WO2022213632A1 - 用于标定毫米波雷达的方法、装置、电子设备及路侧设备 - Google Patents

用于标定毫米波雷达的方法、装置、电子设备及路侧设备 Download PDF

Info

Publication number
WO2022213632A1
WO2022213632A1 PCT/CN2021/135144 CN2021135144W WO2022213632A1 WO 2022213632 A1 WO2022213632 A1 WO 2022213632A1 CN 2021135144 W CN2021135144 W CN 2021135144W WO 2022213632 A1 WO2022213632 A1 WO 2022213632A1
Authority
WO
WIPO (PCT)
Prior art keywords
millimeter
wave radar
coordinate system
topology information
map
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.)
Ceased
Application number
PCT/CN2021/135144
Other languages
English (en)
French (fr)
Inventor
易光启
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Apollo Intelligent Connectivity Beijing Technology Co Ltd
Original Assignee
Apollo Intelligent Connectivity Beijing Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Apollo Intelligent Connectivity Beijing Technology Co Ltd filed Critical Apollo Intelligent Connectivity Beijing Technology Co Ltd
Publication of WO2022213632A1 publication Critical patent/WO2022213632A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

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
    • G01S7/40—Means for monitoring or calibrating

Definitions

  • the present disclosure relates to the technical field of data processing, in particular to the technical fields of artificial intelligence such as computer vision and intelligent transportation, and in particular to a method, device, electronic device, roadside device, computer-readable storage medium, and computer for calibrating millimeter-wave radar program product.
  • Vehicle-road coordination is a concept under smart transportation. What ultimately needs to be improved in vehicle-road collaboration is the "intelligence level" of vehicles and roads to achieve the purpose of safe and automatic driving. It can also be said that the intelligence of vehicle-road collaboration is another process of autonomous driving. The process of intelligentization is divided into the upgrade of smart devices and algorithms covering vehicles and roads. The most important thing in smart devices is the sensor.
  • lidars deployed on the roadside as roadside sensors, or only use radars deployed on vehicles.
  • the embodiments of the present disclosure propose a method, an apparatus, an electronic device, a roadside device, a computer-readable storage medium, and a computer program product for calibrating a millimeter-wave radar.
  • an embodiment of the present disclosure proposes a method for calibrating a millimeter-wave radar, including: generating lane topology information in a millimeter-wave radar coordinate system according to a perception result of the millimeter-wave radar on a vehicle traveling in a target area; According to the map data of the target area, the lane line topology information is generated in the map coordinate system; the millimeter wave radar coordinate system is constructed in the same way as the map coordinate system; based on the preset deviation, it is determined that the lane topology information matches the lane line The actual parameters of the topology information are used to calibrate the millimeter-wave radar, and the deviation is used to correct the perception accuracy error of the millimeter-wave radar.
  • an embodiment of the present disclosure provides an apparatus for calibrating a millimeter-wave radar, including: a lane topology information generating unit, configured to generate a millimeter-wave The lane topology information is generated in the radar coordinate system; the lane line topology information generation unit is configured to generate the lane line topology information in the map coordinate system according to the map data of the target area; wherein, the establishment of the millimeter wave radar coordinate system and the map coordinate system The method is the same; the calibration parameter calculation unit is configured to determine the actual parameters of the lane topology information matching the lane line topology information based on the preset deviation, and use the actual parameters to calibrate the millimeter-wave radar, and the deviation is used to correct the millimeter-wave radar. Perceived accuracy error.
  • embodiments of the present disclosure provide an electronic device, the electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor , the instruction is executed by at least one processor, so that when executed by the at least one processor, the method for calibrating a millimeter-wave radar as described in any implementation manner of the first aspect can be implemented.
  • an embodiment of the present disclosure provides a roadside device, where the roadside device includes the electronic device described in the third aspect.
  • embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to enable a computer to implement the calibration method described in any implementation manner of the first aspect when the computer instructions are executed.
  • the method of millimeter wave radar is used to enable a computer to implement the calibration method described in any implementation manner of the first aspect when the computer instructions are executed.
  • an embodiment of the present disclosure provides a computer program product including a computer program, which, when executed by a processor, can implement the method for calibrating a millimeter-wave radar as described in any implementation manner of the first aspect .
  • the method, device, electronic device, roadside device, computer-readable storage medium, and computer program product for calibrating a millimeter-wave radar provided by the embodiments of the present disclosure, first, according to the perception result of the millimeter-wave radar on the vehicle traveling in the target area , generate lane topology information in the millimeter wave radar coordinate system; sequentially or simultaneously, according to the map data of the target area, generate the lane line topology information in the map coordinate system, the millimeter wave radar coordinate system and the map coordinate system are constructed in the same way Next, based on a preset deviation amount used to correct the perception accuracy error of the millimeter-wave radar, determine the actual parameters of the lane topology information matching the lane line topology information, and use the actual parameters to calibrate the millimeter-wave radar.
  • the perception result of the millimeter-wave radar in the same area and the high-precision map data are used as two kinds of input data, and then the relevant topology information describing the lane is generated in their respective coordinate systems.
  • the two coordinate systems are constructed in the same way, the external parameters of the millimeter-wave radar can be accurately calibrated through the corresponding relationship of the topological structures in different coordinate systems, so that when the millimeter-wave radar is used as a roadside sensor It can also meet the requirements for perception accuracy in vehicle-road collaboration scenarios.
  • FIG. 1 is an exemplary system architecture in which the present disclosure may be applied
  • FIG. 2 is a flowchart of a method for calibrating a millimeter-wave radar according to an embodiment of the present disclosure
  • FIG. 3 is a flowchart of another method for calibrating a millimeter-wave radar according to an embodiment of the present disclosure
  • FIG. 4 is a structural block diagram of an apparatus for calibrating a millimeter-wave radar according to an embodiment of the present disclosure
  • FIG. 5 is a schematic structural diagram of an electronic device suitable for executing a method for calibrating a millimeter-wave radar according to an embodiment of the present disclosure.
  • the acquisition, storage and application of the user's personal information involved all comply with the relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good customs.
  • FIG. 1 illustrates an exemplary system architecture 100 to which embodiments of methods, apparatus, electronic devices, roadside equipment, computer-readable storage media, and computer program products for calibrating millimeter-wave radars of the present disclosure may be applied.
  • the system architecture 100 may include a map database 101 , a millimeter-wave radar 102 , a network 103 , and a calibration server 104 .
  • the network 103 is a medium used to provide a communication link between the map database 101 and the millimeter wave radar 102 and the calibration server 104 .
  • the network 103 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
  • the map database 101 stores the high-precision map data of each area, including the location of traffic facilities, lane positions, etc.; Take the millimeter-wave radar 102 used for sensing the trajectory of the vehicle as an example; the calibration server 104 is used to complete the external parameter calibration of the millimeter-wave radar according to the respectively received high-precision map data and perception results.
  • the data collection, data transmission, and data processing between the above-mentioned execution bodies can all be realized by the applications installed on the above-mentioned execution bodies, for example, the map query application installed on the map database 101 can obtain the high altitude data in the target area.
  • the above-mentioned execution main body may also be installed with other security applications, such as network quality monitoring, abnormal monitoring and repairing applications.
  • the map database 101 and the calibration server 104 may be hardware or software.
  • the map database 101 can be various electronic devices that store the required map data, including but not limited to smart phones, tablet computers, laptop computers and desktop computers or servers; when the map database 101 is software , which can be installed in the electronic devices listed above, and can be implemented as multiple software or software modules, or as a single software or software module, which is not specifically limited here.
  • the calibration server 104 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or it can be implemented as a single server; when the calibration server 104 is software, it can be implemented as multiple software or software modules, or as a A single software or software module is not specifically limited here.
  • the calibration server 104 can provide various services through various built-in applications. Taking an external parameter calibration application that can provide external parameter calibration services for the millimeter-wave radar to be calibrated as an example, the calibration server 104 is running the external parameter calibration application. The following effects can be achieved: firstly, through the network 103 to obtain the perception results of the vehicles traveling in its perception area from the millimeter-wave radar 102 through the network 103, and through the network 103 to obtain the high precision of the same area from the map database 101 map data; then, generate lane topology information under the millimeter-wave radar coordinate system according to the perception result, and generate lane line topology information under the map coordinate system according to the high-precision map data, and establish the millimeter-wave radar coordinate system and the map coordinate system. Finally, based on the preset deviation for correcting the perception accuracy error of the millimeter-wave radar, the actual parameters of the lane topology information matching the lane line topology information are determined, and the millimeter-wave radar is calibrated with the actual parameters.
