CN111879244A - Method for measuring support height and top beam inclination angle of hydraulic support of fully mechanized mining face - Google Patents
Method for measuring support height and top beam inclination angle of hydraulic support of fully mechanized mining face Download PDFInfo
- Publication number
- CN111879244A CN111879244A CN202010742021.6A CN202010742021A CN111879244A CN 111879244 A CN111879244 A CN 111879244A CN 202010742021 A CN202010742021 A CN 202010742021A CN 111879244 A CN111879244 A CN 111879244A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- hydraulic support
- support base
- point
- top beam
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000005065 mining Methods 0.000 title claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 238000005259 measurement Methods 0.000 claims abstract description 27
- 238000001914 filtration Methods 0.000 claims abstract description 25
- 238000009434 installation Methods 0.000 claims abstract description 13
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 17
- 238000005070 sampling Methods 0.000 claims description 14
- 238000013519 translation Methods 0.000 claims description 9
- 230000002146 bilateral effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 239000003245 coal Substances 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 5
- 239000002817 coal dust Substances 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0608—Height gauges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C9/00—Measuring inclination, e.g. by clinometers, by levels
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The embodiment of the invention discloses a method for measuring the supporting height and the top beam inclination angle of a hydraulic support of a fully mechanized coal mining face, and relates to the technical field of monitoring of fully mechanized coal mining face equipment. Acquiring a point cloud image containing a hydraulic support base by adopting a depth camera; denoising the point cloud image by adopting a filtering algorithm; utilizing a point cloud segmentation algorithm to segment the noise-reduced three-dimensional point cloud to obtain a plurality of category point cloud data clusters; selecting a point cloud feature descriptor to perform feature description and extraction on the point cloud cluster; matching in point cloud clustering according to the three-dimensional model of the hydraulic support base to obtain base point cloud; registering the hydraulic support base point cloud with a preset base database point cloud model to obtain six-degree-of-freedom parameters of the support base relative to the depth camera in an actual scene; and obtaining the support height of the hydraulic support and the inclination angle value of the top beam by combining the installation position relation of the depth camera and the top beam. The measuring method can well realize the real-time online measurement of the support height of the hydraulic support and the inclination angle parameter of the top beam.
Description
Technical Field
The invention relates to the technical field of vision measurement application, in particular to a method for measuring the supporting height and the top beam inclination angle of a hydraulic support of a fully mechanized mining face.
Background
The vision measurement is to capture the characteristics of a target object in a three-dimensional space through an image sensor, and then obtain the information of the size, the position, the posture and the like of the target object by utilizing an image processing and recognition technology, so that the pose of the target object in the space is resolved. At present, the vision measurement technology is widely applied in the industrial field, and the image sensor is mainly used for replacing human eyes to accurately acquire the pose information of the target.
The hydraulic support is one of important devices of the underground fully-mechanized mining working face, and accurate acquisition of pose state information of the hydraulic support directly influences automatic cooperative propulsion of the fully-mechanized mining working face. With the development of coal mine intellectualization, the traditional method for adjusting the position and posture state of the hydraulic support by manual observation and experience cannot meet the requirement of intelligent mining, and becomes one of key factors for restricting the establishment of a less-humanized or unmanned working face. Therefore, the development of the autonomous hydraulic support pose measuring system replaces the traditional human eye observation mode, realizes the real-time online monitoring of the pose state of the hydraulic support, and is an important means for improving the production efficiency of a working face and the intelligent degree of a coal mine.
In order to solve the above problems, the invention patent with chinese patent application No. 201710040395.1 discloses a system and a method for measuring the support height and posture of a hydraulic support top beam, which respectively installs a common vision module and a positioning identification plate on the hydraulic support top beam and a base, and calculates the support height and the top beam inclination angle of the hydraulic support by using an image processing technology.
The inventor finds out in the process of realizing the invention: although the method has a simple structure and is convenient to install, the positioning identification plate needs to be installed on each hydraulic support, so that the installation cost is high, the precision is low, and the measurement accuracy is influenced; and the marking plate is easily covered by coal dust or loosened and fallen off, which can affect the normal operation of the measuring system.
Disclosure of Invention
In view of the above, the present invention aims to provide a method for measuring the support height and the top beam inclination angle of a hydraulic support on a fully mechanized mining face, which can at least solve the technical problems in the measurement method and can better realize the real-time online measurement of the support height and the top beam inclination angle parameters of the hydraulic support.
