CN115542362A - High-precision space positioning method, system, equipment and medium for electric power operation site - Google Patents
High-precision space positioning method, system, equipment and medium for electric power operation site Download PDFInfo
- Publication number
- CN115542362A CN115542362A CN202211524412.6A CN202211524412A CN115542362A CN 115542362 A CN115542362 A CN 115542362A CN 202211524412 A CN202211524412 A CN 202211524412A CN 115542362 A CN115542362 A CN 115542362A
- Authority
- CN
- China
- Prior art keywords
- positioning
- power operation
- uwb
- model
- moving target
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000000007 visual effect Effects 0.000 claims abstract description 56
- 238000005516 engineering process Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000010191 image analysis Methods 0.000 claims abstract description 5
- 238000007670 refining Methods 0.000 claims abstract description 4
- 238000005259 measurement Methods 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 230000004927 fusion Effects 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000004807 localization Effects 0.000 claims description 6
- 125000004432 carbon atom Chemical group C* 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000005477 standard model Effects 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 description 12
- 238000012423 maintenance Methods 0.000 description 11
- 238000012360 testing method Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000004088 simulation Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000001815 facial effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- JXASPPWQHFOWPL-UHFFFAOYSA-N Tamarixin Natural products C1=C(O)C(OC)=CC=C1C1=C(OC2C(C(O)C(O)C(CO)O2)O)C(=O)C2=C(O)C=C(O)C=C2O1 JXASPPWQHFOWPL-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/46—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being of a radio-wave signal type
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a high-precision space positioning method, a high-precision space positioning system, high-precision space positioning equipment and a high-precision space positioning medium for an electric power operation site, which belong to the technical field of space positioning and comprise the steps of obtaining the positioning of an electric power operation moving target based on a visual positioning technology; according to the positioning of the power operation moving target, carrying out image analysis on the power operation moving target to obtain characteristic information of the power operation moving target and constructing a three-dimensional model of the power operation moving target; and refining the three-dimensional model of the power operation moving target according to the characteristic information to obtain a high-precision three-dimensional model and updating the positioning of the high-precision three-dimensional model in a three-dimensional scene in real time. By matching UWB or Beidou positioning tags on the dynamic targets, image processing is carried out on the basis of positioning of the moving targets, fine reconstruction of the moving targets in a three-dimensional scene is achieved, and therefore real-time position information of the dynamic targets is obtained and the position state of a dynamic target model is updated in the three-dimensional scene in real time.
Description
Technical Field
The invention relates to the technical field of space positioning, in particular to a high-precision space positioning method, a high-precision space positioning system, high-precision space positioning equipment and high-precision space positioning media for an electric power operation site.
Background
The research of vision-based target detection, identification and tracking algorithm is a hot spot in the field of artificial intelligence, and great progress is made along with the wide application of deep learning in recent years. The deep learning technology is gradually applied to an electric power production environment, and recognition of some targets such as insulators, overhead arcs, transformer substation foreign bodies and equipment temperature is achieved, however, transformer substation scenes are complex, and key target recognition of all links of electric power operation needs to be deeply researched.
The fusion of real scene video information into a three-dimensional virtual model is a branch of virtual reality technology, or a development stage of virtual reality. The three-dimensional video fusion technology is used for matching and fusing one or more videos of a camera image sequence and a three-dimensional virtual scene related to the videos to generate a new dynamic virtual scene or model related to the scene, so that the fusion of the virtual scene and a real-time video is realized. The three-dimensional video fusion technology can realize the fusion application of resources such as small-range or local three-dimensional scenes and videos by relying on an independent three-dimensional engine, and can also realize the visual fusion application of three-dimensional geographic information in a global wide-area range by relying on a three-dimensional geographic information system.
In the electric power operation field, accurate and effective positioning of the position of an operator is an important basis for preventing accidents and guaranteeing the safety of workers. At present, the means for positioning the position of an operator on an electric power operation site is realized by adopting a GPS, a Beidou positioning system and a UWB positioning system, but the accurate spatial position information cannot be extracted only by depending on the GPS, the Beidou positioning system and the UWB positioning system, and meanwhile, the problems of shielding, target posture change, illumination and the like exist on the electric power operation site, and the positioning of an operation target on the electric power operation site can also be influenced.
In summary, the research on the vision-based target detection, recognition and tracking algorithm has made a certain research progress, but how to deal with the influence of the problems such as occlusion, target posture change, illumination and the like is still the focus of the research. The video image data processed by the existing visual positioning algorithm is the projection of a target from a three-dimensional space to a two-dimensional space, and accurate spatial position information cannot be extracted.
The problems of the prior art are as follows:
the video image data processed by the existing visual positioning algorithm for the power operation site is the projection of a target from a three-dimensional space to a two-dimensional space, and accurate space position information of the three-dimensional space cannot be extracted.
Disclosure of Invention
The technical problem to be solved by the application is that video image data processed by the existing visual positioning algorithm for the electric power operation field is the projection of a target from a three-dimensional space to a two-dimensional space, and accurate spatial position information of the three-dimensional space cannot be extracted.
