CN115546108A - Intelligent detection method for appearance quality of automobile tire based on edge cloud cooperation and AR - Google Patents
Intelligent detection method for appearance quality of automobile tire based on edge cloud cooperation and AR Download PDFInfo
- Publication number
- CN115546108A CN115546108A CN202211084168.6A CN202211084168A CN115546108A CN 115546108 A CN115546108 A CN 115546108A CN 202211084168 A CN202211084168 A CN 202211084168A CN 115546108 A CN115546108 A CN 115546108A
- Authority
- CN
- China
- Prior art keywords
- automobile tire
- defect
- image
- real
- intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
Abstract
The invention provides an intelligent detection method, system, storage medium and electronic device for the appearance quality of an automobile tire based on edge cloud coordination and AR, and relates to the technical field of intelligent detection of the appearance quality of the tire. The embodiment of the invention is applied to an edge end which is respectively in communication connection with a cloud service platform and a plurality of terminals, and the method comprises the steps of receiving real-time acquired automobile tire images, wherein the real-time automobile tire images are acquired by the terminals through AR glasses; and calling a deep learning model of the automobile tire appearance detection trained by the cloud service platform, and taking the real-time automobile tire image as the input of the deep learning model to obtain an intelligent quality detection result. The appearance defect of the automobile tire is quickly and accurately detected through a three-layer framework of a cloud service platform, an edge end and a terminal; adopt AR glasses can follow different angles or position and collect many same automobile tire outward appearance images in real time, be favorable to in time discovering the problem, further improve detection efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent detection of tire appearance quality, in particular to an intelligent detection method, system, storage medium and electronic equipment for automobile tire appearance quality based on edge cloud cooperation and AR.
Background
Industrial quality inspection is very important in modern manufacturing industry, and defects such as tiny scratches and pits on the surface of a product can cause serious accidents, for example, the air bubble defect and sundry defect of an automobile tire can directly affect the use effect and even cause life and property loss. The development of artificial intelligence technology has enabled industrial quality inspection, and the efficiency and the accuracy are comprehensively improved.
At present, no special algorithm or technology exists for researching the detection of the appearance defects of the automobile tires, and workers are required to judge whether the tires have the defects or not through image observation and classify the defects according to subjective feeling. The judgment is easily interfered by external conditions, the task of workers is heavy, and the working time is long, so that the phenomena of missed detection and wrong detection in the tire detection process frequently occur. In addition, although a method of edge cloud cooperation is proposed to achieve tire appearance quality detection, the cloud computing platform has low real-time performance of defect detection, and the edge computing platform has limited computing resources and storage resources, so that a complex deep learning model cannot be used.
In view of the above, it is necessary to provide a solution for improving the accuracy and efficiency of the quality detection of the appearance of the automobile tire.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides an intelligent detection method, a system, a storage medium and electronic equipment for the appearance quality of an automobile tire based on edge cloud coordination and AR, and solves the technical problem that the accuracy and efficiency of the existing detection of the appearance quality of the automobile tire are still to be improved.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
an intelligent detection method for the appearance quality of an automobile tire based on edge cloud coordination and AR is applied to an edge end, wherein the edge end is respectively in communication connection with a cloud service platform and a plurality of terminals, and the method comprises the following steps:
s1, receiving a real-time acquired automobile tire image, wherein the real-time automobile tire image is acquired by a terminal through AR glasses;
s2, calling a deep learning model of the automobile tire appearance detection trained by the cloud service platform, and taking the real-time automobile tire image as the input of the deep learning model to obtain an intelligent quality detection result.
Preferably, the method further comprises:
and S3, marking the defect position, the defect type and the probability value of the defect type of the real-time automobile tire image with the defect according to the intelligent quality detection result, and sending the defect position, the defect type and the probability value to a terminal for displaying.
Preferably, the S3 further includes: and sending the marking result to the cloud service platform for optimizing the deep learning model.
Preferably, the deep learning model of S2 adopts a YOLOv5 model, and the training process specifically includes:
s10, constructing a sample data set, wherein the sample data set comprises automobile tire images with defects;
s20, calling initial model parameters by adopting a transfer learning method, inputting the sample data set, and calculating the sample through forward propagation to obtain the position and the size of a tire defect image prediction frame and the type of the contained defects;
s30, taking the category with the highest probability value in the defect samples as a sample defect category;
s40, according to the difference between the sample defect detection type and the actual defect type obtained in the step S30, updating the weight matrix and the bias in forward propagation through gradient descent iteration, and reducing the loss between the prediction frame and the real frame;
s50, repeating the steps S20 to S30 until the set training batch-S ize is reached.