In order to achieve the purpose, the invention provides the following scheme:
the embodiment of the invention provides a method for measuring the supporting height and the top beam inclination angle of a hydraulic support of a fully mechanized coal mining face, which comprises the following steps:
s10, mounting a depth camera vision measurement module on the top beam of the hydraulic support, and acquiring a point cloud image containing color information and depth information of a base of the hydraulic support through a depth camera; the depth camera vision measurement module comprises a depth camera;
s20, carrying out noise reduction processing on the obtained point cloud image by adopting a filtering algorithm to obtain three-dimensional point cloud data subjected to noise reduction processing;
s30, segmenting the three-dimensional point cloud subjected to noise reduction processing by using a point cloud segmentation algorithm to obtain a plurality of point cloud data clusters of different categories;
s40, selecting a point cloud feature descriptor to perform feature description and extraction on the point cloud cluster;
s50, finding out a hydraulic support base point cloud data cluster from a plurality of point cloud data clusters according to a pre-stored hydraulic support base three-dimensional model, and finishing the identification of the hydraulic support base point cloud;
s60, registering the recognized point cloud of the hydraulic support base with a prestored point cloud model of a hydraulic support base database, and calculating according to the position information of the hydraulic support to obtain six-degree-of-freedom parameters of the hydraulic support base relative to the depth camera in an actual scene; the hydraulic support base point cloud comprises position information of the hydraulic support;
and S70, obtaining a hydraulic support supporting height and a top beam inclination angle value according to the obtained six-degree-of-freedom parameter of the hydraulic support base relative to the depth camera and the installation position relation of the depth camera and the hydraulic support top beam so as to complete the measurement of the hydraulic support supporting height and the top beam inclination angle.
Optionally, after step S70, the method further comprises: and S80, sending the measured hydraulic support height and top beam inclination angle values to an upper computer at preset time intervals, so that the upper computer can complete real-time online monitoring of the hydraulic support height and top beam inclination angle parameters.
Optionally, the filtering algorithm adopted in step S20 is a bilateral filtering algorithm.
Optionally, the step S20 specifically includes:
s21, defining a Gaussian filtering weight term and a pixel value weight term based on the space distance;
and S22, combining the Gaussian filtering weight term and the pixel value weight term to obtain a bilateral filtering result based on the Gaussian filtering and the pixel value weight term so as to realize the noise reduction processing of the image.
Optionally, the step S30 specifically includes: and partitioning the three-dimensional point cloud subjected to noise reduction processing by adopting an Euclidean clustering algorithm based on the point cloud boundary to obtain a plurality of point cloud data clusters of different categories.
Optionally, the step S30 specifically includes:
s30, extracting a boundary line of the target point cloud according to the point cloud curvature characteristics to obtain a point cloud group S in the boundary;
s30, constructing a K-d tree to represent the relation between the point cloud groups S;
s30, creating an empty table cluster P and a queue Q to be verified;
s31, initializing parameters of the point cloud group S, specifically: let n points in the point cloud S, wherein any point is piSearching for piRadius of less than r0Neighborhood K, if point p within K neighborhoodikIf the processed point is processed, adding P, otherwise adding Q, and resetting Q to be an empty queue until all points in Q are processed;
and S32, iterating and repeating the steps until all the points in the point cloud group S are processed, and realizing the segmentation of the three-dimensional point cloud.
Optionally, in the step S40, an FPFH descriptor is selected to perform feature description and extraction on the point cloud cluster; the method specifically comprises the following steps:
s41, respectively calculating each point p in the point cloud group S based on the obtained point cloud group SiCorresponding surface normal vector ni;
S42, determining the neighborhood radius r, for each query point PqCalculating all neighbors in the radius r and calculating three elements of point feature histogram features of the neighbors;
s43, inquiring each point PqThe three elements of the point feature histogram feature of (1) are put into the histogram for expression.
Optionally, the step S50 includes:
s51, performing point cloud on the three-dimensional model of the hydraulic support base, and then performing down-sampling to obtain a point cloud model of a hydraulic support base database for storage;
s52, performing registration training on the point cloud model of the hydraulic support base database to obtain a shape model corresponding to the hydraulic support base;
and S53, performing key point detection on the obtained point cloud data clusters, and finding out base point cloud data clusters in the point cloud clusters through an accumulative voting algorithm so as to identify the hydraulic support base.