The application is realized by the following technical scheme:
a first aspect of the present application provides a high-precision spatial positioning method for an electric power operation site, comprising
S1, acquiring the positioning of a power operation moving target based on a visual positioning technology; the UWB auxiliary visual positioning technology is adopted for indoor electric power operation moving targets, and the Beidou auxiliary visual positioning technology is adopted for outdoor electric power operation moving targets; the UWB-assisted visual positioning technology comprises UWB-assisted passive video positioning;
s2, carrying out image analysis on the power operation moving target according to the positioning of the power operation moving target to obtain characteristic information of the power operation moving target and construct a three-dimensional model of the power operation moving target;
and S3, refining the three-dimensional model of the power operation moving target according to the characteristic information to obtain a high-precision three-dimensional model and updating the positioning of the high-precision three-dimensional model in the three-dimensional scene in real time.
In above-mentioned technical scheme, adopt UWB to indoor electric power operation moving object to assist visual positioning technique, adopt big dipper to assist visual positioning technique to outdoor electric power operation moving object, through combining together UWB location technique, big dipper location technique and visual positioning technique simple, can acquire the location of electric power operation moving object in three-dimensional space, reduce electric power operation scene and disturb, shelter from the scheduling problem to realize centimetre level location. The UWB tag or the Beidou positioning tag is worn on the electric power operation moving target, the moving target is subjected to image analysis on the basis of moving target positioning, fine reconstruction of the moving target in a three-dimensional scene is achieved, real-time position information of the moving target is obtained, the position state of a moving target model is updated in the three-dimensional scene in real time, and accurate positioning of the electric power operation moving target in a three-dimensional space is achieved.
In an alternative embodiment, the UWB-assisted passive video positioning method comprises:
positioning the power operation moving target through a binocular vision system formed by two cameras to obtain position information of the power operation moving target in space;
positioning the power operation moving target based on the UWB model to obtain UWB positioning information of the power operation moving target;
and integrating the position information of the power operation moving target in the space and the UWB positioning information of the power operation moving target to obtain the positioning of the power operation moving target.
In an alternative embodiment, the method for integrating the position information of the power operation moving object in the space and the UWB positioning information of the power operation moving object is as follows:
taking the position and the course measured by the binocular vision system and the position measured by the UWB model as observed values, and establishing a UWB/vision fusion observation equation; the UWB/visual fusion observation equation is as follows:
in the above formula, the first and second carbon atoms are,
representing the plane coordinates of the binocular vision system vision measurement,
representing the planar coordinates of the UWB measurements,
indicating the position measurement error of the binocular vision system,
indicating the error in the UWB position measurement,
denotes a deflection angle between plane coordinates measured by a binocular vision system and plane coordinates measured by UWB,
representing the intermediate matrix.
In an alternative embodiment, the UWB model is constructed as follows:
establishing an improved robust EKF model, and adopting the improved robust EKF model as a standard model of the UWB model;
judging whether the improved robust EKF model has gross errors or not by adopting a statistical method;
if gross error exists, calling the robust EKF model as an improved robust EKF model;
if gross error does not exist, the EKF model is invoked as a modified robust EKF model.
In an optional embodiment, the positioning method of the Beidou auxiliary visual positioning technology comprises the following steps:
acquiring an interested area based on a Kalman filtering model and a predicted position of an operation boundary line;
carrying out image edge detection on the region of interest to obtain a positioning region;
constructing a multi-view vision measurement model through a multi-view vision sensor, and constructing a multi-view vision coordinate in a positioning area through the multi-view vision measurement model;
optimizing the multi-view visual coordinate constructed in the positioning area through the multi-view visual measurement model based on a weighted LM algorithm to obtain an optimized multi-view visual coordinate;
based on the Beidou positioning technology, the optimized multi-view visual coordinate is converted into the coordinate of a global positioning system.
In an alternative embodiment, based on the kalman filter model, the method for dynamically acquiring the region of interest by the plurality of vision sensors is as follows:
predicting the current straight line position based on Kalman filtering to obtain a first dynamic region of interest;
and predicting a column number of the operation boundary line in the image coordinate based on a projection method, and obtaining a second dynamic region of interest by taking the column number as a reference and combining the current camera calling condition.
In an alternative embodiment, based on the weighted LM algorithm, the method for optimizing the multi-view vision coordinates constructed in the positioning area by the multi-view vision measurement model is as follows:
carrying out nonlinear optimization on image coordinates obtained after the object points are transformed to the ith multi-view vision sensor by adopting the minimized reprojection error;
normalizing the distance from the multi-view vision sensor to the object, and converting the reciprocal of the distance after normalization into a weighting factor;
and constructing an objective function through the weighting factors, and substituting the multi-view visual coordinates into the objective function to calculate to obtain optimized multi-view visual coordinates.
A second aspect of the present application provides a high-precision spatial positioning system for an electric power work site, comprising
The system comprises a UWB auxiliary video positioning module, a UWB auxiliary active video positioning module and a UWB module, wherein the UWB auxiliary active video positioning module is used for acquiring the positioning of a moving target of indoor electric power operation, and comprises an initialization unit for initializing an environmental image and IMU data, a vision/inertia combination unit for acquiring a vision coordinate and an ultra-wideband unit for acquiring the UWB coordinate;
the Beidou auxiliary visual positioning module is used for acquiring the positioning of an outdoor electric power operation moving target, and comprises a dynamic region of interest module used for reducing the extraction of environmental factors to an operation boundary line, a multi-view visual module used for constructing multi-view visual region coordinates and a Beidou positioning module used for converting the multi-view visual region coordinates into global positioning system coordinates.
