CN116432060A - Target self-adaptive clustering method, device, equipment and storage medium based on radar - Google Patents
Target self-adaptive clustering method, device, equipment and storage medium based on radar Download PDFInfo
- Publication number
- CN116432060A CN116432060A CN202310323644.3A CN202310323644A CN116432060A CN 116432060 A CN116432060 A CN 116432060A CN 202310323644 A CN202310323644 A CN 202310323644A CN 116432060 A CN116432060 A CN 116432060A
- Authority
- CN
- China
- Prior art keywords
- radar
- point
- window
- points
- clustering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000001514 detection method Methods 0.000 claims abstract description 69
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 230000003044 adaptive effect Effects 0.000 claims description 35
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000007423 decrease Effects 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application discloses a radar-based target self-adaptive clustering method, device, equipment and storage medium, wherein the method comprises the following steps: acquiring Lei Dadian cloud data and creating a four-dimensional grid of radar detection data; corresponding each detection point of the radar point cloud data to a four-dimensional grid, and recording index information of each detection point in the grid; creating at least one three-dimensional clustering window based on the grid; judging whether the processing point is a noise point or not, and filtering the noise point; and carrying out self-adaptive clustering or fixed parameter clustering on the detection points. The similarity of the distance, the pitching angle, the horizontal angle and the speed of the radar detection point is considered, and the target clustering process is accelerated by replacing the traditional Euclidean distance by the self-adaptive clustering window based on the grid index; the application uses a specific list structure of point indexes, and only records index information of existence of the detection points so as to minimize storage space.
Description
Technical Field
The present disclosure relates to the field of radar data processing technologies, and in particular, to a target adaptive clustering method, device, equipment, and storage medium based on radar.
Background
Among the various radar types, millimeter wave radar is small in size, easy to integrate and high in spatial resolution. However, due to the defect of insufficient height measurement capability of the traditional millimeter wave radar, the method has larger limitation on distinguishing and identifying short targets, aerial targets and road static targets, and the total output information quantity is not in the same magnitude with the information output of the visible light camera and the laser radar, so that the method has certain limitation. With the continuous breakthrough of the technology in the radar field, the 4D imaging radar sensor breaks through the limitation, but the data processing of the 4D imaging radar still needs to be hard.
Clustering has been widely used to process image data and radar data, and Density-based noisy applied spatial clustering (DBSCAN clustering algorithm, density-Based Spatial Clustering of Applications with Noise) has proven to be one of the most suitable methods among various clustering algorithms. However, DBSCAN also has some drawbacks in radar data clustering, such as unequal dimensions, large calculation amount, and strong parameter dependence.
Disclosure of Invention
Based on the problems, the application provides a radar-based target self-adaptive clustering method, a radar-based target self-adaptive clustering device, radar-based target self-adaptive clustering equipment and a storage medium, wherein a clustering window based on grid indexes is used for replacing Euclidean distance to accelerate a clustering process; at the same time, a specific list structure of point indexes is applied to minimize the storage space.
The embodiment of the application discloses the following technical scheme:
the first aspect of the application provides a radar-based target adaptive clustering method, which comprises the following steps:
acquiring Lei Dadian cloud data and creating a four-dimensional grid of radar detection data;
corresponding each detection point of the radar point cloud data to a four-dimensional grid, and recording index information of each detection point in the grid;
creating at least one three-dimensional clustering window based on grids, wherein detection points with similar speeds and similar distances are located in the window;
setting a threshold value of the number of adjacent points of the window, judging whether the processing points are noise points, and filtering the noise points;
and determining a target contour according to preset information, carrying out self-adaptive clustering on the detection points if the target contour can be obtained, and otherwise, carrying out fixed parameter clustering.