Optionally, in the step S60, the identified point cloud of the hydraulic support base and the point cloud model of the hydraulic support base database are registered by using a sampling consistency registration algorithm; the step 60 specifically includes the steps of:
s61, selecting n 'sampling points from the identified cloud set S' of the hydraulic support base points, comparing the fast point feature histogram features of the sampling points with the fast point feature histogram features extracted from the point cloud set M in the point cloud model of the hydraulic support base database, and finding out the same points as matching point pairs;
s62, selecting 3 groups of non-collinear matching point pairs from the found matching point pairs, and calculating a rotation matrix and a translation matrix between the 3 groups of matching point pairs;
wherein, the step of calculating the rotation matrix and the translation matrix between the 3 groups of matching point pairs comprises the following steps:
setting the coordinates of a pair of matching points in the point cloud of the actual scene of the base and the point cloud of the base point cloud model as P (x)1,y1,z1) And P' (x)1′,y1′,z1'), the rotation matrix between the matching points is R, the translation matrix is t, then
in the formula: the actual scene point cloud of the base is the cloud set S' of the base points of the hydraulic support, the point cloud in the point cloud model of the base is the point cloud set M in the database point cloud model of the hydraulic support, alpha, beta and gamma are euler angles of the hydraulic support base rotating around the x, y and z axes of a camera coordinate system respectively, and delta x, delta y and delta z are displacements of the hydraulic support base in the directions around the x, y and z axes of the camera coordinate system respectively;
and selecting the 3 groups of non-collinear matching point pairs to construct six equations according to the steps, and solving six freedom degree parameters of alpha, beta, gamma, delta x, delta y and delta z.
S63, repeating the step S62, calculating a plurality of groups of six-degree-of-freedom parameter values, and calculating the average value of the six-degree-of-freedom parameter valuesAnd as a final result.
Optionally, the step S70 specifically includes the steps of:
s71, calculating a true value of the support height of the hydraulic support; the method comprises the following steps:
after the depth camera is installed, the distance between the depth camera and the top beam is d, and the initial distance between the depth camera and the hydraulic support base is H0In step S63, the displacement of the hydraulic support base on the Z axis of the camera coordinate system isAfter the hydraulic support moving action is finished, calculating according to a first formula to obtain the supporting height H of the hydraulic support; the first calculation formula is
S72, calculating a true value of the top beam inclination angle; the method comprises the following steps:
setting the initial value of the inclination angle of the top beam of the hydraulic support as theta0In step S63, the Euler angle of the hydraulic support base rotating around the X-axis of the camera coordinate system isAfter the hydraulic support frame moving action is finished, calculating a top beam inclination angle theta according to a second formula; the second formula is:
compared with the prior art, the method for measuring the support height and the top beam inclination angle of the hydraulic support of the fully mechanized mining face provided by the embodiment of the invention has the advantages that the method for measuring the support height and the top beam inclination angle of the hydraulic support of the fully mechanized mining face is implemented by adopting a depth camera three-dimensional visual scanning mode, completing the data clustering identification of the base point cloud of the hydraulic support through point cloud noise reduction, point cloud segmentation and feature description, then utilizing a database model point cloud to estimate the pose of the base point cloud, and finally obtaining the true value of the support height and the top beam inclination angle of the hydraulic support through space geometric operation by combining the installation position relation of the camera. According to the method, a positioning identification plate is not needed, the phenomenon that the measurement system cannot normally operate due to coal dust coverage or loosening and falling of the identification plate is avoided, and the operation stability and the measurement precision of the measurement system are improved. Furthermore, due to the simplification of the related measuring assembly, the installation is simple, and the installation cost can be effectively reduced. Therefore, the real-time online measurement of the support height and the top beam inclination angle parameters of the hydraulic support can be better realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic view of the installation location of a depth camera vision measurement module of the present invention;
FIG. 2 is a flow chart of a method for measuring the support height and the top beam inclination angle of a hydraulic support according to the present invention;
FIG. 3 is a flow chart of a hydraulic support base point cloud image denoising method based on bilateral filtering in the invention;
FIG. 4 is a flow chart of a support base point cloud segmentation method based on a Euclidean clustering algorithm of point cloud boundaries in the invention;
FIG. 5 is a flow chart of a bracket base point cloud cluster identification method based on a CAD three-dimensional model in the invention;
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
It should be apparent that numerous technical details are set forth in the following specific examples in order to provide a more thorough description of the present invention, and it should be apparent to one skilled in the art that the present invention may be practiced without some of these details. In addition, some methods, means, components and applications thereof known to those skilled in the art are not described in detail in order to highlight the gist of the present invention, but the implementation of the present invention is not affected. The embodiments described herein are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a method for measuring the supporting height of a hydraulic support and the inclination angle of a top beam of a fully mechanized mining face, which is suitable for monitoring the supporting height of the hydraulic support and the inclination angle of the top beam relative to a hydraulic support base of the fully mechanized mining face and is further suitable for controlling the pose of the hydraulic support, and as shown in figures 1 and 2, the measuring method comprises the following steps:
and S10, mounting a depth camera vision measurement module 100 on the top beam of the hydraulic support, and acquiring a point cloud image containing color information and depth information of the base of the hydraulic support through a depth camera.
