A method for checking and delivering sealed samples based on intelligent image recognition and radio frequency recognition

Abstract

The present invention discloses a method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification, including: inputting information on different types of sealed samples to determine first input information; inputting information on different types of storage boxes to determine second input information; establishing a matching relationship between the first input information and the second input information, and shooting a first video of storing the sealed samples in a storage box of a corresponding type; determining first monitoring information based on image recognition for the first video; obtaining identification information of a radio frequency tag on a storage box containing the sealed samples to determine second monitoring information; determining sealed sample delivery information based on the first monitoring information and the second monitoring information, and judging the safety of sealed sample delivery based on the sealed sample delivery information. The present invention is based on the storage box for transportation to avoid the risk of damaged and lost sealed samples; at the same time, effective monitoring is performed during the transportation process to improve the safety of the sealed sample delivery process.

Description

Technical Field

[0001] The present invention relates to the technical field of sample sealing and transportation monitoring, and in particular to a sample sealing and transportation method based on intelligent image recognition and radio frequency recognition. Background Art

[0002] Sealed samples for inspection: Send the sealed samples to the testing center for quality inspection. In the allocation and transportation of materials, especially the allocation and transportation of samples, it is necessary to ensure that the items can be transported to the destination intact. However, in the actual operation process, samples will be touched by different people in different processes such as sample packaging and sample transportation. Since these processes are usually carried out in different procedures and fixed points, it cannot be guaranteed that the samples can remain intact after this series of processes, nor can the operations of the samples through this series of processes be traced. Although the existing technology tracks and locates samples by setting radio frequency tags in the samples, which can avoid the loss of samples to a certain extent, it still cannot effectively identify the processing operations and people that the samples have been exposed to during the production, packaging and transportation process.

[0003] At present, when the sealed samples are sent to the testing center for quality inspection, there is no record of the storage boxes used for the transported sealed samples, and effective management cannot be carried out. It is impossible to select suitable storage boxes for transport according to the unique properties of the transported sealed samples, which may lead to the risk of damaged and lost sealed samples, and the management efficiency is low. During the transport process, there is a lack of effective monitoring, and it is impossible to determine whether the sealed samples are lost or replaced, etc., and the safety of the sealed samples during inspection cannot be guaranteed. Summary of the invention

[0004] In order to overcome the problems existing in the prior art, the purpose of the present invention is to provide a method for sample inspection based on intelligent image recognition and radio frequency identification, which is based on storage boxes for transportation, records and effectively manages the storage boxes used for sample transportation, selects appropriate storage boxes for transportation according to the unique properties of the sample transportation, avoids the risk of sample damage and sample loss, and improves management efficiency. At the same time, effective monitoring is carried out during the transportation process to improve the safety of the sample inspection process.

[0005] To achieve the above object, the technical solution of the present invention is as follows:

[0006] A method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification, characterized by comprising:

[0007] 1) Enter information for different types of seals and determine the first entry information;

[0008] 2) Entering information for different types of storage boxes to determine second entry information;

[0009] 3) establishing a matching relationship between the first input information and the second input information, and shooting a first video of storing the sealed sample in a storage box of a corresponding type;

[0010] 4) determining first monitoring information based on image recognition of the first video;

[0011] 5) obtaining identification information of the radio frequency tag on the storage box containing the sealed sample and determining the second monitoring information;

[0012] 6) Determine the sample sealing inspection information according to the first monitoring information and the second monitoring information, and judge the safety of the sample sealing inspection according to the sample sealing inspection information.

[0013] Furthermore, during the inspection process, the sealed sample is photographed based on the camera module inside the storage box to determine the second video; based on the image recognition of the second video, the third monitoring information is determined; the status information of the sealed sample is judged based on the third monitoring information, and the status information is sent to the background server.

