CN115631215B - Moving target monitoring method, system, electronic equipment and storage medium - Google Patents

Moving target monitoring method, system, electronic equipment and storage medium Download PDF

Info

Publication number
CN115631215B
CN115631215B CN202211629156.7A CN202211629156A CN115631215B CN 115631215 B CN115631215 B CN 115631215B CN 202211629156 A CN202211629156 A CN 202211629156A CN 115631215 B CN115631215 B CN 115631215B
Authority
CN
China
Prior art keywords
point cloud
scanning
point
moving
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.)
Active
Application number
CN202211629156.7A
Other languages
Chinese (zh)
Other versions
CN115631215A (en
Inventor
杨星
胡以华
高皓琪
梁振宇
胡睿晗
许颢砾
朱东涛
穆华
王阳阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
National University of Defense Technology
Original Assignee
National University of Defense Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by National University of Defense Technology filed Critical National University of Defense Technology
Priority to CN202211629156.7A priority Critical patent/CN115631215B/en
Publication of CN115631215A publication Critical patent/CN115631215A/en
Application granted granted Critical
Publication of CN115631215B publication Critical patent/CN115631215B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/77—Determining position or orientation of objects or cameras using statistical methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/62—Extraction of image or video features relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10141—Special mode during image acquisition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30241—Trajectory
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computing Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Length Measuring Devices With Unspecified Measuring Means (AREA)

Abstract

The invention provides a moving target monitoring method, a system, electronic equipment and a storage medium, wherein the method comprises the following steps: setting a scanning stepping distance; moving the moving target according to the scanning stepping distance, and scanning the moving target for the first time in the moving process to obtain a first scanning point Yun Juzhen of the moving target; rotating the moving target by 90 degrees anticlockwise, moving according to the scanning stepping distance, and scanning the moving target for the second time in the moving process to obtain a second scanning point cloud matrix of the moving target; constructing a square matrix; performing high candidate point cloud extraction on the square matrix to form a high candidate point cloud set; performing cluster classification on each point cloud to be selected in the point cloud sets to be selected to determine the moving track of the moving target; and predicting the position of the moving target according to the moving track of the moving target. The invention can realize rapid extraction of the monitored target data and realize target monitoring with higher precision.

