WO2022001326A1 - 数据的处理方法、装置、设备、存储介质及程序 - Google Patents

数据的处理方法、装置、设备、存储介质及程序 Download PDF

Info

Publication number
WO2022001326A1
WO2022001326A1 PCT/CN2021/089447 CN2021089447W WO2022001326A1 WO 2022001326 A1 WO2022001326 A1 WO 2022001326A1 CN 2021089447 W CN2021089447 W CN 2021089447W WO 2022001326 A1 WO2022001326 A1 WO 2022001326A1
Authority
WO
WIPO (PCT)
Prior art keywords
point cloud
cloud data
grid
missing
frame
Prior art date
Application number
PCT/CN2021/089447
Other languages
English (en)
French (fr)
Inventor
王哲
付万增
周辉
石建萍
Original Assignee
商汤集团有限公司
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 商汤集团有限公司 filed Critical 商汤集团有限公司
Priority to KR1020217042601A priority Critical patent/KR20220011735A/ko
Priority to JP2021564302A priority patent/JP2022550495A/ja
Publication of WO2022001326A1 publication Critical patent/WO2022001326A1/zh

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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/4802—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • 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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • 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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/50—Systems of measurement based on relative movement of target
    • 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
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • 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
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • 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
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/483—Details of pulse systems
    • G01S7/486—Receivers
    • G01S7/4861—Circuits for detection, sampling, integration or read-out
    • 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
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/491—Details of non-pulse systems
    • G01S7/493—Extracting wanted echo signals
    • 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
    • G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
    • G01S7/497—Means for monitoring or calibrating

