CN117291443B - Intelligent paying-off system based on multidimensional sensing technology - Google Patents
Intelligent paying-off system based on multidimensional sensing technology Download PDFInfo
- Publication number
- CN117291443B CN117291443B CN202311586814.3A CN202311586814A CN117291443B CN 117291443 B CN117291443 B CN 117291443B CN 202311586814 A CN202311586814 A CN 202311586814A CN 117291443 B CN117291443 B CN 117291443B
- Authority
- CN
- China
- Prior art keywords
- image
- paying
- super
- data
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005516 engineering process Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 63
- 238000004088 simulation Methods 0.000 claims abstract description 55
- 230000005540 biological transmission Effects 0.000 claims abstract description 41
- 238000004458 analytical method Methods 0.000 claims abstract description 39
- 238000010276 construction Methods 0.000 claims abstract description 31
- 238000005259 measurement Methods 0.000 claims abstract description 24
- 230000011218 segmentation Effects 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000007726 management method Methods 0.000 claims abstract description 12
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000011217 control strategy Methods 0.000 claims abstract description 10
- 238000007499 fusion processing Methods 0.000 claims abstract description 8
- 230000008569 process Effects 0.000 claims description 35
- 238000012544 monitoring process Methods 0.000 claims description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 32
- 230000008447 perception Effects 0.000 claims description 32
- 238000011156 evaluation Methods 0.000 claims description 31
- 230000004927 fusion Effects 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 29
- 238000007667 floating Methods 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 10
- 230000032683 aging Effects 0.000 abstract description 3
- 230000035882 stress Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 241000282461 Canis lupus Species 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000013439 planning Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000012212 insulator Substances 0.000 description 2
- 238000010223 real-time analysis Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005288 electromagnetic effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent paying-off system based on a multidimensional sensing technology, and relates to the technical field of intelligent sensing analysis; the system comprises a multidimensional information acquisition module, a fusion processing module, a simulation analysis module and a strategy management module; the method comprises the steps of taking acquired power transmission line image information, carrying out super-pixel segmentation pretreatment on the image, combining a guide filtering technology with an image space projection screening method, obtaining high-precision space measurement data, establishing paying-off construction information according to a plurality of dimension data, determining the safety condition of each index by combining simulation analysis results, adjusting a paying-off intelligent control strategy according to safety feedback during paying-off, solving the problem of insufficient ageing accuracy of line length calculation under dynamic conditions, and reducing the safety risk during paying-off.
Description
Technical Field
The invention relates to the technical field of intelligent perception analysis, in particular to an intelligent paying-off system based on a multidimensional perception technology.
Background
The traditional tension paying-off method for the power transmission line is a construction method for keeping a stretched wire at a certain tension to separate from the ground and be in an overhead state in the whole process of wire erection, and is a key link of the power transmission line wire erection construction, the tension paying-off section is generally about eight kilometers long, a tension machine and a traction machine are respectively arranged on a tension field and a traction field by constructors, the tension machine drags the wire in the tension field, tension is provided for the wire, and the ground dragging abrasion of the wire is avoided; the tractor is connected with a traction wire to advance through a traction rope, a traction plate and other construction tools in a traction field; and hanging a paying-off pulley on each tower cross arm where the paying-off section is positioned to support the lead to be pulled through, and finally, pulling the lead to a traction field by a tension field to finish tension paying-off operation.
The prior art has the following defects:
with the rapid development of image information technology, various electric facilities on the ground can be clearly distinguished by means of aerial images of high resolution of unmanned aerial vehicles, in a complex shooting environment, the problems of multipath effect, channel attenuation, building shielding, various illumination backgrounds and the like are outstanding, the information acquisition of the unmanned aerial vehicles is inevitably interfered, further the problems of distortion and blurring of the aerial images are possibly caused, the assessment of the line state is affected, whether the construction conditions obtained in judging images meet the requirements relates to a large number of complex project calculations or not, the actual construction environment is changed, such as wind speed, temperature and the like, the related project calculation amount is larger, the simulation calculation time is longer, and particularly when continuous shelves of large height difference and large span are arranged, the related error project parameters cannot be acquired accurately in real time, so that the construction efficiency and construction quality are reduced, and even safety accidents are possibly caused.
The present invention proposes a solution to the above-mentioned problems.
Disclosure of Invention
In order to overcome the defects in the prior art, the embodiment of the invention provides an intelligent paying-off system based on a multidimensional sensing technology, which is used for accurately extracting complex condition image target identification and corresponding space data through mining the scale mapping relation from an unmanned aerial vehicle image to a physical space; and simultaneously, the simulation software and the artificial intelligence algorithm are combined to tune and trace the relevant parameters to solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the intelligent paying-off system based on the multidimensional sensing technology comprises a multidimensional information acquisition module, a fusion processing module, a simulation analysis module and a strategy management module, wherein the modules are connected through signals;
the multidimensional information acquisition module is used for acquiring acquired transmission line image information and carrying out super-pixel segmentation pretreatment on the image;
the fusion processing module is used for establishing a minimum spanning tree model taking super pixels as nodes according to a graph model theory, performing super pixel fusion on multiple scales to obtain a fusion image, combining a guide filtering technology with an image space projection screening method, and acquiring high-precision space measurement data from the fusion image through a target edge sharpening and space scale scaling algorithm;
the simulation analysis module is used for importing the acquired space measurement data into a simulation analysis model, and analyzing the characteristics of various aspects of the wire in the paying-off process through simulation to obtain wire characteristic data;
the strategy management module is used for establishing paying-off construction information according to the plurality of dimensional data, determining construction safety conditions of various indexes by combining simulation analysis results, and adjusting a control strategy in the paying-off process according to safety feedback during paying-off.
