CN113536850A - Target object size testing method and device based on 77G millimeter wave radar - Google Patents
Target object size testing method and device based on 77G millimeter wave radar Download PDFInfo
- Publication number
- CN113536850A CN113536850A CN202010310386.1A CN202010310386A CN113536850A CN 113536850 A CN113536850 A CN 113536850A CN 202010310386 A CN202010310386 A CN 202010310386A CN 113536850 A CN113536850 A CN 113536850A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- cluster
- target object
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application relates to a target object size testing method and device based on a 77G millimeter wave radar. The method comprises the following steps: transmitting 77G millimeter waves based on a 77G millimeter wave radar, receiving echo signals generated by the reflection of the 77G millimeter waves acting on a target body, respectively calculating to obtain target body distance information, angle information, Doppler velocity information and echo signal intensity information according to the echo signals, constructing point cloud data according to the target body distance information, angle information, Doppler velocity information and echo signal intensity information, generating a point cloud data set according to the point cloud data corresponding to each target body, clustering the point cloud data in the point cloud data set according to a pre-designed clustering algorithm to obtain clusters clustered by a plurality of point cloud data, judging whether each cluster is a target object, and if so, calculating to obtain the size of the target object according to the point cloud data at the edge of each cluster. By adopting the method, the size of the target object can be accurately measured in real time.
Description
Technical Field
The application relates to the technical field of radar speed measurement, in particular to a target object size testing method and device based on a 77G millimeter wave radar.
Background
With the improvement of the living standard of people at present, the demand of people on automobiles is very vigorous, and as the last half year of 2019, the number of motor vehicles in China is up to 3.4 hundred million, and the number of the motor vehicles is continuously increased. The measurement of obstacles in front of a vehicle is an important issue during the use of a car. The measurement schemes commonly used at present are GPS, laser measurement, ultrasonic measurement, millimeter wave radar measurement, and the like.
However, in the current driving scene, GPS, laser measurement, ultrasonic measurement, and millimeter wave radar measurement are affected by various factors, and the size of an obstacle in front of the current vehicle cannot be accurately fed back to the vehicle in real time, so that the driving condition cannot be fed back to the vehicle.
Disclosure of Invention
In view of the above, it is necessary to provide a target object size testing method and device based on a 77G millimeter wave radar, which can solve the problem that the size of the current obstacle in front of the vehicle cannot be accurately fed back to the vehicle in real time.
A target object size testing method based on a 77G millimeter wave radar, the method comprising:
transmitting 77G millimeter waves based on a 77G millimeter wave radar, and receiving echo signals generated by reflection of the 77G millimeter waves acting on a target body;
respectively calculating to obtain target body distance information, angle information, Doppler velocity information and echo signal intensity information according to the echo signals;
point cloud data are constructed according to the distance information, the angle information, the Doppler velocity information and the echo signal intensity information of the target bodies, and a point cloud data set is generated according to the point cloud data corresponding to each target body;
clustering point cloud data in the point cloud data set according to a pre-designed clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data;
and judging whether each cluster is a real detection target object, if so, calculating to obtain the size of the target object according to the point cloud data of the edge of each cluster.
In one embodiment, the method further comprises the following steps: selecting any one point cloud data in the point cloud data set as a center according to a preset density clustering algorithm, and searching the number of the point cloud data in a preset radius; and if the number of the point cloud data is larger than a preset threshold value, determining the point cloud data and the point cloud data in a preset radius as a cluster.
In one embodiment, the method further comprises the following steps: and adopting a Kalman tracking mode, and if the motion states of the previous frame and the next frame of the cluster are the same as other characteristics, judging the cluster as a target object.
In one embodiment, the method further comprises the following steps: mapping the point cloud data in each cluster on an X axis to obtain coordinate values of two point cloud data at the edge of the X axis; and calculating to obtain the size of the target object according to the difference value of the coordinate values.