Definitions

  • the present disclosure relates to the technical field of automatic driving, and in particular, to a data processing method, apparatus, device, storage medium and program.
  • LiDAR devices have been widely used in fields such as autonomous driving, UAV exploration, and map mapping due to their precise ranging capabilities.
  • various applications such as target detection and mapping have been generated; in related technologies, due to various reasons, there may be abnormal problems in the received point cloud data, and then in the abnormal point cloud data based on In the case of applications such as detection and mapping, the accuracy is low.
  • Embodiments of the present disclosure provide at least one data processing method, apparatus, device, storage medium, and program.
  • An embodiment of the present disclosure provides a data processing method, the processing method is executed by an electronic device, and the method includes:
  • the missing point cloud data result is determined; the point cloud data missing result includes the specific missing part of the point cloud data;
  • the missing result of the point cloud data prompt information is issued; wherein, the prompt information is used to indicate the abnormal type of the radar device.
  • the missing result of the point cloud data can be determined according to the multi-frame point cloud data, for example, the distance information is not collected in the point cloud data, and then according to the missing result of the point cloud data, Sending out an indication of the abnormal type of the radar device, it is convenient to timely determine that the point cloud data collected by the radar device is abnormal.
  • An embodiment of the present disclosure provides a device for processing data collected by a radar device, including:
  • an acquisition module configured to acquire multi-frame point cloud data collected by the radar device
  • a determination module configured to determine a missing point cloud data result according to the multi-frame point cloud data; the point cloud data missing result includes the specific missing part of the point cloud data;
  • the prompt module is configured to send prompt information according to the missing result of the point cloud data; wherein the prompt information is used to indicate the abnormal type of the radar device.
  • An embodiment of the present disclosure provides an electronic device, including: a processor, a memory, and a bus, where the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processing The processor and the memory communicate through a bus, and when the machine-readable instructions are executed by the processor, the steps of the processing method described above are executed.
  • An embodiment of the present disclosure provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-described processing method are executed.
  • Embodiments of the present disclosure further provide a computer program, the computer program includes computer-readable codes, and when the computer-readable codes are executed in an electronic device, the processor of the electronic device executes the code to implement the above-mentioned the steps of the processing method described.
  • the data processing method, device, device, storage medium and program provided by the embodiments of the present disclosure obtain multi-frame point cloud data collected by the radar device; determine the missing point cloud data result according to the multi-frame point cloud data;
  • the missing result of the point cloud data includes the specific missing part of the point cloud data; according to the missing result of the point cloud data, prompt information is sent; wherein the prompt information is used to indicate the abnormal type of the radar device.
  • the missing result of the point cloud data can be determined according to the multi-frame point cloud data, for example, the distance information is not collected in the point cloud data, and then according to the missing result of the point cloud data,
  • the abnormal type indicating the radar device is issued, which is convenient to timely determine the abnormality of the point cloud data collected by the radar device.
  • FIG. 1 shows a flowchart of a method for processing data collected by a radar device provided by an embodiment of the present disclosure
  • FIG. 2 shows a schematic diagram of a system architecture to which a method for processing data collected by a radar device according to an embodiment of the present disclosure can be applied;
  • FIG. 3 shows a flowchart of a method for controlling a target vehicle based on point cloud data provided by an embodiment of the present disclosure
  • FIG. 4 shows a flowchart of determining information of an obstacle provided by an embodiment of the present disclosure
  • FIG. 5 shows a flowchart of determining radar blind spot information provided by an embodiment of the present disclosure
  • FIG. 6 shows a flowchart of generating a current radar blind spot grid map provided by an embodiment of the present disclosure
  • FIG. 7A shows a schematic diagram of an optical path provided by an embodiment of the present disclosure
  • FIG. 7B shows a schematic diagram of a grid index sequence corresponding to an optical path provided by an embodiment of the present disclosure
  • FIG. 8 shows a flowchart of determining a radar blind spot provided by an embodiment of the present disclosure
  • FIG. 9 shows a schematic structural diagram of an apparatus 900 for processing data collected by a radar apparatus according to an embodiment of the present disclosure
  • FIG. 10 shows a schematic diagram of an electronic device 1000 provided by an embodiment of the present disclosure.
  • Radar devices are widely used in autonomous driving, map mapping and other fields due to their accurate ranging capabilities. For these different fields, corresponding analysis can be performed based on the point cloud data collected by radar devices. For example, for the field of autonomous driving, it can be based on The point cloud data collected by the radar device installed on the vehicle is used to detect the obstacles existing around the vehicle. The accuracy of obstacle detection depends on the accuracy of the point cloud data collected by the radar device. Therefore, whether there is any abnormality in the point cloud data collected by the radar device , which will directly affect the accuracy of the detection results based on the point cloud data, so it is urgent to provide a solution for anomaly detection for point cloud data.
  • an embodiment of the present disclosure provides a method for processing data collected by a radar device. Based on multi-frame point cloud data collected by a radar device, a missing point cloud data result, such as a point cloud, can be determined according to the multi-frame point cloud data. If the distance information is not collected in the data, then according to the missing result of the point cloud data, the abnormal type indicating the radar device is issued, which is convenient to timely determine the abnormality of the point cloud data collected by the radar device. The cloud data or the radar device is adjusted in time to obtain point cloud data with higher accuracy, thereby improving the accuracy in the case of subsequent detection based on the point cloud data.
  • the execution subject of the method for processing data collected by a radar device provided by the embodiments of the present disclosure is generally It is a computer device with a certain computing capability, for example, the computer device includes: a terminal device or a server or other processing device, and the terminal device can be a user equipment (User Equipment, UE), a mobile device, a computing device, a vehicle-mounted device, a wearable device, etc. .
  • the method for processing data collected by the radar device may be implemented by the processor calling computer-readable instructions stored in the memory.
  • a method for processing data collected by a radar device will be described in detail by taking the execution subject as a server or an electronic device as an example.
  • the processing method includes the following S101 to S103:
  • the radar device may include a lidar device, a millimeter-wave radar device, an ultrasonic radar device, etc.
  • the radar device may be set at a set position of the vehicle.
  • the radar device The included radio wave transmitter can collect point cloud data by emitting a beam of radio waves.
  • the installation position and installation angle of the radar device can be adjusted, and the arrangement angle of the radio wave transmitter of the radar device can be adjusted. Set the time interval to scan the obstacles around the vehicle to obtain point cloud data.
  • the embodiments of the present disclosure will be described by taking the radar device as a lidar device as an example.
  • the radio wave transmitter in the lidar device may be a laser diode
  • the lidar device may be a 64-line radar device, that is, the lidar device may include 64
  • a laser diode can emit 64 coplanar laser beams.
  • the 64 laser beams can be The scanning plane corresponding to each acquisition angle is perpendicular to the ground.
  • the laser diode can acquire point cloud data within a 360-degree rotation range according to the set time interval, and obtain a frame of point cloud data.
  • the radar device can collect a set of point cloud data at every 0.2 degree rotation, and form a data packet corresponding to the collection angle, and after collecting one frame of point cloud data, rotate the collected point cloud data by 360 degrees.
  • the data packet corresponding to the acquisition angle is sent to the server.
  • the missing point cloud data result includes the specific missing part of the point cloud data.
  • the server can determine the result of missing point cloud data according to the collection method when the radar device collects each frame of point cloud data, and the point cloud data corresponding to each frame of point cloud data.
  • the missing result can be normal missing. For example, if there is no obstacle within the range in a certain direction of the radar device, the point will not be collected if the radio wave transmitter in the radar device transmits the radio wave beam in this direction. Cloud data, that is, there is normal point cloud data missing, but if there are obstacles within the range in this direction, but the point cloud data is still not collected, there may be abnormal point cloud data missing results.
  • S103 according to the missing result of the point cloud data, send out prompt information; wherein, the prompt information is used to indicate the abnormal type of the radar device.
  • the embodiment of the present disclosure can analyze the abnormal type of the radar device, and based on this, it is convenient to adjust the radar device in time to obtain accurate point cloud data.
  • the missing result of the point cloud data can be determined according to the multi-frame point cloud data, for example, the distance information is not collected in the point cloud data, and then according to the point cloud data
  • FIG. 2 shows a schematic diagram of a system architecture for processing data collected by a radar device according to an embodiment of the present disclosure
  • the system architecture includes an acquisition terminal 201 , a network 202 and a prompt terminal 203 .
  • the acquisition terminal 201 and the prompting terminal 203 establish a communication connection through the network 202
  • the acquisition terminal 201 reports the multi-frame point cloud data collected by the radar device to the prompting terminal 203 through the network 202
  • the prompting terminal 203 according to the multi-frame point cloud data.
  • Cloud data determine the missing point cloud data result; the missing point cloud data result includes the specific missing part of the point cloud data; and according to the missing result of the point cloud data, obtain prompt information, and send out prompt information; wherein, the prompt information is used for Indicates the type of anomaly of the radar unit.
  • the prompting terminal 203 uploads the prompting information to the network 202 , and sends the prompting information to the obtaining terminal 201 through the network 202 .
  • the acquisition terminal 201 may include a video capture device or an image capture device
  • the prompt terminal 203 may include a visual processing device or a remote server with visual information processing capability.
  • Network 202 may employ wired or wireless connections.
  • the acquiring terminal 201 can be connected to the visual processing device through a wired connection, such as data communication through a bus; when the prompting terminal 203 is a remote server, the acquiring terminal 201 can perform data interaction with a remote server through a wireless network.
  • the acquisition terminal 201 may be a vision processing device with a collection function module, and is specifically implemented as a host with a collection function.
  • the method for processing the data collected by the radar device according to the embodiment of the present disclosure may be executed by the acquisition terminal 201 , and the above-mentioned system architecture may not include the network 202 and the prompt terminal 203 .
  • each frame of point cloud data includes 64*1800 data, where 64 represents 64 laser diodes in the lidar device , 1800 represents 1800 acquisition angles corresponding to the rotation range of the lidar device within 360 degrees (in this embodiment of the present disclosure, starting from 0.2 degrees, including 0.2 degrees, 0.4 degrees, ..., 360 degrees), these 64*1800
  • the data is mapped to a matrix of 64 rows*1800 columns, each row of data corresponds to the data collected by one laser diode at 1800 acquisition angles, and each column represents the data collected by 64 laser diodes at the corresponding acquisition angle.
  • missing data can be represented by setting identifiers or setting data , for example, it can be represented by "-", and the following can be used to detect whether there is a missing point cloud data in each frame, and the corresponding missing point cloud data result according to the row and column matrix.
  • the result of missing point cloud data includes that point cloud data corresponding to at least one radio wave transmitter of the radar device is missing;
  • determine the missing results of point cloud data including:
  • prompt information is issued, including:
  • the prompt information is used to indicate that at least one radio wave transmitter in the radar device is abnormal.
  • the laser diode corresponding to the set of row data corresponds to For example, the second row of data in the matrix is all "-", which means that the second laser diode in the lidar device has not collected point cloud data within the first duration, and it can be determined that the second laser diode in the lidar device has not collected point cloud data within the first duration.
  • the point cloud data corresponding to the two laser diodes are missing.
  • the first duration may correspond to the duration of collecting one frame of point cloud data, or may correspond to the duration of collecting multiple frames of point cloud data.
  • a corresponding prompt message can be sent to facilitate timely correction of the radio wave transmitter to obtain normal point cloud data.
  • the present disclosure it is possible to detect whether the point cloud data corresponding to the radio wave transmitter is missing, so that the faulty radio wave transmitter can be found in time, and it can be adjusted or replaced, so as to obtain a point cloud with high accuracy data.
  • the missing point cloud data result includes that the point cloud data corresponding to at least one acquisition angle is missing;
  • determine the missing results of point cloud data including:
  • each frame of point cloud data in the second duration there is point cloud data corresponding to at least one acquisition angle that does not exist, and corresponding non-existent point cloud data in each frame of point cloud data in the second duration In the case that the acquisition angles are not exactly the same, it is determined that the point cloud data corresponding to the random acquisition angle is missing;
  • prompt information is issued, including:
  • the prompt information is used to indicate that the radar device has abnormal data packet transmission.
  • the radar device as the above-mentioned lidar device as an example
  • whether there is a missing point cloud data corresponding to a random acquisition angle can be detected according to the matrix corresponding to each frame of point cloud data in the second duration.
  • Each group of column data in the matrix corresponds to an acquisition angle, and the data corresponding to the same acquisition angle will be packaged to form a data package. Therefore, the corresponding matrix of multi-frame point cloud data can be determined according to whether there is a lack of random column data. Whether the point cloud data corresponding to the random acquisition angle is missing.
  • the second duration contains three matrices.
  • the first matrix has missing column data in columns 1 to 3
  • the second matrix has missing column data in columns 7 to 11
  • the third matrix has missing data. Because the column data of the 100th to 110th columns are missing, it can be determined that the point cloud data corresponding to the random acquisition angle is missing.
  • a corresponding prompt message can be sent, so that the radar device can be corrected in time to obtain complete point cloud data, or, A missing threshold can be set, and if the proportion of missing column data reaches the missing threshold, a prompt will be given.
  • the point cloud data corresponding to each acquisition angle in the multi-frame point cloud data can be detected, so as to detect whether the radar device has abnormal data packet transmission in time, and the abnormality can be found in time, so as to facilitate timely adjustment and Improve the accuracy of point cloud data.
  • the missing point cloud data result includes that the point cloud data corresponding to at least one acquisition angle is missing;
  • determine the missing results of point cloud data including:
  • point cloud data corresponding to at least one acquisition angle does not exist, and corresponding non-existent point cloud data in each frame of point cloud data in the third duration In the case of the same acquisition angle, it is determined that the point cloud data corresponding to the specific acquisition angle is missing;
  • prompt information is issued, including:
  • the prompt information is used to indicate that the radar device has an abnormal occlusion.
  • whether there is a missing point cloud data corresponding to a specific acquisition angle can be detected according to the matrix corresponding to each frame of point cloud data in the third duration, considering that each group of column data in the matrix corresponds to one acquisition Angle, for the column data corresponding to the same acquisition angle in different frames of point cloud data, it can be regarded as the point cloud data collected by the laser diode of the lidar device at the same acquisition angle.
  • the matrix whether there is missing data in the same column to determine whether there is missing point cloud data corresponding to a specific acquisition angle.
  • the third duration contains three matrices, the first matrix is the missing column data in the first column, the second matrix is the missing column data in the first column, and the third matrix is the first column. If the column data is missing, it can be determined that the point cloud data corresponding to the specific acquisition angle corresponding to the first column is missing.
  • the radar device when it is determined that the point cloud data corresponding to a specific acquisition angle is missing, it can be determined that the radar device is blocked when the corresponding acquisition angle is selected, and corresponding prompt information can be issued to facilitate timely detection of The radar unit is adjusted in position to obtain complete point cloud data.
  • the point cloud data corresponding to each acquisition angle in the multi-frame point cloud data can be detected, so as to detect whether the radar device has an occlusion abnormality in time, and it is convenient to adjust in time when it is determined that there is an occlusion abnormality. Accuracy of cloud data.
  • determining the result of missing point cloud data includes:
  • prompt information is issued, including:
  • the prompt information is used to indicate that the radar device has an abnormal position.
  • the radar can always scan the obstacles in the surrounding environment, so a certain amount of point cloud data can be obtained.
  • the number of point cloud points in the frame point cloud data is kept within a certain range.
  • the valid point cloud data accounts for 30% to 99% of the total rated number.
  • the rated total number is 64*1800.
  • the valid point cloud data refers to the point cloud data collected when the laser beam sent by the laser diode can scan the obstacle, and the invalid point cloud data is the missing point mentioned above.
  • Cloud data such as data in the matrix by setting the identifier "-" can be called invalid point cloud data.
  • the present disclosure represents the effective point cloud data by the total number of point cloud points contained in each frame of point cloud data.
  • the total number of point cloud points contained in each frame of point cloud data A first set threshold may be set, and when it is determined that there is at least one frame of point cloud data in the multi-frame point cloud data and the total number of point cloud points included in the point cloud data is lower than the first set threshold, the at least one frame may be determined.
  • the frame point cloud data is missing, in the embodiment of the present disclosure, if the total number of point cloud points contained in each frame of point cloud data in the continuous multi-frame point cloud data is lower than the first set threshold, in this case In the disclosed embodiment, it may be determined that there are missing points in the point cloud data of consecutive multiple frames.
  • corresponding prompt information can be issued to indicate that the radar device has an abnormal position.
  • the radio wave transmitter in the radar device faces the sky, and in this case, it may not be possible to collect effective data.
  • the data of the point cloud point, by prompting, is convenient to adjust the position of the radar device in time, so as to obtain the complete point cloud data.
  • the number of point cloud points contained in each frame of point cloud data in the multi-frame point cloud data can be detected, so as to detect whether the radar device has a position abnormality in time, and give a prompt in the case of abnormality, which is beneficial to Adjust the radar device in time to improve the accuracy of the point cloud data.
  • determining the result of missing point cloud data includes:
  • prompt information is issued, including:
  • prompt information is sent; wherein, the prompt information is used to indicate that the radar device has abnormal point cloud data transmission.
  • the operating frequency of the radar device can be preset, so that the time required to collect each frame of point cloud data can be predetermined, and the set time interval can be determined correspondingly, such as the collection time of each frame of point cloud data. If it is 100ms, the transmission time interval of two adjacent frames of point cloud data is 100ms. If the collection time of each frame of point cloud data is 50ms, the transmission time interval of two adjacent frames of point cloud data is 50ms.
  • the set time interval may be equal to or slightly larger than the collection time period of each frame of point cloud data.
  • the transmission time interval between two adjacent frames of point cloud data of the radar device is greater than the set time interval, it can be determined that the radar device has abnormal point cloud data transmission.
  • corresponding prompt information can be issued to adjust or replace the radar device in time, thereby improving the accuracy of obtaining each frame of point cloud data according to the set time interval.
  • the transmission time interval of two adjacent frames of point cloud data can be used to detect whether the radar device has the problem of abnormal point cloud data transmission, which is convenient for timely adjustment in the case of abnormality, so as to improve the point cloud data. accuracy.
  • determining the missing point cloud data result according to the multi-frame point cloud data further includes:
  • each frame of point cloud data For each frame of point cloud data, project each frame of point cloud data into the set projection area according to the coordinate positions corresponding to each point cloud point in each frame of point cloud data, and generate a projection grid map corresponding to each frame of point cloud data ; Set the projection area as the area obtained by projecting the scanning area of the radar device on the ground with the radar device as the center in the radar coordinate system;
  • prompt information is issued, including:
  • prompt information is sent; wherein, the prompt information is used to prompt that each frame of point cloud data is point cloud data after coordinate system transformation.
  • the frame of point cloud data is the original point cloud data, that is, if the frame of point cloud data is based on the point cloud data in the coordinate system of the radar device, according to each point cloud in the frame of point cloud data After projecting the frame of point cloud data into the set projection area, the number of points greater than or equal to the second set threshold can be detected in the set projection area.
  • the frame point After the cloud data has undergone coordinate transformation, and then the frame of point cloud data is projected to the set projection area, the number of points detected in the set projection area will be greatly reduced, and may all be smaller than the second set threshold.
  • the point cloud data of this frame is the point cloud data after coordinate system transformation.
  • the second set threshold may be set based on the number of radio wave beams scanned to the ground in the radar device. Even if there are no obstacles around the radar device, the radio wave transmitter in the radar device Radio wave beams can be emitted to the ground, so for the original point cloud data, after projecting the frame of point cloud data to the set projection area, the number of points exceeding the set threshold can be found in the set projection area.
  • a corresponding prompt can be given to prevent errors in applying the point cloud data transformed by the coordinate system according to the original point cloud data.
  • multiple frames of point cloud data can be detected to determine whether each frame of point cloud data is point cloud data in the radar coordinate system, thereby reducing the need to convert the coordinate system-transformed point cloud data into the original point cloud data. Errors that occur when the data is applied.
  • the radar device provided by the embodiment of the present disclosure may be set on the target vehicle.
  • the processing method provided by the embodiment of the present disclosure further includes the following S201 to S203:
  • the scanning area of the radar device can be determined, so that obstacles within the set range from the target vehicle can be scanned, which is implemented in this disclosure.
  • the position information of each point constituting the outline of the obstacle in the set coordinate system can be obtained, and in this way, the outline information of the obstacle within the set range from the target vehicle can be obtained based on the point cloud data.
  • S202 Determine the radar blind spot information of the target vehicle based on the wire harness information transmitted by the radar device and the obstacle information.
  • the wire harness information may include the number of radio wave wire beams emitted by the radar device at each collection angle and the height from the ground, which may be specifically represented by a pre-established line height map.
  • the grid map of the surface area within the set distance from the target vehicle is under the bird's-eye view, and then based on the wire harness information emitted by the radar device, a line height map corresponding to the grid map is generated, wherein the line height map contains three The first two dimensions represent the row and column positions of each raster in the line height map, and the third dimension represents the number of wire bundles contained in each raster.
  • the raster also records the included The height of each harness within this grid.
  • the number of wire harnesses corresponding to each grid refers to the number of wire harnesses emitted by the radar device determined only according to the installation position, installation angle and the arrangement angle of the radar transmitter without considering the existence of obstacles in the grid.
  • the number of wire bundles injected into the grid; in this embodiment of the present disclosure, the wire bundles injected into the grid can be translated to a position where they intersect a line passing through the center point of the grid and perpendicular to the grid plane, The distance between the intersection point and the position of the center point of the grid is used as the harness height of the harness at the grid.
  • the determination of the line height map may not consider the situation of the corresponding obstacles in the grid, that is, the line height map containing the most complete wiring harness is obtained, and the line height map is determined in the later stage when the radar blind spot information is determined,
  • the original wire bundle corresponding to each grid can be provided, and the line height map can be generated as follows:
  • Adjust the internal parameters of the radar device including the preset angle of the vertical direction of the radio wave transmitter, and adjust the external parameters of the radar device, including the installation position and installation angle of the radio wave transmitter on the target vehicle.
  • the internal and external parameters of can calculate the multiple grids that the wire beam emitted by the radar device passes through, and the height of the wire beam at the grid when passing through each grid;
  • the radar blind spot information may be different. For example, for a target object with a larger volume, scanning the contour information of the target object requires more radio wave beams. At least one of the grids with fewer wire harnesses, and, at least one of the grids corresponding to the lowest wire harness height lower than the height of the target object can be used as a blind spot for this type of target object, for example, if the target object is a target object with a height of 1.6 meters , three wire bundles are required to scan the target object, and the height of each wire bundle and the ground is not higher than 1.6 meters, if there is a region where the minimum wire bundle height corresponding to all grids is higher than 1.6 meters, and, the number of effective wire bundles is insufficient At least one of the three items, the area is the blind spot for the target object of 1.6 meters during the driving process of the target vehicle.
  • a small target object such as a target object with a height of 0.8 meters
  • two wire harnesses are required to scan the target object, and the height of each wire harness and the ground is not higher than 0.8 meters. If there are all grids in an area corresponding to The minimum wiring harness height is higher than 0.8 meters, and the number of effective wiring harnesses is less than at least one of the two, then this area is the blind spot for the target object of 0.8 meters during the driving process of the target vehicle.
  • the information of the radar blind spot for the target vehicle during the driving process can be determined continuously through the information of the changing obstacles, so that the driving process of the target vehicle can be effectively carried out based on this. control, thereby reducing the probability of a collision with the target vehicle.
  • the information of the obstacles within the set range from the target vehicle is determined.
  • the following S2011 to S2013 may be included:
  • S2011 based on the point cloud data, determine the contour information of each obstacle within a set range from the target vehicle.
  • the point cloud data may include the coordinate values of each point cloud point in the vehicle body coordinate system, and based on the coordinate values of each point cloud point in the point cloud data, obstacles within a set distance from the target vehicle may be obtained
  • the outline information of the object in the vehicle body coordinate system such as the outline of a pedestrian, the outline of a vehicle, or the outline of a building.