In a preferred embodiment, the step of performing super-pixel segmentation preprocessing on the image in the multi-dimensional information acquisition module includes:
denoising, brightness adjustment and color correction are carried out on the acquired power transmission line image, and super-pixel segmentation is carried out on the power transmission line image;
selecting the number density of super pixels and an initial center point in a color space for initialization;
for each super-pixel, calculating the average value of the pixels contained in the super-pixel to obtain a new center
And calculating the distance between each pixel and the center of all the super pixels, and repeating until the super pixels reach the iteration times.
In a preferred embodiment, the guide filtering technique is combined with the image space projection screening method, and high-precision space measurement data is obtained from the fused image through a target edge sharpening and space scaling algorithm, and the specific steps include:
adjusting pixel values of the target image according to the local statistical information of the guide image;
performing space matching by using characteristic points in the image, and determining the position and the gesture of the target object in the image;
according to the feature points and the camera parameters obtained by matching, performing space three-dimensional reconstruction to obtain coordinates of the target object in space;
further processing the reconstructed three-dimensional data by adopting a space projection screening method to obtain space measurement data, and identifying angular points by calculating the change of local gradients of the images;
and carrying out convolution operation on the fusion image to calculate gradients, and sharpening the image edges according to the calculated gradients.
In a preferred embodiment, setting up paying-off construction information according to a plurality of dimension data, and determining construction safety conditions of various indexes by combining simulation analysis results, the method comprises the following steps:
acquiring paying-off construction information in a paying-off process, wherein the paying-off construction information comprises equipment offset information, simulation accurate information and efficiency fluctuation information;
the equipment offset information comprises a transmission image processing stability index, the simulation accurate information comprises a monitoring error floating value, and the efficiency fluctuation information comprises a value frequency variation index;
and establishing a perception evaluation coefficient by using the transmission image processing stability index in the equipment offset information, the monitoring error floating value in the simulation accurate information and the value frequency variation index in the efficiency fluctuation information.
In a preferred embodiment, the transmission image processing stability index, the monitoring error floating value and the value frequency variation index are in direct proportion to the perception evaluation coefficient.
In a preferred embodiment, adjusting the control strategy during paying-off according to the safety feedback during paying-off comprises:
comparing the perception evaluation coefficient with a safety threshold;
if the perception evaluation coefficient is greater than or equal to the safety threshold value, generating a low safety standard signal;
and if the perception evaluation coefficient is smaller than the safety threshold value, generating a high safety coincidence signal.
In a preferred embodiment, the policy management module adjusts the control policy in the paying-off process according to the safety feedback during paying-off, and the method further comprises the following steps:
analyzing the paying-off process of the generated low-safety standard signal, continuously acquiring the perception evaluation coefficients in real time, establishing a data set, and calculating the mean value and standard deviation in the data set to obtain the outlier degree value of each perception evaluation coefficient;
calculating the deviation value of the mean value of the data elements in the data set to obtain an outlier degree value;
and comparing the outlier degree value of the data in the data set with a set outlier threshold, taking the data as outliers and recording when the outlier degree value of the data in the data set is larger than a discrete threshold, and performing tracing processing when the number of the outliers is larger than or equal to the set number threshold.
The intelligent paying-off system based on the multidimensional sensing technology has the technical effects and advantages that:
according to the invention, the acquired image information of the power transmission line is taken, the image is subjected to super-pixel segmentation pretreatment, the guided filtering technology is combined with the image space projection screening method, the high-precision space measurement data are acquired, the paying-off construction information is established according to the plurality of dimension data, the safety condition of each index is determined by combining simulation analysis results, the paying-off intelligent control strategy is adjusted according to the safety feedback during paying-off, the problem of insufficient ageing accuracy of line length calculation under dynamic conditions is solved, and the safety risk in the paying-off process is reduced.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent paying-off system based on a multidimensional sensing technology.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to achieve the above purpose, fig. 1 shows a schematic structural diagram of an intelligent paying-off system based on a multidimensional sensing technology, which specifically includes a multidimensional information acquisition module, a fusion processing module, a simulation analysis module and a strategy management module, wherein the modules are connected through signals.
The multidimensional information acquisition module is used for acquiring acquired transmission line image information and carrying out super-pixel segmentation pretreatment on the image;
the method comprises the steps of collecting images such as power transmission line images through image collecting equipment, for example, taking an unmanned aerial vehicle as a carrier, taking route planning as an aid, collecting power transmission line image information by using a camera in the unmanned aerial vehicle, transmitting the collected image information, and enabling autonomous flight of the unmanned aerial vehicle to have three functions of sensing, positioning and decision, wherein the sensing is to sense surrounding information including height, weather, obstacles and the like through a sensor of the unmanned aerial vehicle; positioning, namely accurately positioning according to Beidou satellites and a positioning instrument carried by the unmanned aerial vehicle; the decision comprises path planning and motion control, wherein the path planning is to determine an optimal route according to the surrounding environment, and the motion control is used for controlling the steering and flight routes of the unmanned aerial vehicle, so that the effect better than the effect of manual control is achieved; for aerial images acquired by the unmanned aerial vehicle, acquiring the constrained images according to acquisition conditions, such as resolution of selected photos, pitch angle of an acquisition camera, included angles of adjacent acquisition points and the like;
according to the parameters of the load of the camera (lens focal length, camera pixel size and ground resolution) on the unmanned aerial vehicle, the flying height of the unmanned aerial vehicle and the target radius of the acquired image are calculated, namely, the unmanned aerial vehicle is lifted to the position of the height, for example, the distance of the target around the flying radius is ensured, the acquired image can identify the target,ground resolution is a measure of the ability of an acquired image to differentially distinguish between two adjacent minimum distances.
