CN114459708A - Gas leakage monitoring system based on intelligent gas sensing - Google Patents
Gas leakage monitoring system based on intelligent gas sensing Download PDFInfo
- Publication number
- CN114459708A CN114459708A CN202210124858.3A CN202210124858A CN114459708A CN 114459708 A CN114459708 A CN 114459708A CN 202210124858 A CN202210124858 A CN 202210124858A CN 114459708 A CN114459708 A CN 114459708A
- Authority
- CN
- China
- Prior art keywords
- module
- response matrix
- image
- monitoring system
- leakage
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 42
- 230000004044 response Effects 0.000 claims abstract description 67
- 239000011159 matrix material Substances 0.000 claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000010276 construction Methods 0.000 claims abstract description 15
- 239000007789 gas Substances 0.000 claims description 73
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 4
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 13
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 150000001335 aliphatic alkanes Chemical class 0.000 description 1
- 238000007084 catalytic combustion reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/38—Investigating fluid-tightness of structures by using light
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Emergency Alarm Devices (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The invention relates to gas monitoring, in particular to a gas leakage monitoring system based on intelligent gas sensing, which comprises a server, wherein the server acquires real-time dynamic signals of a sensor array through a response signal acquisition module, constructs the acquired response signals into a response matrix by using a response matrix construction module, standardizes the response matrix by using the response matrix processing module, constructs a standard map based on the response matrix after standardized processing through a standard map construction module, and is connected with an identification model generation module which performs model training to generate an identification model and identifies the standard map by using the identification model; the technical scheme provided by the invention can effectively overcome the defects of inaccurate gas leakage monitoring result and poor reliability in the prior art.
Description
Technical Field
The invention relates to gas monitoring, in particular to a gas leakage monitoring system based on intelligent gas sensing.
Background
In the fields of daily life, industrial production and the like, harmful gases, such as flammable and explosive gases of alkanes such as natural gas, petroleum and the like, can cause various hazards due to leakage. In order to reduce the harm of gas leakage, whether there is gas leakage phenomenon in the region needs to be detected, and a common gas detection mode mainly includes: semiconductor, catalytic combustion, electrochemical, and infrared, i.e., a sensor that detects the concentration of a gas in an area by a corresponding detection principle. However, these sensors require contact with gas for detection, so that the detection range of these sensors is small and the response is slow.
With the development of detection technology, there exists a portable remote gas leakage detection device in the prior art, which monitors whether there is gas leakage by manually controlling a laser beam to scan a target area. However, when the portable remote gas leakage detection device is used for gas leakage monitoring, scanning by an operator is inevitably missed, and even a dedicated operator forgets to point to some areas due to manual operation. Therefore, the portable remote gas leakage detection device is adopted for gas leakage monitoring, and the reliability of the gas leakage monitoring is difficult to ensure. Meanwhile, the monitoring device is single, so that the monitoring point and the monitoring data are single, the concentration variation trend of gas leakage cannot be accurately achieved according to the monitoring data, and the field people stream evacuation and rescue work are not facilitated to be carried out.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects in the prior art, the invention provides a gas leakage monitoring system based on intelligent gas sensing, which can effectively overcome the defects of inaccurate gas leakage monitoring result and poor reliability in the prior art.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
a leakage gas monitoring system based on intelligent gas sensing comprises a server, wherein the server acquires real-time dynamic signals of a sensor array through a response signal acquisition module and constructs the acquired response signals into a response matrix through a response matrix construction module, the server standardizes the response matrix through a response matrix processing module, constructs a standard map based on the response matrix after standardized processing through a standard map construction module, and is connected with an identification model generation module which performs model training to generate an identification model and identifies the standard map through the identification model;
the server acquires images of an area to be monitored through the monitoring image acquisition module, preprocesses the acquired images through the image preprocessing module, acquires a leakage area from the preprocessed acquired images through the leakage area acquisition module, simultaneously performs feature extraction and feature selection on the leakage area through the area feature extraction module and the area feature analysis module respectively, outputs an identification result based on the selected features through the identification result output module, and comprehensively judges leakage gas through the identification result obtained by the monitoring result judgment module based on the identification model generation module and the identification result output module.
Preferably, the response matrix construction module constructs the real-time concentration dynamic signals of the sensor array into a response matrix of a × B, wherein the rows represent the number of sensors in the sensor array and the corresponding numbers, and the columns represent the response time of the corresponding sensors.
