CN112654883B - Radar target clustering method and device - Google Patents
Radar target clustering method and device Download PDFInfo
- Publication number
- CN112654883B CN112654883B CN202080004808.0A CN202080004808A CN112654883B CN 112654883 B CN112654883 B CN 112654883B CN 202080004808 A CN202080004808 A CN 202080004808A CN 112654883 B CN112654883 B CN 112654883B
- Authority
- CN
- China
- Prior art keywords
- sample
- radar
- coordinate information
- coordinate
- coordinate axis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
A radar target clustering method and device relate to the field of automatic driving. The method comprises the following steps: acquiring first coordinate information of a plurality of radar samples on a first coordinate axis and second coordinate information of a second coordinate axis (101); for a first sample of the plurality of radar samples, determining a plurality of regions (102) within a predetermined cluster radius R centered on the first sample; calculating a similarity (103) of the first sample with each of the plurality of regions from the first and second coordinate information of the first sample and the first and second coordinate information of the radar sample in each of the plurality of regions on the first axis and the second coordinate information on the second axis; and determining the area with the maximum similarity as a target area according to the similarity of the first sample and each area in the plurality of areas, and determining the cluster (104) to which the first sample belongs according to the cluster information of the radar samples in the target area. The method effectively improves the accuracy and robustness of target clustering.
Description
Technical Field
The application relates to the field of automatic driving, in particular to a radar target clustering method and device.
Background
An Advanced Driving Assistance System (ADAS) performs data acquisition, analysis and related processing on the surrounding environment through a vehicle-mounted sensor, so that the detection and tracking of target objects around a vehicle are realized, the possibility of danger of the vehicle in the automatic driving process is greatly reduced, and the safety of traffic travel is improved. Thus, the in-vehicle sensor needs to be able to monitor the environment around the driven vehicle in real time, and can exhibit a robust adaptive detection effect when the environment changes. Meanwhile, the complex and variable road conditions also provide strict requirements for the detection precision of the vehicle-mounted sensor. Therefore, it is a difficult point to realize real-time high-precision detection of a monitoring target in a dynamic environment. The millimeter wave radar is one of the commonly used vehicle-mounted radars, and can effectively meet the requirements in the automatic driving process. Millimeter wave radar has been paid great attention to because of its long detection distance, high measurement accuracy and strong penetration ability. The method is an indispensable key technology for automatic driving in the future. Meanwhile, due to the high resolution of the millimeter wave radar and the high complexity of the traffic road condition environment, the scattering characteristics of the detected target present complex diversity. The number of scattering points of a single target is usually not unique, and when the number of scattering points of a target is large, tracking all the scattering points greatly increases the processing complexity of the system, especially in a multi-target environment. Therefore, the method for tracking all scattering points is not practical to be applied in a real scene. Therefore, it is important to study the statistical properties of the scattering points of the target.
Clustering (clustering) analysis, as a widely used data information analysis method, can extract the statistical characteristics of objects and distinguish the classes of the objects. Therefore, under the condition of multi-target multi-scattering points, clustering all the scattering points can extract the characteristic information of the scattering points corresponding to each detection target under the condition of distinguishing different detection targets, so as to realize the positioning and tracking of the multi-target under the complex environment. In the millimeter wave radar target tracking process, the realization of clustering analysis on different target scattering points is very important, so that the problem how to improve the accuracy and robustness of a clustering algorithm becomes the problem to be solved at present.
Disclosure of Invention
The application provides a radar target clustering method and device, which effectively improve the accuracy and robustness of target clustering.
In a first aspect, a radar target clustering method is provided. The method comprises the following steps: firstly, acquiring first coordinate information of a plurality of radar samples on a first coordinate axis and second coordinate information of a plurality of radar samples on a second coordinate axis, wherein the first coordinate axis is perpendicular to the second coordinate axis; secondly, determining a plurality of areas within a preset clustering radius R range by taking a first sample as a center on a plane defined by a first coordinate axis and a second coordinate axis for the first sample in the plurality of radar samples; the shape of the region is not limited herein, and for example, the shape of the region may be: the first sample can be any one of a plurality of radar samples, and the second sample of the plurality of radar samples can be selected to execute the following steps because the plurality of radar samples need to be traversed; then, calculating the similarity of the first sample and each of the plurality of areas according to the first coordinate information and the second coordinate information of the radar sample in each of the plurality of areas on the first coordinate axis and the second coordinate information of the radar sample in the first coordinate axis, wherein the similarity is used for representing the similarity of the first sample and the radar sample in each of the plurality of areas; and finally, according to the similarity between the first sample and each of the multiple regions, determining the region with the maximum similarity as a target region, and according to cluster information of radar samples in the target region, determining a cluster to which the first sample belongs, wherein the cluster information is used for identifying the cluster to which the radar sample belongs. In the scheme, a radar target clustering process uses a new ant colony clustering Algorithm (ACC) algorithm, a first sample is determined in a plurality of radar samples, and a plurality of regions are determined in a range of a preset clustering radius R on a plane defined by a first coordinate axis and a second coordinate axis by taking the first sample as a center, so as to provide reference for clustering of the first sample; based on the plurality of regions, a clustering criterion of the first sample is calculated and established through the similarity between the first sample and each region, and the similarity represents the similarity between the first sample and the radar sample in each region, so that the cluster to which the first sample belongs is determined according to the cluster information of the radar sample in the target region with the maximum similarity, the first sample can be more quickly close to the center of one region, and the convergence speed of the algorithm is improved; the scheme has no requirement on the number of clusters, the parameters are simple and only relate to the preset clustering radius R, the parameter input is minimized, and the accuracy and the robustness of target clustering are effectively improved.
In a possible implementation manner, after the target area with the largest similarity is determined, the first sample needs to be moved to the target area, and in this example, a specific manner of moving the first sample to the target area is provided, the first coordinate information of the first sample is updated to the mean value of the first coordinate information of the radar samples in the target area, and the second coordinate information of the first sample is updated to the mean value of the second coordinate information of the radar samples in the target area.