In one embodiment, the method further comprises the following steps: mapping the point cloud data in each cluster on an X axis to obtain coordinate values of two point cloud data at the edge of the X axis; calculating to obtain the point cloud distance of two edges as Xsize according to the difference value of the coordinate values; and acquiring the point cloud data of the cluster of the next frame in a Kalman tracking mode, mapping the point cloud data corresponding to the next frame to an X axis, and determining the cluster as a target object if the coordinate values of two corresponding edges of the point cloud data corresponding to the next frame are X-Xsize/2 and X + Xsize/2 respectively.
In one embodiment, the method further comprises the following steps: performing speed dimension fast Fourier transform on the echo signals to obtain a plurality of distance units, searching a maximum point position from the distance units, and determining target body distance information according to the maximum point position; performing speed dimension fast Fourier transform on the distance units to obtain a plurality of Doppler speed units, searching a maximum point position from the Doppler speed units, and determining Doppler speed information according to the maximum point position; detecting CFAR through constant false alarm to obtain a plurality of target data, performing fast Fourier transform on the target data to obtain a plurality of azimuth angle units, searching for the position of a maximum value point from the azimuth angle units, and determining angle information according to the position of the maximum value point; and determining echo signal strength information according to the signal-to-noise ratio of the echo signal.
A target object size testing apparatus based on a 77G millimeter wave radar, the apparatus comprising:
the transmitting module is used for transmitting 77G millimeter waves based on a 77G millimeter wave radar and receiving echo signals generated by reflection of the 77G millimeter waves on a target body;
the echo processing module is used for respectively calculating target body distance information, angle information, Doppler velocity information and echo signal intensity information according to the echo signals;
the point cloud generating module is used for constructing point cloud data according to the distance information, the angle information, the Doppler velocity information and the echo signal intensity information of the target bodies and generating a point cloud data set according to the point cloud data corresponding to each target body;
the clustering module is used for clustering the point cloud data in the point cloud data set according to a pre-designed clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data;
and the object detection module is used for judging whether each cluster is a real detection target object, and if so, calculating to obtain the size of the target object according to the point cloud data of the edge of each cluster.
A 77G millimeter wave radar comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
transmitting 77G millimeter waves based on a 77G millimeter wave radar, and receiving echo signals generated by reflection of the 77G millimeter waves acting on a target body;
respectively calculating to obtain target body distance information, angle information, Doppler velocity information and echo signal intensity information according to the echo signals;
point cloud data are constructed according to the distance information, the angle information, the Doppler velocity information and the echo signal intensity information of the target bodies, and a point cloud data set is generated according to the point cloud data corresponding to each target body;
clustering point cloud data in the point cloud data set according to a pre-designed clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data;
and judging whether each cluster is a real detection target object, if so, calculating to obtain the size of the target object according to the point cloud data of the edge of each cluster.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
transmitting 77G millimeter waves based on a 77G millimeter wave radar, and receiving echo signals generated by reflection of the 77G millimeter waves acting on a target body;
respectively calculating to obtain target body distance information, angle information, Doppler velocity information and echo signal intensity information according to the echo signals;
point cloud data are constructed according to the distance information, the angle information, the Doppler velocity information and the echo signal intensity information of the target bodies, and a point cloud data set is generated according to the point cloud data corresponding to each target body;
clustering point cloud data in the point cloud data set according to a preset clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data;
and judging whether each cluster is a target object, if so, calculating to obtain the size of the target object according to the point cloud data of the edge of each cluster.
According to the 77G millimeter wave radar-based target object size testing method, the device, the 77G millimeter wave radar and the storage medium, 77G millimeter waves are transmitted through the 77G millimeter wave radar, echo signals generated by reflection of the 77G millimeter waves on a target object are received, and a large number of echo signals can be received. According to the embodiment of the invention, the point cloud data is collected and clustered in the point cloud data set, so that the identification of the target object is facilitated, and the size of the target object can be accurately calculated in real time.
Drawings
FIG. 1 is a diagram of an application scenario of a target object size testing method based on a 77G millimeter wave radar in one embodiment;
FIG. 2 is a schematic flow chart illustrating a target object size testing method based on a 77G millimeter wave radar in one embodiment;
FIG. 3 is a block diagram of a target object size testing device based on a 77G millimeter wave radar in one embodiment;
fig. 4 is an internal structural view of the 77G millimeter wave radar in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The target object size testing method based on the 77G millimeter wave radar can be applied to the application environment shown in FIG. 1. In which 77G millimeter wave radar 102 is installed at the center point of the front of vehicle 104, which may be a man-powered vehicle or an unmanned vehicle.