Further, the creating the four-dimensional grid of radar detection data includes:
calculating a fast fourier transform in a distance dimension, wherein a gate unit value FFT bin size of the distance is used as a grid size;
the size of the grid in the velocity dimension is determined by the FFT bin value over the velocity;
the angles are estimated using a DML algorithm that generates an arithmetic sequence, and the common differences of the estimated sequences are used to determine the grid size in the dimensional angles.
Further, the index information is assigned information preset on each grid line, index information of the detection point is marked and stored, and index information of the detection point which does not exist is not recorded.
Further, in the index information, a difference between two indexes of the distance dimension represents a physical distance of a point, and an index difference of the angle dimension is converted into a physical distance by the following equation:
Δd θ ≈r×sinΔθ。
illustratively, the physical distance between the pitch angle dimension and the horizontal angle dimension index can be calculated by the above formula.
Further, the creating at least one grid-based three-dimensional cluster window comprises:
creating a three-dimensional clustering window based on a grid around the unit of the processing point, wherein the window is a fixed parameter clustering window or a self-adaptive clustering window;
the size of the fixed parameter cluster window is determined by two variables: distance threshold d in distance dimension or angle dimension thr And a speed difference threshold dv thr ；
The three-dimensional clustering window is a cylinder, the distance dimension or the angle dimension is an ellipse, and detection points with similar distances and similar speeds are located in the window.
Further, the number of grid cells occupied by the three-dimensional cluster window decreases with increasing range, which ensures that the spatial size of the cluster window is always the same throughout the area.
Further, setting a threshold value of the number of adjacent points of the window, and judging whether the processing point is a noise point, wherein filtering the noise point includes:
searching index information of all cells in a window of a processing point, and comparing the index information with a point index list; identifying adjacent points of the processing points in the window;
if the number of points is smaller than a given threshold n thr The processing point is marked as a noise point; otherwise, the point is the core point of a point cloud cluster, all adjacent points are also allocated to the cluster, and then the adjacent points are used as new processing points and are processed by the same process of a clustering window;
after all detection points are processed, clusters with selected points are identified and noise points are eliminated.
Further, the predicting the target profile includes:
pre-classifying the targets that may be detected into pedestrians, riders, and vehicles by means of a vector machine (SVM, support Vector Machine) and machine learning; predefining the contour size of each target type;
determining the initial position and the motion direction of the point cloud cluster according to the average coordinates and the average speed of all detection points of the current frame belonging to the same point cloud cluster; meanwhile, storing the maximum and minimum speeds for a cluster window of the next frame, namely, the upper and lower points of the speed dimension in the cluster;
the contour is determined based on the size of the point cloud cluster around the estimated position of the point cloud cluster of the current frame.
Further, the adaptive clustering includes:
determining a cluster window size according to the predefined target classification and the predicted target profile;
the cluster window is defined by the predicted target profile in the distance or angle dimension and the maximum and minimum speeds from the last cycle in the speed dimension.
Further, the four-dimensional grid of radar detection data includes a radial distance dimension, a horizontal angle dimension, a pitch angle dimension, and a radial velocity dimension.
A second aspect of the present application provides a radar-based target adaptive clustering device, including:
four-dimensional grid creation unit: acquiring Lei Dadian cloud data and creating a four-dimensional grid of radar detection data;
point cloud index correspondence unit: corresponding each detection point of the radar point cloud data to a four-dimensional grid, and recording index information of each detection point in the grid;
three-dimensional cluster window creation unit: creating at least one three-dimensional clustering window based on grids, wherein detection points with similar speeds and similar distances are located in the window;
noise point filtering unit: setting a threshold value of the number of adjacent points of the window, judging whether the processing points are noise points, and filtering the noise points;
and (3) an adaptive clustering unit: and determining a target contour according to preset information, carrying out self-adaptive clustering on the detection points if the target contour can be obtained, and otherwise, carrying out fixed parameter clustering.
A third aspect of the present application provides a radar-based target adaptive clustering device, comprising:
the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the radar-based target adaptive clustering method according to the first aspect of the application when executing the computer program.