A third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement a high-precision spatial localization method for an electric power job site when executing the program.
A fourth aspect of the present application provides a computer-readable storage medium having stored thereon a computer program for implementing a method for high-precision spatial localization of an electric power work site when executed by a processor.
Compared with the prior art, the application has the following advantages and beneficial effects:
the UWB or Beidou positioning tag is matched on the dynamic target, the image processing is carried out on the dynamic target on the basis of the positioning of the moving target, the fine reconstruction of the moving target in a three-dimensional scene is realized, the real-time position information of the dynamic target is obtained, the position state of a dynamic target model is updated in the three-dimensional scene in real time, and the error between the reconstructed dynamic model and the actual size is proved to be less than 1% through verification experiments.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings that are required in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and that those skilled in the art may also derive other related drawings based on these drawings without inventive effort. In the drawings:
fig. 1 is a schematic flowchart of a high-precision spatial positioning method for an electric power work site according to an embodiment of the present disclosure;
fig. 2 is a schematic diagram of coordinate transformation for multi-view vision integration Beidou positioning according to an embodiment of the present application;
FIG. 3 is a diagram illustrating an assisted navigation tracking result in a test field at a speed of 0.4m/s according to an embodiment of the present application;
FIG. 4 is a diagram illustrating an assisted navigation tracking result in a test field at a speed of 0.8m/s according to an embodiment of the present application;
fig. 5 is a graph of the result of assisted navigation tracking in a test field at a speed of 1.2m/s according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Example 1
The embodiment provides a high-precision space positioning method for an electric power operation site, wherein the flow of the method is shown in fig. 1, and the method comprises the following steps:
s1, acquiring positioning information of the power operation moving target based on a visual positioning technology.
The UWB auxiliary visual positioning technology is adopted for indoor electric power operation moving targets, and the Beidou auxiliary visual positioning technology is adopted for outdoor electric power operation moving targets; UWB-assisted visual positioning techniques include UWB-assisted active video positioning and UWB-assisted passive video positioning.
For the wearable device which is not configured with the visual system, the positioning of the moving target can be realized by combining a camera installed in a transformer substation with the UWB technology.
Wherein, an improved robust EKF model is adopted as a standard model of the UWB model.
In the improved robust EKF localization model, the robust EKF gain matrix is constructed as follows:
prediction residual
The following are:
In order to improve the positioning angle, a visual/UWB fusion EKF positioning model considering a visual scale factor and an initial direction is constructed, and the state and the measurement equation are respectively expressed as follows:
in the above-mentioned formula, the compound has the following structure,
and
respectively represent a state equation and a measurement equation,
and
are respectively covariance matrix
And
an independent, zero-mean, gaussian noise process,
is a state transition matrix and H is a matrix of distribution characteristics.
In the above formula, the first and second carbon atoms are,
，
which represents the coordinates of a plane or plane,
which is indicative of the speed of the pedestrian,
which represents the angle of the direction of movement,
the scale-scale ambiguity is expressed in terms of,
representing the deflection angle between the visually computed planar coordinates and the UWB computed planar coordinates.
According to the error equation of vision and UWB, the corresponding state model is:
if the visually measured position, heading, and UWB measured position are taken as observations, then the UWB/visual fusion observation equation can be expressed as:
in the above formula, the first and second carbon atoms are,
representing the plane coordinates of the binocular vision system vision measurement,
the planar coordinates of the UWB measurements are represented,
indicating the position measurement error of the binocular vision system,
indicating the error in the measurement of the UWB position,
representing the deflection angle between the plane coordinates measured by the binocular vision system and the plane coordinates measured by the UWB.
In an optional embodiment, for outdoor electric power operation moving targets, a Beidou auxiliary visual positioning technology can be adopted. The device is limited by Beidou positioning precision and movement and geographic environment of field operation construction equipment, meter-level precision positioning can be realized only by simply depending on Beidou positioning at present, and the centimeter-level precision positioning requirement of a dynamic power operation scene cannot be met. Therefore, the Beidou positioning technology and the multi-view vision auxiliary positioning technology are combined to provide positioning accuracy.
As shown in FIG. 2, the coordinate system in the figure is the coordinate system established after the iteration of the optimized weighted LM algorithm, and a point in the coordinate system is taken
Knowing a point on the driving routePIn that
The coordinates in the coordinate system are
G point is at
The coordinates in the coordinate system are
To do so byGEstablishing point as origin
Coordinate system, thenPIs stippled to
Coordinates in a coordinate system
Is composed of
Wherein, the first and the second end of the pipe are connected with each other,
the unit of the middle coordinate is pixel, from which the unit is lengthmCoordinates of (A), (B)x l ，y l )：
With fixed points on the cameraCEstablishing a coordinate system for the origin, which can be measuredCPoint to the groundGIs counted by a horizontal distance ofl 1 Is 2.5m, it is known thatPDotO c The coordinates in the coordinate system are:
construction machinery is installed big dipper and is decidedPosition navigation device, which can obtain vehicle control point by calculationMThe coordinate of the point in the geodetic plane coordinate system O is the coordinate of m and the heading angle of the vehicle. To be provided withMEstablishing coordinate system by taking point as originO m Fixed point on the measuring sum cameraO c A distance ofl 2 ，PIs spotted onO m The coordinates in the coordinate system are:
by means of a positioning systemMThe coordinates in the geodetic coordinate system O are (x w ，y w ) Obtained by calculationPCoordinates of the point in the world coordinate system (x o ，y o ) Namely:
in summary, a point on the route path is knownPImage coordinates of (a), (b)x p ，y p ) The coordinates of the GPS can be obtained (x o ，y o ) Namely:
wherein the content of the first and second substances,
is a matrix
，
Is a matrix
，
Is a matrix
，
Is a matrix
，
Is a matrix
。
In multi-view vision measurement systems, non-linear optimization is usually performed in a way that minimizes the reprojection error, i.e.