Description

Moving target monitoring method, system, electronic equipment and storage medium
Technical Field
The invention belongs to the technical field of automatic monitoring, and particularly relates to a moving target monitoring method and system, electronic equipment and a storage medium.
Background
In the processes of cutting machining and high-precision target detection of a precision machine tool, the precision degree of target imaging determines the machining quality and the detection precision of a workpiece to be machined. For example, in the process of automated precision machine tool machining, the participation of a high-precision milling cutter cannot be avoided; in the field of automatic driving, high-precision target detection can improve the obstacle avoidance capability of an automobile. Therefore, on-line monitoring of targets plays an important role in the smart manufacturing fields such as machine tool cutting, auto-driving, and the like.
At present, an online target monitoring system relates to four-dimensional problems of monitoring precision, conversion time, camera installation position and laser processing technology continuity, and is a comprehensive problem of the four problems. Firstly, the problems of high-precision monitoring, long monitoring conversion time and long reconstruction time need to be solved; secondly, the monitoring task is a set of 2D (light source adding) and 3D point cloud acquisition equipment combined architecture system, the point cloud monitoring device is designed and finished, and the mountable position of internal control is very limited; the laser point cloud is a device which basically works continuously, almost has no intermittent time, and has considerable limitation on measuring target data in the link; monitoring of high precision targets is often accompanied by dense point cloud data. For the calculation of dense point cloud data, online target monitoring needs to be matched due to calculation efficiency. Therefore, the current artificial intelligence based feature extraction algorithm is not efficient due to the calculation efficiency.
Disclosure of Invention
One of the objectives of the present invention is to provide a moving target monitoring method, which can realize rapid extraction of monitored target data and realize target monitoring with higher accuracy.
Another object of the present invention is to provide a moving object monitoring system.
It is a third object of the present invention to provide an electronic apparatus.
It is a fourth object of the present invention to provide a storage medium.
In order to achieve one of the purposes, the invention adopts the following technical scheme:
a moving object monitoring method, the moving object monitoring method comprising:
s1, setting a scanning stepping distance;
s2, moving a moving target according to the scanning stepping distance, and scanning the moving target for the first time in the moving process to obtain a first scanning point Yun Juzhen of the moving target;
s3, rotating the moving target by 90 degrees anticlockwise, moving according to the scanning stepping distance, and scanning the moving target for the second time in the moving process to obtain a second scanning point cloud matrix of the moving target;
s4, acquiring a maximum abscissa, a minimum abscissa, a maximum ordinate and a minimum ordinate in each point cloud from the first scanning point Yun Juzhen and the second scanning point cloud matrix to construct a square matrix;
s5, extracting high candidate point clouds from the square matrix to form a high candidate point cloud set;
s6, performing cluster classification on each point cloud to be selected of the point cloud sets to be selected to determine a moving track of the moving target;
and S7, predicting the position of the moving target according to the moving track of the moving target.
Further, the first scanning point cloud matrix isW*HA matrix of dimensions; the position coordinate of the starting point cloud of the first scanning point cloud matrix is (0,0); wherein, the first and the second end of the pipe are connected with each other,Wthe number of longitudinal point clouds, i.e. the number of rows,Hthe number of the horizontal point clouds is the number of the rows;
the second scanning point cloud matrix isH*WA matrix of dimensions; the starting point cloud of the second scan point cloud matrix has position coordinates of (0,W) (ii) a Wherein the content of the first and second substances,Wthe number of horizontal point clouds, i.e. the number of columns,Hthe number of longitudinal point clouds is the number of lines;
the square matrix is (H+W）*（H+W) A matrix of dimensions; four vertex positions of the square matrixThe coordinates are respectively-W，0）、（H，0）、（H，H+W) And-W，H+W）。
Further, in step S5, the specific process of extracting the high candidate point cloud from the square matrix includes:
s51, acquiring an inscribed circle of the square matrix;
s52, extracting an outer point cloud outside the inscribed circle from the square matrix to form an outer point cloud set;
s53, calculating a first mean value of horizontal coordinates and a second mean value of vertical coordinates of all the external point clouds in the external point cloud set;
and S54, counting all the corresponding external point clouds of which the abscissa is larger than the first mean value and the ordinate is larger than the second mean value in the external point cloud set, and then putting the external point clouds into an empty high candidate point cloud set.
Further, in step S6, the specific implementation process of the cluster classification includes:
step S61, setting the initial serial number of the clusters in the empty clustering cluster asi=1；
S62, selecting a point cloud to be selected from the point cloud set to be selected and putting the point cloud to be selected into the first stepiIn the number cluster;
s63, setting the initial value of the serial number of the residual high candidate point clouds in the high candidate point cloud set asj=1；
Step S64 of calculating the secondiThe horizontal coordinate mean value, the vertical coordinate mean value and the manifold distance mean value of all the point clouds to be selected in the cluster;
step S65, determiningjThe abscissa of the point cloud with the highest candidate point and the second coordinateiWhether the mean interval of the horizontal coordinates of all the high candidate point clouds in the cluster is less thanXA direction distance threshold value ofjThe vertical coordinate of the point cloud with the highest candidate point and the second pointiWhether the mean interval of the vertical coordinates of all the high candidate point clouds in the number cluster is less thanYIf yes, the step S66 is executed; if not, the step S67 is executed;
step S66, calculating the secondjThe manifold distance of the point cloud with the highest candidate point is judgedBreak the firstjManifold distance of the point cloud to be selected and the firstiWhether manifold distance mean intervals of all high candidate point clouds in the cluster are smaller than a manifold distance threshold value or not, if so, determining the first point cloudjPutting the point cloud of the individual height to be selected into the firstiIn cluster, go to step S67; if not, the step S68 is executed;
