WO2023040737A1

WO2023040737A1 - Target location determining method and apparatus, electronic device, and storage medium

Info

Publication number: WO2023040737A1
Application number: PCT/CN2022/117770
Authority: WO
Inventors: 关瀛洲; 王祎男; 魏源伯; 刘汉旭
Original assignee: 中国第一汽车股份有限公司
Priority date: 2021-09-17
Filing date: 2022-09-08
Publication date: 2023-03-23
Also published as: CN113838125B; CN113838125A

Abstract

The present application relates to the technical field of automatic driving, and discloses a target location determining method and apparatus, an electronic device, and a storage medium. The method comprises: determining, according to image data of a target object in an environment where a vehicle is located, a target area of the target object; determining candidate point clouds of the target object according to first point cloud data of the target object in the environment where the vehicle is located and the target area; determining a target point cloud from the candidate point clouds according to degrees of matching between the target area and the candidate point clouds; and determining the location of the target object according to the target point cloud.

Description

Target location determination method, device, electronic device and storage medium

This application claims priority to a Chinese patent application with application number 202111093181.3 filed with the China Patent Office on September 17, 2021, the entire contents of which are incorporated herein by reference.

technical field

The embodiments of the present application relate to the technical field of automatic driving, for example, to a method, an apparatus, an electronic device, and a storage medium for determining a target position.

Background technique

Driving safety requires that autonomous driving have extremely high-precision perception capabilities, and the sensor field of view is fully covered, which can effectively perceive dangerous traffic conditions and traffic behaviors. The camera is one of the earliest sensors used in the automatic driving system, and it is also the sensor of choice for various car manufacturers and automotive researchers. However, it is greatly affected by changes in the external environment, such as night, rainfall, and heavy fog, which will greatly affect the camera. Perception effect; lidar uses many denser laser beams to irradiate the object, receives the laser reflected by the object and then obtains the distance information of the object, which has a larger and denser data volume and higher accuracy than the millimeter-wave radar, but for Adaptability to extreme environments is much lower and more expensive, so improvements are urgently needed.

Contents of the invention

The present application provides a method, device, electronic device and storage medium for determining a target position, so as to improve the accuracy of determining the position of target objects around a vehicle.

In the first aspect, the embodiment of the present application provides a method for determining a target position, the method comprising:

Determine the target area of the target object according to the image data of the target object in the scene where the vehicle is located;

determining a candidate point cloud of the target object according to the first point cloud data of the target object in the scene where the vehicle is located and the target area;

determining a target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud;

According to the target point cloud, the position of the target object is determined.

In the second aspect, the embodiment of the present application also provides a device for determining a target position, which includes:

The target area determination module is configured to determine the target area of the target object according to the image data of the target object in the scene where the vehicle is located;

The candidate point cloud determination module is configured to determine the candidate point cloud of the target object according to the first point cloud data of the target object in the scene where the vehicle is located and the target area;

The target point cloud determination module is configured to determine the target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud;

A position determining module, configured to determine the position of the target object according to the target point cloud.

In a third aspect, the embodiment of the present application also provides an electronic device, the electronic device includes:

at least one processor;

a memory configured to store at least one program;

When the at least one program is executed by the at least one processor, the at least one processor is made to implement the method for determining a target position provided in any embodiment of the present application.

In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method for determining a target location as provided in any embodiment of the present application is implemented.

Description of drawings

FIG. 1 is a flow chart of a method for determining a target position provided in Embodiment 1 of the present application;

FIG. 2 is a flow chart of a method for determining a target location provided in Embodiment 2 of the present application;

Fig. 3 is a flow chart of a method for determining a target position provided in Embodiment 3 of the present application

FIG. 4 is a schematic structural diagram of a device for determining a target position provided in Embodiment 4 of the present application;

FIG. 5 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application.

Detailed ways

The application will be described in detail below in conjunction with the accompanying drawings and embodiments.

Embodiment one

Fig. 1 is a flow chart of a method for determining a target position provided in Embodiment 1 of the present application. This embodiment is applicable to the determination of the position of target objects around a vehicle in automatic driving, especially in extreme environments (bad weather conditions or Dark environment), the situation of determining the position of target objects around the vehicle in automatic driving. The method can be executed by a device for determining a target position, which can be implemented in software and/or hardware, and can be integrated into an electronic device carrying a function of determining a target position, such as a vehicle-mounted controller.

