Concrete witness sampling method and system based on object face recognition
By implanting QR code tags and sample sealing marks in concrete test blocks, and using face recognition technology to verify the authenticity of the sampling and inspection process, the problem of difficult management of witnesses' authenticity and operation of the witnesses is solved. It has achieved effective traceability of concrete test blocks and guaranteed the authenticity of inspection reports.
Patent Information
- Application Number
- CN202411322765.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2024-12-20
AI Technical Summary
In the existing concrete witness sampling methods, the on-the-job status and operational authenticity of witnesses are difficult to manage, resulting in the authenticity of the test report being unable to be guaranteed, and the concrete samples may be replaced during the inspection process, which affects the representativeness of the samples and the test results. accuracy.
Using the concrete witness sampling method based on object face recognition, by implanting QR code tags and multiple sample sealing marks in the concrete test block, combining face recognition and image comparison technology, the personnel during the sampling and inspection process are verified. and the authenticity of the location, and randomly obtain photos during pressure testing for comparison and analysis to ensure the integrity and consistency of the test blocks.
It improves the transparency and traceability of the witness sampling process, significantly reduces the probability of test block replacement, ensures the authenticity and accuracy of the test report, and avoids the problems of insufficient representativeness and distortion of samples.
Smart Images
Figure CN119167962A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of concrete witness sampling, and more specifically, to a concrete witness sampling method and system based on object face recognition. Background Art
[0002] Witness sampling is an important part of the quality inspection of construction projects. Witness sampling is the primary link to ensure the fairness, scientificity and authority of the quality inspection of construction projects. It is directly related to the quality of building materials and the overall quality of construction projects. However, in the actual operation process, due to the disconnection between the sampling and witnessing links, the samples are not representative enough, distorted, or even fake, and are out of touch with the actual quality level of the structural entity. The representativeness and authenticity of the samples are relatively common problems, resulting in the data in the inspection report being unable to truly reflect the quality of the structural entity.
[0003] At present, using the Internet of Things and QR code technology, when witnesses conduct random inspections, they attach QR code labels to the samples and bundle the witness information through smart phone terminals. The testing agency verifies the information during the sampling and transportation of the samples through the testing information system, and tracks the entire process of sampling witness inspection to ensure the authenticity of the inspection samples. However, there is no management of the attendance, operation time and operation location of the witnesses, which may lead to the situation that the witnesses are not on duty before sampling, and it is impossible to guarantee whether the samples sent for inspection are truly sampled, resulting in the inability to guarantee the authenticity of the test report. In addition, the QR code label is implanted when the concrete sample is made. After the witness sampling is completed, the concrete sample needs to be cured before testing. In this process, the QR code label of the concrete sample may also be replaced, and the authenticity of the test report cannot be guaranteed. Summary of the invention
[0004] In view of this, the present invention provides a concrete witness sampling method and system based on object face recognition, which is used to solve the problem that the authenticity of the test report cannot be guaranteed in the existing concrete witness sampling method.
[0005] To achieve the above objectives, the proposed solution is as follows: A concrete witness sampling method based on object face recognition, comprising: When making a concrete test block, a QR code label and N sample sealing markers are implanted into the concrete test block, where N ≥ 3; The sampling user terminal verifies the current sampling location, sampling personnel and witness personnel; if the verification is successful, the QR code label on the concrete test block is scanned, the concrete test block information is input, and the overall photo and front photo of the concrete test block, and the on-site photo of the sampling personnel and witness personnel are taken; The sampling user terminal uploads the QR code label, on-site photos of the sampling personnel and witnesses, and photos of the concrete test block to the server; The detection user terminal scans the QR code label on the concrete test block, takes overall photos and front photos of the concrete test block, and uploads them to the server; The server compares and analyzes the graphics composed of the sample sealing markers in the concrete test block photos uploaded by the sampling user terminal and the detection user terminal; if the concrete test block photos are photos of the same concrete test block, the concrete test block is subjected to pressure testing; When the image acquisition device performs pressure testing on the concrete test block, it randomly acquires a front photo of the concrete test block and uploads it to the server; The server compares and analyzes the graphics composed of the sealing markers in the concrete test block photos uploaded by the sampling user terminal and the image acquisition device. If the concrete test block photos are not photos of the same concrete test block, an alarm prompt is issued.