In one embodiment, as shown in fig. 2, a target object size testing method based on a 77G millimeter wave radar is provided, which is described by taking the example that the method is applied to the 77G millimeter wave radar in fig. 1, and includes the following steps:
and 202, transmitting 77G millimeter waves based on the 77G millimeter wave radar, and receiving echo signals generated by reflection of the 77G millimeter waves on a target body.
The 77G millimeter wave radar is used as an emitter, radial motion of a receiver and the emitter is inevitably generated, and the receiver can be a street lamp, a billboard, a building, a running vehicle and the like on the roadside. By transmitting 77G millimeter waves to the vehicle rear area, a large number of echo signals can be received.
And step 204, respectively calculating to obtain target body distance information, angle information, Doppler velocity information and echo signal strength information according to the echo signals.
By the echo signal, target body distance information, angle information, Doppler velocity information and echo signal intensity information can be calculated.
And step 206, constructing point cloud data according to the distance information, the angle information, the Doppler velocity information and the echo signal intensity information of the target bodies, and generating a point cloud data set according to the point cloud data corresponding to each target body.
When point cloud data are constructed, each point cloud data comprises target body distance information, angle information, Doppler velocity information and echo signal intensity information, namely when the point cloud data are read, the target body distance information, the angle information, the Doppler velocity information and the echo signal intensity information can be extracted. A plurality of point cloud data may form a point cloud data set.
And 208, clustering the point cloud data in the point cloud data set according to a pre-designed clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data.
Because a large amount of point cloud data are disordered, the point cloud data in the point cloud data set can be clustered by adopting a clustering algorithm, the clustering algorithm can adopt algorithms such as K nearest neighbor, K-means, density clustering and the like, and the clustering result is a cluster comprising center point cloud data.
And step 210, judging whether each cluster is a real detection target object, if so, calculating to obtain the size of the target object according to the point cloud data of the edge of each cluster.
After the clusters are obtained, whether the target object is a real detection target object needs to be judged, and if the target object is determined to be the real detection target object, the size of the target object is detected.
According to the target object size testing method based on the 77G millimeter wave radar, the 77G millimeter waves are transmitted through the 77G millimeter wave radar, echo signals generated by reflection of the 77G millimeter waves on a target body are received, a large number of echo signals can be received, therefore, during speed measurement, a large amount of data support is provided, each echo signal is analyzed, an analysis result is used as point cloud data, a point cloud data set is established in sequence, the cluster obtained through clustering is clustered through clustering the point cloud data set, the cluster can be determined as the target object after certain analysis, and then the size of the target object is calculated according to the point cloud data at the edge of each cluster. According to the embodiment of the invention, the point cloud data is collected and clustered in the point cloud data set, so that the identification of the target object is facilitated, and the size of the target object can be accurately calculated in real time.
In one embodiment, the specific way of clustering point cloud data in a point cloud data set according to a preset clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data is as follows: selecting any point cloud data in the point cloud data set as a center according to a preset density clustering algorithm, searching the number of the point cloud data in a preset radius, and determining the point cloud data and the point cloud data in the preset radius as a cluster if the number of the point cloud data is greater than a preset threshold value. The clustering algorithm of the embodiment selects a density algorithm, during execution of the density algorithm, one point cloud data is randomly selected from a point cloud data set, then a radius is set, the number of the point cloud data in the radius is calculated, when the number of the point cloud data is greater than a preset threshold value, the point cloud data and the point cloud data in the preset radius are determined to be a cluster, and the judgment basis is that when 77G millimeter waves are emitted to a target body, a plurality of echo signals can be generated.
Specifically, the density clustering algorithm may be a DBSCAN clustering algorithm.