Preprocessing the acquired power transmission line image, including denoising, brightness adjustment, color correction and the like; selecting a proper super-pixel segmentation algorithm, wherein the super-pixel can be regarded as a node in the graph, and common algorithms comprise an SLIC algorithm, a SEEDS algorithm and the like; taking an SLIC algorithm as an example for step explanation;
step 1, initializing an SLIC algorithm, and selecting the number density of super pixels and initial center points in a color space, wherein the center points can be uniformly distributed on an image;
step 2, for each pixel, calculate its distance from all superpixel centers, which can use color and spatial distance metrics, typically using euclidean distance, with the specific formula:l, a, b are the color values of the pixels (Lab color space), x, y are the spatial coordinates of the pixels, +.>、/>、/>、/>、/>S is a normalization factor for balancing color and spatial distance;
step 3, calculating the average value of the pixels contained in each super pixel to obtain a new center, wherein the specific calculation formula is as follows:,/>,/>、/>is the new coordinates of the super pixel center, N is the number of pixels contained in the super pixel;
repeating the step 2 and the step 3 until the super pixel center is stable or reaches the preset iteration times;
it should be noted that the preset iteration number is set according to the actual situation.
Optional post-processing steps, such as merging too small super pixels to obtain more communicated super pixel segmentation results, visualizing the super pixel segmentation results, generating a super pixel map, and completing the pre-processing of the super pixels;
the fusion processing module is used for establishing a minimum spanning tree model taking super pixels as nodes according to a graph model theory, performing super pixel fusion on multiple scales to obtain a fusion image, combining a guide filtering technology with an image space projection screening method, and acquiring high-precision space measurement data from the fusion image through a target edge sharpening and space scale scaling algorithm;
taking the super pixels as nodes of a graph model, taking similarity measurement as the weight of edges, constructing an undirected graph, wherein the graph is used for representing the relation among the super pixels, and applying a minimum spanning tree algorithm, such as a Prim algorithm or a Kruskal algorithm, to find the minimum spanning tree for connecting all the super pixels;
each super pixel is regarded as an independent set, each set only comprises one super pixel, all edges are ordered according to the weight from small to large, and one edge is selected from the ordered edges. If the two super pixels connected by the edge are not in the same set, adding the two super pixels into the minimum spanning tree, and combining the two sets, wherein the specific steps are as follows:
for each edgeChecking if u and v are in the same set, implemented using a union data structure, u and v are side +.>Representing the two vertices at which the two edges connect;
if u and v are not in the same set, edges are formedAdding a minimum spanning tree, and then merging the sets where u and v are located;
repeating the steps until the minimum spanning tree contains all super pixels;
in the Kruskal algorithm, a merge-look-up operation is used to maintain a set, and a look-up typically includes two main operations:
searching: searching a set where the elements are located, and checking whether the two elements belong to the same set;
combining: merging two sets for merging two different sets into one;
the final obtained set and the edge set of the minimum spanning tree are the minimum spanning tree, a minimum spanning tree model is built, and the final minimum spanning tree is ensured to be the shortest path for connecting all super pixels;
the time complexity of ordering all edges isWhere E is the number of edges and the operational complexity of the search is typically +.>Where V is the number of superpixels, the overall temporal complexity isThe spatial complexity of the union is +.>;
And performing superpixel fusion on multiple scales to obtain a fusion image, and performing superpixel fusion according to the established minimum spanning tree model, namely giving different weights to the superpixels under different scales, and then weighting and merging the superpixels to obtain a final fusion result. The weight can be set according to the importance of the scale, and can be dynamically adjusted through local features of the image;
the super-pixel segmentation results under different scales are respectively regarded as different layers, fusion is carried out layer by layer, and the information of each scale is reserved;
decomposing an image into sub-images with different scales by utilizing the thought of an image pyramid, performing super-pixel segmentation on each scale, and then fusing layer by layer through a pyramid structure to synthesize information on different scales;
mapping the fused super-pixel result back to an image space to generate a fused image, wherein the fused image retains the structural information of the original image and reduces noise and redundant information;
combining a guide filtering technology with an image space projection screening method, using the guide filtering technology, combining an original image and a fusion image, and filtering the image, namely adjusting the pixel value of a target image through local statistical information of the guide image so as to achieve a smoothing effect, wherein the guide image is usually the original fusion image, and the target image is an image needing smoothing;
the image space projection screening method is applied to obtain high-precision space measurement data, and the geometric information of the target is obtained by carrying out space projection and screening on the fused image, specifically:
acquiring an original image to be processed, wherein the image contains a target object, if a guide image exists, the guide image can be used as auxiliary information to help to extract the spatial characteristics of the target object, a color image is converted into a gray image so as to simplify the processing, the image is subjected to denoising operation so as to reduce the influence of interference on spatial measurement, and key feature points in the image are found by using a feature point detection algorithm (such as Harris corner detection, SIFT, SURF and the like);
performing space matching by using characteristic points in the image, and determining the position and the gesture of the target object in the image;
according to the feature points and the camera parameters obtained by matching, performing space three-dimensional reconstruction to obtain coordinates of the target object in space;
further processing the reconstructed three-dimensional data by adopting a space projection screening method to obtain space measurement data, wherein the space measurement data comprises information such as the position, the posture and the like of a target;
harris corner detection is an algorithm for detecting corners in an image, the corners are identified by calculating the change of local gradients of the image, and the following are the detailed steps of Harris corner detection:
first, the image is smoothed, and then the image is calculated in the horizontal directionAnd vertical direction->A gradient over the surface. For example, by using a Sobel or the like filter;
calculating image gradient, enhancing edge characteristics of the target through a target edge sharpening algorithm to enable the edge of the target to be clearer, and adjusting the scale of the image by using a spatial scale scaling algorithm to adapt to different application requirements;
a structural matrix is calculated, the structural matrix M being used to describe the distribution of the local gradients of the image. For each pixel pointThe structural matrix is defined as follows: />;
The corresponding function R of the corner point is calculated,,/>,wherein->Is a determinant of matrix M->Is the trace of matrix M, and k is an empirical parameter typically ranging from 0.04 to 0.06;
setting a response threshold and non-maximum suppression: and marking the pixel points with the response function R larger than the threshold value as potential corner points by setting a threshold value, and carrying out non-maximum suppression on the corresponding fusion image for the redundant corner points, and reserving the local maximum value as a final corner point.