  • the perception results and high-precision map data of the millimeter-wave radar can be obtained from the millimeter-wave radar 102 and the map database 101 in real time, and can also be pre-stored locally in the calibration server 104 in various ways. Therefore, when the server 105 detects that such data has been stored locally (for example, a pending calibration task retained before starting processing), it can choose to obtain the data directly from the local, in which case the exemplary system architecture 100 may not Including millimeter wave radar 102 , map database 101 and network 104 .
  • the methods for calibrating millimeter-wave radars provided by the subsequent embodiments of the present disclosure are generally performed by the calibration server 104 with strong computing power and more computing resources.
  • the apparatus for calibrating millimeter-wave radars is also generally set in the calibration server 104 .
  • map databases millimeter wave radars, networks, and calibration servers in FIG. 1 are merely illustrative. There can be any number of map databases, millimeter-wave radars, networks, and calibration servers depending on implementation needs.
  • FIG. 2 is a flowchart of a method for calibrating a millimeter-wave radar according to an embodiment of the present disclosure, wherein the process 200 includes the following steps:
  • Step 201 Generate lane topology information in the millimeter-wave radar coordinate system according to the perception result of the millimeter-wave radar on the vehicle traveling in the target area;
  • Millimeter wave radar is a radar that works in the millimeter wave band (millimeter wave). Usually millimeter wave refers to the 30-300GHz frequency domain (wavelength is 1-10mm). The wavelength of millimeter wave is between microwave and centimeter wave, so millimeter wave radar has some advantages of microwave radar and photoelectric radar. Compared with optical seekers such as infrared, laser, and TV, the millimeter-wave seeker has a strong ability to penetrate fog, smoke, and dust, and has the characteristics of all-weather (except heavy rain) all day. In addition, the anti-interference of the millimeter-wave seeker can distinguish and identify small targets, and can identify multiple targets at the same time, which not only has the imaging ability but also has the advantages of small size.
  • millimeter-wave radar In the present disclosure, the above-mentioned advantages of millimeter-wave radar are used, and it is applied in the vehicle-road coordination scenario to perceive the vehicle's driving trajectory in the area, so as to realize intelligent transportation with the assistance of big data. It should be understood that the manufacturer will calibrate the internal parameters of the hardware such as millimeter-wave radar when it is produced, and the internal parameters are irrelevant to the specific application scenario. The external parameters are calibrated in various situations of practical application scenarios to improve the perception accuracy in practical application scenarios.
  • the object to be calibrated in this disclosure is the external parameters of the millimeter-wave radar.
  • technicians perform a series of adjustments on the spot, and the most suitable parameters are determined before the calibration.
  • the cost of manpower and material resources is high, and the conventional adjustment method
  • the accuracy is also relatively rough, which cannot meet the accuracy requirements of vehicle-road collaboration scenarios.
  • This step is aimed at generating a lane in the millimeter-wave radar coordinate system by the execution body of the method for calibrating the millimeter-wave radar (for example, the server 105 shown in FIG. 1 ) according to the perception result of the millimeter-wave radar on the vehicle traveling in the target area topology information.
  • the millimeter-wave radar Similar to lidar, the millimeter-wave radar also determines the position information of the object that reflects the radio frequency signal by receiving the radio frequency signal. Therefore, the millimeter-wave radar perceives each position point at each moment, which describes the position point. The distance from the millimeter-wave radar itself, and the "string" of the position points at each moment, the trajectory information of the object can be obtained.
  • the object is usually a vehicle or a pedestrian, and when the vehicle is the main target, it can be understood that the driving trajectory of most vehicles follows the traffic rules, that is, within the required lane range ( The lane range is determined by the lane lines on the left and right sides), so through a large amount of accumulated vehicle trajectory information, the lane range can also be roughly and roughly determined.
  • the present disclosure specifically depicts it as consisting of points and lines Constitute topology information.
  • Step 202 generate lane line topology information in the map coordinate system according to the map data of the target area;
  • this step is aimed at generating the lane line topology information in the map coordinate system by the above-mentioned execution subject according to the map data of the target area.
  • the current map data is generally more accurate, especially compared to the general lane topology information determined based on the trajectory information before the external parameters of the millimeter-wave radar are calibrated. Therefore, in order to calibrate the external parameters of the millimeter-wave radar.
  • the lane line topology information determined based on the high-precision map data is used as accurate information, and the accurate lane line topology information is expected to be used to complete the calibration of the external parameters of the millimeter wave radar.
  • the millimeter-wave radar coordinates describing the lane topology information and the map coordinate system describing the lane line topology information should be established separately based on the same system establishment method, that is, the two coordinate systems follow the same coordinates.
  • the system establishment method is used to prevent the difficulty of subsequent matching caused by the coordinate system establishment method.
  • the millimeter-wave radar coordinate system and the map coordinate system can be established by various system establishment methods, such as any one of a polar coordinate system, a plane rectangular coordinate system, a spatial rectangular coordinate system, and a Cartesian coordinate system.
  • Step 203 Based on the preset deviation, determine the actual parameters of the lane topology information matching the lane line topology information, and use the actual parameters to calibrate the millimeter wave radar.
  • this step aims to determine the actual parameters of the lane topology information matching the lane line topology information by the above-mentioned executive body, so as to calibrate the external parameters of the millimeter-wave radar based on the calculated actual parameters. Since the perception accuracy of the millimeter-wave radar for which the external parameters have not been calibrated is limited, this step also helps to determine the actual parameters based on the deviation used to correct the perception accuracy error of the millimeter-wave radar, in order to improve the accuracy of the actual parameters finally determined.
  • the perception result of the millimeter-wave radar in the same area and the high-precision map data are used as two kinds of input data, and then the relevant topology information describing the lane is generated in the respective coordinate systems, and the In the case of ensuring that the two coordinate systems are constructed in the same way, the external parameters of the millimeter-wave radar can be accurately calibrated through the corresponding relationship of the topological structures in different coordinate systems, so that the millimeter-wave radar can be used as a roadside sensor. It can also meet the requirements for perception accuracy in vehicle-road collaboration scenarios.
  • step 201-step 202 the present disclosure also provides a specific example here for establishing a system based on polar coordinates:
  • the millimeter-wave radar-polar coordinate system is established according to the method of establishing the polar coordinate system;
  • step 201 will be changed to: generate lane topology information in the millimeter-wave radar-polar coordinate system according to the perception result of the millimeter-wave radar on the vehicle traveling in the target area;
  • step 202 will be changed to: generate lane line topology information in the map-polar coordinate system according to the map data of the target area.
  • the system establishment method of the polar coordinate system is more in line with the working characteristics of the millimeter-wave radar, so the effect of the polar coordinate system is better.
  • FIG. 3 is a flowchart of another method for calibrating a millimeter-wave radar according to an embodiment of the present disclosure, wherein the process 300 includes the following steps:
  • Step 301 Acquire the trajectory of the vehicle traveling in the target area perceived by the millimeter-wave radar at each moment;
  • Step 302 Accumulate the sensed vehicle trajectories at each moment to obtain a vehicle trajectory accumulation map
  • Step 303 In the millimeter wave radar coordinate system, generate lane topology information according to the vehicle trajectory accumulation map;
  • the embodiment of the present disclosure provides a specific implementation manner through steps 301 to 303, that is, by accumulating the information of vehicle trajectories perceived by the millimeter-wave radar at each moment, an accumulated vehicle trajectory graph is obtained, and then the vehicle trajectories are accumulated.
  • the trajectory accumulation map describes the lane topology information in the millimeter-wave radar coordinate system.
  • Step 304 Generate lane line topology information in the map coordinate system according to the map data of the target area;
  • step 202 shown in FIG. 2 This step is the same as step 202 shown in FIG. 2 , and for the same part, please refer to the corresponding part of the previous embodiment, which will not be repeated here.
  • Step 305 Determine the second deviation based on the real trajectory of the vehicle traveling in the target area, and calculate the actual parameters that make the lane topology information and the lane line topology information be in a preset matching position;
  • this step is to calculate the actual parameters that make the lane topology information and the lane line topology information be in the preset matching position on the basis that the above-mentioned execution body determines the second deviation based on the real trajectory.
  • the real trajectory of the vehicle can be acquired by the position sensor set on the vehicle.
  • the actual trajectory of the vehicle is calculated to be the same as the vehicle perceived by the millimeter-wave radar.
  • the amount of deviation between trajectories; then, this deviation is used to correct the lane topology generated by the trajectories perceived by the mmWave radar.
  • the conversion relationship between the two topological structures is calculated, and the external parameter calibration of the millimeter-wave radar can be completed.
  • Step 306 Use the actual parameters to calibrate the millimeter-wave radar.
  • the first deviation determined based on the installation position of the millimeter-wave radar can also be used or combined to achieve the same, similar or better correction effect.
  • millimeter-wave radar in the vehicle-road collaboration scenario depends on the acquisition of the parameters of the millimeter-wave radar itself.
  • the calibration work is to obtain the own parameters of the millimeter-wave radar.