In one embodiment, when the size of the target object is measured, a plurality of clusters are obtained by clustering at random, but each cluster is not necessarily a target object, for example, two similar target objects may be detected as a cluster, and therefore it is necessary to determine whether each cluster corresponds to a target object, specifically: and adopting a Kalman tracking mode, and if the motion states of the previous frame and the next frame of the cluster are the same as other characteristics, judging the cluster as a target object. In this embodiment, the other features refer to features extracted from a frame image, the frame refers to an image formed by a point cloud data set formed by the 77G millimeter wave radar emitting 77G millimeter waves each time, and since the 77G millimeter wave radar and a target object may be moving, the obtained images may be different, but since the target object is determined and is not separated due to time change, a cluster obtained in a previous frame and a cluster obtained in a subsequent frame should be the same, and by this principle, it can be determined whether a cluster is a target object. In addition, because the transmitting frequency of the 77G millimeter wave radar is high, the requirement of real-time property can be ensured through detection.
In a specific embodiment, if the cluster of the previous frame and the cluster of the next frame are not necessarily identical, the same object is determined, and a point threshold may be set, for example: the point threshold value is set to 5, when the point difference value of the clusters in the two frames of images exceeds 5, the target object is judged not to be a target object, and if the point difference value is less than or equal to 5, the target object is judged to be an object.
In addition, the images of 3 consecutive frames may be compared, or 3 or more frames may be compared, and this embodiment is not limited thereto.
In one embodiment, when calculating the size of the target object, the specific manner is as follows: and mapping the point cloud data in each cluster on an X axis to obtain coordinate values of two point cloud data at the edge of the X axis, and calculating to obtain the size of the target object according to the difference value of the coordinate values. In this embodiment, the point cloud data in the cluster is two-dimensional data, the two-dimensional data is converted into one-dimensional data by mapping the value X axis, the coordinates of each point cloud data on the X axis can be obtained, and the size of the target object can be calculated by the coordinate values of the edge point cloud data. The method has the advantages of low computing resource consumption and high feedback speed, and meets the requirement of real-time property.
In the above embodiment, the point cloud data is mapped to the X axis, and the size of the target object in the X axis direction is calculated, so that the requirement of the vehicle during operation can be met, because only the width of the target object is generally considered during the operation of the vehicle.
In another specific embodiment, the point cloud data may be mapped to the Y-axis, and the height of the target object may also be calculated, in a manner consistent with the previous embodiment. By correspondingly improving the calculation algorithm, the mapping area of the target object can also be calculated, which is not stated herein.
In one embodiment, determining whether each cluster is a target object may further include: and mapping the point cloud data in each cluster to an X axis, acquiring coordinate values of two point cloud data at the edge of the X axis, calculating to obtain the point cloud distance of the two edges as Xsize according to the difference value of the coordinate values, acquiring the point cloud data of the next frame of clusters by adopting a Kalman tracking mode, mapping the point cloud data corresponding to the next frame to the X axis, and determining the clusters as target objects if the coordinate values of the two edges corresponding to the point cloud data corresponding to the next frame are X-Xsize/2 and X + Xsize/2 respectively. In this embodiment, in a scene where a vehicle is traveling, the width of the same target object generally does not change, and therefore, after the edge point cloud distance corresponding to the previous frame determination cluster is Xsize, the next frame obtains the same result, and the same target object can be determined.
In one embodiment, the echo signal is analyzed as follows: the method comprises the steps of performing speed dimension fast Fourier transform on echo signals to obtain a plurality of distance units, searching a position of a maximum value point from the distance units, determining distance information of a target body according to the position of the maximum value point, performing speed dimension fast Fourier transform on the distance units to obtain a plurality of Doppler speed units, searching the position of the maximum value point from the Doppler speed units, determining Doppler speed information according to the position of the maximum value point, detecting CFAR through a constant false alarm to obtain a plurality of target data, performing fast Fourier transform on the target data to obtain a plurality of azimuth units, searching the position of the maximum value point from the azimuth units, determining angle information according to the position of the maximum value point, and determining intensity information of the echo signals according to the signal-to-noise ratio of the echo signals. In this embodiment, the echo signal can be quickly processed by fast fourier transform, so as to obtain the required parameters.
