CN114401520B - Method and system for detecting thermodynamic diagram of wireless network signal - Google Patents
Method and system for detecting thermodynamic diagram of wireless network signal Download PDFInfo
- Publication number
- CN114401520B CN114401520B CN202111621407.2A CN202111621407A CN114401520B CN 114401520 B CN114401520 B CN 114401520B CN 202111621407 A CN202111621407 A CN 202111621407A CN 114401520 B CN114401520 B CN 114401520B
- Authority
- CN
- China
- Prior art keywords
- rendering
- thermodynamic
- wifi
- actual
- diagram
- 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.)
- Active
Links
- 238000010586 diagram Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000009877 rendering Methods 0.000 claims abstract description 57
- 238000004364 calculation method Methods 0.000 claims abstract description 28
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims description 21
- 238000013135 deep learning Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 4
- 210000005036 nerve Anatomy 0.000 claims description 4
- 230000002776 aggregation Effects 0.000 description 2
- 238000004220 aggregation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/18—Network planning tools
- H04W16/20—Network planning tools for indoor coverage or short range network deployment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/206—Drawing of charts or graphs
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
- H04W16/225—Traffic simulation tools or models for indoor or short range network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a wireless network signal detection thermodynamic diagram method and a system. The method comprises the following steps: step one, converting basic data and real data; step two, calculating a thermodynamic value; step three, thermodynamic diagram rendering; and step four, converting the rendered thermodynamic diagram into a vector diagram. According to the method, a large number of house-type cases are adopted to conduct intelligent training on the rendering model, the calculation speed is high, the result accuracy is higher, and the coverage range of wireless signals can be truly embodied.
Description
Technical Field
The invention belongs to the technical field of wireless network signal detection, and particularly relates to a wireless network signal detection thermodynamic diagram method and system.
Background
With the popularization of wireless networks, more and more families use WiFi, but due to the problem of irregular installation, wireless signals in rooms cannot be reasonably used. In the prior art, only simple thermodynamic diagram rendering can be performed, and a coverage area close to a real wireless signal cannot be obtained.
Chinese patent No. CN202010955730.2 discloses a thermodynamic diagram generating method and electronic equipment, the method comprising: identifying network equipment corresponding to a region to be processed, and acquiring equipment information corresponding to the network equipment, wherein the equipment information comprises network signal strength corresponding to a mobile terminal, and the mobile terminal is a terminal associated with the network equipment; determining terminal distribution information corresponding to the network equipment according to the network signal intensity corresponding to the mobile terminal; and generating the thermodynamic diagram of the area to be processed according to the terminal distribution information corresponding to the network equipment, so as to realize automatic generation of the thermodynamic diagram and improve the thermodynamic diagram generation efficiency. But does not take into account the space in which the device is located and the signal attenuation brought about in various situations, the accuracy is not sufficient.
Chinese patent No. 202110208502.3 discloses a gateway of 5G industrial Internet of things and a control method thereof, and relates to the technical field of industrial dispatching. In the invention, a scheduling control end firstly acquires map information of a scheduling area and acquires scheduling information of a current round task; further acquiring an optimal WiFi signal strength thermodynamic diagram of the gateway of the Internet of things; generating an antenna direction adjusting instruction of the gateway of the Internet of things; after the gateway of the Internet of things executes the antenna direction adjustment instruction, the scheduling control terminal obtains an optimal path of the mobile equipment by using an optimal WiFi signal strength thermodynamic diagram; and finally, sending the optimal path to the mobile equipment through the gateway of the Internet of things. Before scheduling, the gateway of the Internet of things is adjusted for the round of scheduling tasks to obtain the optimal coverage range, and the mobile equipment and the fixed equipment can be ensured to continuously and stably communicate with the scheduling control end. But the acquired map information may be different from the actual map information, so that the actual coverage area of the location cannot be presented.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a wireless network signal detection thermodynamic diagram method and a wireless network signal detection thermodynamic diagram system.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a method for detecting thermodynamic diagrams of wireless network signals, comprising the steps of:
step one, converting basic data and real data;
step two, calculating a thermodynamic value;
step three, thermodynamic diagram rendering;
and step four, converting the rendered thermodynamic diagram into a vector diagram.