As shown in Figure 1, the method may include:

110. Determine the target area of the target object according to the image data of the target object in the scene where the vehicle is located.

Wherein, the target object refers to an object in the scene where the vehicle is located, such as other vehicles. The so-called target area refers to the area where the target object is located in the image data of the scene around the vehicle collected by the image acquisition device. The image collection device may be a camera installed on the vehicle, for example, it may be four groups of cameras, which can collect image data of the front, rear, left, and right directions of the vehicle.

In this embodiment, the image acquisition device acquires the image data of the target object in the scene where the vehicle is located, and then obtains the target area of the target object in the image data based on the target detection model. Wherein, the target detection model may be a YOLO-v3 model.

It should be noted that after the image data of the target object is acquired, the image data may also be corrected based on preset correction parameters. Wherein, the preset correction parameters are set by those skilled in the art according to actual conditions. Exemplarily, target object detection is performed on the corrected image data based on a target detection model to obtain a target area of the target object.

S120. Determine a candidate point cloud of the target object according to the first point cloud data of the target object in the scene where the vehicle is located and the target area.

Wherein, the first point cloud data refers to the point cloud data of the target object in the scene where the vehicle is collected by the millimeter wave radar. It should be noted that four sets of millimeter-wave radars are installed on the vehicle, which can collect point cloud data of target objects in the front, rear, left, and right directions of the vehicle; The point cloud data collected by the wave radar corresponds to a frame of image data collected by the image acquisition device. The so-called candidate point cloud refers to the point cloud data related to the target area.

In this embodiment, the millimeter-wave radar collects the first point cloud data of the target object in the scene where the vehicle is located, and then based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, the first point cloud data is projected onto the image plane coordinate system to obtain the second point cloud data. A candidate point cloud of the target object is determined according to the positional relationship between the second point cloud data and the target area. Exemplarily, the point cloud data falling into the target area in the second point cloud data is used as the candidate point cloud of the target object.

S130. Determine the target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud.

Optionally, the distance between the candidate point cloud and the target area can be used as the matching degree between the target area and the candidate point cloud, and then the target point cloud is determined from the candidate point cloud according to the matching degree.

Among them, the target point cloud refers to the point cloud data that best matches the target area.

Exemplarily, the matching degree may be sorted, and the target point cloud is determined from the candidate point cloud according to the sorting result and a set threshold. For example, the matching degree is sorted from small to large, and the candidate point cloud corresponding to the matching degree greater than the set threshold in the sorting result is used as the target point cloud. Wherein, the set threshold can be set by those skilled in the art according to actual conditions.

S140. Determine the position of the target object according to the target point cloud.

In this embodiment, according to the target point cloud, the basic information of the target object corresponding to the target point cloud collected in the millimeter-wave radar is obtained, wherein the basic information includes information such as the position and speed of the target object. Exemplarily, according to the basic information of the target object, a Kalman filter algorithm is used to determine the position of the target object.

In the technical solution of the embodiment of the present application, the target area of the target object is determined according to the image data of the target object in the scene where the vehicle is located, and then the target object is determined according to the first point cloud data and the target area of the target object in the scene where the vehicle is located Then, according to the matching degree between the target area and the candidate point cloud, the target point cloud is determined from the candidate point cloud, and finally the position of the target object is determined according to the target point cloud. The above technical solution determines the position of the target object in the scene where the vehicle is located through the combination of image data and point cloud data, which improves the accuracy of determining the position of the target object and provides a basis for determining the position of the target object in the surrounding environment of the vehicle in automatic driving. a new way of thinking.

Embodiment two

Fig. 2 is a flow chart of a method for determining a target position provided in Embodiment 2 of the present application. On the basis of the above embodiment, for "according to the first point cloud data of the target object and the target area, determine the candidate point cloud of the target object "Refinement provides an optional implementation.

As shown in Figure 2, the method may include:

S210. Determine the target area of the target object according to the image data of the target object in the scene where the vehicle is located.

S220. Perform three-dimensional transformation on the target area to obtain a point cloud cone.

In this embodiment, based on the three-dimensional transformation model, the target area can be three-dimensionally converted to obtain the point cloud cone corresponding to the target area.

S230. Based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, project the first point cloud data to the image plane coordinate system to obtain second point cloud data.

