CN117092609A - Banister anti-smashing method and device, computer equipment and storage medium - Google Patents

Banister anti-smashing method and device, computer equipment and storage medium Download PDF

Info

Publication number
CN117092609A
CN117092609A CN202311325074.8A CN202311325074A CN117092609A CN 117092609 A CN117092609 A CN 117092609A CN 202311325074 A CN202311325074 A CN 202311325074A CN 117092609 A CN117092609 A CN 117092609A
Authority
CN
China
Prior art keywords
point cloud
barrier gate
cluster
determining
rod piece
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
Application number
CN202311325074.8A
Other languages
Chinese (zh)
Other versions
CN117092609B (en
Inventor
杨青山
徐标
邓志远
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.)
Changsha Microbrain Intelligent Technology Co ltd
Original Assignee
Changsha Microbrain Intelligent Technology Co ltd
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 Changsha Microbrain Intelligent Technology Co ltd filed Critical Changsha Microbrain Intelligent Technology Co ltd
Priority to CN202311325074.8A priority Critical patent/CN117092609B/en
Publication of CN117092609A publication Critical patent/CN117092609A/en
Application granted granted Critical
Publication of CN117092609B publication Critical patent/CN117092609B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • E—FIXED CONSTRUCTIONS
    • E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
    • E01F—ADDITIONAL WORK, SUCH AS EQUIPPING ROADS OR THE CONSTRUCTION OF PLATFORMS, HELICOPTER LANDING STAGES, SIGNS, SNOW FENCES, OR THE LIKE
    • E01F13/00—Arrangements for obstructing or restricting traffic, e.g. gates, barricades ; Preventing passage of vehicles of selected category or dimensions
    • E01F13/04—Arrangements for obstructing or restricting traffic, e.g. gates, barricades ; Preventing passage of vehicles of selected category or dimensions movable to allow or prevent passage
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Electromagnetism (AREA)
  • Computing Systems (AREA)
  • Architecture (AREA)
  • Structural Engineering (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Civil Engineering (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The application relates to a barrier gate smashing prevention method, a barrier gate smashing prevention device, computer equipment and a storage medium. The method comprises the following steps: the method can acquire a point cloud data set formed by a plurality of point cloud data detected by the millimeter wave radar in a detection area, clusters the point cloud data to obtain a plurality of point cloud clusters, performs object analysis based on the point cloud clusters, determines a detection object positioned in the detection area, determines pose information of the detection object, and finally determines relative positions and position change trends between the barrier rod and the barrier passing object by combining the pose information of the barrier rod and the barrier passing object, obtains barrier anti-smashing signals according to the relative positions and the position change trends, prevents the barrier rod from touching the barrier passing object, and improves barrier anti-smashing accuracy.

Description

Banister anti-smashing method and device, computer equipment and storage medium
Technical Field
The present application relates to the field of traffic safety technology, and in particular, to a method, an apparatus, a computer device, a computer readable storage medium and a computer program product for preventing a barrier gate from being crashed.
Background
With the development of traffic safety technology, a barrier gate smashing prevention technology appears, and the situation that a rod piece falls down and smashes the vehicle when the vehicle does not drive away can be avoided by arranging a barrier gate falling rod control sensor.
The traditional barrier gate anti-smashing technology generally adopts infrared or ground sensing to detect the position of a vehicle, so that anti-smashing signals are sent out, and the vehicles passing by are prevented from being smashed. However, when the barrier gate rod piece is an advertisement rod or a barrier rail, the advertisement rod or the barrier rail can be mistakenly identified as a vehicle by infrared rays or ground feel, and a smashing prevention signal is sent out, so that the barrier gate rod piece is always in a lifting state, the operation of the barrier gate is influenced, and the smashing prevention accuracy of the barrier gate is influenced.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a barrier gate anti-smash method, apparatus, computer device, computer readable storage medium, and computer program product that can improve barrier gate anti-smash accuracy.
In a first aspect, the application provides a barrier gate anti-smashing method. The method comprises the following steps:
acquiring a point cloud data set in a detection area of the millimeter wave radar; the point cloud data set comprises a plurality of point cloud data obtained by the millimeter wave radar detection; clustering the point cloud data to obtain a plurality of point cloud clusters; performing object analysis based on each point cloud cluster, determining a detection object positioned in the detection area, and determining pose information of the detection object; the detection object comprises a barrier gate rod piece and a barrier gate passing object; determining the relative position and the position change trend between the barrier gate rod piece and the barrier gate passing object by combining the pose information of the barrier gate rod piece and the barrier gate passing object, and obtaining a barrier gate anti-smashing signal according to the relative position and the position change trend; the barrier gate anti-smashing signal is used for preventing the barrier gate rod piece from touching the barrier gate passing object.
In one embodiment, the clustering processing is performed on each of the point cloud data to obtain a plurality of point cloud clusters, including:
respectively extracting the linear distance between the point cloud of the point cloud data and the millimeter wave radar from each point cloud data; adding a first point cloud with the linear distance meeting a first distance condition and each point cloud with the data difference meeting a difference condition with the first point cloud to a first point cloud cluster; determining each point cloud which is not added to the first point cloud cluster as a residual point cloud; and adding a second point cloud meeting a second distance condition in the residual point clouds and the residual point clouds, which are different from the second point cloud in data and meet the difference condition, to a second point cloud cluster.
In one embodiment, the pose information of the barrier gate lever includes closing; the object analysis is performed based on each point cloud cluster, the detection object in the detection area is determined, and pose information of the detection object is determined, including:
performing object recognition based on each point cloud cluster, and determining a plurality of target point cloud clusters representing the barrier gate rod in each point cloud cluster; under the condition that each point cloud in each target point cloud cluster is located in a set rod piece area and the respective speed of each point cloud meets the speed condition, respectively matching the clustering center data of each target point cloud cluster with the characteristic value of the road brake rod piece in the closing pose; and under the condition that the number of the point cloud clusters matched with the characteristic values meets the number condition, determining that the pose information of the barrier gate rod piece is closed.
In one embodiment, the barrier gate anti-smashing method further comprises:
determining the number of point cloud clusters representing the barrier gate rod piece in each point cloud cluster under the condition that the barrier gate rod piece is in a closed position; if the number of the point cloud clusters is smaller than the set number, determining the number of the historical point cloud clusters of the barrier gate rod piece at each of a plurality of historical moments; and under the condition that the number of the historical point cloud clusters is smaller than the set number, and the historical time satisfies the number condition, determining that the barrier gate rod member is damaged.
In one embodiment, the barrier gate anti-smashing method further comprises:
determining respective boundary information of each target point cloud cluster representing the barrier gate rod under the condition that the barrier gate rod is damaged; corresponding to each group of adjacent points Yun Cu in each target point cloud cluster, determining a point cloud cluster distance between member point cloud clusters contained in each adjacent point cloud cluster based on each boundary information;
and under the condition that the deviation between the point cloud cluster distance and the design distance meets the deviation condition, determining that the damaged position of the barrier gate rod piece is positioned between the member point cloud clusters.