The depth camera vision measurement module 100 includes a depth camera; the depth camera vision measuring module 100 is installed on a top beam 1 of the hydraulic support and is 20-30 cm away from the central line of two column nests of a front upright post 2 of the hydraulic support, the horizontal depression angle of a camera body is 90 degrees, and the depth camera can acquire a point cloud image of a base 3 of the hydraulic support in a visual field.
And S20, carrying out noise reduction processing on the obtained point cloud image by adopting a filtering algorithm to obtain three-dimensional point cloud data subjected to noise reduction processing.
The filtering algorithm is a bilateral filtering algorithm; referring to fig. 3, in some embodiments, the step S20 specifically includes:
s21, S21, defining a Gaussian filtering weight term and a pixel value weight term based on the space distance;
where c (ξ, x) is the Gaussian filter weight based on spatial distance, d (ξ, x) represents the Euclidean distance between two pixels, σsIs the spatial domain standard deviation.
Defining pixel value weight terms
Where s (f (ξ), f (x)) is the pixel value weight, d (f (ξ), f (x)) represents the distance between two pixel values, σ (x))τIs the value range standard deviation.
And S22 and S22, combining the Gaussian filtering weight term and the pixel value weight term to obtain a bilateral filtering result h (x) based on the Gaussian filtering and the pixel value weight term so as to realize the noise reduction processing of the image.
Wherein k (x) is the weight sum of each pixel in the filtering window for weight normalization;
and obtaining the point cloud image of the hydraulic support base subjected to noise reduction treatment by the bilateral filtering algorithm.
And S30, segmenting the three-dimensional point cloud subjected to noise reduction processing by using a point cloud segmentation algorithm to obtain a plurality of point cloud data clusters of different categories.
In this embodiment, an euclidean clustering algorithm based on point cloud boundaries may be adopted to segment the three-dimensional point cloud after noise reduction processing, so as to obtain a plurality of point cloud data clusters of different categories.
Referring to fig. 4, step S30 specifically includes:
step S31, extracting a boundary line of the target point cloud according to the point cloud curvature characteristics to obtain a point cloud group S in the boundary;
step S32, constructing a K-d tree to represent the relationship among the point cloud groups S;
step S33, creating an empty table cluster P and a queue Q to be verified;
step S34, initializing parameters of the point cloud group S, specifically: setting neighborhood search radius r0Setting n points in the point cloud group S, wherein any point is piSearching for piRadius of less than r0Neighborhood K, if point p within K neighborhoodikAdding P if the processed point is processed, or adding Q until all points in Q are processed, and then resetting Q to be an empty queue;
and step S35, iterating and repeating the steps until all the points in the point cloud group S are processed, and realizing the segmentation of the three-dimensional point cloud.
And S40, selecting a point cloud feature descriptor to perform feature description and extraction on the point cloud cluster.
In the machine vision technology, an important task is to extract and describe the position and posture of an object from a scene, and the feature descriptor (feature descriptor) is a term in the machine vision technology field, which is an algorithm for simply extracting local features in a point cloud clustering image.
In the embodiment, an FPFH descriptor is selected to perform feature description and extraction on the point cloud cluster; the method comprises the following specific steps:
s41, respectively calculating each point p in the point cloud group S based on the obtained point cloud group SiCorresponding surface normal vector ni;
S42, determining the neighborhood radius r, for each query point PqCalculating all neighbors in the radius r and calculating three elements of Point Feature Histograms (PFH) features of the neighbors;
s43, inquiring each point PqThe three elements of the point feature histogram feature of (1) are put into the histogram for expression.
And S50, finding out the hydraulic support base point cloud data clusters from the plurality of point cloud data clusters according to a pre-stored hydraulic support base three-dimensional model, and finishing the identification of the hydraulic support base point cloud.
Referring to fig. 5, in some embodiments, the step S50 includes the steps of:
s51, performing point cloud on the three-dimensional model of the hydraulic support base, and then performing down-sampling to obtain a point cloud model of a hydraulic support base database for storage;
s52, performing registration training on the point cloud model of the hydraulic support base database to obtain a shape model corresponding to the hydraulic support base;
with continued reference to fig. 5, as an alternative embodiment, S51 and S52 specifically include the steps of:
performing point cloud on a hydraulic support base CAD three-dimensional model to obtain a base database point cloud model, performing down-sampling on the model, and extracting key points of the model point cloud after the down-sampling;
extracting the characteristics of each key Point by adopting an FPFH (fast Point features descriptors);
constructing dictionary indexes for all feature points by using a K-means clustering algorithm, wherein each individual cluster is used as a word in a dictionary, and each feature of the cluster is used as an example of the word;
calculating the direction from the key point of each feature to the centroid of the model point cloud and the statistical weight of each cluster;
and performing learning training on each key point in the model point cloud to obtain a shape model corresponding to the hydraulic support base model.