The vector diagram can facilitate compatibility with different devices.
Further describing the invention, the real data is the real area and the coverage area of the real router; and the basic data is a house type graph and virtual router frequency.
The invention further describes that the actual area is identified and calculated by the convolutional neural network to identify the area, the length, the width and the indoor wall on the house type graph, and the specific flow comprises the following steps:
11 Collecting one portion of the untreated sample, and copying one portion;
12 Filling each untreated sample into square according to the requirement, converting into 800X 800 pixel size, filling the insufficient part with white, and forming a sample set by all converted samples;
13 Characterizing actual black and gray shapes, identifying sample set features using a labeling tool;
14 Randomly dividing the sample set into a test set and a training set in a ratio of 2:8 and inputting the test set and the training set into a deep learning recognition model network.
The step 11) is to copy one copy to compare with the final picture trained by the model, and observe whether deformation exists in the process of calculation and conversion.
The input end of the deep learning recognition model network adopts mosoic data enhancement to enrich a detection data set, so that the accuracy is maintained while the weight is reduced; the deep learning recognition model network adopts an R-CNN structure, and different trunk layers carry out parameter aggregation on different detection layers; the output end of the deep learning recognition model network adopts CIOU Loss operation, so that regression Loss is more accurate and faster when overlapping and even containing relation exists between the regression Loss and the target frame.
Further describing the invention, the frequency of the virtual router and the coverage area of the actual router are subjected to equal proportion conversion to obtain the router frequency.
Further describing the invention, the thermodynamic value calculation mainly comprises the steps of calculating WiFi coverage gradient values, shelter attenuation values and thermodynamic value color ranges of different power routers.
According to the thermodynamic diagram rendering method, the thermodynamic diagram rendering is mainly performed according to the house type diagram after convolutional network nerve recognition conversion, the thermodynamic diagram model takes WiFi points as the original points, four quadrants are cut to conduct thermodynamic value rendering, and attenuation strength of thermodynamic values is comprehensively judged according to the fact that the rendering distance is enlarged and whether a shielding object exists between the current pixel points and the original points in the rendering process.
A wireless network signal detection thermodynamic diagram system, comprising: the device comprises a data conversion module, a thermodynamic value calculation rule module and a rendering module; the data conversion module is used for converting basic data and real data; the thermodynamic value calculation rule module is used for preparing WiFi coverage gradient values of different power routers, shelter attenuation calculation rules and thermodynamic value color ranges; the rendering module is used for calculating the thermal value and matching the thermal value to render the color.
According to the invention, the data conversion module identifies the area, the length and the width of the house type diagram and the internal wall of the house type diagram through the convolutional neural network, the actual area is obtained through identification and calculation, and the router frequency is obtained through equal proportion conversion between the frequency of the virtual router and the coverage area of the actual router.
According to the invention, the rendering module and the thermodynamic value calculation rule module provide a service interface to the outside, a user submits the house type graph, the WiFi brand, the power and the WiFi coordinate system to the service interface, and then submits the house type graph, the WiFi brand, the power and the WiFi coordinate system to the rendering model for calculation and rendering, and finally obtains a rendering result and returns the rendering result to the user.
According to the invention, the rendering model is trained by collecting the house type photo and performing deep learning rendering thermodynamic diagram model, and the rendering model is iterated continuously, so that the rendering model closest to the actual situation is finally obtained.
The invention has the following beneficial effects:
according to the invention, the intelligent training model is used for converting the house type graph and the actual area, converting the coverage range of the actual router and the frequency of the virtual router, and rendering the thermodynamic value on the converted house type graph, so that a rendering thermodynamic diagram closest to the actual situation is finally obtained, the calculation speed is high, the result accuracy is high, and the coverage range of the wireless signal can be truly embodied.
Drawings
Fig. 1 is a flowchart of a method for detecting a thermodynamic diagram of a wireless network signal.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Example 1:
a method for detecting thermodynamic diagrams of wireless network signals, comprising the steps of:
step one, converting basic data and real data;
step two, calculating a thermodynamic value;
step three, thermodynamic diagram rendering;
and step four, converting the rendered thermodynamic diagram into a vector diagram.