In one embodiment, the detection object is a barrier gate bar; the object analysis is performed based on each point cloud cluster, the detection object in the detection area is determined, and pose information of the detection object is determined, including:
Performing object recognition based on each point cloud cluster, and determining a plurality of target point cloud clusters representing the barrier gate rod in each point cloud cluster; under the condition that each point cloud in each target point cloud cluster is located in a set rod piece area and the target point cloud with speed which does not meet the speed condition exists in each target point cloud cluster, determining a selected point cloud cluster with the farthest distance from a fixed point of the barrier rod piece in each target point cloud cluster, and determining a plurality of historical selected point cloud clusters with the same position as the rod piece represented by the selected point cloud cluster; determining pose information of the barrier gate rod piece based on time-dependent change information of the point cloud cluster positions of the selected point cloud cluster and each historical selected point cloud cluster; the point cloud cluster locations include at least one of cluster centers or cluster boundaries.
In one embodiment, the determining pose information of the barrier gate rod based on the time-dependent change information of the point cloud cluster positions of the selected point cloud cluster and each of the historically selected point cloud clusters includes:
determining respective point cloud cluster positions of the selected point cloud cluster and each of the historical selected point cloud clusters; under the condition that the distance between the positions of the point cloud clusters and the fixed point increases with time, determining that the pose information of the barrier gate rod piece falls; and under the condition that the distance between the positions of the point cloud clusters and the fixed point is reduced along with time, determining that the pose information of the barrier gate rod piece is lifted.
In a second aspect, the application also provides a banister anti-smashing device. The device comprises:
the point cloud data acquisition module is used for acquiring a point cloud data set in a detection area of the millimeter wave radar; the point cloud data set comprises a plurality of point cloud data obtained by the millimeter wave radar detection;
the point cloud cluster determining module is used for carrying out clustering processing on each point cloud data to obtain a plurality of point cloud clusters;
the pose information determining module is used for carrying out object analysis based on each point cloud cluster, determining a detection object positioned in the detection area and determining pose information of the detection object; the detection object comprises a barrier gate rod piece and a barrier gate passing object;
the barrier gate anti-smashing signal determining module is used for determining the relative position and the position change trend between the barrier gate rod piece and the barrier gate passing object by combining the pose information of the barrier gate rod piece and the barrier gate passing object, and obtaining a barrier gate anti-smashing signal according to the relative position and the position change trend; the barrier gate anti-smashing signal is used for preventing the barrier gate rod piece from touching the barrier gate passing object.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the above method when the processor executes the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the above method.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of the above method.
According to the barrier gate anti-smashing method, the device, the computer equipment, the computer readable storage medium and the computer program product, the point cloud data sets are formed by acquiring the plurality of point cloud data obtained through millimeter wave radar detection, the overall profile of the detection object in the detection area is acquired, clustering processing is carried out on each point cloud data to obtain the plurality of point cloud clusters, the point cloud data can be normalized, object analysis is carried out on the basis of each point cloud cluster, the detection object in the detection area is determined, pose information of the detection object is determined, finally, the relative position and the position change trend between the barrier gate rod piece and the barrier gate passing object are determined by combining the pose information of the barrier gate rod piece and the barrier gate passing object, and the barrier gate anti-smashing signal is obtained according to the relative position and the position change trend, so that traffic safety is guaranteed, and the barrier gate anti-smashing accuracy is improved.
Drawings
FIG. 1 is a diagram of an application environment of a barrier gate anti-smashing method in one embodiment;
FIG. 2 is a flow chart of a method for preventing a barrier from crashing in one embodiment;
FIG. 3 is a schematic flow chart of a barrier anti-smashing step in one embodiment;
FIG. 4 is a flowchart of a method for preventing a barrier from being crashed in another embodiment;
FIG. 5 is a block diagram of a barrier anti-smash device in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The barrier gate smashing prevention method provided by the embodiment of the application can be applied to an application environment shown in figure 1. Wherein controller 102 communicates with millimeter-wave radar 104 via a network. The millimeter wave radar 104 is used to transmit electromagnetic waves and receive electromagnetic waves reflected from a detection object, and generates point cloud data of the detection object by transmitting and receiving parameters of the electromagnetic waves. The controller 102 may be a hardware module including various processing chips and peripheral circuits thereof, and having a logic operation function. The processing chip can be a single chip microcomputer, a DSP (Digital Signal Process, digital signal processing) chip or an FPGA (Field Programmable Gate Array ) chip. The controller 102 obtains a point cloud data set formed by a plurality of point cloud data detected by the millimeter wave radar 104 in a detection area, clusters the point cloud data to obtain a plurality of point cloud clusters, performs object analysis based on the point cloud clusters, determines a detection object positioned in the detection area, determines pose information of the detection object, and finally determines a barrier gate anti-smashing signal according to the pose information of each detection object, thereby preventing a barrier gate rod piece from touching a barrier gate passing object.
In one embodiment, as shown in fig. 2, a method for preventing a barrier gate from being crashed is provided, and the method is applied to the controller in fig. 1 for illustration, and includes the following steps:
step S202, acquiring a point cloud data set in a detection area of the millimeter wave radar.
Wherein the point cloud data refers to a set of vectors in a three-dimensional coordinate system. In particular, according to the present application, the point cloud data may be a vector set of one point on the surface of the detection object detected by the millimeter wave radar. In a specific embodiment, the point cloud data of a certain point cloud may include coordinate information of the point cloud, a straight line distance from the point cloud to the millimeter wave radar, an energy value of the point cloud, and a speed of the point cloud. The point cloud data set comprises point cloud data of each of a plurality of point clouds detected by the millimeter wave radar.
Millimeter wave radar is a sensor based on millimeter wave technology for transmitting electromagnetic waves and receiving electromagnetic waves reflected from a detection object, and generating point cloud data of the detection object by transmitting and receiving parameters of the electromagnetic waves. In a specific embodiment, the millimeter wave radar emits electromagnetic waves, the electromagnetic waves are reflected after encountering a detection object, the millimeter wave radar receives echo signals, and the echo signals are subjected to distance FFT (Fast Fourier Transform ), speed FFT (Fast Fourier Transform, fast fourier transform), CFAR (Constant False Alarm Rate, constant false alarm rate detection), DOA (Direction of arrival, direction of arrival estimation) and the like, so as to obtain a point cloud data set.
Specifically, the controller may establish a connection with the millimeter wave radar to obtain a point cloud data set within a detection area of the millimeter wave radar. The point cloud data set comprises a plurality of point cloud data detected by the millimeter wave radar.
Step S204, clustering is carried out on the cloud data of each point to obtain a plurality of point cloud clusters.
The point cloud cluster refers to a point cloud set at least comprising one point cloud. Clustering refers to partitioning a data set into different classes or clusters according to specific criteria such that the similarity of data objects within the same cluster is as large as possible, while the variability of data objects that are not in the same cluster is also as large as possible. In particular, according to the application, the clustering is to divide the point cloud data detected by the millimeter wave radar into a plurality of point cloud clusters according to a set condition, in some specific embodiments, the set condition may be dividing according to the coordinate value in the point cloud data, or selecting one target point cloud first, comparing the point cloud data of the rest point cloud with the point cloud data of the target point cloud, and dividing the rest point cloud and the target point cloud which meet the data difference condition as compared results into the same point cloud cluster.
Specifically, the controller may perform clustering processing on the point cloud data detected by the millimeter wave radar, and divide the point cloud data into a plurality of point cloud clusters. For example, let the cloud data of each point detected by millimeter wave radar be In->And->In case the condition of the clustering process is satisfied, one of the point cloud clusters may be composed of +.>And (3) representing. The specific algorithm collected during the clustering process is not unique, and may be, for example, a K-Means clustering algorithm, a Mean-Shift clustering algorithm, or density-based noise application spatial clustering, or the like.