  • the contour information of each obstacle may be represented by the size of a three-dimensional (3-dimension, 3D) bounding box corresponding to the obstacle, and the 3D bounding box may be a 3D convex polyhedron.
  • 3D three-dimensional
  • the envelope polygon line detection frame of the area corresponding to the obstacle on the ground is determined, and then along the obstacle in the direction perpendicular to the polygon line detection frame, pull Extend the polygon line detection frame until the height of the obstacle is reached, and then the 3D convex polyhedron is obtained.
  • the pre-built grid map is determined according to the shape and size of the target vehicle, the detection range of the radar on the target vehicle, and the grid resolution.
  • the grid occupied by each obstacle in the pre-built grid map can be determined through the coordinate range corresponding to the bottom area of the 3D bounding box corresponding to each obstacle in the vehicle body coordinate system,
  • the grid area occupied by the obstacle in the grid map includes 8 grids, and then based on the height of the 3D bounding box corresponding to the obstacle, it is determined that the obstacle is in the pre-built The height of the obstacle at each grid in the grid map.
  • a grid map can be constructed for the projection area on the ground of the detection range scanned by the radar on the target vehicle.
  • the projection area formed when the radar is installed on the target vehicle does not include the projection of the target vehicle on the ground.
  • the size of the grid map and The shape can be determined by the projected area, and the number of grids contained in the grid map can be determined by the preset grid resolution.
  • the grid resolution can represent the reciprocal of the side length of a single grid, and can also represent the number of grids.
  • the number of grids contained in the grid map can be determined.
  • the higher the grid resolution the smaller the size of a single grid, and the smaller the corresponding size of obstacles at each associated grid. Therefore, the closer the upper surface of the obstacle corresponding to each grid is to the plane, the more accurate it is to determine the height of the obstacle at each grid, but the more the number of grids, the lower the efficiency. Balance accuracy and efficiency to choose a reasonable grid resolution.
  • the current obstacle grid map is used to characterize information about obstacles within a set range from the target vehicle.
  • the corresponding obstacle height can be performed on each grid in the pre-built grid map. After marking, get the current obstacle grid map.
  • the information used to represent the obstacle within the set distance from the target vehicle can be obtained intuitively, so that it is convenient to determine each obstacle based on the grid map of the obstacle and the wire harness information in the embodiment of the present disclosure.
  • the grid corresponds to the height of the effective harness and the number of effective harnesses, so as to prepare for the determination of the radar blind spot information.
  • the wiring harness information includes the wiring harness height of the wiring harness transmitted by the radar in each grid in the pre-built grid map; for the above S202, based on the wiring harness information transmitted by the radar device and the information of the obstacles, Determining the radar blind spot information of the target vehicle, as shown in Figure 5, may include the following S2021 to S2022:
  • the height of the harness corresponding to each grid in the pre-built grid map can be obtained from the line height map constructed above, and then based on the height of the harness corresponding to each grid, and the height of the grid in the current obstacle grid
  • the corresponding obstacle height in the map can be used to determine the number of effective harnesses and the minimum harness height corresponding to the grid, that is, the grid map of the current radar blind area can be obtained.
  • the number of effective wire harnesses corresponding to any grid refers to the number of wire harnesses that can be injected into the grid.
  • the height of the corresponding harness at the grid is higher than the height of the obstacles in the grid; the lowest harness height corresponding to a grid refers to the harness with the lowest height among the corresponding valid harnesses in the grid.
  • the preset target object can be specifically determined in combination with the application scenario of the target vehicle. If the target vehicle is an unmanned vehicle, it mainly travels in the set track area for cargo transportation, and within the set track area The probability of pedestrians appearing is very small, and the probability of goods appearing is high, so the preset target object here can refer to the goods alone.
  • the preset target object may be children.
  • the number of effective harnesses corresponding to each grid in the current radar blind spot grid map and The minimum harness height, the number of effective harnesses and the highest harness height when the target object can be scanned is determined.
  • the minimum harness height corresponding to a grid is higher than the highest harness height that can scan the target object, then the The grid is a radar blind area relative to the target object.
  • the number of effective wiring harnesses and the minimum wiring harness height corresponding to each grid can be quickly determined, so as to obtain the current radar blind spot grid map of the target vehicle.
  • the radar blind spot information is quickly determined, so that the driving process of the target vehicle can be controlled based on the radar blind spot information in the later stage.
  • the size information of each obstacle mainly includes the projected size of the obstacle in the current obstacle grid map, as shown in Figure 7A, it contains two obstacles (recorded as obstacle A and obstacle B respectively) It can be seen that the two optical paths with the largest angle blocked by obstacle A are recorded as L1 and L2 respectively, and the two optical paths with the largest angle blocked by obstacle B are recorded as L3 and L4 respectively, Then all the optical paths located in the angle formed by L1 and L2 can be extracted here, and all the optical paths located in the angle formed by L3 and L4 can be extracted. It can be seen from FIG. 7A that the optical paths located in the angle formed by L1 and L2 Part of the optical path overlaps with the part of the optical path located in the included angle formed by L3 and L4. Here, for the overlapped optical path, only one extraction is required.
  • Each optical path corresponds to multiple wire bundles with one acquisition angle. Taking a 64-bit radar device as an example, each optical path corresponds to 64 wire bundles with one acquisition angle.
  • the angle formed by L4 includes 6 optical paths. Assuming that the angle formed by L1 and L2 and the angle formed by L3 and L4 overlap, there are two optical paths at the angle formed by L2 and L3 in Figure 7A, and this The two optical paths overlap, and only one optical path is extracted for the two overlapping optical paths, so that the updated optical path set obtained here contains 15 optical paths.
  • any one light path corresponds to The grid index sequence of is the index of each grid obtained by sequentially arranging the 20 grids in the order of the emission direction of any light path.
  • the position of each grid in the grid map on the X axis can represent the row position of the grid in the grid map
  • the position of each grid on the grid map on the Y axis can represent the grid in the grid map.
  • the row position in the raster map, the raster that any light path L passes through in the emission direction contains raster A to K, where the row position of raster A in the raster map is 7, and the column position is 6, then it can be passed through (7, 6) represents the index corresponding to the grid A.
  • the indexes of other grids passed through by any optical path L can be determined.
  • the any one can be determined The grid index sequence corresponding to the light path L.
  • each grid index sequence indicated Adjust the minimum harness height and the number of effective harnesses corresponding to each grid.
  • S20214 determine whether the minimum harness height and the number of valid harnesses corresponding to each grid in the last grid index sequence have been adjusted, if not, return to S20213, if so, execute S20215 to obtain the current radar blind spot grid map.
  • each grid index sequence For each grid index sequence, first obtain each beam associated with the optical path corresponding to the grid index sequence, and obtain the lowest beam height and the number of effective beams corresponding to the grid corresponding to the first index in the grid index sequence In the case of adjustment, you can sort all the harnesses associated with the light path in descending order of harness height, start with the lowest harness height, and compare the height of the obstacles corresponding to the grid in turn, and compare the height of the corresponding harness with the highest height.
  • the wire harness with height equal to or higher than the obstacle is regarded as the effective wire harness corresponding to the grid, and the wire harness with the corresponding wire harness height lower than the height of the obstacle is regarded as the invalid wire harness corresponding to the grid (the invalid wire harness is the wire harness blocked by the obstacle),
  • the minimum wire harness height and the number of valid wire harnesses corresponding to the grid can be adjusted, and after the adjustment is completed, the grid identified by the next index of the grid index can be adjusted until the grid index sequence is adjusted.
  • the grid map of the current radar blind area can be obtained.
  • the adjustment method can adjust each grid in sequence according to the emission direction of the wire beam, thereby providing a method for each grid.
  • the minimum wire harness height and the number of effective wire harnesses corresponding to each grid indicated by a grid index sequence can be adjusted in the following manner:
  • one grid index sequence may be any grid index sequence among multiple grid index sequences.
  • first obtain the harness that can be injected into the current grid before adjusting the effective harness corresponding to the current grid in one grid index sequence , first obtain the harness that can be injected into the current grid.
  • the harness that can be injected into the current grid can be the valid harness of the previous grid before the current grid in the grid index sequence. There is no need to compare the corresponding grid index sequence. All wiring harnesses associated with the optical path, which can improve the adjustment speed.
  • the current grid does not only correspond to a unique grid index sequence.
  • the minimum harness height and the number of effective harnesses corresponding to the current grid are adjusted.
  • the minimum harness height and the number of effective harnesses corresponding to the current grid have been saved.
  • the harness height of the effective harness of the current grid determined under the current grid is adjusted to the saved minimum harness height corresponding to the current grid; and in the harness corresponding to the grid index sequence, the number of valid harnesses corresponding to the current grid can also be adjusted based on the current grid. , to adjust the number of saved effective harnesses corresponding to the current grid.
  • the lowest harness height is taken as the The minimum harness height corresponding to the current grid; based on the number of valid harnesses corresponding to the current grid obtained during this adjustment and the number of saved valid harnesses corresponding to the current grid, the maximum number of valid harnesses corresponding to the current grid is obtained as the current grid. After the current grid is adjusted this time, the number of effective harnesses corresponding to the current grid.
  • the saved minimum harness height corresponding to the current grid may be a preset larger value.
  • the current grid corresponds to The number of saved effective harnesses can be a preset smaller value, such as 0.
  • the valid harness corresponding to the current grid After the valid harness corresponding to the current grid is obtained, the valid harness is regarded as the harness that can be injected into the next grid in the grid index sequence, so that the lowest harness height and the number of valid harnesses corresponding to the next grid are performed. In the case of adjustment, there is no need to consider the invalid harnesses corresponding to the current grid, so that the adjustment speed of the minimum harness height and the number of valid harnesses corresponding to subsequent grids can be accelerated.
  • the current grid has no valid wire bundles.
  • the next grid in the grid index sequence grid there is no incoming light in the beam associated with this light path, so there is no need to continue to adjust the minimum beam height and the number of effective beams corresponding to the subsequent grid. If the value is large, assign 0 to the valid harness corresponding to the current grid.
  • the previous grid of the grid will be filtered out.
  • the grid corresponds to the invalid harness, which can improve the adjustment speed.
  • the minimum harness height and the number of effective harnesses corresponding to each grid indicated by each grid index sequence can also be adjusted in the above-mentioned manner, and finally the current radar blind spot grid map is obtained. Also adjust each grid according to the light path emission direction.
  • the obstacle height corresponding to the grid and the beam associated with each optical path needs to be considered at the same time.
  • the contour information of the preset target object here can also be represented by the size information of the 3D bounding box corresponding to the preset target object.
  • the Frames have different numbers of effective harnesses and the highest harness height, where the highest harness height refers to the highest harness height that can scan to the preset target object, when using a harness lower than or equal to the highest harness height to scan the preset target object In this case, the preset target object corresponding to the 3D bounding box can be scanned. In the case of scanning the preset target object with a wire harness higher than the highest wire beam height, the preset target object cannot be scanned.
  • the number of effective harnesses and the minimum harness height of the preset target object scanned by the radar device can be determined.
  • the grid with the corresponding number of effective harnesses less than the number of effective harnesses scanned to the preset target object may be used as the radar blind area corresponding to the preset target object in the current radar blind area grid map;
  • the grid with the corresponding lowest beam height higher than the highest beam height scanned to the preset target object is used as the corresponding radar blind spot in the current radar blind spot grid map of the preset target object;
  • the corresponding number of effective wire beams can be less than the scanned
  • the grid of the number of effective harnesses of the preset target object, and the corresponding minimum harness height is higher than the grid with the highest harness height scanned to the preset target object, as the preset target object in the current radar blind spot grid map The corresponding radar blind spot.
  • different radar blind spots can be determined for different preset target objects, so that the radar blind spot information can be updated in time for different application scenarios, thereby effectively controlling the vehicle to avoid obstacles.
  • controlling the target vehicle according to the radar blind spot information of the target vehicle may include the following (1) to (2):
  • the radar blind area information includes the coordinate range corresponding to the boundary line of the radar blind area in the vehicle body coordinate system with the target vehicle as the origin; the current pose information of the target vehicle may include the position information and orientation information of the target vehicle , and then based on the coordinate range corresponding to the radar blind area, the distance information between the target vehicle and the radar blind area within the set range can be determined.
  • the target vehicle that is closest to the radar blind area can be determined according to the orientation of the target vehicle. side, and the separation distance.
  • the target vehicle can safely avoid the radar blind spot.
  • the change of orientation and speed can be determined.
  • it can be determined based on the safety distance level to which the distance information belongs. The safety distance level The lower it is, the closer the target vehicle is to the radar blind spot.
  • the vehicle can decelerate and drive in the original direction.
  • obstacle avoidance can be performed based on the current pose information of the target vehicle and the radar blind spot, thereby improving the driving safety of the target vehicle.
  • the writing order of each step does not mean a strict execution order but constitutes any limitation on the implementation process, and the specific execution order of each step should be based on its function and possible Internal logic is determined.
  • the embodiment of the present disclosure also provides a processing device corresponding to the method for processing the data collected by the radar device.
  • the implementation of the apparatus can refer to the implementation of the method.
  • FIG. 9 is a schematic diagram of an apparatus 900 for processing data collected by a radar apparatus according to an embodiment of the present disclosure
  • the processing apparatus 900 includes:
  • the acquisition module 901 is configured to acquire multi-frame point cloud data collected by the radar device;
  • the determining module 902 is configured to determine the missing point cloud data result according to the multi-frame point cloud data; the missing point cloud data result includes the specific missing part of the point cloud data;
  • the prompt module 903 is configured to issue prompt information according to the missing result of the point cloud data; wherein the prompt information is used to indicate the abnormal type of the radar device.
  • the result of missing point cloud data includes that point cloud data corresponding to at least one radio wave transmitter of the radar device is missing;
  • the determining module 902 is configured to, in each frame of point cloud data in the first duration, , in the case that the point cloud data corresponding to at least one radio wave transmitter does not exist, it is determined that the point cloud data corresponding to at least one radio wave transmitter is missing;
  • the prompt module 903 is configured to issue prompt information; wherein, the prompt information is used for Indicates an abnormality in at least one radio wave transmitter in the radar unit.
  • the result of missing point cloud data includes that the point cloud data corresponding to at least one acquisition angle is missing;
  • the determining module 902 is configured to, in each frame of point cloud data in the second duration, there is at least one acquisition angle The point cloud data corresponding to the angle does not exist, and in the case where the acquisition angles of the non-existent point cloud data corresponding to the point cloud data of each frame in the second duration are not exactly the same, determine the point cloud data corresponding to the random acquisition angle Missing;
  • the prompt module 903 is configured to send prompt information; wherein, the prompt information is used to indicate that the radar device has abnormal data packet transmission.
  • the result of missing point cloud data includes that the point cloud data corresponding to at least one acquisition angle is missing;
  • the determining module 902 is configured to, in each frame of point cloud data in the third duration, perform a The point cloud data corresponding to the angle does not exist, and when the acquisition angles of the non-existent point cloud data corresponding to each frame of point cloud data in the third duration are the same, it is determined that the point cloud data corresponding to the specific acquisition angle is missing;
  • the prompting module 903 is configured to send out prompting information, wherein the prompting information is used to indicate that the radar device has an abnormal occlusion.
  • the determining module 902 is configured to determine that at least one frame of point cloud data exists in the case that the total number of point cloud points included in at least one frame of point cloud data is lower than the first set threshold. There is a lack in the point cloud data; the prompting module 903 is configured to send out prompting information, wherein the prompting information is used to indicate that the radar device has an abnormal position.
  • the determining module 902 is configured to obtain the transmission time interval between two adjacent frames of point cloud data, and determine whether the transmission time interval is greater than the set time interval; the prompting module 903 is configured to determine the transmission time interval after determining the transmission time interval. When the time interval is greater than the set time interval, a prompt message will be sent; wherein, the prompt message is used to indicate that the radar device has abnormal point cloud data transmission.
  • the determining module 902 is configured to, for each frame of point cloud data, project each frame of point cloud data into the set projection area according to the coordinate positions corresponding to each point cloud point in each frame of point cloud data, Generate a projected grid map corresponding to each frame of point cloud data; set the projection area as the area obtained by projecting the scanning area of the radar device on the ground under the radar coordinate system, with the radar device as the center, and determine the projected grid map Whether the number of included points is less than the second set threshold; the prompting module 903 is configured to issue prompt information when it is determined that the number of points is less than the second set threshold; wherein, the prompt information is used to prompt that each frame of point cloud data is after The point cloud data after coordinate system transformation.
  • the processing device 900 further includes a control module 904, the control module 904 is configured to, in response to that the point cloud data is not missing, determine the information of the obstacles within the set range from the target vehicle based on the point cloud data; the radar The device is arranged on the target vehicle; based on the wire harness information transmitted by the radar device and the information of obstacles, the radar blind spot information of the target vehicle is determined; the target vehicle is controlled according to the radar blind spot information of the target vehicle.
  • control module 904 is configured to, based on the point cloud data, determine the contour information of each obstacle within a set range from the target vehicle; The height of obstacles at each grid in the map; based on the height of the obstacles, the current grid map of obstacles is obtained, and the current grid map of obstacles is used to represent the information of obstacles within the set range from the target vehicle.
  • the wire harness information includes the wire harness height of the wire harness emitted by the radar in each grid in the pre-built grid map; the control module 904 is configured to be based on each grid in the pre-built grid map.
  • the height of the wire harness corresponding to the grid and the current obstacle grid map are used to determine the current radar blind spot grid map; based on the current radar blind spot grid map and the outline information of the preset target object, the target vehicle is determined for the preset target object.
  • the radar blind spot information includes the wire harness height of the wire harness emitted by the radar in each grid in the pre-built grid map; the control module 904 is configured to be based on each grid in the pre-built grid map.
  • the height of the wire harness corresponding to the grid and the current obstacle grid map are used to determine the current radar blind spot grid map; based on the current radar blind spot grid map and the outline information of the preset target object, the target vehicle is determined for the preset target object.
  • the radar blind spot information includes the wire harness height of the wire harness emitted
  • control module 904 is configured to extract, based on the size information of the obstacles contained in the current obstacle grid map and the optical path information obtained by projecting the wire beam emitted by the radar device on the current obstacle grid map,
  • the optical path blocked by any obstacle gets the updated optical path set; for each optical path in the updated optical path set, along the emission direction of the optical path, determine the grid index sequence corresponding to the optical path, and the grid index sequence indicates that multiple
  • the grids are sorted according to the order of the light path emission direction to obtain the index of each grid; for each grid index sequence, the height of each beam at each grid and the height of each beam associated with the beam path corresponding to the grid index sequence are obtained.
  • the height of the obstacle corresponding to the grid adjust the minimum harness height and the number of valid harnesses corresponding to each grid indicated by the grid index sequence until the lowest harness corresponding to each grid in the last grid index sequence is adjusted. After the height and the number of effective harnesses, the grid map of the current radar blind area is obtained.
  • control module 904 is configured to, for the current grid in a grid index sequence, sequentially compare the height of each harness corresponding to the grid index sequence in the current grid with the height corresponding to the current grid the height of the obstacle, the harness whose height is higher than the obstacle height is regarded as the effective harness corresponding to the current grid; the minimum harness height of the current grid is adjusted based on the harness height of the effective harness corresponding to the current grid; In the harnesses corresponding to the grid index sequence, the number of effective harnesses corresponding to the current grid is adjusted; the number of effective harnesses corresponding to the current grid is adjusted; the effective harnesses corresponding to the current grid are used as the input to the next grid in the grid index sequence.
  • Grid take the next grid as the current grid, and continue to perform the steps of adjusting the minimum harness height and the number of valid harnesses corresponding to the current grid, until the harness height of each harness entering the current grid is low In the case of the obstacle height corresponding to the current grid, the minimum harness height and the number of valid harnesses corresponding to each grid in the grid index after this adjustment are obtained.
  • control module 904 is configured to, based on the contour information of the preset target object, determine the number of effective harnesses and the highest harness height that the radar device scans to the preset target object; based on the current radar blind spot grid map, each The number of effective harnesses corresponding to each grid and the number of effective harnesses scanned to the preset target object, and, at least one of the minimum harness height corresponding to each grid and the highest harness height scanned to the preset target object, determine the preset target. Set the radar blind spot corresponding to the target object in the current radar blind spot grid map.
  • an embodiment of the present disclosure further provides an electronic device 1000 .
  • the schematic structural diagram of the electronic device 1000 provided by the embodiment of the present disclosure includes:
  • Embodiments of the present disclosure further provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, data collected by the radar device described in the foregoing method embodiment is executed steps of the processing method.
  • the storage medium may be a volatile or non-volatile computer-readable storage medium.
  • the computer program product of the method for processing data collected by the radar device includes a computer-readable storage medium storing program codes, and the instructions included in the program codes can be used to execute the methods described in the foregoing method embodiments.
  • the steps of the method for processing the data collected by the radar device reference may be made to the foregoing method embodiments.
  • Embodiments of the present disclosure also provide a computer program, which implements any one of the methods in the foregoing embodiments when the computer program is executed by a processor.
  • the computer program product can be specifically implemented by hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), etc. Wait.
  • a computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), Erase programmable read only memory (Electrical Programmable Read Only Memory, EPROM) or flash memory, static random access memory (Static Random-Access Memory, SRAM), portable compact disk read only memory (Compact Disc Read-Only Memory, CD- ROM), Digital Video Disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or raised structures in grooves on which instructions are stored, and any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read-only memory
  • EPROM Erase programmable read only memory
  • EPROM Electrical Programmable Read Only Memory
  • flash memory static random access memory
  • SRAM static random access memory
  • portable compact disk read only memory Compact Disc Read-Only Memory
  • CD- ROM Compact Disc Read-Only Memory
  • DVD Digital Video Disc
  • memory sticks floppy disks
  • mechanical encoding devices such as punch cards or raised structures
  • Computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.
  • the computer readable program instructions described herein may be downloaded to various computing/processing devices from computer readable storage media, or to external computers or external storage devices over networks such as the Internet, local area networks, wide area networks, and wireless networks.
  • the network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer-readable program instructions from a network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .
  • Computer program instructions for performing operations of embodiments of the present disclosure may be assembly instructions, Industry Standard Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or in a form of Source or object code in any combination of programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as the "C" language or similar programming language.
  • the computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement.
  • the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or Wide Area Network (WAN), or may be connected to an external computer (eg, using Internet service provider to connect via the Internet).
  • LAN Local Area Network
  • WAN Wide Area Network
  • electronic circuits such as programmable logic circuits, FPGAs, or Programmable Logic Arrays (PLAs), that can execute computer-readable
  • the program instructions are read to implement various aspects of the embodiments of the present disclosure.
  • the units described as separate components may or may not be physically separated, and components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the technical solutions provided by the embodiments of the present disclosure are essentially or contribute to the prior art or parts of the technical solutions may be embodied in the form of software products, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present disclosure.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .
  • Embodiments of the present disclosure provide a data processing method, device, device, storage medium, and program, wherein the processing method is executed by an electronic device, and the method includes: acquiring multi-frame point cloud data collected by the radar device; According to the multi-frame point cloud data, the missing point cloud data result is determined; the point cloud data missing result includes the specific missing part of the point cloud data; according to the missing point cloud data result, a prompt message is issued; wherein, The prompt information is used to indicate the abnormal type of the radar device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Electromagnetism (AREA)
  • Traffic Control Systems (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Image Analysis (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Optical Radar Systems And Details Thereof (AREA)