Preferably, the constructing the sample data set in S10 specifically includes:
the method comprises the following steps of reasonably arranging a camera outside a tire, and snapshotting the tire in the rotation process of the tire to obtain a plurality of samples containing the same defect, wherein the samples are images shot at different angles or positions;
carrying out mirror image, noise increasing, image brightening, image darkening and image Gaussian filtering operations on the collected images, and expanding an original data set;
and marking the defect region of the image information in the expanded data set by using a LabelImg image marking tool, and determining the actual defect type in the image.
An intelligent automobile tire appearance quality detection system based on edge cloud cooperation and AR is applied to an edge end, the edge end is respectively in communication connection with a cloud service platform and a plurality of terminals, and the method comprises the following steps:
the receiving module is used for receiving the real-time acquired automobile tire images, and the real-time automobile tire images are acquired by the terminal through AR glasses;
and the detection module is used for calling a deep learning model of the automobile tire appearance detection trained by the cloud service platform, taking the real-time automobile tire image as the input of the deep learning model, and acquiring the intelligent quality detection result.
Preferably, the system further comprises:
and the feedback module is used for marking the defect position, the defect type and the probability value of the defect type of the real-time automobile tire image with the defect according to the intelligent quality detection result and sending the real-time automobile tire image with the defect to a terminal for displaying.
Preferably, the feedback module is further configured to send the marking result to the cloud service platform for optimizing the deep learning model.
A storage medium storing a computer program for intelligent detection of automobile tire appearance quality based on edge cloud coordination and AR, wherein the computer program causes a computer to execute the intelligent detection method of automobile tire appearance quality as described above.
An electronic device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the intelligent detection method for the appearance quality of an automobile tire as described above.
(III) advantageous effects
The invention provides an intelligent detection method, system, storage medium and electronic equipment for the appearance quality of an automobile tire based on edge cloud cooperation and AR. Compared with the prior art, the method has the following beneficial effects:
the method is applied to an edge end which is respectively in communication connection with a cloud service platform and a plurality of terminals, and comprises the steps of receiving real-time acquired automobile tire images, wherein the real-time automobile tire images are acquired by the terminals through AR glasses; and calling a deep learning model of the automobile tire appearance detection trained by the cloud service platform, and taking the real-time automobile tire image as the input of the deep learning model to obtain an intelligent quality detection result. The appearance defect of the automobile tire is quickly and accurately detected through a three-layer framework of a cloud service platform, an edge end and a terminal; adopt AR glasses can follow different angles or position and collect many same automobile tire outward appearance images in real time, be favorable to in time discovering the problem, further improve detection efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow diagram of an intelligent detection method for appearance quality of an automobile tire based on edge cloud coordination and AR according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of an intelligent detection method for the appearance quality of an automobile tire based on edge cloud coordination and AR according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a cloud service platform, an edge segment, and a terminal according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer and more complete description of the technical solutions in the embodiments of the present invention, it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the application provides an intelligent detection method, system, storage medium and electronic device for the appearance quality of an automobile tire based on edge cloud cooperation and AR, and solves the technical problem that the accuracy and efficiency of the existing detection of the appearance quality of the automobile tire are still to be improved.
In order to solve the technical problems, the general idea of the embodiment of the application is as follows:
the embodiment of the invention is applied to an edge end which is respectively in communication connection with a cloud service platform and a plurality of terminals, as shown in figure 1, the method comprises the steps of receiving real-time acquired automobile tire images, wherein the real-time automobile tire images are acquired by the terminals through AR glasses; and calling a deep learning model of the automobile tire appearance detection trained by the cloud service platform, and taking the real-time automobile tire image as the input of the deep learning model to obtain an intelligent quality detection result. The appearance defect of the automobile tire is quickly and accurately detected through a three-layer framework of a cloud service platform, an edge end and a terminal; adopt AR glasses can follow different angles or position and collect many same automobile tire outward appearance images in real time, be favorable to in time discovering the problem, further improve detection efficiency.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
The embodiment is as follows:
as shown in fig. 2, an embodiment of the present invention provides an intelligent detection method for appearance quality of an automobile tire based on edge cloud coordination and AR, which is applied to an edge end, where the edge end is respectively in communication connection with a cloud service platform and a plurality of terminals (for example, connected through a USB interface or an ethernet interface), and the method includes:
s1, receiving a real-time acquired automobile tire image, wherein the real-time automobile tire image is acquired by a terminal through AR glasses;
s2, calling a deep learning model of the automobile tire appearance detection trained by the cloud service platform, and taking the real-time automobile tire image as the input of the deep learning model to obtain an intelligent quality detection result.
