CN113065608A - Intelligent troubleshooting system and method based on multiple image recognition - Google Patents
Intelligent troubleshooting system and method based on multiple image recognition Download PDFInfo
- Publication number
- CN113065608A CN113065608A CN202110434857.4A CN202110434857A CN113065608A CN 113065608 A CN113065608 A CN 113065608A CN 202110434857 A CN202110434857 A CN 202110434857A CN 113065608 A CN113065608 A CN 113065608A
- Authority
- CN
- China
- Prior art keywords
- unit
- module
- image
- visible light
- equipment
- 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
- 238000013024 troubleshooting Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000001931 thermography Methods 0.000 claims abstract description 27
- 238000004891 communication Methods 0.000 claims abstract description 25
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000012423 maintenance Methods 0.000 claims abstract description 11
- 239000013589 supplement Substances 0.000 claims abstract description 11
- 230000001502 supplementing effect Effects 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 239000003832 thermite Substances 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims 1
- 230000003111 delayed effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- 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
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent troubleshooting system and method based on multiple image recognition, and the intelligent troubleshooting system comprises a visible light camera, an infrared light supplement lamp, a thermal imaging camera, an internal network, an image receiving module, a preprocessing module, a server, a target recognition neural network module, a learning module, a matching module and an output module, wherein the visible light camera is used for shooting equipment appearance pictures, and the infrared light supplement lamp is used for supplementing light to the visible light camera; compared with the traditional mode that a display screen needs to be watched manually in time to obtain a feedback result, the anti-leakage and anti-lost mode is better, and on the other hand, alarm and communication feedback can enable nearby maintenance personnel to arrive at a maintenance place in time to maintain the equipment in time, so that the phenomenon of excessive loss caused by equipment damage due to delayed maintenance is avoided, and when the appearance of the equipment is increased or replaced, a model can be conveniently and timely increased or modified, so that the use convenience is improved.
Description
Technical Field
The invention relates to the field of data transmission, in particular to an intelligent troubleshooting system based on multiple image recognition, and more particularly to an intelligent troubleshooting system based on multiple image recognition and a method thereof.
Background
The transformer substation is a place for adjusting an electric power system, long-time uninterrupted work is needed, in order to guarantee normal work, an inspection robot is generally required to be arranged to be matched with manual inspection to inspect various devices of the transformer substation, wherein the inspection robot is required to be provided with a troubleshooting system, the troubleshooting system is generally matched with a visible light camera and a thermal imaging camera, the visible light camera is mainly used for troubleshooting faults of appearance, state, gate state, meter reading, liquid leakage and the like of the devices, and the thermal imaging camera is used for troubleshooting whether the devices have high temperature phenomena.
The existing intelligent troubleshooting system based on multiple image recognition has certain disadvantages to be improved, firstly, the existing intelligent troubleshooting system based on multiple image recognition has a single result output mode, only can output pictures through modes such as an LCD (liquid crystal display) and a display screen, the results and the pictures need to be checked manually, when the phenomenon of manual negligence occurs, important information is easy to miss, and the system is poor in practicability and safety; secondly, the existing intelligent troubleshooting system based on multiple image recognition is poor in learning effect, when the appearance of the equipment is increased or replaced, the model is difficult to rebuild, the troubleshooting effect in the later stage is affected, and the practicability is poor.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the existing intelligent troubleshooting system based on multiple image recognition has a single result output mode, only can output pictures in modes of an LCD (liquid crystal display), a display screen and the like, results and images need to be checked manually, when the phenomenon of negligence occurs manually, important information is easy to miss, and the system is poor in practicability and safety; secondly, the existing intelligent troubleshooting system based on multiple image recognition is poor in learning effect, when the appearance of the equipment is increased or replaced, the model is difficult to rebuild, the troubleshooting effect in the later stage is affected, and the practicability is poor.