Abstract

一种数据的处理方法、装置、设备、存储介质及程序，其中，该处理方法由电子设备执行，方法包括：获取雷达装置采集的多帧点云数据（S101）；根据多帧点云数据，确定点云数据缺失结果，点云数据缺失结果包括点云数据的具体缺失部分（S102）；根据点云数据的缺失结果，发出提示信息，其中，提示信息用于指示雷达装置的异常类型（S103）。该方法能够根据雷达装置采集的多帧点云数据确定点云数据缺失结果，能够及时确定雷达装置采集的点云数据存在异常，进而能够提高在基于点云数据进行后续检测时的准确度。

Description

数据的处理方法、装置、设备、存储介质及程序
相关申请的交叉引用
本专利申请要求2020年6月30日提交的中国专利申请号为202010619847.3、申请人为商汤集团有限公司，申请名称为“雷达装置采集的数据的处理方法及处理装置”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
本公开涉及自动驾驶技术领域，具体而言，涉及一种数据的处理方法、装置、设备、存储介质及程序。
背景技术
近年来，激光雷达装置以其精确的测距能力，被广泛用于自动驾驶、无人机勘探以及地图测绘等领域。基于激光雷达提供的点云数据，产生了如目标检测、建图等各类应用；而相关技术中，由于种种原因，接收到的点云数据可能存在异常问题，进而在基于异常的点云数据进行检测、建图等应用的情况下，准确度较低。
发明内容
本公开实施例至少提供一种数据的处理方法、装置、设备、存储介质及程序。
本公开实施例提供了一种数据的处理方法，所述处理方法由电子设备执行，所述方法包括：
获取所述雷达装置采集的多帧点云数据；
根据所述多帧点云数据，确定点云数据缺失结果；所述点云数据缺失结果包括所述点云数据的具体缺失部分；
根据所述点云数据的缺失结果，发出提示信息；其中，所述提示信息用于指示所述雷达装置的异常类型。如此，基于雷达装置采集的多帧点云数据，能够根据该多帧点云数据确定点云数据缺失结果，比如点云数据中未采集到距离信息的情况，然后根据点云数据的缺失结果，发出指示雷达装置的异常类型，便于及时确定雷达装置采集的点云数据存在异常，示例性地，方便对存在异常的点云数据或者雷达装置进行及时进行调整，以便得到准确度较高的点云数据，从而提高在基于点云数据进行后续检测的情况下的准确度。
以下装置、电子设备等的效果描述参见上述方法的说明。
本公开实施例提供了一种雷达装置采集的数据的处理装置，包括：
获取模块，配置为获取所述雷达装置采集的多帧点云数据；
确定模块，配置为根据所述多帧点云数据，确定点云数据缺失结果；所述点云数据缺失结果包括所述点云数据的具体缺失部分；
提示模块，配置为根据所述点云数据的缺失结果，发出提示信息；其中，所述提示信息用于指示所述雷达装置的异常类型。
本公开实施例提供了一种电子设备，包括：处理器、存储器和总线，所述存储器存储有所述处理器可执行的机器可读指令，在所述电子设备运行的情况下，所述处理器与所述存储器之间通过总线通信，所述机器可读指令被所述处理器执行的情况下执行上述所述的处理方法的步骤。
本公开实施例提供了一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行的情况下执行如上述所述的处理方法的步骤。
本公开实施例还提供一种计算机程序，所述计算机程序包括计算机可读代码，在所述计算机可读代码在电子设备中运行的情况下，所述电子设备的处理器执行用于实现上述所述的处理方法的步骤。
本公开实施例提供的数据的处理方法、装置、设备、存储介质及程序，获取所述雷达装置采集的多帧点云数据；根据所述多帧点云数据，确定点云数据缺失结果；所述点云数据缺失结果包括所述点云数据的具体缺失部分；根据所述点云数据的缺失结果，发出提示信息；其中，所述提示信息用于指示所述雷达装置的异常类型。如此，基于雷达装置采集的多帧点云数据，能够根据该多帧点云数据确定点云数据缺失结果，比如点云数据中未采集到距离信息的情况，然后根据点云数据的缺失结果，发出指示雷达装置的异常类型，便于及时确定雷达装置采集的点云数据存在异常。
为使本公开的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
为了更清楚地说明本公开实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，此处的附图被并入说明书中并构成本说明书中的一部分，这些附图示出了符合本公开的实施例，并与说明书一起用于说明本公开的技术方案。应当理解，以下附图仅示出了本公开的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1示出了本公开实施例所提供的一种雷达装置采集的数据的处理方法的流程图；
图2示出可以应用本公开实施例的雷达装置采集的数据的处理方法的一种系统架构示意图；
图3示出了本公开实施例所提供的一种基于点云数据控制目标车辆的方法流程图；
图4示出了本公开实施例所提供的一种确定障碍物的信息的流程图；
图5示出了本公开实施例所提供的一种确定雷达盲区信息的流程图；
图6示出了本公开实施例所提供的一种生成当前雷达盲区栅格地图的流程图；
图7A示出了本公开实施例所提供的一种光路示意图；
图7B示出了本公开实施例所提供的一种与光路对应的栅格索引序列的示意图；
图8示出了本公开实施例提供的一种确定雷达盲区的流程图；
图9示出了本公开实施例提供的一种雷达装置采集的数据的处理装置900的结构示意图；
图10示出了本公开实施例提供的一种电子设备1000的示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合本公开实施例中附图，对本公开实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本公开一部分实施例，而不是全部的实施例。通常在此处附图中描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本公开的实施例的详细描述并非旨在限制要求保护的本公开的范围，而是仅仅表示本公开的选定实施例。基于本公开的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本公开保护的范围。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。
雷达装置以其精准的测距能力，被广泛应用于自动驾驶、地图测绘等领域，针对这些不同领域，均可以基于雷达装置采集的点云数据进行对应分析，比如，针对自动驾驶领域，可以基于车辆上安装的雷达装置采集的点云数据来检测车辆周围存在的障碍物，障碍物检测的准确度依赖于雷达装置采集的点云数据的准确度，因此雷达装置采集的点云数据是否存在异常，将直接影响到基于该点云数据的检测结果的准确度，因此亟待提 供一种针对点云数据进行异常检测的方案。
基于上述研究，本公开实施例提供了一种雷达装置采集的数据的处理方法，基于雷达装置采集的多帧点云数据，能够根据该多帧点云数据确定点云数据缺失结果，比如点云数据中未采集到距离信息的情况，然后根据点云数据的缺失结果，发出指示雷达装置的异常类型，便于及时确定雷达装置采集的点云数据存在异常，示例性地，方便对存在异常的点云数据或者雷达装置进行及时进行调整，以便得到准确度较高的点云数据，从而提高在基于点云数据进行后续检测的情况下的准确度。
为便于对本公开实施例进行理解，首先对本公开实施例所公开的一种雷达装置采集的数据的处理方法进行详细介绍，本公开实施例所提供的雷达装置采集的数据的处理方法的执行主体一般为具有一定计算能力的计算机设备，该计算机设备例如包括：终端设备或服务器或其它处理设备，终端设备可以为用户设备(User Equipment，UE)、移动设备、计算设备、车载设备、可穿戴设备等。在本公开实施例中，该雷达装置采集的数据的处理方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。
本公开实施例将以执行主体为服务器或电子设备为例，对雷达装置采集的数据的处理方法进行详细介绍。
参见图1所示，为本公开实施例提供的雷达装置采集的数据的处理方法的流程图，该处理方法包括以下S101至S103：
S101，获取雷达装置采集的多帧点云数据。
雷达装置可以包括激光雷达装置、毫米波雷达装置和超声波雷达装置等，在本公开实施例中针对自动驾驶领域，雷达装置可以设置在车辆的设定位置上，在车辆的行驶过程中，雷达装置中包含的无线电波发射器可以通过发射无线电波线束来采集点云数据。
在本公开实施例中，雷达装置设置在车辆上的情况下，可以调整雷达装置的安装位置和安装角度，以及调整雷达装置的无线电波发射器的布置角度，这样在车辆行驶过程中，可以按照设定时间间隔对车辆周围的障碍物进行扫描，得到点云数据。
本公开实施例将以雷达装置为激光雷达装置为例进行说明，激光雷达装置中的无线电波发射器可以是激光二极管，激光雷达装置可以是64线的雷达装置，即该激光雷达装置可以包含64个激光二极管，可以发射出共面的64根激光线束，在应用过程中，通过调整激光雷达装置的安装位置和安装角度，以及调整无线电波发射器的布置角度，可以使得这64根激光线束在每个采集角度对应的扫描平面与地面垂直，随着激光雷达装置的机械旋转，使得激光二极管能够按照设定时间间隔采集其旋转360度范围内获得点云数据，得到一帧点云数据。
在本公开实施例中，雷达装置可以按照每旋转0.2度采集一组点云数据，并形成对应采集角度的数据包，然后在采集完一帧点云数据后，将旋转360度采集到的各个采集角度对应的数据包发送至服务器。
S102，根据多帧点云数据，确定点云数据缺失结果；点云数据缺失结果包括点云数据的具体缺失部分。
服务器在接收到雷达装置采集的每帧点云数据后，可以按照雷达装置采集每帧点云数据的情况下的采集方式，确定出点云数据缺失结果，每帧点云数据对应的点云数据缺失结果可以为正常缺失，比如在雷达装置的某个方向不存在范围内的障碍物的情况下，雷达装置中的无线电波发射器朝该方向发射无线电波线束的情况下并不会采集到点云数据，即存在正常的点云数据缺失，但是若该方向存在范围内的障碍物，但是仍然未采集到点云数据，则可能存在异常的点云数据缺失结果。
S103，根据点云数据的缺失结果，发出提示信息；其中，提示信息用于指示雷达装置的异常类型。
综上，本公开实施例通过分析点云数据缺失结果中的具体缺失部分，可以分析出雷 达装置的异常类型，基于此进行提示，便于及时对雷达装置进行调整，以得到准确的点云数据。
本公开实施例中，基于雷达装置采集的多帧点云数据，能够根据该多帧点云数据确定点云数据缺失结果，比如点云数据中未采集到距离信息的情况，然后根据点云数据的缺失结果，发出指示雷达装置的异常类型，便于及时确定雷达装置采集的点云数据存在异常，在本公开实施例中，方便对存在异常的点云数据或者雷达装置进行及时进行调整，以便得到准确度较高的点云数据，从而提高在基于点云数据进行后续检测的情况下的准确度。
图2示出可以应用本公开实施例的雷达装置采集的数据的处理的一种系统架构示意图；如图2所示，该系统架构中包括：获取终端201、网络202和提示终端203。为实现支撑一个示例性应用，获取终端201和提示终端203通过网络202建立通信连接，获取终端201通过网络202向提示终端203上报雷达装置采集的多帧点云数据，提示终端203根据多帧点云数据，确定点云数据缺失结果；所述点云数据缺失结果包括点云数据的具体缺失部分；以及根据点云数据的缺失结果，得到提示信息，并发出提示信息；其中，提示信息用于指示雷达装置的异常类型。最后，提示终端203将提示信息上传至网络202，并通过网络202发送提示信息给获取终端201。
作为示例，获取终端201可以包括视频采集设备或图像采集设备，提示终端203可以包括具有视觉信息处理能力的视觉处理设备或远程服务器。网络202可以采用有线或无线连接方式。其中，在提示终端203为视觉处理设备的情况下，获取终端201可以通过有线连接的方式与视觉处理设备通信连接，例如通过总线进行数据通信；在提示终端203为远程服务器的情况下，获取终端201可以通过无线网络与远程服务器进行数据交互。
或者，在一些场景中，获取终端201可以是带有采集功能模组的视觉处理设备，具体实现为带有采集功能的主机。这时，本公开实施例的雷达装置采集的数据的处理方法可以由获取终端201执行，上述系统架构可以不包含网络202和提示终端203。
下面将结合具体实施例，对上述S101至S103进行具体阐述。
为了便于统计点云数据缺失结果中的具体缺失部分，本公开实施例提供了一种具体缺失部分的确定方式，将每帧点云数据映射至矩阵中，以上述提到的64线激光雷达装置为例，若该激光雷达装置在各个采集角度均能够采集到数据，在本公开实施例中，每帧点云数据包含64*1800个数据，其中，64表示激光雷达装置中的64个激光二极管，1800表示激光雷达装置旋转360度范围内对应的1800个采集角度(在本公开实施例中，从0.2度开始，包括0.2度、0.4度、…、360度)，可以将这64*1800个数据按照映射至64行*1800列的矩阵中，每行数据对应一个激光二极管在1800个采集角度采集的数据，每列表示64个激光二极管在对应采集角度采集到的数据。
一般情况下，无论存在正常的点云数据缺失，还是异常的点云数据缺失，64行*1800列的矩阵中会包含缺失的数据，缺失的数据可以通过设定标识符或者设定数据来表示，比如可以通过“-”来表示，下面可以根据该行列矩阵来检测每帧点云数据是否存在缺失，以及对应的点云数据缺失结果。
在本公开实施例中，点云数据缺失结果包括雷达装置的至少一个无线电波发射器对应的点云数据存在缺失；
根据多帧点云数据，确定点云数据缺失结果，包括：
在第一持续时间中的每一帧点云数据中，在至少一个无线电波发射器对应的点云数据均不存在的情况下，确定至少一个无线电波发射器对应的点云数据缺失；
根据点云数据的缺失结果，发出提示信息，包括：
发出提示信息；其中，提示信息用于指示雷达装置中的至少一个无线电波发射器存 在异常。
在本公开实施例中，以雷达装置为上述激光雷达装置为例，可以根据矩阵中的缺失数据来检测是否存在至少一个激光二极管对应的点云数据存在缺失，考虑到矩阵中的每组行数据均对应一个激光二极管，因此可以通过检测是否存在行数据缺失来确定是否存在至少一个激光二极管存在异常。
在本公开实施例中，可以检测第一持续时间中的每一帧点云数据对应的矩阵中是否存在至少一组行数据的缺失，若存在，则可以确定该组行数据对应的激光二极管对应的点云数据缺失，比如矩阵中第二行数据均为“-”，可以说明该激光雷达装置中的第二个激光二极管在第一持续时间内均未采集到点云数据，可以确定该第二个激光二极管对应的点云数据缺失。
在本公开实施例中，第一持续时间可以对应采集一帧点云数据的时长，也可以对应采集多帧点云数据的时长，为了降低偶然性，可以通过对多帧点云数据各自对应的矩阵进行检测，从而能够更加准确确定是否存在至少一个激光二极管对应的点云数据缺失。
在本公开实施例中，在确定存在至少一个无线电波发射器对应的点云数据缺失，可以发出对应的提示信息，便于及时对该无线电波发射器进行修正，以得到正常的点云数据。
本公开实施例中，可以通过检测是否存在无线电波发射器对应的点云数据缺失，以便及时发现故障的无线电波发射器，能够对其进行调整或者更换，从而获取到准确度较高的点云数据。
在本公开实施例中，点云数据缺失结果包括至少一个采集角度对应的点云数据存在缺失；
根据多帧点云数据，确定点云数据缺失结果，包括：
在第二持续时间中的每一帧点云数据中，存在至少一个采集角度对应的点云数据不存在，且在第二持续时间中的各帧点云数据中对应的不存在的点云数据的采集角度不完全相同的情况下，确定随机采集角度对应的点云数据缺失；
根据点云数据的缺失结果，发出提示信息，包括：
发出提示信息；其中，提示信息用于指示雷达装置存在数据包传输异常。
在本公开实施例中，以雷达装置为上述激光雷达装置为例，可以根据第二持续时间中的每一帧点云数据对应的矩阵来检测是否存在随机采集角度对应的点云数据缺失，考虑到矩阵中每组列数据均对应一个采集角度，同一采集角度对应的数据会被打包构成一个数据包，因此针对多帧点云数据各自对应的矩阵，可以根据是否存在随机列数据的缺失来确定是否存在随机采集角度对应的点云数据缺失。
在本公开实施例中，可以检测第二持续时间中的每一帧点云数据对应的矩阵中是否存在至少一个列数据不存在，且第二持续时间中各个矩阵中对应的缺失列数据的列号不完全相同，比如第二持续时间中包含三个矩阵，第一个矩阵为第1至3列的列数据缺失，第二个矩阵为第7至11列的列数据缺失，第三个矩阵为第100至110列的列数据缺失，可以确定存在随机采集角度对应的点云数据缺失。
在本公开实施例中，在确定存在随机采集角度对应的点云数据缺失的情况下，可以发出对应的提示信息，便于及时对该雷达装置进行修正，以得到完整的点云数据，或者，也可以设定缺失阈值，若列数据缺失的比例达到缺失阈值，再进行提示。
本公开实施例中，可以对多帧点云数据中每个采集角度对应的点云数据进行检测，以便及时检测雷达装置是否存在数据包传输异常，能够及时发现存在异常，从而便于及时调整，以提高点云数据的准确度。
在本公开实施例中，点云数据缺失结果包括至少一个采集角度对应的点云数据存在缺失；
根据多帧点云数据，确定点云数据缺失结果，包括：
在第三持续时间中的每一帧点云数据中，在至少一个采集角度对应的点云数据不存在，且在第三持续时间中的各帧点云数据中对应的不存在的点云数据的采集角度相同的情况下，确定特定采集角度对应的点云数据缺失；
根据点云数据的缺失结果，发出提示信息，包括：
发出提示信息；其中，提示信息用于指示雷达装置存在遮挡异常。
在本公开实施例中，可以根据第三持续时间中的每一帧点云数据对应的矩阵来检测是否存在特定采集角度对应的点云数据缺失，考虑到矩阵中每组列数据均对应一个采集角度，针对不同帧点云数据中相同的采集角度对应的列数据，可以看作激光雷达装置的激光二极管在同一采集角度采集的点云数据，因此，可以通过检测多帧点云数据各自对应的矩阵中，是否存在相同列数据的缺失，来确定是否存在特定采集角度对应的点云数据缺失。
在本公开实施例中，可以检测第三持续时间中的每一帧点云数据对应的矩阵中是否存在至少一个列数据不存在，且第三持续时间中各个矩阵中对应的缺失列数据的列号完全相同，比如第三持续时间中包含三个矩阵，第一个矩阵为第1列的列数据缺失，第二个矩阵为第1列的列数据缺失，第三个矩阵为第1列的列数据缺失，可以确定存在与第1列对应的特定采集角度对应的点云数据缺失。
在本公开实施例中，在确定存在特定采集角度对应的点云数据缺失的情况下，可以确定雷达装置在选择至对应采集角度时存在被遮挡的问题，可以发出对应的提示信息，便于及时对该雷达装置进行位置调整，以得到完整的点云数据。
