Point cloud data processing method, device, equipment and autonomous driving vehicle

Abstract

The present disclosure discloses a method, device, equipment, and autonomous driving vehicle for processing point cloud data, relating to the field of autonomous driving technology. A specific implementation scheme comprises: obtaining speed measurement values ​​of the point cloud data; determining each measurement point of the point cloud data using the speed measurement values ​​of the point cloud data and the attitude measurement values ​​of the point cloud data relative to the point cloud radar from which the point cloud data originates; performing a Hough transform on the measurement points to obtain the distribution of each measurement point in the Hough space; searching for the peak value of the distribution in the Hough space; and determining the dynamic and static state of the target based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space. The present disclosure implements the dynamic and static state judgment of point cloud data.

Description

Technical Field

[0001] The present disclosure relates to the field of computer application technology, and in particular to a method, device, equipment, and autonomous driving vehicle for processing point cloud data in the field of autonomous driving technology. Background Art

[0002] The continuous development of autonomous driving technology has driven the continuous advancement of vehicle body sensor systems and related technologies. Among the many sensors, millimeter-wave radar has the ability to operate around the clock and in all weather conditions, such as rain, snow, fog, and at night. It also serves as an effective auxiliary and support for cameras and lidar sensors. Early automotive millimeter-wave radars focused primarily on target-level obstacle detection and parameter measurement. To provide more detailed and richer information about the driving environment, 4D point cloud radar has become the current development trend. 4D point cloud radar, also known as imaging millimeter-wave radar, achieves four-dimensional environmental perception, including distance, horizontal and vertical positioning, and speed.

[0003] For downstream applications, the dynamic and static state of point cloud data is a very important input information. For example, different processing is performed for moving and stationary objects. Therefore, determining the dynamic and static state of point cloud data is a crucial step. Summary of the Invention

[0004] In view of this, the present disclosure provides a method, device, equipment and autonomous driving vehicle for processing point cloud data, so as to facilitate the dynamic and static state judgment of point cloud data.

[0005] According to a first aspect of the present disclosure, a method for processing point cloud data is provided, comprising:

[0006] Get velocity measurements from point cloud data;

[0007] Determine each measurement point of the point cloud data using a velocity measurement of the point cloud data and an attitude measurement of the point cloud data relative to a point cloud radar from which the point cloud data originates;

[0008] Performing Hough transform on each measurement point to obtain the distribution of each measurement point in Hough space;

[0009] Searching for the peak value of the distribution in the hough space;

[0010] The dynamic and static states of the target are determined based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space.

[0011] According to a second aspect of the present disclosure, there is provided a point cloud data processing device, comprising:

[0012] A measurement value acquisition unit, used for acquiring a velocity measurement value of the point cloud data;

[0013] a measurement point determination unit, configured to determine measurement points of the point cloud data using a velocity measurement value of the point cloud data and a posture measurement value of the point cloud data relative to a point cloud radar from which the point cloud data originates;

[0014] A Hough transform unit is used to perform Hough transform on each measurement point to obtain the distribution of each measurement point in the Hough space;

[0015] A peak search unit, configured to search for peaks distributed in the hough space;

[0016] The motion / static discrimination unit is used to determine the motion / static state of the target based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space.

[0017] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0021] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method as described above.

[0022] According to a fifth aspect of the present disclosure, a computer program product includes a computer program, which implements the method described above when executed by a processor.

[0023] According to a sixth aspect of the present disclosure, an autonomous driving vehicle includes the electronic device as described above.

[0024] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0026] Figure 1 A flow chart of a method for processing point cloud data provided in an embodiment of the present disclosure;

[0027] Figure 2A flow chart for obtaining velocity measurements of point cloud data provided by an embodiment of the present disclosure;

[0028] Figure 3a A geometric relationship diagram of target observation by a point cloud radar provided in an embodiment of the present disclosure;

[0029] Figure 3b A schematic diagram of the geometric relationship of vehicle motion provided by an embodiment of the present disclosure;

[0030] Figure 3c and Figure 3d A schematic diagram of Hough transformation provided by an embodiment of the present disclosure;

[0031] Figure 4 A schematic diagram of the structure of a point cloud data processing device provided in an embodiment of the present disclosure;

[0032] Figure 5 is a block diagram of an electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0034] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0035] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0036] Figure 1This is a flow chart of a method for processing point cloud data provided by an embodiment of the present disclosure. The execution subject of this method may be a point cloud data processing device, which may be an application located in a local terminal, or a functional unit such as a plug-in or software development kit (SDK) in an application located in a local terminal, or may be located on a server side. This embodiment of the present invention does not specifically limit this. Figure 1 As shown in , the method may include the following steps:

[0037] In 101 , velocity measurements of point cloud data are obtained.