And S53, performing key point detection on the obtained point cloud data clusters, and finding out base point cloud data clusters in the point cloud clusters through an accumulative voting algorithm so as to identify the hydraulic support base.
With continued reference to fig. 5, in some embodiments, S53 includes the following steps:
detecting key points of point cloud clusters obtained in an actual scene;
extracting the characteristics of the detected key points, and searching the closest words in a training model dictionary;
predicting a point cloud center through an accumulative voting algorithm;
traversing each point i in the point cloud, and calculating a first Euclidean distance mean value between each point i and the central point; wherein, the formula used for calculation is as follows:
and calculating to obtain a second Euclidean distance mean value of the point cloud in the point cloud model of the base database and the central point thereof according to the step of calculating the Euclidean distance between the point cloud in the point cloud cluster obtained in the actual scene and the central point thereof.
And obtaining similarity based on the ratio of the first Euclidean distance mean value and the second Euclidean distance mean value of the point clouds in the actual scene obtained by calculation, and taking the point cloud cluster with the highest similarity as an identification result.
S60, registering the recognized point cloud of the hydraulic support base with a prestored point cloud model of a hydraulic support base database, and calculating according to the position information of the hydraulic support to obtain six-degree-of-freedom parameters of the hydraulic support base relative to the depth camera in an actual scene; the hydraulic support base point cloud comprises position information of the hydraulic support.
The step S60 is specifically to register the recognized hydraulic support base point cloud and the hydraulic support base database point cloud model through a sampling consistency registration algorithm; the step 60 specifically includes the steps of:
s61, selecting n 'sampling points from the identified cloud set S' of the hydraulic support base points, comparing the fast point feature histogram features of the sampling points with the fast point feature histogram features extracted from the point cloud set M in the point cloud model of the hydraulic support base database, and finding out the same points as matching point pairs;
s62, selecting 3 groups of non-collinear matching point pairs from the found matching point pairs, and calculating a rotation matrix and a translation matrix between the 3 groups of matching point pairs;
wherein, the step of calculating the rotation matrix and the translation matrix between the 3 groups of matching point pairs comprises the following steps:
setting the coordinates of a pair of matching points in the point cloud of the actual scene of the base and the point cloud of the base point cloud model as P (x)1,y1,z1) And P' (x)1′,y1′,z1'), between matching pointsThe rotation matrix is R, the translation matrix is t, then
in the formula: the actual scene point cloud of the base is the cloud set S' of the base points of the hydraulic support, the point cloud in the point cloud model of the base is the point cloud set M in the database point cloud model of the hydraulic support, alpha, beta and gamma are euler angles of the hydraulic support base rotating around the x, y and z axes of a camera coordinate system respectively, and delta x, delta y and delta z are displacements of the hydraulic support base in the directions around the x, y and z axes of the camera coordinate system respectively;
and selecting the 3 groups of non-collinear matching point pairs to construct six equations according to the steps, and solving six freedom degree parameters of alpha, beta, gamma, delta x, delta y and delta z.
S63, repeating the step S62, calculating a plurality of groups of six-degree-of-freedom parameter values, and calculating the average value of the six-degree-of-freedom parameter valuesAnd as a final result.
And S70, obtaining a hydraulic support supporting height and a top beam inclination angle value according to the obtained six-degree-of-freedom parameter of the hydraulic support base relative to the depth camera and the installation position relation of the depth camera and the hydraulic support top beam so as to complete the measurement of the hydraulic support supporting height and the top beam inclination angle.
In some embodiments, step S70 specifically includes the steps of:
s71, calculating a true value of the support height of the hydraulic support; the method comprises the following steps:
after the depth camera is installed, the distance between the depth camera and the top beam is d, and the initial distance between the depth camera and the hydraulic support base is d
H0Step S63The displacement of the base of the pressing bracket on the Z axis of the camera coordinate system isAfter the hydraulic support moving action is finished, calculating according to a first formula to obtain the support height H of the hydraulic support; the first calculation formula is
S72, calculating a true value of the top beam inclination angle; the method comprises the following steps:
setting the initial value of the inclination angle of the top beam of the hydraulic support as theta0In step S63, the Euler angle of the hydraulic support base rotating around the X-axis of the camera coordinate system isAfter the hydraulic support frame moving action is finished, calculating a top beam inclination angle theta according to a second formula; the second formula is:
in the related art mentioned in the background section, the measured support height of the hydraulic bracket is not the true value of the support height, and the specific reason is that: in the measuring process, the height from the focal point of the camera to the bottom plate is used for replacing the supporting height of the hydraulic support, and the camera has a certain height to the top beam, so that the measured supporting height is not the real supporting height of the hydraulic support. Thus, the measurement results are not accurate enough.