本公开实施例中，可以对多帧点云数据中每个采集角度对应的点云数据进行检测，以便及时检测雷达装置是否存在遮挡异常，方便在确定存在遮挡异常时能够及时调整，从而提高点云数据的准确度。
在本公开实施例中，根据多帧点云数据，确定点云数据缺失结果，包括：
确定多帧点云数据中存在至少一帧点云数据包含的点云点的总数量低于第一设定阈值的情况下，确定至少一帧点云数据中存在缺失；
根据点云数据的缺失结果，发出提示信息，包括：
发出提示信息；其中，提示信息用于指示雷达装置存在位置异常。
雷达装置在多种应用场景下，比如自动驾驶、测绘等，雷达总能扫描到周周环境中的障碍物，因此可以得到一定数量的点云数据，但是在不同的应用场景下，得到的每帧点云数据中的点云点的数量保持在一定范围内，比如针对自动驾驶领域，每帧点云数据中，有效点云数据占额定总数量的30％至99％，以上述激光雷达装置为例，额定总数量为64*1800，有效点云数据是指激光二极管发送的激光线束能够扫描到障碍物的情况下采集的点云数据，无效点云数据即为上述提到的缺失的点云数据，比如矩阵中通过设定标识符“-”数据可以称为无效点云数据。
在本公开实施例中，本公开通过每帧点云数据中包含的点云点的总数量来表示有效点云数据，针对特定的应用场景，每帧点云数据包含的点云点的总数量可以设置有第一设定阈值，在确定多帧点云数据中存在至少一帧点云数据中包含的点云点的总数量低于该第一设定阈值的情况下，可以确定该至少一帧点云数据存在缺失，在本公开实施例中，若存在连续多帧点云数据中的每帧点云数据包含的点云点的总数量低于第一设定阈值的情况下，在本公开实施例中可以确定连续多帧点云数据存在缺失。
在本公开实施例中，针对该情况，可以发出对应的提示信息，指示雷达装置存在位置异常，比如在自动驾驶领域，雷达装置中的无线电波发射器朝向天空，该情况可能无法采集到有效的点云点的数据，通过进行提示，便于及时对该雷达装置进行位置调整，以得到完整的点云数据。
本公开实施例中，可以通过检测多帧点云数据中每帧点云数据包含的点云点的数量，以便及时检测雷达装置是否存在位置异常，并在存在异常的情况下进行提示，有益于对雷达装置及时调整，从而提高点云数据的准确度。
在本公开实施例中，根据多帧点云数据，确定点云数据缺失结果，包括：
获取相邻两帧点云数据之间的传输时间间隔，确定传输时间间隔是否大于设定时间间隔；
根据点云数据的缺失结果，发出提示信息，包括：
在确定传输时间间隔大于设定时间间隔的情况下，发出提示信息；其中，提示信息用于指示雷达装置存在点云数据传输异常。
在本公开实施例中，雷达装置的工作频率可以预先设定，这样每采集一帧点云数据需要的时长可以预先确定，对应地可以确定设定时间间隔，比如每帧点云数据的采集时长为100ms，则相邻两帧点云数据的传输时间间隔为100ms，若每帧点云数据的采集时长为50ms，则相邻两帧点云数据的传输时间间隔为50ms。
在本公开实施例中，设定时间间隔可以等于或略大于每帧点云数据的采集时长，比如在每帧点云数据的采集时长为100ms的情况下，设定时间间隔可以为105ms，在雷达装置针对相邻两帧点云数据之间的传输时间间隔大于设定时间间隔时，可以确定雷达装置存在点云数据传输异常。
在本公开实施例中，针对该情况，可以发出对应的提示信息，以便及时对雷达装置进行调整或者更换，从而能够提高按照设定时间间隔得到每帧点云数据的准确度。
本公开实施例中，可以通过相邻两帧点云数据的传输时间间隔，来检测雷达装置是否存在点云数据传输异常的问题，便于在存在异常的情况下及时进行调整，从而提高点云数据的准确度。
除了上述点云数据缺失结果的情况，在本公开实施例中，根据多帧点云数据，确定点云数据缺失结果，还包括：
针对每帧点云数据，按照每帧点云数据中各个点云点对应的坐标位置，将每帧点云数据投影至设定投影区域内，生成与每帧点云数据对应的投影栅格图；设定投影区域为在雷达坐标系下，以雷达装置为中心，以雷达装置的扫描区域在地面投影得到的区域；
确定投影栅格图中包含的点数量是否小于第二设定阈值；
根据点云数据缺失结果，发出提示信息，包括：
在确定点数量小于第二设定阈值的情况下，发出提示信息；其中，提示信息用于提示每帧点云数据为经过坐标系转换后的点云数据。
针对每帧点云数据，若该帧点云数据为原始点云数据，即该帧点云数据是基于雷达装置坐标系下的点云数据的情况下，按照该帧点云数据中各个点云点对应的坐标位置，将该帧点云数据投影至设定投影区域内后，可以在该设定投影区域中检测到大于或等于第二设定阈值的点数量，但是，若对该帧点云数据进行了坐标转换，再将该帧点云数据投影至设定投影区域后，在该设定投影区域检测到的点数量会大大降低，可能都小于第二设定阈值，此时可以确定该帧点云数据为经过坐标系转换后的点云数据。
在本公开实施例中，第二设定阈值可以通过雷达装置中扫描到地面的无线电波线束的数量为基础进行设定，即使雷达装置周围不存在障碍物，但是雷达装置中的无线电波发射器可以向地面发射无线电波线束，因此针对原始点云数据，将该帧点云数据投影至设定投影区域后，可以在该设定投影区域中找到超过设定阈值的点数量。
在本公开实施例中，可以对该情况进行对应提示，防止将经过坐标系转换后的点云数据按照原始点云数据进行应用出现差错。
本公开实施例中，可以对多帧点云数据进行检测，确定每帧点云数据是否为雷达坐标系下的点云数据，从而可以减少将经过坐标系转换后的点云数据按照原始点云数据进 行应用的情况下出现的差错。
在本公开实施例中，以自动驾驶领域为例，本公开实施例提供的雷达装置可以设置于目标车辆上，如图3所示，本公开实施例提供的处理方法还包括以下S201至S203：
S201，响应于点云数据不缺失，基于点云数据，确定距离目标车辆设定范围内的障碍物的信息。
雷达装置在目标车辆上的安装位置、安装角度以及雷达发射器的布置角度调整完毕后，雷达装置的扫描区域可以确定，这样可以扫描到距离目标车辆设定范围内的障碍物，在本公开实施例中可以获取到构成障碍物轮廓的各个点在设定坐标系下的位置信息，按照该方式可以基于该点云数据，得到距离该目标车辆设定范围内的障碍物的轮廓信息。
S202，基于雷达装置发射的线束信息、以及障碍物的信息，确定目标车辆的雷达盲区信息。
其中，线束信息可以包括雷达装置在各个采集角度发射的无线电波线束的数目以及与地面的高度，具体可以通过预先建立的线高地图来表示，在本公开实施例中，可以预先构建包含目标车辆，且与目标车辆距离设定范围内的地表区域在鸟瞰图下的栅格地图，然后基于雷达装置发射的线束信息，生成与该栅格地图对应的线高地图，其中，线高地图包含三个维度，前两个维度表示每个栅格在该线高地图中的行位置和列位置，第三个维度表示每个栅格包含的线束数目，另外，该栅格中还记录有包含的每条线束在该栅格内的高度。
其中，每个栅格对应的线束数目是指不考虑该栅格存在障碍物的情况下，仅根据雷达装置安装位置、安装角度以及雷达发射器的布置角度，确定的雷达装置发射的线束中，射入该栅格的线束数目；在本公开实施例中，可以通过将射入该栅格的线束平移至与穿过栅格中心点且垂直于栅格平面的直线相交的位置后，将该交点与该栅格的中心点位置之间的距离作为该条线束在该栅格处的线束高度。
在本公开实施例中，确定线高地图可以不考虑栅格中对应的障碍物的情况，即获取包含最完整的线束的线高地图，该线高地图在后期确定雷达盲区信息的情况下，可以提供每个栅格对应的原始线束，具体可以按照以下方式生成线高地图：
(1)预先构建与目标车辆距离设定范围内的地表栅格地图，该地表栅格地图包含多个栅格；
(2)调整雷达装置的内参，具体包括无线电波发射器垂直方向的预设角度，以及调整雷达装置的外参，具体包括无线电波发射器在目标车辆上的安装位置和安装角度，基于调整好的内参和外参可以计算出雷达装置发射的线束经过的多个栅格，以及在经过每个栅格的情况下在该栅格处的线束高度；
(3)记录并保存每个栅格对应的线束数目和线束高度，可以得到线高地图。
S203，按照雷达盲区信息，控制目标车辆。
在本公开实施例中，针对不同类型的目标对象，雷达盲区信息可能不同，比如，针对体积较大的目标对象，扫描到该目标对象的轮廓信息，需要的无线电波线束较多，此时对应线束较少的栅格，和，对应最低线束高度低于该目标对象高度的栅格中的至少之一可以作为针对该类型的目标对象的盲区，比如，若目标对象为身高1.6米的目标对象，扫描到该目标对象需要三条线束，且每条线束与地面的高度不高于1.6米，若存在一个区域内的所有栅格对应的最低线束高度均高于1.6米，和，有效线束数目不足三条中的至少之一，则该区域即为该目标车辆在行驶过程中，针对1.6米的目标对象的盲区。
针对体型较小的目标对象，比如高度为0.8米的目标对象，扫描该目标对象需要两条线束，且每条线束与地面的高度不高于0.8米，若存在一个区域内的所有栅格对应的最低线束高度均高于0.8米，和，有效线束数目不足两条中的至少之一，则该区域即为该目标车辆在行驶过程中，针对0.8米的目标对象的盲区。
本公开实施例中，可以在目标车辆行驶过程中，不断地通过变化的障碍物的信息，来确定针对目标车辆在行驶过程中的雷达盲区信息，从而可以基于此对目标车辆的行驶过程进行有效控制，从而降低目标车辆发生碰撞的概率。
在本公开实施例中，针对上述S201，基于点云数据，确定距离目标车辆设定范围内的障碍物的信息，如图4所示，可以包括以下S2011至S2013：
S2011，基于点云数据，确定距离目标车辆设定范围内的每个障碍物的轮廓信息。
在本公开实施例中，点云数据可以包含各个点云点在车体坐标系下的坐标值，基于点云数据中各个点云点坐标值，可以得到与目标车辆距离设定范围内的障碍物在车体坐标系下的轮廓信息，比如一个行人的轮廓，一辆车辆的轮廓，或者一个建筑物的轮廓。
在本公开实施例中，每个障碍物的轮廓信息可以通过该障碍物对应的三维(3-dimension，3D)边界框的尺寸来表示，该3D边界框可以是3D凸多面体，下面简述3D凸多面体的确定过程：
在本公开实施例中，基于该障碍物对应的点云数据，确定该障碍物在地面对应区域的包络多边行检测框，然后沿该障碍物在垂直与该多边行检测框的方向，拉伸该多边行检测框，直至达到障碍物高度，则得到该3D凸多面体。
S2012，基于轮廓信息，确定每个障碍物在预先构建的栅格地图中的各个栅格处的障碍物高度。
其中，预先构建的栅格地图是根据目标车辆的形状和尺寸、目标车辆上的雷达的检测范围以及栅格分辨率确定的。
在本公开实施例中，通过每个障碍物对应的3D边界框底部区域在车体坐标系中对应的坐标范围，可以确定每个障碍物在预先构建的栅格地图中所占的栅格，在本公开实施例中，比如该障碍物在栅格地图中所占的栅格区域包含8个栅格，再基于该障碍物对应的3D边界框的高度，确定出该障碍物在预先构建的栅格地图中的各个栅格处的障碍物高度。
可以针对目标车辆上的雷达扫描到的检测范围在地面的投影区域构建栅格地图，雷达安装在目标车辆上的情况下形成的投影区域不包含目标车辆在地面的投影，栅格地图的尺寸和形状可以由该投影区域确定，栅格地图包含的栅格数量可以由预先设置的栅格分辨率决定，栅格分辨率可以表征单个栅格的边长的倒数，同时可以表示单位面积内包含的栅格数量。
栅格分辨率确定后，栅格地图包含的栅格数量就可以确定，栅格分辨率越高，单个栅格的尺寸越小，障碍物在关联的各个栅格处对应的尺寸就越小，因此障碍物在各个栅格处对应的上表面越接近平面，这样在确定各个栅格处的障碍物高度时就越准确，但是栅格数量越多，效率会相应降低，这里可以根据大数据来平衡准确度和效率，进而选择合理的栅格分辨率。
S2013，基于障碍物高度，得到当前障碍物栅格地图。
当前障碍物栅格地图用于表征距离目标车辆设定范围内的障碍物的信息。
在本公开实施例中，可以基于每个障碍物在预先构建的栅格地图中的各个栅格处的障碍物高度，对预先构建的栅格地图中的每个栅格进行对应障碍物高度进行标记后，得到当前障碍物栅格地图。
本公开实施例中，可以直观地得到用于表征与目标车辆距离设定范围内的障碍物的信息，从而便于后期基于该障碍物栅格地图和线束信息，在本公开实施例中确定每个栅格对应的有效线束高度和有效线束数目，从而为确定雷达盲区信息做准备。
在本公开实施例中，线束信息包括雷达发射的线束在预先构建的栅格地图中的每个栅格内的线束高度；针对上述S202，基于雷达装置发射的线束信息、以及障碍物的信息，确定目标车辆的雷达盲区信息，如图5所示，可以包括以下S2021至S2022：
S2021，基于预先构建的栅格地图中的每个栅格对应的线束高度，以及当前障碍物栅格地图，确定当前雷达盲区栅格地图。
其中，预先构建的栅格地图中每个栅格对应的线束高度可以从上文构建的线高地图中获取，然后基于每个栅格对应的线束高度，以及该栅格在当前障碍物栅格地图中对应的障碍物高度，可以确定该栅格对应的有效线束数目以及最低线束高度，即得到当前雷达盲区栅格地图。
其中，任一栅格对应的有效线束数目是指能够射入该任一栅格的线束的数目，在本公开实施例中，一个栅格处存在有障碍物，则该栅格对应的有效线束为在该栅格处对应的线束高度高于该栅格中的障碍物高度的线束；一个栅格对应的最低线束高度是指该栅格中对应的有效线束中高度最低的线束。
S2022，基于当前雷达盲区栅格地图以及预设目标对象的轮廓信息，确定目标车辆针对该预设目标对象的雷达盲区信息。
在本公开实施例中，预设目标对象具体可以结合目标车辆的应用场景决定，若该目标车辆为无人驾驶车辆，主要行驶在设定轨道区域内进行货物运输，在该设定轨道区域内出现行人的概率很小，出现货物的概率较大，则这里的预设目标对象可以单指货物。
在本公开实施例中，若该目标车辆主要行驶在居民区，居民区的孩童较多，则这里的预设目标对象可以为孩童。
具体基于当前雷达盲区栅格地图以及预设目标对象的轮廓信息，确定目标车辆针对该预设目标对象的雷达盲区信息，可以通过当前雷达盲区栅格地图中每个栅格对应的有效线束数目和最低线束高度，以及能够扫描到目标对象的情况下的有效线束数目和最高线束高度决定，当一个栅格对应的最低线束高度都高于能够扫描到目标对象的最高线束高度的情况下，则该栅格相对于该目标对象为雷达盲区，具体情况详见上文实施例所述。
本公开实施例中，可以快速确定每个栅格对应的有效线束数目和最低线束高度，从而得到目标车辆的当前雷达盲区栅格地图，在本公开实施例中基于预设目标对象的轮廓信息，快速确定雷达盲区信息，从而便于后期基于该雷达盲区信息控制目标车辆的行驶过程。
针对上述S2021，基于预先构建的栅格地图中的每个栅格对应的线束高度，以及当前障碍物栅格地图，确定当前雷达盲区栅格地图，如图6所示，可以包括以下S20211至S20215：
S20211，基于当前障碍物栅格地图中包含的障碍物的尺寸信息、以及雷达装置发射的线束在当前障碍物栅格地图上投影得到的光路信息，提取被任一障碍物遮挡的光路得到更新光路集合。
其中，每个障碍物的尺寸信息主要包含该障碍物在当前障碍物栅格地图中的投影尺寸，如图7A所示，为包含两个障碍物(分别记录为障碍物A和障碍物B)的当前障碍物栅格地图，可以看到，被障碍物A遮挡的最大角度的两条光路分别记录为L1和L2，被障碍物B遮挡的最大角度的两条光路分别记录为L3和L4，则这里可以提取位于L1和L2构成的夹角中的所有光路，以及提取位于L3和L4构成的夹角中的所有光路，可以从图7A中看到，位于L1和L2构成的夹角中的部分光路与位于L3和L4构成的夹角中的部分光路重合，这里针对重合的光路，只提取一次即可。
每条光路对应一个采集角度的多条线束，以64位雷达装置为例，每条光路对应一个采集角度的64条线束，若位于L1和L2构成的夹角中包含10条光路，位于L3和L4构成的夹角中包含6条光路，假设L1和L2构成的夹角和L3和L4构成的夹角的重合部分，如图7A中L2和L3构成的夹角处存在两条光路，且这两条光路发生重合，针对这两条重合的光路只提取一条，这样这里得到的更新光路集合中包含15条光路。
S20212，针对更新光路集合中的每条光路，沿该光路的发射方向，确定与该条光路 对应的栅格索引序列，栅格索引序列表示将多个栅格按照光路发射方向的顺序依次排序得到的各个栅格的索引。
在本公开实施例中，针对更新光路集合中的任一条光路，在不考虑障碍物的情况下，若该任一条光路在当前栅格地图中穿过20个栅格，则该任一条光路对应的栅格索引序列即为这20个栅格按照该任一条光路发射方向的顺序依次排列得到的各个栅格的索引。
为了便于理解，引入图7B，栅格地图各个栅格在X轴中位置可以表示该栅格在栅格地图中的行位置，栅格地图各个栅格在Y轴中位置可以表示该栅格在栅格地图中的行位置，任一光路L沿发射方向穿过的栅格包含栅格A至K，其中栅格A在栅格地图中的行位置为7，列位置为6，则可以通过(7，6)表示该栅格A对应的索引，同理可以确定出该任一光路L穿过的其它栅格的索引，这里按照栅格A至K的顺序，即可以确定出该任一光路L对应的栅格索引序列。
S20213，针对每个栅格索引序列，按照栅格索引序列对应的光路关联的每条线束在各个栅格处的线束高度以及该栅格对应的障碍物高度，对该栅格索引序列指示的每个栅格对应的最低线束高度和有效线束数目进行调整。
S20214，判断是否调整完最后一个栅格索引序列中每个栅格对应的最低线束高度和有效线束数目，若否，返回执行S20213，若是，则执行S20215，得到当前雷达盲区栅格地图。
针对每个栅格索引序列，首先获取该栅格索引序列对应的光路关联的每条线束，在对该栅格索引序列中的第一个索引对应的栅格对应的最低线束高度和有效线束数目进行调整的情况下，可以将该光路关联的所有线束按照线束高度从低至高的顺序进行排序后，从最低线束高度开始，依次与该栅格对应的障碍物高度进行比较，将对应线束高度高于或等于该障碍物高度的线束作为该栅格对应的有效线束，将对应线束高度低于该障碍物高度的线束作为该栅格对应的无效线束(无效线束即被障碍物遮挡的线束)，通过该方式即可以对该栅格对应的最低线束高度和有效线束数目进行调整，并在调整完毕后，继续调整该栅格索引的下一个索引标识的栅格，直至调整完该栅格索引序列指示的每个栅格后，继续调整其它栅格索引序列中每个栅格对应的最低线束高度和有效线束数目后，可以得到当前雷达盲区栅格地图。
本公开实施例中，提出依次针对每条光路对应的栅格索引序列指示的栅格进行调整，且该调整方式能够按照线束发射方向对每个栅格依次进行调整，从而提供了一种针对每个栅格对应的最低线束高度和有效线束数目进行有序更新的方式。
具体地，针对上述S20213，可以按照以下方式对一个栅格索引序列指示的每个栅格对应的最低线束高度和有效线束数目进行调整：
(1)针对一个栅格索引序列中的当前栅格，依次比较该栅格索引序列对应的每条线束在当前栅格中的线束高度与当前栅格对应的障碍物高度，将线束高度高于障碍物高度的线束作为当前栅格对应的有效线束。
其中，一个栅格索引序列可以为多个栅格索引序列中的任一栅格索引序列，在本公开实施例中，在针对一个栅格索引序列中的当前栅格对应的有效线束进行调整前，先获取能够射入当前栅格的线束，能够射入当前栅格的线束可以为该栅格索引序列中位于当前栅格之前的上一个栅格的有效线束，无需比较该栅格索引序列对应的光路关联的所有线束，从而可以提高调整速度。