Preferably, the response matrix processing module normalizes each response matrix to a value range of 1 to 255, and normalizes the normalized response matrix.
Preferably, the standard map building module builds a color pillar standard map for the response matrix after the normalization processing according to a uniform color template and a drawing standard.
Preferably, the system further comprises an identification model training module, the response matrix building module builds a standard response matrix based on real-time dynamic signals of gases with different types and different concentrations, which are collected by the response signal collecting module, the standard map building module builds a training map library based on the standard response matrix after standardization processing and sends the training map library to the identification model training module, and the identification model training module inputs the training map library into the identification model generating module for model training.
Preferably, the recognition model generation module performs feature extraction on the map data in the training map library, performs learning training, and generates a recognition model for performing leakage gas recognition based on a standard map.
Preferably, the image preprocessing module performs non-uniformity correction on the acquired image by using a one-point correction algorithm, a two-point correction algorithm or a scene-based non-uniformity correction algorithm, removes fixed pattern noise, and performs filtering processing on the acquired image after the non-uniformity correction by using an improved bilateral filtering algorithm.
Preferably, the leakage area obtaining module obtains the leakage area from the pre-processed collected image by using a method combining background difference and inter-frame difference, and includes:
acquiring an initial background image based on the first N frames of acquired images, and acquiring an updated background image by adopting a background updating algorithm;
carrying out background difference on the current frame acquired image and the updated background image, and then carrying out morphological filtering to obtain a background difference image;
performing interframe difference on the previous N frames of collected images to obtain interframe difference images;
and performing AND operation on the background difference image and the inter-frame difference image, and acquiring a leakage area from the current frame acquisition image.
Preferably, the characteristics extracted by the regional characteristic extraction module for the leakage region include time domain characteristics and wavelet domain characteristics, and the regional characteristic analysis module performs characteristic selection on the characteristics extracted by the regional characteristic extraction module by using a principal component analysis method.
Preferably, the identification result output module comprises a non-linear prediction model of the support vector machine, and the non-linear prediction model takes the features selected by the region feature analysis module as input and outputs the identification result of the leaking gas based on the kernel function of the support vector machine.
(III) advantageous effects
Compared with the prior art, the leakage gas monitoring system based on intelligent gas sensing provided by the invention has the advantages that on one hand, the response signal acquisition module acquires real-time dynamic signals of the sensor array, the response matrix construction module constructs the acquired response signals into the response matrix, the standard map is constructed through the standard map construction module, and finally, the trained identification model is used for obtaining an identification result; on the other hand, the monitoring image acquisition module acquires images of a region to be monitored, the leakage region acquisition module acquires a leakage region from the preprocessed acquired images, the region feature extraction module and the region feature analysis module are respectively used for carrying out feature extraction and feature selection on the leakage region, finally, the identification result is output based on the selected features, distributed detection and non-contact detection are fully integrated, the application range of gas leakage monitoring is widened, and meanwhile, the accuracy and the reliability of the gas leakage monitoring result are effectively improved.
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 invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a schematic flow chart of gas leakage monitoring using a sensor array according to the present invention;
fig. 3 is a schematic flow chart of gas leakage monitoring by image acquisition of a region to be monitored in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. 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.
A gas leakage monitoring system based on intelligent gas sensing comprises a server, wherein the server acquires real-time dynamic signals of a sensor array through a response signal acquisition module and constructs the acquired response signals into a response matrix through a response matrix construction module, the server standardizes the response matrix through a response matrix processing module, a standard map is constructed through the standard map construction module based on the response matrix after standardized processing, and the server is connected with an identification model generation module which performs model training to generate an identification model and identifies the standard map through the identification model.
In this application technical scheme, still include recognition model training module, recognition model training module carries out the process of model training to recognition model among the recognition model generation module, includes:
the response matrix construction module constructs a standard response matrix based on real-time dynamic signals of different types and different concentrations of gas acquired by the response signal acquisition module, the standard map construction module constructs a training map library based on the standard response matrix after standardization processing and sends the training map library to the recognition model training module, and the recognition model training module inputs the training map library into the recognition model generation module for model training;
and the recognition model generation module is used for extracting the characteristics of the map data in the training map library, performing learning training and generating a recognition model for recognizing the leaked gas based on the standard map. The learning training can adopt a pattern recognition method which supports a vector machine or deep learning.