In the above formula:
representing the coordinates of the image obtained after the object point is transformed to the ith camera before adjustment,
and the coordinate of the image obtained after the adjusted object point is transformed to the ith camera is shown. When the parameters of each camera, the measurement environment and other factors are the same, the distance from the camera to the object point has obvious influence on imaging noise, and the farther the distance is, the higher the noise is, otherwise, the smaller the noise is. When designing an objective function, the reciprocal of the camera-to-object point distance is converted into a weighting factor, and meanwhile, in order to increase the comparability between different cameras, the distance information is normalized.
In the above formula, the first and second carbon atoms are,
in order to be a weighting factor, the weighting factor,
the distance of the object point o to the camera i,
is the coordinates of the point of the oi object,
coordinates of the ci camera. Thus, the final objective function is
Will be provided with
Substituting the target function and converting into equation system form to obtain
In the above formula x w 、y w 、z w A unit vector representing a three-dimensional space;
is a parameter coefficient, F ui 、F vi For the optimized sub-targeting function, u i ，v i Intermediate variables for iterative solution.
The calculation formula relates to
A derivative of (a), a derived Jacobian matrix of
In the above formula, the values in the Jacobian matrix J are respectively F ui 、F vi About x w 、y w 、z w The first partial derivative of the direction. By substituting the above formula into the following formula, the increment can be obtained
In the above equation, μ is the updated damping coefficient. Therefore, the coordinates constructed in the positioning area through the multi-view vision measurement model are optimized by adopting a weighted LM algorithm, and the specific calculation steps are as follows:
(1) Calculating an initial value of the coordinates of the object points according to an orthogonal projection method, setting an iteration termination constant to be e, an actual descending effect threshold to be epsilon, iteration times to be k, and initializing mu;
(2) Using information about the current estimated world coordinates of the object point and camera parameters
Solving a jacobian matrix J by the derivative of the equation, and calculating mu;
(3) Calculating an increment delta P;
(4) Calculating rho and evaluating the current descending effect;
(5) If ρ < ε, μ =0.5 μ, and returns to step (3), otherwise, continues to perform step (6);
(6) If it is
Or the number of iterations is greater than or equal tokStopping iteration and outputting the optimized result, otherwise, returning to the step (2) to enter the next iteration.
In order to analyze the real-time performance of the operation boundary line extraction algorithm, the present embodiment counts the image processing steps of 100 construction process pictures before and after the algorithm improvement and the average time of the whole image processing process, and the results are shown in the following table:
as can be seen from the data in the table above, the average processing time of each image is shortened from 0.176087s before algorithm improvement to 0.064547s, which is 63.3% shorter than the original processing time, and the processing time of the image after algorithm improvement can better meet the requirement of the navigation system on the image processing time.
The map of the result of the assisted navigation tracking in the field is shown in fig. 3 when the speed is 0.4m/s, and the result of the assisted navigation in the field plot when the speed is 0.4m/s is shown in the following table:
as can be seen from fig. 3 and the above table, when the construction machine performs the straight line work in the test site at a speed of 0.4m/s, the maximum lateral deviation is 6.5cm, the average value is 0.49cm, and the standard deviation is 3.05cm after the first work to the lateral deviation of 0 in the case where the initial deviation is 30 cm. The result shows that the system simulation track and the actual position of the construction machine converge by continuously updating Beidou positioning data and visual picture information under the condition of larger initial deviation in a test field. Along with the prolonging of the operation tracking time, the more stable the positioning precision of the simulation operation is, and the auxiliary navigation effect can well meet the requirements.
The map of the result of the assisted navigation tracking in the field is shown in fig. 4 when the speed is 0.8m/s, and the result of the assisted navigation in the field plot when the speed is 0.8m/s is shown in the following table:
as can be seen from fig. 4 and the above table, when the construction machine performs the straight line work in the test site at a speed of 0.8m/s, in the case where the initial deviation is 30cm, the maximum lateral deviation is 13.7cm, the average value is 0.82cm, and the standard deviation is 5.98cm after the first work to the lateral deviation of 0. And adjusting the pose of the construction machine under the condition of larger initial deviation, so that the construction machine walks according to the predicted track. The result shows that the system simulation track and the actual position of the construction machine converge by continuously updating Beidou positioning data and visual picture information under the condition of larger initial deviation in a test field. Along with the extension of the operation tracking time, the more stable the positioning precision of the simulation operation is, and the auxiliary navigation effect can well meet the design requirement.