(2)基于当前栅格对应的有效线束的线束高度对当前栅格的最低线束高度进行调整；以及基于在该栅格索引序列对应的线束中，当前栅格对应的有效线束数目，对当前栅格对应的有效线束数目进行调整。
这里考虑到当前栅格不仅仅对应唯一的栅格索引序列，在该当前栅格对应多条栅格索引序列的情况下，针对当前栅格对应的最低线束高度以及有效线束数目进行调整的情 况下，考虑到之前对该当前栅格进行调整后，已经保存了该当前栅格对应的最低线束高度和有效线束数目，这里在对当前栅格再进行调整的情况下，可以基于在当前调整的情况下确定的当前栅格的有效线束的线束高度对当前栅格对应的已保存的最低线束高度进行调整；以及在该栅格索引序列对应的线束中，同样可以基于当前栅格对应的有效线束数目，对当前栅格对应的已保存的有效线束数目进行调整。
在本公开实施例中，在当前栅格对应的有效线束的线束高度和当前栅格对应的已保存的最低线束高度中，取最低的线束高度作为在本次对当前栅格进行调整后，该当前栅格对应的最低线束高度；基于本次调整时得到的当前栅格对应的有效线束数目和当前栅格对应的已保存的有效线束数目，得到该当前栅格对应的最大有效线束数目作为在本次对当前栅格进行调整后，该当前栅格对应的有效线束数目。
在本公开实施例中，在当前栅格仅仅对应一条栅格索引序列的情况下，当前栅格对应的已保存的最低线束高度可以为预设的一个较大值，另外，当前栅格对应的已保存的有效线束数可以为预设的一个较小值，比如0。
(3)将当前栅格对应的有效线束作为射入该栅格索引序列中下一个栅格的线束，并将下一个栅格作为当前栅格，继续执行对该当前栅格对应的最低线束高度和有效线束数目进行调整的步骤，直至射入当前栅格的每个线束的线束高度均低于当前栅格对应的障碍物高度时，得到该栅格索引中每个栅格在本次调整后对应的最低线束高度以及有效线束数目。
在得到当前栅格对应的有效线束后，将该有效线束作为可以射入该栅格索引序列中下一个栅格的线束，这样在针对该下一个栅格对应的最低线束高度和有效线束数目进行调整的情况下，无需考虑当前栅格对应的无效线束，从而可以加快对后续栅格对应的最低线束高度和有效线束数目的调整速度。
在射入当前栅格的每个线束的线束高度均低于当前栅格对应的障碍物高度的情况下，说明该当前栅格没有有效线束，此时针对该栅格索引序列中的下一个栅格，在该条光路关联的线束中，并没有射入的光线，因而无需继续对后续栅格对应的最低线束高度和有效线束数目进行调整，这里可以对该当前栅格的最低线束高度赋予较大值，对该当前栅格对应的有效线束赋值0。
本公开实施例中，在针对一个栅格索引序列指示的每个栅格对应的最低线束高度和有效线束数目进行调整的情况下，针对每个栅格，均会过滤掉该栅格的上一个栅格对应的无效线束，从而可以提高调整速度。
在本公开实施例中，还可以同时按照上述方式调整每个栅格索引序列指示的每个栅格对应的最低线束高度和有效线束数目，最终得到当前雷达盲区栅格地图，在同时调整时，同样按照光路发射方向，对每个栅格进行调整。
在本公开实施例中，在调整同时包含多条光路的栅格对应的最低线束高度和有效线束数目，需要同时考虑每条光路关联的线束与该栅格对应的障碍物高度。
针对上述S2022，基于当前雷达盲区栅格地图以及预设目标对象的轮廓信息，确定针对该预设目标对象的雷达盲区信息，如图8所示，可以包括以下S20221至S20222：
S20221，基于预设目标对象的轮廓信息，确定雷达装置扫描到预设目标对象的有效线束数目以及最高线束高度。
这里的预设目标对象的轮廓信息同样可以通过预设目标对象对应的3D边界框的尺寸信息来表示，在通过雷达扫描该3D边界框对应的预设目标对象的情况下，不同尺寸的3D边界框具有不同的有效线束数目以及最高线束高度，这里最高线束高度是指能够扫描到该预设目标对象的最高线束高度，在使用低于或等于该最高线束高度的线束扫描预设目标对象的情况下，能够扫描到该3D边界框对应的预设目标对象，在使用高于该最高线束高度的线束扫描预设目标对象的情况下，则无法扫描到该预设目标对象。
在本公开实施例中，在通过目标车辆的应用场景确定出预设目标对象的轮廓信息后，即可以确定雷达装置扫描到预设目标对象的有效线束数目以及最低线束高度。
S20222，基于当前雷达盲区栅格地图中，每个栅格对应的有效线束数目以及扫描到预设目标对象的有效线束数目，和，每个栅格对应的最低线束高度以及扫描到预设目标对象的最高线束高度中的至少之一，确定预设目标对象在当前雷达盲区栅格地图中对应的雷达盲区。
在本公开实施例中，可以将对应的有效线束数目少于扫描到预设目标对象的有效线束数目的栅格，作为预设目标对象在当前雷达盲区栅格地图中对应的雷达盲区；可以将对应的最低线束高度高于扫描到预设目标对象的最高线束高度的栅格，作为预设目标对象在当前雷达盲区栅格地图中对应的雷达盲区；可以将应的有效线束数目少于扫描到预设目标对象的有效线束数目的栅格，且对应的最低线束高度高于扫描到预设目标对象的最高线束高度的栅格，作为预设目标对象在当前雷达盲区栅格地图中对应的雷达盲区。
本公开实施例中，针对不同的预设目标对象，可以确定不同的雷达盲区，便于针对不同的应用场景，及时更新雷达盲区信息，从而有效控制车辆避障。
针对上述S203，按照目标车辆的雷达盲区信息，控制目标车辆，可以包括以下(1)至(2)：
(1)基于目标车辆的当前位姿信息和雷达盲区信息，确定目标车辆与设定范围内的雷达盲区之间的距离信息。
(2)基于距离信息，控制目标车辆进行减速避障。
在本公开实施例中，雷达盲区信息包括雷达盲区的边界线在以目标车辆为原点的车体坐标系下对应的坐标范围；目标车辆的当前位姿信息可以包括目标车辆的位置信息和朝向信息，然后基于雷达盲区对应的坐标范围，可以确定出该目标车辆与设定范围内的雷达盲区之间的距离信息，这里可以根据目标车辆的朝向，确定出目标车辆中与雷达盲区最接近的一侧，以及间隔距离。
然后基于上述确定的距离信息，可以确定出目标车辆如何行驶可以安全避开该雷达盲区，比如可以确定朝向的变化，以及速度变化，具体可以基于距离信息所属的安全距离等级来确定，安全距离等级越低，表示目标车辆与雷达盲区越接近。
在本公开实施例中，若该距离信息所属的安全距离等级较低，此时可以紧急刹车，若该距离信息所属的安全距离等级较高，可以沿原始方向减速行驶。
本公开实施例，可以基于目标车辆的当前位姿信息和雷达盲区进行避障，从而提高目标车辆的行驶安全性。
本领域技术人员可以理解，在具体实施方式的上述方法中，各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定，各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
基于同一技术构思，本公开实施例中还提供了与雷达装置采集的数据的处理方法对应的处理装置，由于本公开实施例中的装置解决问题的原理与本公开实施例上述处理方法相似，因此装置的实施可以参见方法的实施。
参照图9所示，为本公开实施例提供的一种雷达装置采集的数据的处理装置900的示意图，该处理装置900包括：
获取模块901，配置为获取雷达装置采集的多帧点云数据；
确定模块902，配置为根据多帧点云数据，确定点云数据缺失结果；点云数据缺失结果包括点云数据的具体缺失部分；
提示模块903，配置为根据点云数据的缺失结果，发出提示信息；其中，提示信息用于指示雷达装置的异常类型。
在本公开实施例中，点云数据缺失结果包括雷达装置的至少一个无线电波发射器对 应的点云数据存在缺失；确定模块902，配置为在第一持续时间中的每一帧点云数据中，在至少一个无线电波发射器对应的点云数据均不存在的情况下，确定至少一个无线电波发射器对应的点云数据缺失；提示模块903，配置为发出提示信息；其中，提示信息用于指示雷达装置中的至少一个无线电波发射器存在异常。
在本公开实施例中，点云数据缺失结果包括至少一个采集角度对应的点云数据存在缺失；确定模块902，配置为在第二持续时间中的每一帧点云数据中，存在至少一个采集角度对应的点云数据不存在，且在第二持续时间中的各帧点云数据中对应的不存在的点云数据的采集角度不完全相同的情况下，确定随机采集角度对应的点云数据缺失；提示模块903，配置为发出提示信息；其中，提示信息用于指示雷达装置存在数据包传输异常。
在本公开实施例中，点云数据缺失结果包括至少一个采集角度对应的点云数据存在缺失；确定模块902，配置为在第三持续时间中的每一帧点云数据中，在至少一个采集角度对应的点云数据不存在，且在第三持续时间中的各帧点云数据中对应的不存在的点云数据的采集角度相同的情况下，确定特定采集角度对应的点云数据缺失；提示模块903，配置为发出提示信息；其中，提示信息用于指示雷达装置存在遮挡异常。
在本公开实施例中，确定模块902，配置为确定多帧点云数据中存在至少一帧点云数据包含的点云点的总数量低于第一设定阈值的情况下，确定至少一帧点云数据中存在缺失；提示模块903，配置为发出提示信息；其中，提示信息用于指示雷达装置存在位置异常。
在本公开实施例中，确定模块902，配置为获取相邻两帧点云数据之间的传输时间间隔，确定传输时间间隔是否大于设定时间间隔；提示模块903，配置为在确定传输时间间隔大于设定时间间隔的情况下，发出提示信息；其中，提示信息用于指示雷达装置存在点云数据传输异常。
在本公开实施例中，确定模块902，配置为针对每帧点云数据，按照每帧点云数据中各个点云点对应的坐标位置，将每帧点云数据投影至设定投影区域内，生成与每帧点云数据对应的投影栅格图；设定投影区域为在雷达坐标系下，以雷达装置为中心，以雷达装置的扫描区域在地面投影得到的区域；确定投影栅格图中包含的点数量是否小于第二设定阈值；提示模块903，配置为在确定点数量小于第二设定阈值的情况下，发出提示信息；其中，提示信息用于提示每帧点云数据为经过坐标系转换后的点云数据。
在本公开实施例中，处理装置900还包括控制模块904，控制模块904，配置为响应于点云数据不缺失，基于点云数据，确定距离目标车辆设定范围内的障碍物的信息；雷达装置设置于目标车辆上；基于雷达装置发射的线束信息、以及障碍物的信息，确定目标车辆的雷达盲区信息；按照目标车辆的雷达盲区信息，控制目标车辆。
在本公开实施例中，控制模块904，配置为基于点云数据，确定距离目标车辆设定范围内的每个障碍物的轮廓信息；基于轮廓信息，确定每个障碍物在预先构建的栅格地图中的各个栅格处的障碍物高度；基于障碍物高度，得到当前障碍物栅格地图，当前障碍物栅格地图用于表征距离目标车辆设定范围内的障碍物的信息。
在本公开实施例中，线束信息包括雷达发射的线束在预先构建的栅格地图中的每个栅格内的线束高度；控制模块904，配置为基于预先构建的栅格地图中的每个栅格对应的线束高度，以及当前障碍物栅格地图，确定当前雷达盲区栅格地图；基于当前雷达盲区栅格地图以及预设目标对象的轮廓信息，确定目标车辆针对该预设目标对象的雷达盲区信息。
在本公开实施例中，控制模块904，配置为基于当前障碍物栅格地图中包含的障碍物的尺寸信息、以及雷达装置发射的线束在当前障碍物栅格地图上投影得到的光路信息，提取被任一障碍物遮挡的光路得到更新光路集合；针对更新光路集合中的每条光路，沿该光路的发射方向，确定与该条光路对应的栅格索引序列，栅格索引序列表示将多个栅 格按照光路发射方向的顺序依次排序得到的各个栅格的索引；针对每个栅格索引序列，按照该栅格索引序列对应的光路关联的每条线束在各个栅格处的线束高度以及该栅格对应的障碍物高度，对该栅格索引序列指示的每个栅格对应的最低线束高度和有效线束数目进行调整，直至调整完最后一个栅格索引序列中每个栅格对应的最低线束高度和有效线束数目后，得到当前雷达盲区栅格地图。
在本公开实施例中，控制模块904，配置为针对一个栅格索引序列中的当前栅格，依次比较该栅格索引序列对应的每条线束在当前栅格中的线束高度与当前栅格对应的障碍物高度，将线束高度高于障碍物高度的线束作为当前栅格对应的有效线束；基于当前栅格对应的有效线束的线束高度对当前栅格的最低线束高度进行调整；以及基于在该栅格索引序列对应的线束中，当前栅格对应的有效线束数目，对当前栅格对应的有效线束数目进行调整；将当前栅格对应的有效线束作为射入该栅格索引序列中下一个栅格的线束，并将下一个栅格作为当前栅格，继续执行对当前栅格对应的最低线束高度和有效线束数目进行调整的步骤，直至射入当前栅格的每个线束的线束高度均低于当前栅格对应的障碍物高度的情况下，得到该栅格索引中每个栅格在本次调整后对应的最低线束高度以及有效线束数目。
在本公开实施例中，控制模块904，配置为基于预设目标对象的轮廓信息，确定雷达装置扫描到预设目标对象的有效线束数目以及最高线束高度；基于当前雷达盲区栅格地图中，每个栅格对应的有效线束数目以及扫描到预设目标对象的有效线束数目，和，每个栅格对应的最低线束高度以及扫描到预设目标对象的最高线束高度中的至少之一，确定预设目标对象在当前雷达盲区栅格地图中对应的雷达盲区。
关于装置中的各模块的处理流程、以及各模块之间的交互流程的描述可以参照上述方法实施例中的相关说明，这里不再详述。
对应于图1中的雷达装置采集的数据的处理方法，本公开实施例还提供了一种电子设备1000，如图10所示，为本公开实施例提供的电子设备1000结构示意图，包括：
处理器101、存储器102、和总线103；存储器102用于存储执行指令，包括内存1021和外部存储器1022；这里的内存1021也称内存储器，用于暂时存放处理器101中的运算数据，以及与硬盘等外部存储器1022交换的数据，处理器101通过内存1021与外部存储器1022进行数据交换，在电子设备1000运行的情况下，处理器101与存储器102之间通过总线103通信，使得处理器101执行以下指令：获取雷达装置采集的多帧点云数据；根据多帧点云数据，确定点云数据缺失结果；点云数据缺失结果包括点云数据的具体缺失部分；根据点云数据的缺失结果，发出提示信息；其中，提示信息用于指示雷达装置的异常类型。
本公开实施例还提供一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行的情况下执行上述方法实施例中所述的雷达装置采集的数据的处理方法的步骤。其中，该存储介质可以是易失性或非易失的计算机可读取存储介质。
本公开实施例所提供的雷达装置采集的数据的处理方法的计算机程序产品，包括存储了程序代码的计算机可读存储介质，所述程序代码包括的指令可用于执行上述方法实施例中所述的雷达装置采集的数据的处理方法的步骤，具体可参见上述方法实施例。
本公开实施例还提供一种计算机程序，该计算机程序被处理器执行的情况下实现前述实施例的任意一种方法。该计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中，所述计算机程序产品具体体现为计算机存储介质，在另一个可选实施例中，计算机程序产品具体体现为软件产品，例如软件开发包(Software Development Kit，SDK)等等。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设 备。计算机可读存储介质例如可以是但不限于电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(Random Access Memory，RAM)、只读存储器(Read-Only Memory，ROM)、可擦除可编程只读存储器(Electrical Programmable Read Only Memory，EPROM)或闪存、静态随机存取存储器(Static Random-Access Memory，SRAM)、便携式压缩盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)、数字多功能盘(Digital Video Disc，DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本公开实施例操作的计算机程序指令可以是汇编指令、指令集架构(Industry Standard Architecture，ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言，诸如Smalltalk、C++等，以及常规的过程式编程语言，诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络，包括局域网(Local Area Network，LAN)或广域网(Wide Area Network，WAN)连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、FPGA或可编程逻辑阵列(Programmable Logic Arrays，PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开实施例的各个方面。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统和装置的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。在本公开所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，又例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本公开各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存 储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解，本公开实施例提供的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上所述实施例，仅为本公开的具体实施方式，用以说明本公开的技术方案，而非对其限制，本公开的保护范围并不局限于此，尽管参照前述实施例对本公开进行了详细的说明，本领域的普通技术人员应当理解：任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化，或者对其中部分技术特征进行等同替换；而这些修改、变化或者替换，并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围，都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应所述以权利要求的保护范围为准。
工业实用性
本公开实施例提供了一种数据的处理方法、装置、设备、存储介质及程序，其中，该处理方法由电子设备执行，所述方法包括：获取所述雷达装置采集的多帧点云数据；根据所述多帧点云数据，确定点云数据缺失结果；所述点云数据缺失结果包括所述点云数据的具体缺失部分；根据所述点云数据的缺失结果，发出提示信息；其中，所述提示信息用于指示所述雷达装置的异常类型。