In one possible implementation, the similarity of the regions is a parameter indicating a degree of similarity (or correlation) of the first sample with the radar samples in any one of the plurality of regions. The similarity can be characterized by the similarity of the distance, speed, acceleration, angle and other parameters between the radar samples. For example, if the average euclidean distance between the first sample and the radar sample in a region is small, the first sample is said to have a high similarity with the radar sample in the region, and can be classified as a class after clustering. The embodiment based on this application provides a way to calculate similarity: determining Euclidean distances between the first sample and the radar samples in each of the plurality of areas according to the first coordinate information and the second coordinate information of the first sample and the radar samples in each of the plurality of areas; and calculating the similarity of the first sample and each of the plurality of regions according to the Euclidean distance. Another way of calculating the similarity is provided, the similarity is calculated according to the following formula,
wherein the content of the first and second substances,
is the similarity of the first sample to each of the plurality of regions, XKFirst coordinate information of radar samples K in the region on a first coordinate axis, YKSecond coordinate information, X, of the radar samples K in the region on a second coordinate axisOIs first coordinate information, Y, of the first sample in a first coordinate axisOIs second coordinate information of the first sample in a second coordinate axis, LiIs a sample set of regions. Yet another way of calculating the similarity is provided, the similarity is calculated according to the following formula,
wherein the content of the first and second substances,
is the similarity of the first sample to each of the plurality of regions, XKFirst coordinate information of radar samples K in the region on a first coordinate axis, YKSecond coordinate information, X, of the radar samples K in the region on a second coordinate axisOIs first coordinate information of the first sample in a first coordinate axis, YOIs second coordinate information of the first sample in a second coordinate axis, LiIs a sample set of regions.
In one possible implementation, since the cluster information is used to identify the cluster to which the radar sample belongs, one example is that the cluster information includes a cluster number. In one example, a way to determine a cluster to which a first sample belongs is provided: updating the cluster number of the first sample to the cluster number of the radar sample closest to the first sample in the target area; in another example, a way to determine a cluster to which a first sample belongs is provided: and updating the cluster number of the first sample to the cluster number with the most cluster numbers used by the radar samples in the target area. In this possible implementation the clustering of the first samples is achieved by updating the cluster number of the first samples.
In a possible implementation manner, since the radar samples are generally samples obtained from samples captured from an object in a three-dimensional space, in the above scheme, a plane formed by a first sample on a first coordinate axis and a second coordinate axis has been clustered, and a third coordinate axis perpendicular to the first coordinate axis and the second coordinate axis needs to be clustered, the method further includes: and updating third coordinate information of the first sample on a third coordinate axis to be an average value of the radar sample in the target area on the third coordinate information of the third coordinate axis, wherein the third coordinate axis is perpendicular to the first coordinate axis, and the third coordinate axis is perpendicular to the second coordinate axis. This enables clustering of radar samples in three-dimensional space.
In a second aspect, a radar target clustering device is provided for implementing the above various methods. The radar target clustering device comprises modules, units or means (means) corresponding to the implementation of the method, and the modules, units or means can be implemented by hardware, software or hardware to execute corresponding software. The hardware or software includes one or more modules or units corresponding to the above functions.
In a third aspect, a radar target clustering device is provided, including: a processor and a memory; the memory is configured to store computer instructions that, when executed by the processor, cause the communication device to perform the method of any of the above aspects. The radar clustering means may be a radar.
In a fourth aspect, a radar target clustering apparatus is provided, including: a processor; the processor is configured to be coupled to the memory, and after reading the instructions in the memory, perform the method according to any one of the above aspects. The radar clustering means may be a radar.
In a fifth aspect, there is provided a computer readable storage medium having stored therein instructions which, when run on a computer, cause the computer to perform the method of any of the above aspects.
In a sixth aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any of the above aspects.
In a seventh aspect, a radar target clustering device (for example, the radar target clustering device may be a chip or a chip system) is provided, and the radar target clustering device includes a processor configured to implement the functions recited in any one of the above aspects. In one possible design, the radar target clustering device further includes a memory for storing necessary program instructions and data. When the radar target clustering device is a chip system, the radar target clustering device can be formed by a chip, and can also comprise a chip and other discrete devices. The radar clustering means may be a radar.
For technical effects brought by any one of the design manners in the second aspect to the seventh aspect, reference may be made to the technical effects brought by different design manners in the first aspect, and details are not described here.
Drawings
Fig. 1 is a schematic structural diagram of a vehicle-mounted terminal according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a radar target clustering method according to an embodiment of the present application;
FIG. 3 is a schematic view of a driving road scene provided in an embodiment of the present application;
FIG. 4 is a first schematic view of a region according to an embodiment of the present disclosure;
FIG. 5 is a second schematic view of a region according to an embodiment of the present disclosure;
FIG. 6 is a third schematic view of a region according to an embodiment of the present disclosure;
FIG. 7 is a fourth schematic view of a region according to an embodiment of the present disclosure;
FIG. 8 is a sample illustration of a radar provided by an embodiment of the present application for the travel road scenario shown in FIG. 3;
FIG. 9 provides clustering results for radar samples in the driving road scene shown in FIG. 8 using Dbscan for embodiments of the present application;
FIG. 10 is a clustering result of radar samples in the driving road scene shown in FIG. 8 using the radar target clustering method provided by the embodiment of the present application;
fig. 11 is a schematic structural diagram of a radar target clustering device according to an embodiment of the present application.
Detailed Description
The technical terms used in the embodiments of the present application are first described as follows:
the K-means, K-means clustering algorithm (K-means clustering algorithm) is an iterative solution clustering analysis algorithm, and comprises the steps of dividing data into K groups in advance, randomly selecting K objects as initial clustering centers, calculating the distance between each object and each seed clustering center, and allocating each object to the nearest clustering center. The cluster centers and the objects assigned to them represent a cluster. The cluster center of a cluster is recalculated for each sample assigned based on the objects existing in the cluster. This process will be repeated until some termination condition is met. The termination condition may be that no (or minimum number) objects are reassigned to different clusters, no (or minimum number) cluster centers are changed again, and the sum of squared errors is locally minimal.