The method comprises the steps of obtaining high-precision space measurement data from a fusion image through a target edge sharpening algorithm and a space scaling algorithm, wherein the target edge sharpening is an image processing technology, performing convolution operation on the fusion image by using a Sobel operator to calculate gradients, further monitoring and sharpening the edges of the image, enabling the edges of the image to increase characteristics, improving edge definition, then using the space scaling algorithm to adjust the scale of the image, adjusting the scale of the image in image processing to be larger or smaller, and selecting a proper space scaling algorithm according to actual conditions, wherein the spatial scaling algorithm comprises nearest interpolation, bilinear interpolation, bicubic interpolation and the like.
The simulation analysis module is used for importing the acquired space measurement data into a simulation analysis model, and analyzing the characteristics of various aspects of the wire in the paying-off process through simulation to obtain wire characteristic data;
the obtained high-precision space measurement data are imported into a collection model of the wire body, the material properties and the section properties of the wire body are combined, the mechanical properties and the stress characteristics of different voltage grades of historical similar lines and different types of power transmission lines are combined, then the influence mechanism conditions of the lines are analyzed according to different meteorological conditions, tower spacing, height differences, electromagnetic effects of adjacent wires and the like, a wire body stress and sag simulation method analysis model is established by using ANSYS finite element analysis software, a gray wolf algorithm is embedded in the ANSYS, and the wire body stress and sag are rapidly solved;
specifically, discrete meshing is carried out on the wire body, a finite element mesh is established, loading conditions of the corresponding wire body, namely the application force or traction of the wire body by a tractor, boundary conditions are set, the loading conditions comprise support points of the wire body and fixed conditions at the boundary, ANSYS is operated to carry out statics or dynamics finite element analysis on the wire body, relevant results such as stress distribution, bending moment and the like of the wire body under different loading and boundary conditions are obtained, a gray wolf algorithm is embedded into the finite element analysis, an objective function of the gray wolf algorithm is defined, parameters which need to be optimized such as the stress, the sag and the like of the wire body are set, parameters such as population size, iteration times and the like of the gray wolf algorithm are set, typical stress and sag distribution characteristics of various wire bodies are summarized through simulation, estimated values are set for the stress analysis, sag and wire body length boundary of the wire body in the actual paying-off process, and the paying-off process is analyzed according to the estimated values.
The strategy management module is used for establishing paying-off construction information according to the plurality of dimensional data, determining construction safety conditions of various indexes by combining simulation analysis results, and adjusting a control strategy in the paying-off process according to safety feedback during paying-off.
In paying-off operation, the wire body is continuously dynamically and non-uniformly paid-off all the time under the action of the traction machine, and under the influence of the environmental variable factor of paying-off and the wire body dead weight, the wire is especially arranged on a continuous gear rack with large height difference and large gear distance, so that the wire body length of each gear distance is difficult to accurately calculate, the wire body sag, angle and stress conditions of some gear distances are not in accordance with the safety requirements, and hidden danger can be buried for subsequent paying-off and operation.
The method comprises the steps that a strategy management module acquires paying-off construction information in a paying-off process, wherein the paying-off construction information comprises equipment offset information, simulation accurate information and efficiency fluctuation information;
the equipment offset information comprises a transmission image processing stability index and is calibrated to be CST, the simulation accurate information comprises a monitoring error floating value and is calibrated to be JCW, and the efficiency fluctuation information comprises a value frequency variation index and is calibrated to be QZP;
the transmission image processing stability index in the equipment offset information plays an important role in analyzing the paying-off process, the transmission image processing stability index refers to the transmission stability condition of the fusion image which is acquired in the paying-off process and transmitted to the simulation model for analysis, and the transmission image processing stability index plays a role in the following aspects:
accuracy of data: important data for analysis are contained in the fusion image, and data loss or distortion is easily caused by unstable transmission, so that accuracy analysis on the paying-off state of the power transmission line is affected;
response real-time: in the paying-off process, the real-time performance is crucial to monitoring and control, and the instability of transmission causes delay, so that the real-time performance is reduced, and the influence on timely adjusting the state of a wire body or performing safety control is caused;
monitoring and early warning: for the scene needing real-time monitoring and early warning, the response of the early warning system becomes unreliable due to unstable image transmission, and the timely identification capability of potential problems is reduced.