The map of the result of the assisted navigation tracking in the field is shown in fig. 5 when the speed is 1.2m/s, and the result of the assisted navigation in the field plot when the speed is 0.8m/s is shown in the following table:
as can be seen from fig. 5 and the above table, when the construction machine performs the straight line work in the test site at a speed of 1.2m/s, the maximum lateral deviation is 19.2cm, the average value is 1.40cm, and the standard deviation is 7.06cm after the first work to the lateral deviation of 0 in the case where the initial deviation is 30 cm. The result can basically meet the design requirement of the auxiliary navigation, but small-range obvious fluctuation occurs in the auxiliary navigation process, and subsequent analysis through wheel marks is caused by brake steering of construction machinery in the form process, and the deviation does not influence the application effect of the Beidou imitation auxiliary visual positioning technology in the simulation system.
The field test result shows that when the construction machine respectively runs at the speeds of 0.4m/s, 0.8m/s and 1.2m/s for experiments, the maximum values of the transverse deviation are respectively 6.5cm, 13.7cm and 19.2cm, the average values of the deviation are respectively 0.49cm,0.87cm and 1.40cm, the standard deviation difference is respectively 3.05cm,5.98cm and 7.06cm, the positioning precision is higher than that of the positioning precision of the Beidou navigation which is only relied on, and the positioning precision requirement of the simulation system for assisting navigation under the electric power operation environment can be met.
And S2, performing image analysis on the positioned electric power operation moving target to obtain characteristic information of the electric power operation moving target and construct a three-dimensional model of the electric power operation moving target.
And a live-action three-dimensional model scanning technology, a point cloud fusion technology and a refined modeling technology are adopted to model various maintenance vehicles and operators, and the real structures and textures of the vehicles and the operators are restored. The maintenance vehicle models are named according to models, and a dynamic target fine model library is formed by the maintenance vehicle models and the operator models.
For the maintenance vehicle, the model code is identified through an image identification technology and is used as characteristic information.
Specifically, the steps are as follows:
A. and acquiring vehicle information from a real-time video stream image of the monitoring video in a dynamic acquisition mode.
B. And preprocessing collected inspection vehicle model code images such as noise filtering, contrast enhancement, image scaling and the like.
C. And detecting the license plate by adopting algorithms such as projection analysis, connected domain analysis, machine learning and the like according to the information such as the texture feature, the color feature, the shape feature and the like of the license plate. The projection analysis method is characterized in that the number of times of alternate appearance of license plate characters and the background is more than that of other parts, and the model code of the maintenance vehicle is positioned through projection analysis of images in the horizontal direction and the vertical direction.
And the connected domain analysis is used for positioning the model code of the maintenance vehicle by detecting and combining the connected domains according to the characteristic that each character in the model code of the maintenance vehicle is a connected domain and the structures and colors of the connected domains are consistent.
D. After the maintenance vehicle model code area is extracted, the maintenance vehicle model code area needs to be divided by taking one character as a unit.
E. And carrying out normalization processing on the gray level image of the segmented character, extracting the characteristic, then carrying out machine learning or matching with a character database template, and finally selecting the result with the highest matching degree as the recognition result.
For the operator, apparent features and geometric features having individual representativeness are recognized as feature information by an image recognition technique.
Specifically, the steps are as follows:
A. and establishing a face image database.
B. And extracting the facial image characteristics in the facial image database according to the facial characteristic information.
And S3, refining the three-dimensional model of the power operation moving target according to the characteristic information, and acquiring the high-precision three-dimensional model and positioning and updating the high-precision three-dimensional model in a three-dimensional scene.
The dynamic target refined model library comprises various maintenance vehicle models and operation personnel models. For the maintenance vehicle, extracting the model code identified in the database; and for the operator, extracting through the recognized person name, and adjusting the three-dimensional model according to the height in the operator information.
The method is characterized in that a UWB or Beidou positioning tag is arranged on a dynamic target, a series of algorithm operations including image acquisition, preprocessing, model coding positioning, character segmentation, character recognition, result output and the like are adopted on the basis of positioning the moving target, fine reconstruction of the moving target in a three-dimensional scene is achieved, real-time position information of the dynamic target is obtained, the position state of a dynamic target model is updated in the three-dimensional scene in real time, and verification experiments prove that the error between the reconstructed dynamic model and the actual size is smaller than 1%.
Example 2
The present embodiment provides a high-precision spatial positioning system for an electric power work site based on embodiment 1, including:
the system comprises a UWB auxiliary video positioning module, a UWB auxiliary video positioning module and a video processing module, wherein the UWB auxiliary video positioning module is used for acquiring the positioning of a moving target of indoor power operation, and comprises an initialization unit for initializing an environmental image and IMU data, a vision/inertia combination unit for acquiring a vision coordinate and an ultra-wideband unit for acquiring the UWB coordinate;
the Beidou auxiliary visual positioning module is used for acquiring the positioning of an outdoor electric power operation moving target, and comprises a dynamic region of interest module used for reducing the extraction of environmental factors to an operation boundary line, a multi-view visual module used for constructing multi-view visual region coordinates and a Beidou positioning module used for converting the multi-view visual region coordinates into global positioning system coordinates.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only examples of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. The high-precision space positioning method for the electric power operation site is characterized by comprising the following steps of:
s1, acquiring the positioning of a power operation moving target based on a visual positioning technology; the UWB auxiliary visual positioning technology is adopted for indoor electric power operation moving targets, and the Beidou auxiliary visual positioning technology is adopted for outdoor electric power operation moving targets; the UWB-assisted visual positioning technology comprises UWB-assisted passive video positioning;
s2, performing image analysis on the power operation moving target according to the positioning of the power operation moving target to obtain characteristic information of the power operation moving target and construct a three-dimensional model of the power operation moving target;
and S3, refining the three-dimensional model of the power operation moving target according to the characteristic information to obtain a high-precision three-dimensional model and updating the positioning of the high-precision three-dimensional model in the three-dimensional scene in real time.