[0006] Preferably, the process of the sampling user terminal verifying the current sampling location, sampling personnel and witness personnel includes: The sampling user terminal obtains the current sampling location and determines whether the current sampling location is within a preset target sampling area; If they are within the target sampling area, the identities of the samplers and witnesses will be verified through facial recognition.
[0007] Preferably, the process of comparing and analyzing the graphics composed of the sample sealing markers in the photo of the concrete test block by the server includes: Extract the position of each sample seal marker in each concrete test block photo; Connect the first sample seal marker on the far left and the second sample seal marker on the far right in the photo of each concrete test block to obtain a reference axis; Taking the reference axis as a reference, diverge toward the third sample sealing marker to obtain a triangle formed by the sample sealing markers; Measure the angles of a triangle; Compare the lines and angles of the triangles formed by the sealing markers in the photos of each concrete specimen.
[0008] Preferably, after the sampling user terminal scans the QR code label on the concrete test block, the method further includes: Determine whether the scanned QR code label is unique; If yes, the process of inputting the concrete test block information and taking overall and frontal photos of the concrete test block, and on-site photos of the sampling personnel and witnesses is performed; If not, an alarm will be issued.
[0009] A concrete witness sampling system based on object face recognition, realizing the aforementioned concrete witness sampling method, the system comprises: a QR code label, N sample sealing markers, a sampling user terminal, a detection user terminal, an image acquisition device, and a server; The QR code label and N sample sealing markers are embedded in the concrete test block, where N ≥ 3; The sampling user terminal verifies the current sampling location, sampling personnel and witness personnel; if the verification is successful, the QR code label on the concrete test block is scanned, the concrete test block information is input, and the overall photo and front photo of the concrete test block, and the on-site photo of the sampling personnel and witness personnel are taken; The sampling user terminal uploads the QR code label, on-site photos of the sampling personnel and witnesses, and photos of the concrete test block to the server; The detection user terminal scans the QR code label on the concrete test block, takes overall photos and front photos of the concrete test block, and uploads them to the server; The server compares and analyzes the graphics composed of the sample sealing markers in the photos of the concrete test blocks uploaded by the sampling user terminal and the detection user terminal; if the photos of the concrete test blocks are photos of the same concrete test block, the concrete test block is subjected to pressure testing; When the image acquisition device performs pressure testing on the concrete test block, it randomly acquires a front photo of the concrete test block and uploads it to the server; The server compares and analyzes the graphics composed of the sealing sample markers in the photos of the concrete test blocks uploaded by the sampling user terminal and the image acquisition device. If the photos of the concrete test blocks are not photos of the same concrete test block, an alarm prompt is issued.
[0010] It can be seen from the above technical solutions that the concrete witness sampling method based on object face recognition provided by the present invention collects and verifies the information of the current sampling location, sampling personnel and witness personnel through the sampling user terminal, ensuring that the current sampling personnel and witness personnel are at the sampling site, avoiding the situation where the witness personnel are not present. The QR code label and N sample sealing markers are implanted into the concrete test block, and then the photos of the sampled and inspected concrete test blocks and the photos of the sampled and tested concrete test blocks are compared and analyzed respectively. By analyzing the graphics formed between the N sample sealing markers on the photos of each concrete test block, it is verified whether the concrete test blocks at each stage have been replaced, and the whole process of witness sampling can be traced, which increases the difficulty of replacing the concrete test blocks and greatly reduces the probability of the concrete test blocks being replaced during the inspection and maintenance process, thereby ensuring the authenticity of the test report. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0012] Figure 1 A flow chart of a concrete witness sampling method based on object face recognition provided by an embodiment of the present invention; Figure 2 A schematic diagram of sealing a concrete test block provided by an embodiment of the present invention; Figure 3a-3c They are schematic diagrams of input interfaces for different on-site information provided by embodiments of the present invention; Figure 4a-4b They are schematic diagrams of input interfaces for different sample verification information provided by embodiments of the present invention; Figure 5a-5b They are respectively schematic diagrams of different graphic compositions of sample sealing markers provided in embodiments of the present invention. DETAILED DESCRIPTION
[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0014] First, the concrete witness sampling system based on object face recognition provided by the present invention is introduced. The sampling system includes: a QR code label, N sealing sample markers, a sampling user terminal, a detection user terminal, an image acquisition device, and a server.
[0015] The QR code label and N sample sealing markers are embedded into the concrete test block when the concrete test block is produced, where N≥3.
[0016] The sampling user terminal and the detection user terminal can be terminal devices such as mobile phones and tablets. The image acquisition device can be a monitoring camera and other devices. Through the sampling user terminal and the detection user terminal, the staff can enter information.
[0017] The server can be a service device arranged on the network side. The server can exchange data with the sampling user terminal, the second detection user terminal and the image acquisition device through the network. The server can be implemented by a single server or a server cluster composed of multiple servers. In the embodiment of the present application, the server can obtain the concrete test block photos uploaded by the detection user terminal and the image acquisition device, and compare and analyze the concrete photos uploaded by the sampling user terminal with the concrete test block photos uploaded by the detection user terminal and the image acquisition device.
[0018] The concrete witness sampling system based on object face recognition provided in this embodiment implants a QR code label and N sample sealing markers into a concrete test block, and then compares and analyzes the photos of the sampled and inspected concrete test blocks and the photos of the sampled and tested concrete test blocks. By analyzing the graphics formed between the N sample sealing markers on the photos of each concrete test block, it is verified whether the concrete test blocks at each stage have been replaced, which increases the difficulty of replacing concrete test blocks and greatly reduces the probability of concrete test blocks being replaced during inspection and maintenance, thereby ensuring the authenticity of the test report.
[0019] Based on the concrete witness sampling system based on object face recognition provided in the above-mentioned embodiment, the concrete witness sampling method based on object face recognition provided in this embodiment is introduced. Figure 1 As shown, the method includes: When making concrete test blocks, a QR code label and N sample sealing markers are embedded into the concrete test blocks, where N ≥ 3. The sampling personnel take samples on site and make test blocks under the witness of the witnesses. In the process of making the test blocks, in addition to embedding the QR code label into the concrete test blocks, N sample sealing markers need to be placed on the surface of the concrete test blocks, and the sample sealing markers need to be slightly pressed with tools to embed them into the concrete test blocks so that they are not easy to fall off. Figure 2 As shown, a QR code label and a sample sealing marker are implanted into a concrete test block, wherein the sample sealing marker can be colorful.
[0020] The sampling user terminal verifies the current sampling location, sampling personnel and witnesses.
[0021] Specifically, the sampling user terminal obtains the current sampling location and determines whether the current sampling location is within the preset target sampling area. If the current sampling location is within the target sampling area, it proves that the sampling personnel and witness personnel are currently at the sampling site. For example, the target sampling area is determined in advance through an electronic fence, and the current sampling location is obtained through the sampling user terminal. Figure 3a As shown, it is determined whether the current sampling location is within the preset electronic fence.
[0022] If the current sampling location is not within the target sampling area, an alarm will be issued; if the current sampling location is within the target sampling area, the identity of the sampler and witness will be verified through the face recognition function.
[0023] If the face verification fails, the witness is not at the sampling site; if the face verification passes, it proves that the person at the current sampling site is the witness himself, and the sampler and witness are photographed with the witness site as the background. After the verification is passed, scan the QR code label on the concrete test block, enter the concrete test block information, and take photos of the entire sealed sample and the front of the concrete test block, as well as on-site photos of the sampler and witness. Figure 3b As shown in the figure, the input concrete test block information includes: project location, molding date, design grade, curing conditions, etc. Figure 3c As shown, with the witness site as the background, take on-site photos of the witness personnel, on-site photos of the sampling personnel, overall photos and front photos of the sealed concrete test blocks, etc.
[0024] The sampling user terminal uploads the QR code label, on-site photos of the sampling personnel and witnesses, and photos of the concrete test block to the server.
[0025] The detection user terminal scans the QR code label on the concrete test block, takes photos of the whole and front of the concrete test block, and uploads them to the server. When the detection agency accepts the business, it checks the sealing mark and sealing condition of the sample. After the inspection is passed, the detection user terminal scans the QR code label on the concrete test block, takes photos of the whole and front of the concrete test block, and then uploads the concrete test block to the server. Scanning the QR code label of the concrete test block can get the following Figure 4a The concrete test block information shown. Figure 4b As shown, corresponding photos of the whole and front views of the concrete specimens were taken.