The acquisition logic for the transmission image processing stability index is as follows:
acquiring bandwidth data volume DK used by image acquisition device to transmit image to receiving deviceThe transmission time length SC required for transmitting the image is calculated to obtain a bandwidth measurement value:the method comprises the steps of obtaining the packet loss rate PL by dividing the number of data packets received by a receiving device by the number of data packets totally transmitted by an image acquisition device, obtaining the transmission duration DL by subtracting the data packet transmission time from the data packet receiving time, and calculating the transmission quality value: />The difference between the start and end stage recording time stamps of the image processing is acquired as processing time CL, and a transmission stability value is calculated: />Calculating to obtain a transmission image processing stability index, wherein the calculated expression is as follows: />。
It should be noted that, bandwidth measurement, packet loss rate, transmission delay, and the like generally need to be acquired by using a network monitoring tool and related protocols, and a common network monitoring tool, such as iperf, speedtest, may be used to acquire related data.
The monitoring error floating value in the simulation accurate information refers to the error floating condition between the actual monitoring value and the simulation value in the simulation analysis process, and when the simulation analysis is carried out on related parameters in the paying-off process, due to the reasons of simplification of a model, change of environmental factors, sensor precision and the like, a certain deviation exists between the simulation value and the actual monitoring value, and the monitoring error floating value has an influence on the following aspects:
decision support: in the paying-off process, an accurate simulation result is very important for decision making, and the consideration of the monitoring error floating value can help a decision maker to understand the reliability of simulation more comprehensively, so that the decision making and planning can be made more accurately;
model calibration and optimization: the monitoring error floating value reflects the inconsistency between the simulation model and the actual situation, and the problems in the model can be identified, calibrated and optimized by analyzing the error floating value, so that the accuracy and the reliability of the model are improved.
The acquisition logic for the monitored error float value is as follows:
acquiring data of an actual monitoring value and a simulation value, calculating an error between the actual monitoring value and the simulation value for each monitoring data point, counting the error of each monitoring data point and establishing an error set, wherein the error = the actual monitoring value-the simulation value:m is a positive integer, and a monitoring error mean value is obtained>Calculating a monitoring error floating value, wherein the calculation expression is as follows: />。
It should be noted that, the collected data may include sensor measurement, field monitoring data, and simulation data generated in the simulation process, where the monitoring data point refers to the simulation data in the monitoring process that analyzes the data at the corresponding time point and the actual data at the corresponding time point.
The value frequency variation index in the efficiency fluctuation information refers to the condition of acquiring frequency of acquiring an analysis result by performing real-time simulation analysis in the paying-off process, and the value frequency variation index can play a role in the following aspects:
consistency of analysis result acquisition: if the value frequency variation index is lower, the frequency of the real-time simulation analysis in the paying-off process is relatively stable, and the acquisition consistency of the analysis result is high;
simulation efficiency fluctuation conditions: the higher value frequency variation index reflects the fluctuation condition of simulation efficiency, and frequent fluctuation means that the acquisition frequency of analysis results is higher in some time periods, the data change is quicker, and the data is unstable in the paying-off process.
The acquisition logic of the value frequency variation index is as follows:
obtaining imitation in each unit timeTime series data of true analysis result, establishing a time series data set, acquiring the update frequency of data in the time series data set, and establishing a data update frequency setW is a positive integer, and the update frequency mean value +.>And standard deviationThe kernel density of the data updating frequency set is calculated, and the calculation formula is as follows:h represents a time span, and the value density value is obtained through calculation:and establishes the Density function value set +.>F is a positive integer, a value frequency variation index is calculated, and the calculated expression is: />。
It should be noted that, the time length is set according to the actual requirement in a unit time, for example, the time length is 1 minute, 1 hour, etc., the update frequency of the data refers to the case of updating the relevant data, the ratio of the time to the update times is obtained, the kernel function describes the probability distribution of the data on different values, and the time span is usually selected by using a method of cross-validation, etc. to represent the whole probability density.
The equipment offset information, the simulation accurate information and the efficiency fluctuation information are simultaneously generated to generate a perception evaluation coefficient, and the perception evaluation coefficient is transmitted to a fusion processing module;
the obtained stable index CST of the transmission image processing, the floating value JCW of the monitoring error and the frequency variation of the valueThe index QZP is normalized to generate a perception evaluation coefficient, and the perception evaluation coefficient is calibrated asOne expression for example is: />Wherein->For the perception evaluation coefficient +.>、/>、/>Processing the preset scaling factors of the stability index CST, the monitoring error floating value JCW and the value frequency variation index QZP for transmitting the image, and、/>、/>are all greater than 0.
It should be noted that, the size of the preset scaling factor is a specific numerical value obtained by quantizing each parameter, and in order to facilitate the subsequent comparison, the size of the scaling factor depends on the number of sample data and the person skilled in the art to initially set a corresponding preset scaling factor for each group of sample data; and the method is not unique, and only the proportional relation between the parameter and the quantized numerical value is not influenced, for example, the proportional relation between the image processing stability index and the perception evaluation coefficient is transmitted.
The formula shows that the larger the transmission image processing stability index is, the larger the monitoring error floating value is, the larger the value frequency variation index is, namely the larger the expression value of the perception evaluation coefficient is, the probability of paying off real-time problems in paying off is high, the situation that the real-time problems do not accord with expected standards easily occurs when paying off is indicated, the smaller the transmission image processing stability index is, the smaller the monitoring error floating value is, the smaller the value frequency variation index is, namely the smaller the expression value of the perception evaluation coefficient is, the probability of paying off real-time problems in paying off is low, and the paying off real-time problems are not easy to occur.