[0038] In 102 , each measurement point of the point cloud data is determined using a velocity measurement value of the point cloud data and a posture measurement value of the point cloud data relative to a radar from which the point cloud data originates.

[0039] In 103, Hough transform is performed on each measurement point to obtain the distribution of each measurement point in the Hough space.

[0040] In 104, the peak value of the above distribution in the Hough space is searched.

[0041] In 105 , the dynamic or static state of the target is determined based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space.

[0042] It can be seen from the above technical solution that the present invention searches for the peak value of the distribution of each measurement point in the Hough space after performing Hough transform on the measurement points of the point cloud data, and determines the dynamic and static state of the target based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space, thereby realizing the dynamic and static state judgment of the point cloud data.

[0043] In addition, the method for distinguishing the dynamic and static states provided by the present disclosure does not rely on the input of external vehicle body information, thus avoiding misjudgment caused by the accuracy of the input vehicle body information.

[0044] The steps of the above method are described in detail below with reference to the embodiments. First, the above step 101, namely "obtaining velocity measurement values ​​of point cloud data", is described in detail.

[0045] To facilitate understanding, a brief introduction to the detection environment involved in the embodiments of the present disclosure is first provided. A vehicle is typically equipped with multiple or various radars, and the radars can be installed at different locations on the vehicle. Each radar is typically configured to have a different measurement range. In addition to radars, the vehicle also includes other sensors to sense various variables around the vehicle and within the vehicle body. Sensors may also include cameras, light detection and ranging units, infrared sensors, steering sensors, throttle sensors, brake sensors, audio sensors, temperature sensors, and the like.

[0046] As one implementation, the velocity measurement value of the point cloud data can be obtained by measuring the velocity of the point cloud data relative to the radar from which the point cloud data originated. For ease of description in subsequent embodiments, the radar from which the point cloud data originated will be referred to as the "point cloud radar." For example, the velocity measurement value of each point cloud relative to the point cloud radar can be directly used as the velocity measurement value of each point cloud radar.

[0047] However, in actual scenarios, point cloud radars such as millimeter-wave radars have a speed ambiguity problem. This speed ambiguity problem is caused by the fact that the speed measurement range of the point cloud radar is narrower than the speed range of the target in the actual scenario. When the speed of the target exceeds the speed measurement range of the point cloud radar, it will cause "speed ambiguity", that is, the speed measurement value of the point cloud is inaccurate. To address this problem, the embodiment of the present disclosure provides an optimal way to obtain the speed measurement value of the point cloud data. The specific process can be as follows: Figure 2 As shown in , the following steps are included:

[0048] In 201 , the static speed value of each point cloud is determined using the vehicle body parameters estimated from the previous frame of point cloud data, the attitude measurement value of the point cloud data relative to the point cloud radar, and the offset of the point cloud radar relative to the installation position of the central radar.

[0049] Assuming that the target point cloud is in a stationary state, the speed relative to the target point cloud measured by the point cloud radar is called the static speed value in the embodiment of the disclosure. As one implementation method, the static speed value of the i-th point cloud is It can be determined using the following formula:

[0050]

[0051] in, and is the azimuth and pitch angle of the i-th point cloud relative to the point cloud radar, that is, the attitude measurement value. mount 、y mount The horizontal and vertical axis offset of the point cloud radar relative to the installation position of the center radar. Usually the center radar is installed on the rear axle of the vehicle. car 、ω car Respectively represent the body parameters of the vehicle carrying the point cloud radar, namely, speed and angular velocity. The body parameters are estimated using point cloud data, and the specific estimation method will be described in the subsequent embodiments. Since the vehicle's motion parameters do not change much between the two frames (milliseconds) when calculating the static speed value, and the static speed estimation here is for speed defuzzification processing, the accuracy requirement is not high. Therefore, the body parameters estimated in the previous frame are used in formula (1). In this way, the static speed value can be calculated for each point cloud.