Claims (21)

  1. 一种雷达装置采集的数据的处理方法，所述处理方法由电子设备执行，所述方法包括：
    获取所述雷达装置采集的多帧点云数据；
    根据所述多帧点云数据，确定点云数据缺失结果；所述点云数据缺失结果包括所述点云数据的具体缺失部分；
    根据所述点云数据的缺失结果，发出提示信息；其中，所述提示信息用于指示所述雷达装置的异常类型。
  2. 根据权利要求1所述的处理方法，其中，所述点云数据缺失结果包括所述雷达装置的至少一个无线电波发射器对应的点云数据存在缺失；
    所述根据所述多帧点云数据，确定点云数据缺失结果，包括：
    在第一持续时间中的每一帧点云数据中，在所述至少一个无线电波发射器对应的点云数据均不存在的情况下，确定所述至少一个无线电波发射器对应的点云数据缺失；
    所述根据所述点云数据的缺失结果，发出提示信息，包括：
    发出提示信息；其中，所述提示信息用于指示所述雷达装置中的所述至少一个无线电波发射器存在异常。
  3. 根据权利要求1所述的处理方法，其中，所述点云数据缺失结果包括至少一个采集角度对应的点云数据存在缺失；
    所述根据所述多帧点云数据，确定点云数据缺失结果，包括：
    在第二持续时间中的每一帧点云数据中，存在所述至少一个采集角度对应的点云数据不存在，且在所述第二持续时间中的各帧点云数据中对应的不存在的点云数据的采集角度不完全相同的情况下，确定随机采集角度对应的点云数据缺失；
    所述根据所述点云数据的缺失结果，发出提示信息，包括：
    发出提示信息；其中，所述提示信息用于指示所述雷达装置存在数据包传输异常。
  4. 根据权利要求1所述的处理方法，其中，所述点云数据缺失结果包括至少一个采集角度对应的点云数据存在缺失；
    所述根据所述多帧点云数据，确定点云数据缺失结果，包括：
    在第三持续时间中的每一帧点云数据中，在所述至少一个采集角度对应的点云数据不存在，且在所述第三持续时间中的各帧点云数据中对应的不存在的点云数据的采集角度相同的情况下，确定特定采集角度对应的点云数据缺失；
    所述根据所述点云数据的缺失结果，发出提示信息，包括：
    发出提示信息；其中，所述提示信息用于指示所述雷达装置存在遮挡异常。
  5. 根据权利要求1所述的处理方法，其中，所述根据所述多帧点云数据，确定点云数据缺失结果，包括：
    确定所述多帧点云数据中存在至少一帧点云数据包含的点云点的总数量低于第一设定阈值的情况下，确定所述至少一帧点云数据中存在缺失；
    所述根据所述点云数据的缺失结果，发出提示信息包括：
    发出提示信息；其中，所述提示信息用于指示所述雷达装置存在位置异常。
  6. 根据权利要求1所述的处理方法，其中，所述根据所述多帧点云数据，确定点云数据缺失结果，包括：
    获取相邻两帧点云数据之间的传输时间间隔，确定所述传输时间间隔是否大于设定时间间隔；
    所述根据所述点云数据的缺失结果，发出提示信息包括：
    在确定所述传输时间间隔大于所述设定时间间隔的情况下，发出提示信息；其中，所述提示信息用于指示所述雷达装置存在点云数据传输异常。
  7. 根据权利要求1所述的处理方法，其中，所述根据所述多帧点云数据，确定点云数据缺失结果，包括：
    针对每帧点云数据，按照所述每帧点云数据中各个点云点对应的坐标位置，将所述每帧点云数据投影至设定投影区域内，生成与所述每帧点云数据对应的投影栅格图；所述设定投影区域为在雷达坐标系下，以所述雷达装置为中心，以所述雷达装置的扫描区域在地面投影得到的区域；
    确定所述投影栅格图中包含的点数量是否小于第二设定阈值；
    所述根据所述点云数据缺失结果，发出提示信息，包括：
    在确定所述点数量小于第二设定阈值的情况下，发出提示信息；其中，所述提示信息提示所述每帧点云数据为经过坐标系转换后的点云数据。
  8. 根据权利要求1至7任一所述的处理方法，其中，响应于所述点云数据不缺失，所述处理方法还包括：
    基于所述点云数据，确定距离目标车辆设定范围内的障碍物的信息；所述雷达装置设置于所述目标车辆上；
    基于所述雷达装置发射的线束信息、以及所述障碍物的信息，确定所述目标车辆的雷达盲区信息；
    按照所述雷达盲区信息，控制所述目标车辆。
  9. 根据权利要求8所述的处理方法，其中，所述基于所述点云数据，确定距离所述目标车辆设定范围内的障碍物的信息，包括：
    基于所述点云数据，确定距离所述目标车辆设定范围内的每个障碍物的轮廓信息；
    基于所述轮廓信息，确定所述每个障碍物在预先构建的栅格地图中的各个栅格处的障碍物高度；
    基于所述障碍物高度，得到当前障碍物栅格地图，所述当前障碍物栅格地图用于表征距离所述目标车辆设定范围内的障碍物的信息。
  10. 根据权利要求9所述的处理方法，其中，所述线束信息包括所述雷达发射的线束在所述预先构建的栅格地图中的每个栅格内的线束高度；所述基于所述雷达装置发射的线束信息、以及所述障碍物的信息，确定所述目标车辆的雷达盲区信息，包括：
    基于所述预先构建的栅格地图中的每个栅格对应的线束高度，以及所述当前障碍物栅格地图，确定当前雷达盲区栅格地图；
    基于所述当前雷达盲区栅格地图以及预设目标对象的轮廓信息，确定所述目标车辆针对该预设目标对象的雷达盲区信息。
  11. 根据权利要求10所述的处理方法，其中，所述基于所述预先构建的栅格地图中的每个栅格对应的线束高度，以及所述当前障碍物栅格地图，确定当前雷达盲区栅格地图，包括：
    基于所述当前障碍物栅格地图中包含的障碍物的尺寸信息、以及所述雷达装置发射的线束在所述当前障碍物栅格地图上投影得到的光路信息，提取被任一障碍物遮挡的光路得到更新光路集合；
    针对所述更新光路集合中的每条光路，沿该光路的发射方向，确定与该条光路对应的栅格索引序列，所述栅格索引序列表示将多个栅格按照光路发射方向的顺序依次排序得到的各个栅格的索引；
    针对每个栅格索引序列，按照所述栅格索引序列对应的光路关联的每条线束在各个栅格处的线束高度以及所述栅格对应的障碍物高度，对所述栅格索引序列指示的每个栅 格对应的最低线束高度和有效线束数目进行调整，直至调整完最后一个栅格索引序列中每个栅格对应的最低线束高度和有效线束数目后，得到所述当前雷达盲区栅格地图。
  12. 根据权利要求11所述的处理方法，其中，按照以下方式对一个栅格索引序列指示的每个栅格对应的最低线束高度和有效线束数目进行调整：
    针对一个栅格索引序列中的当前栅格，依次比较所述栅格索引序列对应的每条线束在所述当前栅格中的线束高度与所述当前栅格对应的障碍物高度，将线束高度高于障碍物高度的线束作为所述当前栅格对应的有效线束；
    基于所述当前栅格对应的有效线束的线束高度对所述当前栅格的最低线束高度进行调整；以及基于在所述栅格索引序列对应的线束中，所述当前栅格对应的有效线束数目，对所述当前栅格对应的有效线束数目进行调整；
    将所述当前栅格对应的有效线束作为射入所述栅格索引序列中下一个栅格的线束，并将所述下一个栅格作为当前栅格，继续执行对所述当前栅格对应的最低线束高度和有效线束数目进行调整的步骤，直至射入当前栅格的每个线束的线束高度均低于当前栅格对应的障碍物高度的情况下，得到所述栅格索引中每个栅格在本次调整后对应的最低线束高度以及有效线束数目。
  13. 根据权利要求10至12任一所述的处理方法，其中，所述基于所述当前雷达盲区栅格地图以及预设目标对象的轮廓信息，确定针对该预设目标对象的雷达盲区信息，包括：
    基于所述预设目标对象的轮廓信息，确定所述雷达装置扫描到所述预设目标对象的有效线束数目以及最高线束高度；
    基于所述当前雷达盲区栅格地图中，每个栅格对应的所述有效线束数目以及扫描到所述预设目标对象的有效线束数目，和，每个栅格对应的最低线束高度以及扫描到所述预设目标对象的最高线束高度中的至少之一，确定所述预设目标对象在所述当前雷达盲区栅格地图中对应的雷达盲区。
  14. 一种雷达装置采集的数据的处理装置，包括：
    获取模块，配置为获取所述雷达装置采集的多帧点云数据；
    确定模块，配置为根据所述多帧点云数据，确定点云数据缺失结果；所述点云数据缺失结果包括所述点云数据的具体缺失部分；
    提示模块，配置为根据所述点云数据的缺失结果，发出提示信息；其中，所述提示信息用于指示所述雷达装置的异常类型。
  15. 根据权利要求14所述的处理装置，其中，所述点云数据缺失结果包括所述雷达装置的至少一个无线电波发射器对应的点云数据存在缺失；
    所述确定模块配置为在第一持续时间中的每一帧点云数据中，在所述至少一个无线电波发射器对应的点云数据均不存在的情况下，确定所述至少一个无线电波发射器对应的点云数据缺失；
    所述提示模块配置为发出提示信息；其中，所述提示信息用于指示所述雷达装置中的所述至少一个无线电波发射器存在异常。
  16. 根据权利要求14所述的处理装置，其中，所述点云数据缺失结果包括至少一个采集角度对应的点云数据存在缺失；
    所述确定模块配置为在第二持续时间中的每一帧点云数据中，存在所述至少一个采集角度对应的点云数据不存在，且在所述第二持续时间中的各帧点云数据中对应的不存在的点云数据的采集角度不完全相同的情况下，确定随机采集角度对应的点云数据缺失；
    所述提示模块配置为发出提示信息；其中，所述提示信息用于指示所述雷达装置存在数据包传输异常。
  17. 根据权利要求14所述的处理装置，其中，所述点云数据缺失结果包括至少一个 采集角度对应的点云数据存在缺失；
    所述确定模块配置为在第三持续时间中的每一帧点云数据中，在所述至少一个采集角度对应的点云数据不存在，且在所述第三持续时间中的各帧点云数据中对应的不存在的点云数据的采集角度相同的情况下，确定特定采集角度对应的点云数据缺失；
    所述提示模块配置为发出提示信息；其中，所述提示信息用于指示所述雷达装置存在遮挡异常。
  18. 根据权利要求14所述的处理装置，其中，所述确定模块配置为确定所述多帧点云数据中存在至少一帧点云数据包含的点云点的总数量低于第一设定阈值的情况下，确定所述至少一帧点云数据中存在缺失；
    所述提示模块配置为发出提示信息；其中，所述提示信息用于指示所述雷达装置存在位置异常。
  19. 一种电子设备，包括：处理器、存储器和总线，所述存储器存储有所述处理器可执行的机器可读指令，在所述电子设备运行的情况下，所述处理器与所述存储器之间通过总线通信，所述机器可读指令被所述处理器执行时执行如权利要求1至13任一所述的处理方法的步骤。
  20. 一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行如权利要求1至13任一所述的处理方法的步骤。
  21. 一种计算机程序，所述计算机程序包括计算机可读代码，在所述计算机可读代码在电子设备中运行的情况下，所述电子设备的处理器执行用于实现如权利要求1至13任一所述的处理方法的步骤。
PCT/CN2021/089447 2020-06-30 2021-04-23 数据的处理方法、装置、设备、存储介质及程序 WO2022001326A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1020217042601A KR20220011735A (ko) 2020-06-30 2021-04-23 데이터 처리 방법, 장치, 기기, 저장매체 및 프로그램
JP2021564302A JP2022550495A (ja) 2020-06-30 2021-04-23 データの処理方法、装置、機器、記憶媒体及びプログラム