Step S206, object analysis is carried out based on the cloud clusters of each point, detection objects in the detection area are determined, and pose information of the detection objects is determined.
Wherein the detection object refers to an object that can be detected by the millimeter wave radar in the detection area. The detection objects may include a barrier pole and a barrier passing object, wherein the barrier passing object may refer to a person, a running vehicle, and the like.
The pose information includes at least one of position information or pose information of the detection object. For example, in the case where the detection object is a barrier gate lever, the pose information of the barrier gate lever may be "open", "close", "raise", and "drop", or the like; in the case of a person as the detection object, the pose information of the person may be "move under the barrier gate lever", "stationary under the barrier gate lever", "move sideways of the barrier gate lever", "stationary sideways of the barrier gate lever", or the like; in the case where the detection object is a running vehicle, the pose information of the running vehicle may be "moving under the barrier lever", "stationary under the barrier lever", "moving sideways of the barrier lever", "stationary sideways of the barrier lever", or the like.
Specifically, the controller may perform object analysis on each point cloud cluster to determine a detection object located in the detection area. The detection object may include at least one of a barrier pole and a barrier passing object. In some specific embodiments, the controller may set different object matching conditions for different detected objects, which may be characterized by, for example, object contours, object point cloud energy, or object volumes, etc. And carrying out matching analysis on each point cloud cluster and each object matching condition respectively, and determining the object type of the detection object represented by each point cloud cluster. For example, if the point cloud cluster a meets the object matching condition of the pedestrian, determining that the detection object represented by the point cloud cluster a is the pedestrian; for another example, if the point cloud set formed by the point cloud cluster B and the point cloud cluster C meets the object matching condition of the barrier gate rod, the detection object represented by the point cloud set is the barrier gate rod. In a specific embodiment, the controller may determine the object pose of the detection object based on the respective coordinate information characterizing the respective point clouds of the detection object. The object pose may include an object position and an object pose. The object position can be characterized by a point cloud cluster center position or a boundary position, and the object gesture can be characterized by a point cloud cluster contour.
Step S208, the relative position and the position change trend between the barrier gate rod piece and the barrier gate passing object are determined by combining the pose information of the barrier gate rod piece and the barrier gate passing object, and the barrier gate anti-smashing signal is obtained according to the relative position and the position change trend.
The barrier gate anti-smashing signal is a lifting signal sent to the barrier gate rod piece and used for preventing the barrier gate rod piece from touching a barrier gate passing object. The relative position may be characterized by at least one of a distance or an angle. The positional change trend may include a change trend of at least one of distance or angle. For example, the position change trend may include a relative distance becoming smaller or larger, and a relative angle becoming smaller or larger.
Specifically, the controller can combine the pose information of each of the barrier gate rod piece and the barrier gate passing object to determine the relative position between the barrier gate rod piece and the barrier gate passing object and the position change trend, judge whether the relative position reaches the set threshold condition or not, determine the barrier gate anti-smashing signal based on the actual situation of the position change trend, and prevent the barrier gate rod piece from touching the barrier gate passing object, so that traffic accidents are avoided. For example, when the controller determines that the relative positions of the barrier gate rod and the person reach the set threshold condition and the position change trend is that the relative distance becomes smaller, the controller can send a barrier gate anti-smashing signal. In some specific embodiments, when the pose information of the barrier gate rod is closed, the controller does not send a barrier gate anti-smashing signal no matter whether a barrier gate passing object exists in the detection area of the millimeter wave radar; when the pose information of the barrier gate rod piece is open, fall or lift, if a barrier gate passing object exists in the detection area of the millimeter wave radar, the controller sends a barrier gate anti-smashing signal; when the pose information of the barrier gate rod piece is open, fall or lift, if no barrier gate passing object exists in the detection area of the millimeter wave radar, the controller cannot send a barrier gate anti-smashing signal.
According to the barrier gate anti-smashing method, the plurality of point cloud data obtained through millimeter wave radar detection are obtained to form the point cloud data set, the overall outline of the detection object in the detection area is obtained, clustering processing is carried out on each point cloud data to obtain the plurality of point cloud clusters, the point cloud data can be normalized, object analysis is carried out on the basis of each point cloud cluster, the detection object in the detection area is determined, pose information of the detection object is determined, and therefore the barrier gate anti-smashing signal is determined according to the type of the detection object and the pose information of the detection object, traffic safety is guaranteed, and anti-smashing accuracy of the barrier gate is improved.
In one embodiment, step S204 includes: respectively extracting the linear distance between the point cloud of the point cloud data and the millimeter wave radar from the point cloud data; adding a first point cloud with a linear distance meeting a first distance condition and each point cloud with a data difference meeting a difference condition with the first point cloud to a first point cloud cluster; determining each point cloud which is not added to the first point cloud cluster as a residual point cloud; and adding the second point cloud meeting the second distance condition in the residual point clouds and the residual point clouds with the data difference meeting the difference condition with the second point cloud to the second point cloud cluster.
The first distance condition may be a condition that a linear distance between point cloud data of the point cloud and the millimeter wave radar is shortest, a linear distance between point cloud data of the point cloud and the millimeter wave radar is longest, or a linear distance between point cloud data of the point cloud and the millimeter wave radar is moderate and equidistant. That is, the first distance condition may be set by the technician himself. Further, the second distance condition may also be set by the technician, which will not be described herein. In some specific embodiments, the first distance condition and the second distance condition may or may not be identical.
The difference condition may refer to a condition satisfied by a difference between point cloud data of two point clouds. In a specific embodiment, the differential conditions may include the following two conditions:
wherein (1)>Is the coordinate of the first point cloud on the x-axis,/->Is the coordinate of the ith point cloud on the x-axis,/->Point cloud data x-axis threshold value, which is two point clouds,/-for>Is the coordinate of the first point cloud on the y-axis,/->Is the coordinate of the ith point cloud on the y-axis,/->Is the point cloud data y-axis threshold for two point clouds,is the energy value of the ith point cloud, +.>The energy threshold value of the point cloud is that the energy reflected by the detection object of the millimeter wave radar is different in different distance segments, and the energy is attenuated along with the increase of the distance. The point cloud energy threshold for each set distance segment is +. >Different, threshold value +.for each set distance segment>The size of (2) can be obtained by actual measurement.
Wherein (1)>Refers to the speed of the ith point cloud; />The speed resolution is determined by configuration parameters of the millimeter wave radar, and can be adjusted according to actual conditions; />Is a very small positive number, since the overall speed of movement of the bar element is substantially uniform,/therefore>The value of (2) remains substantially unchanged.
Specifically, the controller may extract the straight line distance between the point cloud of the point cloud data and the millimeter wave radar from the point cloud data detected by the millimeter wave radar, select a first point cloud whose straight line distance satisfies a first distance condition, compare the point cloud data of the point clouds except the first point cloud with the first point cloud, add the point clouds whose data difference satisfies a difference condition to the first point cloud cluster, then the first point cloud cluster may include all the point clouds related to or same as the first point cloud, then determine the point clouds except the point clouds included in the first point cloud cluster as remaining point clouds, select a second point cloud whose straight line distance satisfies a second distance condition, compare the point cloud data of the point clouds except the second point cloud with the second point cloud, add the point clouds whose data difference satisfies a difference condition to the second point cloud, then the second point cloud may include all the point clouds related to or same as the second point cloud, and so on, and then repeat the determination until all the point clouds are in the third point cloud cluster.