A fourth aspect of the present application provides a computer readable storage medium having instructions stored therein which, when run on a terminal device, cause the terminal device to perform a radar-based target adaptive clustering method as described in the first aspect of the present application.
Compared with the prior art, the application has the following beneficial effects:
the method combines the traditional DBSCAN clustering algorithm, provides a target clustering method based on four-dimensional grids, considers the similarity of the distance, angle and speed of points, and accelerates the target clustering process by replacing Euclidean distance by a self-adaptive clustering window based on grid indexes;
the application uses a specific list structure of point indexes, and only records index information of the existence of the detection points so as to minimize storage space.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of a target adaptive clustering method based on radar according to an embodiment of the present application;
fig. 2 is a conceptual diagram of a four-dimensional grid and cluster window for creating radar detection data according to an embodiment of the present application;
fig. 3 is a schematic diagram of an adaptive clustering flow provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of a target adaptive clustering device based on radar according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a target adaptive clustering device based on radar according to an embodiment of the present application.
Detailed Description
As described above, clustering has been widely used to process image data and radar data, and density-based noisy applied spatial clustering (DBSCAN) has proven to be one of the most suitable methods in various clustering algorithms because it is applicable to arbitrary object shapes, and does not require prior information, such as the exact number of clusters in the dataset. However, DBSCAN also has some drawbacks in radar data clustering, such as unequal dimensions, large calculation amount, and strong parameter dependence.
In view of this, the target adaptive clustering method based on radar provided in the embodiment of the present application includes: acquiring Lei Dadian cloud data and creating a four-dimensional grid of radar detection data; corresponding each detection point of the radar point cloud data to a four-dimensional grid, and recording index information of each detection point in the grid; creating at least one three-dimensional clustering window based on grids, wherein detection points with similar speeds and similar distances are located in the window; setting a threshold value of the number of adjacent points of the window, judging whether the processing points are noise points, and filtering the noise points; and determining a target contour according to preset information, carrying out self-adaptive clustering on the detection points if the target contour can be obtained, and otherwise, carrying out fixed parameter clustering. The method combines the traditional DBSCAN clustering algorithm, provides a target clustering method based on four-dimensional grids, considers the similarity of the distance, angle and speed of points, and accelerates the target clustering process by replacing Euclidean distance by a self-adaptive clustering window based on grid indexes; the application uses a specific list structure of point indexes, and only records index information of the existence of the detection points so as to minimize storage space.
In order to make the present application solution better understood by those skilled in the art, the following description will clearly and completely describe the technical solution in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Referring to fig. 1, the flow chart of a target adaptive clustering method based on radar provided in the embodiment of the present application is shown in fig. 1, where the target adaptive clustering method based on radar includes:
s110: acquiring Lei Dadian cloud data and creating a four-dimensional grid of radar detection data;
s110 includes:
s1101, creating a four-dimensional grid of radar detection data:
for example, referring to fig. 2, a fast fourier transform is calculated in a distance dimension, where a gate element of distance, i.e., FFT bin value size, is used as a grid size;
as a possible implementation, see Δr in the figure, the FFT bin value is 0.0633m.
The grid size in the velocity dimension is determined by the gate units in velocity, i.e. the FFT bin values; as a possible implementation, the FFT bin value is 0.0397m/s
The angles are estimated using the DML algorithm, a deterministic maximum likelihood algorithm, which generates an arithmetic sequence that uses the common differences of the estimated sequences to determine the size of the grid in the dimensional angles.
As a possible embodiment, the common difference is 0.25 degrees.
S120: corresponding each detection point of the radar point cloud data to a four-dimensional grid, and recording index information of each detection point in the grid;
s120 includes:
s1201, determining index information:
the index information is assigned information preset on each grid line, the index information of the detection point is marked and stored, and the index information of the detection point which does not exist is not recorded.