step S67, judgmentjWhether or not equal toJ’If yes, go to step S68; if not, then orderj=j+1, return to step S64;
wherein, the first and the second end of the pipe are connected with each other,J’obtaining the number of the high candidate point clouds in the current high candidate point cloud set;
s68, judging whether the current point cloud set to be selected is empty or not, if so, ending; if not, then orderi=iAnd +1, forming a new high point cloud set to be selected by the residual high point clouds to be selected as the current high point cloud set to be selected, and returning to the step S62.
Further, in step S66, the manifold distance of the high candidate point cloud is a sum of squares of an abscissa and an ordinate of the high candidate point cloud.
In order to achieve the second purpose, the invention adopts the following technical scheme:
a moving object monitoring system, the moving object monitoring system comprising:
a setting module for setting a scanning stepping distance;
the first scanning module is used for moving the moving target according to the scanning stepping distance and scanning the moving target for the first time in the moving process to obtain a first scanning point Yun Juzhen of the moving target;
the second scanning module is used for moving the moving target according to the scanning stepping distance after rotating the moving target by 90 degrees anticlockwise, and performing second scanning on the moving target in the moving process to obtain a second scanning point cloud matrix of the moving target;
the building module is used for obtaining the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate in each point cloud from the first scanning point Yun Juzhen and the second scanning point cloud matrix so as to build a square matrix;
the extraction module is used for extracting high candidate point clouds from the square matrix to form a high candidate point cloud set;
the cluster classification module is used for performing cluster classification on each point cloud with high candidate points of the point cloud sets with high candidate points to determine the moving track of the moving target;
and the position prediction module is used for predicting the position of the moving target according to the moving track of the moving target.
Further, the extraction module comprises:
the acquisition submodule is used for acquiring an inscribed circle of the square matrix;
the extraction submodule is used for extracting an outer point cloud outside the inscribed circle from the square matrix to form the outer point cloud set;
the first calculation sub-module is used for calculating a first mean value of horizontal coordinates and a second mean value of vertical coordinates of all the external point clouds in the external point cloud set;
and the counting submodule is used for counting all the corresponding external point clouds of which the abscissa is greater than the first mean value and the ordinate is greater than the second mean value in the external point cloud set and then putting the external point clouds into an empty high candidate point cloud set.
Further, the cluster classification module comprises:
a first setting submodule for setting an initial serial number of a cluster in an empty cluster toi=1；
A selection submodule for selecting a point cloud to be selected from the point cloud set to be selected and placing the point cloud to be selected in the second moduleiIn cluster number;
a second setting submodule for setting the initial value of the serial number of the remaining high candidate point clouds in the high candidate point cloud set to bej=1；
A second calculation submodule for calculating the secondiThe horizontal coordinate mean value, the vertical coordinate mean value and the manifold distance mean value of all the point clouds to be selected in the cluster;
a first judgment sub-module for judging whetherjThe abscissa of the point cloud with the height to be selected and the point cloudFirst, theiWhether the mean interval of the horizontal coordinates of all the high candidate point clouds in the cluster is less thanXA direction distance threshold value ofjThe vertical coordinate of the point cloud with the highest candidate point and the second pointiWhether the mean interval of the vertical coordinates of all the high candidate point clouds in the cluster is less thanYA direction distance threshold, if so, then the second stepjThe horizontal coordinate and the vertical coordinate of the point cloud to be selected are transmitted to a first judgment submodule; if not, thenjTransmitting to a second judgment submodule;
a second judgment sub-module for calculating the secondjThe manifold distance of the point clouds to be selected is judgedjManifold distance of the point cloud to be selected and the firstiWhether the manifold distance mean value interval of all the high point clouds to be selected in the number cluster is smaller than a manifold distance threshold value or not, if so, the first point cloud is judged to be selectedjThe point cloud of the individual high candidate is put into the firstiIn cluster, and willjTransmitting to a third judgment submodule; if not, thenjTransmitting to a fourth judgment submodule;
a third judgment sub-module for judgingjWhether or not equal toJ’If yes, then willjTransmitting to a fourth judgment submodule; if not, then letj=j+1, and willjTransmitting to a second computing submodule;
wherein the content of the first and second substances,J’obtaining the number of the high candidate point clouds in the current high candidate point cloud set;
the fourth judgment sub-module is used for judging whether the current point cloud set to be selected is empty or not, and if yes, ending the judgment; if not, then leti= i And +1, forming a new high point cloud set to be selected by the residual high point clouds to be selected, using the new high point cloud set to be selected as the current high point cloud set to be selected, and transmitting the current high point cloud set to the selection submodule.
In order to achieve the third purpose, the invention adopts the following technical scheme:
an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the moving object monitoring method when executing the computer program.
In order to achieve the fourth purpose, the invention adopts the following technical scheme:
a storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the moving object monitoring method described above.
In summary, the scheme provided by the invention has the following technical effects:
the method comprises the steps of moving according to a scanning stepping distance, and carrying out first scanning on a moving target in the moving process to obtain a first scanning point Yun Juzhen of the moving target so as to obtain the initial size of the target; rotating the moving target by 90 degrees anticlockwise, moving according to the scanning stepping distance, and scanning the moving target for the second time in the moving process to obtain a second scanning point cloud matrix of the moving target, so that denser high-precision point cloud data are effectively acquired; acquiring a maximum abscissa, a minimum abscissa, a maximum ordinate and a minimum ordinate in each point cloud from the first scanning point Yun Juzhen and the second scanning point cloud matrix to construct a square matrix, thereby solving the precision error of the line scanning camera and improving the precision of the target to be detected; extracting high candidate point clouds from the square matrix to form a high candidate point cloud set; and performing cluster classification on each point cloud to be selected of the point cloud sets to be selected so as to determine the moving track of the moving target and perform position prediction, thereby realizing high-precision extraction of data of the target in a short time and improving the efficiency of on-line monitoring of the target.