It is worth to be noted that, from the list processed by the CFAR algorithm, both peak values and non-peak values are included in the point cloud information, and peak value detection is not performed.
It should be understood that, although the steps in the flowchart of fig. 2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 3, there is provided a target object size testing apparatus based on a 77G millimeter wave radar, including: a transmitting module 302, an echo processing module 304, a point cloud generating module 306, a clustering module 308 and a speed measuring module 310, wherein:
the transmitting module 302 is used for transmitting 77G millimeter waves based on a 77G millimeter wave radar and receiving echo signals generated by reflection of the 77G millimeter waves on a target body;
the echo processing module 304 is configured to respectively calculate distance information, angle information, doppler velocity information, and echo signal intensity information of a target according to the echo signal;
the point cloud generating module 306 is configured to construct point cloud data according to the target distance information, the angle information, the doppler velocity information, and the echo signal intensity information, and generate a point cloud data set according to the point cloud data corresponding to each target;
and the clustering module 308 is configured to cluster the point cloud data in the point cloud data set according to a pre-designed clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data.
And the object detection module 310 is configured to determine whether each cluster is a real detection target object, and if yes, calculate the size of the target object according to the point cloud data of the edge of each cluster.
In one embodiment, the clustering module 308 is further configured to select any one of the point cloud data in the point cloud data sets as a center according to a preset density clustering algorithm, and search the number of the point cloud data within a preset radius; and if the number of the point cloud data is larger than a preset threshold value, determining the point cloud data and the point cloud data in a preset radius as a cluster.
In one embodiment, the object detection module 310 is further configured to determine that the cluster is the target object by using a kalman tracking method if a previous frame and a next frame of the cluster are the same.
In one embodiment, the object detection module 310 is further configured to map the point cloud data in each cluster onto the X-axis, and obtain coordinate values of two point cloud data at the edge of the X-axis; and calculating to obtain the size of the target object according to the difference value of the coordinate values.
In one embodiment, the object detection module 310 is further configured to map the point cloud data in each cluster onto the X-axis, and obtain coordinate values of two point cloud data at the edge of the X-axis; calculating to obtain the point cloud distance of two edges as Xsize according to the difference value of the coordinate values; and acquiring the point cloud data of the cluster of the next frame in a Kalman tracking mode, mapping the point cloud data corresponding to the next frame to an X axis, and determining the cluster as a target object if the coordinate values of two corresponding edges of the point cloud data corresponding to the next frame are X-Xsize/2 and X + Xsize/2 respectively.
In one embodiment, the echo processing module 304 is configured to perform a velocity-dimensional fast fourier transform on the echo signal to obtain a plurality of distance units, search a maximum point position from the distance units, and determine target distance information according to the maximum point position; performing speed dimension fast Fourier transform on the distance units to obtain a plurality of Doppler speed units, searching a maximum point position from the Doppler speed units, and determining Doppler speed information according to the maximum point position; detecting CFAR through constant false alarm to obtain a plurality of target data, performing fast Fourier transform on the target data to obtain a plurality of azimuth angle units, searching for the position of a maximum value point from the azimuth angle units, and determining angle information according to the position of the maximum value point; and determining echo signal strength information according to the signal-to-noise ratio of the echo signal.
For the specific definition of the target object size testing device based on the 77G millimeter wave radar, reference may be made to the above definition of the target object size testing method based on the 77G millimeter wave radar, and details are not repeated here. The respective modules in the 77G millimeter wave radar-based target object size testing apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or be independent of a processor in the 77G millimeter wave radar, and can also be stored in a memory in the 77G millimeter wave radar in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a 77G millimeter wave radar is provided, the internal structure of which may be as shown in fig. 4. The 77G millimeter wave radar comprises a transceiving front end, a DSP processor and an ARM processor which are sequentially connected, and the vehicle speed is output through a network interface. Wherein, the processor of the 77G millimeter wave radar is used for providing calculation and control capability. The memory of the 77G millimeter wave radar comprises a nonvolatile 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 an operating system and computer programs in the non-volatile storage medium. The network interface of the 77G millimeter wave radar is used for communication with an external terminal through a network/local connection. The computer program is executed by a processor to realize a target object size testing method based on the 77G millimeter wave radar.