The Dbscan, a noise-based density clustering method with noise, is a density-based clustering method, and divides a current sample point and other sample points according to a connection relation by defining three relations of density direct, density reachable and density connection, so as to realize the final clustering of the sample points. When the Dbscan algorithm is executed, a neighborhood distance threshold value X is required to be given, and therefore the neighborhood S is defined as a subset formed by all points in the sample set, wherein the distance between the points and the current sample point is not more than X. Meanwhile, a sample number threshold value M in the neighborhood is given. When the number of other sample points in the neighborhood S of the sample point is not less than M, the point is marked as a core object. All core objects in the sample set are first computed and labeled. Then, any core object in the sample set is selected as a starting point, and then sample points having a density reachable relation with the starting point are found as a set, wherein all the points in the set have the same category relation. All core objects are traversed in this manner until the end.
ACO, the rationale for ant colony optimization, is: and (3) representing a feasible solution of the problem to be optimized by using the walking paths of the ants, wherein all paths of the whole ant group form a solution space of the problem to be optimized. The shorter ants release a larger amount of pheromone, and as time advances, the concentration of pheromone accumulated on the shorter paths gradually increases, and the number of ants selecting the paths also increases. Finally, the whole ant can be concentrated on the optimal path under the action of positive feedback, and the corresponding optimal solution of the problem to be optimized is obtained. Ant Colony Clustering (ACC) is a method for clustering based on current data density. The process of finding food and carrying corpses by ants can be regarded as an intelligent autonomous clustering process, and each ant autonomously approaches to the place with the largest number of ants according to the intensity of pheromones to finally form clusters. The traditional ant colony clustering algorithm places all sample points in a two-dimensional grid, places a plurality of ants in the two-dimensional grid, and clusters all the sample points by utilizing the continuous movement of the ants in the two-dimensional grid.
In the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of the singular or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple. In addition, the embodiments of the present application use the words "first", "second", etc. to distinguish objects with similar names or functions or actions, and those skilled in the art will understand that the words "first", "second", etc. do not limit the quantity and execution order.
The embodiment of the application can be applied to terminal equipment, and the terminal equipment can be equipment for realizing a wireless communication function, such as a terminal or a chip which can be used in the terminal. Which may be a User Equipment (UE), a Mobile Station (MS), a Mobile Terminal (MT), etc., is a device that provides voice and/or data connectivity to a user. For example, the terminal device includes a handheld device, an in-vehicle device, and the like having a wireless connection function. Currently, the terminal device may be: a mobile phone (mobile phone), a tablet computer, a notebook computer, a palm top computer, a Mobile Internet Device (MID), a wearable device, a Virtual Reality (VR) device, an Augmented Reality (AR) device, a wireless terminal in industrial control (industrial control), a wireless terminal in self driving (self driving), a wireless terminal in remote surgery (remote medical supply), a wireless terminal in smart grid (smart grid), a wireless terminal in transportation safety (smart security), a wireless terminal in city (smart city), a wireless terminal in smart home (smart home), and the like. The method can be particularly applied to terminal equipment needing to implement target identification, such as an Advanced Driving Assistance System (ADAS) vehicle-mounted terminal or radar.
Optionally, as shown in fig. 1, a schematic structural diagram of the vehicle-mounted terminal 01 provided in the embodiment of the present application is provided, and the radar target clustering device provided in the embodiment of the present application may be the vehicle-mounted terminal 01 itself or a chip integrated in the vehicle-mounted terminal 01.
The vehicle-mounted terminal 01 includes at least one processor (exemplarily illustrated in fig. 1 by including one processor 101) and at least one transceiver (exemplarily illustrated in fig. 1 by including one transceiver 103). Optionally, the in-vehicle terminal 01 may further include at least one memory (exemplarily illustrated in fig. 1 by including one memory 102), at least one output device (exemplarily illustrated in fig. 1 by including one output device 104), and at least one input device (exemplarily illustrated in fig. 1 by including one input device 105).
The processor 101, memory 102 and transceiver 103 are connected by a communication line. The communication link may include a path for transmitting information between the aforementioned components.
The processor 101 may be a general-purpose Central Processing Unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more ics for controlling the execution of programs in accordance with the present disclosure. In a specific implementation, the processor 101 may also include a plurality of CPUs, and the processor 101 may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor, as an embodiment. A processor herein may refer to one or more devices, circuits, or processing cores that process data (e.g., computer program instructions).
The memory 102 may be a device having a storage function. Such as, but not limited to, read-only memory (ROM) or other types of static memory devices that may store static information and instructions, Random Access Memory (RAM) or other types of dynamic memory devices that may store information and instructions, electrically erasable programmable read-only memory (EEPROM), compact disk read-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory 102 may be separate and coupled to the processor 101 via a communication link. The memory 102 may also be integrated with the processor 101.
The memory 102 is used for storing computer-executable instructions for executing the present application, and is controlled by the processor 101 to execute. Specifically, the processor 101 is configured to execute computer-executable instructions stored in the memory 102, so as to implement the target clustering method described in the embodiment of the present application.
Alternatively, in this embodiment of the application, the processor 101 may also perform a function related to processing in the target clustering method provided in the following embodiments of the application, and the transceiver 103 is responsible for communicating with other devices or a communication network, which is not specifically limited in this embodiment of the application.
Optionally, the computer execution instruction in the embodiment of the present application may also be referred to as an application program code or a computer program code, which is not specifically limited in the embodiment of the present application.
The transceiver 103 may use any transceiver or other device for communicating with other devices or communication networks, such as ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), or the like. The transceiver 103 includes a transmitter (Tx) and a receiver (Rx).
The output device 104 is in communication with the processor 101 and may display information in a variety of ways. For example, the output device 104 may be a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display device, a Cathode Ray Tube (CRT) display device, a projector (projector), or the like.
The input device 105 is in communication with the processor 101 and can accept user input in a variety of ways. For example, the input device 105 may be a mouse, a keyboard, a touch screen device, or a sensing device, among others. In addition, the input device may include a radar sensor as used in embodiments of the present application, wherein the radar sensor may collect information about objects (e.g., people, animals, vehicles, etc.) in the road space to obtain radar samples.