Example 2:
a method for detecting thermodynamic diagrams of wireless network signals, comprising the steps of:
step one, converting basic data and real data;
the real data is the actual area and the coverage area of an actual router; and the basic data is a house type graph and virtual router frequency.
The actual area is identified and calculated by the convolutional neural network to identify the area, length, width and internal wall of the house, and the specific flow comprises:
11 Collecting one portion of the untreated sample, and copying one portion;
12 Filling each untreated sample into square according to the requirement, converting into 800X 800 pixel size, filling the insufficient part with white, and forming a sample set by all converted samples;
13 Characterizing actual black and gray shapes, identifying sample set features using a labeling tool;
14 Randomly dividing the sample set into a test set and a training set according to the proportion of 2:8, and inputting the test set and the training set into a deep learning recognition model network;
the step 11) is to copy one copy to compare with the final picture trained by the model, and observe whether deformation exists in the process of calculation and conversion.
The input end of the deep learning recognition model network adopts mosoic data enhancement to enrich a detection data set, so that the accuracy is maintained while the weight is reduced; the deep learning recognition model network adopts an R-CNN structure, and different trunk layers carry out parameter aggregation on different detection layers; the output end of the deep learning recognition model network adopts CIOU Loss operation, so that regression Loss is more accurate and faster when overlapping and even containing relation exists between the regression Loss and the target frame.
And the frequency of the virtual router and the coverage range of the actual router are subjected to equal proportion conversion to obtain the router frequency.
Step two, calculating a thermodynamic value;
the thermodynamic value calculation is mainly to calculate WiFi coverage gradient values, shelter attenuation values and thermodynamic value color ranges of different power routers.
Step three, thermodynamic diagram rendering;
the thermodynamic diagram rendering is mainly based on the house type diagram after convolutional network nerve recognition conversion, and the thermodynamic diagram model uses WiFi points as origins, and cuts four quadrants to render thermodynamic values; and comprehensively judging the attenuation strength of the thermal value along with the expansion of the rendering distance and whether a shielding object exists between the current pixel point and the original point in the rendering process.
And step four, converting the rendered thermodynamic diagram into a vector diagram.
Example 3:
a wireless network signal detection thermodynamic diagram system, comprising: the device comprises a data conversion module, a thermodynamic value calculation rule module and a rendering module; the data conversion module is used for converting basic data and real data; the thermodynamic value calculation rule module is used for preparing WiFi coverage gradient values of different power routers, shelter attenuation calculation rules and thermodynamic value color ranges; the rendering module is used for calculating the thermal value and matching the thermal value to render the color.
Example 4:
a wireless network signal detection thermodynamic diagram system, comprising: the device comprises a data conversion module, a thermodynamic value calculation rule module and a rendering module; the data conversion module is used for converting basic data and real data; the data conversion module identifies the area, the length and the width of the house type graph and the internal wall of the house type through the convolutional neural network, identifies and calculates the actual area, and converts the frequency of the virtual router and the coverage area of the actual router in equal proportion to obtain the frequency of the router.
The thermodynamic value calculation rule module is used for preparing WiFi coverage gradient values of different power routers, shelter attenuation calculation rules and thermodynamic value color ranges.
The rendering module is used for calculating the thermal value and matching the thermal value to render the color.
The rendering module and the thermodynamic value calculation rule module provide a service interface to the outside, a user submits the house type graph, the WiFi brand, the power and the WiFi coordinate system to the service interface, and then submits the house type graph, the WiFi brand, the power and the WiFi coordinate system to the rendering model for calculation and rendering, and finally obtains a rendering result and returns the rendering result to the user.
The rendering model is trained by collecting the house type photo deep learning rendering thermodynamic diagram model, and the rendering model is iterated continuously, so that the rendering model closest to the actual situation is finally obtained.
The above embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, the scope of which is defined by the claims. Various modifications and equivalent arrangements of parts may be made to the present invention within the spirit and scope of the invention, and such modifications and equivalents should be considered to fall within the scope of the invention.