Those skilled in the art will appreciate that the structure shown in fig. 4 is only a block diagram of a part of the structure related to the present application, and does not constitute a limitation on the 77G millimeter wave radar to which the present application is applied, and a specific 77G millimeter wave radar may include more or less components than those shown in the figure, or combine some components, or have different component arrangements.
In one embodiment, a 77G millimeter wave radar is provided comprising a memory storing a computer program and a processor implementing the steps of the above-described method embodiments when the processor executes the computer program.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A target object size testing method based on a 77G millimeter wave radar, wherein the 77G millimeter wave radar is installed at the center point of the head of a vehicle, the method comprises the following steps:
transmitting 77G millimeter waves based on a 77G millimeter wave radar, and receiving echo signals generated by reflection of the 77G millimeter waves acting on a target body;
respectively calculating to obtain target body distance information, angle information, Doppler velocity information and echo signal intensity information according to the echo signals;
point cloud data are constructed according to the distance information, the angle information, the Doppler velocity information and the echo signal intensity information of the target bodies, and a point cloud data set is generated according to the point cloud data corresponding to each target body;
clustering point cloud data in the point cloud data set according to a pre-designed clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data;
and judging whether each cluster is a real detection target object, if so, calculating to obtain the size of the target object according to the point cloud data of the edge of each cluster.
2. The method of claim 1, wherein the clustering the point cloud data in the point cloud data set according to a preset clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data comprises:
selecting any one point cloud data in the point cloud data set as a center according to a preset density clustering algorithm, and searching the number of the point cloud data in a preset radius;
and if the number of the point cloud data is larger than a preset threshold value, determining the point cloud data and the point cloud data in a preset radius as a cluster.
3. The method of claim 1, wherein the determining whether each cluster is a target object comprises:
and adopting a Kalman tracking mode, and if the motion states of the previous frame and the next frame of the cluster are the same as other characteristics, judging the cluster as a target object.
4. The method of claim 1, wherein calculating the size of the target object from the point cloud data of each cluster edge comprises:
mapping the point cloud data in each cluster on an X axis to obtain coordinate values of two point cloud data at the edge of the X axis;
and calculating to obtain the size of the target object according to the difference value of the coordinate values.
5. The method of claim 3, wherein determining whether each cluster is a target object comprises:
mapping the point cloud data in each cluster on an X axis to obtain coordinate values of two point cloud data at the edge of the X axis;
calculating to obtain the point cloud distance of two edges as Xsize according to the difference value of the coordinate values;
and acquiring the point cloud data of the cluster of the next frame in a Kalman tracking mode, mapping the point cloud data corresponding to the next frame to an X axis, and determining the cluster as a target object if the coordinate values of two corresponding edges of the point cloud data corresponding to the next frame are X-Xsize/2 and X + Xsize/2 respectively.
6. The method according to any one of claims 1 to 5, wherein the step of calculating target distance information, angle information, Doppler velocity information and echo signal strength information from the echo signals comprises:
performing speed dimension fast Fourier transform on the echo signals to obtain a plurality of distance units, searching a maximum point position from the distance units, and determining target body distance information according to the maximum point position;
performing speed dimension fast Fourier transform on the distance units to obtain a plurality of Doppler speed units, searching a maximum point position from the Doppler speed units, and determining Doppler speed information according to the maximum point position;
detecting CFAR through constant false alarm to obtain a plurality of target data, performing fast Fourier transform on the target data to obtain a plurality of azimuth angle units, searching for the position of a maximum value point from the azimuth angle units, and determining angle information according to the position of the maximum value point;
and determining echo signal strength information according to the signal-to-noise ratio of the echo signal.