In this embodiment, by selecting one target point cloud, comparing the rest point clouds with the point cloud data of the target point cloud, putting the point clouds in one point cloud cluster, which satisfies the difference condition, and repeating the traversing operation, all the point cloud data can be finally distinguished into a plurality of point cloud clusters according to the set condition, so that the process of processing the point cloud data by the controller is more convenient, the efficiency of processing the point cloud data by the controller is improved, and the working efficiency of the barrier anti-smashing method is improved.
In one embodiment, the pose information for the barrier gate lever includes closing. In the case of this embodiment, step S206 includes: performing object recognition based on each point cloud cluster, and determining a plurality of target point cloud clusters representing the barrier gate rod pieces in each point cloud cluster; under the condition that each point cloud in each target point cloud cluster is positioned in a set rod piece area and the respective speed of each point cloud meets the speed condition, respectively matching the clustering center data of each target point cloud cluster with the characteristic value of the road gate rod piece in the closing position; and under the condition that the number of the point cloud clusters matched with the characteristic values meets the number condition, determining that the pose information of the barrier gate rod piece is closed.
The set rod piece area refers to an area in which point clouds detected by the millimeter wave radar are basically distributed in the moving or static process of the road gate rod piece. In a specific embodiment, the set lever region may be noted as ，/>And->The maximum value and the minimum value of the x-axis direction in the rod piece area are respectively set. The speed condition may be that the speed of the pointing cloud is 0, or that the speed of the pointing cloud is close to 0,i.e., less than or equal to a speed threshold approaching 0.
The cluster center data may refer to cluster center data of a target point cloud cluster, including x-axis center data and y-axis center data. The x-axis center data is obtained by averaging coordinate values of the point cloud data in the target point cloud cluster on an x-axis coordinate, and the y-axis center data is obtained by averaging coordinate values of the point cloud data in the target point cloud cluster on a y-axis coordinate.
The characteristic value of the road gate bar in the closing position refers to the characteristic value recorded by the controller when the road gate bar is in the closing position. In a specific embodiment, the characteristic value acquisition process of the road gate bar in the closed position is as follows: the controller selects one point cloud cluster with the most clustering point clouds among the target point cloud clusters belonging to the barrier gate rod as a concerned point cloud cluster of the barrier gate rod, and detects the clustering center data change of the concerned point cloud cluster in the falling process of the barrier gate rod. When the barrier gate rod piece falls, the y-axis coordinate value of the clustering center data at the current moment can be gradually increased, and the x-axis coordinate value can be stable. When the change of the y-axis coordinate value and the x-axis coordinate value of the clustering center data tends to be stable, comparing the y-axis coordinate value and the x-axis coordinate value of the clustering center data at the current moment with the y-axis coordinate value and the x-axis coordinate value of the clustering center data at the historical moment, if the number of times that the comparison result tends to be stable is larger than a set number threshold, determining that the current moment is in a closing pose, and recording the characteristic value that the road gate is in the closing pose, wherein the characteristic value comprises: maximum value of current y direction of road gate rod piece Minimum value in y direction of current moment of bar element of road gate +.>Maximum value in x direction of the current moment of the bar element +.>Minimum value in x-direction of the current moment of the bar element +.>Average value of clustering centers of the focus point cloud cluster in accumulated time of the road gate rod piece and moving speed of y-axis direction of the focus point cloud cluster when the road gate rod piece falls +.>And a movement rate +/of the focus cloud cluster in the y-axis direction when the gate bar member is lifted>。
Specifically, the controller may perform object recognition based on each point cloud cluster, determine a plurality of target point cloud clusters representing the barrier gate rod from each point cloud cluster, determine whether point cloud data of each point cloud in each target point cloud cluster is included in data of a set rod area, and determine whether respective speeds of each point cloud meet a speed condition, and if each point cloud in each target point cloud cluster is located in the set rod area and the respective speeds of each point cloud meet the speed condition, match cluster center data of each target point cloud cluster with feature values of the barrier gate rod in a closing pose, and determine pose information of the barrier gate rod to be closed if the number of point cloud clusters matched with the feature values reaches a set number. In a specific embodiment, the controller may traverse the cloud data of points detected by the millimeter wave radar When the point clouds to which the point cloud data belong are all located in the set bar member area, namelyAnd->When the condition 1 is satisfied; when the cloud cluster center data of a certain target point is matched with the characteristic value of the closed pose of the road gate rod, the condition 2 is satisfied; when the conditions 1 and 2 are met, the count value is +1, otherwise, the count value is cleared, and when the count value reaches 10 (adjustable), the pose information of the barrier gate rod piece is determined to be closed.
In this embodiment, whether the barrier gate rod is stationary is determined according to whether the cloud data of each point is located in the set rod piece area and whether the speed of the cloud data of each point meets the speed condition, and under the condition that the barrier gate rod is stationary, the clustering center data of the cloud clusters of each target point of the barrier gate rod is respectively matched with the characteristic value of the barrier gate rod in the closing pose, and the similarity of the state of the barrier gate rod at the current moment and the state of the closing pose is determined, so that the closing pose of the barrier gate rod can be accurately identified, and the accuracy of barrier gate anti-smashing is improved.
In one embodiment, the barrier gate anti-smashing method further comprises the following steps: under the condition that the barrier gate rod piece is in a closing pose, determining the number of the point cloud clusters representing the barrier gate rod piece in each point cloud cluster; if the number of the point cloud clusters is smaller than the set number, determining the number of the historical point cloud clusters of each barrier gate rod piece at a plurality of historical moments; and under the condition that the number of the historical point cloud clusters is smaller than the set number, the number condition is met at the historical moment, and the fact that the road gate rod piece is damaged is determined.
The set number refers to the set number of point cloud clusters. Further, the set number is set according to the number of point cloud clusters of undamaged barrier gate bars in the closed position. The number condition refers to a time-of-day number condition of the history time. For example, "1 history time", "2 history times", "3 history times", and the like are possible.
Specifically, the controller may determine the number of point cloud clusters representing the barrier gate rod in the point cloud clusters under the condition that the barrier gate rod is in the closed position, if the number of point cloud clusters is smaller than the set number, acquire the number of historical point cloud clusters of the barrier gate rod at each of a plurality of historical moments, and prove that the information represented by the number of point cloud clusters at the plurality of moments of the barrier gate rod is damaged under the condition that the number of historical point cloud clusters is smaller than the set number of historical moments and meets the condition of the number of moments, so that the barrier gate rod can be determined to be damaged.
In this embodiment, under the condition that the barrier gate rod is in the closed position, according to the comparison between the number of the point cloud clusters of the barrier gate rod and the set number at the current time and the historical time, whether the barrier gate rod is damaged is finally determined, so that a worker can conveniently and timely maintain the barrier gate rod, and the safety of a barrier gate facility is improved.
In one embodiment, the barrier gate anti-smashing method further comprises the following steps: determining respective boundary information of each target point cloud cluster representing the barrier gate rod piece under the condition that the barrier gate rod piece is damaged; corresponding to each group of adjacent point cloud clusters in each target point cloud cluster, determining the point cloud cluster distance between each member point cloud cluster contained in the adjacent point cloud clusters based on each boundary information; and under the condition that the deviation between the point cloud cluster distance and the design distance meets the deviation condition, determining that the damaged position of the road gate rod piece is positioned between the member point cloud clusters.