Determining the safety condition of each index by combining simulation analysis results;
comparing the generated perception evaluation coefficient with a safety threshold value to generate a low safety standard signal and a high safety coincidence signal;
after the perception evaluation coefficient is obtained, comparing the perception evaluation coefficient with a safety threshold;
if the perception evaluation coefficient is greater than or equal to the safety threshold, a low safety standard signal is generated, which indicates that the real-time condition Kuang Jiaocha of the paying-off process is easy to cause safety problems, multiple verification is needed, and paying-off is determined to meet real-time requirements;
and if the perception evaluation coefficient is smaller than the safety threshold, generating a high-safety coincidence signal, wherein the high-safety coincidence signal indicates that the current paying-off construction process is in a normal state.
The strategy management module adjusts a control strategy in the paying-off process according to the safety feedback during paying-off, and specifically comprises the following steps:
the strategy management module receives the low-safety standard signal and then carries out intelligent control adjustment on paying-off;
analyzing the paying-off process of the generated low-safety standard signal, continuously acquiring the perception evaluation coefficients in real time, establishing a data set, calculating the mean value and the standard deviation in the data set to obtain the outlier degree value of each perception evaluation coefficient, and determining whether the paying-off process of the generated low-safety standard signal frequently has the problem of poor real-time accuracy;
calculating the mean value and standard deviation of the perception evaluation coefficients in the data set;
for each data, calculating the deviation value of the mean value of the data set to obtain an outlier degree value, wherein the specific formula for obtaining the outlier degree value is as follows:wherein->Data points within the data set +.>For mean value->Is the standard deviation;
comparing the outlier degree value of the data in the data set with a set outlier threshold, when the outlier degree value of the data in the data set is larger than the discrete threshold, indicating that the perceived evaluation coefficient is too large in outlier degree, taking the data as outliers and recording, and when the number of the outliers is larger than or equal to the set number threshold, judging that problems occur in paying-off construction and needing tracing processing.
Based on the type of the simulation analysis data, corresponding tracing is carried out, for example, the length and sag of the wire to the wire body are influenced by the hooking state of the tension insulator, and then real-time data acquisition is carried out on the tension insulator hooked by the wire again and is used as reference data for subsequent simulation analysis.
Furthermore, the intelligent paying-off system can be upgraded by combining with the actual paying-off construction requirement, and the hardware part of the intelligent paying-off system comprises an unmanned plane, a high-reliability signal transmission base station, a real-time analysis terminal, a controller and a protective pulley, wherein the real-time analysis terminal and the controller are high in computing performance, large in storage capacity and convenient to carry; the software part meets the requirements of friendly interface, convenient operation and open interface, has the secondary development function, and the whole system can realize the functions of real-time collection of data, active risk early warning and automatic paying-off control under various scenes, thereby improving paying-off construction efficiency and site safety level.
The threshold information in this embodiment is preset by a professional, and is not explained here too much.
According to the invention, the acquired image information of the power transmission line is taken, the image is subjected to super-pixel segmentation pretreatment, the guided filtering technology is combined with the image space projection screening method, the high-precision space measurement data are acquired, the paying-off construction information is established according to the plurality of dimension data, the safety condition of each index is determined by combining simulation analysis results, the paying-off intelligent control strategy is adjusted according to the safety feedback during paying-off, the problem of insufficient ageing accuracy of line length calculation under dynamic conditions is solved, and the safety risk in the paying-off process is reduced.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product.
Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (5)
1. Intelligent paying-off system based on multidimensional sensing technology, and is characterized in that: the system comprises a multidimensional information acquisition module, a fusion processing module, a simulation analysis module and a strategy management module, wherein the modules are connected through signals;
the multidimensional information acquisition module is used for acquiring acquired transmission line image information and carrying out super-pixel segmentation pretreatment on the image;
the fusion processing module is used for establishing a minimum spanning tree model taking super pixels as nodes according to a graph model theory, performing super pixel fusion on multiple scales to obtain a fusion image, combining a guide filtering technology with an image space projection screening method, and acquiring high-precision space measurement data from the fusion image through a target edge sharpening and space scale scaling algorithm;
the simulation analysis module is used for importing the acquired space measurement data into a simulation analysis model, and analyzing the characteristics of various aspects of the wire in the paying-off process through simulation to obtain wire characteristic data;
the strategy management module is used for establishing paying-off construction information according to the plurality of dimensional data, determining construction safety conditions of various indexes by combining simulation analysis results, and adjusting a control strategy in the paying-off process according to safety feedback during paying-off;
in the multidimensional information acquisition module, the step of carrying out super-pixel segmentation preprocessing on the image comprises the following steps:
denoising, brightness adjustment and color correction are carried out on the acquired power transmission line image, and super-pixel segmentation is carried out on the power transmission line image;