In this embodiment, clustering is performed on the first point cloud data to obtain clustered point cloud data. Exemplarily, the first point cloud data can be clustered based on the DNSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to obtain clustered point cloud data.

Exemplarily, based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, the clustered point cloud data is projected to the image plane coordinate system to obtain the second point cloud data.

It can be understood that by clustering the first point cloud data, irrelevant point cloud data can be filtered out, so that the determination of the subsequent target position is more accurate.

S240. Determine a candidate point cloud of the target object according to the positional relationship between the second point cloud data and the point cloud cone.

In this embodiment, the point cloud data falling into the point cloud cone in the second point cloud data is used as the candidate point cloud of the target object; the second point cloud data falling outside the point cloud cone is eliminated.

S250. Determine the target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud.

S260. Determine the position of the target object according to the target point cloud.

In the technical solution of the embodiment of the present application, the target area of the target object is determined according to the image data of the target object in the scene where the vehicle is located, and the target area is three-dimensionally converted to obtain a point cloud cone. Based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, the first point cloud data is projected to the image plane coordinate system to obtain the second point cloud data, and then according to the relationship between the second point cloud data and the point cloud cone The positional relationship determines the candidate point cloud of the target object, and then determines the target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud, and finally determines the position of the target object according to the target point cloud. The above technical solution determines the position of the target object in the scene where the vehicle is located through the combination of image data and point cloud data, which improves the accuracy of determining the position of the target object and provides a basis for determining the position of the target object in the surrounding environment of the vehicle in automatic driving. a new way of thinking.

Embodiment Three

Fig. 3 is a flow chart of a method for determining a target position provided in Embodiment 3 of the present application. On the basis of the above-mentioned embodiment, for "according to the matching degree between the target area and the candidate point cloud, determine the target from the candidate point cloud "point cloud" refinement, providing an optional implementation.

As shown in Figure 3, the method may include:

S310. Determine a target area of the target object according to the image data of the target object in the scene where the vehicle is located.

S320. Determine a candidate point cloud of the target object according to the first point cloud data of the target object in the scene where the vehicle is located and the target area.

S330. For each candidate point cloud, determine the matching degree between the candidate point cloud and the target area according to the point cloud coordinates of the candidate point cloud, the basic information of the target area, and the focal length of the acquisition device.

Wherein, the basic information of the target area includes the size information of the target area and the coordinates of the center point of the target area; the size information includes the width and height of the target area. The focal length of the acquisition device (that is, the image acquisition device) includes a focal length in a horizontal direction and a focal length in a vertical direction.

Optionally, the first distance between the target object and the vehicle is determined according to the point cloud coordinates of the candidate point cloud. For example, the square of the abscissa and the square of the ordinate of the point cloud coordinates may be added, and the added result may be used as the first distance between the target object and the vehicle.

After the first distance is determined, an estimated height and an estimated width of the target object may be determined according to the first distance, the width or height in the size information, and the focal length of the acquisition device.

Exemplarily, the estimated height of the target object can be determined according to the first distance, the height in the size information, and the vertical focal length of the acquisition device, for example, it can be determined by the following formula:

Wherein, h represents the estimated height of the target object, f _y represents the vertical focal length of the acquisition device, |y ₂ −y ₁ | represents the height in the size information, and r represents the first distance.

Exemplarily, the estimated width of the target object can be determined according to the first distance, the width in the size information, and the horizontal focal length of the acquisition device, for example, it can be determined by the following formula:

Wherein, w represents the estimated width of the target object, f _x represents the horizontal focal length of the acquisition device, |x ₂ −x ₁ | represents the width in the size information, and r represents the first distance.

After determining the estimated height and estimated width of the target object, the second distance between the target object and the vehicle may be determined according to the estimated width or estimated height of the target object, the focal length of the acquisition device, and the width or height in the size information.

Exemplarily, if the height of the target object is known, the second distance between the target object and the vehicle is determined according to the height of the target object, the vertical focal length of the collection device, and the height in the size information. For example, it can be determined by the following formula:

Among them, r' represents the second distance between the target object and the vehicle, h' represents the height of the target object, |y ₂ -y ₁ | represents the height in the size information, and f _y represents the vertical focal length of the acquisition device.