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010619847.3A CN113866791A (zh) 2020-06-30 2020-06-30 雷达装置采集的数据的处理方法及处理装置
CN202010619847.3 2020-06-30

Publications (1)

Publication Number Publication Date
WO2022001326A1 true WO2022001326A1 (zh) 2022-01-06

Family

ID=78981762

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/089447 WO2022001326A1 (zh) 2020-06-30 2021-04-23 数据的处理方法、装置、设备、存储介质及程序

Country Status (4)

Country Link
JP (1) JP2022550495A (zh)
KR (1) KR20220011735A (zh)
CN (1) CN113866791A (zh)
WO (1) WO2022001326A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114782438A (zh) * 2022-06-20 2022-07-22 深圳市信润富联数字科技有限公司 物体点云修正方法、装置、电子设备和存储介质
CN114822035A (zh) * 2022-05-09 2022-07-29 北京亮道智能汽车技术有限公司 一种路侧感知设备异常识别方法及路侧感知融合系统
CN114897895A (zh) * 2022-07-12 2022-08-12 深圳市信润富联数字科技有限公司 点云调平方法、装置、电子设备及存储介质
CN115032618A (zh) * 2022-08-12 2022-09-09 深圳市欢创科技有限公司 应用于激光雷达的盲区修复方法、装置及激光雷达
CN115880442A (zh) * 2023-02-06 2023-03-31 宝略科技(浙江)有限公司 一种基于激光扫描的三维模型重建方法以及系统
WO2024065173A1 (en) * 2022-09-27 2024-04-04 Apollo Intelligent Driving Technology (Beijing) Co., Ltd. Cloud based scanning for detection of sensors malfunction for autonomous vehicles

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114545443A (zh) * 2022-02-09 2022-05-27 北京三快在线科技有限公司 一种盲区识别方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103913728A (zh) * 2014-04-01 2014-07-09 中国人民解放军总装备部军械技术研究所 一种便携式雷达综合测试仪及测试方法
WO2017097654A1 (de) * 2015-12-09 2017-06-15 Valeo Schalter Und Sensoren Gmbh Verfahren zum erkennen einer funktionsbeeinträchtigung eines laserscanners, laserscanner und kraftfahrzeug
CN109085608A (zh) * 2018-09-12 2018-12-25 奇瑞汽车股份有限公司 车辆周围障碍物检测方法及装置
CN109407064A (zh) * 2018-12-12 2019-03-01 北京遥感设备研究所 一种雷达设备图像传输故障诊断方法
CN110007315A (zh) * 2019-04-09 2019-07-12 深圳市速腾聚创科技有限公司 激光雷达检测设备、检测方法和控制系统
CN110133658A (zh) * 2019-04-28 2019-08-16 惠州市德赛西威智能交通技术研究院有限公司 一种应用于车载雷达的故障检测方法以及系统
CN111044985A (zh) * 2019-12-06 2020-04-21 浙江吉利汽车研究院有限公司 车用毫米波雷达的异常检测方法及异常检测系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5465128B2 (ja) * 2010-08-11 2014-04-09 株式会社トプコン 点群位置データ処理装置、点群位置データ処理システム、点群位置データ処理方法、および点群位置データ処理プログラム
IE86364B1 (en) * 2012-06-11 2014-03-26 Actionphoto Internat As Closed loop 3D video scanner for generation of textured 3D point cloud
US10176589B2 (en) * 2017-01-31 2019-01-08 Mitsubishi Electric Research Labroatories, Inc. Method and system for completing point clouds using planar segments
CN109817021B (zh) * 2019-01-15 2021-11-02 阿波罗智能技术(北京)有限公司 一种激光雷达路侧盲区交通参与者避让方法和装置
CN110879401B (zh) * 2019-12-06 2023-08-04 南京理工大学 基于相机和激光雷达的无人驾驶平台实时目标3d检测方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103913728A (zh) * 2014-04-01 2014-07-09 中国人民解放军总装备部军械技术研究所 一种便携式雷达综合测试仪及测试方法
WO2017097654A1 (de) * 2015-12-09 2017-06-15 Valeo Schalter Und Sensoren Gmbh Verfahren zum erkennen einer funktionsbeeinträchtigung eines laserscanners, laserscanner und kraftfahrzeug
CN109085608A (zh) * 2018-09-12 2018-12-25 奇瑞汽车股份有限公司 车辆周围障碍物检测方法及装置
CN109407064A (zh) * 2018-12-12 2019-03-01 北京遥感设备研究所 一种雷达设备图像传输故障诊断方法
CN110007315A (zh) * 2019-04-09 2019-07-12 深圳市速腾聚创科技有限公司 激光雷达检测设备、检测方法和控制系统
CN110133658A (zh) * 2019-04-28 2019-08-16 惠州市德赛西威智能交通技术研究院有限公司 一种应用于车载雷达的故障检测方法以及系统
CN111044985A (zh) * 2019-12-06 2020-04-21 浙江吉利汽车研究院有限公司 车用毫米波雷达的异常检测方法及异常检测系统

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114822035A (zh) * 2022-05-09 2022-07-29 北京亮道智能汽车技术有限公司 一种路侧感知设备异常识别方法及路侧感知融合系统
CN114782438A (zh) * 2022-06-20 2022-07-22 深圳市信润富联数字科技有限公司 物体点云修正方法、装置、电子设备和存储介质
CN114782438B (zh) * 2022-06-20 2022-09-16 深圳市信润富联数字科技有限公司 物体点云修正方法、装置、电子设备和存储介质
CN114897895A (zh) * 2022-07-12 2022-08-12 深圳市信润富联数字科技有限公司 点云调平方法、装置、电子设备及存储介质
CN115032618A (zh) * 2022-08-12 2022-09-09 深圳市欢创科技有限公司 应用于激光雷达的盲区修复方法、装置及激光雷达
WO2024065173A1 (en) * 2022-09-27 2024-04-04 Apollo Intelligent Driving Technology (Beijing) Co., Ltd. Cloud based scanning for detection of sensors malfunction for autonomous vehicles
CN115880442A (zh) * 2023-02-06 2023-03-31 宝略科技(浙江)有限公司 一种基于激光扫描的三维模型重建方法以及系统

Also Published As

Publication number Publication date
KR20220011735A (ko) 2022-01-28
CN113866791A (zh) 2021-12-31
JP2022550495A (ja) 2022-12-02

Similar Documents

Publication Publication Date Title
WO2022001326A1 (zh) 数据的处理方法、装置、设备、存储介质及程序
CN110286387B (zh) 应用于自动驾驶系统的障碍物检测方法、装置及存储介质
EP3798974B1 (en) Method and apparatus for detecting ground point cloud points
US20210263159A1 (en) Information processing method, system, device and computer storage medium
CN108509820B (zh) 障碍物分割方法及装置、计算机设备及可读介质
CN106919908B (zh) 障碍物识别方法及装置、计算机设备及可读介质
CN106934347B (zh) 障碍物识别方法及装置、计算机设备及可读介质
WO2022001322A1 (zh) 一种车辆控制方法、装置、电子设备及存储介质
CN106951847A (zh) 障碍物检测方法、装置、设备及存储介质
CN112347999A (zh) 障碍物识别模型训练方法、障碍物识别方法、装置及系统
KR102428050B1 (ko) 정보 보완 방법, 차선 인식 방법, 지능형 주행 방법 및 관련 제품
WO2022160896A1 (zh) 集装箱卡车与起重机的对位方法及相关设备
CN108710367B (zh) 激光数据识别方法、装置、机器人及存储介质
CN111666876B (zh) 用于检测障碍物的方法、装置、电子设备和路侧设备
CN111988524A (zh) 一种无人机与摄像头协同避障方法、服务器及存储介质
WO2022087916A1 (zh) 定位方法、装置、电子设备和存储介质
CN111337898B (zh) 激光点云的处理方法、装置、设备及存储介质
CN113454558A (zh) 障碍物检测方法、装置、无人机和存储介质
CN111027522A (zh) 基于深度学习的探鸟定位系统
CN113650016B (zh) 机械臂路径规划系统、方法、装置、电子设备及存储介质
CN115236693A (zh) 轨道侵限检测方法、装置、电子设备和存储介质
CN113776520B (zh) 地图构建、使用方法、装置、机器人和介质
CN115909253A (zh) 一种目标检测、模型训练方法、装置、设备及存储介质
CN114779207A (zh) 噪声数据识别方法、装置及存储介质
CN115690224A (zh) 雷达和相机的外参标定方法、电子设备及存储介质

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021564302

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20217042601

Country of ref document: KR

Kind code of ref document: A

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

Ref document number: 21832035

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: 21832035

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 05/07/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21832035

Country of ref document: EP

Kind code of ref document: A1