CN115660924A - Real-time high-precision early warning method for distribution network operation based on AI vision - Google Patents
Real-time high-precision early warning method for distribution network operation based on AI vision Download PDFInfo
- Publication number
- CN115660924A CN115660924A CN202211339610.5A CN202211339610A CN115660924A CN 115660924 A CN115660924 A CN 115660924A CN 202211339610 A CN202211339610 A CN 202211339610A CN 115660924 A CN115660924 A CN 115660924A
- Authority
- CN
- China
- Prior art keywords
- early warning
- operator
- equipment
- roi
- relative position
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a real-time high-precision early warning method for distribution network operation based on AI vision, which comprises the following steps: collecting a panoramic image of a working environment, constructing a relative position coordinate system based on the image and acquiring a relative position conversion matrix; performing operation site video identification by using a yolo target detection model, and respectively acquiring ROI (region of interest) areas of operators and charged equipment; determining coordinate information of the operating personnel and the electrified equipment by using the relative position conversion matrix and the auxiliary positioning equipment; and calculating the distance between the operating personnel and the live equipment by using a Gaussian distance formula, comparing the distance with the safety distance, and performing dangerous area early warning based on the comparison result. The method provided by the invention can greatly improve the operation safety of operators, is beneficial to personnel supervision in a complex power distribution operation environment, and reduces the pain problem caused by the lack of real-time performance of the existing early warning system due to the over-slow response speed caused by manual data inspection and manual data summarization.
Description
Technical Field
The invention relates to the technical field of intelligent monitoring of distribution network operation, in particular to a real-time high-precision early warning method for distribution network operation based on AI vision.
Background
In recent years, the intelligent monitoring technology for power distribution network operation has been steadily advanced in power grids, and intelligent devices such as a safety management and control ball and a monitoring camera are gradually applied to power distribution network stations and other intelligent test points.
However, in the floor application practice of the prior power distribution network field operation monitoring, in the face of complex operation scenes such as suburbs and fields, the intelligent monitoring technology and the terminal equipment often need to check and establish a live safety area range on the spot after repeated communication of specially-assigned persons before operation, and accidents are often caused by negligence or fatigue in the operation process, so that the operation personnel can act in a dangerous area adjacent to the operation personnel; in addition, the existing early warning system cannot realize a real-time early warning function, so that the danger coefficient of an operator in live working is greatly increased. With the development of deep learning neural network technology and the development of computer vision theory, aiming at the existing problems, the camera for arranging the control ball can be used for carrying out picture tracking on the target and tracking the position of the detected target based on perception auxiliary means such as positioning information and the like, the violation behaviors are effectively identified and prejudged, and the early warning of the safe distance is further realized to reduce the occurrence of dangerous behaviors.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned problems.
Therefore, the technical problem solved by the invention is as follows: how to identify dangerous areas for real-time forewarning.
In order to solve the technical problems, the invention provides the following technical scheme: a real-time high-precision early warning method for distribution network operation based on AI vision comprises the following steps:
acquiring a panoramic image of a working environment, constructing a relative position coordinate system based on the image and acquiring a relative position conversion matrix;
performing operation site video identification by using a yolo target detection model, and respectively acquiring ROI (region of interest) areas of operators and charged equipment;
determining coordinate information of an operator and the electrified equipment by using the relative position matrix and the auxiliary positioning equipment;
and calculating the distance between the operating personnel and the live equipment by using a Gaussian distance formula, comparing the distance with the safety distance, and performing dangerous area early warning based on the comparison result.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: the constructing a relative position coordinate system comprises:
the collected panoramic image is used as a reference image, one distributed control ball in the reference image is selected as an origin, a relative position coordinate system is constructed according to relative position information among a plurality of distributed control balls, and position coordinate information of each pixel point in the reference image is obtained based on the relative position coordinate system.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: the relative position conversion matrix includes:
collecting operation field images by using a camera equipped with a distribution control ball, and correcting the reference image based on the collected field images; selecting a plurality of key points in the acquired field image, and calculating a relative position conversion matrix between the two planes according to the relative position coordinates of the key points on the shot image and the reference image.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: the obtaining of the ROI area of the operator and the live equipment comprises the following steps:
detecting whether an operator and the charged equipment are in the same picture by using a yolo target detection model, and if the operator and the charged equipment are in the same picture, acquiring charged voltage data of the equipment through a background system; and if the voltage data is not 0, respectively acquiring the ROI (region of interest) information of the operator and the charged equipment at the moment.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: the auxiliary positioning device specifically comprises: a map positioning device that can be used to determine location information, comprising: UWB and Beidou.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: the coordinate information of the operator and the charged equipment comprises: the relative position coordinates of the ROI central point of the operator, the relative position coordinates of the ROI central point of the charged device, the three-dimensional coordinates of the ROI central point of the operator, the three-dimensional coordinates of the ROI central point of the charged device, the two-dimensional coordinates of the ROI central point of the operator and the two-dimensional coordinates of the ROI central point of the charged device.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: further comprising: after the three-dimensional coordinates of the ROI area of the operator and the ROI area of the charged device are determined in a mode of combining yolo target detection and positioning auxiliary equipment, the two-dimensional coordinates of the ROI area of the operator and the ROI area of the charged device are obtained in a mapping mode.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: utilize yolo target detection model to carry out operation scene video identification, include: decoding the video according to the working site environment video, and labeling the live equipment and the working personnel in the decoded image, particularly, finely labeling the body part characteristic information of the working personnel; and then inputting the marked pictures into a yolo-improved-based video target detection neural network model for iterative training to obtain a video target detection model capable of identifying operators and live equipment.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: the euclidean distance formula, expressed as:
wherein, P 1 Two-dimensional coordinates of the center point of the ROI of the operator 1 ，y 1 ) Is represented by P 2 Two-dimensional coordinates referring to the center point of the ROI area of the charged device in (x) 2 ，y 2 ) And (4) showing.
As an optimal scheme of the AI vision-based real-time high-precision early warning method for distribution network operation, the invention comprises the following steps: the dangerous area early warning based on the comparison result comprises the following steps: comparing the calculated distance with a preset safety distance, if the calculated distance is not greater than the safety distance, judging that the operator is close to or crosses the safety distance during operation, and sending a real-time early warning signal to the operator in a dangerous area; and if the calculated distance is greater than the safety distance, judging that the operator is not close to the dangerous area during operation, and continuing the operation of the distribution network.
The invention has the beneficial effects that: according to the invention, the tracking of operators and live equipment under the complex power distribution environment based on AI vision is realized by using a computer vision theory and a deep learning neural network technology, the accurate positioning of the operators and the live equipment is realized by using a yolo target detection model and a relative position conversion matrix, the calculation of the distance between the operators and a dangerous area is realized by using a Gaussian distance calculation formula, and the early warning of accidental entering of the operators into the dangerous area is further realized; the method provided by the invention can greatly improve the operation safety of the operators, effectively prevent accidents caused by the carelessness of the operators entering dangerous areas, is beneficial to personnel supervision in complex power distribution operation environments, and reduces the pain problems caused by the lack of real-time property of the existing early warning system due to the over-slow response speed caused by manual data patrol and manual data summarization.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is an overall flowchart of a real-time high-precision early warning method for distribution network operation based on AI vision according to an embodiment of the present invention;
FIG. 2 is a flow diagram of a vision-based three-dimensional coordinate system building module according to an embodiment of the invention;
FIG. 3 is a flowchart of training a yolo-based video target detection model for workers and live equipment according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a goal detection network model based on yolo improvement according to an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Also in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, which are only for convenience of description and simplification of description, but do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 to 4, an embodiment of the present invention provides a real-time high-precision early warning method for distribution network operation based on AI vision, including:
s1: collecting a panoramic image of a working environment, constructing a relative position coordinate system based on the image and acquiring a relative position conversion matrix.
Furthermore, cameras equipped with a plurality of field distribution control balls arranged in a power distribution field are used for shooting live working scenes so as to acquire a panoramic image of a working environment in a monitoring area of the working field.
Furthermore, the collected panoramic image is used as a reference image, one distributed control ball in the reference image is selected as an origin, a relative position coordinate system is constructed according to relative position information among the plurality of distributed control balls, and further the position coordinate information of each pixel point in the reference image is obtained based on the constructed relative position coordinate system.
Furthermore, the reference image is corrected based on the image shot by the cloth control ball;
specifically, firstly, the internal parameters and distortion coefficients of all cameras need to be calculated and calibrated through a calibretanecamra function in opencv; then, correction is carried out through undistort function in opencv.
It should be noted that, the image taken by the distribution control ball at the present location of the distribution network operation is not a top view in the air, but a picture with a certain inclination angle with the ground; therefore, a panoramic image of the working environment formed by splicing the pictures collected by the plurality of control balls has certain distortion, and in order to ensure the accuracy of the reference image, the panoramic image needs to be corrected by using the function of opencv, so that the coordinate accuracy of the panoramic image can be improved.