  • This embodiment is designed according to the real-time data characteristics of millimeter-wave radars used in traffic scenarios and the data characteristics of intersections, and includes three parts: 1) data collected by road section equipment and high-precision maps; 2) topology structure extraction; 3) Radar calibration algorithm, discussed separately below:
  • the millimeter-wave radar In the vehicle-road collaboration scenario, in some places, when the millimeter-wave radar is newly installed, due to the inconsistency of the construction period and the coordination of various units, the coordinates of the sensor cannot be determined in time. At this time, the only condition may be to give a high-precision map of a certain road section, and then obtain some basic information about the obstacles perceived by the radar after the power is connected to the network. At this time, the input data required to complete the calibration is a high-precision map, and the millimeter-wave radar set on the roadside to be calibrated senses the state of vehicles passing through its sensing area. The collection of the above input data does not need to be present at the scene;
  • the millimeter-wave radar coordinate system and the high-precision map coordinate system are both established based on polar coordinates.
  • optimization methods can be used to convert polar coordinates of high-precision map lane line topology, millimeter-wave radar
  • the lane topology is optimized to the best matching position. Based on the parameters corresponding to the best matching position, the external parameter calibration of the millimeter-wave radar is completed.
  • the actual trajectory of the vehicle is calculated to be the same as the vehicle perceived by the millimeter-wave radar.
  • the amount of deviation between trajectories; then, this deviation is used to correct the lane topology generated by the trajectories perceived by the mmWave radar.
  • the conversion relationship between the two topological structures is calculated, and the external parameter calibration of the millimeter-wave radar can be completed.
  • the calibration parameters of the millimeter-wave radar can be easily obtained.
  • the solution is safe and easy to use.
  • the information processing formula can be:
  • frame map_radar is the point density map of the accumulated driving trajectory
  • acc(*) represents the accumulation method in the historical window
  • It is an estimation and classification strategy to remove abnormal trajectories, ultra-short trajectories, etc.
  • trace set_radar represents the trajectory of radar input.
  • R and T are the final optimized radar parameters
  • cluster size is a measure of the aggregated clusters of lane lines in polar coordinates.
  • the present disclosure provides an embodiment of an apparatus for calibrating a millimeter-wave radar, and the apparatus embodiment corresponds to the method embodiment shown in FIG. 2 .
  • the device can be specifically applied to various electronic devices.
  • the apparatus 400 for calibrating a millimeter-wave radar in this embodiment may include: a lane topology information generating unit 401 , a lane line topology information generating unit 402 , and a calibration parameter calculating unit 403 .
  • the lane topology information generating unit 401 is configured to generate lane topology information in the millimeter-wave radar coordinate system according to the perception result of the millimeter-wave radar on the vehicle driving in the target area; the lane line topology information generating unit 402 is configured to According to the map data of the target area, the lane line topology information is generated in the map coordinate system; wherein, the millimeter-wave radar coordinate system and the map coordinate system are constructed in the same way; the calibration parameter calculation unit 403 is configured to be based on a preset deviation amount , determine the actual parameters that the lane topology information matches the lane line topology information, and use the actual parameters to calibrate the millimeter-wave radar.
  • the lane topology information generating unit 401 in the apparatus 400 for calibrating a millimeter-wave radar: the lane topology information generating unit 401 , the lane line topology information generating unit 402 , and the calibration parameter calculating unit 403
  • the specific processing and the technical effects brought by them can be respectively Reference is made to the related descriptions of steps 201-203 in the embodiment corresponding to FIG. 2, which are not repeated here.
  • the lane topology information generating unit 401 may be further configured to:
  • the lane topology information is generated according to the vehicle trajectory accumulation map.
  • the calibration parameter calculation unit 403 may include a parameter calculation subunit configured to determine that the lane topology information matches the actual parameters of the lane line topology information, and the parameter calculation subunit is further configured to :
  • the calibration parameter calculation unit 403 may include a deviation quantum unit configured to be based on a preset deviation amount, and the deviation quantum unit is further configured to:
  • the second deviation amount is determined based on the actual trajectory of the vehicle traveling in the target area.
  • the system establishment method adopted by the millimeter-wave radar coordinate system and the map coordinate system is any one of the following:
  • Polar coordinate system plane Cartesian coordinate system, space Cartesian coordinate system, Cartesian coordinate system.
  • the device 400 for calibrating a millimeter-wave radar also includes:
  • the millimeter-wave radar-polar coordinate system establishment unit is configured to take the installation position of the millimeter-wave radar as the origin of the coordinate system, and establish the millimeter-wave radar-polar coordinate system according to the system establishment method of polar coordinates;
  • the map-polar coordinate system establishing unit is configured to obtain the map reference point of the preset map, and establish the map-polar coordinate system according to the method of establishing the polar coordinate system;
  • the lane topology information generating unit is further configured to:
  • the lane line topology information generating unit is further configured to:
  • the lane line topology information is generated in the map-polar coordinate system.
  • This embodiment exists as a device embodiment corresponding to the above method embodiment.
  • the perception result of the millimeter-wave radar in the same area and the high-precision map data are used as two kinds of input data, and then the It generates relevant topology information describing the lanes in their respective coordinate systems.
  • the external parameters of the millimeter-wave radar can be checked through the corresponding relationship between the topology structures in different coordinate systems. The more accurate calibration enables the use of millimeter-wave radar as a roadside sensor to meet the requirements for perception accuracy in vehicle-road collaboration scenarios.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product, and a roadside device.
  • FIG. 5 shows a schematic block diagram of an example electronic device 500 that may be used to implement embodiments of the present disclosure.
  • Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 500 includes a computing unit 501 that can be executed according to a computer program stored in a read only memory (ROM) 502 or loaded from a storage unit 508 into a random access memory (RAM) 503 Various appropriate actions and handling. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored.
  • the computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504.
  • An input/output (I/O) interface 505 is also connected to bus 504 .
  • Various components in the device 500 are connected to the 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, an optical disk, etc. ; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 509 allows the device 500 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.
  • Computing unit 501 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of computing units 501 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various specialized artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the computing unit 501 performs the various methods and processes described above, such as the method for calibrating a millimeter-wave radar.
  • a method for calibrating a millimeter-wave radar may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 508 .
  • part or all of the computer program may be loaded and/or installed on device 500 via ROM 502 and/or communication unit 509 .
  • the computer program When the computer program is loaded into RAM 503 and executed by computing unit 501, one or more steps of the above-described method for calibrating a millimeter-wave radar may be performed.
  • the computing unit 501 may be configured by any other suitable means (eg, by means of firmware) to perform the method for calibrating a millimeter-wave radar.
  • the roadside device may include, in addition to the electronic device, a communication component and the like, and the electronic device may be integrated with the communication component, or may be provided separately.
  • the electronic device can acquire data such as pictures and videos from the sensing device (such as a roadside camera, which may also be called a roadside camera), so as to perform image and video processing and data calculation.
  • the electronic device itself may also have a perceptual data acquisition function and a communication function, such as an AI camera, and the electronic device may directly perform image and video processing and data calculation based on the acquired perceptual data.
  • Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC systems on chips system
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that
  • the processor which may be a special purpose or general-purpose programmable processor, may 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 an output device.
  • Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer.
  • a display device eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or trackball
  • Other kinds 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 (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.
  • the systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
  • a computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, also known as a cloud computing server or a cloud host. It is a host product in the cloud computing service system to solve the management difficulties in traditional physical host and virtual private server (VPS, Virtual Private Server) services. Large, weak business expansion defects.
  • VPN Virtual Private Server
  • the perception result of the millimeter-wave radar in the same area and the high-precision map data are used as two kinds of input data, and then the relevant topology information describing the lane is generated in the respective coordinate systems, and the In the case of ensuring that the two coordinate systems are constructed in the same way, the external parameters of the millimeter-wave radar can be accurately calibrated through the corresponding relationship of the topological structures in different coordinate systems, so that the millimeter-wave radar can be used as a roadside sensor. It can also meet the requirements for perception accuracy in vehicle-road collaboration scenarios.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种用于标定毫米波雷达的方法、装置、电子设备、路侧设备、计算机可读存储介质及计算机程序产品，该方法包括：根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息（201）；根据目标区域的地图数据，在地图坐标系下生成车道线拓扑信息，毫米波雷达坐标系与地图坐标系的建系方式相同（202）；基于预设的偏差量，确定车道拓扑信息匹配于车道线拓扑信息的实际参数，利用实际参数标定毫米波雷达（203）。应用该方法不仅可以无需标定人员到现场进行标定，同时也提升了标定精度，满足车路协同场景对精度的要求。