And the response matrix construction module constructs the real-time concentration dynamic signals of the sensor array into an A-B response matrix. Wherein, the row represents the number of sensors in the sensor array and the corresponding number, and the column represents the response time of the corresponding sensor. The gas sensors with different response characteristics are utilized to form a sensor detection module in a sensor array, and the sensor array responds to the concentration signal of the volatile gas to be detected.
The response matrix processing module normalizes each response matrix to a value range of 1-255, and meanwhile normalizes the normalized response matrix.
And the standard map building module builds a color column standard map according to the response matrix after the standardization treatment and the drawing standard, and the trained recognition model is used for recognizing the color column standard map, so that a recognition result for the leaked gas can be obtained, wherein the recognition result comprises the condition of whether the gas leakage occurs and the concentration of the leaked gas.
As shown in fig. 1 and 3, the server acquires an image of a region to be monitored through the monitoring image acquisition module, preprocesses the acquired image through the image preprocessing module, acquires a leakage region from the preprocessed acquired image through the leakage region acquisition module, simultaneously performs feature extraction and feature selection on the leakage region through the region feature extraction module and the region feature analysis module, respectively, outputs an identification result based on the selected feature through the identification result output module, and comprehensively determines the leakage gas through the identification result obtained by the monitoring result determination module based on the identification model generation module and the identification result output module.
The image preprocessing module carries out non-uniformity correction on the collected image, removes fixed pattern noise, and adopts an improved bilateral filtering algorithm to carry out filtering processing on the collected image after the non-uniformity correction. The image preprocessing module carries out non-uniformity correction on the acquired image by adopting a one-point correction algorithm, a two-point correction algorithm or a scene-based non-uniformity correction algorithm.
The leakage area obtaining module obtains a leakage area from the preprocessed acquired image by adopting a method combining background difference and interframe difference, and comprises the following steps:
acquiring an initial background image based on the first N frames of acquired images, and acquiring an updated background image by adopting a background updating algorithm;
carrying out background difference on the current frame acquired image and the updated background image, and then carrying out morphological filtering to obtain a background difference image;
performing interframe difference on the previous N frames of collected images to obtain interframe difference images;
and performing AND operation on the background difference image and the inter-frame difference image, and acquiring a leakage area from the current frame acquisition image. The background updating algorithm comprises a visual extraction algorithm and an edge extraction algorithm.
The characteristics extracted by the leakage area by the area characteristic extraction module comprise time domain characteristics and wavelet domain characteristics, and the characteristic extraction module is used for selecting the characteristics extracted by the area characteristic extraction module by adopting a principal component analysis method. The time domain features comprise gray scale features, texture features of gray scale co-occurrence matrixes, brightness histogram features and the like, and the wavelet domain features are wavelet high-frequency energy features.
The identification result output module comprises a nonlinear prediction model of the support vector machine, the nonlinear prediction model takes the characteristics selected by the region characteristic analysis module as input, and the identification result of the leaked gas is output based on the kernel function of the support vector machine, wherein the identification result comprises the condition of whether the gas leakage occurs or not.
In the technical scheme, distributed detection mainly based on the sensor array and non-contact detection mainly based on image acquisition are fully integrated, and the server comprehensively judges the leaked gas through the monitoring result judging module based on the identifying result obtained by the identifying model generating module and the identifying result output module, so that the application range of gas leakage monitoring is widened, and meanwhile, the accuracy and the reliability of the gas leakage monitoring result are effectively improved.
The above examples are only intended to illustrate the technical solution of the present invention, but 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; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. The utility model provides a leakage gas monitoring system based on gaseous intelligent perception which characterized in that: the server acquires real-time dynamic signals of a sensor array through a response signal acquisition module, constructs the acquired response signals into a response matrix through a response matrix construction module, standardizes the response matrix through a response matrix processing module, constructs a standard map based on the response matrix after the standardized processing through a standard map construction module, and is connected with a recognition model generation module which performs model training to generate a recognition model and recognizes the standard map through the recognition model;
the server acquires images of an area to be monitored through the monitoring image acquisition module, preprocesses the acquired images through the image preprocessing module, acquires a leakage area from the preprocessed acquired images through the leakage area acquisition module, simultaneously performs feature extraction and feature selection on the leakage area through the area feature extraction module and the area feature analysis module respectively, outputs an identification result based on the selected features through the identification result output module, and comprehensively judges leakage gas through the identification result obtained by the monitoring result judgment module based on the identification model generation module and the identification result output module.