2. A method of high accuracy spatial location of an electrical work site as defined in claim 1, wherein said UWB assisted passive video location method comprises:
positioning the power operation moving target through a binocular vision system formed by two cameras to obtain position information of the power operation moving target in space;
positioning the power operation moving target based on the UWB model to obtain UWB positioning information of the power operation moving target;
and integrating the position information of the power operation moving target in the space and the UWB positioning information of the power operation moving target to obtain the positioning of the power operation moving target.
3. A high-precision spatial positioning method for an electric power work site according to claim 2, wherein the method of integrating the positional information of the electric power work moving object in space and the UWB positioning information of the electric power work moving object is as follows:
taking the position and the course measured by the binocular vision system and the position measured by the UWB model as observed values, and establishing a UWB/vision fusion observation equation; the UWB/visual fusion observation equation is as follows:
in the above formula, the first and second carbon atoms are,
representing the plane coordinates of the binocular vision system vision measurement,
representing the planar coordinates of the UWB measurements,
indicating the position measurement error of the binocular vision system,
indicating the error in the UWB position measurement,
plane coordinates representing binocular vision system measurements and UWB measurementsThe angle of deflection therebetween is such that,
representing the intermediate matrix.
4. A high-precision spatial positioning method for an electric power work site according to claim 3, wherein the UWB model is constructed by:
establishing an improved robust EKF model, and adopting the improved robust EKF model as a standard model of the UWB model;
judging whether the improved robust EKF model has gross errors or not by adopting a statistical method;
if gross error exists, the robust EKF model is invoked as the improved robust EKF model.
5. The high-precision space positioning method for the electric power operation site according to claim 1, wherein the positioning method of the Beidou auxiliary visual positioning technology comprises the following steps:
acquiring an interested region based on a Kalman filtering model and a working boundary line prediction position;
carrying out image edge detection on the region of interest to obtain a positioning region;
constructing a multi-view vision measurement model through a multi-view vision sensor, and constructing a multi-view vision coordinate in a positioning area through the multi-view vision measurement model;
optimizing the multi-view visual coordinate constructed in the positioning area through the multi-view visual measurement model based on a weighted LM algorithm to obtain an optimized multi-view visual coordinate;
and based on the Beidou positioning technology, the optimized multi-view visual coordinate is converted into the coordinate of a global positioning system.
6. The method for high-precision spatial location of an electric power operation field according to claim 5, wherein based on the Kalman filtering model, the method for dynamically acquiring the region of interest by a plurality of vision sensors comprises the following steps:
predicting the current straight line position based on Kalman filtering to obtain a first dynamic region of interest;
and predicting a column number of the operation boundary line in the image coordinate based on a projection method, and obtaining a second dynamic region of interest by taking the column number as a reference and combining the current camera calling condition.
7. The high-precision space positioning method for the electric power operation field according to claim 5, wherein based on the weighted LM algorithm, the method for optimizing the multi-view vision coordinates constructed in the positioning area by the multi-view vision measurement model comprises the following steps:
carrying out nonlinear optimization on image coordinates obtained after the object points are transformed to the ith multi-view vision sensor by adopting the minimized reprojection error;
normalizing the distance from the multi-view vision sensor to the object, and converting the reciprocal of the distance after normalization into a weighting factor;
and constructing an objective function through the weighting factors, and substituting the multi-view visual coordinates into the objective function to calculate to obtain optimized multi-view visual coordinates.