Description

用于标定毫米波雷达的方法、装置、电子设备及路侧设备
本专利申请要求于2021年4月9日提交的、申请号为202110384091.3、发明名称为“用于标定毫米波雷达的方法、装置、电子设备及路侧设备”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本公开涉及数据处理技术领域，具体涉及计算机视觉、智能交通等人工智能技术领域，尤其涉及一种用于标定毫米波雷达的方法、装置、电子设备、路侧设备、计算机可读存储介质及计算机程序产品。
背景技术
车路协同是智慧交通下的一个概念。车路协同最终需要提高的是车和路的“智能化水平”，以达到安全自动行驶的目的，也可以说，车路协同的智能化是无人驾驶实现的另一种进程。而智能化的过程具体拆分开，就是覆盖车和路的智能设备升级和算法升级，其中智能设备中最重要的就是传感器。
相关技术通常采用在路侧部署激光雷达作为路侧传感器，或者仅使用部署在车上的雷达。
发明内容
本公开实施例提出了一种用于标定毫米波雷达的方法、装置、电子设备、路侧设备、计算机可读存储介质及计算机程序产品。
第一方面，本公开实施例提出了一种用于标定毫米波雷达的方法，包括：根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息；根据目标区域的地图数据，在地图坐标系下生成车道线拓扑信息；其中，毫米波雷达坐标系与地图坐标系的建系方式相同；基于预设的偏差量，确定车道拓扑信息匹配于车道线拓扑信息的 实际参数，利用实际参数标定毫米波雷达，偏差量用于修正毫米波雷达的感知精度误差。
第二方面，本公开实施例提出了一种用于标定毫米波雷达的装置，包括：车道拓扑信息生成单元，被配置成根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息；车道线拓扑信息生成单元，被配置成根据目标区域的地图数据，在地图坐标系下生成车道线拓扑信息；其中，毫米波雷达坐标系与地图坐标系的建系方式相同；标定参数计算单元，被配置成基于预设的偏差量，确定车道拓扑信息匹配于车道线拓扑信息的实际参数，利用实际参数标定毫米波雷达，偏差量用于修正毫米波雷达的感知精度误差。
第三方面，本公开实施例提供了一种电子设备，该电子设备包括：至少一个处理器；以及与至少一个处理器通信连接的存储器；其中，存储器存储有可被至少一个处理器执行的指令，该指令被至少一个处理器执行，以使至少一个处理器执行时能够实现如第一方面中任一实现方式描述的用于标定毫米波雷达的方法。
第四方面，本公开实施例提供了一种路侧设备，该路侧设备包括如第三方面所描述的电子设备。
第五方面，本公开实施例提供了一种存储有计算机指令的非瞬时计算机可读存储介质，该计算机指令用于使计算机执行时能够实现如第一方面中任一实现方式描述的用于标定毫米波雷达的方法。
第六方面，本公开实施例提供了一种包括计算机程序的计算机程序产品，该计算机程序在被处理器执行时能够实现如第一方面中任一实现方式描述的用于标定毫米波雷达的方法。
本公开实施例提供的用于标定毫米波雷达的方法、装置、电子设备、路侧设备、计算机可读存储介质及计算机程序产品，首先，根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息；依次或同时的，根据目标区域的地图数据，在地图坐标系下生成车道线拓扑信息，毫米波雷达坐标系与地图坐标系的建系方式相同；接下来，基于用于修正毫米波雷达的感知精度误差的预设的偏差量，确定车道拓扑信息匹配于车道线拓扑信息的实际参 数，利用实际参数标定毫米波雷达。
本公开所提供的技术方案中，将同区域的毫米波雷达的感知结果以及高精度的地图数据作为两种输入数据，然后将其在各自的坐标系下生成描述车道的相关拓扑信息，在保证两个坐标系建系方式相同的情况下，就可以通过不同坐标系下的拓扑结构的对应关系对毫米波雷达的外参进行较为准确的标定，进而使得在使用毫米波雷达作为路侧传感器时也能够满足车路协同场景下对感知精度的要求。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本公开的其它特征、目的和优点将会变得更明显：
图1是本公开可以应用于其中的示例性系统架构；
图2为本公开实施例提供的一种用于标定毫米波雷达的方法的流程图；
图3为本公开实施例提供的另一种用于标定毫米波雷达的方法的流程图；
图4为本公开实施例提供的一种用于标定毫米波雷达的装置的结构框图；
图5为本公开实施例提供的一种适用于执行用于标定毫米波雷达的方法的电子设备的结构示意图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。需要说明 的是，在不冲突的情况下，本公开中的实施例及实施例中的特征可以相互组合。
本公开的技术方案中，所涉及的用户个人信息的获取，存储和应用等，均符合相关法律法规的规定，采取了必要的保密措施，且不违背公序良俗。
图1示出了可以应用本公开的用于标定毫米波雷达的方法、装置、电子设备、路侧设备、计算机可读存储介质及计算机程序产品的实施例的示例性系统架构100。
如图1所示，系统架构100可以包括地图数据库101、毫米波雷达102、网络103，以及标定服务器104。网络103用以在地图数据库101和毫米波雷达102与标定服务器104之间提供通信链路的介质。网络103可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
地图数据库101存储有各区域的高精度地图数据，包括交通设施位置、车道位置等；毫米波雷达102用于通过接收反射回的毫米波段的信号确定反射物的位置信息，本公开以架设在路侧、用于感知行驶的车辆轨迹的毫米波雷达102为例；标定服务器104则用于根据分别接收到的高精度地图数据、感知结果，完成对毫米波雷达的外参标定。
上述各执行主体之间的数据采集、数据传输以及数据处理，均可以通过安装在上述各执行主体上的应用来实现，例如通过安装在地图数据库101上的地图查询类应用获取目标区域内的高精度地图数据，通过安装在标定服务器104上的标定参数计算应用实现数据的处理等。此外，对保证上述主体应用的正常运行，上述执行主体上还可以安装有其它保障类应用，例如网络质量监控、异常监控及修复等应用。
地图数据库101和标定服务器104可以是硬件，也可以是软件。当地图数据库101为硬件时，可以是存储有所需地图数据的各种电子设备，包括但不限于智能手机、平板电脑、膝上型便携计算机和台式计算机或服务器；当地图数据库101为软件时，可以安装在上述所列举的电子设备中，其可以实现成多个软件或软件模块，也可以实现成 单个软件或软件模块，在此不做具体限定。当标定服务器104为硬件时，可以实现成多个服务器组成的分布式服务器集群，也可以实现成单个服务器；当标定服务器104为软件时，可以实现成多个软件或软件模块，也可以实现成单个软件或软件模块，在此不做具体限定。
标定服务器104可以通过内置的各种应用可以提供各种服务，以可以为待标定的毫米波雷达提供外参标定服务的外参标定类应用为例，标定服务器104在运行该外参标定类应用时可实现如下效果：首先，通过网络103从毫米波雷达102处获取其在一段时间内对其感知区域内行驶的车辆的感知结果，以及通过网络103从地图数据库101处获取相同区域的高精度地图数据；然后，根据该感知结果在毫米波雷达坐标系下生成车道拓扑信息，以及根据该高精度地图数据在地图坐标系下生成车道线拓扑信息，毫米波雷达坐标系与地图坐标系的建系方式相同；最后，基于用于修正毫米波雷达的感知精度误差的预设的偏差量，确定车道拓扑信息匹配于车道线拓扑信息的实际参数，并利用实际参数标定毫米波雷达。
需要指出的是，毫米波雷达的感知结果和高精度地图数据除可以实时从毫米波雷达102和地图数据库101中获取到之外，也可以通过各种方式预先存储在标定服务器104本地。因此，当服务器105检测到本地已经存储有这些数据时(例如开始处理之前留存的待处理标定任务)，可选择直接从本地获取这些数据，在此种情况下，示例性系统架构100也可以不包括毫米波雷达102、地图数据库101和网络104。
本公开后续各实施例所提供的用于标定毫米波雷达的方法一般由拥有较强运算能力、较多运算资源的标定服务器104来执行，相应地，用于标定毫米波雷达的装置一般也设置于标定服务器104中。
应该理解，图1中的地图数据库、毫米波雷达、网络和标定服务器的数目仅仅是示意性的。根据实现需要，可以具有任意数目的地图数据库、毫米波雷达、网络和标定服务器。
请参考图2，图2为本公开实施例提供的一种用于标定毫米波雷达的方法的流程图，其中流程200包括以下步骤：
步骤201：根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息；