Furthermore, a plurality of key points are selected from the shot image, and a relative position conversion matrix between the two planes is calculated by using a findHomography function in opencv according to relative position coordinates of the key points on the shot image and the reference image.
S2: and performing operation field video identification by using the yolo target detection model to obtain ROI areas of operators and charged equipment.
Furthermore, the collected working environment video is identified by the yolo target detection model for the operators and the charged equipment.
In an optional embodiment, firstly, a video is decoded according to an environment video of a working site, and a live device and a worker in the decoded image are labeled, wherein the feature information of a body part of the worker needs to be finely labeled; and inputting the marked pictures into a yolo-improved-based video target detection neural network model for iterative training to obtain a video target detection model capable of identifying operators and live equipment, wherein the specific working flow of the video target detection model is shown in fig. 3.
It should be noted that the reason for performing the work site environment video recognition using the yolo target detection model is to remove the detection video stream of the worker and the live equipment with low confidence.
Furthermore, when the same video picture of the operator and the charged equipment is successfully detected, the charged voltage data of the equipment is acquired through a background system; and if the voltage data is not 0, respectively acquiring the ROI area information of the operator and the charged equipment at the moment.
It should be noted that, when the voltage of the distribution network operation site is 0, the detection of the constructors and the live equipment does not need to be performed by wasting the computing resources; when the voltage is greater than 0, in order to ensure the safety of the distribution network operation constructors, the distance between the constructors and the electrified equipment needs to be detected; therefore, the voltage of the distribution network operation site needs to be judged before the ROI is acquired.
S3: and determining coordinate information of the operator and the electrified equipment by using the relative position matrix and the auxiliary positioning equipment.
Further, the center point of the obtained ROI region is used to obtain the position coordinates of the center point of the region corresponding to the reference map through a relative position matrix, wherein the relative position coordinates of the center point of the ROI region of the operator are expressed as:
the relative position coordinates of the central point of the ROI of the charged equipment are as follows:
furthermore, the map information is registered by using the positioning auxiliary equipment, so that the three-dimensional coordinate information of the live equipment and the operator is acquired.
It should be noted that the positioning assistance device includes UWB, beidou, and the like map positioning devices for determining position information.
It should also be noted that the position information of the live-line equipment and the operator is acquired by combining the yolo target detection and the auxiliary positioning equipment, so that the acquired three-dimensional coordinate information of the live-line equipment and the operator is more accurate, and the accuracy of the early warning of the dangerous area is further improved.
Furthermore, mapping the three-dimensional coordinate information of the operator and the charged device to a two-dimensional coordinate system to obtain two-dimensional coordinates of the operator and the charged device respectively, where the two-dimensional coordinates of the operator are:
the two-dimensional coordinates of the charged device are:
s4: and calculating the distance between the operating personnel and the live equipment by using a Gaussian distance formula, comparing the distance with the safety distance, and performing dangerous area early warning based on the comparison result.
Further, using the Gaussian distance formula
And calculating the distance between the operator and the electrified equipment.
Further, the calculated distance is compared with a preset safety distance for determining whether the operator is in the dangerous area.
Note that the determination etalon body is: if the calculated distance is not greater than the safety distance, judging that the operator is adjacent to or spans the safety distance during operation, and sending a real-time early warning signal to the operator in the dangerous area; and if the calculated distance is greater than the safety distance, judging that the operator is not close to the dangerous area during operation, and continuing to perform power distribution network operation.
Example 2
Referring to fig. 1 to 4, an embodiment of the invention provides a real-time high-precision early warning method for distribution network operation based on AI vision, and the beneficial effects of the invention are verified through application conditions in two distribution operation sites.
Acquiring a panoramic image of an operating environment through ball arrangement and control equipment on a high-voltage power distribution operating site; when constructors enter a site, the site distribution and control balls start to detect and track entering personnel in real time, the site distribution and control balls start to monitor the area of the electrified equipment in real time according to signals of the electrified equipment, and the real-time early warning system can acquire coordinate information of electrified objects.
When an operator enters a monitoring area, the distance between the operator and a charged object is calculated based on a three-dimensional coordinate positioning algorithm of vision, and position information is assisted and calibrated according to a UWB chip carried by the charged operator. And calculating the linear distance of the operator and the charged object on a two-dimensional plane according to the coordinates of the operator and the charged object, and when the distance between the operator and the charged device does not accord with the background voltage grade data and the corresponding safe distance, starting to give an alarm by the early warning system.