And S3, marking the defect position, the defect type and the probability value of the defect type of the real-time automobile tire image with the defect according to the intelligent quality detection result, sending the mark to a terminal for displaying, and sending the mark result to a cloud service platform for optimizing the deep learning model.
According to the embodiment of the invention, the three-layer framework of the cloud service platform, the edge end and the terminal as shown in FIG. 3 is adopted, so that the appearance defects of the automobile tire can be quickly and accurately detected; after the intelligent quality detection result is sent to the terminal, relevant personnel can take corresponding operations according to the detection result and feed back the defect image and the marking result to the cloud computing platform to optimize the model, so that the accuracy and the efficiency of the appearance quality detection of the automobile tire are improved.
The following will describe each step of the above technical solution in detail with reference to the specific content:
in step S1, a real-time acquired automobile tire image is received, and the real-time automobile tire image is acquired by a terminal using AR glasses.
Adopt AR glasses can follow different angles or position and collect many same automobile tire outward appearance images in real time, be favorable to in time discovering the problem, further improve detection efficiency.
In step S2, a deep learning model of the automobile tire appearance detection trained by the cloud service platform is called, and the real-time automobile tire image is used as an input of the deep learning model to obtain an intelligent quality detection result.
The deep learning model of the S2 adopts a YOLOv5 model, and the training process specifically comprises the following steps:
s10, constructing a sample data set, wherein the sample data set comprises automobile tire images with defects; specifically, the method comprises the following steps:
the method comprises the following steps of reasonably arranging a camera outside a tire, and taking a snapshot in the tire rotating process to obtain a plurality of samples containing the same defect, wherein the samples are images shot at different angles or positions respectively; assuming that the total number of samples in the original data set is 400 pictures, the samples are divided into 2 categories with defects and defects, each category has 200 pictures, wherein 140 pictures are respectively in the test set, and 60 pictures are respectively in the verification set: bubble defect images and debris defect images.
In order to make the trained model more robust, the collected images are subjected to mirror image, noise increasing, image brightening, image darkening and image Gaussian filtering operation, and an original data set is expanded; the expanded data set comprises 2400 pictures in total, 840 images in each category of the training set, and 360 pictures in each category of the testing set.
And marking the defect region of the image information in the expanded data set by using a LabelImg image marking tool, determining the actual defect type in the image, and finally constructing a sample data set.
S20, training through a hot-rolled strip steel surface defect data set of the university of northeast to obtain initial parameter setting information of the YOLOv5 model, and calling initial model parameters by adopting a transfer learning method.
Inputting the sample data set into the model, and calculating the sample through forward propagation to obtain the position and the size of a tire defect image prediction frame and the type of the contained defects;
s30, taking the category with the highest probability value in the defect samples as a sample defect category;
s40, according to the difference between the sample defect detection type and the actual defect type obtained in the step S30, updating the weight matrix and the bias in forward propagation through gradient descent iteration, and reducing the loss between the prediction frame and the real frame;
and S50, repeating the steps S20 to S30 until the set training batch size is reached.
In step S3, according to the quality intelligent detection result, marking the defect position, the defect type and the probability value of the defect type of the real-time automobile tire image with the defect, sending the marking result to a terminal for displaying, and sending the marking result to the cloud service platform for optimizing the deep learning model.
And sending the marking result to a terminal for displaying, wherein the marking result is used for assigning relevant workers to take further operation.
And sending the marking result to the cloud service platform for continuously adjusting model parameters (such as training times, initial learning rate, initial image size and the like of the model), improving the accuracy of identifying the appearance defects of the automobile tires and reducing loss values. And saving the trained weight model best.pt, directly calling when the model is trained next time, and outputting a defect detection result.
According to the embodiment of the invention, model training is carried out on the cloud computing platform, and defect detection is carried out on the edge computing platform, so that the computing burden of the cloud is reduced, and the real-time performance of the system is improved; the detection efficiency of the algorithm is high, the average precision of the two categories is improved, and the labor cost is reduced.
The embodiment of the invention provides an intelligent automobile tire appearance quality detection system based on edge cloud cooperation and AR, which is applied to an edge terminal, wherein the edge terminal is respectively in communication connection with a cloud service platform and a plurality of terminals, and the method comprises the following steps:
the receiving module is used for receiving the real-time acquired automobile tire images, and the real-time automobile tire images are acquired by the terminal through AR glasses;
the detection module is used for calling a deep learning model of the appearance detection of the automobile tire trained by the cloud service platform, taking the real-time automobile tire image as the input of the deep learning model and acquiring the intelligent quality detection result;
and the feedback module is used for marking the defect position, the defect type and the probability value of the defect type of the real-time automobile tire image with the defect according to the intelligent quality detection result, sending the mark to a terminal for displaying, and sending the mark result to the cloud service platform for optimizing the deep learning model.