S1202, in the index information, a difference between two indexes of a distance dimension represents a physical distance of a point, and an index difference of an angle dimension is converted into a physical distance by the following equation:
Δd θ ≈r×sinΔθ。
s130: creating at least one three-dimensional clustering window based on grids, wherein detection points with similar speeds and similar distances are located in the window;
s130 includes:
s1301, creating at least one three-dimensional clustering window based on the grid comprises:
creating a three-dimensional clustering window based on a grid around the unit of the processing point, wherein the window is a fixed parameter clustering window or a self-adaptive clustering window;
wherein the size of the fixed parameter cluster window is determined by two variables: distance threshold d in distance dimension or angle dimension thr And a speed difference threshold dv thr ；
The three-dimensional clustering window is a cylinder, the distance dimension or the angle dimension is an ellipse, and detection points with similar distances and similar speeds are located in the window.
S1302, the number of grid cells occupied by the three-dimensional cluster window decreases with increasing range, which ensures that the spatial size of the cluster window is always the same throughout the area.
S140: setting a threshold value of the number of adjacent points of the window, judging whether the processing points are noise points, and filtering the noise points;
s1401, setting a threshold value of the number of adjacent points of the window, judging whether the processing point is a noise point, and filtering the noise point:
searching index information of all cells in a window of a processing point, and comparing the index information with a point index list; identifying adjacent points of the processing points in the window;
if the number of points is smaller than a given threshold n thr The processing point is marked as a noise point; otherwise, the point is the core point of a point cloud cluster, all adjacent points are also allocated to the cluster, and then the adjacent points are used as new processing points and are processed by the same process of a clustering window;
after all detection points are processed, clusters with selected points are identified and noise points are eliminated.
S150: and determining a target contour according to preset information, carrying out self-adaptive clustering on the detection points if the target contour can be obtained, and otherwise, carrying out fixed parameter clustering.
S1501, predicting a target contour:
pre-classifying the targets that may be detected into pedestrians, riders, and vehicles by means of a vector machine (SVM, support Vector Machine) and machine learning; predefining the contour size of each target type;
determining the initial position and the motion direction of the point cloud cluster according to the average coordinates and the average speed of all detection points of the current frame belonging to the same point cloud cluster; meanwhile, storing the maximum and minimum speeds for a cluster window of the next frame, namely, the upper and lower points of the speed dimension in the cluster;
the contour is determined based on the size of the point cloud cluster around the estimated position of the point cloud cluster of the current frame.
S1502, adaptive clustering:
determining a cluster window size according to the predefined target classification and the predicted target profile;
the cluster window is defined by the predicted target profile in the distance or angle dimension and the maximum and minimum speeds from the last cycle in the speed dimension.
Further, the four-dimensional grid of radar detection data includes a radial distance dimension, a horizontal angle dimension, a pitch angle dimension, and a radial velocity dimension.
Referring to fig. 3, the radar point cloud data set is denoted as P, and target profile information is determined according to a predefined target classification; if the initial contour information can be obtained, selecting a clustering window with a predefined contour corresponding to the size to perform target clustering on the Lei Dadian cloud data set P to obtain a first clustering result P m If the target profile information cannot be obtained due to the sparse point cloud or other reasons, performing target clustering on the Lei Dadian cloud data set P by using a clustering window with fixed parameters to obtain a second clustering result P g The first clustering result P m And second aggregate result P g Combining the clustering information of the target clusters to obtain a final target clustering result P c 。
Referring to fig. 4, the structure schematic diagram of a radar-based target adaptive clustering device provided in the embodiment of the present application, as shown in fig. 4, the radar-based target adaptive clustering device includes:
four-dimensional grid creation unit: acquiring Lei Dadian cloud data and creating a four-dimensional grid of radar detection data;
point cloud index correspondence unit: corresponding each detection point of the radar point cloud data to a four-dimensional grid, and recording index information of each detection point in the grid;
three-dimensional cluster window creation unit: creating at least one three-dimensional clustering window based on grids, wherein detection points with similar speeds and similar distances are located in the window;
noise point filtering unit: setting a threshold value of the number of adjacent points of the window, judging whether the processing points are noise points, and filtering the noise points;
and (3) an adaptive clustering unit: and determining a target contour according to preset information, carrying out self-adaptive clustering on the detection points if the target contour can be obtained, and otherwise, carrying out fixed parameter clustering.