7. A target object size testing device based on a 77G millimeter wave radar, the device comprising:
the transmitting module is used for transmitting 77G millimeter waves based on a 77G millimeter wave radar and receiving echo signals generated by reflection of the 77G millimeter waves on a target body;
the echo processing module is used for respectively calculating target body distance information, angle information, Doppler velocity information and echo signal intensity information according to the echo signals;
the point cloud generating module is used for constructing point cloud data according to the distance information, the angle information, the Doppler velocity information and the echo signal intensity information of the target bodies and generating a point cloud data set according to the point cloud data corresponding to each target body;
the clustering module is used for clustering the point cloud data in the point cloud data set according to a pre-designed clustering algorithm to obtain a cluster formed by clustering a plurality of point cloud data;
and the object detection module is used for judging whether each cluster is a real detection target object, and if so, calculating to obtain the size of the target object according to the point cloud data of the edge of each cluster.
8. The device according to claim 7, wherein the clustering module is further configured to select any one of the point cloud data sets as a center according to a preset density clustering algorithm, and search for the number of the point cloud data within a preset radius; and if the number of the point cloud data is larger than a preset threshold value, determining the point cloud data and the point cloud data in a preset radius as a cluster.
9. A77G millimeter wave radar comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010310386.1A CN113536850B (en) | 2020-04-20 | 2020-04-20 | Target object size testing method and device based on 77G millimeter wave radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010310386.1A CN113536850B (en) | 2020-04-20 | 2020-04-20 | Target object size testing method and device based on 77G millimeter wave radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113536850A true CN113536850A (en) | 2021-10-22 |
| CN113536850B CN113536850B (en) | 2022-09-30 |
Family
ID=78123563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010310386.1A Active CN113536850B (en) | 2020-04-20 | 2020-04-20 | Target object size testing method and device based on 77G millimeter wave radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113536850B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114140997A (en) * | 2021-12-06 | 2022-03-04 | 河北地质大学 | System and method for monitoring and early warning of retention and physical condition of old people in toilet of nursing home |
| CN114442081A (en) * | 2021-12-21 | 2022-05-06 | 珠海格力电器股份有限公司 | Personnel detection method, device, storage medium and electronic equipment |
| CN115236627A (en) * | 2022-09-21 | 2022-10-25 | 深圳安智杰科技有限公司 | Millimeter wave radar data clustering method based on multi-frame Doppler velocity dimension expansion |
| WO2023124780A1 (en) * | 2021-12-27 | 2023-07-06 | 北京万集科技股份有限公司 | Point cloud data augmentation method and apparatus, and computer device, system and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957106A (en) * | 2016-04-26 | 2016-09-21 | 湖南拓视觉信息技术有限公司 | Method and apparatus for tracking three-dimensional targets |
| US20190285410A1 (en) * | 2017-02-28 | 2019-09-19 | Riken | Point cloud data extraction method and point cloud data extraction device |
| CN110275153A (en) * | 2019-07-05 | 2019-09-24 | 上海大学 | A kind of waterborne target detection and tracking based on laser radar |
| CN110361727A (en) * | 2019-07-22 | 2019-10-22 | 浙江大学 | A kind of millimetre-wave radar multi-object tracking method |
| CN110647835A (en) * | 2019-09-18 | 2020-01-03 | 合肥中科智驰科技有限公司 | Target detection and classification method and system based on 3D point cloud data |
| CN110766719A (en) * | 2019-09-21 | 2020-02-07 | 北醒（北京）光子科技有限公司 | Target tracking method, device and storage medium |
| CN110866449A (en) * | 2019-10-21 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Method and device for identifying target object in road |
| CN110969855A (en) * | 2019-12-13 | 2020-04-07 | 长沙莫之比智能科技有限公司 | Traffic flow monitoring system based on millimeter wave radar |
-
2020
- 2020-04-20 CN CN202010310386.1A patent/CN113536850B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957106A (en) * | 2016-04-26 | 2016-09-21 | 湖南拓视觉信息技术有限公司 | Method and apparatus for tracking three-dimensional targets |
| US20190285410A1 (en) * | 2017-02-28 | 2019-09-19 | Riken | Point cloud data extraction method and point cloud data extraction device |
| CN110275153A (en) * | 2019-07-05 | 2019-09-24 | 上海大学 | A kind of waterborne target detection and tracking based on laser radar |
| CN110361727A (en) * | 2019-07-22 | 2019-10-22 | 浙江大学 | A kind of millimetre-wave radar multi-object tracking method |
| CN110647835A (en) * | 2019-09-18 | 2020-01-03 | 合肥中科智驰科技有限公司 | Target detection and classification method and system based on 3D point cloud data |
| CN110766719A (en) * | 2019-09-21 | 2020-02-07 | 北醒（北京）光子科技有限公司 | Target tracking method, device and storage medium |
| CN110866449A (en) * | 2019-10-21 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Method and device for identifying target object in road |
| CN110969855A (en) * | 2019-12-13 | 2020-04-07 | 长沙莫之比智能科技有限公司 | Traffic flow monitoring system based on millimeter wave radar |
Non-Patent Citations (1)
| Title |
|---|
| 胡云卿 等: "智轨电车多源环境感知系统", 《控制与信息技术》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114140997A (en) * | 2021-12-06 | 2022-03-04 | 河北地质大学 | System and method for monitoring and early warning of retention and physical condition of old people in toilet of nursing home |
| CN114140997B (en) * | 2021-12-06 | 2024-01-16 | 河北地质大学 | Monitoring and early warning system and method for residence and physical condition of old people in rest house toilet |
| CN114442081A (en) * | 2021-12-21 | 2022-05-06 | 珠海格力电器股份有限公司 | Personnel detection method, device, storage medium and electronic equipment |
| WO2023124780A1 (en) * | 2021-12-27 | 2023-07-06 | 北京万集科技股份有限公司 | Point cloud data augmentation method and apparatus, and computer device, system and storage medium |
| CN115236627A (en) * | 2022-09-21 | 2022-10-25 | 深圳安智杰科技有限公司 | Millimeter wave radar data clustering method based on multi-frame Doppler velocity dimension expansion |
| CN115236627B (en) * | 2022-09-21 | 2022-12-16 | 深圳安智杰科技有限公司 | Millimeter wave radar data clustering method based on multi-frame Doppler velocity dimension expansion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113536850B (en) | 2022-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113536850B (en) | Target object size testing method and device based on 77G millimeter wave radar | |
| US11340332B2 (en) | Method and apparatus for processing radar data | |
| KR20210096607A (en) | Radar Deep Learning | |
| JP5908193B1 (en) | Radar signal processing device | |
| CN109581353B (en) | Multi-target tracking method and system based on automobile radar | |
| CN112513679B (en) | Target identification method and device | |
| CN112824931A (en) | Method and apparatus for improving radar data using reference data | |
| Li et al. | High Resolution Radar-based Occupancy Grid Mapping and Free Space Detection. | |
| CN113109802B (en) | Target motion state judging method, device, radar equipment and storage medium | |
| JP7152355B2 (en) | Obstacle detection device and obstacle detection method | |
| JP2018115931A (en) | Radar device and method for detecting target | |
| US20230184926A1 (en) | Radar anti-spoofing system for identifying ghost objects created by reciprocity-based sensor spoofing | |
| US20230139751A1 (en) | Clustering in automotive imaging | |
| CN112946623B (en) | Speed measuring method and device based on 77G millimeter wave radar installed on vehicle | |
| US11841419B2 (en) | Stationary and moving object recognition apparatus | |
| JP7418476B2 (en) | Method and apparatus for determining operable area information | |
| CN116699596A (en) | Method and device for correcting speed of millimeter wave radar of vehicle | |
| US20220373672A1 (en) | Multipath classification in radar detections | |
| JP2017122646A (en) | Moving object detection device | |
| WO2022089193A1 (en) | Method for controlling vehicle-mounted radar signal, and electronic device and storage medium | |
| WO2021189206A1 (en) | Radar signal processing method and radar signal processing apparatus | |
| JP2022059892A (en) | Object tracking device | |
| CN117784028B (en) | Random clutter recognition method, system, computer device and storage medium | |
| EP4357813A1 (en) | A vehicle radar system arranged to provide an estimated road lane | |
| KR102208175B1 (en) | Adaptive tracking frequency control method of mobile radar |
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 |