiring the position image after super-resolution reconstruction, and acquiring the position and category of the experimental instrument in the position image by using the target detection algorithm based on the convolutional neural network comprises the following steps: S311, acquiring the position image after super-resolution reconstruction, and extracting a preset number of frames as candidate regions from top to bottom by using the selective search method; S312, expanding the edges of the screened candidate regions to 227x227 size, and extracting the features of each candidate region by using the convolutional neural network; S313, classifying each candidate region by using a preset linear SVM classifier, and performing coordinate regression on the candidate region frames after the classification to obtain the position and category of the experimental instrument.

Images