[0014] Further, information is input for different types of seal samples to determine the first input information, including:

[0015] 11) Collecting a 3D image of the seal, analyzing the 3D image, and determining the type and spatial coordinates of the seal;

[0016] 12) Determining volume information of the sealed sample according to the spatial coordinates;

[0017] 13) Query the preset type-density data table according to the type of the seal to determine the target density;

[0018] 14) Determine the weight information of the sealed sample according to the target density and volume information;

[0019] 15) Determine first input information according to the volume information and the weight information.

[0020] The 3D image is analyzed to determine the type of the sealing sample, including:

[0021] Structural division of 3D images based on image recognition to determine each component part;

[0022] Each component is matched with a preset component respectively, and the type of corresponding sealing sample is determined according to the matching result.

[0023] Determining first monitoring information based on image recognition for the first video includes:

[0024] 41) performing frame processing on the first video to obtain a plurality of frame images, and determining sequence information between the plurality of frame images;

[0025] 42) performing image recognition on a plurality of frames of images according to the sequence information to determine image feature information corresponding to each frame of image;

[0026] 43) determining the step of storing in a storage box according to the image feature information, and comparing it with the preset storage step, and classifying it according to the comparison result to obtain classification information;

[0027] 44) dividing the sequence information into a plurality of subsequence information according to the classification information;

[0028] 45) Determine first monitoring information based on a plurality of subsequence information.

[0029] Further, performing image recognition on a plurality of frames of images according to the sequence information to determine image feature information corresponding to each frame of image includes:

[0030] In each frame of the image, an image corresponding to the seal, an image corresponding to the storage box, and an image including the seal and the storage box are determined as target images;

[0031] The first position of the seal, the second position of the storage box, and the association between the first position and the second position are determined according to the target image, and then the image feature information corresponding to each frame of the image is determined.

[0032] In each frame of image, an image corresponding to the seal, an image corresponding to the storage box, and an image including the seal and the storage box are determined as target images, including:

[0033] Identify the seal sample, extract the outline of the seal sample, obtain a first outline, and determine a first image corresponding to the first outline;

[0034] Identify the storage box, extract the contour of the storage box to obtain a second contour, and determine a second image corresponding to the second contour;

[0035] determining a third image including the first contour and the second contour;

[0036] A target image is determined according to the first image, the second image and the third image.

[0037] Furthermore, the present invention also includes: before performing image recognition on the plurality of image frames according to the sequence information, performing image denoising processing on the plurality of image frames.

[0038] Obtaining identification information of a radio frequency tag on a storage box containing a sealed sample and determining second monitoring information includes:

[0039] Based on the radio frequency identifier identifying the radio frequency tag on the storage box, determine to extract information;

[0040] Preprocessing the extracted information to obtain identification information;

[0041] The second monitoring information is determined according to the identification information.

[0042] The preprocessing includes data screening and data repair.

[0043] The beneficial effects of the present invention are: transporting based on the storage box avoids the risk of damage to the sealed sample and loss of the sealed sample. At the same time, effective monitoring is carried out during the transport process to improve the safety of the sealed sample inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of a method for sealing and inspecting samples based on intelligent image recognition and radio frequency recognition of the present invention;

[0045] Figure 2 is a flow chart of determining first input information according to an embodiment of the present invention;

[0046] Figure 3 is a flowchart of determining first monitoring information according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0048] like Figure 1 As shown, the embodiment of the present invention proposes a method for checking and delivering sealed samples based on intelligent image recognition and radio frequency recognition, including steps S1-S6:

[0049] S1. Enter information for different types of seals and determine first entry information;

[0050] S2. Enter information for different types of storage boxes to determine second entry information;

[0051] S3, establishing a matching relationship between the first input information and the second input information, and shooting a first video of storing the sealed sample in a storage box of a corresponding type;

[0052] S4. Determine first monitoring information based on image recognition of the first video;

[0053] S5, obtaining identification information of the radio frequency tag on the storage box containing the sealed sample, and determining the second monitoring information;

[0054] S6. Determine the sample sealing and inspection information according to the first monitoring information and the second monitoring information, and judge the safety of the sample sealing and inspection according to the sample sealing and inspection information.