Exemplarily, if the width of the target object is known, the second distance between the target object and the vehicle is determined according to the width of the target object, the horizontal focal length of the acquisition device, and the width in the size information. For example, it can be determined by the following formula:

Among them, r' represents the second distance between the target object and the vehicle, w' represents the width of the target object, |x ₂ -x ₁ | represents the width in the size information, and f _x represents the horizontal focal length of the acquisition device.

Optionally, the first distance, the estimated height, the estimated width, the coordinates of the center point of the candidate point cloud, the second distance and basic information are input into the neural network model to obtain the matching degree between the candidate point cloud and the target area. Wherein, the neural network model may be a radial basis neural network.

Exemplarily, the first distance, the estimated height, the estimated width, the coordinates of the center point of the candidate point cloud, the second distance and basic information are input into the neural network model, and after processing by the neural network model, the distance between the candidate point cloud and the target area is obtained. suitability.

It can be understood that the accuracy of the matching degree can be enhanced by determining the matching degree of the candidate point cloud and the target area through the neural network model.

S340. Determine the target point cloud from the at least one candidate point cloud according to the matching degree between the at least one candidate point cloud and the target area.

S350. Determine the position of the target object according to the target point cloud.

In the technical solution of the embodiment of the present application, the target area of the target object is determined according to the image data of the target object in the scene where the vehicle is located, and then the target object is determined according to the first point cloud data and the target area of the target object in the scene where the vehicle is located and for each candidate point cloud, according to the point cloud coordinates of the candidate point cloud, the basic information of the target area and the focal length of the acquisition device, determine the matching degree between the candidate point cloud and the target area, and then according to at least one The matching degree between the candidate point cloud and the target area is used to determine the target point cloud from the at least one candidate point cloud, and finally the position of the target object is determined according to the target point cloud. The above technical solution determines the position of the target object in the scene where the vehicle is located through the combination of image data and point cloud data, which improves the accuracy of determining the position of the target object and provides a basis for determining the position of the target object in the surrounding environment of the vehicle in automatic driving. a new way of thinking.

Embodiment four

Fig. 4 is a schematic structural diagram of a target position determination device provided in Embodiment 4 of the present application. This embodiment is applicable to the determination of the position of target objects around the vehicle in automatic driving, especially in extreme environments (bad weather conditions or Dark environment), the situation of determining the position of target objects around the vehicle in automatic driving. The device can be realized by means of software and/or hardware, and can be integrated into an electronic device carrying the function of determining the target position, such as a vehicle controller.

As shown in Figure 4, the device may include a target area determination module 410, a candidate point cloud determination module 420, a target point cloud determination module 430 and a position determination module 440, wherein,

The target area determination module 410 is configured to determine the target area of the target object according to the image data of the target object in the scene where the vehicle is located;

The candidate point cloud determination module 420 is configured to determine the candidate point cloud of the target object according to the first point cloud data and the target area of the target object in the scene where the vehicle is located;

The target point cloud determining module 430 is configured to determine the target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud;

The position determination module 440 is configured to determine the position of the target object according to the target point cloud.

Optionally, the candidate point cloud determination module 420 includes a point cloud stack obtaining unit, a second point cloud data obtaining unit and a candidate point cloud determining unit, wherein,

The point cloud stack obtains the unit, which is set to perform three-dimensional conversion of the target area to obtain the point cloud cone;

The second point cloud data obtaining unit is configured to project the first point cloud data to the image plane coordinate system based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system to obtain the second point cloud data;

The candidate point cloud determining unit is configured to determine the candidate point cloud of the target object according to the positional relationship between the second point cloud data and the point cloud cone.

Optionally, the number of candidate point clouds is at least one, and the target point cloud determination module 430 includes a matching degree determination unit and a target point cloud determination unit, wherein,

The matching degree determining unit is configured to, for each candidate point cloud, determine the matching degree of the candidate point cloud and the target area according to the point cloud coordinates of the candidate point cloud, the basic information of the target area and the focal length of the acquisition device; the basic information includes The size information of the target area and the coordinates of the center point of the target area;

The target point cloud determining unit is configured to determine the target point cloud from the at least one candidate point cloud according to the matching degree between the at least one candidate point cloud and the target area.