2. The intelligent gas sensing-based leaking gas monitoring system according to claim 1, wherein: the response matrix construction module constructs the real-time concentration dynamic signals of the sensor array into an A x B response matrix, wherein rows represent the number and corresponding numbers of the sensors in the sensor array, and columns represent the response time of the corresponding sensors.
3. The intelligent gas sensing-based leaking gas monitoring system according to claim 1, wherein: the response matrix processing module normalizes each response matrix to a value range of 1-255, and meanwhile normalizes the normalized response matrix.
4. The intelligent gas sensing-based leaking gas monitoring system according to claim 1, wherein: and the standard map building module builds the color pillar standard map for the response matrix after the standardization processing according to a uniform color template and a drawing standard.
5. The intelligent gas sensing-based leaking gas monitoring system according to claim 1, wherein: the system further comprises a recognition model training module, the response matrix building module builds a standard response matrix based on real-time dynamic signals of different types and different concentrations of gases collected by the response signal collecting module, the standard map building module builds a training map library based on the standard response matrix after standardization processing and sends the training map library to the recognition model training module, and the recognition model training module inputs the training map library into the recognition model generating module for model training.
6. The intelligent gas sensing-based leaking gas monitoring system according to claim 5, wherein: and the recognition model generation module is used for extracting features of map data in the training map library, performing learning training and generating a recognition model for recognizing the leaked gas based on the standard map.
7. The intelligent gas sensing-based leaking gas monitoring system according to claim 1, wherein: the image preprocessing module carries out non-uniformity correction on the acquired image by adopting a one-point correction algorithm, a two-point correction algorithm or a scene-based non-uniformity correction algorithm, removes fixed pattern noise, and carries out filtering processing on the acquired image after the non-uniformity correction by adopting an improved bilateral filtering algorithm.
8. The intelligent gas sensing-based leaking gas monitoring system according to claim 1, wherein: the leakage area obtaining module obtains a leakage area from the preprocessed acquired image by adopting a method combining background difference and interframe difference, and comprises the following steps:
acquiring an initial background image based on the first N frames of acquired images, and acquiring an updated background image by adopting a background updating algorithm;
carrying out background difference on the current frame acquired image and the updated background image, and then carrying out morphological filtering to obtain a background difference image;
performing interframe difference on the previous N frames of collected images to obtain interframe difference images;
and performing AND operation on the background difference image and the inter-frame difference image, and acquiring a leakage area from the current frame acquisition image.
9. The intelligent gas sensing-based leaking gas monitoring system according to claim 1, wherein: the characteristics extracted by the regional characteristic extraction module for the leakage region comprise time domain characteristics and wavelet domain characteristics, and the regional characteristic analysis module selects the characteristics extracted by the regional characteristic extraction module by adopting a principal component analysis method.
10. The intelligent gas sensing-based leaking gas monitoring system according to claim 1, wherein: the identification result output module comprises a nonlinear prediction model of the support vector machine, the nonlinear prediction model takes the characteristics selected by the region characteristic analysis module as input, and the leakage gas identification result is output based on the kernel function of the support vector machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210124858.3A CN114459708A (en) | 2022-02-10 | 2022-02-10 | Gas leakage monitoring system based on intelligent gas sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210124858.3A CN114459708A (en) | 2022-02-10 | 2022-02-10 | Gas leakage monitoring system based on intelligent gas sensing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114459708A true CN114459708A (en) | 2022-05-10 |
Family
ID=81413070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210124858.3A Pending CN114459708A (en) | 2022-02-10 | 2022-02-10 | Gas leakage monitoring system based on intelligent gas sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114459708A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109716108A (en) * | 2016-12-30 | 2019-05-03 | 同济大学 | A kind of Asphalt Pavement Damage detection system based on binocular image analysis |