For technical terms mentioned in the present application, the following is explained here:
the 4D is compared with the traditional millimeter wave radar, namely the 3D radar, and only has three dimensions of distance, speed and azimuth angle, the information perception capability of pitching angle is increased, and the longitudinal target can be identified with high resolution; the imaging is similar to the point cloud imaging effect of a laser radar, compared with the traditional millimeter wave radar, the number of radio frequency receiving and transmitting channels of the 4D imaging radar is more than ten times, and the imaging can show rich point cloud images, distance, speed and angle information for targets and environments along with the great improvement of pitching angle resolution.
Detecting point: the detection point in the embodiment of the application refers to a direct microwave reflection point obtained by detecting the 4D radar from the sensor, and one detection point does not necessarily reflect one target directly.
And (3) point cloud: the point data set of the microwave radar, especially the millimeter wave radar, which is the information reflected by the wave beam of the sensor is called as point cloud, the point-to-point distance is larger and is called as sparse point cloud, and the point-to-point distance is smaller and forms denser point cloud clusters.
Processing point: when radar data is processed, the detection point of the current calculation processing is the processing point.
Referring to fig. 5, a schematic structural diagram of an electronic device 700 suitable for use in implementing embodiments of the present disclosure is shown for implementing the functionality corresponding to the radar-based overflow detection device shown in fig. 5. The electronic device shown in fig. 5 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.
As shown in fig. 5, the electronic device 700 may include a processing means (e.g., a central processor, a graphics processor, etc.) 701, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage means 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
In general, the following devices may be connected to the I/O interface 705: input devices 706 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 707 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 708 including, for example, magnetic tape, hard disk, etc.; and a communication device 709. The communication means 709 may allow the electronic device 700 to communicate wirelessly or by wire with other devices to exchange data. While fig. 5 shows an electronic device 700 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a non-transitory computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via communication device 709, or installed from storage 708, or installed from ROM 702. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 701.
It should be noted that the computer readable medium of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
In the present application, however, a computer-readable signal medium may include a data signal that propagates in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
While several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present application. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
The foregoing description is only of the preferred embodiments of the present application and is presented as a description of the principles of the technology being utilized. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this application is not limited to the specific combinations of features described above, but it is intended to cover other embodiments in which any combination of features described above or equivalents thereof is possible without departing from the spirit of the disclosure. Such as the above-described features and technical features having similar functions (but not limited to) disclosed in the present application are replaced with each other.
Claims (13)
1. A radar-based target adaptive clustering method, the method comprising:
acquiring Lei Dadian cloud data and creating a four-dimensional grid of radar detection data;
corresponding each detection point of the radar point cloud data to a four-dimensional grid, and recording index information of each detection point in the grid;
creating at least one three-dimensional clustering window based on grids, wherein detection points with similar speeds and similar distances are located in the window;
setting a threshold value of the number of adjacent points of the window, judging whether the processing points are noise points, and filtering the noise points;
and determining a target contour according to preset information, carrying out self-adaptive clustering on the detection points if the target contour can be obtained, and otherwise, carrying out fixed parameter clustering.
2. The radar-based target adaptive clustering method of claim 1, wherein the creating a four-dimensional grid of radar detection data comprises:
computing a fast fourier transform in a distance dimension, wherein gate element values of the distances are used as a grid size;
the grid size in the velocity dimension is determined by the gate cell value of the velocity;
the angles are estimated using a DML algorithm that generates an arithmetic sequence that uses the common differences of the sequences to determine the grid size in the dimensional angles.
3. The radar-based target adaptive clustering method according to claim 1, wherein the index information is assigned information preset at each grid line, the index information for the detection point is stored in a marked manner, and the index information for the detection point is not recorded.
4. The radar-based target adaptive clustering method according to claim 1, wherein in the index information, a difference between two indexes of a distance dimension represents a physical distance of a point, and an index difference of an angle dimension is converted into a physical distance by:
Δd θ ≈r×sinΔθ。
5. the radar-based target adaptive clustering method of claim 1, wherein the creating at least one grid-based three-dimensional clustering window comprises:
creating a three-dimensional clustering window based on a grid around the unit of the processing point, wherein the window is a fixed parameter clustering window or a self-adaptive clustering window;
the size of the fixed parameter cluster window is determined by two variables: distance threshold d in distance dimension or angle dimension thr And a speed difference threshold dv thr ；
The three-dimensional clustering window is a cylinder, and detection points with similar distances and similar speeds are located in the window.
6. The radar-based target adaptive clustering method of claim 5, wherein the number of grid cells occupied by the three-dimensional clustering window decreases with increasing range.
7. The radar-based target adaptive clustering method according to claim 1, wherein the setting the threshold value of the number of adjacent points in the window, determining whether the processing point is a noise point, and filtering the noise point includes:
searching index information of all cells in a window of a processing point, and comparing the index information with a point index list; identifying adjacent points of the processing points in the window;
if the number of points is less than the preset threshold n thr The processing point is marked as a noise point; otherwise, the point is the core point of a point cloud cluster, all adjacent points are also allocated to the cluster, and then the adjacent points are used as new processing points and are processed by the same process of a clustering window;
after all detection points are processed, clusters with selected points are identified and noise points are eliminated.
8. The radar-based target adaptive clustering method of claim 1, wherein predicting the target profile comprises:
pre-classifying the targets that may be detected into pedestrians, riders, and vehicles through a vector machine and machine learning; predefining the contour size of each target type;
determining the initial position and the motion direction of the point cloud cluster according to the average coordinates and the average speed of all detection points of the current frame belonging to the same point cloud cluster; meanwhile, storing the maximum and minimum speeds for a cluster window of the next frame, namely, the upper and lower points of the speed dimension in the cluster;
the contour is determined based on the size of the point cloud cluster around the estimated position of the point cloud cluster of the current frame.
9. The radar-based target adaptive clustering method of claim 1, wherein the adaptive clustering comprises:
determining a cluster window size according to the predefined target classification and the predicted target profile;
the cluster window is defined by the predicted target profile in the distance or angle dimension and the maximum and minimum speeds from the last cycle in the speed dimension.
10. The radar-based target adaptive clustering method of claim 1, wherein the four-dimensional grid of radar detection data includes a radial distance dimension, a horizontal angle dimension, a pitch angle dimension, and a radial velocity dimension.
11. A radar-based target adaptive clustering device, comprising:
four-dimensional grid creation unit: acquiring Lei Dadian cloud data and creating a four-dimensional grid of radar detection data;
point cloud index correspondence unit: corresponding each detection point of the radar point cloud data to a four-dimensional grid, and recording index information of each detection point in the grid;
three-dimensional cluster window creation unit: creating at least one three-dimensional clustering window based on grids, wherein detection points with similar speeds and similar distances are located in the window;
noise point filtering unit: setting a threshold value of the number of adjacent points of the window, judging whether the processing points are noise points, and filtering the noise points;
and (3) an adaptive clustering unit: and determining a target contour according to preset information, carrying out self-adaptive clustering on the detection points if the target contour can be obtained, and otherwise, carrying out fixed parameter clustering.
12. A radar-based target adaptive clustering device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed, implements the radar-based target adaptive clustering method of any one of claims 1-10.
13. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein instructions, which when run on a terminal device, cause the terminal device to perform the radar-based target adaptive clustering method according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310323644.3A CN116432060A (en) | 2023-03-30 | 2023-03-30 | Target self-adaptive clustering method, device, equipment and storage medium based on radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310323644.3A CN116432060A (en) | 2023-03-30 | 2023-03-30 | Target self-adaptive clustering method, device, equipment and storage medium based on radar |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116432060A true CN116432060A (en) | 2023-07-14 |
Family
ID=87093711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310323644.3A Pending CN116432060A (en) | 2023-03-30 | 2023-03-30 | Target self-adaptive clustering method, device, equipment and storage medium based on radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116432060A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116816208A (en) * | 2023-08-30 | 2023-09-29 | 同致电子科技（厦门）有限公司 | Vehicle door radar static obstacle recognition enhancement method |
| CN117274651A (en) * | 2023-11-17 | 2023-12-22 | 北京亮道智能汽车技术有限公司 | Object detection method and device based on point cloud and computer readable storage medium |
-
2023
- 2023-03-30 CN CN202310323644.3A patent/CN116432060A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116816208A (en) * | 2023-08-30 | 2023-09-29 | 同致电子科技（厦门）有限公司 | Vehicle door radar static obstacle recognition enhancement method |
| CN116816208B (en) * | 2023-08-30 | 2023-12-22 | 同致电子科技（厦门）有限公司 | Vehicle door radar static obstacle recognition enhancement method |
| CN117274651A (en) * | 2023-11-17 | 2023-12-22 | 北京亮道智能汽车技术有限公司 | Object detection method and device based on point cloud and computer readable storage medium |
| CN117274651B (en) * | 2023-11-17 | 2024-02-09 | 北京亮道智能汽车技术有限公司 | Object detection method and device based on point cloud and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022166400A1 (en) | Method, apparatus and device for processing three-dimensional point cloud, and storage medium | |
| US10885352B2 (en) | Method, apparatus, and device for determining lane line on road | |
| CN116432060A (en) | Target self-adaptive clustering method, device, equipment and storage medium based on radar | |
| CN108229419B (en) | Method and apparatus for clustering images | |
| US10984266B2 (en) | Vehicle lamp detection methods and apparatuses, methods and apparatuses for implementing intelligent driving, media and devices | |
| JP2021523443A (en) | Association of lidar data and image data | |
| EP3893201A1 (en) | Methods and systems for data visualization | |
| CN111209978B (en) | Three-dimensional visual repositioning method and device, computing equipment and storage medium | |
| CN114137509B (en) | Millimeter wave Lei Dadian cloud clustering method and device | |
| CN108470174B (en) | Obstacle segmentation method and device, computer equipment and readable medium | |
| KR102217020B1 (en) | Object detection device in very high-resolution aerial images baseo om single-stage digh-density pyramid feature network | |
| CN113256712A (en) | Positioning method, positioning device, electronic equipment and storage medium | |
| CN110390706B (en) | Object detection method and device | |
| CN111950543A (en) | Target detection method and device | |
| CN110910445B (en) | Object size detection method, device, detection equipment and storage medium | |
| CN113011317A (en) | Three-dimensional target detection method and detection device | |
| CN115100099A (en) | Point cloud data processing method, device, equipment and medium | |
| CN110517354B (en) | Method, device, system and medium for three-dimensional point cloud segmentation | |
| CN114495041A (en) | Method, device, equipment and medium for measuring distance between vehicle and target object | |
| WO2024007972A1 (en) | Object association method, computer device, computer readable storage medium, and vehicle | |
| CN116523970B (en) | Dynamic three-dimensional target tracking method and device based on secondary implicit matching | |
| CN112115810A (en) | Target identification method, system, computer equipment and storage medium based on information fusion | |
| CN116563802A (en) | Tunnel scene judging method, device, equipment and storage medium | |
| CN114882046A (en) | Panoramic segmentation method, device, equipment and medium for three-dimensional point cloud data | |
| CN110634155A (en) | Target detection method and device based on deep learning |
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 |