毫米波雷达，是工作在毫米波波段(millimeter wave)探测的雷达。通常毫米波是指30～300GHz频域(波长为1～10mm)的。毫米波的波长介于微波和厘米波之间，因此毫米波雷达兼有微波雷达和光电雷达的一些优点。与红外、激光、电视等光学导引头相比，毫米波导引头穿透雾、烟、灰尘的能力强，具有全天候(大雨天除外)全天时的特点。另外，毫米波导引头的抗干扰、还能分辨识别很小的目标，而且能同时识别多个目标，不仅具有成像能力还存在体积小的优点。
在本公开利用毫米波雷达具有的上述优点，将其应用在车路协同场景下对区域内的车辆行驶轨迹进行感知，以便在大数据辅助下实现智慧交通。应当理解的是，毫米波雷达这类硬件在生成出厂时厂家会对其内部参数进行标定，内部参数是无关于具体应用场景的，而毫米波雷达在具体部署在某个路段后，还需要结合实际应用场景的各种情况对其外参进行标定，以提升对实际应用场景下的感知精度。
本公开要标定的对象是毫米波雷达的外参，常规方式下均是由技术人员在实地进行一系列调校，确定最合适的参数后进行标定，人力物力成本较高，常规的调校方式的精度也较为粗糙，无法满足车路协同场景对精度的要求。
本步骤旨在由用于标定毫米波雷达的方法的执行主体(例如图1所示的服务器105)据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息。
类似于激光雷达，毫米波雷达也是通过对接收到的射频信号来确定反射回该射频信号的物体的位置信息，因此毫米波雷达在各时刻感知到的就是一个个位置点，该位置点描述了距毫米波雷达自身的距离，而将各时刻的位置点“串”起来，就能够得到该物体的轨迹信息。
当毫米波雷达部署在路口时，该物体通常为车辆或行人，以车辆为主要目标时，可以理解的是：大部分车辆的行驶轨迹都是遵照交通规则的，即在要求的车道范围内(车道范围由左右两侧的车道线确定)行驶，因此通过大量累加的车辆轨迹信息，也可以大体的、粗糙的确定出车道的范围， 本公开为便于描述，将其具体描绘为由点和线构成的拓扑信息。
步骤202：根据目标区域的地图数据，在地图坐标系下生成车道线拓扑信息；
在步骤201的基础上，本步骤旨在由上述执行主体根据目标区域的地图数据，在地图坐标系下生成车道线拓扑信息。
应当理解的是，当前的地图数据一般精度较高，尤其是相比于毫米波雷达在外参未进行标定前基于轨迹信息确定出的大体车道拓扑信息，因此为了对毫米波雷达的外参进行标定，本公开将基于高精度的地图数据确定出的车道线拓扑信息作为准确的信息，以期利用该准确的车道线拓扑信息来完成对毫米波雷达外参的标定。
需要说明的是，为了完成标定，描述车道拓扑信息的毫米波雷达坐标，与描述车道线拓扑信息的地图坐标系，应当基于相同的建系方式分别建立得到，即两个坐标系遵循相同的坐标系建立方式，以防止因坐标系建立方式为后续匹配带来的困难。
具体的，毫米波雷达坐标系和地图坐标系可采用多种建系方式建立得到，例如极坐标系、平面直角坐标系、空间直角坐标系、笛卡尔坐标系等坐标系的任意一种。
步骤203：基于预设的偏差量，确定车道拓扑信息匹配于车道线拓扑信息的实际参数，并利用实际参数标定毫米波雷达。
在步骤202的基础上，本步骤旨在由上述执行主体确定车道拓扑信息匹配于车道线拓扑信息的实际参数，从而基于计算出的实际参数对毫米波雷达的外参进行标定。由于外参未完成标定的毫米波雷达的感知精度有限，因此本步骤还基于用于修正毫米波雷达的感知精度误差的偏差量帮忙确定实际参数，以期提升最终确定出的实际参数的准确性。
本实施例所提供的技术方案中，将同区域的毫米波雷达的感知结果以及高精度的地图数据作为两种输入数据，然后将其在各自的坐标系下生成描述车道的相关拓扑信息，在保证两个坐标系建系方式相同的情况下，就可以通过不同坐标系下的拓扑结构的对应关系对毫米波雷达的外参进行较为准确的标定，进而使得在使用毫米波雷达作为路侧传感器时也能够满足车路协同场景下对感知精度的要求。
为加深对步骤201-步骤202实现过程的理解，本公开还在此处具体基于极坐标进行建系给出具体的例子：
以毫米波雷达的安装位置为坐标系原点，按照极坐标的建系方式建立毫米波雷达-极坐标系；
获取预设地图的地图基准点，按照极坐标的建系方式建立地图-极坐标系；
对应的，上述步骤201将变更为：根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达-极坐标系下生成车道拓扑信息；
对应的，上述步骤202将变更为：根据目标区域的地图数据，在地图-极坐标系下生成车道线拓扑信息。
区别于常规的建系方式，极坐标系的建系方式与毫米波雷达的工作特性更加符合，因此采用极坐标系效果更佳。
请参考图3，图3为本公开实施例提供的另一种用于标定毫米波雷达的方法的流程图，其中流程300包括以下步骤：
步骤301：获取毫米波雷达在各时刻感知到的行驶在目标区域内的车辆的轨迹；
步骤302：对感知到的各时刻的车辆的轨迹进行累加，得到车辆轨迹累加图；
步骤303：在毫米波雷达坐标系下，根据车辆轨迹累加图生成车道拓扑信息；
针对步骤201，本公开实施例通过步骤301-步骤303提供了一种具体的实现方式，即通过累加毫米波雷达对各时刻的感知到的车辆轨迹的信息，得到车辆轨迹累加图，然后将车辆轨迹累加图在毫米波雷达坐标系下描述车道拓扑信息。
步骤304：根据目标区域的地图数据，在地图坐标系下生成车道线拓扑信息；
本步骤与如图2所示的步骤202一致，相同部分内容请参见上一实施例的相应部分，此处不再进行赘述。
步骤305：基于行驶在目标区域内的车辆的真实轨迹确定第二偏差量，计算使车道拓扑信息与车道线拓扑信息处于预设匹配位置的实际参数；
在步骤303和步骤304的基础上，本步骤旨在由上述执行主体具体基于真实轨迹确定出第二偏差量的基础上，计算使车道拓扑信息与车道线拓扑信息处于预设匹配位置的实际参数。其中，车辆的真实轨迹可以通过设置在车辆上的位置传感器获取到。
假定毫米波雷达坐标系和地图坐标系均采用了极坐标的建系方式，那么在极坐标系下，相似的线段过同一点，在带噪声的情况下会汇聚成不同个点簇的曲线，本步骤可通过优化可将极坐标化的高精地图车道线拓扑、毫米波雷达生成车道拓扑优化到最佳匹配的位置。应当理解的是，两拓扑信息之间本身就存在对应关系，因此在两者处于最佳匹配的位置时，可以认定此时的效果为使毫米波雷达处于最合适的外参标定后的效果。
由于未完成外参标定的毫米波雷达的给出车道位置不准确，只能给出了该毫米雷达朝向的大致方位，因此本步骤通过车辆的真实轨迹计算得到与毫米波雷达所感知到的车辆轨迹之间的偏差量；接着，使用该偏差量修正毫米波雷达感知的轨迹生成的车道拓扑。最终计算两个拓扑结构之间的转换关系，即可完成毫米波雷达的外参标定。
步骤306：利用实际参数标定毫米波雷达。
应当理解的是，步骤301-步骤303所提供的具体实现方式，与通过步骤305所提供的具体实现方式之间，完全不存在因果和依赖关系，完全是针对不同的上位技术方案所给出的不同下位实现方式，完全可以与流程200所示的实施例形成不同的实施例，本实施例仅作为同时存在两个具体实现方式的优选实施例存在。
除上一实施例中步骤305所采用的基于行驶在所述目标区域内的车辆的真实轨迹确定第二偏差量，也可以换用或结合基于毫米波雷达的安装位置确定出的第一偏差量来实现相同、近似或更好的修正效果。
为加深理解，本公开还结合一个具体应用场景，给出了一种具体的实现方案：
车路协同场景毫米波雷达的使用依赖于对毫米波自身参数的获取，标定的工作就是要获得毫米波雷达自身参数。本实施例根据用于交通场景下的毫米波雷达的实时数据特性、以及结合路口的数据特性设计得到，包括三个部分：1)路段设备采集的数据以及高精地图；2)拓扑结构提取；3)雷达标定算法，下面分别展开论述：
1)路端设备采集的数据以及高精地图：
在车路协同场景中，有些地方在新安装毫米波雷达的情况下由于工期，各个单位的协同等问题的不一致，无法及时的给传感器坐标定。此时，仅有的条件可能就是给出某段路段的高精地图，然后在通电通网后能够获取雷达感知的障碍物的一些基本信息。此时，对完成标定所需的输入数据为高精度地图，设置在路侧的待标定的毫米波雷达对经过其感知区域的车辆的状态感知。上述输入数据的采集不需要到亲临现场；
2)拓扑结构提取：
根据感知到的车辆的轨迹的叠加信息(可表示为车辆轨迹信息累加图)，构建毫米波雷达坐标系下的车道拓扑信息；根据提取自高精地图的数据库的相同区域数据，构建在高精地图坐标系下的车道线拓扑信息。其中，毫米波雷达坐标系和高精地图坐标系均基于极坐标建立得到。
3)毫米波雷达的标定算法：
利用在极坐标下相似的线段过同一点，且在带噪声的情况下会汇聚成不同个点簇的曲线的特性，通过优化手段可将极坐标化的高精地图车道线拓扑、毫米波雷达车道拓扑优化到最佳匹配位置。基于最佳匹配位置对应的参数完成对毫米波雷达的外参标定。
由于未完成外参标定的毫米波雷达的给出车道位置不准确，只能给出了该毫米雷达朝向的大致方位，因此本步骤通过车辆的真实轨迹计算得到与毫米波雷达所感知到的车辆轨迹之间的偏差量；接着，使用该偏差量修正毫米波雷达感知的轨迹生成的车道拓扑。最终计算两 个拓扑结构之间的转换关系，即可完成毫米波雷达的外参标定。