Optionally, the matching degree determining unit includes a first distance determining subunit, an estimated information determining subunit, a second distance determining subunit, and a matching degree determining subunit, wherein,

The first distance determination subunit is configured to determine the first distance between the target object and the vehicle according to the point cloud coordinates of the candidate point cloud;

The estimated information determination subunit is configured to determine the estimated height and estimated width of the target object according to the first distance, the width or height in the size information of the target area, and the focal length of the acquisition device;

The second distance determination subunit is configured to determine the second distance between the target object and the vehicle according to the estimated width or estimated height of the target object, the focal length of the acquisition device, and the width or height in the size information of the target area;

The matching degree determination subunit is configured to input the first distance, estimated height, estimated width, coordinates of the center point of the candidate point cloud, the second distance and basic information into the neural network model to obtain the degree of matching between the candidate point cloud and the target area .

Optionally, the candidate point cloud determination module 420 also includes a cluster point cloud determination unit, wherein the distance point cloud unit is set to:

Clustering the first point cloud data to obtain clustered point cloud data;

Correspondingly, the second point cloud data obtaining unit is also set as:

Based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, the clustered point cloud data is projected to the image plane coordinate system to obtain the second point cloud data.

Optionally, the target point cloud determination module 430 is set to:

The matching degree is sorted, and the target point cloud is determined from the candidate point cloud according to the sorting result and the set threshold.

Optionally, the device also includes a correction processing module, the correction processing module is configured to:

Correction processing is performed on the image data based on preset correction parameters.

The above-mentioned device for determining a target position can execute the method for determining a target position provided in any embodiment of the present application, and has corresponding functional modules for executing the method.

Embodiment five

Fig. 5 is a schematic structural diagram of an electronic device provided in Embodiment 5 of the present application, and Fig. 5 shows a block diagram of an exemplary device suitable for implementing the implementation manner of the embodiment of the present application. The device shown in FIG. 5 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.

As shown in FIG. 5, electronic device 12 takes the form of a general-purpose computing device. Components of the electronic device 12 may include, but are not limited to, at least one processor or processing unit 16 , a system memory 28 , and a bus 18 connecting various system components including the system memory 28 and the processing unit 16 .

Bus 18 represents at least one of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (Industry Standard Architecture, ISA) bus, Micro Channel Architecture (Micro Channel Architecture, MCA) bus, Enhanced ISA bus, Video Electronics Standards Association (Video Electronics Standards Association, VESA) local bus and peripheral component interconnect (Peripheral Component Interconnect, PCI) bus.

Electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 12 and include both volatile and nonvolatile media, removable and non-removable media.

System memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory (cache 32). The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk") may be provided, as well as a removable non-volatile disk (such as a Compact Disc- Read Only Memory, CD-ROM), Digital Video Disc (Digital Video Disc-Read Only Memory, DVD-ROM) or other optical media) CD-ROM drive. In these cases, each drive may be connected to bus 18 via at least one data medium interface. The system memory 28 may include at least one program product, which has a set of (for example, at least one) program modules configured to execute the functions of the various embodiments of the embodiments of the present application.

a program/utility 40 having a set (at least one) of program modules 42, such as may be stored in system memory 28, such as but not limited to an operating system, at least one application program, other program modules, and program data, Implementations of networked environments may be included in each or some combination of these examples. The program module 42 generally executes the functions and/or methods in the embodiments described in the embodiments of this application.

The electronic device 12 can also communicate with at least one external device 14 (such as a keyboard, a pointing device, a display 24, etc.), and can also communicate with at least one device that enables a user to interact with the electronic device 12, and/or communicate with the electronic device 12. 12. Any device capable of communicating with at least one other computing device (eg, network card, modem, etc.). This communication can be performed through an input/output (Input/Output, I/O) interface 22 . Moreover, the electronic device 12 can also communicate with at least one network (such as a local area network (Local Area Network, LAN), a wide area network (Wide Area Network, WAN) and/or a public network such as the Internet) through the network adapter 20. Network adapter 20 communicates with other modules of electronic device 12 over bus 18, as shown. It should be appreciated that although not shown, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays) of Independent Disks, RAID) systems, tape drives, and data backup storage systems.

The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28 , for example, realizing the method for determining the target position provided by the embodiment of the present application.

Embodiment six

Embodiment 6 of the present application also provides a computer-readable storage medium on which a computer program (or called computer-executable instructions) is stored. When the program is executed by a processor, it is used to execute the target location provided by the embodiment of the present application. Determine the method, which includes:

Determine the candidate point cloud of the target object according to the first point cloud data and the target area of the target object in the scene where the vehicle is located;

Determine the target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud;

According to the target point cloud, determine the position of the target object.

The computer storage medium in the embodiments of the present application may use any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with at least one lead, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable Read-Only Memory ((Erasable Programmable Read-Only Memory, EPROM) or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above . In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in conjunction with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a data signal carrying computer readable program code in baseband or as part of a carrier wave. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. .

The program code contained on the computer readable medium can be transmitted by any appropriate medium, including but not limited to wireless, electric wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.

Computer program codes for performing the operations of the embodiments of the present application may be written in one or more programming languages or combinations thereof, the programming languages including object-oriented programming languages—such as Java, Smalltalk, C++, including A conventional procedural programming language such as the "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. Where a remote computer is involved, the remote computer may be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g. via the Internet using an Internet Service Provider). .

Claims

A method for determining a target location, comprising:

Determine the target area of the target object according to the image data of the target object in the scene where the vehicle is located;

determining a candidate point cloud of the target object according to the first point cloud data of the target object in the scene where the vehicle is located and the target area;

determining a target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud;

According to the target point cloud, the position of the target object is determined.
The method according to claim 1, wherein said determining the candidate point cloud of the target object according to the first point cloud data of the target object and the target area comprises:

performing three-dimensional transformation on the target area to obtain a point cloud cone;

Based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, projecting the first point cloud data to the image plane coordinate system to obtain the second point cloud data;

A candidate point cloud of the target object is determined according to a positional relationship between the second point cloud data and the point cloud cone.
The method according to claim 1, wherein the number of the candidate point cloud is at least one, and the target is determined from the candidate point cloud according to the matching degree between the target area and the candidate point cloud. Point cloud, including:

For each candidate point cloud, determine the matching degree between the candidate point cloud and the target area according to the point cloud coordinates of the candidate point cloud, the basic information of the target area and the focal length of the acquisition device; the basic information includes the target area The size information of the area and the coordinates of the center point of the target area;

The target point cloud is determined from the at least one candidate point cloud according to the matching degree between the at least one candidate point cloud and the target area.
The method according to claim 3, wherein the matching degree of the candidate point cloud and the target area is determined according to the point cloud coordinates of the candidate point cloud, the basic information of the target area, and the focal length of the acquisition device, include:

determining a first distance between the target object and the vehicle according to the point cloud coordinates of the candidate point cloud;

determining an estimated height and an estimated width of the target object according to the first distance, the width or height in the size information of the target area, and the focal length of the collection device;

determining a second distance between the target object and the vehicle according to the estimated width or estimated height of the target object, the focal length of the acquisition device, and the width or height in the size information of the target area;

Input the first distance, the estimated height, the estimated width, the coordinates of the center point of the candidate point cloud, the second distance and the basic information into the neural network model to obtain the candidate point cloud and the target Matching degree of the region.
According to the method according to claim 2, said first point cloud data is projected onto the image plane coordinate system based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, and before obtaining the second point cloud data, Also includes:

Clustering the first point cloud data to obtain clustered point cloud data;

Correspondingly, based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, the first point cloud data is projected to the image plane coordinate system to obtain the second point cloud data, including:

Based on the conversion relationship between the radar plane coordinate system and the image plane coordinate system, the clustered point cloud data is projected onto the image plane coordinate system to obtain the second point cloud data.
The method according to claim 1, wherein said determining the target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud comprises:

The matching degree is sorted, and the target point cloud is determined from the candidate point cloud according to the sorting result and the set threshold.
The method according to claim 1, further comprising:

Correction processing is performed on the image data based on preset correction parameters.
A device for determining a target location, comprising:

The target area determination module is configured to determine the target area of the target object according to the image data of the target object in the scene where the vehicle is located;

The candidate point cloud determination module is configured to determine the candidate point cloud of the target object according to the first point cloud data and the target area of the target object in the scene where the vehicle is located;

The target point cloud determination module is configured to determine the target point cloud from the candidate point cloud according to the matching degree between the target area and the candidate point cloud;

A position determining module, configured to determine the position of the target object according to the target point cloud.
An electronic device comprising:

at least one processor;

a memory configured to store at least one program;

When the at least one program is executed by the at least one processor, the at least one processor is made to implement the target position determination method according to any one of claims 1-7.
A computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method for determining a target position according to any one of claims 1-7 is implemented.