It is to be understood that the configuration shown in fig. 1 does not constitute a specific limitation to the in-vehicle terminal 01. For example, in other embodiments of the present application, the in-vehicle terminal 01 may include more or less components than those shown, or combine some components, or split some components, or arrange different components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The following will explain the object clustering method provided by the embodiment of the present application with reference to the in-vehicle terminal 01 shown in fig. 1. It should be noted that, in the following embodiments of the present application, names of messages between network elements or names of parameters in messages are only an example, and other names may also be used in a specific implementation, which is not specifically limited in this embodiment of the present application.
In the radar target clustering method, after a radar echo signal of a target (e.g., a vehicle or a person) is subjected to signal processing (ranging, speed measuring, angle measuring, and the like), a plurality of scattering points and/or reflecting points (a large number of scattering points and/or reflecting points form a point cloud) of the target in a three-dimensional space are obtained, and thus one target corresponds to the plurality of scattering points and/or reflecting points. A scattering point and/or a reflection point of a target in the present invention is also referred to as a first sample, a target point or a radar sample.
Referring to fig. 2, a radar target clustering method is provided, which includes the following steps:
101. first coordinate information of the multiple radar samples on a first coordinate axis and second coordinate information of a second coordinate axis are obtained, wherein the first coordinate axis is perpendicular to the second coordinate axis.
In this step, referring to fig. 3, when the method is applied to a driving road scene, the terminal device may sample people and vehicles in the driving road scene shown in fig. 3 through the radar sensor, and generate a radar sample. The radar samples may be recorded as a run of sample points, and each sample point may be, for example, first coordinate information on a first coordinate axis X, second coordinate information on a second coordinate axis Y, and third coordinate information on a third coordinate axis Z having three spatial coordinates, wherein X, Y, Z form a three-dimensional spatial coordinate system, and two of the three coordinate systems are perpendicular to each other, because the radar samples are collected in a three-dimensional space. In step 101, since only the coordinate information of X, Y two-axis coordinates is used, the three-dimensional radar sample can be divided into two parts, one part stores XY coordinate information { X, Y } and the other part stores Z coordinate information { Z }. Of course, the scheme is mainly described by taking a driving road scene as an example, so the terminal device is mainly described by taking a vehicle-mounted terminal as an example. Of course, when the method is applied to a virtual reality scene, for example, a home VR game scene, for example, when object identification clustering needs to be performed on articles in a home, the scheme provided by the embodiment of the application may also be used in VR devices.
102. For a first sample in the radar samples, a plurality of areas within a predetermined clustering radius R range are determined on a plane defined by the first coordinate axis and the second coordinate axis with the first sample as the center.
In step 102, the distances between the other samples in the coordinate system and the first sample O are calculated using the coordinate information { X, Y } of the first sample O as a center. For other samples, the neighborhood of the first sample 0 in the range of the radius R can be determined by using the set predetermined clustering radius R, and then a plurality of regions can be determined in the range of the predetermined clustering radius R by using a similar two-dimensional coordinate plane quadrant division mode. Referring specifically to FIG. 4, four square regions can be defined within a neighborhood of radius R, each region being R/(2^ (1/2)) in length and width. As shown in fig. 4, a plurality of regions (1-4) are determined in the coordinate system, the regions 1-4 all belonging within the neighbourhood of the first sample O. The shape of the region in FIG. 4 is described above by taking a square with a side length of R/(2^ (1/2)) as an example. Furthermore, the shape of the region may also be: circular, fan-shaped, or polygonal. As shown in fig. 5, the neighborhood of the first sample O may also be directly divided into four sectorial regions (1-4), although more sectorial regions are also possible. For another example, referring to fig. 6, more regions may be determined in the neighborhood of the first sample O, such as regions (1-9) in the form of a squared figure as shown in fig. 6. Or as shown in fig. 7, circular areas (1-4) are determined in the neighborhood of the first sample O, and so on.
Further, it should be noted that: for the predetermined cluster radius R, the predetermined cluster radius R is set before clustering starts. The value of R is obtained according to the required clustering resolution and/or the spacing distance between each target object in the actual road scene. For example, for a scene with small target interval and pedestrians/bicycles, R is set to be 0.6-0.8 m; for a scenario where the target separation is large, and the primary detection target is a vehicle, R is set to about 1.5 meters. When the point cloud detection characteristics are not ideal resulting in a lack of density between multiple points of a single target, R may be further lengthened. In addition, the first sample O may be any one of the radar samples, and since the multiple radar samples need to be traversed, any one of the multiple radar samples may be selected as the second sample at the next time, and the following steps may be performed.
103. And calculating the similarity of the first sample and each of the plurality of areas according to the first coordinate information and the second coordinate information of the first sample and the radar sample in each of the plurality of areas on the first coordinate axis and the second coordinate information of the radar sample in each of the plurality of areas on the second coordinate axis.
Wherein, step 103 specifically comprises: determining Euclidean distances between the first sample and the radar sample in each of the plurality of areas according to the first coordinate information of the first sample and the second coordinate information of the radar sample in each of the plurality of areas on the first coordinate axis and the second coordinate information of the radar sample in the second coordinate axis; the similarity of the first sample to each of the plurality of regions is calculated based on the euclidean distance. Wherein the similarity is a parameter indicating the degree of similarity (or correlation) of the first sample O with radar samples in one of the areas 1-4 (taking fig. 4 as an example). The similarity may be characterized by the similarity of parameters such as distance, velocity, acceleration, angle, etc. between samples. For example, if the average euclidean distance between the first sample and the radar sample of an area is small, the first sample is said to have a high similarity with the radar sample of the area, and can be classified into one class after clustering.
Two specific methods for calculating the similarity are provided below, method one: the similarity is calculated according to the following formula.
The second method comprises the following steps: the similarity is calculated according to the following formula.
104. And determining the area with the maximum similarity as a target area according to the similarity between the first sample and each of the plurality of areas, and determining the cluster to which the first sample belongs according to the cluster information of the radar samples in the target area.
Furthermore, before step 104, the first sample needs to be moved into the target region with the greatest similarity. The method specifically comprises the following steps: and updating the first coordinate information of the first sample to be the mean value of the first coordinate information of the radar samples in the target area, and updating the second coordinate information of the first sample to be the mean value of the second coordinate information of the radar samples in the target area. For the current first sample O, comparing the similarity sizes corresponding to all the areas (such as areas 1-4 in FIG. 4), moving the first sample to the target area with the maximum similarity, and taking the mean value of the coordinate information of all the radar samples in the target area as the new coordinate information of the first sample O. Specifically, according to the similarity corresponding to the four regions obtained by calculation, when the maximum value is not 0, moving the first sample O to the region with the maximum similarity, and taking the mean value of the coordinate information of all radar samples in the region as the new coordinate information of the first sample O; and when the maximum value of the similarity is 0, it represents that the current first sample O is an independent noise point, and the first sample O is not moved.
Further, in step 104, the cluster information indicates information that the radar sample in the target area has indicating which cluster it belongs to, for example, the cluster information may be a cluster number. In this way, the cluster number can indicate the number of the cluster (cluster) to which each radar sample belongs after clustering the radar samples. The cluster number to which each radar sample belongs in each iteration may vary depending on the clustering result for the first sample. Specifically, according to the movement characteristic of the first sample O, when the first sample O is not an independent noise point, if the first sample O has no cluster number, the cluster number of the first sample O is updated to the cluster number of the radar sample closest to the first sample in the target area, that is, the cluster number of the radar sample C closest to the first sample O is assigned to the first sample O; or if the radar sample C closest to the first sample O has no cluster number, the cluster number of the first sample O is updated to the cluster number with the largest cluster number used by the radar sample in the target area, that is, the cluster number with the largest occurrence number in the target area is assigned to the first sample O.
In addition, for the case that the first sample O is an independent noise point, skipping the cluster number updating stage, and iterating the samples of other independent non-noise points which are not updated in the loop; and for the condition that the first sample is the dependent noise point, after moving and updating the cluster number, the iterative sample replacement is consistent with the dependent noise point condition.
And after all the radar samples are subjected to iteration updating, judging whether the iteration reaches a convergence condition, if so, ending the loop, and otherwise, continuing to perform the next iteration. The steps of determining the convergence condition are specifically: and after each iteration, calculating the sum S of the distances between the first sample O in each cluster and all other radar samples in the cluster, and judging that the clustering is finished when the calculation result S is less than a preset threshold. Generally, when the number of iterations is about 3, the clustering process of the sample data can be converged. And after the iteration is stopped, regarding the radar samples with the same cluster number as the radar samples of the same cluster, thereby finishing the clustering of each radar sample.
Finally, the third coordinate information of the first sample O on the third coordinate axis (Z axis) is updated in the following manner: and updating the third coordinate information of the first sample O on the third coordinate axis to be the mean value of the radar samples in the target area on the third coordinate information of the third coordinate axis.
In the scheme, a radar target clustering process uses a new ant colony clustering algorithm ACC algorithm, a first sample is determined in a plurality of radar samples, and a plurality of areas are determined in a range of a preset clustering radius R on a plane defined by a first coordinate axis and a second coordinate axis by taking the first sample as a center, so as to provide reference for clustering of the first sample; based on the plurality of regions, a clustering criterion of the first sample is calculated and established through the similarity between the first sample and each region, and the similarity represents the similarity between the first sample and the radar sample in each region, so that the cluster to which the first sample belongs is determined according to the cluster information of the radar sample in the target region with the maximum similarity, the first sample can be more quickly close to the center of one region, and the convergence speed of the algorithm is improved; the scheme has no requirement on the number of clusters, the parameters are simple and only relate to the preset clustering radius R, the parameter input is minimized, and the accuracy and the robustness of the target clustering method are effectively improved.
The specific effect of the target clustering algorithm provided by the embodiment of the present application is explained with reference to fig. 8, where fig. 8 provides a radar sample illustration for the traveling road scene illustrated in fig. 3, where the units of the X-axis and the Y-axis are m, and each point represents a scattering point and/or a reflection point of a target, the speed velocity (m/s) of the radar sample is also illustrated in fig. 8, where fig. 9 provides a clustering result of the radar sample in the traveling road scene illustrated in fig. 8 by using Dbscan, fig. 10 provides a clustering result of the radar sample in the traveling road scene illustrated in fig. 8 by the scheme provided by the embodiment of the present application, where one point in fig. 9 and 10 represents one target (e.g. a vehicle or a person) in fig. 3, and fig. 9 and 10 clearly show that the clustering result of Dbscan in a circle is classified as one radar sample, the clustering result of the method is classified by two samples, so that the clustering result of the graph 10 is consistent with two pedestrian targets in a circle in the graph 3, and the accuracy of the clustering result is higher; and two pedestrian targets in the circle in fig. 3 are clustered into one target in fig. 9, so that the clustering result is low in accuracy.
In addition, compared with a K-mean algorithm, the scheme provided by the embodiment of the application avoids the limitation caused by the condition that the K cannot be known because the clustering number K does not need to be known in advance. Compared with the traditional ACC, the convergence speed is too low due to the pointless ant colony clustering movement, the movement criterion of the first sample is set in the method, so that the first sample can be more quickly close to the center of the area, and the convergence speed of the algorithm is improved. Compared with a Dbscan algorithm, the method has the advantages that due to the fact that double-parameter X, M joint deployment is needed in an actual scene, the method is high in algorithm complexity and poor in clustering performance, and only one parameter R is adopted, so that the algorithm complexity is reduced, the clustering performance is improved, and the robustness of the algorithm is effectively guaranteed.
It is to be understood that, in the above embodiments, the method and/or the steps implemented by the vehicle-mounted terminal may also be implemented by a component (e.g., a chip or a circuit) that can be used for the vehicle-mounted terminal.