The embodiment of the invention provides a storage medium, which stores a computer program for intelligent detection of appearance quality of an automobile tire based on edge cloud cooperation and AR, wherein the computer program enables a computer to execute the intelligent detection method of the appearance quality of the automobile tire.
An embodiment of the present invention provides an electronic device, including:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the intelligent detection method for the appearance quality of an automobile tire as described above.
It can be understood that, the intelligent detection system, the storage medium, and the electronic device for the appearance quality of the automobile tire based on the edge cloud coordination and the AR provided in the embodiment of the present invention correspond to the intelligent detection method for the appearance quality of the automobile tire based on the edge cloud coordination and the AR provided in the embodiment of the present invention, and the explanation, the example, the beneficial effects, and other parts of the relevant contents may refer to the corresponding parts in the intelligent detection method for the appearance quality of the automobile tire, which are not described herein again.
In summary, compared with the prior art, the method has the following beneficial effects:
1. the embodiment of the invention realizes the rapid and accurate detection of the appearance defects of the automobile tire through the three-layer framework of the cloud service platform, the edge end and the terminal; after the intelligent quality detection result is sent to the terminal, relevant personnel can take corresponding operations according to the detection result and feed back the defect image and the marking result to the cloud computing platform to optimize the model, so that the accuracy and the efficiency of the appearance quality detection of the automobile tire are improved.
2. Adopt AR glasses can follow different angles or position and collect many same automobile tire outward appearance images in real time, be favorable to in time discovering the problem, further improve detection efficiency.
3. According to the embodiment of the invention, model training is carried out on the cloud computing platform, and defect detection is carried out on the edge computing platform, so that the computing burden of the cloud is reduced, and the real-time performance of the system is improved; the detection efficiency of the algorithm is high, the average precision of the two categories is improved, and the labor cost is reduced.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An intelligent detection method for the appearance quality of an automobile tire based on edge cloud coordination and AR is characterized by being applied to an edge end, wherein the edge end is in communication connection with a cloud service platform and a plurality of terminals respectively, and the method comprises the following steps:
s1, receiving a real-time acquired automobile tire image, wherein the real-time automobile tire image is acquired by a terminal through AR glasses;
s2, calling a deep learning model of the automobile tire appearance detection trained by the cloud service platform, and taking the real-time automobile tire image as the input of the deep learning model to obtain an intelligent quality detection result.
2. The intelligent detection method for the appearance quality of the automobile tire according to claim 1, further comprising:
and S3, marking the defect position, the defect type and the probability value of the defect type of the real-time automobile tire image with the defect according to the intelligent quality detection result, and sending the mark to a terminal for displaying.
3. The intelligent detection method for the appearance quality of the automobile tire according to claim 2, wherein the step S3 further comprises: and sending the marking result to the cloud service platform for optimizing the deep learning model.
4. The intelligent detection method for the appearance quality of the automobile tire according to any one of claims 1 to 3, wherein the deep learning model of S2 adopts a YOLOv5 model, and the training process specifically comprises:
s10, constructing a sample data set, wherein the sample data set comprises automobile tire images with defects;
s20, calling initial model parameters by adopting a transfer learning method, inputting the sample data set, and calculating the sample through forward propagation to obtain the position and the size of a tire defect image prediction frame and the type of the contained defects;
s30, taking the category with the highest probability value in the defect samples as a sample defect category;
s40, according to the difference between the sample defect detection type and the actual defect type obtained in the step S30, updating the weight matrix and the bias in forward propagation through gradient descent iteration, and reducing the loss between the prediction frame and the real frame;
and S50, repeating the steps S20 to S30 until the set exercise batch size is reached.
5. The intelligent detection method for the appearance quality of the automobile tire according to claim 4, wherein the step S10 of constructing a sample data set specifically comprises the following steps:
the method comprises the following steps of reasonably arranging a camera outside a tire, and taking a snapshot in the tire rotating process to obtain a plurality of samples containing the same defect, wherein the samples are images shot at different angles or positions respectively;
carrying out mirror image, noise increasing, image brightening, image darkening and image Gaussian filtering operations on the collected images, and expanding an original data set;
and marking the defect region of the image information in the expanded data set by using a LabelImg image marking tool, and determining the actual defect type in the image.