8. High accuracy spatial localization system of electric power operation scene, its characterized in that includes:
the system comprises a UWB auxiliary video positioning module, a UWB auxiliary video positioning module and a video processing module, wherein the UWB auxiliary video positioning module is used for acquiring the positioning of a moving target of indoor power operation, and comprises an initialization unit for initializing an environmental image and IMU data, a vision/inertia combination unit for acquiring a vision coordinate and an ultra-wideband unit for acquiring the UWB coordinate;
the Beidou auxiliary visual positioning module is used for acquiring the positioning of an outdoor electric power operation moving target, and comprises a dynamic region of interest module used for reducing the extraction of environmental factors to an operation boundary line, a multi-view visual module used for constructing multi-view visual region coordinates and a Beidou positioning module used for converting the multi-view visual region coordinates into global positioning system coordinates.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the method of high-precision spatial localization of an electric power job site according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out a method for high-precision spatial localization of an electric power work site according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211524412.6A CN115542362A (en) | 2022-12-01 | 2022-12-01 | High-precision space positioning method, system, equipment and medium for electric power operation site |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211524412.6A CN115542362A (en) | 2022-12-01 | 2022-12-01 | High-precision space positioning method, system, equipment and medium for electric power operation site |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115542362A true CN115542362A (en) | 2022-12-30 |
Family
ID=84722565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211524412.6A Pending CN115542362A (en) | 2022-12-01 | 2022-12-01 | High-precision space positioning method, system, equipment and medium for electric power operation site |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115542362A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118102233A (en) * | 2024-04-22 | 2024-05-28 | 南方电网调峰调频发电有限公司 | Object positioning method and device for multiple scenes of pumped storage foundation engineering |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077539A (en) * | 2013-01-23 | 2013-05-01 | 上海交通大学 | Moving object tracking method under complicated background and sheltering condition |
| CN104715252A (en) * | 2015-03-12 | 2015-06-17 | 电子科技大学 | License plate character segmentation method with combination of dynamic template and pixel points |
| CN106647784A (en) * | 2016-11-15 | 2017-05-10 | 天津大学 | Miniaturized unmanned aerial vehicle positioning and navigation method based on Beidou navigation system |
| CN107133563A (en) * | 2017-03-17 | 2017-09-05 | 深圳市能信安科技股份有限公司 | A kind of video analytic system and method based on police field |
| CN107967473A (en) * | 2016-10-20 | 2018-04-27 | 南京万云信息技术有限公司 | Based on picture and text identification and semantic robot autonomous localization and navigation |
| CN108012325A (en) * | 2017-10-30 | 2018-05-08 | 上海神添实业有限公司 | A kind of navigation locating method based on UWB and binocular vision |
| CN108549771A (en) * | 2018-04-13 | 2018-09-18 | 山东天星北斗信息科技有限公司 | A kind of excavator auxiliary construction system and method |
| CN109002744A (en) * | 2017-06-06 | 2018-12-14 | 中兴通讯股份有限公司 | Image-recognizing method, device and video monitoring equipment |
| CN109489629A (en) * | 2018-12-07 | 2019-03-19 | 国网四川省电力公司电力科学研究院 | A kind of safety monitoring method of electric power line pole tower |
| CN111401364A (en) * | 2020-03-18 | 2020-07-10 | 深圳市市政设计研究院有限公司 | License plate positioning algorithm based on combination of color features and template matching |
| CN111476233A (en) * | 2020-03-12 | 2020-07-31 | 广州杰赛科技股份有限公司 | License plate number positioning method and device |
| CN111508006A (en) * | 2020-04-23 | 2020-08-07 | 南开大学 | Moving target synchronous detection, identification and tracking method based on deep learning |
| CN112101343A (en) * | 2020-08-17 | 2020-12-18 | 广东工业大学 | License plate character segmentation and recognition 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 |
| CN112560745A (en) * | 2020-12-23 | 2021-03-26 | 南方电网电力科技股份有限公司 | Method for discriminating personnel on electric power operation site and related device |
| CN113392839A (en) * | 2021-05-18 | 2021-09-14 | 浙江大华技术股份有限公司 | Method and device for recognizing license plate of non-motor vehicle, computer equipment and storage medium |
| CN114092875A (en) * | 2021-11-01 | 2022-02-25 | 南方电网深圳数字电网研究院有限公司 | Operation site safety supervision method and device based on machine learning |
| CN114723824A (en) * | 2022-04-01 | 2022-07-08 | 浙江工业大学 | Indoor single positioning method based on binocular camera and ultra wide band fusion |
| CN115326053A (en) * | 2022-08-18 | 2022-11-11 | 华南理工大学 | Mobile robot multi-sensor fusion positioning method based on double-layer vision |
| CN115412846A (en) * | 2022-08-31 | 2022-11-29 | 常熟理工学院 | Underground multi-scene identity detection positioning method, system and storage medium |
-
2022
- 2022-12-01 CN CN202211524412.6A patent/CN115542362A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077539A (en) * | 2013-01-23 | 2013-05-01 | 上海交通大学 | Moving object tracking method under complicated background and sheltering condition |
| CN104715252A (en) * | 2015-03-12 | 2015-06-17 | 电子科技大学 | License plate character segmentation method with combination of dynamic template and pixel points |
| CN107967473A (en) * | 2016-10-20 | 2018-04-27 | 南京万云信息技术有限公司 | Based on picture and text identification and semantic robot autonomous localization and navigation |