[0052] The following briefly describes the derivation process of the above formula (1).

[0053] Assume that the geometric relationship of the point cloud radar on the vehicle to the target observation is as follows: Figure 3a As shown in , point O is the origin of the radar coordinates. A stationary scattering point in the scene will generate point cloud i (i.e., the i-th point cloud mentioned above), and its azimuth relative to the point cloud radar is Assume that the velocity vector of the point cloud radar at the current moment caused by the vehicle body movement is v car , direction is θ v , then the velocity measurement value of the point cloud by the radar is the static velocity value With radar movement speed v car The following relationship is satisfied:

[0054]

[0055] Figure 3b is a schematic diagram of the vehicle motion geometry. Figure 3b O is the coordinate origin of the vehicle body, which can be considered as the center of the rear axle of the vehicle. The horizontal and vertical axis offsets of the point cloud radar relative to the coordinate origin of the vehicle body are x mount 、y mount .in accordance with Figure 3b The geometric relationship shown in is used to expand the above formula (2) to obtain the following formula:

[0056]

[0057] Further considering the pitch angle of the point cloud relative to the point cloud radar, the above formula (1) can be obtained.

[0058] In 202, the fuzzy parameter that minimizes the difference between the static speed value of the point cloud and the speed measurement value of the point cloud radar is determined by using the correspondence between the static speed value of the point cloud, the speed measurement range of the point cloud radar, the fuzzy parameter, and the speed measurement value of the point cloud by the point cloud radar.

[0059] Since the velocity measurement value of each point cloud by the point cloud radar may be fuzzy, the actual velocity of the point cloud relative to the point cloud radar is Probably a speed measurement Add or subtract integer multiples, for example:

[0060]

[0061] Where n is an integer, which may be a positive integer or a negative integer. amb Determined by the speed measurement interval of the point cloud radar, for example, if the speed measurement interval of the point cloud radar is [-15,15], then Ω ambThe value is 30. The speed measurement range of the point cloud radar is a design parameter of the point cloud radar and is its own characteristic.

[0062] Here you can choose the value of n so that and The difference is the smallest, that is, the following formula is used to determine n amb :

[0063]

[0064] Among them, n amb is a fuzzy parameter.

[0065] In 203 , the speed measurement value of each point cloud is determined using the fuzzy parameter of each point cloud, the speed measurement value of the point cloud by the point cloud radar, and the speed measurement interval.

[0066] After determining the fuzzy parameter n amb The velocity measurement for each point cloud can then be determined using the following formula:

[0067]

[0068] in, is the velocity measurement value after defuzzification of the i-th point cloud.

[0069] The method shown in this embodiment can determine the speed measurement value of the point cloud after defuzzification, thereby solving the problem of inaccurate speed measurement value of the point cloud caused by the narrow speed measurement range of the point cloud radar, and also laying the foundation for the subsequent accurate judgment of the dynamic and static state of the point cloud.

[0070] The above step 102, namely "determining each measurement point of the point cloud data by using the velocity measurement value of the point cloud data and the attitude measurement value of the point cloud data relative to the radar from which the point cloud data originates", is described in detail below in conjunction with an embodiment.

[0071] Continuing the derivation of the above formula (6), for a stationary point cloud, the above formula (6) That is, So the following formula is obtained:

[0072]

[0073] It can be seen that in the measurement space and If the linear relationship is satisfied, the coordinates of the measurement point (x i ,y i )for:

[0074]

[0075]

[0076] The above step 103, i.e., "performing a Hough transform on each measurement point to obtain a distribution of each measurement point in the Hough space", and the above step 104, i.e., "searching for a peak value of the distribution in the Hough space", are described in detail below with reference to an embodiment.