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 embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart of a moving object monitoring method according to the present invention;
FIG. 2 is a schematic diagram of a square matrix for an exemplary grinding tool of the present invention;
fig. 3 is a schematic diagram of the cluster classification result of the grinding tool of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 embodiment provides a moving target monitoring method, and referring to fig. 1, the moving target monitoring method includes:
s1, setting a scanning stepping distance.
The scanning step distance of the present embodiment may be set to 2εum，εAnd the point cloud detection precision is obtained.
S2, moving the moving target according to the scanning stepping distance, and scanning the moving target for the first time in the moving process to obtain a first scanning point Yun Juzhen of the moving target;
in this embodiment, a point cloud collection device is first installed, and the point cloud collection device and a moving target are distributed in a vertical direction, so that the distance between the point cloud collection device and the target to be detected (i.e., the moving target) is within a monitoring range, the moving target is fixed on a moving platform, and the moving platform is a marble platform. To ensure that a linear-rotary machine can be implementedεum moving precision, the moving platform is a marble gantry frame, and the moving guide rail is a crossed roller guide rail. In order to obtain high acceleration, the mounting component is made of aviation aluminum and is designed in a hollow mode.
The linear-rotary motor drives the mobile platform to move a mobile object (such as a part to be monitored) so as to scan the step distance 2εum trigger signal triggers the point cloud acquisition device to perform scanning processing (i.e. the step distance per moving scan is 2εWhen um, trigger a touchSignals the point cloud acquisition equipment to carry out scanning once), and controls the linear-rotating motor to drive the moving platform to move the moving target by half of the scanning stepping distance (namely, the point cloud acquisition equipment moves by a scanning stepping distance) in a recursive mode after scanning is finishedεum), by scanning step distance 2εum trigger signal triggers the point cloud collecting device to perform recursive scanning (i.e. the linear-rotary motor firstly controls the mobile platform to move firstlyεum later, then at 2 per moveεum, controlling and triggering a trigger signal to carry out scanning processing on the point cloud acquisition equipment for one time until the mobile target is scanned by recursion outgoing), and obtaining first scanning point cloud data. The first scan point cloud data of the present embodiment is represented by a first scan point cloud matrix. The first cloud matrix of scanning points isW*HA matrix of dimensions, the position coordinates of the starting point cloud of the first scanning point cloud matrix being (0,0),Wthe number of longitudinal point clouds, i.e. the number of rows (i.e. the longitudinal scan length of the moving object),Hthe number of horizontal point clouds is the number of columns (i.e. the horizontal scanning width of the moving object).
If the point cloud acquisition equipment is 3200 point clouds along the X-axis direction, one point cloud is generated along the Y-axis direction for every scanning stepping distance, and the Y-axis direction is 16000 point clouds. Assuming that the origin of coordinates of the first scanning point cloud matrix (i.e., the location coordinates of the starting point cloud) is (0,0), the horizontal coordinate interval point can be expressed as
Figure DEST_PATH_IMAGE001
The ordinate interval points can be expressed as
Figure 307919DEST_PATH_IMAGE002
Then the first scan point cloud matrix is represented as:
Figure 287376DEST_PATH_IMAGE004
。
and S3, rotating the moving target by 90 degrees anticlockwise, moving according to the scanning stepping distance, and scanning the moving target for the second time in the moving process to obtain a second scanning point cloud matrix of the moving target.
This embodiment performs a 90 degree hour rotation according to the following formula:
Figure 880163DEST_PATH_IMAGE006
；
wherein the content of the first and second substances,Xbefore rotationXA shaft;Ybefore rotationYA shaft;
Figure DEST_PATH_IMAGE007
is rotatedXA shaft; />
Figure 150738DEST_PATH_IMAGE008
Is rotatedYA shaft.
After the moving target is rotated 90 degrees counterclockwise, the linear-rotary motor is controlled to drive the moving platform to move and rotate, and then the moving target moves by a half scanning step distance (namely, the moving target moves by the scanning step distance)εum), by scanning step distance 2εThe triggering signal of um triggers the point cloud acquisition equipment to perform secondary scanning processing to obtain second scanning point cloud data. The second scanning point cloud data of the embodiment is represented by a second scanning point cloud matrix, and the second scanning point cloud matrix isH*WA matrix of dimensions, the position coordinates of the starting point cloud of the second scanned point cloud matrix being (0,W），Wthe number of horizontal point clouds, i.e. the number of columns,Hthe number of longitudinal point clouds, i.e., the number of rows, and the second scanning point cloud matrix is represented as:
Figure DEST_PATH_IMAGE009
。
s4, acquiring a maximum abscissa, a minimum abscissa, a maximum ordinate and a minimum ordinate in each point cloud from the first scanning point Yun Juzhen and the second scanning point cloud matrix to construct a square matrix;
the embodiment extracts the maximum abscissa in the first scanning point Yun Juzhen and the second scanning point cloud matrixHMinimum abscissa-WMost preferablyLarge ordinateH+WAnd minimum ordinate 0, construct: (H+W）*（H+W) A square matrix of dimension, four vertex position coordinates of the square matrix are respectively-W，0）、（H，0）、（H，H+W) And-W，H+W) Reference is made to the square matrix of fig. 2, taking as an example a grinding tool.
And S5, extracting high candidate point clouds from the square matrix to form a high candidate point cloud set.
According to the embodiment, the outer point cloud outside the inner circle tangent plane is obtained according to the inner circle radius of the square matrix, and the high candidate point cloud of the moving target is extracted from the outer point cloud. The specific process of extracting the high candidate point cloud from the square matrix comprises the following steps:
s51, acquiring an inscribed circle of the square matrix;
s52, extracting an outer point cloud outside the inscribed circle from the square matrix to form an outer point cloud set;
in this embodiment, the position coordinates of each external point cloud in the external point cloud set satisfy the following conditions:
(X-X k ) 2 +(Y-Y k ) 2 ﹥R 2 inner ；
wherein the content of the first and second substances,X k andY k respectively as an outer point cloudkThe abscissa and ordinate of the individual outside point cloud;XandYrespectively an abscissa and an ordinate of a central point of the inscribed circle;R inner is the radius of the inscribed circle;k=1，2，…，K，Kand collecting the number of the outer point clouds in the outer point cloud.
Suppose thatXAndYscanning the moving target by the point cloud acquisition equipment to obtain point cloud dataXThe direction has 3200 point clouds,Y6400 point clouds are arranged in the direction, and the outer point clouds outside the plane of the inscribed circle are obtained according to the formulaX h AndY h 。
and S53, calculating a first mean value of horizontal coordinates and a second mean value of vertical coordinates of all the external point clouds in the external point cloud set.
And S54, counting all the external point clouds corresponding to the external point cloud set with the abscissa larger than the first mean value and the ordinate larger than the second mean value, and then putting the external point clouds into an empty high candidate point cloud set.
The high candidate point clouds in the high candidate point cloud set of the embodiment satisfy the following conditions:
X j ﹥mean(X k )；
Y j ﹥mean(Y k )；
wherein, the first and the second end of the pipe are connected with each other,X j andY j respectively as the first point cloud setjThe horizontal coordinate and the vertical coordinate of the point cloud to be selected,j=1，2，…，J，Jcollecting the point clouds with high candidate number;X k andY k respectively as the outer point cloudkThe abscissa and ordinate of the individual outside point cloud;mean(X k ) For outer point cloud concentrationKThe mean value of the abscissa of the individual outer point cloud, namely the first mean value;mean(Y k ) For outer point cloud concentrationKAnd the mean value of the ordinate of the individual outer point clouds is the second mean value.
S6, performing cluster classification on each point cloud to be selected of the point cloud sets to be selected to determine a moving track of the moving target;
and performing cluster classification on each high candidate point cloud of the high candidate point cloud set, and firstly obtaining initialized cluster clusters and distributing point cloud pairs. And performing cluster updating processing on the point cloud distributed to the initialized cluster to obtain a self-adaptive updating result of the cluster. Based on the self-adaptive updating result of the cluster, monitoring calculation is performed according to the preset condition constraint to obtain a monitoring result, and referring to the cluster classification result of fig. 3, which takes the grinding tool as an example.
The embodiment adopts an unsupervised clustering mode and utilizes the steps to obtainX j AndY j to realize cluster clusteringAnd (4) updating. The specific implementation process of cluster classification comprises the following steps:
step S61, setting the initial serial number of the clusters in the empty clustering cluster asi=1；
S62, selecting a point cloud to be selected from the point cloud set to be selected and placing the point cloud to be selected into the first stepiHorn clusterC i Performing the following steps;
s63, setting the initial value of the sequence number of the residual high point clouds to be selected in the high point cloud set to bej=1；
Step S64 of calculating the secondiThe horizontal coordinate mean value, the vertical coordinate mean value and the manifold distance mean value of all the point clouds to be selected in the cluster;
step S65, judgingjThe abscissa of the point cloud with the highest candidate point and the second coordinateiWhether the mean interval of the horizontal coordinates of all the high candidate point clouds in the cluster is less thanXA direction distance threshold value ofjThe vertical coordinate of the point cloud with the highest candidate point and the second pointiWhether the mean interval of the vertical coordinates of all the high candidate point clouds in the number cluster is less thanYIf yes, the step S66 is executed; if not, the step S67 is executed;
is provided withXThreshold of direction distanceφ x AndYthreshold of direction distanceφ y When it comes tojHorizontal coordinate of individual high candidate point cloudX j (i) (in theXDirection and distance) fromiThe mean of the abscissas corresponding to each cluster (i.e. the firstiAll high candidate points in each cluster areXDirection mean distance) difference (i.e., spacing) less thanXThreshold of direction distanceφ x And a firstjA high candidate point cloud isYDirection distance (abscissa)Y j (i) And a first step ofiMean value of ordinate corresponding to individual cluster (i.e. the firstiAll the high candidate point clouds in each cluster areYDirection mean distance) difference less thanYThreshold of direction distanceφ y (i.e. the mean value of the vertical coordinates of all the high candidate point clouds), namely:
X j (i)-[C i ] x <φ x ；
Y j (i)-[C i ] y <φ y 。
step S66, calculating the secondjThe manifold distance of the point cloud with the highest candidate point is judgedjManifold distance of the point cloud to be selected and the firstiWhether the manifold distance mean value interval of all the high point clouds to be selected in the number cluster is smaller than a manifold distance threshold value or not, if so, the first point cloud is judged to be selectedjPutting the point cloud of the individual height to be selected into the firstiIn cluster, go to step S67; if not, the step S68 is executed;
first of this embodimentjThe manifold distance of the point clouds to be selected is the firstjThe sum of squares of the abscissa and ordinate of the individual point clouds, i.e.X j 2 AndY j 2 . When it comes tojThe manifold distance of the individual high candidate point clouds and the existing firstiThe manifold distance mean value interval of all high candidate point clouds in the cluster is less than the manifold distance threshold valueφThen it is firstjThe point cloud of the individual high candidate belongs toiCluster number.
Step S67, judgmentjWhether or not equal toJ’If yes, go to step S68; if not, then letj=j+1, return to step S64;
wherein the content of the first and second substances,J’obtaining the number of the high candidate point clouds in the current high candidate point cloud set;
s68, judging whether the high candidate point cloud set is empty or not, if so, ending; if not, then orderi= i And +1, forming a new high point cloud set to be selected by the residual high point clouds to be selected as the current high point cloud set to be selected, and returning to the step S62.
And S7, predicting the position of the moving target according to the moving track of the moving target.