In the embodiment, on the basis of obtaining the six-degree-of-freedom parameter of the hydraulic support relative to the depth camera through calculation, the installation position relation between the depth camera and the top beam is further calibrated to obtain the support height and the inclination true value of the hydraulic support, so that the measurement accuracy can be improved, accurate data support is provided for pose control of the hydraulic support, and the control accuracy is improved.
In some embodiments, after step S70, the method further includes step S80, sending the measured hydraulic support height and roof beam inclination angle values to an upper computer at predetermined time intervals, so that the upper computer performs real-time online monitoring of hydraulic support height and roof beam inclination angle parameters.
The interval time sent to the upper computer can be set by itself, and for example, the interval time is sent once for 30 s.
In summary, according to the method for measuring the support height and the top beam inclination angle of the hydraulic support on the fully mechanized mining face provided by the embodiment of the invention, a depth camera three-dimensional visual scanning mode is adopted, the clustering identification of the base point cloud data of the hydraulic support is completed through point cloud noise reduction, point cloud segmentation and feature description, then the pose estimation is performed by using the database model point cloud, and finally the support height and the top beam inclination angle truth value of the hydraulic support are obtained through space geometric operation by combining the installation position relation of the camera and the top beam, so that the measurement of the support height and the top beam inclination angle of the hydraulic support is completed. According to the method, a positioning identification plate is not needed, the phenomenon that the measurement system cannot normally operate due to coal dust coverage or loosening and falling of the identification plate is avoided, and the operation stability and the measurement precision of the measurement system are improved. Furthermore, due to the simplification of the related measuring assembly, the installation is simple, and the installation cost can be effectively reduced. Therefore, the real-time online monitoring of the support height of the hydraulic support and the inclination angle parameter of the top beam can be better realized. The measuring method provided by the embodiment of the invention has the advantages of simple structure, high measuring precision, capability of completing online measurement and monitoring without positioning the marking plate, and capability of providing accurate data support for the subsequent further pose control of the hydraulic support so as to improve the control precision.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for measuring the supporting height and the top beam inclination angle of a hydraulic support of a fully mechanized mining face is characterized by comprising the following steps:
s10, mounting a depth camera vision measurement module on the top beam of the hydraulic support, and acquiring a point cloud image containing color information and depth information of a base of the hydraulic support through a depth camera; the depth camera vision measurement module comprises a depth camera;
s20, carrying out noise reduction processing on the obtained point cloud image by adopting a filtering algorithm to obtain three-dimensional point cloud data subjected to noise reduction processing;
s30, segmenting the three-dimensional point cloud subjected to noise reduction processing by using a point cloud segmentation algorithm to obtain a plurality of point cloud data clusters of different categories;
s40, selecting a point cloud feature descriptor to perform feature description and extraction on the point cloud cluster;
s50, finding out a hydraulic support base point cloud data cluster from a plurality of point cloud data clusters according to a pre-stored hydraulic support base three-dimensional model, and finishing the identification of the hydraulic support base point cloud;
s60, registering the recognized point cloud of the hydraulic support base with a prestored point cloud model of a hydraulic support base database, and calculating according to the position information of the hydraulic support to obtain six-degree-of-freedom parameters of the hydraulic support base relative to the depth camera in an actual scene; the hydraulic support base point cloud comprises position information of the hydraulic support;
and S70, obtaining a hydraulic support supporting height and a top beam inclination angle value according to the obtained six-degree-of-freedom parameter of the hydraulic support base relative to the depth camera and the installation position relation of the depth camera and the hydraulic support top beam so as to complete the measurement of the hydraulic support supporting height and the top beam inclination angle.
2. The method according to claim 1, wherein after step S70, the method further comprises: and S80, sending the measured hydraulic support height and top beam inclination angle values to an upper computer at preset time intervals, so that the upper computer can complete real-time online monitoring of the hydraulic support height and top beam inclination angle parameters.
3. The method according to claim 1, wherein the filtering algorithm adopted in step S20 is a bilateral filtering algorithm.
4. The method according to claim 3, wherein the step S20 specifically includes:
s21, defining a Gaussian filtering weight term and a pixel value weight term based on the space distance;
and S22, combining the Gaussian filtering weight term and the pixel value weight term to obtain a bilateral filtering result based on the Gaussian filtering and the pixel value weight term so as to realize the noise reduction processing of the image.