[0077] The Hough transform, proposed by Paul Hough in 1962, is an effective tool for line estimation. Its principle is to utilize the line-point duality between image space and Hough parameter space to transform the detection problem in image space into parameter space. In this disclosure, the principle of the Hough transform is utilized to transform the measurement space where each measurement point is located into Hough space. Specifically, each measurement point is projected onto a curve in Hough space, resulting in the distribution of ρ(i)-θ(i) in Hough space as follows:

[0078] ρ(i)=x i ·cosθ(i)+y i sinθ(i) (10)

[0079] The above transformation is equivalent to converting the measurement space (x i ,y i ) coordinates are converted to the hough space where the polar coordinates are located. Figure 3c As shown in , for a straight line in the measurement space, the distance from the origin to the straight line is ρ0, and the angle between the distance and the x-axis is θ0. Then the straight line converted to the hough space corresponds to a point (ρ0, θ0).

[0080] For each point cloud, measure the point (x i ,y i ) corresponds to a curve ρ(i)-θ(i) in the Hough space. Since most point clouds in actual scenes are stationary targets, the straight lines where the measurement points of these static targets are located in the measurement space correspond to the intersection points of the curves in the Hough space, such as Figure 3d As shown in . Therefore, the peak of the search hough space is the position where the curves intersect the most (ρ peak ,θ peak ), the peak value is the ideal parameter value of the stationary target.

[0081] The peak search in the Hough space can be performed using existing methods. Currently, there are relatively mature technologies to implement peak search in the Hough space, and packaged functions such as houghpeaks() are provided for direct calling. Therefore, the specific method of peak search is described in detail in the embodiment of the present disclosure.

[0082] The above step 105, namely "determining the dynamic and static state of the target based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space" is described in detail below with reference to an embodiment.

[0083] From the above derivation, we can see that for the peak value of the hough space, the corresponding straight line in the measurement space can be regarded as the straight line where the measurement point of the ideal static target is located. In other words, if the measurement point (x i ,y i ) is in a stationary state, then theoretically it should satisfy:

[0084] x i cosθ peak +y i sinθ peak =ρ peak (11)

[0085] Then, conversely, the dynamic or static state of the point cloud can be determined by judging the distance from the measurement point of the point cloud to the straight line corresponding to the peak value in the measurement space. The closer the distance, the greater the possibility of being in a static state.

[0086] The measurement point (x i ,y i ) to the distance d from the peak value to the straight line corresponding to the peak value in the measurement space i It can be determined using the following formula:

[0087] d i =|ρ compute -ρ peak |=|x i cosθ peak +y i sinθ peak -ρ peak | (12)

[0088] If d i If the distance is greater than or equal to a preset distance threshold thre_v, the i-th point cloud is considered to be in motion; otherwise, the i-th point cloud is considered to be stationary. The distance threshold thre_v can be determined by the velocity measurement accuracy of the point cloud radar, and the specific value can be based on empirical or experimental values.

[0089] Furthermore, after step 105, the vehicle body parameters corresponding to the point cloud data of the current frame may be further estimated for use in processing the next frame of point cloud data, that is, in speed defuzzification processing of the next frame of point cloud data.

[0090] When estimating vehicle body parameters, the above peak values ​​and the offset of the point cloud radar relative to the center radar installation position can be used for estimation. As one implementation method, by combining the above formulas (7) to (9), the following vehicle body parameter estimation results can be obtained:

[0091]

[0092]

[0093] By using the methods described in the above embodiments to determine the static and dynamic state of point clouds, a crucial foundation is provided for downstream applications. For example, autonomous driving scenarios often place greater emphasis on dynamic targets. Therefore, the methods provided in the embodiments of this disclosure can be used to perform static and dynamic determination, filtering out point clouds in motion and using static point clouds as background information.

[0094] For another example, in some application scenarios, it is necessary to pay attention to small moving targets. In this case, the distance threshold thre_v is controlled to achieve recognition of small moving targets with a certain accuracy in the manner provided by the present disclosure.

[0095] The above is a detailed description of the method provided by the present disclosure. The following is a detailed description of the device provided by the present disclosure in conjunction with embodiments.

[0096] Figure 4 A schematic diagram of the structure of a point cloud data processing device provided in an embodiment of the present disclosure, such as Figure 4 As shown in FIG, the apparatus 400 may include: a measurement value acquisition unit 410, a measurement point determination unit 420, a Hough transform unit 430, a peak search unit 440, and a motion / static discrimination unit 450, and may further include a vehicle body parameter estimation unit 460. The main functions of each component unit are as follows:

[0097] The measurement value acquisition unit 410 is used to acquire the velocity measurement value of the point cloud data.