The invention solves the technical problems through the following technical scheme, and discloses an intelligent troubleshooting system and method based on multiple image recognition, wherein the intelligent troubleshooting system comprises a visible light camera, an infrared light supplement lamp, a thermal imaging camera, an intranet, an image receiving module, a preprocessing module, a server, a target recognition neural network module, a learning module, a matching module and an output module;
the visible light camera is used for shooting an appearance picture of the equipment;
the infrared light supplement lamp is used for supplementing light to the visible light camera;
the thermal imaging camera is used for shooting a thermal image picture of the equipment;
the intranet is used for data wireless transmission;
the image receiving module is used for receiving shot pictures of the visible light camera and the thermal imaging camera;
the preprocessing module is used for preprocessing the received picture;
the server is used for processing, calculating and executing all commands of the whole intelligent troubleshooting system based on multiple image recognition;
the target recognition neural network module is used for storing a normal state model of the equipment;
the learning module is used for learning a neural network module;
the matching module is used for comparing the acquired image with the neural network module;
the output module is used for outputting the matching result.
Preferably, the output module comprises a feedback unit A, LCD, an alarm unit, a communication unit, an alarm and a communication terminal storage unit.
Preferably, the specific processing steps of the output module are as follows:
the method comprises the following steps: the matching result is fed back to the LCD by the feedback unit A to be displayed, and a maintenance operator can observe the matching result through the LCD;
step two: meanwhile, the feedback unit A feeds the result back to the alarm unit, the alarm unit judges the data result fed back by the feedback unit A, and when the result is in an abnormal state of the equipment, the alarm is pushed to work to give an alarm, so that the situation that field personnel go to maintain in front is indicated;
step three: meanwhile, the communication unit acquires the communication terminal information from the communication terminal storage unit and sends the alarm information to the communication terminal.
Preferably, the feedback unit a further includes a judging unit, and the judging unit is configured to judge the fed back device status result, and timely push the alarm unit to work in the abnormal state.
Preferably, the learning module comprises an image input unit, a convolution and sampling unit, a transformation and calculation unit, an output unit, a reading and writing unit and a feedback unit B.
Preferably, the learning module specifically processes the following steps:
s1: the image input unit acquires a visible light image and a thermal imaging image initialized by the equipment, and inputs a value convolution and sampling unit;
s2: the convolution and sampling module performs convolution-first and sampling-later work on the visible light image and the thermal imaging image to complete basic training;
s3: the visible light image and the thermite image after convolution and sampling are transformed, calculated and pruned by a transforming and calculating unit to obtain a deep target recognition neural network model;
s4: the target recognition neural network model is output to the read-write unit through the output unit, people check the model through the read-write unit and judge whether the model is correct or not, and if the model is incorrect, the model is fed back to the convolution and sampling unit, the transformation calculation unit or the output unit through the feedback unit B to be relearned;
s5: and when the judgment is correct, directly outputting and storing.
The intelligent troubleshooting method based on multiple image recognition specifically comprises the following steps:
a1: the method comprises the following steps that a visible light camera and a thermal imaging camera are mounted on the inspection robot, the visible light camera shoots an equipment appearance picture, the thermal imaging camera shoots an equipment thermal image picture, and an infrared light supplementing lamp supplements light for the visible light camera when the appearance picture is shot;
a2: the shot pictures are transmitted to a server through an intranet and received by an image receiving module, and the received images are preprocessed by a preprocessing module, wherein the preprocessing module is used for adjusting contrast, brightness and the like;
a3: the preprocessed image is flashed in a server, the matching module matches the preprocessed image with the target recognition neural network module, and finally, a matching result is output by the output module;
a4: when a person adds a device or changes the appearance of a device, the model can be re-established through the learning module.
Compared with the prior art, the invention has the following advantages:
through the arrangement of the output module, the matching result is fed back to the LCD by the feedback unit A to be displayed, a maintenance person can observe the matching result through the LCD, the feedback unit A feeds the result back to the alarm unit, the alarm unit judges the data result fed back by the feedback unit A, when the result is in an abnormal state of equipment, the alarm is pushed to work to give an alarm to indicate that field personnel go forward to maintenance, the communication unit acquires the information of the communication terminal from the communication terminal storage unit and sends the information of the alarm to the communication terminal, three feedback modes of field feedback, alarm feedback and communication feedback are realized, on one hand, compared with the traditional mode that the feedback result is acquired by manually watching a display screen in time, the leakage prevention and loss prevention are realized, on the other hand, the alarm and communication feedback can enable nearby maintenance persons to arrive at a maintenance place in time, the equipment is maintained in time, so that the phenomenon of excessive loss caused by equipment damage due to delayed maintenance is avoided;
by arranging the learning module, the image input unit acquires a visible light image and a thermal imaging image initialized by the equipment, and the input value convolution and sampling unit performs convolution-first sampling work and then sampling work on the visible light image and the thermal imaging image to complete basic training, the visible light image and the thermal imaging image after convolution and sampling are transformed, calculated and pruned by the transformation and calculation unit to obtain a deep target recognition neural network model, the target recognition neural network model is output to the read-write unit through the output unit, people check the model through the read-write unit to judge whether the model is correct or not, if so, the model is fed back to the convolution and sampling unit, the transformation and calculation unit or the output unit through the feedback unit B to be relearned, when the appearance of the equipment is increased or changed, the model can be conveniently and timely increased or modified, the convenience of use is improved.
Drawings
FIG. 1 is a system block diagram of the present invention;
FIG. 2 is a system diagram of an output module of the present invention;
FIG. 3 is a system diagram of the learning module of the present invention.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
As shown in fig. 1-3, the present embodiment provides a technical solution: the intelligent troubleshooting system based on multiple image recognition and the method thereof comprise a visible light camera, an infrared light supplement lamp, a thermal imaging camera, an intranet, an image receiving module, a preprocessing module, a server, a target recognition neural network module, a learning module, a matching module and an output module;
the visible light camera is used for shooting the appearance picture of the equipment;
the infrared light supplement lamp is used for supplementing light to the visible light camera;
the thermal imaging camera is used for shooting a thermal image picture of the equipment;
the intranet is used for data wireless transmission;
the image receiving module is used for receiving shot pictures of the visible light camera and the thermal imaging camera;
the preprocessing module is used for preprocessing the received picture;
the server is used for processing, calculating and executing all commands of the whole intelligent troubleshooting system based on the multiple image recognition;
the target recognition neural network module is used for storing the normal state model of the equipment;
the learning module is used for learning the neural network module;
the matching module is used for comparing the acquired image with the neural network module;
the output module is used for outputting the matching result.
The output module comprises a feedback unit A, LCD, an alarm unit, a communication unit, an alarm and a communication terminal storage unit.
The specific processing steps of the output module are as follows:
the method comprises the following steps: the matching result is fed back to the LCD by the feedback unit A to be displayed, and a maintenance operator can observe the matching result through the LCD;
step two: meanwhile, the feedback unit A feeds the result back to the alarm unit, the alarm unit judges the data result fed back by the feedback unit A, and when the result is in an abnormal state of the equipment, the alarm is pushed to work to give an alarm, so that the situation that field personnel go to maintain in front is indicated;
step three: meanwhile, the communication unit acquires the communication terminal information from the communication terminal storage unit and sends the alarm information to the communication terminal.
The feedback unit A also comprises a judging unit which is used for judging the equipment state result fed back and pushing the alarm unit to work in time in the abnormal state.
The learning module comprises an image input unit, a convolution unit, a sampling unit, a transformation unit, a calculation unit, an output unit, a reading and writing unit and a feedback unit B.
The learning module comprises the following specific processing steps:
s1: the image input unit acquires a visible light image and a thermal imaging image initialized by the equipment, and inputs a value convolution and sampling unit;
s2: the convolution and sampling module performs convolution-first and sampling-later work on the visible light image and the thermal imaging image to complete basic training;
s3: the visible light image and the thermite image after convolution and sampling are transformed, calculated and pruned by a transforming and calculating unit to obtain a deep target recognition neural network model;
s4: the target recognition neural network model is output to the read-write unit through the output unit, people check the model through the read-write unit and judge whether the model is correct or not, and if the model is incorrect, the model is fed back to the convolution and sampling unit, the transformation calculation unit or the output unit through the feedback unit B to be relearned;
s5: and when the judgment is correct, directly outputting and storing.
The intelligent troubleshooting method based on multiple image recognition is characterized by comprising the following steps:
a1: the method comprises the following steps that a visible light camera and a thermal imaging camera are mounted on the inspection robot, the visible light camera shoots an equipment appearance picture, the thermal imaging camera shoots an equipment thermal image picture, and an infrared light supplementing lamp supplements light for the visible light camera when the appearance picture is shot;
a2: the shot pictures are transmitted to a server through an intranet and received by an image receiving module, and the received images are preprocessed by a preprocessing module, wherein the preprocessing module is used for adjusting contrast, brightness and the like;
a3: the preprocessed image is flashed in a server, the matching module matches the preprocessed image with the target recognition neural network module, and finally, a matching result is output by the output module;
a4: when a person adds a device or changes the appearance of a device, the model can be re-established through the learning module.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (7)
1. The intelligent troubleshooting system based on multiple image recognition is characterized by comprising a visible light camera, an infrared light supplement lamp, a thermal imaging camera, an intranet, an image receiving module, a preprocessing module, a server, a target recognition neural network module, a learning module, a matching module and an output module;
the visible light camera is used for shooting an appearance picture of the equipment;
the infrared light supplement lamp is used for supplementing light to the visible light camera;
the thermal imaging camera is used for shooting a thermal image picture of the equipment;
the intranet is used for data wireless transmission;
the image receiving module is used for receiving shot pictures of the visible light camera and the thermal imaging camera;
the preprocessing module is used for preprocessing the received picture;
the server is used for processing, calculating and executing all commands of the whole intelligent troubleshooting system based on multiple image recognition;
the target recognition neural network module is used for storing a normal state model of the equipment;
the learning module is used for learning a neural network module;
the matching module is used for comparing the acquired image with the neural network module;
the output module is used for outputting the matching result.
2. The intelligent troubleshooting system based on multiple image recognition of claim 1 characterized in that: the output module comprises a feedback unit A, LCD, an alarm unit, a communication unit, an alarm and a communication terminal storage unit.
3. The intelligent troubleshooting system based on multiple image recognition of claim 2 characterized in that: the specific processing steps of the output module are as follows:
the method comprises the following steps: the matching result is fed back to the LCD by the feedback unit A to be displayed, and a maintenance operator can observe the matching result through the LCD;
step two: meanwhile, the feedback unit A feeds the result back to the alarm unit, the alarm unit judges the data result fed back by the feedback unit A, and when the result is in an abnormal state of the equipment, the alarm is pushed to work to give an alarm, so that the situation that field personnel go to maintain in front is indicated;
step three: meanwhile, the communication unit acquires the communication terminal information from the communication terminal storage unit and sends the alarm information to the communication terminal.
4. The intelligent troubleshooting system based on multiple image recognition of claim 5 characterized in that: the feedback unit A also comprises a judging unit which is used for judging the fed back equipment state result and pushing the alarm unit to work in time in the abnormal state.
5. The intelligent troubleshooting system based on multiple image recognition of claim 1 characterized in that: the learning module comprises an image input unit, a convolution unit, a sampling unit, a conversion unit, a calculation unit, an output unit, a reading and writing unit and a feedback unit B.
6. The intelligent troubleshooting system based on multiple image recognition of claim 4 characterized in that: the learning module comprises the following specific processing steps:
s1: the image input unit acquires a visible light image and a thermal imaging image initialized by the equipment, and inputs a value convolution and sampling unit;
s2: the convolution and sampling module performs convolution-first and sampling-later work on the visible light image and the thermal imaging image to complete basic training;
s3: the visible light image and the thermite image after convolution and sampling are transformed, calculated and pruned by a transforming and calculating unit to obtain a deep target recognition neural network model;
s4: the target recognition neural network model is output to the read-write unit through the output unit, people check the model through the read-write unit and judge whether the model is correct or not, and if the model is incorrect, the model is fed back to the convolution and sampling unit, the transformation calculation unit or the output unit through the feedback unit B to be relearned;
s5: and when the judgment is correct, directly outputting and storing.
7. The intelligent troubleshooting method based on multiple image recognition is characterized by comprising the following steps:
a1: the method comprises the following steps that a visible light camera and a thermal imaging camera are mounted on the inspection robot, the visible light camera shoots an equipment appearance picture, the thermal imaging camera shoots an equipment thermal image picture, and an infrared light supplementing lamp supplements light for the visible light camera when the appearance picture is shot;
a2: the shot pictures are transmitted to a server through an intranet and received by an image receiving module, and the received images are preprocessed by a preprocessing module, wherein the preprocessing module is used for adjusting contrast, brightness and the like;
a3: the preprocessed image is flashed in a server, the matching module matches the preprocessed image with the target recognition neural network module, and finally, a matching result is output by the output module;
a4: when a person adds a device or changes the appearance of a device, the model can be re-established through the learning module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110434857.4A CN113065608A (en) | 2021-04-22 | 2021-04-22 | Intelligent troubleshooting system and method based on multiple image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110434857.4A CN113065608A (en) | 2021-04-22 | 2021-04-22 | Intelligent troubleshooting system and method based on multiple image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113065608A true CN113065608A (en) | 2021-07-02 |
Family
ID=76567454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110434857.4A Pending CN113065608A (en) | 2021-04-22 | 2021-04-22 | Intelligent troubleshooting system and method based on multiple image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065608A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207155816U (en) * | 2017-09-02 | 2018-03-30 | 张娜 | A kind of robot inspection system based on intelligent power generation station |
| CN110009530A (en) * | 2019-04-16 | 2019-07-12 | 国网山西省电力公司电力科学研究院 | A kind of nerve network system and method suitable for portable power inspection |
| CN110174174A (en) * | 2019-05-28 | 2019-08-27 | 广东电网有限责任公司 | Detection terminal and its application method based on infrared heat and visual light imaging |
| CN111080634A (en) * | 2019-12-23 | 2020-04-28 | 北京新松融通机器人科技有限公司 | Transformer appearance defect identification method based on inspection robot and Cascade RCNN algorithm |
-
2021
- 2021-04-22 CN CN202110434857.4A patent/CN113065608A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN207155816U (en) * | 2017-09-02 | 2018-03-30 | 张娜 | A kind of robot inspection system based on intelligent power generation station |
| CN110009530A (en) * | 2019-04-16 | 2019-07-12 | 国网山西省电力公司电力科学研究院 | A kind of nerve network system and method suitable for portable power inspection |
| CN110174174A (en) * | 2019-05-28 | 2019-08-27 | 广东电网有限责任公司 | Detection terminal and its application method based on infrared heat and visual light imaging |
| CN111080634A (en) * | 2019-12-23 | 2020-04-28 | 北京新松融通机器人科技有限公司 | Transformer appearance defect identification method based on inspection robot and Cascade RCNN algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 鲁守银等: "机器人在变电站设备巡检中的应用", 《机器人技术与应用》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104616626B (en) | A kind of display device brightness regulating apparatus and method | |
| CN104698647B (en) | liquid crystal display device and its control method | |
| CN110222624B (en) | Dynamic human face detection device | |
| CN104320635B (en) | GIS position of the switch remote online monitoring system based on video | |
| CN116911823A (en) | AR (augmented reality) glasses-based substation inspection interaction method and system | |
| CN111863216A (en) | Vision screening and managing system and method | |
| CN105005281A (en) | Intelligent transformer substation inspection real-time data display system and method based on Google glasses | |
| CN107480797B (en) | LNG dispenser fault diagnosis and elimination system and operation method thereof | |
| CN113065608A (en) | Intelligent troubleshooting system and method based on multiple image recognition | |
| CN105070204A (en) | Miniature AMOLED optical display | |
| CN204909387U (en) | Examine shadow mirror based on mobile intelligent Terminal | |
| CN202161299U (en) | Visual function examination device | |
| CN115361531B (en) | Intelligent ring main unit monitoring system based on remote video monitoring | |
| CN111508761A (en) | System for monitoring high-voltage isolating switch contact | |
| CN116152945A (en) | Under-mine inspection system and method based on AR technology | |
| CN110177301A (en) | A kind of TV and its method actively limiting viewing distance protection eyesight | |
| CN102467659A (en) | High-definition image type face identification and monitoring system | |
| CN206057491U (en) | A kind of high pressure equipment is ultraviolet, infrared imaging on-line monitoring equipment | |
| CN102346227A (en) | Endoscope technology-based discharge-trace inspection system | |
| CN211744560U (en) | Intelligent image processing device | |
| CN114121251A (en) | Prompting method and medical instrument system | |
| CN108388103B (en) | System and method for testing projection delay of window screen of aircraft cockpit | |
| CN106821300A (en) | Color vision detection method and system | |
| CN208988837U (en) | A kind of eye eyesight check device | |
| CN114666572B (en) | Device and method for rapidly positioning intermittent fault of visible light video |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210702 |
|
| RJ01 | Rejection of invention patent application after publication |