通过以上两个部分的可以很方便的获得毫米波雷达的标定参数，在实际操作中该方案安全，简单易用。
为加深对毫米波雷达的标定参数的解算方案中关键步骤的理解，此处对这其进行再次展开说明：
1)在毫米波雷达标定的过程中，需要使用可靠的数据，去除噪声、误检等因素的影响，因此对雷达路侧记录的信息，信息的预处理，通过叠加雷达视角下的社会车辆的信息，获得雷达可视方向的雷达轨迹叠加点位密度图。
信息处理公式可以为：
Figure PCTCN2021135144-appb-000001
其中，frame map_radar是累加行车轨迹的点位密度图，acc(*)表征历史窗口内的累加方式，
Figure PCTCN2021135144-appb-000002
是估计归类策略，去除异常轨迹、超短轨迹等等，trace set_radar代表雷达输入的轨迹。
2)根据frame map_radar获得毫米波雷达视角下的推算车道拓扑结构radar topology，同时在高精地图中提取hd topology，然后将这两个拓扑结果以及雷达坐标原点(radar ori)放入下述参数计算公式进行优化得到雷达的R，T参数，然后对雷达的参数进行校验、修正后即可使用：(R，T)＝argminmax{cluster size(radar ori,radar topology,hd topology)}；
其中，R，T是最终优化的雷达参数，cluster size是极坐标下车道线的聚合簇的度量，当argminmax函数找到雷达估计导出的拓扑结构和高精地图的拓扑结构的最大可能匹配度同时保证整体的cluster size最小的时候即可获得最优的R，T优化结果。
进一步参考图4，作为对上述各图所示方法的实现，本公开提供了一种用于标定毫米波雷达的装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于各种电子设备中。
如图4所示，本实施例的用于标定毫米波雷达的装置400可以包括：车道拓扑信息生成单元401、车道线拓扑信息生成单元402、标定参数计算单元403。其中，车道拓扑信息生成单元401，被配置成根据毫米 波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息；车道线拓扑信息生成单元402，被配置成根据目标区域的地图数据，在地图坐标系下生成车道线拓扑信息；其中，毫米波雷达坐标系与地图坐标系的建系方式相同；标定参数计算单元403，被配置成基于预设的偏差量，确定车道拓扑信息匹配于车道线拓扑信息的实际参数，利用实际参数标定毫米波雷达。
在本实施例中，用于标定毫米波雷达的装置400中：车道拓扑信息生成单元401、车道线拓扑信息生成单元402、标定参数计算单元403的具体处理及其所带来的技术效果可分别参考图2对应实施例中的步骤201-203的相关说明，在此不再赘述。
在本实施例的一些可选的实现方式中，车道拓扑信息生成单元401可以被进一步配置成：
获取毫米波雷达在各时刻感知到的行驶在目标区域内的车辆的轨迹；
对感知到的各时刻的车辆的轨迹进行累加，得到车辆轨迹累加图；
在毫米波雷达坐标系下，根据车辆轨迹累加图生成车道拓扑信息。
在本实施例的一些可选的实现方式中，标定参数计算单元403可以包括被配置成确定车道拓扑信息匹配于车道线拓扑信息的实际参数的参数计算子单元，参数计算子单元被进一步配置成：
计算使车道拓扑信息与车道线拓扑信息处于预设匹配位置的实际参数。
在本实施例的一些可选的实现方式中，标定参数计算单元403可以包括被配置成基于预设的偏差量的偏差量子单元，偏差量子单元被进一步配置成：
基于毫米波雷达的安装位置确定第一偏差量；
和/或
基于行驶在目标区域内的车辆的真实轨迹确定第二偏差量。
在本实施例的一些可选的实现方式中，毫米波雷达坐标系和地图坐标系所采用的建系方式为以下任意一种：
极坐标系、平面直角坐标系、空间直角坐标系、笛卡尔坐标系。
在本实施例的一些可选的实现方式中，用于标定毫米波雷达的装 置400中还包括：
毫米波雷达-极坐标系建立单元，被配置成以毫米波雷达的安装位置为坐标系原点，按照极坐标的建系方式建立毫米波雷达-极坐标系；
地图-极坐标系建立单元，被配置成获取预设地图的地图基准点，按照极坐标的建系方式建立地图-极坐标系；
对应的，车道拓扑信息生成单元被进一步配置成：
根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达-极坐标系下生成车道拓扑信息；
对应的，车道线拓扑信息生成单元被进一步配置成：
根据目标区域的地图数据，在地图-极坐标系下生成车道线拓扑信息。
本实施例作为对应于上述方法实施例的装置实施例存在，本实施例所提供的技术方案中，将同区域的毫米波雷达的感知结果以及高精度的地图数据作为两种输入数据，然后将其在各自的坐标系下生成描述车道的相关拓扑信息，在保证两个坐标系建系方式相同的情况下，就可以通过不同坐标系下的拓扑结构的对应关系对毫米波雷达的外参进行较为准确的标定，进而使得在使用毫米波雷达作为路侧传感器时也能够满足车路协同场景下对感知精度的要求。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品，以及一种路侧设备。
图5示出了可以用来实施本公开的实施例的示例电子设备500的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图5所示，设备500包括计算单元501，其可以根据存储在只读存储器(ROM)502中的计算机程序或者从存储单元508加载到随 机访问存储器(RAM)503中的计算机程序，来执行各种适当的动作和处理。在RAM 503中，还可存储设备500操作所需的各种程序和数据。计算单元501、ROM 502以及RAM 503通过总线504彼此相连。输入/输出(I/O)接口505也连接至总线504。
设备500中的多个部件连接至I/O接口505，包括：输入单元506，例如键盘、鼠标等；输出单元507，例如各种类型的显示器、扬声器等；存储单元508，例如磁盘、光盘等；以及通信单元509，例如网卡、调制解调器、无线通信收发机等。通信单元509允许设备500通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
计算单元501可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元501的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元501执行上文所描述的各个方法和处理，例如用于标定毫米波雷达的方法。例如，在一些实施例中，用于标定毫米波雷达的方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元508。在一些实施例中，计算机程序的部分或者全部可以经由ROM 502和/或通信单元509而被载入和/或安装到设备500上。当计算机程序加载到RAM 503并由计算单元501执行时，可以执行上文描述的用于标定毫米波雷达的方法的一个或多个步骤。备选地，在其他实施例中，计算单元501可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行用于标定毫米波雷达的方法。
可选的，路侧设备除了包括电子设备，还可以包括通信部件等，电子设备可以和通信部件一体集成，也可以分体设置。电子设备可以获取感知设备(如路侧相机也可称为路侧摄像头)的数据，例如图片和视频等，从而进行图像视频处理和数据计算。可选的，电子设备自身也可以具备感知数据获取功能和通信功能，例如是AI相机，电子设备可以直接基于获取的感知数据进行图像视频处理和数据计算。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电 路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置 来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，又称为云计算服务器或云主机，是云计算服务体系中的一项主机产品，以解决传统物理主机与虚拟专用服务器(VPS，Virtual Private Server)服务中存在的管理难度大，业务扩展性弱的缺陷。
本实施例所提供的技术方案中，将同区域的毫米波雷达的感知结果以及高精度的地图数据作为两种输入数据，然后将其在各自的坐标系下生成描述车道的相关拓扑信息，在保证两个坐标系建系方式相同的情况下，就可以通过不同坐标系下的拓扑结构的对应关系对毫米波雷达的外参进行较为准确的标定，进而使得在使用毫米波雷达作为路侧传感器时也能够满足车路协同场景下对感知精度的要求。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。

Claims (16)

  1. 一种用于标定毫米波雷达的方法，包括：
    根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息；
    根据所述目标区域的地图数据，在地图坐标系下生成车道线拓扑信息；其中，所述毫米波雷达坐标系与所述地图坐标系的建系方式相同；
    基于预设的偏差量，确定所述车道拓扑信息匹配于所述车道线拓扑信息的实际参数，利用所述实际参数标定所述毫米波雷达；其中，所述偏差量用于修正所述毫米波雷达的感知精度误差。
  2. 根据权利要求1所述的方法，其中，所述根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息，包括：
    获取所述毫米波雷达在各时刻感知到的行驶在所述目标区域内的车辆的轨迹；
    对感知到的各时刻的车辆的轨迹进行累加，得到车辆轨迹累加图；
    在所述毫米波雷达坐标系下，根据所述车辆轨迹累加图生成所述车道拓扑信息。
  3. 根据权利要求1所述的方法，其中，所述确定所述车道拓扑信息匹配于所述车道线拓扑信息的实际参数，包括：
    计算使所述车道拓扑信息与所述车道线拓扑信息处于预设匹配位置的实际参数。
  4. 根据权利要求1所述的方法，其中，所述方法包括确定所述预设的偏差量，确定所述预设的偏差量包括：
    基于所述毫米波雷达的安装位置确定第一偏差量；
    和/或
    基于行驶在所述目标区域内的车辆的真实轨迹确定第二偏差量。
  5. 根据权利要求1所述的方法，其中，所述毫米波雷达坐标系和所述地图坐标系所采用的建系方式为以下任意一种：
    极坐标系、平面直角坐标系、空间直角坐标系、笛卡尔坐标系。
  6. 根据权利要求5所述的方法，还包括：
    以所述毫米波雷达的安装位置为坐标系原点，按照极坐标的建系方式建立毫米波雷达-极坐标系；
    获取预设地图的地图基准点，按照极坐标的建系方式建立地图-极坐标系；
    对应的，所述根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息，包括：
    根据所述毫米波雷达对所述目标区域内所行驶车辆的感知结果，在所述毫米波雷达-极坐标系下生成所述车道拓扑信息；
    对应的，所述根据所述目标区域的地图数据，在地图坐标系下生成的车道线拓扑信息，包括：
    根据所述目标区域的地图数据，在所述地图-极坐标系下生成车道线拓扑信息。
  7. 一种用于标定毫米波雷达的装置，包括：
    车道拓扑信息生成单元，被配置成根据毫米波雷达对目标区域内所行驶车辆的感知结果，在毫米波雷达坐标系下生成车道拓扑信息；
    车道线拓扑信息生成单元，被配置成根据所述目标区域的地图数据，在地图坐标系下生成车道线拓扑信息；其中，所述毫米波雷达坐标系与所述地图坐标系的建系方式相同；
    标定参数计算单元，被配置成基于预设的偏差量，确定所述车道拓扑信息匹配于所述车道线拓扑信息的实际参数，利用所述实际参数标定所述毫米波雷达；其中，所述偏差量用于修正所述毫米波雷达的感知精度误差。
  8. 根据权利要求7所述的装置，其中，所述车道拓扑信息生成单元被进一步配置成：
    获取所述毫米波雷达在各时刻感知到的行驶在所述目标区域内的车辆的轨迹；
    对感知到的各时刻的车辆的轨迹进行累加，得到车辆轨迹累加图；
    在所述毫米波雷达坐标系下，根据所述车辆轨迹累加图生成所述车道拓扑信息。
  9. 根据权利要求7所述的装置，其中，所述标定参数计算单元包括被配置成确定所述车道拓扑信息匹配于所述车道线拓扑信息的实际参数的参数计算子单元，所述参数计算子单元被进一步配置成：
    计算使所述车道拓扑信息与所述车道线拓扑信息处于预设匹配位置的实际参数。
  10. 根据权利要求7所述的装置，其中，所述标定参数计算单元包括被配置成基于预设的偏差量的偏差量子单元，所述偏差量子单元被进一步配置成：
    基于所述毫米波雷达的安装位置确定第一偏差量；
    和/或
    基于行驶在所述目标区域内的车辆的真实轨迹确定第二偏差量。
  11. 根据权利要求7所述的装置，其中，所述毫米波雷达坐标系和所述地图坐标系所采用的建系方式为以下任意一种：
    极坐标系、平面直角坐标系、空间直角坐标系、笛卡尔坐标系。
  12. 根据权利要求11所述的装置，还包括：
    毫米波雷达-极坐标系建立单元，被配置成以所述毫米波雷达的安装位置为坐标系原点，按照极坐标的建系方式建立毫米波雷达-极坐标系；
    地图-极坐标系建立单元，被配置成获取预设地图的地图基准点，按照极坐标的建系方式建立地图-极坐标系；
    对应的，所述车道拓扑信息生成单元被进一步配置成：
    根据所述毫米波雷达对所述目标区域内所行驶车辆的感知结果，在所述毫米波雷达-极坐标系下生成所述车道拓扑信息；
    对应的，所述车道线拓扑信息生成单元被进一步配置成：
    根据所述目标区域的地图数据，在所述地图-极坐标系下生成车道线拓扑信息。
  13. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-6中任一项所述的用于标定毫米波雷达的方法。
  14. 一种路侧设备，包括如权利要求13所述的电子设备。
  15. 一种存储有计算机指令的非瞬时计算机可读存储介质，所述计算机指令用于使计算机执行权利要求1-6中任一项所述的用于标定毫米波雷达的方法。
  16. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-6中任一项所述的用于标定毫米波雷达的方法。
PCT/CN2021/135144 2021-04-09 2021-12-02 用于标定毫米波雷达的方法、装置、电子设备及路侧设备 Ceased WO2022213632A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110384091.3A CN113093128A (zh) 2021-04-09 2021-04-09 用于标定毫米波雷达的方法、装置、电子设备及路侧设备
CN202110384091.3 2021-04-09

Publications (1)

Publication Number Publication Date
WO2022213632A1 true WO2022213632A1 (zh) 2022-10-13

Family

ID=76676020

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/135144 Ceased WO2022213632A1 (zh) 2021-04-09 2021-12-02 用于标定毫米波雷达的方法、装置、电子设备及路侧设备

Country Status (2)

Country Link
CN (1) CN113093128A (zh)
WO (1) WO2022213632A1 (zh)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115830268A (zh) * 2022-11-24 2023-03-21 北京百度网讯科技有限公司 用于优化感知算法的数据的获取方法、装置和存储介质
CN115856812A (zh) * 2022-11-11 2023-03-28 东风汽车集团股份有限公司 基于毫米波雷达的目标物显示方法、装置、设备、介质
CN116087894A (zh) * 2022-12-05 2023-05-09 南京慧尔视智能科技有限公司 雷达姿态检测方法、装置、电子设备以及存储介质
CN116242399A (zh) * 2023-03-09 2023-06-09 智道网联科技(北京)有限公司 车道线精度验证方法、装置、电子设备及存储介质
CN116339328A (zh) * 2023-03-17 2023-06-27 重庆长安汽车股份有限公司 数据处理方法、装置、电子设备以及车辆
CN116520265A (zh) * 2023-04-27 2023-08-01 深圳承泰科技有限公司 毫米波雷达安装角度的校准方法、系统、设备及存储介质
CN116881583A (zh) * 2023-07-26 2023-10-13 软通动力信息技术(集团)股份有限公司 一种物联网感知数据与空间模型匹配度计算方法及装置
CN118068306A (zh) * 2024-02-20 2024-05-24 三一智能装备有限公司 激光雷达在载体上安装角度的标定方法、设备和存储介质
CN118519107A (zh) * 2024-07-24 2024-08-20 江西五十铃汽车有限公司 一种雷达反射特性测试方法及系统
CN119179051A (zh) * 2024-11-08 2024-12-24 浙江中控信息产业股份有限公司 一种在快速路交通场景下多雷达原点信息自动校准的方法、系统、设备以及介质
CN119199781A (zh) * 2024-11-29 2024-12-27 山东沂蒙交通发展集团有限公司 一种基于栅格地图的路侧传感器自动联合标定方法
CN119541201A (zh) * 2024-11-20 2025-02-28 中咨泰克交通工程集团有限公司 一种基于可移动感知设备的交通事件全天候检测方法及系统
CN121208769A (zh) * 2025-11-26 2025-12-26 北京理工睿行电子科技有限公司 车载毫米波雷达安装误差自校准方法、装置、设备及介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113093128A (zh) * 2021-04-09 2021-07-09 阿波罗智联(北京)科技有限公司 用于标定毫米波雷达的方法、装置、电子设备及路侧设备
CN115797899A (zh) * 2021-09-09 2023-03-14 华为技术有限公司 一种车道线检测方法及装置
CN114567665A (zh) * 2022-01-26 2022-05-31 阿波罗智能技术(北京)有限公司 节点间通信的方法、装置、设备、介质及自动驾驶车辆
CN115963459A (zh) * 2022-12-30 2023-04-14 苏州万集车联网技术有限公司 雷达设备的配准方法、雷达设备及计算机可读存储介质
CN116188817B (zh) * 2023-01-06 2025-12-09 同济大学 一种基于图匹配的车路协同系统多传感器时空标定方法
CN116466349A (zh) * 2023-04-03 2023-07-21 北京行易道科技有限公司 一种雷达定位方法、装置、电子设备及存储介质
CN117471461B (zh) * 2023-12-26 2024-03-08 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) 一种用于车载辅助驾驶系统的路侧雷达服务装置和方法
CN121721584A (zh) * 2026-02-13 2026-03-24 频感智联(上海)科技有限公司 基于自然道路特征的车载雷达外参标定方法、设备、存储介质及程序产品