6. The intelligent automobile tire appearance quality detection system based on edge cloud cooperation and AR is characterized by being applied to an edge end, wherein the edge end is in communication connection with a cloud service platform and a plurality of terminals respectively, and the method comprises the following steps:
the receiving module is used for receiving the real-time acquired automobile tire images, and the real-time automobile tire images are acquired by the terminal through AR glasses;
and the detection module is used for calling a deep learning model of the automobile tire appearance detection trained by the cloud service platform, taking the real-time automobile tire image as the input of the deep learning model, and acquiring the intelligent quality detection result.
7. The intelligent detection system for the appearance quality of the automobile tire according to claim 6, characterized by further comprising:
and the feedback module is used for marking the defect position, the defect type and the probability value of the defect type of the real-time automobile tire image with the defect according to the intelligent quality detection result and sending the real-time automobile tire image with the defect to a terminal for displaying.
8. The intelligent detection method for the appearance quality of the automobile tire according to claim 7, wherein the feedback module is further configured to send the marking result to the cloud service platform for optimizing the deep learning model.
9. A storage medium storing a computer program for intelligent detection of appearance quality of automobile tires based on edge cloud coordination and AR, wherein the computer program causes a computer to execute the intelligent detection method of appearance quality of automobile tires according to any one of claims 1 to 5.
10. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs comprising instructions for performing the intelligent detection method of the appearance quality of automobile tires according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211084168.6A CN115546108A (en) | 2022-09-06 | 2022-09-06 | Intelligent detection method for appearance quality of automobile tire based on edge cloud cooperation and AR |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211084168.6A CN115546108A (en) | 2022-09-06 | 2022-09-06 | Intelligent detection method for appearance quality of automobile tire based on edge cloud cooperation and AR |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115546108A true CN115546108A (en) | 2022-12-30 |
Family
ID=84725552
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211084168.6A Pending CN115546108A (en) | 2022-09-06 | 2022-09-06 | Intelligent detection method for appearance quality of automobile tire based on edge cloud cooperation and AR |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115546108A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116152228A (en) * | 2023-04-14 | 2023-05-23 | 山东奇妙智能科技有限公司 | Tire defect detection method and system based on machine vision and machine learning |
-
2022
- 2022-09-06 CN CN202211084168.6A patent/CN115546108A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116152228A (en) * | 2023-04-14 | 2023-05-23 | 山东奇妙智能科技有限公司 | Tire defect detection method and system based on machine vision and machine learning |
CN116152228B (en) * | 2023-04-14 | 2023-06-27 | 山东奇妙智能科技有限公司 | Tire defect detection method and system based on machine vision and machine learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP7138753B2 (en) | Image defect detection method, device, electronic device, storage medium and product | |
CN111951249A (en) | Mobile phone light guide plate defect visual detection method based on multitask learning network | |
CN111680750B (en) | Image recognition method, device and equipment | |
CN111402236B (en) | Hot rolled strip steel surface defect grading method based on image gray value | |
CN113469951B (en) | Hub defect detection method based on cascade region convolutional neural network | |
CN113393438B (en) | Resin lens defect detection method based on convolutional neural network | |
CN110020691B (en) | Liquid crystal screen defect detection method based on convolutional neural network impedance type training | |
CN115131283A (en) | Defect detection and model training method, device, equipment and medium for target object | |
WO2024002187A1 (en) | Defect detection method, defect detection device, and storage medium | |
CN114743102A (en) | Furniture board oriented flaw detection method, system and device | |
CN115546108A (en) | Intelligent detection method for appearance quality of automobile tire based on edge cloud cooperation and AR | |
CN115937101A (en) | Quality detection method, device, equipment and storage medium | |
CN115829995A (en) | Cloth flaw detection method and system based on pixel-level multi-scale feature fusion | |
CN111879972A (en) | Workpiece surface defect detection method and system based on SSD network model | |
CN113205511B (en) | Electronic component batch information detection method and system based on deep neural network | |
CN117372424B (en) | Defect detection method, device, equipment and storage medium | |
CN114881996A (en) | Defect detection method and device | |
CN110852318A (en) | Drainage pipeline defect accurate positioning method and system | |
CN113516652A (en) | Battery surface defect and adhesive detection method, device, medium and electronic equipment | |
CN113870204A (en) | Method and device for detecting abnormality of optical glass | |
CN113327243A (en) | PAD light guide plate defect visualization detection method based on AYOLOv3-Tiny new framework | |
CN115239733B (en) | Crack detection method and apparatus, terminal device and storage medium | |
CN115984215A (en) | Fiber bundle defect detection method based on twin network | |
CN115457323A (en) | Visual inspection system-based method for classifying non-uniform surface defects of mobile phone glass screen | |
CN115222691A (en) | Image defect detection method, system and related device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |