Concrete test block sampling identification method and system, computer equipment and storage medium
By establishing a QR code image set and using the recognition model of the MaskR-CNN algorithm, the concrete test block samples are identified, which solves the problem of low identification efficiency of label encoding of concrete sample blocks in the prior art, and improves the identification accuracy and efficiency of the test.
Patent Information
- Application Number
- CN202411839060.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-13
- Publication Date
- 2025-04-08
AI Technical Summary
The prior art has low efficiency in label encoding identification of concrete sample blocks, which affects the identification accuracy and efficiency of the automation process of compressive strength tests.
By establishing a QR code image set of concrete test blocks, and using the recognition model of MaskR-CNN algorithm for training, combining the transfer learning algorithm to identify the QR code electronic tags, improving the sampling and recognition efficiency of concrete test block samples.
It improves the identification efficiency of concrete test block samples, avoids the impact of paper label damage on the test, and enhances the automated process of compressive strength test.
Smart Images
Figure CN119783707A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of image recognition technology, and in particular to a concrete test block sampling recognition method, system, computer equipment and storage medium. Background Art
[0002] QR code is a new encoding method that has attracted much attention in recent years. It can store a larger amount and more types of data and is widely used in shopping, transportation and other scenarios. The traditional QR code positioning method uses image processing related operations to mark and find the three feature areas of the QR code to locate the QR code, and then detects it with the relevant QR code scanning algorithm.
[0003] However, traditional positioning methods require the use of image matching methods, and algorithms such as ZBar have high requirements on the resolution and angle of the QR code. This method is cumbersome and can only produce rough QR code positioning for judgment and detection. Its effect is poor and its efficiency is low. Summary of the invention
[0004] The object of the present invention is to provide a concrete test block sampling and identification method, system, computer equipment and storage medium to solve the problem of low recognition efficiency of label coding of concrete samples in the prior art.
[0005] The present invention is achieved through the following technical solutions:
[0006] In a first aspect, a method for sampling and identifying concrete test blocks is provided, comprising the following steps: establishing a two-dimensional code image set of concrete test blocks; the two-dimensional code image set includes multiple two-dimensional code images and multiple two-dimensional code labels; establishing a recognition model based on the MaskR-CNN algorithm; using a transfer learning algorithm to input the two-dimensional code image set into the recognition model, and training the recognition model; sampling concrete test blocks to be tested; calling a qrcode database to number the sampled concrete test block samples, and forming two-dimensional code electronic tags corresponding to the numbers of the concrete test block samples; using the recognition model to identify the two-dimensional code electronic tags to obtain recognition results; and performing concrete test block sampling and recognition according to the recognition results.
[0007] Furthermore, sampling of the concrete test block to be tested includes the following steps: setting a continuous pouring amount and a plurality of test cycle groups; setting a sampling amount and a number of concrete test block samples corresponding to each test cycle group; one test cycle group corresponds to one test cycle; for each test cycle group, using the concrete test block compression test robot to clamp the concrete test block sample according to the corresponding sampling amount and the number of concrete test block samples.
[0008] Furthermore, the method for numbering the concrete test block samples obtained by sampling is: calling a qrcode database, performing a two-dimensional code generation process on the number, and obtaining the two-dimensional code electronic tag.
[0009] In a second aspect, a concrete test block sampling and identification system is provided, comprising: an image set establishment module, used to establish a two-dimensional code image set of a concrete test block; the two-dimensional code image set includes multiple two-dimensional code images and multiple two-dimensional code labels; a model establishment module, used to establish a recognition model based on the MaskR-CNN algorithm; a model training module, used to input the two-dimensional code image set into the recognition model using a transfer learning algorithm, and train the recognition model; a sample sampling module, used to sample the concrete test block to be tested; a sample numbering module, used to number the sampled concrete test block samples, and generate a two-dimensional code electronic label corresponding to the number of the concrete test block sample; a label identification module, used to identify the two-dimensional code electronic label using the identification model to obtain an identification result; and a sampling identification module, used to perform concrete test block sampling and identification according to the identification result.
[0010] Furthermore, the sample sampling module includes: a first data setting unit, used to set the continuous pouring volume and multiple test cycle groups; one test cycle group corresponds to one test cycle; a second data setting unit, used to set the sampling volume and the number of concrete test block samples corresponding to each test cycle group; a sample clamping unit, used to clamp the concrete test block samples according to the corresponding sampling volume and the number of concrete test block samples using the concrete test block compression test robot for each test cycle group.
[0011] In a third aspect, a computer device is provided, comprising a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the concrete test block sampling and identification method as described in the first aspect.
[0012] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored on the computer-readable storage medium. When the instructions are executed on a computer, the concrete test block sampling and identification method as described in the first aspect is executed.