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110132305A (zh) * 2019-04-28 2019-08-16 浙江吉利控股集团有限公司 一种实时校准方法及装置
CN110660218A (zh) * 2019-09-29 2020-01-07 上海莫吉娜智能信息科技有限公司 利用毫米波雷达的高精度地图制作方法及系统
CN110850378A (zh) * 2019-11-22 2020-02-28 深圳成谷科技有限公司 一种路侧雷达设备自动校准方法和装置
US20200081092A1 (en) * 2018-09-07 2020-03-12 Samsung Electronics Co., Ltd. Method of calibrating alignment model for sensors and electronic device performing the method
CN112433203A (zh) * 2020-10-29 2021-03-02 同济大学 一种基于毫米波雷达数据的车道线形检测方法
CN112526470A (zh) * 2020-12-22 2021-03-19 北京百度网讯科技有限公司 标定雷达参数的方法和装置、电子设备、存储介质
CN112526465A (zh) * 2020-11-23 2021-03-19 北京小马慧行科技有限公司 动态标定车载毫米波雷达的方位角度安装偏差的方法
CN112558023A (zh) * 2019-09-25 2021-03-26 华为技术有限公司 传感器的标定方法和装置
CN113093128A (zh) * 2021-04-09 2021-07-09 阿波罗智联(北京)科技有限公司 用于标定毫米波雷达的方法、装置、电子设备及路侧设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007257536A (ja) * 2006-03-24 2007-10-04 Fujitsu Ltd ミリ波レーダによる道路交通監視装置
CN108694882B (zh) * 2017-04-11 2020-09-22 百度在线网络技术（北京）有限公司 用于标注地图的方法、装置和设备
CN108550269B (zh) * 2018-06-01 2021-06-11 中物汽车电子扬州有限公司 基于毫米波雷达的交通流量检测系统及其检测方法
CN109709961B (zh) * 2018-12-28 2021-12-07 百度在线网络技术（北京）有限公司 道路障碍物检测方法、装置及自动驾驶汽车
CN109870689B (zh) * 2019-01-08 2021-06-04 武汉中海庭数据技术有限公司 毫米波雷达与高精矢量地图匹配的车道级定位方法与系统
CN110793544B (zh) * 2019-10-29 2021-12-14 北京百度网讯科技有限公司 路侧感知传感器参数标定方法、装置、设备及存储介质
CN111787481B (zh) * 2020-06-17 2021-06-29 北京航空航天大学 一种基于5g的路车协调高精度感知方法
CN112578357B (zh) * 2020-12-24 2024-05-28 阿波罗智联(北京)科技有限公司 雷达标定参数的修正方法、装置、电子设备和路侧设备

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200081092A1 (en) * 2018-09-07 2020-03-12 Samsung Electronics Co., Ltd. Method of calibrating alignment model for sensors and electronic device performing the method
CN110132305A (zh) * 2019-04-28 2019-08-16 浙江吉利控股集团有限公司 一种实时校准方法及装置
CN112558023A (zh) * 2019-09-25 2021-03-26 华为技术有限公司 传感器的标定方法和装置
CN110660218A (zh) * 2019-09-29 2020-01-07 上海莫吉娜智能信息科技有限公司 利用毫米波雷达的高精度地图制作方法及系统
CN110850378A (zh) * 2019-11-22 2020-02-28 深圳成谷科技有限公司 一种路侧雷达设备自动校准方法和装置
CN112433203A (zh) * 2020-10-29 2021-03-02 同济大学 一种基于毫米波雷达数据的车道线形检测方法
CN112526465A (zh) * 2020-11-23 2021-03-19 北京小马慧行科技有限公司 动态标定车载毫米波雷达的方位角度安装偏差的方法
CN112526470A (zh) * 2020-12-22 2021-03-19 北京百度网讯科技有限公司 标定雷达参数的方法和装置、电子设备、存储介质
CN113093128A (zh) * 2021-04-09 2021-07-09 阿波罗智联(北京)科技有限公司 用于标定毫米波雷达的方法、装置、电子设备及路侧设备

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115856812A (zh) * 2022-11-11 2023-03-28 东风汽车集团股份有限公司 基于毫米波雷达的目标物显示方法、装置、设备、介质
CN115830268A (zh) * 2022-11-24 2023-03-21 北京百度网讯科技有限公司 用于优化感知算法的数据的获取方法、装置和存储介质
CN116087894A (zh) * 2022-12-05 2023-05-09 南京慧尔视智能科技有限公司 雷达姿态检测方法、装置、电子设备以及存储介质
CN116242399A (zh) * 2023-03-09 2023-06-09 智道网联科技(北京)有限公司 车道线精度验证方法、装置、电子设备及存储介质
CN116339328A (zh) * 2023-03-17 2023-06-27 重庆长安汽车股份有限公司 数据处理方法、装置、电子设备以及车辆
CN116520265A (zh) * 2023-04-27 2023-08-01 深圳承泰科技有限公司 毫米波雷达安装角度的校准方法、系统、设备及存储介质
CN116881583A (zh) * 2023-07-26 2023-10-13 软通动力信息技术(集团)股份有限公司 一种物联网感知数据与空间模型匹配度计算方法及装置
CN118068306A (zh) * 2024-02-20 2024-05-24 三一智能装备有限公司 激光雷达在载体上安装角度的标定方法、设备和存储介质
CN118519107A (zh) * 2024-07-24 2024-08-20 江西五十铃汽车有限公司 一种雷达反射特性测试方法及系统
CN119179051A (zh) * 2024-11-08 2024-12-24 浙江中控信息产业股份有限公司 一种在快速路交通场景下多雷达原点信息自动校准的方法、系统、设备以及介质
CN119541201A (zh) * 2024-11-20 2025-02-28 中咨泰克交通工程集团有限公司 一种基于可移动感知设备的交通事件全天候检测方法及系统
CN119199781A (zh) * 2024-11-29 2024-12-27 山东沂蒙交通发展集团有限公司 一种基于栅格地图的路侧传感器自动联合标定方法
CN121208769A (zh) * 2025-11-26 2025-12-26 北京理工睿行电子科技有限公司 车载毫米波雷达安装误差自校准方法、装置、设备及介质

Also Published As

Publication number Publication date
CN113093128A (zh) 2021-07-09

Similar Documents

Publication Publication Date Title
WO2022213632A1 (zh) 用于标定毫米波雷达的方法、装置、电子设备及路侧设备
KR102581429B1 (ko) 장애물을 탐지하는 방법, 장치, 전자 기기, 저장 매체 및 프로그램
CN113989450B (zh) 图像处理方法、装置、电子设备和介质
US20220215565A1 (en) Method for generating depth map, elecronic device and storage medium
CN112763995B (zh) 雷达标定方法、装置、电子设备和路侧设备
CN110793544B (zh) 路侧感知传感器参数标定方法、装置、设备及存储介质
KR20210151724A (ko) 차량 포지셔닝 방법, 장치, 전자 기기, 저장 매체 및 컴퓨터 프로그램
WO2023028774A1 (zh) 一种激光雷达的标定方法、装置及存储介质
WO2024197815A1 (zh) 一种工程机械的建图、方法、设备、及可读存储介质
CN111307166A (zh) 一种构建占据栅格地图的方法及其装置、处理设备
CN114051628B (zh) 一种确定目标对象点云集的方法及装置
CN111666876B (zh) 用于检测障碍物的方法、装置、电子设备和路侧设备
CN113920273B (zh) 图像处理方法、装置、电子设备和存储介质
WO2022237821A1 (zh) 生成交通标志线地图的方法、设备和存储介质
CN112763993A (zh) 标定雷达参数的方法和装置、电子设备、存储介质
CN115690739A (zh) 多传感器融合障碍物存在性检测方法和自动驾驶车辆
CN114419159A (zh) 相机标定方法、装置、电子设备和可读存储介质
CN113706704B (zh) 基于高精地图规划路线的方法、设备以及自动驾驶车辆
CN113177980B (zh) 用于自动驾驶的目标对象速度确定方法、装置及电子设备
CN115880353B (zh) 确定路面病害的面积的方法、装置及计算机程序产品
CN114581621B (zh) 地图数据处理方法、装置、电子设备和介质
CN113378694B (zh) 生成目标检测和定位系统及目标检测和定位的方法及装置
CN115060303A (zh) 自动驾驶车辆的传感器标定方法、装置及电子设备
CN114443679A (zh) 一种地图数据更新方法、装置、设备以及存储介质
CN113987228A (zh) 一种数据库构建方法、一种定位方法及其相关设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21935849

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21935849

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 28/02/2024)

122 Ep: pct application non-entry in european phase

Ref document number: 21935849

Country of ref document: EP

Kind code of ref document: A1