The boundary information may be composed of a maximum value of point cloud data of all point clouds in the target point cloud cluster in an x-axis, a minimum value of the x-axis, a maximum value of the y-axis, and a minimum value of the y-axis. The design distance may refer to the distance between the point cloud clusters without damaging the road gate bar. In a specific embodiment, the barrier bars are barrier bars, where a certain distance exists between each barrier and the distance is fixed, in which case the design distance may not be a fixed distance between the barriers, and all distances within a certain deviation range from the fixed distance may be used as the design distance. For example, if the barrier bars are barrier bars, the distance between each barrier is 10 cm, the design distance may be selected within the interval of [9,11] cm.
The deviation condition may be that a deviation between the pointing cloud cluster distance and the design distance is greater than a set deviation threshold. For example, if the deviation threshold is "5 cm", when the deviation between the point cloud cluster distance and the design distance is "6 cm", the deviation between the point cloud cluster distance and the design distance satisfies the deviation condition.
Specifically, under the condition that the barrier gate rod member is damaged, the controller may determine boundary information corresponding to each target point cloud cluster of the barrier gate rod member, determine a point cloud cluster distance between each member point cloud cluster included in each group of adjacent point cloud clusters according to the boundary information, compare the point cloud cluster distance with the design distance, and when the point cloud cluster distance between the member point cloud clusters of the group of adjacent point cloud clusters and the design distance meet a deviation condition, consider that damage exists in the adjacent point cloud clusters, and the damaged position is the position between the two member point cloud clusters. For example, if the distances between each two adjacent point cloud clusters of the road gate member are respectively "2 cm", "5 cm", "10 cm" and "15 cm", and the design distance is "10 cm", the road gate member is damaged because the distance between the two adjacent point cloud clusters is greater than the design distance, and the damaged position is the position between the member point cloud clusters of the two adjacent point cloud clusters. Further, if the distances between the plurality of adjacent point cloud clusters in the barrier gate rod are all larger than the set distance, then the barrier gate rod is considered to be damaged at a plurality of positions, and the plurality of damaged positions are distances between the member point cloud clusters of the plurality of adjacent point cloud clusters.
According to the method, under the condition that the barrier gate rod piece is damaged, the damage position of the barrier gate rod piece is determined by comparing the point cloud cluster distance between the member point cloud clusters in each adjacent point cloud cluster of the barrier gate rod piece with the design distance, so that the maintenance efficiency of the barrier gate rod piece can be improved, and the safety is further improved.
In one embodiment, the detection object is a barrier gate pole. In the case of this embodiment, step S206 includes: performing object recognition based on each point cloud cluster, and determining a plurality of target point cloud clusters representing the barrier gate rod pieces in each point cloud cluster; under the condition that each point cloud in each target point cloud cluster is located in a set rod piece area and the target point cloud with the speed which does not meet the speed condition exists in each target point cloud cluster, determining a selected point cloud cluster which is farthest from a fixed point of a road gate rod piece in each target point cloud cluster, and determining a plurality of historical selected point cloud clusters which are the same as the rod piece represented by the selected point cloud cluster in position; and determining pose information of the road gate rod piece based on the time-dependent change information of the position of the point cloud cluster of each selected point cloud cluster and each history selected point cloud cluster.
The speed condition may refer to a case where the speed of the target point cloud is zero. When the target point cloud with the speed which does not meet the speed condition exists in each target point cloud cluster, the detection object which each target point cloud cluster belongs to is considered to be in a motion state.
The historical selected point cloud cluster refers to a point cloud cluster which has the same position as the rod represented by the selected point cloud cluster in a historical time frame. In a specific embodiment, the historical selected point cloud clusters may be point cloud clusters with the same rod positions represented by the selected point cloud clusters in one historical time frame or point cloud clusters with the same rod positions represented by the selected point cloud clusters in a plurality of historical time frames. Where a historical time frame may refer to the first second and n historical time frames may refer to the first n seconds. In another specific embodiment, the historical time frame may also be one time frame separated by a set time. For example, the historical time frame may be a time frame 2 seconds apart from the current time frame, and the plurality of historical time frames may be a plurality of historical time frames obtained by collecting one time frame 2 seconds apart.
Specifically, since the detection object is a barrier gate rod, the controller may first perform object recognition according to each point cloud cluster, determine a plurality of target point cloud clusters belonging to the barrier gate rod, and then determine that each point cloud in each target point cloud cluster is located in a set rod area, and determine that the barrier gate rod is in a motion state when there is a target point cloud in each target point cloud cluster whose speed does not satisfy a speed condition. The position change of the point cloud cluster which is farthest from the fixed point of the barrier gate rod is most obvious in the movement process of the barrier gate rod, so that the point cloud cluster which is farthest from the fixed point of the barrier gate rod in the target point cloud cluster is determined to be a selected point cloud cluster, a plurality of historical selected point cloud clusters which are the same as the rod position represented by the selected point cloud cluster are determined, the time change information of the position of each of the selected point cloud cluster and each of the historical selected point cloud clusters is analyzed, and the pose information of the barrier gate rod is determined. Further, the point cloud cluster locations may include at least one of cluster centers or cluster boundaries. In some specific embodiments, the process of analyzing the time-dependent change information of the position of the selected point cloud cluster and the position of each historical selected point cloud cluster may be to compare the cluster center and the cluster boundary of the selected point cloud cluster with the cluster center and the cluster boundary of each historical selected point cloud cluster, or to compare the cluster center and the cluster boundary of the selected point cloud cluster with the cluster center and the cluster boundary of the historical selected point cloud cluster of the previous historical time frame, and then to compare the cluster center and the cluster boundary of the historical selected point cloud cluster of the previous historical time frame with the cluster center and the cluster boundary of the historical selected point cloud cluster of the previous historical time frame relative to the previous historical time frame, and so on, which are not repeated herein.
In the embodiment, under the condition that the barrier gate rod piece is determined to be in a motion state, the pose information of the barrier gate rod piece is determined according to the time-varying information of the point cloud cluster positions of a plurality of time frames representing the same rod piece position, so that the accuracy of barrier gate anti-smashing is improved.
In one embodiment, determining pose information of the road brake bar member based on time-dependent change information of respective point cloud cluster positions of the selected point cloud cluster and each of the historical selected point cloud clusters comprises: determining respective point cloud cluster positions of the selected point cloud cluster and each historical selected point cloud cluster; under the condition that the distance between the cloud cluster positions of each point and a fixed point increases along with time, determining that pose information of the barrier gate rod piece is falling; and under the condition that the distance between the positions of the cloud clusters of each point and the fixed point is reduced along with time, determining that the pose information of the barrier gate rod piece is lifting.
Wherein, the falling refers to the falling motion state of the road gate rod from the open position to the closed position. Lifting refers to the lifting movement of the bar member from the closed position to the open position.
Specifically, the controller may determine the positions of the selected point cloud cluster and the respective point cloud clusters of each history selected point cloud cluster, when the distance between the positions of the selected point cloud clusters and the fixed point increases with time, the position of the selected point cloud cluster is represented to be lowered relative to each history point cloud cluster, so that the pose information of the barrier gate rod member can be determined to be lowered; when the distance between the positions of the point cloud clusters and the fixed point is reduced with time, the position of the selected point cloud cluster is increased relative to the positions of the history point cloud clusters, and then the pose information of the barrier gate rod can be determined to be lifting. In some particular embodiments, the controller may center clusters of the selected point cloud cluster And gatherClass boundary->Placing the cloud clusters into a sliding window, and clustering the cloud clusters at the selected pointsCluster boundary->Clustering center of cloud cluster with history selected point in sliding window +.>Cluster boundary->Comparing if it meets->、Determining the pose information of the barrier gate rod member as falling; if it meets、/>And (3) determining that the pose information of the barrier gate rod piece is lifting. Wherein the sliding window uses an array +.>The representation includes 10 elements in the array, each element including information
In the millimeter wave radar detection process, one exists for each time framePut it into->In (2), n is increased by 1, so that the value of +.>Information.
According to the method and the device, according to the time-dependent change conditions of the distance between the point cloud cluster position of the selected point cloud cluster and the point cloud cluster position of each history selected point cloud cluster relative to the fixed point, whether the pose information of the barrier gate rod piece falls or rises can be determined, different motion states of the barrier gate rod piece are distinguished, and the accuracy of barrier gate smashing prevention is improved.
In one embodiment, as shown in fig. 3, the barrier gate anti-smashing method includes:
step S301, acquiring a point cloud data set in a detection area of a millimeter wave radar;
The point cloud data set comprises a plurality of point cloud data obtained by millimeter wave radar detection;
step S302, respectively extracting the linear distance between the point cloud of the point cloud data and the millimeter wave radar from the point cloud data;
step S303, determining a first point cloud with the minimum linear distance from the point clouds in the point cloud data set;
step S304, the first point cloud and each residual point cloud which has the data difference meeting the difference condition with the first point cloud are extracted from the point cloud data set, and the extracted point clouds are added to the same point cloud cluster;
step S305, judging whether all point clouds in the point cloud data set are taken out; if not, returning to the step S303, if yes, executing the step S306;
step S306, performing object recognition based on the obtained point cloud clusters, and determining a plurality of target point cloud clusters representing the barrier gate rod pieces in the point cloud clusters;
step S307, under the condition that each point cloud in each target point cloud cluster is positioned in a set rod piece area and the respective speed of each point cloud meets the speed condition, the respective clustering center data of each target point cloud cluster is respectively matched with the characteristic value of the road brake rod piece in the closing pose;
step S308, determining pose information of the barrier gate rod piece to be closed under the condition that the number of the point cloud clusters matched with the characteristic values meets the number condition;
Step S309, determining the number of point cloud clusters representing the barrier gate rod pieces in the point cloud clusters under the condition that the barrier gate rod pieces are in the closed position;
step S310, if the number of the point cloud clusters is smaller than the set number, determining the number of the historical point cloud clusters of the barrier gate rod piece at each of a plurality of historical moments;
step S311, determining that the barrier gate rod member is damaged under the condition that the number of the historical point cloud clusters is smaller than the set number and the number condition is met at historical time;
step S312, determining respective boundary information of each target point cloud cluster representing the barrier gate rod piece under the condition that the barrier gate rod piece is damaged;
step S313, corresponding to each group of adjacent point cloud clusters in each target point cloud cluster, determining the point cloud cluster distance between each member point cloud cluster contained in the adjacent point cloud clusters based on each boundary information;
step S314, determining that the damaged position of the road gate rod piece is positioned between member point cloud clusters under the condition that the deviation between the point cloud cluster distance and the design distance meets the deviation condition;
step S315, under the condition that each point cloud in each target point cloud cluster is positioned in a set rod piece area and the target point cloud with speed which does not meet the speed condition exists in each target point cloud cluster, determining a selected point cloud cluster which is farthest from a fixed point of a road gate rod piece in each target point cloud cluster, and determining a plurality of historical selected point cloud clusters which are the same as the rod piece represented by the selected point cloud cluster in position;
Step S316, determining respective point cloud cluster positions of the selected point cloud cluster and each history selected point cloud cluster;
step S317, under the condition that the distance between the cloud cluster positions of each point and a fixed point increases along with time, determining that the pose information of the barrier gate rod piece is falling;
step S318, under the condition that the distance between the cloud cluster positions of each point and a fixed point is reduced along with time, determining that the pose information of the barrier gate rod piece is lifted;
the point cloud cluster position comprises at least one of a cluster center or a cluster boundary, and the detection objects comprise barrier gate rod pieces and barrier gate passing objects;
step S319, determining the relative position and the position change trend between the barrier gate rod piece and the barrier gate passing object by combining the pose information of the barrier gate rod piece and the barrier gate passing object, and obtaining a barrier gate anti-smashing signal according to the relative position and the position change trend;
the barrier gate anti-smashing signal is used for preventing a barrier gate rod piece from touching a barrier gate passing object.
In a specific embodiment, the clustering process is performed on the point cloud data, and a process of obtaining a plurality of point cloud clusters is shown in fig. 4:
step S401, initializing parameters and naming the point cloud cluster asLet k=0;
step S402, taking the point cloud which is not marked in the point cloud data set and is closest to the millimeter wave radar as a first point cloud;
Step S403, selecting a point cloud from the point cloud data set；
Step S404, atIn the case that the difference between the point cloud data of (a) and the first point cloud data satisfies the difference conditionAdd to point cloud cluster->In (a) and (b);
step S405, let i=i+1;
step S406, judging whether all point clouds which are not added with marks are traversed;
returning to step S403 if all the point clouds to which the mark is not added have not been traversed;
step S407, let k=k+1 in the case of traversing all point clouds not added with a mark;
step S408, judging whether unmarked points exist in the point cloud data set;
returning to step S402 if there are unlabeled points in the point cloud dataset;
step S409, under the condition that no unlabeled point exists in the point cloud data set, the clustering is finished to obtain a plurality of clustered point cloud clusters；
Calculating the center of each point cloud cluster in the clustered multiple point cloud clusters M to be recorded as。
In a specific embodiment, if the current point cloud data set is an empty set, that is, there is no detection object in the currently set detection area, it is determined that the road brake lever member is in the open position.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a barrier gate anti-smashing device for realizing the barrier gate anti-smashing method. The implementation of the solution provided by the device is similar to that described in the above method, so the specific limitation of one or more embodiments of the barrier gate anti-smashing device provided below may be referred to the limitation of the barrier gate anti-smashing method hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 5, a barrier gate anti-smash device 500 is provided, comprising: the system comprises a point cloud data acquisition module, a pose information determination module, a point cloud cluster determination module and a barrier gate anti-smashing signal determination module, wherein:
the point cloud data acquisition module 502 is configured to acquire a point cloud data set in a detection area of the millimeter wave radar; the point cloud data set comprises a plurality of point cloud data obtained by millimeter wave radar detection;
the point cloud cluster determining module 504 is configured to perform clustering processing on the point cloud data to obtain a plurality of point cloud clusters;
the pose information determining module 506 is configured to perform object analysis based on the cloud clusters of points, determine a detection object located in the detection area, and determine pose information of the detection object; the detection objects comprise a barrier gate rod piece and a barrier gate passing object;
The barrier gate anti-smashing signal determining module 508 is used for determining the relative position and the position change trend between the barrier gate rod piece and the barrier gate passing object by combining the pose information of the barrier gate rod piece and the barrier gate passing object, and obtaining the barrier gate anti-smashing signal according to the relative position and the position change trend; the barrier gate anti-smashing signal is used for preventing a barrier gate rod piece from touching a barrier gate passing object.
In one embodiment, the point cloud cluster determining module is specifically configured to: respectively extracting the linear distance between the point cloud of the point cloud data and the millimeter wave radar from the point cloud data; adding a first point cloud with a linear distance meeting a first distance condition and each point cloud with a data difference meeting a difference condition with the first point cloud to a first point cloud cluster; determining each point cloud which is not added to the first point cloud cluster as a residual point cloud; and adding the second point cloud meeting the second distance condition in the residual point clouds and the residual point clouds with the data difference meeting the difference condition with the second point cloud to the second point cloud cluster.
In one embodiment, the pose information of the barrier gate lever includes closing. In the case of this embodiment, the pose information determination module is configured to: performing object recognition based on each point cloud cluster, and determining a plurality of target point cloud clusters representing the barrier gate rod pieces in each point cloud cluster; under the condition that each point cloud in each target point cloud cluster is positioned in a set rod piece area and the respective speed of each point cloud meets the speed condition, respectively matching the clustering center data of each target point cloud cluster with the characteristic value of the road gate rod piece in the closing position; and under the condition that the number of the point cloud clusters matched with the characteristic values meets the number condition, determining that the pose information of the barrier gate rod piece is closed.
In one embodiment, the barrier gate anti-smashing device further comprises a barrier gate bar damage judging module, and the barrier gate anti-smashing device is specifically used for: under the condition that the barrier gate rod piece is in a closing pose, determining the number of the point cloud clusters representing the barrier gate rod piece in each point cloud cluster; if the number of the point cloud clusters is smaller than the set number, determining the number of the historical point cloud clusters of each barrier gate rod piece at a plurality of historical moments; and under the condition that the number of the historical point cloud clusters is smaller than the set number, the number condition is met at the historical moment, and the fact that the road gate rod piece is damaged is determined.
In one embodiment, the barrier gate anti-smashing device further comprises a barrier gate bar damage position judging module, which is specifically used for: determining respective boundary information of each target point cloud cluster representing the barrier gate rod piece under the condition that the barrier gate rod piece is damaged; corresponding to each group of adjacent point cloud clusters in each target point cloud cluster, determining the point cloud cluster distance between each member point cloud cluster contained in the adjacent point cloud clusters based on each boundary information; and under the condition that the deviation between the point cloud cluster distance and the design distance meets the deviation condition, determining that the damaged position of the road gate rod piece is positioned between the member point cloud clusters.
In one embodiment, the detection object is a barrier gate bar. In the case of this embodiment, the pose information determination module includes: the target point cloud cluster determining unit is used for carrying out object identification based on each point cloud cluster and determining a plurality of target point cloud clusters which characterize the barrier gate rod piece in each point cloud cluster; a history selected point cloud cluster determining unit, configured to determine a selected point cloud cluster with the farthest distance from a fixed point of the barrier rod in each target point cloud cluster, and determine a plurality of history selected point cloud clusters with the same position as the rod represented by the selected point cloud cluster, when each point cloud in each target point cloud is located in a set rod area and a target point cloud with a speed that does not meet a speed condition exists in each target point cloud; the pose information determining unit is used for determining pose information of the road brake bar piece based on time-dependent change information of the point cloud cluster positions of the selected point cloud cluster and each history selected point cloud cluster; the point cloud cluster location includes at least one of a cluster center or a cluster boundary.
In one embodiment, the pose information determining unit is specifically configured to: determining respective point cloud cluster positions of the selected point cloud cluster and each historical selected point cloud cluster; under the condition that the distance between the cloud cluster positions of each point and a fixed point increases along with time, determining that pose information of the barrier gate rod piece is falling; and under the condition that the distance between the positions of the cloud clusters of each point and the fixed point is reduced along with time, determining that the pose information of the barrier gate rod piece is lifting.
All or part of the modules in the barrier gate anti-smashing device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program when executed by the processor is used for realizing a barrier gate anti-smashing method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory having a computer program stored therein and a processor that implements the steps of the method described above when the computer program is executed.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, implements the steps of the above method.
In an embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, implements the steps of the above method.
The user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims (10)

1. A banister anti-smashing method is characterized by comprising the following steps:
acquiring a point cloud data set in a detection area of the millimeter wave radar; the point cloud data set comprises a plurality of point cloud data obtained by the millimeter wave radar detection;
clustering the point cloud data to obtain a plurality of point cloud clusters;
performing object analysis based on each point cloud cluster, determining a detection object positioned in the detection area, and determining pose information of the detection object; the detection object comprises a barrier gate rod piece and a barrier gate passing object;
Determining the relative position and the position change trend between the barrier gate rod piece and the barrier gate passing object by combining the pose information of the barrier gate rod piece and the barrier gate passing object, and obtaining a barrier gate anti-smashing signal according to the relative position and the position change trend; the barrier gate anti-smashing signal is used for preventing the barrier gate rod piece from touching the barrier gate passing object.
2. The method of claim 1, wherein clustering each of the point cloud data to obtain a plurality of point cloud clusters comprises:
respectively extracting the linear distance between the point cloud of the point cloud data and the millimeter wave radar from each point cloud data;
adding a first point cloud with the linear distance meeting a first distance condition and each point cloud with the data difference meeting a difference condition with the first point cloud to a first point cloud cluster;
determining each point cloud which is not added to the first point cloud cluster as a residual point cloud;
and adding a second point cloud meeting a second distance condition in the residual point clouds and the residual point clouds, which are different from the second point cloud in data and meet the difference condition, to a second point cloud cluster.
3. The method of claim 1, wherein the pose information of the barrier gate lever comprises closing; the object analysis is performed based on each point cloud cluster, the detection object in the detection area is determined, and pose information of the detection object is determined, including:
performing object recognition based on each point cloud cluster, and determining a plurality of target point cloud clusters representing the barrier gate rod in each point cloud cluster;
under the condition that each point cloud in each target point cloud cluster is located in a set rod piece area and the respective speed of each point cloud meets the speed condition, respectively matching the clustering center data of each target point cloud cluster with the characteristic value of the road brake rod piece in the closing pose;
and under the condition that the number of the point cloud clusters matched with the characteristic values meets the number condition, determining that the pose information of the barrier gate rod piece is closed.
4. The method according to claim 1, wherein the method further comprises:
determining the number of point cloud clusters representing the barrier gate rod piece in each point cloud cluster under the condition that the barrier gate rod piece is in a closed position;
if the number of the point cloud clusters is smaller than the set number, determining the number of the historical point cloud clusters of the barrier gate rod piece at each of a plurality of historical moments;
And under the condition that the number of the historical point cloud clusters is smaller than the set number, and the historical time satisfies the number condition, determining that the barrier gate rod member is damaged.
5. The method according to claim 4, wherein the method further comprises:
determining respective boundary information of each target point cloud cluster representing the barrier gate rod piece under the condition that the barrier gate rod piece is damaged;
corresponding to each group of adjacent points Yun Cu in each target point cloud cluster, determining a point cloud cluster distance between member point cloud clusters contained in each adjacent point cloud cluster based on each boundary information;
and under the condition that the deviation between the point cloud cluster distance and the design distance meets the deviation condition, determining that the damaged position of the barrier gate rod piece is positioned between the member point cloud clusters.
6. The method according to any one of claims 1 to 5, wherein the detection object is a barrier gate bar; the object analysis is performed based on each point cloud cluster, the detection object in the detection area is determined, and pose information of the detection object is determined, including:
performing object recognition based on each point cloud cluster, and determining a plurality of target point cloud clusters representing the barrier gate rod in each point cloud cluster;
Under the condition that each point cloud in each target point cloud cluster is located in a set rod piece area and the target point cloud with speed which does not meet the speed condition exists in each target point cloud cluster, determining a selected point cloud cluster with the farthest distance from a fixed point of the barrier rod piece in each target point cloud cluster, and determining a plurality of historical selected point cloud clusters with the same position as the rod piece represented by the selected point cloud cluster;
determining pose information of the barrier gate rod piece based on time-dependent change information of the point cloud cluster positions of the selected point cloud cluster and each historical selected point cloud cluster; the point cloud cluster locations include at least one of cluster centers or cluster boundaries.
7. The method of claim 6, wherein determining pose information of the barrier pole based on time-dependent change information of respective point cloud cluster positions of the selected point cloud cluster and each of the historically selected point cloud clusters comprises:
determining respective point cloud cluster positions of the selected point cloud cluster and each of the historical selected point cloud clusters;
under the condition that the distance between the positions of the point cloud clusters and the fixed point increases with time, determining that the pose information of the barrier gate rod piece falls;
And under the condition that the distance between the positions of the point cloud clusters and the fixed point is reduced along with time, determining that the pose information of the barrier gate rod piece is lifted.
8. A barrier anti-smash device, the device comprising:
the point cloud data acquisition module is used for acquiring a point cloud data set in a detection area of the millimeter wave radar; the point cloud data set comprises a plurality of point cloud data obtained by the millimeter wave radar detection;
the point cloud cluster determining module is used for carrying out clustering processing on each point cloud data to obtain a plurality of point cloud clusters;
the pose information determining module is used for carrying out object analysis based on each point cloud cluster, determining a detection object positioned in the detection area and determining pose information of the detection object; the detection object comprises a barrier gate rod piece and a barrier gate passing object;
the barrier gate anti-smashing signal determining module is used for determining the relative position and the position change trend between the barrier gate rod piece and the barrier gate passing object by combining the pose information of the barrier gate rod piece and the barrier gate passing object, and obtaining a barrier gate anti-smashing signal according to the relative position and the position change trend; the barrier gate anti-smashing signal is used for preventing the barrier gate rod piece from touching the barrier gate passing object.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
CN202311325074.8A 2023-10-13 2023-10-13 Banister anti-smashing method and device, computer equipment and storage medium Active CN117092609B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311325074.8A CN117092609B (en) 2023-10-13 2023-10-13 Banister anti-smashing method and device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311325074.8A CN117092609B (en) 2023-10-13 2023-10-13 Banister anti-smashing method and device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN117092609A true CN117092609A (en) 2023-11-21
CN117092609B CN117092609B (en) 2024-01-09

Family

ID=88783575

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311325074.8A Active CN117092609B (en) 2023-10-13 2023-10-13 Banister anti-smashing method and device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117092609B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109633571A (en) * 2018-12-18 2019-04-16 长沙莫之比智能科技有限公司 A kind of 77GHz millimeter wave gate cracking protection radar signal processing device
CN111830508A (en) * 2020-06-23 2020-10-27 北京航空航天大学 Barrier gate anti-smashing system and method adopting millimeter wave radar
CN111897278A (en) * 2020-09-30 2020-11-06 深圳电目科技有限公司 Barrier gate control method and system based on radar
CN115331413A (en) * 2022-08-11 2022-11-11 深圳安智杰科技有限公司 Barrier gate rod early warning method and device, electronic equipment and storage medium
US20230048680A1 (en) * 2020-04-28 2023-02-16 Huawei Technologies Co., Ltd. Method and apparatus for passing through barrier gate crossbar by vehicle
CN116256756A (en) * 2023-03-14 2023-06-13 森思泰克河北科技有限公司 Vehicle anti-smashing method and device based on radar detection, terminal and storage medium
CN116575371A (en) * 2023-05-10 2023-08-11 济宁港航龙拱港有限公司 Anti-smashing and anti-misoperation barrier gate opening system and method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109633571A (en) * 2018-12-18 2019-04-16 长沙莫之比智能科技有限公司 A kind of 77GHz millimeter wave gate cracking protection radar signal processing device
US20230048680A1 (en) * 2020-04-28 2023-02-16 Huawei Technologies Co., Ltd. Method and apparatus for passing through barrier gate crossbar by vehicle
CN111830508A (en) * 2020-06-23 2020-10-27 北京航空航天大学 Barrier gate anti-smashing system and method adopting millimeter wave radar
CN111897278A (en) * 2020-09-30 2020-11-06 深圳电目科技有限公司 Barrier gate control method and system based on radar
CN115331413A (en) * 2022-08-11 2022-11-11 深圳安智杰科技有限公司 Barrier gate rod early warning method and device, electronic equipment and storage medium
CN116256756A (en) * 2023-03-14 2023-06-13 森思泰克河北科技有限公司 Vehicle anti-smashing method and device based on radar detection, terminal and storage medium
CN116575371A (en) * 2023-05-10 2023-08-11 济宁港航龙拱港有限公司 Anti-smashing and anti-misoperation barrier gate opening system and method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
徐韶华: "基于图像识别的车道闸杆防砸系统研究", 西部交通科技, no. 06 *

Also Published As

Publication number Publication date
CN117092609B (en) 2024-01-09

Similar Documents

Publication Publication Date Title
CN108681693B (en) License plate recognition method based on trusted area
CN109753975A (en) Training sample obtaining method and device, electronic equipment and storage medium
KR102373753B1 (en) Method, and System for Vehicle Recognition Tracking Based on Deep Learning
KR100519781B1 (en) Object tracking method and apparatus
CN107909027B (en) Rapid human body target detection method with shielding treatment
US20140169639A1 (en) Image Detection Method and Device
CN103632382A (en) Compressive sensing-based real-time multi-scale target tracking method
CN106778474A (en) 3D human body recognition methods and equipment
Chen et al. Multi-shape descriptor vehicle classification for urban traffic
CN111915583B (en) Vehicle and pedestrian detection method based on vehicle-mounted thermal infrared imager in complex scene
CN112990313B (en) Hyperspectral image anomaly detection method and device, computer equipment and storage medium
CN107657244A (en) A kind of human body tumble behavioral value system and its detection method based on multiple-camera
CN106780568B (en) A kind of video target tracking method based on the irregular piecemeal LBP of compression
CN109658128A (en) A kind of shops based on yolo and centroid tracking enters shop rate statistical method
Wang et al. Counting people with support vector regression
Srinidhi et al. Pothole detection using CNN and AlexNet
CN117092609B (en) Banister anti-smashing method and device, computer equipment and storage medium
JP2014048702A (en) Image recognition device, image recognition method, and image recognition program
CN113205108A (en) YOLOv 4-based multi-target vehicle detection and tracking method
Saini et al. Region and feature matching based vehicle tracking for accident detection
CN116052099A (en) Small target detection method for unstructured road
Gad et al. Crowd density estimation using multiple features categories and multiple regression models
JP6611257B2 (en) Action recognition device and action recognition method
CN115171160A (en) Method for constructing robust lightweight fall detection neural network under software and hardware constraints
Philip et al. Hybrid tracking model for multiple object videos using second derivative based visibility model and tangential weighted spatial tracking model

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