| CN109784390A (en) * | 2019-01-03 | 2019-05-21 | 西安交通大学 | A kind of artificial intelligence smell dynamic response map gas detection recognition methods |
| CN111141460A (en) * | 2019-12-25 | 2020-05-12 | 西安交通大学 | Equipment gas leakage monitoring system and method based on artificial intelligence sense organ |
| CN111325721A (en) * | 2020-02-13 | 2020-06-23 | 北京信息科技大学 | Gas leakage detection method and system based on infrared thermal imaging |
| US20200264572A1 (en) * | 2019-02-14 | 2020-08-20 | Carrier Corporation | Intelligent control system and method |
| US20200320659A1 (en) * | 2019-04-05 | 2020-10-08 | Baker Hughes Oilfield Operations Llc | Segmentation and prediction of low-level temporal plume patterns |
| CN112709935A (en) * | 2020-12-09 | 2021-04-27 | 解光有 | Equipment gas leakage monitoring system and method based on artificial intelligence sense organ |
| CN113375063A (en) * | 2021-06-07 | 2021-09-10 | 国家石油天然气管网集团有限公司西气东输分公司 | Intelligent monitoring method and system for natural gas pipeline leakage |
-
2022
- 2022-02-10 CN CN202210124858.3A patent/CN114459708A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109716108A (en) * | 2016-12-30 | 2019-05-03 | 同济大学 | A kind of Asphalt Pavement Damage detection system based on binocular image analysis |
| CN109784390A (en) * | 2019-01-03 | 2019-05-21 | 西安交通大学 | A kind of artificial intelligence smell dynamic response map gas detection recognition methods |
| US20200264572A1 (en) * | 2019-02-14 | 2020-08-20 | Carrier Corporation | Intelligent control system and method |
| US20200320659A1 (en) * | 2019-04-05 | 2020-10-08 | Baker Hughes Oilfield Operations Llc | Segmentation and prediction of low-level temporal plume patterns |
| CN111141460A (en) * | 2019-12-25 | 2020-05-12 | 西安交通大学 | Equipment gas leakage monitoring system and method based on artificial intelligence sense organ |
| CN111325721A (en) * | 2020-02-13 | 2020-06-23 | 北京信息科技大学 | Gas leakage detection method and system based on infrared thermal imaging |
| CN112709935A (en) * | 2020-12-09 | 2021-04-27 | 解光有 | Equipment gas leakage monitoring system and method based on artificial intelligence sense organ |
| CN113375063A (en) * | 2021-06-07 | 2021-09-10 | 国家石油天然气管网集团有限公司西气东输分公司 | Intelligent monitoring method and system for natural gas pipeline leakage |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111209876B (en) | Oil leakage defect detection method and system | |
| CN110148130B (en) | Method and device for detecting part defects | |
| US11830174B2 (en) | Defect inspecting device, defect inspecting method, and storage medium | |
| CN107782733B (en) | Image recognition nondestructive detection device and method for metal surface defects | |
| CN108596880A (en) | Weld defect feature extraction based on image procossing and welding quality analysis method | |
| CN109376773A (en) | Crack detecting method based on deep learning | |
| CN109410192B (en) | Fabric defect detection method and device based on multi-texture grading fusion | |
| CN104598888B (en) | A kind of recognition methods of face gender | |
| CN112308854B (en) | Automatic detection method and system for chip surface flaws and electronic equipment | |
| CN111739020B (en) | Automatic labeling method, device, equipment and medium for periodic texture background defect label | |
| CN115330802B (en) | Method for extracting debonding defect of X-ray image of carbon fiber composite gas cylinder | |
| CN112419261B (en) | Visual acquisition method and device with abnormal point removing function | |
| CN115661160B (en) | Panel defect detection method, system, device and medium | |
| CN108460344A (en) | Dynamic area intelligent identifying system in screen and intelligent identification Method | |
| CN112749656A (en) | Air switch state detection method and device based on ORB feature matching and yolo | |
| CN116977909B (en) | Deep learning fire intensity recognition method and system based on multi-modal data | |
| CN109086643A (en) | A kind of gift box label detection method and system based on machine vision | |
| CN114459708A (en) | Gas leakage monitoring system based on intelligent gas sensing | |
| CN113191977A (en) | Image enhancement system for target detection and identification under severe environment condition | |
| CN115792919B (en) | Method for identifying polluted hot spot area through horizontal scanning monitoring of aerosol laser radar | |
| CN116091503B (en) | Method, device, equipment and medium for discriminating panel foreign matter defects | |
| CN114022415B (en) | Liquid crystal display defect detection method based on single-pixel feature clustering cluster establishment | |
| CN113887634B (en) | Electric safety belt detection and early warning method based on improved two-step detection | |
| CN114742823A (en) | Intelligent detection method for scratches on surface of object | |
| CN112927222B (en) | Method for realizing multi-type photovoltaic array hot spot detection based on hybrid improved Faster R-CNN |
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 |