[0013] Compared with the prior art, the present invention has the following advantages and beneficial effects: by numbering concrete test block samples and generating corresponding two-dimensional code electronic tags, the influence of damage to paper labels on the concrete test block samples during the foreign test can be avoided, and the two-dimensional resistance tags are further identified by a recognition model based on the MaskR-CNN algorithm, thereby improving the sampling and recognition efficiency of concrete test block samples. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0015] Figure 1 A schematic diagram of a flow chart of a concrete test block sampling and identification method provided by an embodiment of the present invention;
[0016] Figure 2 A schematic diagram of the network topology structure of the concrete test block sampling and identification method provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0017] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.
[0018] Example
[0019] In view of the low recognition accuracy of the label coding of concrete samples in the prior art, which reduces the recognition accuracy and recognition efficiency of concrete samples in the automated process of compressive strength test, the first aspect of this embodiment provides a concrete test block sampling and recognition method. Figure 1 As shown, the method comprises the following steps:
[0020] Step 1: Create a QR code image set of concrete test blocks.
[0021] The QR code image set contains 91 categories of objects, 328,000 images and 2,500,000 labels.
[0022] Step 2: Establish a recognition model based on the MaskR-CNN algorithm.
[0023] like Figure 2 As shown in the figure, Mask R-CNN uses ResNet-FPN (residual network-feature pyramid network) to extract image features and pass them into a two-level network. One level uses a region proposal network (RPN) to read the feature map and generate a possible target area. The second level generates possible classifications as well as bounding boxes and masks.
[0024] Furthermore, in parallel with predicting the classification and coordinate information, a mask prediction branch is added at this stage. This branch uses FCN (fully convolutional network) to predict each ROI (Region Of Interest) is predicted at the pixel level to generate an m×m mask, which can obtain a more accurate prediction mask. For each mask, the ROIAlign layer is used to use bilinear interpolation to calculate the exact value of the input feature at the fixed sampling position in each ROI, and the result value is aggregated to ensure that the mask accurately corresponds to the original input image. At the same time, the rectangular box classification and coordinate regression are performed in parallel, which simplifies the network process.
[0025] Step 3: Use a transfer learning algorithm to input the two-dimensional code image set into the recognition model to train the recognition model.
[0026] Considering that the QR code images in the image set contain a large number of natural features, the pre-trained weights are used and the data set is input into the model for training using the transfer learning method.
[0027] Step 4: Take samples of the concrete test blocks to be tested.
[0028] Specifically, the method for sampling the concrete test block to be tested is:
[0029] Step 4.1: Set the continuous pouring volume and multiple test cycle groups; set the sampling volume and the number of concrete test block samples corresponding to each test cycle group. In this embodiment, the continuous pouring volume is set to 7200 cubic meters, and three test cycle groups are set. Among them, the test cycle of the first test cycle group is 7 days, the test cycle of the second test cycle group is 28 days, and the test cycle of the third test cycle group is 90 days. In addition, each test cycle group is set to sample every 720 cubic meters, including five water-cement ratios of 0.35, 0.40, 0.45, 0.50 and 0.55. The specimens include different types such as compression, splitting tension, elastic modulus, impermeability, and frost resistance, and each test cycle group consists of 3 concrete test block samples.
[0030] Step 4.2: For each test cycle group, the concrete specimen compression test robot is used to clamp the concrete specimen samples according to the corresponding sampling volume and the number of concrete specimen samples.
[0031] Step 5: Retrieve the QR code database to number the concrete test block samples obtained by sampling, and generate a QR code electronic tag corresponding to the number of the concrete test block sample.
[0032] Step 6: Use the recognition model to identify the QR code electronic tag and obtain the recognition result.
[0033] Step 7: Sample and identify the concrete test blocks based on the identification results.
[0034] Corresponding to the first aspect above, the second aspect of this embodiment provides a concrete test block sampling and identification system, including:
[0035] An image set establishment module is used to establish a two-dimensional code image set of a concrete test block; the two-dimensional code image set includes multiple two-dimensional code images and multiple two-dimensional code labels; a model establishment module is used to establish a recognition model based on the MaskR-CNN algorithm; a model training module is used to input the two-dimensional code image set into the recognition model using a transfer learning algorithm and train the recognition model; a sample sampling module is used to sample the concrete test blocks to be tested; a sample numbering module is used to number the sampled concrete test blocks and generate a two-dimensional code electronic label corresponding to the number of the concrete test block samples; a label recognition module is used to recognize the two-dimensional code electronic label using the recognition model to obtain a recognition result; a sampling recognition module is used to perform concrete test block sampling and recognition according to the recognition result.
[0036] Furthermore, the sample sampling module includes: a first data setting unit, used to set the continuous pouring volume and multiple test cycle groups; one test cycle group corresponds to one test cycle; a second data setting unit, used to set the sampling volume and the number of concrete test block samples corresponding to each test cycle group; a sample clamping unit, used to clamp the concrete test block samples according to the corresponding sampling volume and the number of concrete test block samples using the concrete test block compression test robot for each test cycle group.