selecting the number density of super pixels and an initial center point in a color space for initialization;
calculating an average value of the pixels for each super pixel to obtain a new center;
calculating the distance between each pixel and the center of all the super pixels, and repeating until the super pixels reach the iteration times;
establishing a minimum spanning tree model taking super pixels as nodes according to a graph model theory, and performing super pixel fusion on multiple scales to obtain a fusion image, wherein the method comprises the following specific steps of:
taking the superpixels as nodes of a graph model, taking similarity measurement as the weight of edges, constructing an undirected graph, wherein the undirected graph is used for representing the relation among the superpixels, and applying a minimum spanning tree algorithm to connect the minimum spanning trees of all the superpixels;
regarding each super pixel as an independent set, wherein each set only comprises one super pixel, sorting all edges according to the weight from small to large, selecting one edge from the sorted edges, adding the selected edge into a minimum spanning tree if two super pixels connected with the selected edge are not in the same set, and merging the two sets until the minimum spanning tree comprises all the super pixels;
using Kruskal algorithm, merging and searching the sets through merging, taking the finally obtained set and the edge set of the minimum spanning tree as the minimum spanning tree, and establishing a minimum spanning tree model, wherein the minimum spanning tree is connected with the shortest paths of all super pixels;
performing superpixel fusion on multiple scales to obtain a fusion image, performing superpixel fusion according to the established minimum spanning tree model, giving weights to superpixels under different scales, and performing weighted combination to obtain a final fusion result, wherein the specific process is as follows:
taking the super-pixel segmentation results under different scales as different layers, fusing the super-pixel segmentation results layer by layer, and reserving information of each scale;
decomposing an image into sub-images with different scales by using the thought of an image pyramid, performing super-pixel segmentation on each scale, fusing layer by layer through a pyramid structure, and synthesizing information on different scales;
mapping the fused super-pixel result back to an image space to generate a fused image, wherein the fused image retains the structural information of the original image;
combining a guided filtering technology with an image space projection screening method, and acquiring high-precision space measurement data from a fused image through a target edge sharpening and space scale scaling algorithm, wherein the method comprises the following specific steps of:
adjusting pixel values of the target image according to the local statistical information of the guide image;
performing space matching by using characteristic points in the image, and determining the position and the gesture of the target object in the image;
carrying out space three-dimensional reconstruction according to the feature points obtained by matching to obtain coordinates of the target object in space;
processing the reconstructed three-dimensional data by adopting a space projection screening method, identifying angular points by calculating the change of local gradients of the image, and obtaining space measurement data according to the angular points;
and carrying out convolution operation on the fusion image to calculate gradients, and sharpening the image edges according to the calculated gradients.
2. The intelligent pay-off system based on multidimensional sensing technology as recited in claim 1, wherein: setting up paying-off construction information according to a plurality of dimension data, and determining the construction safety condition of each index by combining simulation analysis results, wherein the paying-off construction information comprises the following steps:
acquiring paying-off construction information in a paying-off process, wherein the paying-off construction information comprises equipment offset information, simulation accurate information and efficiency fluctuation information;
the equipment offset information comprises a transmission image processing stability index, the simulation accurate information comprises a monitoring error floating value, and the efficiency fluctuation information comprises a value frequency variation index;
and generating a perception evaluation coefficient by combining the transmission image processing stability index in the equipment offset information, the monitoring error floating value in the simulation accurate information and the value frequency variation index in the efficiency fluctuation information.
3. The intelligent pay-off system based on multidimensional sensing technology as recited in claim 2, wherein: the image processing stability index, the monitoring error floating value and the value frequency variation index are transmitted to form a proportional relation with the perception evaluation coefficient.
4. The intelligent pay-off system based on multidimensional sensing technology as recited in claim 3, wherein: according to the safety feedback during paying off, adjusting a control strategy in the paying off process, comprising:
comparing the perception evaluation coefficient with a safety threshold;
if the perception evaluation coefficient is greater than or equal to the safety threshold value, generating a low safety standard signal;
and if the perception evaluation coefficient is smaller than the safety threshold value, generating a high safety coincidence signal.
5. The intelligent pay-off system based on multidimensional sensing technology as recited in claim 4, wherein: the strategy management module adjusts the control strategy in the paying-off process according to the safety feedback during paying-off, and the method further comprises the following steps:
analyzing the paying-off process of the generated low-safety standard signal, acquiring the perception evaluation coefficients in real time, establishing a data set, and calculating the mean value and standard deviation in the data set to obtain the outlier degree value of each perception evaluation coefficient;
calculating the deviation value of the mean value of the data elements in the data set to obtain an outlier degree value;