[0026] The server compares and analyzes the graphics composed of the sample seal markers in the concrete test block photos uploaded by the sampling user terminal and the testing user terminal. The server compares and analyzes the front view of the concrete test block taken during the witness sampling with the front view of the concrete test block sent for inspection. The server determines whether the concrete test block sent for inspection is the concrete test block for witness sampling by analyzing the consistency between the graphics composed of the sample seal markers in the front view.
[0027] If the photos of each concrete test block are not photos of the same concrete test block, it proves that the concrete test block has been replaced during the inspection process, and an alarm can be issued. If the photos of each concrete test block are photos of the same concrete stone, it proves that the concrete test block submitted for inspection has not been replaced, and the concrete test block submitted for inspection is subjected to pressure test.
[0028] In order to prevent the concrete test block from being replaced during the pressure test, the testing organization can randomly capture the front side photo of the concrete test block through the installed image acquisition device when performing the pressure test on the concrete test block, and upload it to the server.
[0029] After receiving the photos uploaded by the image acquisition device, the server can compare and analyze the graphics composed of the sample sealing markers in the concrete test block photos uploaded by the sampling user terminal and the image acquisition device. The server determines whether the tested concrete test block is the concrete test block for witness sampling by analyzing the consistency between the graphics composed of the sample sealing markers in the front photo. If the photos of each concrete test block are photos of the same concrete test block, it proves that the concrete test block has not been replaced during the test process, and the test report can be output; if the photos of each concrete test block are not photos of the same concrete test block, it proves that the concrete test block has been replaced during the test process, and an alarm can be issued.
[0030] The concrete witness sampling method based on object face recognition provided in this embodiment collects and verifies the information of the current sampling location, sampling personnel and witness personnel through the sampling user terminal, ensuring that the current sampling personnel and witness personnel are at the sampling site to avoid the situation where the witness personnel are not present. The QR code label and N sample sealing markers are implanted into the concrete test block, and then the photos of the sampled and inspected concrete test blocks and the photos of the sampled and tested concrete test blocks are compared and analyzed respectively. By analyzing the graphics formed between the N sample sealing markers on the photos of each concrete test block, it is verified whether the concrete test blocks at each stage have been replaced. The entire process of witness sampling can be traced, which increases the difficulty of replacing concrete test blocks and greatly reduces the probability of concrete test blocks being replaced during inspection and maintenance, thereby ensuring the authenticity of the test report.
[0031] Furthermore, the concrete witness sampling method based on object face recognition provided in this embodiment can also perform the following operations after the sampling user terminal scans the QR code label on the concrete test block: Determine whether the scanned QR code label is unique. The sampling user terminal calls the label microservice interface to verify the uniqueness of the QR code label. If the QR code label is unique, the process of inputting the concrete test block information and taking the overall photo and the front photo of the concrete test block is executed; if it is not unique, an alarm prompt is issued.
[0032] Next, this embodiment introduces the process of the server side comparing and analyzing the graphics composed of the sample sealing markers in the photo of the concrete test block, and the process includes: Extract the location of each sample seal marker in each concrete test block photo. There are six sample seal markers embedded in the concrete test block: yellow A, orange B, red C, purple D, dark blue E, and light blue F. Extract the location of each sample seal marker, the sample seal marker distribution is as follows Figure 5a-5b shown.
[0033] Connect the first sample seal marker on the far left and the second sample seal marker on the far right in each concrete test block photo to obtain the reference axis. Figure 5a As shown, the first sample sealing marker F located on the far left and the sample sealing marker C located on the far right among the six sample sealing markers are connected to obtain a reference axis CF.
[0034] Taking the reference axis as the reference, the third sample sealing marker is diverged to obtain a triangle composed of sample sealing markers. The third sample sealing marker is any sample sealing marker different from the first sample sealing marker and the second sample sealing marker. Figure 5a-5b As shown, the reference axis CF diverges toward the third sample sealing markers A and E respectively, and triangles CFA and CFE formed by the sample sealing markers are obtained.
[0035] Measure the degrees of each angle in a triangle. Use the angle measurement algorithm to measure the degrees of each angle in the triangle. Figure 5a In the CFA triangle figure shown, ∠A=113°, ∠C=29°, and ∠F=38°.
[0036] Compare the lines and angles of the triangles formed by the seal markers in each concrete test block photo. Compare the lines and angles of the triangles formed by the same seal markers in different concrete test block photos. If they are the same, it proves that the concrete test blocks in the concrete test block photos are the same.
[0037] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.
[0038] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0039] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A concrete witness sampling method based on object face recognition, characterized in that: include: When making a concrete test block, a QR code label and N sample sealing markers are implanted into the concrete test block, where N ≥ 3; The sampling user terminal verifies the current sampling location, sampling personnel and witness personnel; if the verification is successful, the QR code label on the concrete test block is scanned, the concrete test block information is input, and the overall photo and front photo of the concrete test block, and the on-site photo of the sampling personnel and witness personnel are taken; The sampling user terminal uploads the QR code label, on-site photos of the sampling personnel and witnesses, and photos of the concrete test block to the server; The detection user terminal scans the QR code label on the concrete test block, takes overall photos and front photos of the concrete test block, and uploads them to the server; The server compares and analyzes the graphics composed of the sample sealing markers in the concrete test block photos uploaded by the sampling user terminal and the detection user terminal; if the concrete test block photos are photos of the same concrete test block, the concrete test block is subjected to pressure testing; When the image acquisition device performs pressure testing on the concrete test block, it randomly acquires a front photo of the concrete test block and uploads it to the server; The server compares and analyzes the graphics composed of the sealing markers in the concrete test block photos uploaded by the sampling user terminal and the image acquisition device. If the concrete test block photos are not photos of the same concrete test block, an alarm prompt is issued.
2. The concrete witness sampling method based on object face recognition according to claim 1 is characterized in that: The process of the sampling user terminal verifying the current sampling location, sampling personnel and witnesses includes: The sampling user terminal obtains the current sampling location and determines whether the current sampling location is within a preset target sampling area; If they are within the target sampling area, the identities of the samplers and witnesses will be verified through facial recognition.
3. The concrete witness sampling method based on object face recognition according to claim 1 is characterized in that: The process of comparing and analyzing the graphics composed of the seal markers in the photo of the concrete test block by the server includes: Extract the position of each sample seal marker in each concrete test block photo; Connect the first sample seal marker on the far left and the second sample seal marker on the far right in the photo of each concrete test block to obtain a reference axis; Taking the reference axis as a reference, diverge toward the third sample sealing marker to obtain a triangle formed by the sample sealing markers; Measure the angles of a triangle; Compare the lines and angles of the triangles formed by the sealing markers in the photos of each concrete specimen.
4. The concrete witness sampling method based on object face recognition according to claim 3 is characterized in that: After the sampling user terminal scans the QR code label on the concrete test block, it also includes: Determine whether the scanned QR code label is unique; If yes, the process of inputting the concrete test block information and taking overall and frontal photos of the concrete test block, and on-site photos of the sampling personnel and witnesses is performed; If not, an alarm will be issued.
5. A concrete witness sampling system based on object face recognition, characterized in that: To implement the concrete witness sampling method described in any one of claims 1 to 4, the system comprises: a QR code label, N sample sealing markers, a sampling user terminal, a detection user terminal, an image acquisition device, and a server; The QR code label and N sample sealing markers are embedded in the concrete test block, where N ≥ 3; The sampling user terminal verifies the current sampling location, sampling personnel and witness personnel; if the verification is successful, the QR code label on the concrete test block is scanned, the concrete test block information is input, and the overall photo and front photo of the concrete test block, and the on-site photo of the sampling personnel and witness personnel are taken; The sampling user terminal uploads the QR code label, on-site photos of the sampling personnel and witnesses, and photos of the concrete test block to the server; The detection user terminal scans the QR code label on the concrete test block, takes overall photos and front photos of the concrete test block, and uploads them to the server; The server compares and analyzes the graphics composed of the sample sealing markers in the photos of the concrete test blocks uploaded by the sampling user terminal and the detection user terminal; if the photos of the concrete test blocks are photos of the same concrete test block, the concrete test block is subjected to pressure testing; When the image acquisition device performs pressure testing on the concrete test block, it randomly acquires a front photo of the concrete test block and uploads it to the server; The server compares and analyzes the graphics composed of the sealing markers in the photos of the concrete test blocks uploaded by the sampling user terminal and the image acquisition device. If the photos of the concrete test blocks are not photos of the same concrete test block, an alarm prompt is issued.