[0037] The third aspect of the present embodiment provides a computer device for executing the concrete test block sampling and identification method as described in the first aspect or any possible design scheme in the first aspect, including a memory, a processor and a transceiver connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the concrete test block sampling and identification method as described in the first aspect or any possible design scheme in the first aspect. Specifically, the memory may include, but is not limited to, a random access memory (Random-Access Memory, RAM), a read-only memory (Read-Only Memory, ROM), a flash memory (Flash Memory), a first-in-first-out memory (First Input First Output, FIFO) and / or a first-in-last-out memory (First Input Last Output, FILO), etc.; the processor may include, but is not limited to, a microprocessor of the STM32F105 series. In addition, the computer device may also include, but is not limited to, a power module, a display screen and other necessary components.
[0038] The working process, working details and technical effects of the aforementioned computer equipment provided in the third aspect of this embodiment can be referred to the concrete test block sampling and identification method described in the first aspect or any possible design scheme in the first aspect, and will not be repeated here.
[0039] In a fourth aspect of the present embodiment, there is provided a computer-readable storage medium storing instructions for the concrete test block sampling and identification method as described in the first aspect or any possible design scheme in the first aspect, that is, the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the concrete test block sampling and identification method as described in the first aspect or any possible design scheme in the first aspect is executed. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to computer-readable storage media such as floppy disks, optical disks, hard disks, flash memory, USB flash drives and / or memory sticks (MemoryStick), and the computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices.
[0040] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the fourth aspect of this embodiment can be referred to the concrete test block sampling and identification method described in the first aspect or any possible design scheme in the first aspect, and will not be repeated here.
[0041] In a fifth aspect, the present embodiment provides a computer program product comprising instructions, which, when executed on a computer, causes the computer to execute the concrete test block sampling and identification method as described in the first aspect or any possible design scheme in the first aspect. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
[0042] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A concrete test block sampling and identification method, characterized in that: The following steps are involved: Establishing a two-dimensional code image set of a concrete test block; the two-dimensional code image set includes a plurality of two-dimensional code images and a plurality of two-dimensional code labels; Establish a recognition model based on the MaskR-CNN algorithm; Using a transfer learning algorithm, the two-dimensional code image set is input into the recognition model to train the recognition model; Take samples of the concrete test blocks to be tested; The qrcode database is retrieved to number the concrete test block samples obtained by sampling, and a two-dimensional code electronic label corresponding to the number of the concrete test block sample is generated; Using the recognition model to recognize the two-dimensional code electronic tag, and obtaining a recognition result; Concrete test block sampling and identification are performed according to the identification result.
2. A concrete test block sampling and identification method according to claim 1, characterized in that: Sampling the concrete test block to be tested includes the following steps: Set the continuous pouring volume and multiple test cycle groups; set the sampling volume and number of concrete test block samples corresponding to each test cycle group; one test cycle group corresponds to one test cycle; For each test cycle group, the concrete test block compression test robot is used to clamp concrete test block samples according to the corresponding sampling volume and the number of concrete test block samples.
3. A concrete test block sampling and identification method according to claim 1, characterized in that: The method for numbering the concrete test block samples obtained by sampling is: calling the qrcode database, performing two-dimensional code generation processing on the number, and obtaining the two-dimensional code electronic label.
4. A concrete test block sampling and identification system, characterized in that: include: An image set establishment module, used to establish a two-dimensional code image set of a concrete test block; the two-dimensional code image set includes a plurality of two-dimensional code images and a plurality of two-dimensional code labels; Model building module, used to build a recognition model based on the MaskR-CNN algorithm; A model training module, used to input the two-dimensional code image set into the recognition model using a transfer learning algorithm to train the recognition model; A sample sampling module is used to sample the concrete test block to be tested; The sample numbering module is used to number the concrete test block samples obtained by sampling and generate a two-dimensional code electronic label corresponding to the number of the concrete test block sample; A tag recognition module is used to recognize the two-dimensional code electronic tag using the recognition model to obtain a recognition result; The sampling and identification module is used to perform concrete test block sampling and identification according to the identification result.
5. A concrete test block sampling and identification system according to claim 4, characterized in that: The sample sampling module comprises: A first data setting unit is used to set a continuous pouring volume and a plurality of test cycle groups; one test cycle group corresponds to one test cycle; The second data setting unit is used to set the sampling volume and the number of concrete test block samples corresponding to each test cycle group; The sample clamping unit is used for clamping the concrete test block samples according to the corresponding sampling amount and the number of concrete test block samples by using the concrete test block compression test robot for each test cycle group.
6. A computer device, characterized in that: The invention comprises a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the concrete test block sampling and identification method as claimed in any one of claims 1 to 3.
7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the concrete test block sampling and identification method according to any one of claims 1 to 3 is executed.