[0098] The measurement point determination unit 420 is configured to determine measurement points of the point cloud data using the velocity measurement value of the point cloud data and the attitude measurement value of the point cloud data relative to the point cloud radar from which the point cloud data originates.

[0099] The Hough transform unit 430 is configured to perform a Hough transform on each measurement point to obtain the distribution of each measurement point in the Hough space.

[0100] The peak search unit 440 is used to search for peaks distributed in the Hough space.

[0101] The motion / static discrimination unit 450 is used to determine the motion / static state of the target based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space.

[0102] As a preferred implementation, the measurement value acquisition unit 410 may specifically include: a static speed estimation subunit 411 , a fuzzy estimation subunit 412 and a defuzzification processing subunit 413 .

[0103] The static speed estimation subunit 411 is used to determine the static speed value of each point cloud using the vehicle body parameters estimated from the previous frame of point cloud data, the attitude measurement value of the point cloud data relative to the point cloud radar, and the offset of the point cloud radar relative to the central radar installation position.

[0104] The fuzzy estimation subunit 412 is used to use the correspondence between the static speed value of the point cloud, the speed measurement range of the point cloud radar, the fuzzy parameters, and the speed measurement value of the point cloud radar on the point cloud to determine the fuzzy parameters that minimize the difference between the static speed value of the point cloud and the speed measurement value of the point cloud radar on the point cloud.

[0105] The defuzzification processing subunit 413 is used to determine the speed measurement value of each point cloud by using the fuzzy parameters of each point cloud, the speed measurement value of the point cloud by the point cloud radar, and the speed measurement interval.

[0106] As one possible implementation method, the measurement point determination unit 420 is specifically configured to determine the coordinates (x i ,y i ), where x i Determined by the azimuth of the i-th point cloud relative to the point cloud radar, y i It is determined by the azimuth and elevation angles of the i-th point cloud relative to the point cloud radar and the velocity measurement value of the i-th point cloud.

[0107] As one of the feasible methods, the motion-static discrimination unit 450 is specifically used to determine that the target point cloud is in motion if the distance from the measurement point of the target point cloud to the straight line corresponding to the peak in the measurement space is greater than or equal to a preset distance threshold; otherwise, the target point cloud is determined to be in a stationary state.

[0108] The vehicle body parameter estimation unit 460 is used to estimate the vehicle body parameters for processing the next frame of point cloud data by using the peak value and the offset of the point cloud radar relative to the central radar installation position.

[0109] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0110] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0111] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product, and an autonomous driving vehicle.

[0112] like Figure 5 , which is a block diagram of an electronic device for processing point cloud data according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0113] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0114] Various components in device 500 are connected to I / O interface 505, including: an input unit 506, such as a keyboard, mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, optical disk, etc.; and a communication unit 509, such as a network card, modem, wireless communication transceiver, etc. The communication unit 509 allows device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0115] The computing unit 501 can be various general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the point cloud data processing method. For example, in some embodiments, the point cloud data processing method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 508.

[0116] In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 802 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the point cloud data processing method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to execute the point cloud data processing method in any other appropriate manner (e.g., via firmware).

[0117] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0119] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0121] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0122] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within a cloud computing service ecosystem that addresses the management difficulties and poor scalability of traditional physical hosts and virtual private servers (VPs). The server may also be a server in a distributed system or a server integrated with blockchain.

[0123] The autonomous driving vehicle provided by the embodiments of the present disclosure includes at least the above-mentioned electronic equipment.