In the embodiment, the initial size of the target is obtained by moving according to the scanning stepping distance and scanning the moving target for the first time in the moving process to obtain a first scanning point Yun Juzhen of the moving target; after rotating the moving target by 90 degrees anticlockwise, moving the moving target according to the scanning stepping distance, and scanning the moving target for the second time in the moving process to obtain a second scanning point cloud matrix of the moving target, so that denser high-precision point cloud data are effectively acquired; acquiring a maximum abscissa, a minimum abscissa, a maximum ordinate and a minimum ordinate in each point cloud from the first scanning point Yun Juzhen and the second scanning point cloud matrix to construct a square matrix, so that the accuracy error of the line scanning camera is solved, and the accuracy of the target to be detected is improved; extracting high candidate point clouds from the square matrix to form a high candidate point cloud set; and performing cluster classification on each point cloud to be selected of the point cloud sets to be selected so as to determine the moving track of the moving target and perform position prediction, thereby realizing high-precision extraction of data of the target in a short time and improving the efficiency of on-line monitoring of the target.
The above embodiments can be implemented by the moving object monitoring system given in the following embodiments:
another embodiment provides a moving object monitoring system, including:
the setting module is used for setting a scanning stepping distance;
the first scanning module is used for moving the moving target according to the scanning stepping distance and scanning the moving target for the first time in the moving process to obtain a first scanning point Yun Juzhen of the moving target;
the second scanning module is used for moving the moving target according to the scanning stepping distance after rotating the moving target by 90 degrees anticlockwise, and performing second scanning on the moving target in the moving process to obtain a second scanning point cloud matrix of the moving target;
the building module is used for obtaining the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate in each point cloud from the first scanning point Yun Juzhen and the second scanning point cloud matrix so as to build a square matrix;
the extraction module is used for extracting high candidate point clouds from the square matrix to form a high candidate point cloud set;
the cluster classification module is used for performing cluster classification on each point cloud to be selected of the point cloud sets to be selected so as to determine the moving track of the moving target;
and the position prediction module is used for predicting the position of the moving target according to the moving track of the moving target.
Further, the extraction module comprises:
the acquisition submodule is used for acquiring an inscribed circle of the square matrix;
the extraction submodule is used for extracting an outer point cloud outside the inscribed circle from the square matrix to form the outer point cloud set;
the first calculation sub-module is used for calculating a first mean value of horizontal coordinates and a second mean value of vertical coordinates of all the external point clouds in the external point cloud set;
and the counting submodule is used for counting all the corresponding external point clouds of which the abscissa is greater than the first mean value and the ordinate is greater than the second mean value in the external point cloud set and then putting the external point clouds into an empty high candidate point cloud set.
Further, the cluster classification module comprises:
a first setting submodule for setting an initial serial number of a cluster in an empty cluster toi=1；
A selection submodule for selecting a point cloud to be selected from the point cloud set to be selected and placing the point cloud to be selected in the second moduleiIn cluster number;
a second setting submodule for setting the initial value of the serial number of the remaining high candidate point clouds in the high candidate point cloud set to bej=1；
A second calculation submodule for calculating the secondiThe horizontal coordinate mean value, the vertical coordinate mean value and the manifold distance mean value of all the point clouds to be selected in the cluster;
a first judgment sub-module for judging the secondjThe abscissa of the point cloud with the highest candidate point and the second coordinateiWhether the mean interval of the horizontal coordinates of all the high candidate point clouds in the cluster is less thanXA direction distance threshold value ofjThe vertical coordinate of the point cloud to be selected and the first pointiVertical seats of all high candidate point clouds in clusterWhether the standard mean interval is less thanYA direction distance threshold, if so, then the second stepjThe horizontal coordinate and the vertical coordinate of the point cloud to be selected are transmitted to a first judgment submodule; if not, the method willjTransmitting to a second judgment submodule;
a second judgment sub-module for calculating the secondjThe manifold distance of the point clouds to be selected is judgedjManifold distance of the point cloud to be selected and the firstiWhether the manifold distance mean value interval of all the high point clouds to be selected in the number cluster is smaller than a manifold distance threshold value or not, if so, the first point cloud is judged to be selectedjThe point cloud of the individual high candidate is put into the firstiIn cluster and willjTransmitting to a third judgment submodule; if not, thenjTransmitting to a fourth judgment submodule;
a third judgment sub-module for judgingjWhether or not equal toJ’If yes, then willjTransmitting to a fourth judgment submodule; if not, then orderj=j+1, and willjTransmitting to a second computing submodule;
wherein the content of the first and second substances,J’the number of the point clouds to be selected which are left in the point cloud set to be selected which is high is the current number of the point clouds to be selected which are left high;
a fourth judgment submodule, configured to judge whether the high candidate point cloud set is empty, if so, ending the process; if not, then orderi= i And +1, forming a new high point cloud set to be selected by the residual high point clouds to be selected, using the new high point cloud set to be selected as the current high point cloud set to be selected, and transmitting the current high point cloud set to the selection submodule.
Yet another embodiment provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps in the moving object monitoring method provided in the above embodiment when executing the computer program.
Yet another embodiment provides a storage medium having a computer program stored thereon, where the computer program, when executed by a processor, implements the steps in the moving object monitoring method provided by the above embodiment.
It should be noted that the technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, the scope of the present description should be considered. The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.

Claims (8)

1. A moving object monitoring method, comprising:
s1, setting a scanning stepping distance;
s2, moving a moving target according to the scanning stepping distance, and scanning the moving target for the first time in the moving process to obtain a first scanning point Yun Juzhen of the moving target;
s3, rotating the moving target by 90 degrees anticlockwise, moving according to the scanning stepping distance, and scanning the moving target for the second time in the moving process to obtain a second scanning point cloud matrix of the moving target;
s4, acquiring a maximum abscissa, a minimum abscissa, a maximum ordinate and a minimum ordinate in each point cloud from the first scanning point Yun Juzhen and the second scanning point cloud matrix to construct a square matrix;
s5, extracting high candidate point clouds from the square matrix to form a high candidate point cloud set;
in step S5, the specific process of extracting the high candidate point cloud from the square matrix includes:
s51, acquiring an inscribed circle of the square matrix;
s52, extracting an outer point cloud outside the inscribed circle from the square matrix to form an outer point cloud set;
s53, calculating a first mean value of horizontal coordinates and a second mean value of vertical coordinates of all the external point clouds in the external point cloud set;
s54, counting all the external point clouds corresponding to the external point clouds, wherein the horizontal coordinates of the external point clouds are larger than the first mean value, and the vertical coordinates of the external point clouds are larger than the second mean value, and then putting the external point clouds into an empty high-candidate point cloud set;
s6, performing cluster classification on each point cloud to be selected of the point cloud sets to be selected to determine a moving track of the moving target;
and S7, predicting the position of the moving target according to the moving track of the moving target.
2. The moving object monitoring method of claim 1, wherein the first cloud matrix of scanning points isW*HA matrix of dimensions; the position coordinate of the starting point cloud of the first scanning point cloud matrix is (0,0); wherein the content of the first and second substances,Wthe number of longitudinal point clouds, i.e. the number of rows,Hthe number of the horizontal point clouds is the number of the columns;
the second scanning point cloud matrix isH*WA matrix of dimensions; the starting point cloud of the second scan point cloud matrix has position coordinates of (0,W) (ii) a Wherein the content of the first and second substances,Wthe number of horizontal point clouds, i.e. the number of columns,Hthe number of longitudinal point clouds is the number of lines;
the square matrix is (H+W）*（H+W) A matrix of dimensions; the coordinates of the four vertex positions of the square matrix are respectively-W，0）、（H，0）、（H，H+W) And-W，H+W）。
3. The moving object monitoring method according to claim 1, wherein in step S6, the specific implementation process of the cluster classification includes:
step S61, setting the initial serial number of the clusters in the empty clustering cluster asi=1；
S62, selecting a point cloud with high candidate from the point cloud set with high candidate and putting the point cloud with high candidate into the point cloud setFirst, theiIn cluster number;
s63, setting the initial value of the sequence number of the residual high point clouds to be selected in the high point cloud set to bej=1；
Step S64 of calculating the secondiThe horizontal coordinate mean value, the vertical coordinate mean value and the manifold distance mean value of all the point clouds to be selected in the cluster;
step S65, judgingjThe abscissa of the point cloud with the highest candidate point and the second coordinateiWhether the mean interval of the horizontal coordinates of all the high candidate point clouds in the cluster is less thanXA direction distance threshold value ofjThe vertical coordinate of the point cloud with the highest candidate point and the second pointiWhether the mean interval of the vertical coordinates of all the high candidate point clouds in the number cluster is less thanYIf yes, the process goes to step S66; if not, the step S67 is executed;
step S66, calculating the secondjThe manifold distance of the point cloud with the highest candidate point is judgedjManifold distance of the point cloud to be selected and the firstiWhether the manifold distance mean value interval of all the high point clouds to be selected in the number cluster is smaller than a manifold distance threshold value or not, if so, the first point cloud is judged to be selectedjThe point cloud of the individual high candidate is put into the firstiIn cluster number, go to step S67; if not, the step S68 is executed;
step S67, judgmentjWhether or not equal toJ’If yes, go to step S68; if not, then letj=j+1, return to step S64;
wherein, the first and the second end of the pipe are connected with each other,J’obtaining the number of the high candidate point clouds in the current high candidate point cloud set;
s68, judging whether the high candidate point cloud set is empty or not, if so, ending; if not, then leti=i+1, forming a new high point cloud set to be selected by the remaining high point clouds to be selected, using the new high point cloud set to be selected as the current high point cloud set to be selected, and returning to the step S62.
4. The moving object monitoring method according to claim 3, wherein in step S66, the manifold distance of the high candidate point cloud is the square sum of the abscissa and the ordinate of the high candidate point cloud.
5. A moving object monitoring system, comprising:
a setting module for setting a scanning stepping distance;
the first scanning module is used for moving the moving target according to the scanning stepping distance and scanning the moving target for the first time in the moving process to obtain a first scanning point Yun Juzhen of the moving target;
the second scanning module is used for moving the moving target according to the scanning stepping distance after rotating the moving target by 90 degrees anticlockwise, and performing second scanning on the moving target in the moving process to obtain a second scanning point cloud matrix of the moving target;
the building module is used for obtaining the maximum abscissa, the minimum abscissa, the maximum ordinate and the minimum ordinate of each point cloud from the first scanning point Yun Juzhen and the second scanning point cloud matrix so as to build a square matrix;
the extraction module is used for extracting high candidate point clouds from the square matrix to form a high candidate point cloud set; the extraction module comprises:
the acquisition submodule is used for acquiring an inscribed circle of the square matrix;
the extraction submodule is used for extracting an outer point cloud outside the inscribed circle from the square matrix to form the outer point cloud set;
the first calculation submodule is used for calculating a first mean value of horizontal coordinates and a second mean value of vertical coordinates of all the external point clouds in the external point cloud set;
the statistical submodule is used for counting all the corresponding external point clouds of which the horizontal coordinate is greater than the first mean value and the vertical coordinate is greater than the second mean value in the external point cloud set and then putting the external point clouds into an empty high candidate point cloud set;
the cluster classification module is used for performing cluster classification on each point cloud to be selected of the point cloud sets to be selected so as to determine the moving track of the moving target;
and the position prediction module is used for predicting the position of the moving target according to the moving track of the moving target.
6. The moving object monitoring system of claim 5, wherein the cluster classification module comprises:
a first setting submodule for setting an initial serial number of a cluster in an empty cluster toi=1；
A selection submodule for selecting a point cloud to be selected from the point cloud set to be selected and placing the point cloud to be selected in the second moduleiIn cluster number;
a second setting submodule for setting the initial value of the serial number of the remaining high candidate point clouds in the high candidate point cloud set to bej=1；
A second calculation submodule for calculating the secondiThe horizontal coordinate mean value, the vertical coordinate mean value and the manifold distance mean value of all the point clouds to be selected in the cluster;
a first judgment sub-module for judging the secondjThe abscissa of the point cloud with the highest candidate point and the second coordinateiWhether the mean interval of the horizontal coordinates of all the high candidate point clouds in the cluster is less thanXA direction distance threshold value ofjThe vertical coordinate of the point cloud to be selected and the first pointiWhether the mean interval of the vertical coordinates of all the high candidate point clouds in the cluster is less thanYA direction distance threshold, if so, then the second stepjThe horizontal coordinate and the vertical coordinate of the point cloud to be selected are transmitted to a first judgment submodule; if not, thenjTransmitting to a second judgment submodule;
a second judgment sub-module for calculating the secondjThe manifold distance of the point cloud with the highest candidate point is judgedjManifold distance of the point cloud to be selected and the firstiWhether the manifold distance mean value interval of all the high point clouds to be selected in the number cluster is smaller than a manifold distance threshold value or not, if so, the first point cloud is judged to be selectedjThe point cloud of the individual high candidate is put into the firstiIn cluster, and willjTransmitting to a third judgment submodule; if not, the method willjTransmitting to a fourth judgment submodule;
a third judgment sub-module for judgingjWhether or not equal toJ’If yes, then willjTransmitting to a fourth judgment submodule; if not, then letj=j+1, and willjTransmitting to a second computing submodule;
wherein the content of the first and second substances,J’the number of the point clouds to be selected which are left in the point cloud set to be selected which is high is the current number of the point clouds to be selected which are left high;
a fourth judgment submodule, configured to judge whether the high candidate point cloud set is empty, if so, ending the process; if not, then orderi=iAnd +1, forming a new high point cloud set to be selected by the residual high point clouds to be selected, using the new high point cloud set to be selected as the current high point cloud set to be selected, and transmitting the current high point cloud set to the selection submodule.
7. An electronic device, characterized in that the electronic device comprises a memory and a processor, the memory storing a computer program, the processor implementing the steps in the moving object monitoring method according to any one of claims 1 to 4 when executing the computer program.
8. A storage medium, characterized in that the storage medium has stored thereon a computer program which, when executed by a processor, carries out the steps in the moving object monitoring method of any one of claims 1 to 4.
CN202211629156.7A 2022-12-19 2022-12-19 Moving target monitoring method, system, electronic equipment and storage medium Active CN115631215B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211629156.7A CN115631215B (en) 2022-12-19 2022-12-19 Moving target monitoring method, system, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211629156.7A CN115631215B (en) 2022-12-19 2022-12-19 Moving target monitoring method, system, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN115631215A CN115631215A (en) 2023-01-20
CN115631215B true CN115631215B (en) 2023-04-07

Family

ID=84910624

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211629156.7A Active CN115631215B (en) 2022-12-19 2022-12-19 Moving target monitoring method, system, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115631215B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021072710A1 (en) * 2019-10-17 2021-04-22 深圳市大疆创新科技有限公司 Point cloud fusion method and system for moving object, and computer storage medium
CN113052881A (en) * 2021-03-24 2021-06-29 王程 Automatic registration method for extracting pole point in indoor three-dimensional point cloud
CN114693751A (en) * 2020-12-30 2022-07-01 合肥美亚光电技术股份有限公司 Data processing method, point cloud data registration method and device and intraoral scanning equipment

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107341819B (en) * 2017-05-09 2020-04-28 深圳市速腾聚创科技有限公司 Target tracking method and storage medium
US11151788B2 (en) * 2019-12-27 2021-10-19 Woven Planet North America, Inc. Systems and methods for presenting a reconstructed representation of a moving object detected in a scene
CN113970752A (en) * 2020-07-22 2022-01-25 商汤集团有限公司 Target detection method and device, electronic equipment and storage medium
CN113303564A (en) * 2021-04-30 2021-08-27 泉州华中科技大学智能制造研究院 Dynamic following glue spraying method and system for soles
CN114419098A (en) * 2022-01-18 2022-04-29 长沙慧联智能科技有限公司 Moving target trajectory prediction method and device based on visual transformation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021072710A1 (en) * 2019-10-17 2021-04-22 深圳市大疆创新科技有限公司 Point cloud fusion method and system for moving object, and computer storage medium
CN114693751A (en) * 2020-12-30 2022-07-01 合肥美亚光电技术股份有限公司 Data processing method, point cloud data registration method and device and intraoral scanning equipment
CN113052881A (en) * 2021-03-24 2021-06-29 王程 Automatic registration method for extracting pole point in indoor three-dimensional point cloud

Also Published As

Publication number Publication date
CN115631215A (en) 2023-01-20

Similar Documents

Publication Publication Date Title
CN108458715B (en) Robot positioning initialization method based on laser map
CN111429574B (en) Mobile robot positioning method and system based on three-dimensional point cloud and vision fusion
CN109961440B (en) Three-dimensional laser radar point cloud target segmentation method based on depth map
CN111007073B (en) Method and system for online detection of part defects in additive manufacturing process
CN110780305B (en) Track cone detection and target point tracking method based on multi-line laser radar
CN109755995B (en) Robot automatic charging docking method based on ROS robot operating system
CN110033457B (en) Target point cloud segmentation method
CN107356933B (en) Unstructured road detection method based on four-line laser radar
CN111443359B (en) Positioning method, device and equipment
CN113096094B (en) Three-dimensional object surface defect detection method
CN110850371B (en) High-resolution sound source positioning method based on Green function correction
CN112883820B (en) Road target 3D detection method and system based on laser radar point cloud
CN116402866A (en) Point cloud-based part digital twin geometric modeling and error assessment method and system
CN114004869A (en) Positioning method based on 3D point cloud registration
CN115239887A (en) Method and system for reconstructing Manhattan building axis with high precision by utilizing indoor and outdoor point clouds
Choe et al. Fast point cloud segmentation for an intelligent vehicle using sweeping 2D laser scanners
CN116109601A (en) Real-time target detection method based on three-dimensional laser radar point cloud
CN110851978B (en) Camera position optimization method based on visibility
CN115631215B (en) Moving target monitoring method, system, electronic equipment and storage medium
CN113536959A (en) Dynamic obstacle detection method based on stereoscopic vision
CN112507929A (en) Vehicle body spot welding slag accurate detection method based on improved YOLOv3 network
CN112232248A (en) Method and device for extracting plane features of multi-line LiDAR point cloud data
CN111880197A (en) Road boundary detection method based on four-line laser radar
CN113985435A (en) Mapping method and system fusing multiple laser radars
CN110189403B (en) Underwater target three-dimensional reconstruction method based on single-beam forward-looking sonar

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