Claims (2)
1. A method for detecting thermodynamic diagrams of wireless network signals, comprising the steps of:
step one, converting basic data and real data;
the real data is the actual area and the coverage area of an actual router; the basic data is a house type graph and virtual router frequency;
the actual area is identified and calculated by the convolutional neural network to identify the area, length, width and internal wall of the house, and the specific flow comprises:
11 Collecting one portion of the untreated sample, and copying one portion;
12 Filling each untreated sample into square according to the requirement, converting into 800X 800 pixel size, filling the insufficient part with white, and forming a sample set by all converted samples;
13 Characterizing actual black and gray shapes, identifying sample set features using a labeling tool;
14 Randomly dividing the sample set into a test set and a training set according to the proportion of 2:8, and inputting the test set and the training set into a deep learning recognition model network;
the frequency of the virtual router and the coverage area of the actual router are subjected to equal proportion conversion to obtain the router frequency;
step two, calculating a thermodynamic value;
the thermodynamic value calculation is mainly to calculate WiFi coverage gradient values, shelter attenuation values and thermodynamic value color ranges of different power routers;
step three, thermodynamic diagram rendering;
the thermodynamic diagram rendering is mainly based on a house type diagram after convolutional network nerve recognition conversion, the thermodynamic diagram model takes WiFi points as an origin, four quadrants are cut to conduct thermodynamic value rendering, and attenuation strength of thermodynamic values is comprehensively judged according to the fact that rendering distances are enlarged and whether shielding objects exist between current pixel points and the origin in the rendering process;
and step four, converting the rendered thermodynamic diagram into a vector diagram.
2. A wireless network signal detection thermodynamic diagram system, comprising: the device comprises a data conversion module, a thermodynamic value calculation rule module and a rendering module;
the data conversion module is used for converting basic data and real data; the real data is the actual area and the coverage area of an actual router; the basic data is a house type graph and virtual router frequency;
the actual area is identified and calculated by the convolutional neural network to identify the area, length, width and internal wall of the house, and the specific flow comprises:
11 Collecting one portion of the untreated sample, and copying one portion;
12 Filling each untreated sample into square according to the requirement, converting into 800X 800 pixel size, filling the insufficient part with white, and forming a sample set by all converted samples;
13 Characterizing actual black and gray shapes, identifying sample set features using a labeling tool;
14 Randomly dividing the sample set into a test set and a training set according to the proportion of 2:8, and inputting the test set and the training set into a deep learning recognition model network;
the frequency of the virtual router and the coverage area of the actual router are subjected to equal proportion conversion to obtain the router frequency;
the thermodynamic value calculation rule module is used for preparing WiFi coverage gradient values of different power routers, shelter attenuation calculation rules and thermodynamic value color ranges; the method comprises the following steps: the rendering module and the thermodynamic value calculation rule module provide a service interface to the outside, a user submits a house type graph, a WiFi brand, a power and a WiFi coordinate system to the service interface, and then submits the house type graph, the WiFi brand, the power and the WiFi coordinate system to a rendering model for calculation and rendering, and finally obtains a rendering result and returns the rendering result to the user;
the rendering module is used for performing calculation of the thermal value and matching rendering color of the thermal value; the calculation of the thermodynamic value mainly comprises the steps of calculating WiFi coverage gradient values, shelter attenuation values and thermodynamic value color ranges of different power routers; the matched rendering color of the thermodynamic value is mainly that the thermodynamic diagram model takes WiFi points as the original points according to the house type diagram after convolutional network nerve recognition conversion, four quadrants are cut to conduct the thermodynamic value rendering, and the attenuation degree of the thermodynamic value is comprehensively judged according to the fact that the rendering distance is enlarged and whether a shielding object exists between the current pixel point and the original points in the rendering process.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111621407.2A CN114401520B (en) | 2021-12-28 | 2021-12-28 | Method and system for detecting thermodynamic diagram of wireless network signal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111621407.2A CN114401520B (en) | 2021-12-28 | 2021-12-28 | Method and system for detecting thermodynamic diagram of wireless network signal |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114401520A CN114401520A (en) | 2022-04-26 |