[0055] The working principle and beneficial effects of the above technical solution: In the process of sending sealed samples for inspection, there are many different types of sealed samples that need to be sent for inspection. Before sending for inspection, information of different types of sealed samples is entered to determine the first input information; the information of the sealed samples is automatically input to realize the recording of different types of sealed samples. Information is entered for different types of storage boxes to determine the second input information; and the recording of different types of storage boxes is realized. A matching relationship between the first input information and the second input information is established, and a first video of storing the sealed samples in a storage box of the corresponding type is captured; the sealed samples are transported based on the storage boxes, and the storage boxes used for transporting the sealed samples are recorded and effectively managed. According to the unique attributes of the transported sealed samples, suitable storage boxes are selected for transport, so as to avoid the risk of damage to the sealed samples and loss of the sealed samples, and improve management efficiency. The matching relationship between the first input information and the second input information is recorded, and the information is recorded and backed up at the inspection end before inspection, so as to improve data management efficiency. Based on image recognition, the first video is used to determine the first monitoring information; the identification information of the radio frequency tag on the storage box containing the sealed sample is obtained to determine the second monitoring information; based on the first monitoring information and the second monitoring information, the sealed sample inspection information is determined, and the safety of the sealed sample inspection is judged based on the sealed sample inspection information. At the same time, during the transportation process, effective monitoring is carried out based on intelligent image recognition and radio frequency identification to improve the safety of the sealed sample inspection process.

[0056] Some embodiments of the present invention further include:

[0057] During the inspection process, the sealed sample is photographed based on the camera module inside the storage box to determine the second video;

[0058] determining third monitoring information based on image recognition of the second video;

[0059] The state information of the sealing sample is determined according to the third monitoring information, and the state information is sent to the backend server.

[0060] The working principle and beneficial effects of the above technical solution are as follows: During the inspection process, the sealed sample is photographed based on the camera module inside the storage box to determine the second video; the third monitoring information is determined based on the image recognition of the second video; the status information of the sealed sample is determined based on the third monitoring information, and the status information is sent to the background server. The sealed sample inside the storage box is also effectively monitored, and combined with the radio frequency identification technology, the storage box and the sealed sample inside the storage box are comprehensively monitored during the inspection process.

[0061] like Figure 2 As shown, in some embodiments of the present invention, information entry is performed on different types of seals to determine first entry information, including steps S11-S15:

[0062] S11, collecting a 3D image of the sample seal, analyzing the 3D image, and determining the type and spatial coordinates of the sample seal;

[0063] S12, determining volume information of the sealed sample according to the spatial coordinates;

[0064] S13, querying the preset type-density data table according to the type of the sealing sample, and determining the target density;

[0065] S14, determining the weight information of the sealed sample according to the target density and volume information;

[0066] S15. Determine first input information according to the volume information and the weight information.

[0067] The working principle and beneficial effects of the above technical solution are as follows: a 3D image of the sample seal is collected, the 3D image is analyzed, and the type and spatial coordinates of the sample seal are determined; the method for determining the spatial coordinates includes: establishing a coordinate system, determining the spatial coordinates in the 3D image, and determining the actual size of the sample seal based on the conversion of the actual size in the image, and then determining the actual spatial coordinates. The volume information of the sample seal is determined according to the spatial coordinates; the preset type-density data table is queried according to the type of the sample seal to determine the target density; the weight information of the sample seal is determined according to the target density and volume information; the first input information is determined according to the volume information and the weight information. To facilitate automatic recognition of the sample seal, the volume information and the weight information are determined based on image recognition technology, and recorded as the first input information.

[0068] In some embodiments of the present invention, parsing the 3D image to determine the type of the sealing sample includes:

[0069] Structural division of 3D images based on image recognition to determine each component part;

[0070] Each component is matched with a preset component respectively, and the type of corresponding sealing sample is determined according to the matching result.

[0071] The working principle and beneficial effects of the above technical solution are as follows: the 3D image is structurally divided based on image recognition to determine each component part; each component is to determine the image corresponding to each component of the sample. Each component is matched with the preset component respectively, and the type of the corresponding sample is determined according to the matching result. The preset component is the image corresponding to the component included in the database. According to the matching result, the type of the corresponding sample is determined, which is convenient for determining which components are included in the sample, and then determining the type of the sample.

[0072] like Figure 3 As shown, in some embodiments of the present invention, determining first monitoring information based on image recognition for a first video includes:

[0073] S41 performs frame processing on the first video to obtain a plurality of frame images, and determines sequence information between the plurality of frame images;

[0074] S42 performs image recognition on a plurality of frames of images according to the sequence information to determine image feature information corresponding to each frame of image;

[0075] S43 determines the step of storing in the storage box according to the image feature information, compares it with the preset storage step, and classifies it according to the comparison result to obtain classification information;

[0076] S44 divides the sequence information into a plurality of subsequence information according to the classification information;

[0077] S45 determines first monitoring information according to the plurality of subsequence information.

[0078] The working principle and beneficial effects of the above technical solution are as follows: the first video is processed by frame division to obtain several frames of images, and the sequence information between the several frames of images is determined; image recognition is performed on the several frames of images according to the sequence information to determine the image feature information corresponding to each frame of image; the step of storing in the storage box is determined according to the image feature information, and compared with the preset storage step, and classified according to the comparison result to obtain classification information; according to the classification information, the sequence information is divided into several sub-sequence information; the first monitoring information is determined according to the several sub-sequence information. It is convenient for users to view the corresponding sub-sequence information according to their needs, avoiding the need to perform search operations when viewing, saving time, and improving user experience.

[0079] Performing image recognition on a plurality of frames of images according to the sequence information to determine image feature information corresponding to each frame of image includes:

[0080] In each frame of the image, an image corresponding to the seal, an image corresponding to the storage box, and an image including the seal and the storage box are determined as target images;

[0081] The first position of the seal, the second position of the storage box, and the association between the first position and the second position are determined according to the target image, and then the image feature information corresponding to each frame of the image is determined.

[0082] The working principle and beneficial effects of the above technical solution are as follows: in each frame of image, the image corresponding to the seal, the image corresponding to the storage box, and the image including the seal and the storage box are determined as the target image; the first position of the seal, the second position of the storage box, and the association between the first position and the second position are determined according to the target image, and then the image feature information corresponding to each frame of image is determined. This facilitates accurate determination of the image feature information corresponding to each frame of image.

[0083] In each frame of image, an image corresponding to the seal, an image corresponding to the storage box, and an image including the seal and the storage box are determined as target images, including:

[0084] Identify the seal sample, extract the outline of the seal sample, obtain a first outline, and determine a first image corresponding to the first outline;

[0085] Identify the storage box, extract the contour of the storage box to obtain a second contour, and determine a second image corresponding to the second contour;

[0086] determining a third image including the first contour and the second contour;

[0087] A target image is determined according to the first image, the second image and the third image.

[0088] The working principle and beneficial effects of the above technical solution are as follows: the seal is identified and the contour of the seal is extracted to determine the first image corresponding to the first contour; the storage box is identified to determine the second image corresponding to the second contour; a third image including the first contour and the second contour is determined; and a target image is determined based on the first image, the second image and the third image. This facilitates the rapid and accurate determination of the target image.

[0089] The present invention further comprises: before performing image recognition on the plurality of frames of images according to the sequence information, performing image denoising processing on the plurality of frames of images.

[0090] The beneficial effect of the above technical solution is that it facilitates improving the accuracy of image recognition.

[0091] Obtaining identification information of a radio frequency tag on a storage box containing a sealed sample and determining second monitoring information includes:

[0092] Based on the radio frequency identifier identifying the radio frequency tag on the storage box, determine to extract information;

[0093] Preprocessing the extracted information to obtain identification information; the preprocessing includes data screening and data repair;

[0094] The second monitoring information is determined according to the identification information.

[0095] The beneficial effects of the above technical solution are: based on the radio frequency identifier, the radio frequency tag on the storage box is identified to determine the extracted information; the extracted information is preprocessed to obtain identification information; based on the preprocessing, invalid data is removed and missing data is repaired to obtain accurate identification information, thereby accurately determining the second monitoring information.

[0096] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification, characterized in that: include: 1) Enter information for different types of seals and determine the first entry information; 2) Entering information for different types of storage boxes to determine second entry information; 3) establishing a matching relationship between the first input information and the second input information, and shooting a first video of storing the sealed sample in a storage box of a corresponding type; 4) Determining first monitoring information based on image recognition of the first video, including: 41) performing frame processing on the first video to obtain a plurality of frame images, and determining sequence information between the plurality of frame images; 42) performing image recognition on a plurality of frames of images according to the sequence information to determine image feature information corresponding to each frame of image; 43) determining the step of storing in a storage box according to the image feature information, and comparing it with the preset storage step, and classifying it according to the comparison result to obtain classification information; 44) dividing the sequence information into a plurality of subsequence information according to the classification information; 45) determining first monitoring information according to a plurality of subsequence information; 5) obtaining identification information of the radio frequency tag on the storage box containing the sealed sample and determining the second monitoring information; 6) Determine the sample sealing inspection information according to the first monitoring information and the second monitoring information, and judge the safety of the sample sealing inspection according to the sample sealing inspection information.

2. The method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification as claimed in claim 1, characterized in that: During the inspection process, a camera module installed inside the storage box shoots the sealed sample to determine the second video; based on image recognition of the second video, the third monitoring information is determined; the status information of the sealed sample is judged according to the third monitoring information, and the status information is sent to the background server.

3. The method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification as claimed in claim 1, characterized in that: In step 1), information is input for different types of seals to determine first input information, including: 11) Collecting a 3D image of the seal, analyzing the 3D image, and determining the type and spatial coordinates of the seal; 12) Determining volume information of the sealed sample according to the spatial coordinates; 13) Query the preset type-density data table according to the type of the seal to determine the target density; 14) Determine the weight information of the sealed sample according to the target density and volume information; 15) Determine first input information according to the volume information and the weight information.

4. The method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification as claimed in claim 3, characterized in that: The 3D image is analyzed to determine the type of the sealing sample, including: Structural division of 3D images based on image recognition to determine each component part; Each component is matched with a preset component respectively, and the type of corresponding sealing sample is determined according to the matching result.

5. The method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification as claimed in claim 1, characterized in that: Performing image recognition on a plurality of frames of images according to the sequence information to determine image feature information corresponding to each frame of image includes: In each frame of the image, an image corresponding to the seal, an image corresponding to the storage box, and an image including the seal and the storage box are determined as target images; The first position of the seal, the second position of the storage box, and the association between the first position and the second position are determined according to the target image, and then the image feature information corresponding to each frame of the image is determined.

6. The method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification as claimed in claim 5, characterized in that: In each frame of image, an image corresponding to the seal, an image corresponding to the storage box, and an image including the seal and the storage box are determined as target images, including: Identify the seal sample, extract the outline of the seal sample, obtain a first outline, and determine a first image corresponding to the first outline; Identify the storage box, extract the contour of the storage box to obtain a second contour, and determine a second image corresponding to the second contour; determining a third image including the first contour and the second contour; A target image is determined according to the first image, the second image and the third image.

7. The method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification as claimed in claim 1, characterized in that: Before performing image recognition on a plurality of frames of images according to the sequence information, image denoising is performed on the plurality of frames of images.

8. The method for checking and delivering sealed samples based on intelligent image recognition and radio frequency identification as claimed in claim 1, characterized in that: In step 5), the identification information of the radio frequency tag on the storage box containing the sealed sample is obtained to determine the second monitoring information, including: Based on the radio frequency identifier identifying the radio frequency tag on the storage box, determine to extract information; Preprocessing the extracted information to obtain identification information; The second monitoring information is determined according to the identification information.

9. The method for checking and delivering sealed samples based on intelligent image recognition and radio frequency recognition as claimed in claim 8, characterized in that: The preprocessing includes data screening and data repair.

Images