| CN106647784A (en) * | 2016-11-15 | 2017-05-10 | 天津大学 | Miniaturized unmanned aerial vehicle positioning and navigation method based on Beidou navigation system |
| CN107133563A (en) * | 2017-03-17 | 2017-09-05 | 深圳市能信安科技股份有限公司 | A kind of video analytic system and method based on police field |
| CN109002744A (en) * | 2017-06-06 | 2018-12-14 | 中兴通讯股份有限公司 | Image-recognizing method, device and video monitoring equipment |
| CN108012325A (en) * | 2017-10-30 | 2018-05-08 | 上海神添实业有限公司 | A kind of navigation locating method based on UWB and binocular vision |
| CN108549771A (en) * | 2018-04-13 | 2018-09-18 | 山东天星北斗信息科技有限公司 | A kind of excavator auxiliary construction system and method |
| CN109489629A (en) * | 2018-12-07 | 2019-03-19 | 国网四川省电力公司电力科学研究院 | A kind of safety monitoring method of electric power line pole tower |
| CN111476233A (en) * | 2020-03-12 | 2020-07-31 | 广州杰赛科技股份有限公司 | License plate number positioning method and device |
| CN111401364A (en) * | 2020-03-18 | 2020-07-10 | 深圳市市政设计研究院有限公司 | License plate positioning algorithm based on combination of color features and template matching |
| CN111508006A (en) * | 2020-04-23 | 2020-08-07 | 南开大学 | Moving target synchronous detection, identification and tracking method based on deep learning |
| CN112101343A (en) * | 2020-08-17 | 2020-12-18 | 广东工业大学 | License plate character segmentation and recognition 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 |
| CN112560745A (en) * | 2020-12-23 | 2021-03-26 | 南方电网电力科技股份有限公司 | Method for discriminating personnel on electric power operation site and related device |
| CN113392839A (en) * | 2021-05-18 | 2021-09-14 | 浙江大华技术股份有限公司 | Method and device for recognizing license plate of non-motor vehicle, computer equipment and storage medium |
| CN114092875A (en) * | 2021-11-01 | 2022-02-25 | 南方电网深圳数字电网研究院有限公司 | Operation site safety supervision method and device based on machine learning |
| CN114723824A (en) * | 2022-04-01 | 2022-07-08 | 浙江工业大学 | Indoor single positioning method based on binocular camera and ultra wide band fusion |
| CN115326053A (en) * | 2022-08-18 | 2022-11-11 | 华南理工大学 | Mobile robot multi-sensor fusion positioning method based on double-layer vision |
| CN115412846A (en) * | 2022-08-31 | 2022-11-29 | 常熟理工学院 | Underground multi-scene identity detection positioning method, system and storage medium |
Non-Patent Citations (13)
| Title |
|---|
| 刘德辉: ""基于双目视觉里程计辅助的UWB/GNSS室内外定位算法研究"" * |
| 刘德辉: ""基于双目视觉里程计辅助的UWB/GNSS室内外定位算法研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 刘飞: ""多传感器融合的高精度无缝定位模型与方法研究"" * |
| 周爱国 等: ""基于加权 Levenberg-Marquardt的多目视觉同名物点定位算法"" * |
| 周爱国 等: ""基于加权 Levenberg-Marquardt的多目视觉同名物点定位算法"", 《激光与光电子学进展》 * |
| 张明军 等: ""一种基于机器学习的车牌识别***的设计"" * |
| 李鹏 等: ""改进自适应抗差容积卡尔曼滤波多源室内定位"", 《导航定位与授时》 * |
| 杨博: ""视觉/惯性/超宽带组合定位***关键技术研究"" * |
| 王璇: ""基于视觉的电力***输电线检测与跟踪"" * |
| 王璇: ""基于视觉的电力***输电线检测与跟踪"", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 申炳琦 等: ""移动机器人 UWB 与 VIO 组合室内定位算法"" * |
| 申炳琦 等: ""移动机器人 UWB 与 VIO 组合室内定位算法"", 《计算机应用》 * |
| 郑顾平 等: ""基于机器学习的多车牌识别算法应用研究"" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118102233A (en) * | 2024-04-22 | 2024-05-28 | 南方电网调峰调频发电有限公司 | Object positioning method and device for multiple scenes of pumped storage foundation engineering |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111563442B (en) | Slam method and system for fusing point cloud and camera image data based on laser radar | |
| Dhiman et al. | Pothole detection using computer vision and learning | |
| CN110531759B (en) | Robot exploration path generation method and device, computer equipment and storage medium | |
| CN111429574B (en) | Mobile robot positioning method and system based on three-dimensional point cloud and vision fusion | |
| Zhao et al. | Detection, tracking, and geolocation of moving vehicle from uav using monocular camera | |
| CN108898676B (en) | Method and system for detecting collision and shielding between virtual and real objects | |
| WO2021021862A1 (en) | Mapping and localization system for autonomous vehicles | |
| CN114140761A (en) | Point cloud registration method and device, computer equipment and storage medium | |
| CN111998862A (en) | Dense binocular SLAM method based on BNN | |
| CN114463932B (en) | Non-contact construction safety distance active dynamic identification early warning system and method | |
| CN115542362A (en) | High-precision space positioning method, system, equipment and medium for electric power operation site | |
| Yu et al. | Accurate and robust visual localization system in large-scale appearance-changing environments | |
| Wang et al. | 3D-LIDAR based branch estimation and intersection location for autonomous vehicles | |
| CN114721008A (en) | Obstacle detection method and device, computer equipment and storage medium | |
| Kampker et al. | Concept study for vehicle self-localization using neural networks for detection of pole-like landmarks | |
| CN114549549A (en) | Dynamic target modeling tracking method based on instance segmentation in dynamic environment | |
| CN114049362A (en) | Transform-based point cloud instance segmentation method | |
| Sun et al. | Real-time and fast RGB-D based people detection and tracking for service robots | |
| Suzuki et al. | SLAM using ICP and graph optimization considering physical properties of environment | |
| CN116188417A (en) | Slit detection and three-dimensional positioning method based on SLAM and image processing | |
| CN115497086A (en) | 3D scene flow estimation method based on fine-grained identification in automatic driving | |
| CN115761265A (en) | Method and device for extracting substation equipment in laser radar point cloud | |
| Kim et al. | 3D pose estimation and localization of construction equipment from single camera images by virtual model integration | |
| CN112146647B (en) | Binocular vision positioning method and chip for ground texture | |
| Zhang et al. | Vision-based uav positioning method assisted by relative attitude classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221230 |