[0124] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0125] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for processing point cloud data, comprising: Get velocity measurements from point cloud data; Determine each measurement point of the point cloud data using a velocity measurement of the point cloud data and an attitude measurement of the point cloud data relative to a point cloud radar from which the point cloud data originates; Performing Hough transform on each measurement point to obtain the distribution of each measurement point in Hough space; Searching for the peak value of the distribution in the hough space; Determine the dynamic and static state of the target based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space; Wherein, obtaining the speed measurement value of the point cloud data includes: Determine the static speed value of each point cloud using the vehicle body parameters estimated from the previous frame of point cloud data, the attitude measurement value of the point cloud data relative to the point cloud radar, and the offset of the point cloud radar relative to the central radar installation position; Determining a fuzzy parameter that minimizes the difference between the static speed value of the point cloud and the speed measurement value of the point cloud by the point cloud radar using a correspondence between the static speed value of the point cloud, the speed measurement interval of the point cloud radar, the fuzzy parameter, and the speed measurement value of the point cloud by the point cloud radar; The speed measurement value of each point cloud is determined by using the fuzzy parameters of each point cloud, the speed measurement value of the point cloud by the point cloud radar on the point cloud, and the speed measurement interval.

2. The method according to claim 1, wherein Determining each measurement point of the point cloud data using the velocity measurement value of the point cloud data and the attitude measurement value of the point cloud data relative to the point cloud radar includes: The coordinates of the measurement point of the i-th point cloud (x i ,y i ), x i Determined by the azimuth angle of the i-th point cloud relative to the point cloud radar, y i It is determined by the azimuth angle and pitch angle of the i-th point cloud relative to the point cloud radar and the speed measurement value of the i-th point cloud.

3. The method according to any one of claims 1 to 2, wherein Determining the dynamic and static state of the target based on the distance from each measurement point to the straight line corresponding to the peak value in the measurement space includes: If the distance from the measurement point of the target point cloud to the straight line corresponding to the peak in the measurement space is greater than or equal to a preset distance threshold, the target point cloud is determined to be in a moving state; otherwise, the target point cloud is determined to be in a stationary state.

4. The method according to claim 1, further comprising: The peak value and the offset of the point cloud radar relative to the central radar installation position are used to estimate vehicle body parameters for processing the next frame of point cloud data.

5. A point cloud data processing device, comprising: A measurement value acquisition unit, used for acquiring a velocity measurement value of the point cloud data; a measurement point determination unit, configured to determine measurement points of the point cloud data using a velocity measurement value of the point cloud data and a posture measurement value of the point cloud data relative to a point cloud radar from which the point cloud data originates; A Hough transform unit is used to perform Hough transform on each measurement point to obtain the distribution of each measurement point in the Hough space; A peak search unit, configured to search for peaks distributed in the hough space; A motion / static discrimination unit, configured to determine the motion / static state of the target based on the distance between each measurement point and the straight line corresponding to the peak value in the measurement space; The measurement value acquisition unit specifically includes: A static speed estimation subunit is used to determine the static speed value of each point cloud using the vehicle body parameters estimated from the previous frame of point cloud data, the attitude measurement value of the point cloud data relative to the point cloud radar, and the offset of the point cloud radar relative to the central radar installation position; a fuzzy estimation subunit, configured to determine a fuzzy parameter that minimizes a difference between the static speed value of the point cloud and the speed measurement value of the point cloud by the point cloud radar, by using a correspondence between the static speed value of the point cloud, the speed measurement interval of the point cloud radar, the fuzzy parameter, and the speed measurement value of the point cloud by the point cloud radar; The defuzzification processing subunit is used to determine the speed measurement value of each point cloud by using the fuzzy parameters of each point cloud, the speed measurement value of the point cloud by the point cloud radar and the speed measurement interval.

6. The device according to claim 5, wherein: The measuring point determination unit is specifically used to determine the coordinates (x i ,y i ), where x i Determined by the azimuth angle of the i-th point cloud relative to the point cloud radar, y i It is determined by the azimuth angle and pitch angle of the i-th point cloud relative to the point cloud radar and the speed measurement value of the i-th point cloud.

7. The device according to any one of claims 5 to 6, wherein: The motion-static discrimination unit is specifically configured to determine that the target point cloud is in motion if the distance from the measurement point of the target point cloud to the straight line corresponding to the peak in the measurement space is greater than or equal to a preset distance threshold; otherwise, determine that the target point cloud is in a stationary state.

8. The apparatus according to claim 5, further comprising: The vehicle body parameter estimation unit is used to estimate the vehicle body parameters for processing the next frame of point cloud data by using the peak value and the offset of the point cloud radar relative to the installation position of the central radar.

9. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 4.

11. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 4.

12. An autonomous driving vehicle comprising the electronic device according to claim 9.

Images