5. The method according to claim 1 or 3, wherein the step S30 is specifically: and partitioning the three-dimensional point cloud subjected to noise reduction processing by adopting an Euclidean clustering algorithm based on the point cloud boundary to obtain a plurality of point cloud data clusters of different categories.
6. The method according to claim 5, wherein the step S30 specifically includes:
s30, extracting a boundary line of the target point cloud according to the point cloud curvature characteristics to obtain a point cloud group S in the boundary;
s30, constructing a K-d tree to represent the relation between the point cloud groups S;
s30, creating an empty table cluster P and a queue Q to be verified;
s31, initializing parameters of the point cloud group S, specifically: let n points in the point cloud S, wherein any point is piSearching for piRadius of less than r0Neighborhood K, if point p within K neighborhoodikIf the processed point is processed, adding P, otherwise adding Q, and resetting Q to be an empty queue until all points in Q are processed;
and S32, iterating and repeating the steps until all the points in the point cloud group S are processed, and realizing the segmentation of the three-dimensional point cloud.
7. The method according to claim 1, wherein in step S40, the FPFH descriptor is selected to perform feature description and extraction on the point cloud cluster; the method specifically comprises the following steps:
s41, respectively calculating each point p in the point cloud group S based on the obtained point cloud group SiCorresponding surface normal vector ni;
S42, determining the neighborhood radius r, for each query point PqCalculating all neighbors in the radius r and calculating three elements of point feature histogram features of the neighbors;
s43, inquiring each point PqThe three elements of the point feature histogram feature of (1) are put into the histogram for expression.
8. The method according to claim 1, wherein the step S50 includes:
s51, performing point cloud on the three-dimensional model of the hydraulic support base, and then performing down-sampling to obtain a point cloud model of a hydraulic support base database for storage;
s52, performing registration training on the point cloud model of the hydraulic support base database to obtain a shape model corresponding to the hydraulic support base;
and S53, performing key point detection on the obtained point cloud data clusters, and finding out base point cloud data clusters in the point cloud clusters through an accumulative voting algorithm so as to identify the hydraulic support base.
9. The method according to claim 1, wherein the step S60 is to register the identified hydraulic support base point cloud and the hydraulic support base database point cloud model, in particular by a sampling consistency registration algorithm; the step 60 specifically includes the steps of:
s61, selecting n 'sampling points from the identified cloud set S' of the hydraulic support base points, comparing the fast point feature histogram features of the sampling points with the fast point feature histogram features extracted from the point cloud set M in the point cloud model of the hydraulic support base database, and finding out the same points as matching point pairs;
s62, selecting 3 groups of non-collinear matching point pairs from the found matching point pairs, and calculating a rotation matrix and a translation matrix between the 3 groups of matching point pairs;
wherein, the step of calculating the rotation matrix and the translation matrix between the 3 groups of matching point pairs comprises the following steps:
setting the coordinates of a pair of matching points in the point cloud of the actual scene of the base and the point cloud of the base point cloud model as P (x)1,y1,z1) And P' (x)1′,y1′,z1'), the rotation matrix between the matching points is R, the translation matrix is t, then
in the formula: the base actual scene point cloud is the hydraulic support base point cloud set S', the point cloud in the base point cloud model is the point cloud set M in the hydraulic support base database point cloud model,
alpha, beta and gamma are respectively euler angles of the hydraulic support base rotating around the x, y and z axes of the camera coordinate system,
the delta x, the delta y and the delta z are respectively the displacement of the hydraulic support base in the directions of x, y and z axes of a camera coordinate system;
selecting the 3 groups of non-collinear matching point pairs to construct six equations according to the steps, and solving six freedom degree parameters of alpha, beta, gamma, delta x, delta y and delta z;
10. The method according to claim 1, wherein the step S70 specifically comprises the steps of:
s71, calculating a true value of the support height of the hydraulic support; the method comprises the following steps:
after the depth camera is installed, the distance between the depth camera and the top beam is d, and the initial distance between the depth camera and the hydraulic support base is H0In step S63, the displacement of the hydraulic support base on the Z axis of the camera coordinate system isAfter the hydraulic support moving action is finished, calculating according to a first formula to obtain the support height H of the hydraulic support; the first calculation formula is
S72, calculating a true value of the top beam inclination angle; the method comprises the following steps:
setting the initial value of the inclination angle of the top beam of the hydraulic support as theta0In step S63, the Euler angle of the hydraulic support base rotating around the X-axis of the camera coordinate system isAfter the hydraulic support frame moving action is finished, calculating a top beam inclination angle theta according to a second formula; the second formula is:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010742021.6A CN111879244B (en) | 2020-07-28 | 2020-07-28 | Method for measuring support height and top beam inclination angle of hydraulic support of fully mechanized mining face |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010742021.6A CN111879244B (en) | 2020-07-28 | 2020-07-28 | Method for measuring support height and top beam inclination angle of hydraulic support of fully mechanized mining face |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111879244A true CN111879244A (en) | 2020-11-03 |
CN111879244B CN111879244B (en) | 2022-04-29 |
Family
ID=73201883
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010742021.6A Active CN111879244B (en) | 2020-07-28 | 2020-07-28 | Method for measuring support height and top beam inclination angle of hydraulic support of fully mechanized mining face |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111879244B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112419482A (en) * | 2020-11-23 | 2021-02-26 | 太原理工大学 | Three-dimensional reconstruction method for mine hydraulic support group pose fused with depth point cloud |
CN115903592A (en) * | 2022-11-10 | 2023-04-04 | 山东新普锐智能科技有限公司 | Hydraulic car unloader control method and system based on pose detection |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106908000A (en) * | 2017-01-20 | 2017-06-30 | 中国矿业大学 | A kind of measuring system and method for hydraulic support top beam bearing height and attitude |
CN109737874A (en) * | 2019-01-17 | 2019-05-10 | 广东省智能制造研究所 | Dimension of object measurement method and device based on 3D vision technology |
-
2020
- 2020-07-28 CN CN202010742021.6A patent/CN111879244B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106908000A (en) * | 2017-01-20 | 2017-06-30 | 中国矿业大学 | A kind of measuring system and method for hydraulic support top beam bearing height and attitude |
CN109737874A (en) * | 2019-01-17 | 2019-05-10 | 广东省智能制造研究所 | Dimension of object measurement method and device based on 3D vision technology |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112419482A (en) * | 2020-11-23 | 2021-02-26 | 太原理工大学 | Three-dimensional reconstruction method for mine hydraulic support group pose fused with depth point cloud |
CN112419482B (en) * | 2020-11-23 | 2023-12-01 | 太原理工大学 | Three-dimensional reconstruction method for group pose of mine hydraulic support with depth point cloud fusion |
CN115903592A (en) * | 2022-11-10 | 2023-04-04 | 山东新普锐智能科技有限公司 | Hydraulic car unloader control method and system based on pose detection |
CN115903592B (en) * | 2022-11-10 | 2024-05-10 | 山东新普锐智能科技有限公司 | Control method and system of hydraulic unloader based on pose detection |
Also Published As
Publication number | Publication date |
---|---|
CN111879244B (en) | 2022-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111563442B (en) | Slam method and system for fusing point cloud and camera image data based on laser radar | |
CN110781827B (en) | Road edge detection system and method based on laser radar and fan-shaped space division | |
CN109685066B (en) | Mine target detection and identification method based on deep convolutional neural network | |
CN106709950B (en) | Binocular vision-based inspection robot obstacle crossing wire positioning method | |
CN111598946B (en) | Object pose measuring method and device and storage medium | |
CN111879244B (en) | Method for measuring support height and top beam inclination angle of hydraulic support of fully mechanized mining face | |
CN103136525B (en) | A kind of special-shaped Extended target high-precision locating method utilizing Generalized Hough Transform | |
CN111223133A (en) | Registration method of heterogeneous images | |
CN113470090A (en) | Multi-solid-state laser radar external reference calibration method based on SIFT-SHOT characteristics | |
KR101460313B1 (en) | Apparatus and method for robot localization using visual feature and geometric constraints | |
CN113379712A (en) | Steel bridge bolt disease detection method and system based on computer vision | |
CN113884002A (en) | Pantograph slide plate upper surface detection system and method based on two-dimensional and three-dimensional information fusion | |
CN108108737A (en) | Closed loop detecting system and method based on multi-feature fusion | |
CN111783721A (en) | Lane line extraction method of laser point cloud and electronic equipment | |
Wang | Automatic extraction of building outline from high resolution aerial imagery | |
CN110246165B (en) | Method and system for improving registration speed of visible light image and SAR image | |
CN109902532A (en) | A kind of vision closed loop detection method | |
CN111964595B (en) | Fully-mechanized mining face hydraulic support supporting height and top beam inclination angle measuring device | |
CN114463425A (en) | Workpiece surface featureless point positioning method based on probability Hough linear detection | |
CN111462310B (en) | Bolt defect space positioning method based on multi-view geometry | |
CN113313765A (en) | Positioning method, positioning device, electronic equipment and storage medium | |
Betge-Brezetz et al. | Object-based modelling and localization in natural environments | |
CN116468805A (en) | Homography matrix determination method, system and equipment | |
CN111445578B (en) | Map three-dimensional road feature identification method and system | |
CN115457130A (en) | Electric vehicle charging port detection and positioning method based on depth key point regression |
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 |