The scheme provided by the embodiment of the application is introduced mainly from the perspective of the method flow implemented by the vehicle-mounted terminal. Correspondingly, the embodiment of the application also provides a radar target clustering device, and the radar target clustering device is used for realizing the various methods. The radar target clustering device can be the vehicle-mounted terminal or the radar; or the radar target clustering device can be a device comprising the vehicle-mounted terminal or the radar, or the radar target clustering device can be a component of the vehicle-mounted terminal or the radar. It is understood that the radar target clustering device comprises hardware structures and/or software modules for executing the functions in order to realize the functions. Those of skill in the art would readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiment of the present application, functional modules of the radar target clustering device may be divided according to the method embodiments, for example, each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.
Referring to fig. 11, the radar target clustering apparatus includes: acquisition unit 1101, processing unit 1102.
The acquiring unit 1101 is configured to acquire first coordinate information of a plurality of radar samples on a first coordinate axis and second coordinate information of a second coordinate axis, where the first coordinate axis is perpendicular to the second coordinate axis; a processing unit 1102, configured to determine, for a first sample of the plurality of radar samples acquired by the acquisition unit 1101, a plurality of regions within a predetermined clustering radius R range on a plane defined by the first coordinate axis and the second coordinate axis with the first sample as a center; the processing unit 1102 is further configured to calculate a similarity between the first sample and each of the plurality of regions according to the first coordinate information and the second coordinate information of the first sample and the first coordinate information of the radar sample in each of the plurality of regions on the first coordinate axis and the second coordinate information of the radar sample in each of the plurality of regions on the second coordinate axis, where the similarity is used to represent the similarity between the first sample and the radar sample in each of the plurality of regions; the processing unit 1102 is further configured to determine, according to a similarity between the first sample and each of the multiple regions, a region with a maximum similarity as a target region, and determine, according to cluster information of the radar samples in the target region, a cluster to which the first sample belongs, where the cluster information is used to identify a cluster to which the radar sample belongs.
Optionally, the processing unit 1102 is further configured to update the first coordinate information of the first sample to a mean value of the first coordinate information of the radar samples in the target area, and update the second coordinate information of the first sample to a mean value of the second coordinate information of the radar samples in the target area.
Optionally, the processing unit 1102 is specifically configured to determine, according to the first coordinate information and the second coordinate information of the first sample and the first coordinate information of the radar sample in each of the multiple regions on the first coordinate axis and the second coordinate information of the radar sample in each of the multiple regions on the second coordinate axis, a euclidean distance between the first sample and the radar sample in each of the multiple regions; calculating a similarity of the first sample to each of the plurality of regions according to the Euclidean distance.
Optionally, the processing unit 1102 is specifically configured to calculate the similarity of the regions according to the following formula,
wherein the content of the first and second substances,
for the similarity of the first sample to each of the plurality of regions, XKFirst coordinate information, Y, of the radar sample K in the area on the first coordinate axisKSecond coordinate information, X, of the radar sample K in the area on the second coordinate axisOIs first coordinate information, Y, of the first sample in the first coordinate axisOSecond coordinate information, L, of the first sample in the second coordinate axisiIs a sample set of the region.
Optionally, the processing unit 1102 is specifically configured to calculate the similarity of the regions according to the following formula,
wherein the content of the first and second substances,
for the first sample and each of the plurality of regionsDegree of similarity, XKFirst coordinate information, Y, of the radar sample K in the area on the first coordinate axisKSecond coordinate information, X, of the radar sample K in the area on a second coordinate axisOFirst coordinate information, Y, of the first sample in the first coordinate axisOSecond coordinate information, L, of the first sample in the second coordinate axisiIs a sample set of the region.
Optionally, the cluster information includes a cluster number, and the processing unit 1102 is specifically configured to update the cluster number of the first sample to the cluster number of the radar sample closest to the first sample in the target area; or updating the cluster number of the first sample to the cluster number with the largest cluster number used by the radar sample in the target area.
Optionally, the processing unit 1102 is further configured to update third coordinate information of the first sample on a third coordinate axis to an average of the third coordinate information of the radar sample in the target area on the third coordinate axis, where the third coordinate axis is perpendicular to the first coordinate axis, and the third coordinate axis is perpendicular to the second coordinate axis.
Optionally, the shape of the region is: fan-shaped, circular or polygonal.
All relevant contents of the steps related to the method embodiment may be referred to the functional description of the corresponding functional module, and are not described herein again.
In this embodiment, the radar target clustering device is presented in a form of dividing each functional module in an integrated manner. A "module" herein may refer to a particular ASIC, a circuit, a processor and memory that execute one or more software or firmware programs, an integrated logic circuit, and/or other device that provides the described functionality. In a simple embodiment, the radar target clustering device may be in the form of a vehicle-mounted terminal or a radar as shown in fig. 1.
For example, the processor 101 in the in-vehicle terminal shown in fig. 1 may execute the instructions by calling a computer stored in the memory 102, so that the in-vehicle terminal executes the method in the above-described method embodiment.
Specifically, the functions/implementation procedures of the acquisition unit 1101 and the processing unit 1102 in fig. 11 may be implemented by the processor 101 in the in-vehicle terminal shown in fig. 1 calling a computer execution instruction stored in the memory 102. Since the radar target clustering device provided in this embodiment can execute the method described above, the technical effects obtained by the radar target clustering device can be obtained by referring to the method described above, and are not described herein again.
Optionally, an embodiment of the present application further provides a radar target clustering device (for example, the radar target clustering device may be a chip or a chip system), where the radar target clustering device includes a processor and an interface, and the processor is configured to read an instruction to execute the method in any one of the above method embodiments. In one possible design, the radar target clustering device further includes a memory. The memory is used for storing necessary program instructions and data, and the processor can call the program codes stored in the memory to instruct the radar target clustering device to execute the method in any method embodiment. Of course, the memory may not be in the computing device. When the radar target clustering device is a chip system, the radar target clustering device may be composed of a chip, and may also include a chip and other discrete devices, which is not specifically limited in this embodiment of the present application.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the application are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or can comprise one or more data storage devices, such as a server, a data center, etc., that can be integrated with the medium. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others. In the embodiment of the present application, the computer may include the aforementioned apparatus.
While the present application has been described in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.
Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the present application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Finally, it should be noted that: the above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (19)
1. A radar target clustering method is characterized by comprising the following steps:
acquiring first coordinate information of a plurality of radar samples on a first coordinate axis and second coordinate information of a second coordinate axis, wherein the first coordinate axis is perpendicular to the second coordinate axis;
determining a plurality of areas within a preset clustering radius R range by taking a first sample as a center on a plane defined by the first coordinate axis and the second coordinate axis for the first sample in the plurality of radar samples; the preset clustering radius R is obtained according to the required clustering resolution and/or the spacing distance between targets, and one target corresponds to a plurality of radar samples;
calculating a similarity of the first sample to each of the plurality of regions according to the first and second coordinate information of the first sample and the first and second coordinate information of the radar sample in each of the plurality of regions on the first coordinate axis, wherein the similarity is used for representing the similarity of the first sample to the radar sample in each of the plurality of regions;
determining the area with the maximum similarity as a target area according to the similarity between the first sample and each of the multiple areas, and determining the cluster to which the first sample belongs according to cluster information of the radar samples in the target area, wherein the cluster information is used for identifying the cluster to which the radar sample belongs.
2. The method according to claim 1, wherein after determining the region with the largest similarity as a target region, further comprising:
updating the first coordinate information of the first sample to be a mean of the first coordinate information of the radar samples in the target area, and updating the second coordinate information of the first sample to be a mean of the second coordinate information of the radar samples in the target area.
3. The method of claim 1 or 2, wherein the calculating the similarity of the first sample to each of the plurality of regions from the first and second coordinate information of the first sample and the first and second coordinate information of the radar sample in each of the plurality of regions in the first coordinate axis comprises:
determining Euclidean distances between the first sample and the radar sample in each of the plurality of areas according to the first coordinate information and the second coordinate information of the radar sample in each of the plurality of areas and the first coordinate information of the radar sample in the first coordinate axis and the second coordinate information of the radar sample in the second coordinate axis;
calculating a similarity of the first sample to each of the plurality of regions according to the Euclidean distance.
4. The method of claim 1 or 2, wherein the calculating the similarity of the first sample to each of the plurality of regions from the first and second coordinate information of the first sample and the first and second coordinate information of the radar sample in each of the plurality of regions in the first coordinate axis comprises:
the similarity of the regions is calculated according to the following formula,
5. The method of claim 1 or 2, wherein the calculating the similarity of the first sample to each of the plurality of regions from the first and second coordinate information of the first sample and the first and second coordinate information of the radar sample in each of the plurality of regions in the first coordinate axis comprises:
the similarity of the regions is calculated according to the following formula,
6. The method according to claim 1 or 2, wherein the cluster information includes a cluster number, and the determining the cluster to which the first sample belongs according to the cluster information of the radar samples in the target area includes:
updating the cluster number of the first sample to the cluster number of the radar sample closest to the first sample in the target area;
or updating the cluster number of the first sample to the cluster number with the largest cluster number used by the radar sample in the target area.
7. The method according to claim 1 or 2, characterized in that the method further comprises:
and updating third coordinate information of the first sample on a third coordinate axis to be an average value of the radar sample in the target area on the third coordinate information of the third coordinate axis, wherein the third coordinate axis is perpendicular to the first coordinate axis, and the third coordinate axis is perpendicular to the second coordinate axis.
8. A method according to claim 1 or 2, wherein the shape of the region is: fan-shaped, circular or polygonal.
9. A radar target clustering apparatus, comprising:
the radar sample acquisition device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring first coordinate information of a plurality of radar samples on a first coordinate axis and second coordinate information of a second coordinate axis, and the first coordinate axis is perpendicular to the second coordinate axis;
the processing unit is used for determining a plurality of areas within a preset clustering radius R range by taking a first sample as a center on a plane defined by the first coordinate axis and the second coordinate axis for the first sample in the plurality of radar samples acquired by the acquisition unit; the preset clustering radius R is obtained according to the required clustering resolution and/or the spacing distance between targets, and one target corresponds to a plurality of radar samples;
the processing unit is further configured to calculate a similarity between the first sample and each of the plurality of regions according to the first coordinate information and the second coordinate information of the first sample and the first coordinate information of the radar sample in each of the plurality of regions on the first coordinate axis and the second coordinate information of the radar sample in each of the plurality of regions on the second coordinate axis, wherein the similarity is used for representing the similarity between the first sample and the radar sample in each of the plurality of regions;
the processing unit is further configured to determine, according to a similarity between the first sample and each of the multiple regions, a region with a maximum similarity as a target region, and determine, according to cluster information of the radar samples in the target region, a cluster to which the first sample belongs, where the cluster information is used to identify the cluster to which the radar sample belongs.
10. The radar target clustering device according to claim 9, wherein the processing unit is further configured to update the first coordinate information of the first sample to a mean of the first coordinate information of the radar samples in the target area, and update the second coordinate information of the first sample to a mean of the second coordinate information of the radar samples in the target area.
11. The radar target clustering device according to claim 9 or 10, wherein the processing unit is specifically configured to determine euclidean distances between the first sample and the radar samples in each of the plurality of regions according to the first coordinate information and the second coordinate information of the first sample and the first coordinate information of the radar samples in each of the plurality of regions on the first coordinate axis and the second coordinate information of the radar samples in the second coordinate axis; calculating a similarity of the first sample to each of the plurality of regions according to the Euclidean distance.
12. The radar target clustering device according to claim 9 or 10, wherein the processing unit is specifically configured to calculate the similarity of the regions according to the following formula,
13. The radar target clustering device according to claim 9 or 10, wherein the processing unit is specifically configured to calculate the similarity of the regions according to the following formula,
14. The radar target clustering device according to claim 9 or 10, wherein the cluster information includes a cluster number, and the processing unit is specifically configured to update the cluster number of the first sample to the cluster number of the radar sample closest to the first sample in the target area; or updating the cluster number of the first sample to the cluster number with the largest cluster number used by the radar sample in the target area.
15. The radar target clustering device according to claim 9 or 10, wherein the processing unit is further configured to update third coordinate information of the first sample on a third coordinate axis to a mean value of the third coordinate information of the radar samples on the third coordinate axis in the target area, the third coordinate axis being perpendicular to the first coordinate axis, and the third coordinate axis being perpendicular to the second coordinate axis.
16. The radar target clustering apparatus according to claim 9 or 10, wherein the shape of the region is: fan-shaped, circular or polygonal.
17. A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1-8.
18. A chip comprising a processor and an interface;
the processor is configured to read instructions to perform the method of any one of claims 1 to 8.
19. A radar, comprising: a processor and a memory;
the memory is to store computer executable instructions that, when executed by the processor, cause the radar to perform the method of any one of claims 1-8.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/081219 WO2021189328A1 (en) | 2020-03-25 | 2020-03-25 | Radar target clustering method and apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112654883A CN112654883A (en) | 2021-04-13 |
| CN112654883B true CN112654883B (en) | 2022-05-31 |
Family
ID=75368450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080004808.0A Active CN112654883B (en) | 2020-03-25 | 2020-03-25 | Radar target clustering method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112654883B (en) |
| WO (1) | WO2021189328A1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2934636A1 (en) * | 2015-07-21 | 2017-01-21 | Airbus Ds Electronics And Border Security Gmbh | Method for increasing the situational awareness and the location detection of obstacles in the presence of aerosol clouds |
| CN109613509A (en) * | 2018-12-30 | 2019-04-12 | 北京润科通用技术有限公司 | A kind of clustering method and device of trailer-mounted radar scattering point |
| CN110231602A (en) * | 2019-06-27 | 2019-09-13 | 中国航空工业集团公司雷华电子技术研究所 | A kind of high-volume sea-surface target point mark extraction algorithm based on two-dimentional multidomain treat-ment |
| CN110824421A (en) * | 2019-11-15 | 2020-02-21 | 广东博智林机器人有限公司 | Position information processing method and device, storage medium and electronic equipment |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9261601B2 (en) * | 2013-06-01 | 2016-02-16 | Savari, Inc. | System and method for lane boundary estimation and host vehicle position and orientation |
| CN103559504B (en) * | 2013-11-04 | 2016-08-31 | 北京京东尚科信息技术有限公司 | Image target category identification method and device |
| CN105224958A (en) * | 2015-10-29 | 2016-01-06 | Tcl集团股份有限公司 | A kind of clustering method and device |
| KR20200098480A (en) * | 2017-09-13 | 2020-08-20 | 벨로다인 라이더, 인크. | Multi-resolution, simultaneous position measurement and mapping based on 3-D LIDAR measurements |
| CN109543704B (en) * | 2017-09-22 | 2021-02-23 | 比亚迪股份有限公司 | Multi-target clustering method and device for automobile and vehicle-mounted radar |
| CN109765557B (en) * | 2018-12-30 | 2021-05-04 | 上海微波技术研究所（中国电子科技集团公司第五十研究所） | FOD target self-adaptive rapid classification identification method, system and medium based on distribution characteristics |
| CN110895333B (en) * | 2019-12-05 | 2022-06-03 | 电子科技大学 | Rapid 77G vehicle-mounted radar data clustering method based on Doppler frequency |
-
2020
- 2020-03-25 CN CN202080004808.0A patent/CN112654883B/en active Active
- 2020-03-25 WO PCT/CN2020/081219 patent/WO2021189328A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2934636A1 (en) * | 2015-07-21 | 2017-01-21 | Airbus Ds Electronics And Border Security Gmbh | Method for increasing the situational awareness and the location detection of obstacles in the presence of aerosol clouds |
| CN109613509A (en) * | 2018-12-30 | 2019-04-12 | 北京润科通用技术有限公司 | A kind of clustering method and device of trailer-mounted radar scattering point |
| CN110231602A (en) * | 2019-06-27 | 2019-09-13 | 中国航空工业集团公司雷华电子技术研究所 | A kind of high-volume sea-surface target point mark extraction algorithm based on two-dimentional multidomain treat-ment |
| CN110824421A (en) * | 2019-11-15 | 2020-02-21 | 广东博智林机器人有限公司 | Position information processing method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112654883A (en) | 2021-04-13 |
| WO2021189328A1 (en) | 2021-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3798974B1 (en) | Method and apparatus for detecting ground point cloud points | |
| US11030803B2 (en) | Method and apparatus for generating raster map | |
| CN112847343B (en) | Dynamic target tracking and positioning method, device, equipment and storage medium | |
| WO2021097618A1 (en) | Point cloud segmentation method and system, and computer storage medium | |
| Huang et al. | Indoor detection and tracking of people using mmwave sensor | |
| US10565721B2 (en) | Information processing device and information processing method for specifying target point of an object | |
| US8983490B2 (en) | Locating a mobile device | |
| CN112526513A (en) | Millimeter wave radar environment map construction method and device based on clustering algorithm | |
| US20150019161A1 (en) | Movement line information generation system, movement line information generation method and movement line information generation program | |
| CN111563450B (en) | Data processing method, device, equipment and storage medium | |
| JP2023508705A (en) | Data transmission method and device | |
| CN110390706B (en) | Object detection method and device | |
| WO2022087916A1 (en) | Positioning method and apparatus, and electronic device and storage medium | |
| CN110470308A (en) | A kind of obstacle avoidance system and method | |
| CN107526058B (en) | Indoor orientation method, apparatus and system | |
| CN114842445A (en) | Target detection method, device, equipment and medium based on multi-path fusion | |
| US20160019248A1 (en) | Methods for processing within-distance queries | |
| CN115393681A (en) | Target fusion method and device, electronic equipment and storage medium | |
| CN113177980B (en) | Target object speed determining method and device for automatic driving and electronic equipment | |
| CN114528941A (en) | Sensor data fusion method and device, electronic equipment and storage medium | |
| CN112418316B (en) | Robot repositioning method and device, laser robot and readable storage medium | |
| CN112654883B (en) | Radar target clustering method and device | |
| CN115507840A (en) | Grid map construction method, grid map construction device and electronic equipment | |
| CN116047558A (en) | Positioning method and device | |
| CN112509384B (en) | Intelligent street lamp-based aircraft control method and intelligent street lamp |
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 |