CN114401520B true CN114401520B (en) | 2024-02-09 |
Family
ID=81229217
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111621407.2A Active CN114401520B (en) | 2021-12-28 | 2021-12-28 | Method and system for detecting thermodynamic diagram of wireless network signal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114401520B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109712151A (en) * | 2018-12-31 | 2019-05-03 | 航天精一(广东)信息科技有限公司 | A kind of method of reverse color applying drawing thermodynamic chart |
CN110059750A (en) * | 2019-04-17 | 2019-07-26 | 广东三维家信息科技有限公司 | House type shape recognition process, device and equipment |
CN112183637A (en) * | 2020-09-29 | 2021-01-05 | 中科方寸知微(南京)科技有限公司 | Single-light-source scene illumination re-rendering method and system based on neural network |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20210143923A1 (en) * | 2019-11-12 | 2021-05-13 | Plano Molding Company, Llc | System and method for monitoring and mapping signal strength |
-
2021
- 2021-12-28 CN CN202111621407.2A patent/CN114401520B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109712151A (en) * | 2018-12-31 | 2019-05-03 | 航天精一(广东)信息科技有限公司 | A kind of method of reverse color applying drawing thermodynamic chart |
CN110059750A (en) * | 2019-04-17 | 2019-07-26 | 广东三维家信息科技有限公司 | House type shape recognition process, device and equipment |
CN112183637A (en) * | 2020-09-29 | 2021-01-05 | 中科方寸知微(南京)科技有限公司 | Single-light-source scene illumination re-rendering method and system based on neural network |
Non-Patent Citations (2)
Title |
---|
室内无线网络覆盖信号的三维动态仿真方法;肖胜笔 等;广东通信技术(第2018年09期期);第64-66页 * |
肖胜笔 等.室内无线网络覆盖信号的三维动态仿真方法.广东通信技术.(第2018年09期期),第64-66页. * |
Also Published As
Publication number | Publication date |
---|---|
CN114401520A (en) | 2022-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107742093B (en) | Real-time detection method, server and system for infrared image power equipment components | |
CN107590456B (en) | Method for detecting small and micro targets in high-altitude video monitoring | |
CN110033453A (en) | Based on the power transmission and transformation line insulator Aerial Images fault detection method for improving YOLOv3 | |
CN114973002A (en) | Improved YOLOv 5-based ear detection method | |
CN111401246A (en) | Smoke concentration detection method, device, equipment and storage medium | |
CN111179262A (en) | Electric power inspection image hardware fitting detection method combined with shape attribute | |
CN110298330B (en) | Monocular detection and positioning method for power transmission line inspection robot | |
CN113284144B (en) | Tunnel detection method and device based on unmanned aerial vehicle | |
CN113255590A (en) | Defect detection model training method, defect detection method, device and system | |
CN111402250A (en) | Machine vision defect detection method and platform based on edge calculation | |
Tian et al. | Corrosion identification of fittings based on computer vision | |
CN114401520B (en) | Method and system for detecting thermodynamic diagram of wireless network signal | |
CN111597868A (en) | SSD-based substation disconnecting switch state analysis method | |
CN112926415A (en) | Pedestrian avoiding system and pedestrian monitoring method | |
CN110334818B (en) | Method and system for automatically identifying pipeline | |
KR102144474B1 (en) | Method for detecting injurious insect in image | |
CN116630749A (en) | Industrial equipment fault detection method, device, equipment and storage medium | |
CN112699776B (en) | Training sample optimization method, target detection model generation method, device and medium | |
CN112508946B (en) | Cable tunnel anomaly detection method based on antagonistic neural network | |
CN111429411B (en) | X-ray defect image sample generation method for carbon fiber composite core wire | |
CN113505844A (en) | Label generation method, device, equipment, storage medium and program product | |
CN113947563A (en) | Cable process quality dynamic defect detection method based on deep learning | |
CN113989684A (en) | Method and system for marking and grading machine inspection defect picture images | |
CN114299354A (en) | Insulator detection positioning method based on rotating frame identification network | |
CN112927170A (en) | Automatic defect removal method in semiconductor manufacturing process |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |