CN111047731A - AR technology-based telecommunication room inspection method and system - Google Patents
AR technology-based telecommunication room inspection method and system Download PDFInfo
- Publication number
- CN111047731A CN111047731A CN201911357764.5A CN201911357764A CN111047731A CN 111047731 A CN111047731 A CN 111047731A CN 201911357764 A CN201911357764 A CN 201911357764A CN 111047731 A CN111047731 A CN 111047731A
- Authority
- CN
- China
- Prior art keywords
- model
- real
- video
- information
- inspection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for inspecting a telecommunication room based on AR technology, belonging to the technical field of machine room inspection and comprising the following steps: s1: acquiring a real-time video; s2: identifying the video; s3: labeling abnormal items; s4: and uploading the record. In step S2, before real-time synchronous recognition of the real-time video information, a PB (network limited) model of the corresponding item needs to be established, and when recognizing wastepaper waste, recognizing sundries except machine room equipment, and recognizing whether water stains exist on the ceiling, the first PB model is used for recognition. Compared with the conventional inspection mode, the inspection method has the advantages that the labor cost and the material cost of inspection are reduced; the comprehensive maintenance personnel can be rectified, reformed and guided in real time, and the working efficiency is improved; the comprehensive maintenance personnel safety awareness can be improved, the inspection data is saved, the subsequent inspection and the workload statistics are facilitated, and the comprehensive maintenance personnel safety awareness is worthy of being popularized and used.
Description
Technical Field
The invention relates to the technical field of machine room inspection, in particular to a method and a system for inspecting a telecommunication machine room based on an AR technology.
Background
At present, telecommunication comprehensive maintenance personnel need to regularly inspect a machine room, various inspection items are shot and transmitted to an inspection system during inspection, quality inspection is carried out on the shot pictures by the inspection system or quality supervision personnel, and a work order is sent again for adjustment and modification when unqualified inspection work orders are found.
The existing inspection mode has certain defects, for example, an inspection work order needs to take more pictures, and a machine room inspection work order needs to take more than ten pictures of various types of machine room sanitation, machine room temperature and humidity meters, machine room hole plugging conditions, machine room illumination, air conditioning, electricity safety and the like; the repayment order is reformed, so that the cost of manpower, material resources and the like is increased; the unqualified inspection item is rectified and reformed without guide, and the rectification is easy to repeat; the picture shooting content is limited, the situation of the machine room cannot be completely reflected, and no complete polling data is reserved. Aiming at the defects, a method and a system for inspecting a telecommunication room based on an AR technology are provided.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: how to solve the problems of excessive photo shooting quantity, inconvenient rectification, incomplete polling and the like of the conventional machine room polling method, and provides a telecom machine room polling method based on AR technology.
The invention solves the technical problems through the following technical scheme, and the invention comprises the following steps:
s1: obtaining real-time video
The comprehensive maintenance personnel use the camera shooting equipment provided with the AR application to carry out machine room inspection, open the AR application and obtain a real-time video by using a camera of the camera shooting equipment;
s2: identifying video
The method comprises the steps that real-time synchronous identification is carried out on an image identification terminal through acquired real-time video information, and all information of a machine room in the real-time video is detected and identified, wherein the identification of all information comprises the identification of paper scrap garbage, the identification of sundries except machine room equipment, the identification of whether a ceiling is soaked with water or not and the identification of whether machine frame wiring is smooth or not;
s3: annotating outlier items
After the abnormal items are identified, the video is processed by using the openCV, the abnormal items are marked and displayed on the camera equipment, and therefore comprehensive maintenance personnel are guided to carry out rectification and modification;
s4: upload records
And uploading the video information in the inspection process to a cloud server in real time, and analyzing and counting the completion condition of the inspection work order.
Further, in step S2, before performing real-time synchronous identification on the real-time video information, a PB (network defined) model of the corresponding item needs to be established, and when identifying wastepaper waste, identifying sundries except machine room equipment, and identifying whether water stains exist on a ceiling, the first PB model is used for identification, and when identifying whether the routing lines of the rack are smoothly crossed or not, the second PB model is used for identification.
Further, the generating process of the first PB model includes the following steps:
s201: collecting a large number of sample pictures of paper scraps, sundries and water stains on a ceiling in a machine room;
s202: manually marking paper scraps, sundries and water stains in the picture;
s203: identifying the characteristics of paper scraps, sundries and water stains by using a YOLO algorithm;
the process of identifying features using the YOLO algorithm is as follows:
s2031: dividing the image containing paper scraps, impurities and water stains into S multiplied by S grids
S2032: acquiring each grid image in the S multiplied by S grids;
s2033: b Bounding boxes and confidence values (confidence scores) are predicted in each grid, the Bounding boxes reflect the positions of the grids, the confidence scores reflect the accuracy of the boxes, and if no target exists, the confidence values are zero;
wherein each bounding box contains 5 values: x, y, w, h and confidence, respectively; (x, y) coordinates represent the center of the bounding box relative to the grid cell bounding box; w (width) and h (height) are both predicted with respect to the entire image; confidence represents the Intersection (IOU) between the predicted box and the actual bounding box; each grid cell also predicts C conditional class probabilities, which are encoded as tensors of SxS (B × 5+ C);
s2034: obtaining a final result according to the confidence score and the predicted probability of each grid;
s204: a first PB model file is generated, which converts the model in the weights format generated by the YOLO algorithm into a model in the PB format that can be run on an android-type mobile phone system by using a darkflow tool.
Further, the process of using the first PB model for identification includes the steps of:
s211: acquiring each frame of image in a real-time video, inputting the image into a first PB model, and identifying characteristics of paper scraps, sundries and water stain images by using the first PB model; inputting an image into a first PB model, returning the probability that the image contains paper scraps, sundries and water stains by using the model, wherein if the probability is more than 80%, the image contains the paper scraps, the sundries and the water stains, and otherwise, the image does not contain the paper scraps, the sundries and the water stains;
s212: and when the abnormal item is detected and identified, the model returns the coordinate information of the abnormal item, and the coordinates of the image abnormal item are identified by a red frame by using openCV.
Further, the generation process of the second PB model includes the following steps:
s231: collecting a large number of wiring sample pictures in a machine room;
s232: sample image classification is carried out by adopting a transfer learning method and using a deep neural network inclusion-v 3 model;
s233: a second PB model file is generated, which is a model in the PB format.
Further, the process of using the second PB model for identification includes the steps of:
s241: the wiring rack is scanned from top to bottom by using the camera to acquire wiring information videos, and the top-down scanning mode is convenient for correcting the identification result according to context information and time sequence information;
s242: calling a second PB model to detect the routing information video to obtain a detection result;
s2421: and inputting each frame of image of the video into the PB model, and simultaneously recording the time of each frame of image in the video.
S2422: judging whether the type of the wiring column is in the standard or not by utilizing the model, if so, continuously judging whether the wiring is in the standard (smooth) or not, if not, re-shooting the wiring video, and if so, entering the next step;
s243: correcting the detection result by using the time sequence information and the context information of the routing information video;
the correction process comprises the following steps:
s2431: acquiring images of non-wiring columns, and if the image time is after the first wiring column appears and before the last wiring column appears, determining that the image is unqualified and needing to shoot wiring information video again;
s2432: judging whether the number of times of the first routing column and the last routing column appearing in the video is more than one time, and if the number of times of appearance is more than one time, indicating that the video is unqualified;
s2433: judging whether the appearance time interval of the first routing column and the appearance time interval of the last routing column exceed 30s, if so, determining that the first routing column is unqualified;
s244: if the detection result is abnormal, prompting the comprehensive maintenance personnel to carry out rectification in a mode of dispatching a system work order and a short message; and if no abnormity exists, the video is watermarked to obtain the computer room information, the geographical position information and the routing inspection information, and the video is uploaded to the cloud server to be stored.
Further, in step S243, it is required to determine whether the MODF trace frame is completely scanned from top to bottom when the detection result is corrected. The reason for this determination is to meet the business regulations and facilitate the subsequent correction of the recognition result according to the context information and the timing information, and the specific manner of the determination is to perform the determination according to the timing information and the context information.
The invention also provides a system for inspecting the telecommunication room based on the AR technology, which comprises the following components:
the video acquisition module is used for polling the machine room to acquire a real-time video;
the identification module is used for carrying out real-time synchronous identification on the image identification terminal through the acquired real-time video information and detecting and identifying various information of the machine room in the real-time video;
the marking module is used for marking the abnormal items after identifying the abnormal items and displaying the abnormal items on the camera shooting equipment;
the record uploading module is used for uploading the video information in the inspection process to the cloud server in real time and analyzing and counting the completion condition of the inspection work order;
the central processing module is used for sending instructions to other modules to complete related actions;
the video acquisition module, the identification module, the marking module and the record uploading module are all electrically connected with the central processing module.
Compared with the prior art, the invention has the following advantages: compared with the conventional routing inspection mode, the routing inspection method based on the AR technology not only reduces the cost of manpower and material resources for routing inspection; the comprehensive maintenance personnel can be rectified, reformed and guided in real time, and the working efficiency is improved; the comprehensive maintenance personnel safety awareness can be improved, the inspection data is saved, the subsequent inspection and the workload statistics are facilitated, and the comprehensive maintenance personnel safety awareness is worthy of being popularized and used.
Drawings
FIG. 1 is a schematic overall flow chart of a polling method in the embodiment of the invention;
FIG. 2 is a schematic diagram of a process for identifying paper scraps, impurities and water stains in the embodiment of the invention;
fig. 3 is a schematic diagram of a trace specification identification process according to an embodiment 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 to 3, the present embodiment provides a technical solution: a method for inspecting a telecommunication room based on an AR technology comprises the following steps:
s1: obtaining real-time video
The comprehensive maintenance personnel use the mobile phone with the AR application to carry out machine room inspection, open the AR application on the mobile phone, and obtain the real-time video by using the mobile phone camera.
S2: identifying video
The real-time video information is obtained, real-time synchronous identification is carried out on an image identification terminal (PC), all information of a machine room in the real-time video is detected and identified, and the identification of all information comprises the identification of wastepaper garbage, the identification of sundries except machine room equipment, the identification of whether a ceiling is soaked with water or not and the identification of whether a rack is wired smoothly or not.
S3: annotating outlier items
And after the abnormal items are identified, processing the video by using the openCV, marking the abnormal items out, and displaying the marked abnormal items on a mobile phone screen, thereby guiding comprehensive maintenance personnel to carry out rectification.
S4: upload records
And uploading the video information in the inspection process to a cloud server in real time, and analyzing and counting the completion condition of the inspection work order.
In step S2, before real-time synchronous identification of real-time video information, a PB (network defined) model corresponding to the item needs to be established, and when identifying paper scrap waste, identifying sundries except machine room equipment, and identifying whether water stains exist on a ceiling, the first PB model is used for identification, and when identifying whether routing lines of a rack are smoothly crossed or not, the second PB model is used for identification.
The generation process of the first PB model comprises the following steps:
s201: collecting a large number of sample pictures of paper scraps, sundries and water stains on a ceiling in a machine room;
s202: manually marking paper scraps, sundries and water stains in the picture;
s203: identifying the characteristics of paper scraps, sundries and water stains by using a YOLO algorithm;
the process of identifying features using the YOLO algorithm is as follows:
s2031: dividing the image containing paper scraps, impurities and water stains into S multiplied by S grids
S2032: acquiring each grid image in the S multiplied by S grids;
s2033: b Bounding boxes and confidence scores (confidence score) are predicted in each grid. The bounding box reflects its position, the confidence score reflects the accuracy of the box, and if there is no target, the confidence value is zero.
Wherein each bounding box contains 5 values: x, y, w, h and confidence, respectively; (x, y) coordinates represent the center of the bounding box relative to the grid cell bounding box; w (width) and h (height) are both predicted with respect to the entire image; confidence represents the Intersection (IOU) between the predicted box and the actual bounding box; each grid cell also predicts C conditional class probabilities, which are encoded as tensors of SxS (B × 5+ C);
s2034: obtaining a final result according to the confidence score and the predicted probability of each grid;
s204: a first PB model file is generated. The model converts the model in weights format, which is generated by a YOLO algorithm, into a model in PB format, which can be run on an android-type mobile phone system, by using a darkflow tool.
The process of identifying with the first PB model includes the steps of:
s211: acquiring each frame of image in a real-time video, inputting the image into a first PB model, and identifying characteristics of paper scraps, sundries and water stain images by using the first PB model;
the identification process by using the first PB model is to input an image into the PB model, the model returns the probability that the image contains objects such as paper scraps, sundries, water stains and the like, if the probability is more than 80%, the image contains the paper scraps, the sundries and the water stains, otherwise, the image does not contain the paper scraps, the sundries and the water stains;
s212: when the abnormal item is detected and identified, the model returns the coordinate information of the abnormal item, and the coordinates of the image abnormal item are identified by a red frame by using openCV.
The generation process of the second PB model comprises the following steps:
s231: collecting a large number of wiring sample pictures in a machine room;
s232: sample image classification is carried out by adopting a transfer learning method and using a deep neural network inclusion-v 3 model;
s233: a second PB model file is generated, which is a model in the PB format.
Before classifying the sample image by using the inclusion-v 3 model in step S232, firstly, downloading a standard model of an acceptance-v 3 model from an image database ImageNet, then performing relevant configuration on the standard model according to the requirements of the present embodiment on the model, and finally executing training and batch processing commands to generate the inclusion-v 3 model in step S232.
The configuration and training process of the inclusion-v 3 model in the step S232 specifically includes the following steps:
s2321: establishing a folder, establishing subfolders in the folder, wherein the subfolders are respectively a wiring compliance class, a wiring non-compliance class, a wiring column class and a non-wiring column class, and putting corresponding training pictures;
s2322: py file is configured, including the path of the trained picture, the path of the storage model, the label file, the training steps and the like;
s2323: training and batch command generation models are performed.
The process of identifying using the second PB model includes the steps of:
s241: scanning the wiring rack from top to bottom by using a camera to acquire wiring information video;
s242: calling a second PB model to detect the routing information video to obtain a detection result;
the specific detection process is as follows:
s2421: inputting each frame of image of the video into a PB model, and recording the time of each frame of image in the video;
s2422: the model firstly judges whether the video is on the same type of wiring column, if so, the model continuously judges whether the wiring is standard (smooth), if not, the video of the wiring needs to be shot again, and if so, the next step is carried out;
s243: correcting the detection result by using the time sequence information and the context information of the routing information video;
the contents of the correction are as follows:
1) acquiring an image of a non-wiring column, and if the image time is after the first wiring column appears and before the last wiring column appears, indicating that the image is not qualified and needing to shoot wiring information video again;
2) the first routing column and the last routing column can only appear once in the video, and if the first routing column and the last routing column appear for many times, the video is unqualified;
3) the time interval between the appearance of the first routing column and the appearance of the last routing column cannot exceed 30s, otherwise, the first routing column is unqualified;
s244: if the detection result is abnormal, prompting the comprehensive maintenance personnel to carry out rectification in a mode of dispatching a system work order and a short message; and if no abnormity exists, the video is watermarked to obtain the computer room information, the geographical position information and the routing inspection information, and the video is uploaded to the cloud server to be stored.
In step S243, when the detection result is corrected, it is determined whether the MODF trace frame is completely scanned from top to bottom, and the reason for this determination is as follows: the subsequent correction of the identification result according to the context information and the time sequence information is regulated and convenient in service; the specific judgment method for this judgment is as follows: and judging according to the time sequence information and the context information.
It should be noted that the inclusion-V3 model is an image classification model trained by google on the large image database ImageNet, and the inclusion-V3 model has 47 layers in total.
This embodiment also provides a telecommunications room system of patrolling and examining based on AR technique, includes:
the video acquisition module is used for polling the machine room to acquire a real-time video;
the identification module is used for carrying out real-time synchronous identification on the image identification terminal through the acquired real-time video information and detecting and identifying various information of the machine room in the real-time video;
the marking module is used for marking the abnormal items after identifying the abnormal items and displaying the abnormal items on the camera shooting equipment;
the record uploading module is used for uploading the video information in the inspection process to the cloud server in real time and analyzing and counting the completion condition of the inspection work order;
the central processing module is used for sending instructions to other modules to complete related actions;
the video acquisition module, the identification module, the marking module and the record uploading module are all electrically connected with the central processing module.
In summary, compared with the current polling method, the polling method for the telecommunication room based on the AR technology of the embodiment not only reduces the manpower and material costs of polling; the comprehensive maintenance personnel can be rectified, reformed and guided in real time, and the working efficiency is improved; the comprehensive maintenance personnel safety awareness can be improved, the inspection data is saved, the subsequent inspection and the workload statistics are facilitated, and the comprehensive maintenance personnel safety awareness is worthy of being popularized and used.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
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 (10)
1. A method for inspecting a telecommunication room based on an AR technology is characterized by comprising the following steps:
s1: obtaining real-time video
The method comprises the following steps of (1) carrying out machine room inspection by using a camera device, and acquiring a real-time video through a camera of the camera device;
s2: identifying video
The method comprises the steps that real-time synchronous identification is carried out on an image identification terminal through acquired real-time video information, and all information of a machine room in the real-time video is detected and identified, wherein the identification of all information comprises the identification of paper scrap garbage, the identification of sundries except machine room equipment, the identification of whether a ceiling is soaked with water or not and the identification of whether machine frame wiring is smooth or not;
s3: annotating outlier items
After the abnormal items are identified, processing the video, marking the abnormal items, and displaying the abnormal items on the camera shooting equipment so as to guide comprehensive maintenance personnel to carry out rectification;
s4: upload records
And uploading the video information in the inspection process to a cloud server in real time, and analyzing and counting the completion condition of the inspection work order.
2. The method for inspecting the telecommunication room based on the AR technology according to the claim 1, characterized in that: in step S2, before real-time synchronous identification of the real-time video information, a PB model corresponding to the item needs to be established, and when identifying wastepaper waste, identifying sundries other than equipment in the machine room, and identifying whether water stains exist on the ceiling, the first PB model is used for identification, and when identifying whether the routing of the rack is smooth or not, the second PB model is used for identification.
3. The method for inspecting the telecommunication room based on the AR technology according to the claim 2, characterized in that: the generation process of the first PB model comprises the following steps:
s201: collecting a large number of sample pictures of paper scraps, sundries and water stains on a ceiling in a machine room;
s202: manually marking paper scraps, sundries and water stains in the picture;
s203: identifying the characteristics of paper scraps, impurities and water stains;
s204: a first PB model file is generated.
4. The method for inspecting the telecommunication room based on the AR technology according to the claim 3, characterized in that: in step S203, the process of identifying the characteristics of paper scraps, impurities and water stains is as follows:
s2031: dividing the image containing paper scraps, impurities and water stains into S multiplied by S grids
S2032: acquiring each grid image in the S multiplied by S grids;
s2033: b Bounding boxes and confidence values are predicted in each grid, the Bounding boxes reflect the positions of the grids, the confidence scores reflect the accuracy of the boxes, and if no target exists, the confidence values are zero;
wherein each bounding box contains 5 values: x, y, w, h and confidence, respectively; (x, y) coordinates represent the center of the bounding box relative to the grid cell bounding box; w denotes the width, h denotes the height, all predicted with respect to the whole image; confidence represents the intersection between the predicted box and the actual bounding box; each grid cell also predicts C conditional class probabilities, which are encoded as tensors of SxS (B × 5+ C);
s2034: and obtaining a final result according to the confidence score and the predicted probability of each grid.
5. The method for inspecting the telecommunication room based on the AR technology according to claim 4, wherein the method comprises the following steps: the process of identifying with the first PB model includes the steps of:
s211: acquiring each frame of image in a real-time video, inputting the image into a first PB model, returning the probability that the image contains paper scraps, sundries and water stains by using the model, wherein if the probability is more than 80%, the image contains the paper scraps, the sundries and the water stains, and otherwise, the image does not contain the paper scraps, the sundries and the water stains;
s212: and when the abnormal item is detected and identified, the model returns the coordinate information of the abnormal item, and the coordinates of the image abnormal item are identified by a red frame by using openCV.
6. The method for inspecting the telecommunication room based on the AR technology according to the claim 2, characterized in that: the generation process of the second PB model comprises the following steps:
s231: collecting a large number of wiring sample images in a machine room;
s232: sample image classification is carried out by adopting a transfer learning method and using a deep neural network inclusion-v 3 model;
s233: and generating a second PB model file.
7. The method for routing inspection of the telecommunication room based on the AR technology as claimed in claim 6, wherein in the step S232, the configuration and training process of the inclusion-v 3 model specifically comprises the following steps:
s2321: establishing a folder, establishing subfolders in the folder, wherein the subfolders are respectively a wiring compliance class, a wiring non-compliance class, a wiring column class and a non-wiring column class, and putting corresponding training pictures;
s2322: py file is configured, and the file comprises a training picture path, a model storage path, a label file and training steps;
s2323: training and batch command generation models are performed.
8. The method for inspecting the telecommunication room based on the AR technology according to the claim 2, characterized in that: the process of identifying using the second PB model includes the steps of:
s241: scanning the wiring rack from top to bottom by using a camera to acquire wiring information video;
s242: calling a second PB model to detect the routing information video to obtain a detection result;
s243: correcting the detection result by using the time sequence information and the context information of the routing information video;
s244: if the detection result is abnormal, prompting the comprehensive maintenance personnel to carry out rectification in a mode of dispatching a system work order and a short message; and if no abnormity exists, the video is watermarked to obtain the computer room information, the geographical position information and the routing inspection information, and the video is uploaded to the cloud server to be stored.
9. The method for inspecting the telecommunication room based on the AR technology as claimed in claim 8, wherein: in step S243, it is necessary to determine whether the MODF trace frame is completely scanned from top to bottom when the detection result is corrected.
10. An inspection system for a telecommunication room based on AR technology, which is characterized in that the inspection is carried out according to the inspection method for the telecommunication room according to any claim 1 to 9, and comprises the following steps:
the video acquisition module is used for polling the machine room to acquire a real-time video;
the identification module is used for carrying out real-time synchronous identification on the image identification terminal through the acquired real-time video information and detecting and identifying various information of the machine room in the real-time video;
the marking module is used for marking the abnormal items after identifying the abnormal items and displaying the abnormal items on the camera shooting equipment;
the record uploading module is used for uploading the video information in the inspection process to the cloud server in real time and analyzing and counting the completion condition of the inspection work order;
the central processing module is used for sending instructions to other modules to complete related actions;
the video acquisition module, the identification module, the marking module and the record uploading module are all electrically connected with the central processing module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911357764.5A CN111047731A (en) | 2019-12-25 | 2019-12-25 | AR technology-based telecommunication room inspection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911357764.5A CN111047731A (en) | 2019-12-25 | 2019-12-25 | AR technology-based telecommunication room inspection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111047731A true CN111047731A (en) | 2020-04-21 |
Family
ID=70239614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911357764.5A Pending CN111047731A (en) | 2019-12-25 | 2019-12-25 | AR technology-based telecommunication room inspection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111047731A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950506A (en) * | 2020-08-25 | 2020-11-17 | 中山大学 | MOCVD equipment maintenance assisting method and system based on AR technology |
| CN112067934A (en) * | 2020-09-18 | 2020-12-11 | 山东工业职业学院 | Electrical control cabinet fault monitoring system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779541A (en) * | 2016-11-30 | 2017-05-31 | 长威信息科技发展股份有限公司 | A kind of warehouse management method and system based on AR technologies |
| CN107944412A (en) * | 2017-12-04 | 2018-04-20 | 国网山东省电力公司电力科学研究院 | Transmission line of electricity automatic recognition system and method based on multilayer convolutional neural networks |
| CN109636944A (en) * | 2018-12-12 | 2019-04-16 | 国网重庆市电力公司信息通信分公司 | Wearable device power grid based on augmented reality makes an inspection tour repair method and its system |
| CN109815998A (en) * | 2019-01-08 | 2019-05-28 | 科大国创软件股份有限公司 | A kind of AI dress dimension method for inspecting and system based on YOLO algorithm |
| CN110031909A (en) * | 2019-04-18 | 2019-07-19 | 西安天和防务技术股份有限公司 | Safe examination system and safety inspection method |
| CN110321853A (en) * | 2019-07-05 | 2019-10-11 | 杭州巨骐信息科技股份有限公司 | Distribution cable external force damage prevention system based on video intelligent detection |
| CN110379036A (en) * | 2019-06-26 | 2019-10-25 | 广东康云科技有限公司 | Intelligent substation patrol recognition methods, system, device and storage medium |
| CN110400387A (en) * | 2019-06-26 | 2019-11-01 | 广东康云科技有限公司 | A kind of joint method for inspecting, system and storage medium based on substation |
-
2019
- 2019-12-25 CN CN201911357764.5A patent/CN111047731A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779541A (en) * | 2016-11-30 | 2017-05-31 | 长威信息科技发展股份有限公司 | A kind of warehouse management method and system based on AR technologies |
| CN107944412A (en) * | 2017-12-04 | 2018-04-20 | 国网山东省电力公司电力科学研究院 | Transmission line of electricity automatic recognition system and method based on multilayer convolutional neural networks |
| CN109636944A (en) * | 2018-12-12 | 2019-04-16 | 国网重庆市电力公司信息通信分公司 | Wearable device power grid based on augmented reality makes an inspection tour repair method and its system |
| CN109815998A (en) * | 2019-01-08 | 2019-05-28 | 科大国创软件股份有限公司 | A kind of AI dress dimension method for inspecting and system based on YOLO algorithm |
| CN110031909A (en) * | 2019-04-18 | 2019-07-19 | 西安天和防务技术股份有限公司 | Safe examination system and safety inspection method |
| CN110379036A (en) * | 2019-06-26 | 2019-10-25 | 广东康云科技有限公司 | Intelligent substation patrol recognition methods, system, device and storage medium |
| CN110400387A (en) * | 2019-06-26 | 2019-11-01 | 广东康云科技有限公司 | A kind of joint method for inspecting, system and storage medium based on substation |
| CN110321853A (en) * | 2019-07-05 | 2019-10-11 | 杭州巨骐信息科技股份有限公司 | Distribution cable external force damage prevention system based on video intelligent detection |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950506A (en) * | 2020-08-25 | 2020-11-17 | 中山大学 | MOCVD equipment maintenance assisting method and system based on AR technology |
| CN112067934A (en) * | 2020-09-18 | 2020-12-11 | 山东工业职业学院 | Electrical control cabinet fault monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
| US11321583B2 (en) | Image annotating method and electronic device | |
| CN110569874A (en) | Garbage classification method and device, intelligent terminal and storage medium | |
| CN110516529A (en) | It is a kind of that detection method and system are fed based on deep learning image procossing | |
| CN112966772A (en) | Multi-person online image semi-automatic labeling method and system | |
| CN110049121B (en) | Data center inspection system based on augmented reality technology | |
| CN109558792B (en) | Method and system for detecting internet logo content based on samples and features | |
| CN112070135A (en) | Power equipment image detection method and device, power equipment and storage medium | |
| KR102503116B1 (en) | Automatic Data Set Generation Device and their Control Method for AI Machine Learning Learning | |
| CN111310826B (en) | Method and device for detecting labeling abnormality of sample set and electronic equipment | |
| CN110458794B (en) | Quality detection method and device for accessories of rail train | |
| CN112508109B (en) | Training method and device for image recognition model | |
| TW202009681A (en) | Sample labeling method and device, and damage category identification method and device | |
| CN111047731A (en) | AR technology-based telecommunication room inspection method and system | |
| CN112613569A (en) | Image recognition method, and training method and device of image classification model | |
| CN114119518A (en) | Method and system for detecting temperature abnormal point in infrared image of current transformer | |
| CN112102443A (en) | Marking system and marking method suitable for substation equipment inspection image | |
| CN115269438A (en) | Automatic testing method and device for image processing algorithm | |
| CN112004063B (en) | Method for monitoring connection correctness of oil discharge pipe based on multi-camera linkage | |
| CN113408630A (en) | Transformer substation indicator lamp state identification method | |
| CN114694130A (en) | Method and device for detecting telegraph poles and pole numbers along railway based on deep learning | |
| CN115829234A (en) | Automatic supervision system based on classroom detection and working method thereof | |
| CN113850773A (en) | Detection method, device, equipment and computer readable storage medium | |
| CN115456984A (en) | High-speed image recognition defect detection system based on two-dimensional code | |
| CN115359505A (en) | Electric power drawing detection and extraction method and system |
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: 20200421 |
|
| RJ01 | Rejection of invention patent application after publication |