In a climbing power distribution operation site, acquiring a panoramic image of an operation environment through a ball arrangement and control device, calibrating the panoramic image by using the unmanned aerial vehicle to lift off, and establishing a prior map of a visual map; when a constructor enters a site, a ball control distribution picture is started to track and monitor the constructor in real time; then acquiring charged object information according to the background voltage data, and obtaining an ROI (region of interest) area through target detection; and obtaining three-dimensional coordinate information of the constructor and the charged object, carrying out coordinate registration through UWB information of a working environment field, and sending out an alarm to the operator in the dangerous area through coordinate distance calculation between the constructor and the charged object.
Therefore, no matter in a high-voltage power distribution operation scene or a climbing power distribution operation scene, the panoramic image can be obtained by using the control ball, the real-time tracking of the operating personnel and the live equipment is realized by using the target detection model, and whether the operating personnel are in a dangerous area or not is judged by obtaining the position information of the operating personnel and the live equipment.
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable connection, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, or the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of illustration, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A real-time high-precision early warning method for distribution network operation based on AI vision is characterized by comprising the following steps:
collecting a panoramic image of a working environment, constructing a relative position coordinate system based on the image and acquiring a relative position conversion matrix;
performing operation site video identification by using a yolo target detection model, and respectively acquiring ROI (region of interest) areas of operators and charged equipment;
determining coordinate information of an operator and the electrified equipment by using the relative position conversion matrix and the auxiliary positioning equipment;
and calculating the distance between the operating personnel and the live equipment by using a Gaussian distance formula, comparing the distance with the safety distance, and performing dangerous area early warning based on the comparison result.
2. The AI vision based real-time high accuracy early warning method for distribution network operations as recited in claim 1, further comprising: the constructing of the relative position coordinate system comprises:
the collected panoramic image is used as a reference image, one distributed control ball in the reference image is selected as an origin, a relative position coordinate system is constructed according to relative position information among a plurality of distributed control balls, and position coordinate information of each pixel point in the reference image is obtained based on the relative position coordinate system.
3. The AI vision based real-time high accuracy early warning method for distribution network operation as recited in claim 1 or 2, further comprising: the relative position conversion matrix includes:
collecting operation field images by using a camera equipped with a distribution control ball, and correcting the reference image based on the collected field images; selecting a plurality of key points in the acquired field image, and calculating a relative position conversion matrix between the two planes according to the relative position coordinates of the key points on the shot image and the reference image.
4. The AI vision based real-time high accuracy early warning method for distribution network operations as recited in claim 3, further comprising: the obtaining of the ROI area of the operator and the live equipment comprises the following steps:
detecting whether an operator and the charged equipment are in the same picture by using a yolo target detection model, and if the operator and the charged equipment are in the same picture, acquiring charged voltage data of the equipment through a background system; and if the voltage data is not 0, respectively acquiring the ROI area information of the operator and the charged equipment at the moment.
5. The AI vision based real-time high accuracy early warning method for distribution network operations as recited in claim 3, further comprising: the auxiliary positioning equipment specifically comprises: a map location device that may be used to determine location information, comprising: UWB and Beidou.
6. The AI vision based real-time high accuracy early warning method for distribution network operation as recited in claim 4 or 5, further comprising: the coordinate information of the operating personnel and the charged equipment comprises: the relative position coordinates of the ROI central point of the operator, the relative position coordinates of the ROI central point of the charged device, the three-dimensional coordinates of the ROI central point of the operator, the three-dimensional coordinates of the ROI central point of the charged device, the two-dimensional coordinates of the ROI central point of the operator and the two-dimensional coordinates of the ROI central point of the charged device.
7. The AI vision based real-time high accuracy early warning method for distribution network operations as recited in claim 6, further comprising: further comprising: after three-dimensional coordinates of the ROI of the operator and the ROI of the charged device are determined in a mode of combining yolo target detection and positioning auxiliary equipment, two-dimensional coordinate center points of the ROI of the operator and the ROI of the charged device are obtained in a mapping mode.
8. The AI vision based real-time high accuracy early warning method for distribution network operations as recited in claim 7, further comprising: utilize yolo target detection model to carry out job site video identification, include: decoding the video according to the working site environment video, and labeling the live equipment and the working personnel in the decoded image, particularly, finely labeling the body part characteristic information of the working personnel; and then inputting the marked pictures into a yolo-improved-based video target detection neural network model for iterative training to obtain a video target detection model capable of identifying operators and live equipment.
9. The AI vision based real-time high accuracy early warning method for distribution network operations of claim 8, wherein: the euclidean distance formula, expressed as:
wherein, P 1 Two-dimensional coordinates of the center point of the ROI of the operator 1 ，y 1 ) Is represented by P 2 Refers to the two-position coordinate of the center point of the ROI area of the charged device 2 ，y 2 ) And (4) showing.
10. The AI vision based real-time high accuracy early warning method for distribution network operation as recited in claim 8 or 9, further comprising: the dangerous area early warning based on the comparison result comprises the following steps: comparing the calculated distance with a preset safety distance, if the calculated distance is not greater than the safety distance, judging that the operator is adjacent to or spans the safety distance during operation, and sending a real-time early warning signal to the operator in a dangerous area; and if the calculated distance is greater than the safety distance, judging that the operator is not close to the dangerous area during operation, and continuing the operation of the distribution network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211339610.5A CN115660924A (en) | 2022-10-28 | 2022-10-28 | Real-time high-precision early warning method for distribution network operation based on AI vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211339610.5A CN115660924A (en) | 2022-10-28 | 2022-10-28 | Real-time high-precision early warning method for distribution network operation based on AI vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115660924A true CN115660924A (en) | 2023-01-31 |
Family
ID=84994178
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211339610.5A Pending CN115660924A (en) | 2022-10-28 | 2022-10-28 | Real-time high-precision early warning method for distribution network operation based on AI vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660924A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115861407A (en) * | 2023-02-28 | 2023-03-28 | 山东未来网络研究院(紫金山实验室工业互联网创新应用基地) | Safe distance detection method and system based on deep learning |
| CN117549330A (en) * | 2024-01-11 | 2024-02-13 | 四川省铁路建设有限公司 | Construction safety monitoring robot system and control method |
-
2022
- 2022-10-28 CN CN202211339610.5A patent/CN115660924A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115861407A (en) * | 2023-02-28 | 2023-03-28 | 山东未来网络研究院(紫金山实验室工业互联网创新应用基地) | Safe distance detection method and system based on deep learning |
| CN117549330A (en) * | 2024-01-11 | 2024-02-13 | 四川省铁路建设有限公司 | Construction safety monitoring robot system and control method |
| CN117549330B (en) * | 2024-01-11 | 2024-03-22 | 四川省铁路建设有限公司 | Construction safety monitoring robot system and control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115660924A (en) | Real-time high-precision early warning method for distribution network operation based on AI vision | |
| US20210049918A1 (en) | Systems and methods for adaptive property analysis via autonomous vehicles | |
| US10930015B2 (en) | Method and system for calibrating multiple cameras | |
| CN110142785A (en) | A kind of crusing robot visual servo method based on target detection | |
| US20200198139A1 (en) | Map creation method of mobile robot and mobile robot | |
| CN112396656B (en) | Outdoor mobile robot pose estimation method based on fusion of vision and laser radar | |
| CN108279677B (en) | Rail robot detection method based on binocular vision sensor | |
| CN111967323B (en) | Electric power live working safety detection method based on deep learning algorithm | |
| CN115205286B (en) | Method for identifying and positioning bolts of mechanical arm of tower-climbing robot, storage medium and terminal | |
| Lee et al. | Intelligent robot for worker safety surveillance: Deep learning perception and visual navigation | |
| CN113919627A (en) | Intelligent monitoring method applied to hydro-junction engineering | |
| CN113749646A (en) | Monocular vision-based human body height measuring method and device and electronic equipment | |
| CN113065462A (en) | Monitoring method, device, equipment and storage medium for power grid overhead line | |
| CN110322508B (en) | Auxiliary positioning method based on computer vision | |
| CN116453212A (en) | Method suitable for detecting illegal behaviors in electric power construction scene | |
| CN115994953A (en) | Power field security monitoring and tracking method and system | |
| CN102853821A (en) | Ship GPS positioning and checking method and ship GPS interactive system | |
| Prasser et al. | Probabilistic visual recognition of artificial landmarks for simultaneous localization and mapping | |
| CN115690573A (en) | Base station acceptance method, device, equipment and storage medium | |
| CN114169404A (en) | Method for intelligently acquiring quantitative information of slope diseases based on images | |
| CN113989335A (en) | Method for automatically positioning workers in factory building | |
| CN112802058A (en) | Method and device for tracking illegal moving target | |
| JP2003240622A (en) | Liquid level recognition processing device and liquid level monitoring system | |
| CN115494878B (en) | Unmanned aerial vehicle line patrol path adjustment method and device based on obstacle avoidance | |
| CN111738082A (en) | Identification method and device for automatically tracking and positioning fire source point based on machine vision |
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 |