and comparing the outlier degree value of the data in the data set with a set outlier threshold, taking the data as outliers and recording when the outlier degree value of the data in the data set is larger than a discrete threshold, and performing tracing processing when the number of the outliers is larger than or equal to the set number threshold.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311586814.3A CN117291443B (en) | 2023-11-27 | 2023-11-27 | Intelligent paying-off system based on multidimensional sensing technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311586814.3A CN117291443B (en) | 2023-11-27 | 2023-11-27 | Intelligent paying-off system based on multidimensional sensing technology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117291443A CN117291443A (en) | 2023-12-26 |
CN117291443B true CN117291443B (en) | 2024-02-13 |
Family
ID=89252141
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311586814.3A Active CN117291443B (en) | 2023-11-27 | 2023-11-27 | Intelligent paying-off system based on multidimensional sensing technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117291443B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118282777B (en) * | 2024-05-31 | 2024-08-16 | 环球数科集团有限公司 | Data safety transmission system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101266164B1 (en) * | 2013-01-15 | 2013-05-21 | (주)선운 이앤지 | Measuring system for insuring safety distenance of overhead transmission line and its method for producing 3d simulation |
CN111340826A (en) * | 2020-03-25 | 2020-06-26 | 南京林业大学 | Single tree crown segmentation algorithm for aerial image based on superpixels and topological features |
CN112164004A (en) * | 2020-09-14 | 2021-01-01 | 武汉大学 | Color correction method for jointly optimizing global and local color consistency |
CN112465401A (en) * | 2020-12-17 | 2021-03-09 | 国网四川省电力公司电力科学研究院 | Electric power operation safety control system based on multi-dimensional information fusion and control method thereof |
CN113962830A (en) * | 2021-11-15 | 2022-01-21 | 国网辽宁省电力有限公司营口供电公司 | Intelligent three-dimensional protection management system based on multi-fusion processor control module |
CN114139326A (en) * | 2021-12-08 | 2022-03-04 | 国网陕西省电力有限公司建设分公司 | Three-dimensional GIS-based transmission line tension paying-off simulation system |
WO2022121060A1 (en) * | 2020-12-12 | 2022-06-16 | 浙江工业大学之江学院 | Visual perception three-dimensional reconstruction technology-based fire intelligent early warning system and method |
CN115455802A (en) * | 2022-07-29 | 2022-12-09 | 国网浙江省电力有限公司电力科学研究院 | Low-voltage distribution network modeling based on data driving and visualization method thereof |
-
2023
- 2023-11-27 CN CN202311586814.3A patent/CN117291443B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101266164B1 (en) * | 2013-01-15 | 2013-05-21 | (주)선운 이앤지 | Measuring system for insuring safety distenance of overhead transmission line and its method for producing 3d simulation |
CN111340826A (en) * | 2020-03-25 | 2020-06-26 | 南京林业大学 | Single tree crown segmentation algorithm for aerial image based on superpixels and topological features |
CN112164004A (en) * | 2020-09-14 | 2021-01-01 | 武汉大学 | Color correction method for jointly optimizing global and local color consistency |
WO2022121060A1 (en) * | 2020-12-12 | 2022-06-16 | 浙江工业大学之江学院 | Visual perception three-dimensional reconstruction technology-based fire intelligent early warning system and method |
CN112465401A (en) * | 2020-12-17 | 2021-03-09 | 国网四川省电力公司电力科学研究院 | Electric power operation safety control system based on multi-dimensional information fusion and control method thereof |
CN113962830A (en) * | 2021-11-15 | 2022-01-21 | 国网辽宁省电力有限公司营口供电公司 | Intelligent three-dimensional protection management system based on multi-fusion processor control module |
CN114139326A (en) * | 2021-12-08 | 2022-03-04 | 国网陕西省电力有限公司建设分公司 | Three-dimensional GIS-based transmission line tension paying-off simulation system |
CN115455802A (en) * | 2022-07-29 | 2022-12-09 | 国网浙江省电力有限公司电力科学研究院 | Low-voltage distribution network modeling based on data driving and visualization method thereof |
Non-Patent Citations (5)
Title |
---|
Engineering simulation for loadout of a tension leg platform;S.K.Sinha;《Offshore technology conference 》;第1-10页 * |
基于超像素融合算法的显著区域检测;王海罗;汪渤;周志强;李笋;踪华;;北京理工大学学报(第08期);第836-841页 * |
基于部分线段图像识别的悬链线弧垂实测方法;池小兵;黄阳垚;黄景标;莫枝阅;;科技创新与应用(第36期);第60-62页 * |
容和层次聚类的高分辨率遥感图像超像素分割方法;黄亮 等;《红外与毫米波学报》;第263-272页 * |
张力架线计算及动态仿真软件系统架构设计;王杰;;科技资讯(第30期);第23-27页 * |
Also Published As
Publication number | Publication date |
---|---|
CN117291443A (en) | 2023-12-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110378196B (en) | Road visual detection method combining laser point cloud data | |
CN108256446B (en) | Method, device and equipment for determining lane line in road | |
CN113902897B (en) | Training of target detection model, target detection method, device, equipment and medium | |
CN112001958B (en) | Virtual point cloud three-dimensional target detection method based on supervised monocular depth estimation | |
CN117291443B (en) | Intelligent paying-off system based on multidimensional sensing technology | |
CN111033318A (en) | Local weather prediction | |
CN116719339A (en) | Unmanned aerial vehicle-based power line inspection control method and system | |
CN109726739A (en) | A kind of object detection method and system | |
CN115240087A (en) | Tree barrier positioning analysis method and system based on binocular stereo vision and laser point cloud | |
CN118279876B (en) | Automatic obstacle avoidance method and system for cleaning vehicle based on image processing | |
CN114556445A (en) | Object recognition method, device, movable platform and storage medium | |
CN117809297B (en) | Three-dimensional reconstruction-based intelligent identification method for dangerous source of power transmission line | |
CN116311218A (en) | Noise plant point cloud semantic segmentation method and system based on self-attention feature fusion | |
CN117406027A (en) | Distribution network fault distance measurement method and system | |
CN111354028A (en) | Binocular vision-based power transmission channel hidden danger identification and tracking method | |
CN113096039A (en) | Depth information completion method based on infrared image and depth image | |
CN106846325B (en) | Automatic method for determining optimal segmentation result of remote sensing image | |
CN111598097B (en) | Instrument position and reading identification method and system based on robot vision | |
CN117475309A (en) | Method, system, equipment and medium for monitoring edible biomass on grassland | |
JP6950647B2 (en) | Data determination device, method, and program | |
CN112733584A (en) | Intelligent alarm method and device for communication optical cable | |
CN116612430A (en) | Method for estimating water level by utilizing video monitoring system based on deep learning | |
CN118501895B (en) | Intelligent mapping method and system based on laser detection | |
CN118351491B (en) | Line operation and maintenance monitoring method and system based on image recognition | |
CN118351469B (en) | Vision-based vehicle positioning method under road side view angle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |