WO2022017189A1 - 汽车雷达的目标筛选方法、装置、设备和存储介质 - Google Patents

汽车雷达的目标筛选方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2022017189A1
WO2022017189A1 PCT/CN2021/105182 CN2021105182W WO2022017189A1 WO 2022017189 A1 WO2022017189 A1 WO 2022017189A1 CN 2021105182 W CN2021105182 W CN 2021105182W WO 2022017189 A1 WO2022017189 A1 WO 2022017189A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
lane
target
distance
output
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2021/105182
Other languages
English (en)
French (fr)
Inventor
蔡世民
崔茂源
孙连明
谭明伟
冷长峰
韩贤贤
徐刚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
FAW Group Corp
Original Assignee
FAW Group Corp
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 FAW Group Corp filed Critical FAW Group Corp
Publication of WO2022017189A1 publication Critical patent/WO2022017189A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous 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
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
    • G01S7/411—Identification of targets based on measurements of radar reflectivity

Definitions

  • the embodiments of the present application relate to driving assistance and automatic driving technologies, for example, to a target screening method, apparatus, device, and storage medium for automotive radar.
  • millimeter-wave radar Because millimeter-wave radar has the characteristics of long detection distance, high detection accuracy and little impact on the environment, millimeter-wave radar is more and more widely used in the field of driver assistance and automatic driving.
  • the millimeter-wave radar can only output a limited number of targets.
  • the false alarm rate of millimeter wave radar for target detection is relatively high, and the false alarm rate for static target detection is higher (due to the influence of ground clutter).
  • the automotive Ethernet is in its infancy, the application has just started, and the cost is relatively high.
  • the traditional controller area network (CAN) and the variable rate CAN (CAN with Flexible) are mostly used for millimeter wave radar signal transmission.
  • Data-Rate, CAN-FD) communication due to the limited transmission bandwidth, usually the radar can only output 16 targets (the increase of output targets will cause the network load to be too high and cause network congestion). Therefore, when the number of targets output by the radar is limited, how to obtain more effective targets for the upper-layer system becomes an urgent problem to be solved.
  • Embodiments of the present application provide a target screening method, device, device, and storage medium for automotive radar, which can achieve more effective target objects when the number of targets output by the radar is limited.
  • An embodiment of the present application provides a target screening method for an automotive radar, including: acquiring state information of a vehicle and attribute information of a target object; predicting a driving trajectory of the vehicle according to the state information, and determining Lane area; match the attribute information and the lane area with a preset screening principle, and determine the target object to be output according to the matching result, wherein the preset screening principle is used to detect the target object to filter.
  • the embodiment of the present application further provides a target screening device, comprising: an information acquisition module configured to acquire state information of the vehicle and attribute information of a target object; a lane determination module configured to predict the vehicle according to the state information The driving trajectory is determined according to the driving trajectory, and the lane area is determined; the target matching module is set to match the attribute information and the lane area with the preset screening principle, and determine the target object to be output according to the matching result, wherein the The preset screening principle is used to screen the target object detected by the automotive radar.
  • Embodiments of the present application also provide a device, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements any of the methods provided by the embodiments of the present application when the processor executes the program.
  • a device including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor implements any of the methods provided by the embodiments of the present application when the processor executes the program. 1.
  • Embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, implements the target screening method for an automotive radar according to any one of the embodiments of the present application.
  • FIG. 1 is a flowchart of a target screening method for an automotive radar provided in Embodiment 1 of the present application;
  • FIG. 2 is a flowchart of a target screening method for an automotive radar provided in Embodiment 2 of the present application;
  • FIG. 2a is a flowchart of the screening principle of a target screening method for automotive radar provided in Embodiment 2 of the present application;
  • FIG. 3 is a working schematic diagram of a target screening method for automotive radar provided in Embodiment 2 of the present application;
  • FIG. 4 is a working schematic diagram of another target screening method for automotive radar provided in Embodiment 2 of the present application.
  • FIG. 5 is a flowchart of a target screening method for an automotive radar provided in Embodiment 3 of the present application;
  • FIG. 6 is a schematic structural diagram of a target screening device for an automotive radar provided in Embodiment 4 of the present application;
  • FIG. 7 is a schematic structural diagram of an in-vehicle device provided in Embodiment 5 of the present application.
  • FIG. 1 is a flowchart of a target screening method for an automotive radar provided in Embodiment 1 of the present application. This embodiment is applicable to the situation of screening obstacles for driving assistance and automatic driving.
  • the method can be executed by a target screening device, and the device can be implemented in a software/hardware manner.
  • the device can be configured in on-board equipment. As shown in Figure 1, the method includes the following steps.
  • step S110 the state information of the vehicle and the attribute information of the target object are acquired.
  • the state information of the own vehicle refers to information such as the yaw rate and the steering wheel angle of the own vehicle, and is used to predict the driving trajectory of the own vehicle.
  • the target object refers to the target in front of the vehicle, which can be detected by the forward millimeter wave radar.
  • the attribute information of the target object includes the type, motion state, and position of the target object.
  • the motion state of the target object includes: dynamic target and static target.
  • Dynamic targets include four-wheeled vehicles, two-wheeled vehicles, pedestrians and/or unknown targets.
  • Step S120 Predict the driving track of the vehicle according to the state information, and determine the lane area according to the driving track.
  • the area in front of the vehicle needs to be divided, which can be divided according to the lane. Since the radar cannot detect the lane line, the target screening device can predict the driving trajectory of the vehicle according to the state information, and determine the lane area according to the driving trajectory. For example, the target screening device can be based on the car radar. The obtained information such as the yaw rate and steering wheel angle of the vehicle can predict the driving trajectory of the vehicle, and then predict the lane area.
  • the lane area may include the area of the own lane, the area of the left N lanes and the right N lanes in the same prescribed driving direction of the own lane, where N is an integer.
  • determining the lane area according to the driving trajectory may include: taking the boundary located on the left side of the driving trajectory and the distance from the driving trajectory as the first set distance and the boundary located on the right side of the driving trajectory and between the driving trajectory and the driving trajectory.
  • the area between the boundary whose distance is the first set distance is determined as the own lane; the boundary which is located on the left side of the driving track and the distance from the driving track is the second set distance and the boundary which is located on the left side of the driving track and has a distance from the driving track.
  • the area between the boundary of the first set distance from the driving track is determined as the left lane; the boundary located on the right side of the driving track and the distance from the driving track is the second set distance.
  • the area between the right side of the driving track and the boundary of the distance from the driving track is the first set distance is determined as the right lane; the left side of the driving track and the distance from the driving track is the third set.
  • the area between the boundary of the fixed distance and the boundary located on the left side of the driving track and the distance from the driving track is the second set distance is determined as the second left lane; the area located on the right side of the driving track and between the driving track
  • the area between the boundary whose distance is the third set distance and the boundary located on the right side of the travel track and whose distance from the travel track is the second set distance is determined as the second right lane.
  • the area located on the left side of the vehicle's running track is 0-1.8m away from the vehicle's running track
  • the area located on the right side of the vehicle's running track is 0-1.8m away from the vehicle's running track.
  • the area located on the left side of the vehicle's driving track and 1.8-6m away from the vehicle's driving track is determined as the left lane, and the area located on the right side of the vehicle's driving track and 1.8-6m away from the vehicle's driving track is determined as the right lane.
  • the area located on the left side of the vehicle's driving track and 6-10m away from the vehicle's driving track is determined as the second left area, and the area located on the right side of the vehicle's driving track and 6-10m away from the vehicle's driving track is determined as the right area.
  • the driving trajectory of the vehicle can also be acquired according to the camera of the vehicle, and the driving trajectory is sent to the vehicle radar, and the lane area is determined according to the driving trajectory.
  • Step S130 Match the attribute information and the lane area with the preset screening principle, and determine the target object to be output according to the matching result.
  • the screening principle is used to screen the target objects detected by the automotive radar. Since the automotive radar can detect all target objects in front of the vehicle, the number of target objects that the automotive radar can output is limited during the driving process of the vehicle. Therefore, according to the physical characteristics of the automotive radar and the requirements of the upper system, the output of the automotive radar is Under the premise that the number of target objects is limited, it is necessary to output as many valid target objects as possible according to the preset screening principle.
  • the screening principle may include a lane division dimension, a target dynamic and static category dimension, and/or a static target sparse processing dimension, and the like.
  • the lane division dimension refers to outputting the target object according to the lane area where the vehicle and the target object are located, for example, outputting the target object closest to the vehicle in the driving direction of the vehicle in this lane, and outputting the vehicle traveling along the left lane and/or the right lane.
  • the target object closest to the vehicle in the direction, or the target object closest to the vehicle along the driving direction of the vehicle in the second left lane and/or the second right lane is output.
  • the dynamic and static category dimension of the target refers to the output of the target object according to the dynamic and static state of the target object.
  • the dimension of static target sparse processing refers to outputting a static target whose adjacent lanes in the current lane and/or the separation distance along the driving direction of the vehicle in the current lane satisfy certain conditions.
  • Conditional static target output the separation distance in the left lane and the right lane along the vehicle's driving direction that satisfies the preset second condition static target, and/or output the left and right lanes along the vehicle's driving direction
  • the separation distance A static target that satisfies the preset third condition.
  • the automotive radar Since the automotive radar is mainly responsible for the target detection in front of the vehicle, it can directly output the target object in front of the vehicle that is closest to the vehicle based on the lane division dimension.
  • the automotive radar will output many target objects one after another. If it is not suppressed, the limited target objects will be filled up quickly, and the dynamic targets a little further away will be missed, and the static targets will be sparsely processed.
  • the dimension can control the output number of static targets. When the number of target objects output by the automotive radar is limited, more effective target objects can be obtained.
  • the screening principle may also include a dynamic target classification dimension.
  • Dynamic targets can be divided into four categories: four-wheeled vehicles, two-wheeled vehicles, pedestrians and unknown targets. Due to the large radar reflection area of vehicle targets, the false alarm rate of vehicle radar detection of vehicle targets is low. Vehicles driving on the road Focus on the vehicle target.
  • the dynamic target classification dimension refers to preferentially outputting vehicle targets, for example, preferentially outputting four-wheeled vehicles.
  • the screening principle may further include the dimension of the dangerous vehicle ahead, where the dangerous vehicle in front refers to the most dangerous vehicle target in front of the vehicle.
  • the dimension of the dangerous vehicle ahead refers to the priority output of the vehicle target closest to the vehicle in the lane.
  • the screening principle may include at least one of the following principles sorted by priority: outputting the two vehicle targets closest to the vehicle in the driving direction of the vehicle in the lane; outputting the distance in the lane along the driving direction of the vehicle; The 2 closest dynamic targets of the vehicle; output the 2 static targets closest to the vehicle in the driving direction of the vehicle in this lane; output the closest dynamic target to the vehicle along the driving direction of the vehicle in the left lane; output the right A dynamic target closest to the vehicle in the driving direction of the vehicle in one lane; Sort with other dynamic targets in the right lane, and output the first set number of other dynamic targets according to the sorting result; output other static targets whose separation distance along the vehicle's driving direction in this lane satisfies the preset first condition; output the left The distance between the first lane and the first right lane along the vehicle's driving direction satisfies the static target of the second preset condition; The distance between the dynamic target and the vehicle, sort other dynamic targets in this lane, the first left lane, the first right
  • the screening principle also includes: during the movement of the vehicle, match the detected static target with the outputted static target, determine the detected and outputted static target according to the matching result, and output the detected and outputted static target.
  • For the output of the static target during the movement of the vehicle, ensure the output of the static target closest to the vehicle. If the outputted static target does not disappear, do not delete it. Continue to detect the static target on the basis of the outputted static target. And output the detected static target that has been exported.
  • the state information of the vehicle is obtained, the driving trajectory of the vehicle is predicted, the lane area is determined according to the driving trajectory, the acquired attribute information and lane area of the target object are matched with the preset screening principle, and according to the matching result Determining the target object to be output, under the circumstance that the number of target objects output by the automotive radar is limited, more effective target objects can be obtained, avoiding too many unconcerned target objects occupying limited network resources.
  • FIG. 2 is a flowchart of a target screening method for an automotive radar provided in Embodiment 2 of the present application. This embodiment is described on the basis of the above-mentioned embodiment. As shown in FIG. 2 , the method includes the following steps.
  • step S210 the state information of the vehicle and the attribute information of the target object are acquired.
  • Step S220 Predict the driving track of the vehicle according to the state information, and determine the lane area according to the driving track.
  • the area is determined as this lane; the boundary located on the left side of the driving track and the distance from the driving track is the second set distance and the distance on the left side of the driving track and the distance from the driving track is the first set distance.
  • the area between the boundaries of is determined as the left lane; the distance between the boundary located on the right side of the driving trajectory and the distance from the driving trajectory is the second set distance and the distance between the boundary located on the right side of the driving trajectory and the driving trajectory.
  • the area between the boundaries of the first set distance is determined as the right lane; the boundary located on the left side of the driving track and the distance between the third set distance and the boundary of the third set distance is located on the left side of the driving track and is opposite to the driving track.
  • the area between the boundaries where the distance between the trajectories is the second set distance is determined as the second left lane;
  • Step S230 Determine the type of the target object according to the attribute information.
  • Types of target objects include: dynamic targets and static targets.
  • Dynamic targets include target object types such as four-wheeled vehicles, two-wheeled vehicles, pedestrians, and/or unknown targets.
  • Step S240 Determine the lane where the target object is located according to the lateral distance between the target object and the vehicle.
  • FIG. 3 is a working schematic diagram of a target screening method for an automotive radar provided in Embodiment 2 of the present application. As shown in Fig.
  • the area located on the left side of the vehicle's running track and the distance from the vehicle's running track is 0-1.8m and the area on the right side of the vehicle's running track with a distance of 0-1.8m from the vehicle's running track are determined as In this lane, the area located on the left side of the vehicle's driving track and 1.8-6m away from the vehicle's driving track is determined as the left lane, and the area located on the right side of the vehicle's driving track and 1.8-6m away from the vehicle's driving track is determined.
  • the area located on the left side of the vehicle's driving track and 6-10m away from the vehicle's driving track is determined as the second left area, and the area located on the right side of the vehicle's driving track is 6-10m away from the vehicle's driving track.
  • the area is identified as the second right lane.
  • the target object is located on the left side of the vehicle's driving track and 1m away from the vehicle's driving track, determine that the lane where the target object is located is the same lane; if the target object is located on the right side of the vehicle's driving track, 3m away from the vehicle's driving track If the target object is located in an area that is 8m away from the vehicle's driving track on the left side of the vehicle's driving track, it is determined that the target object's lane is the second left lane.
  • Step S250 Based on the type of the target object and the lane where it is located, select the target object to be output from the target objects according to a preset screening principle.
  • Fig. 2a is a flowchart of a screening principle of a target screening method for an automotive radar provided in Embodiment 2 of the present application. As shown in FIG. 2a, step S250 may include the following steps.
  • Step S2501 when the target objects are the two closest vehicle targets in the vehicle's driving direction in the current lane to the vehicle, output the two vehicle targets in the current lane along the vehicle's driving direction that are closest to the vehicle.
  • vehicle objects (1) and (2) are the two vehicle objects closest to the vehicle in the driving direction of the vehicle in this lane, and vehicle objects (1) and (2) are output in sequence.
  • Step S2502 when the target objects are the two closest dynamic targets to the vehicle in the driving direction of the vehicle in the current lane, output the two dynamic targets closest to the vehicle in the driving direction of the vehicle in the current lane.
  • the dynamic targets (3) and (4) are the two dynamic targets closest to the vehicle in the driving direction of the vehicle in the current lane, and the dynamic targets (3) and (4) are output in sequence.
  • Step S2503 when the target objects are the two closest static objects to the vehicle in the driving direction of the vehicle in the current lane, output the two static objects closest to the vehicle in the driving direction of the vehicle in the current lane.
  • the static targets (5) and (6) are the two static targets closest to the vehicle in the driving direction of the vehicle in the lane, and the static targets (5) and (6) are output in sequence.
  • Step S2504 when the target object is a dynamic target in the left lane along the driving direction of the vehicle closest to the vehicle, output the dynamic target in the left lane along the vehicle driving direction closest to the vehicle.
  • the dynamic target (7) is a dynamic target in the left lane that is closest to the vehicle in the driving direction of the vehicle, and the dynamic target (7) is output.
  • Step S2505 when the target object is a dynamic target in the right lane along the driving direction of the vehicle that is closest to the vehicle, output the closest dynamic target to the vehicle along the vehicle driving direction in the right lane.
  • the dynamic target ( 8 ) is a dynamic target in the right lane that is closest to the vehicle along the vehicle's driving direction, and the dynamic target ( 8 ) is output.
  • Step S2506 Based on the distances between other dynamic targets in the current lane, the left lane and the right lane along the vehicle's driving direction and the vehicle, sort other dynamic targets in the current lane, the left lane and the right lane, and according to the sorting results Output the first set number of other dynamic objects.
  • the dynamic target (9) is based on the distances between other dynamic targets in the current lane, the left lane and the right lane and the vehicle in the driving direction of the vehicle.
  • the other dynamic targets in a lane are sorted, and one dynamic target is output according to the sorting result.
  • Step S2507 when the target object is other static targets whose separation distance along the vehicle's driving direction in the current lane satisfies the preset first condition, output other static targets whose separation distance along the vehicle's driving direction satisfies the preset first condition in the current lane .
  • the preset first condition may be based on the current static target, the static target whose distance along the vehicle traveling direction and the current static target is less than or equal to the separation distance is not output, and the static target whose distance is greater than the separation distance is output.
  • other static objects (10) in the current lane are output at intervals of 2 m along the vehicle traveling direction. That is, taking the current static target as the base point, the distance from the current static target along the driving direction of the vehicle is not output when the distance from the current static target is greater than 0 and less than or equal to 2m, and the static target with the distance from the current static target greater than 2m is output.
  • the 2 static targets for this lane that were output earlier are also applicable to this step.
  • the preset first condition can also be based on the current static target, and determine whether there is a separation distance along the driving direction of the vehicle. If the separation distance exists along the driving direction of the vehicle, the distance between the The static target whose distance is less than or equal to the separation distance is not output, and the static target whose distance is greater than the separation distance is output; if the separation distance does not exist along the driving direction of the vehicle, the static target is output from near to far along the driving direction of the vehicle. For example, taking 2m as the interval distance, along the direction of the vehicle, if the distance between static targets is 2m, the static target whose distance from the current static target is greater than 0 and less than or equal to 2m will not be output, and the static target greater than 2m will not be output. Output, if the separation distance between static objects does not exist 2m, the static objects are output from near to far along the vehicle's running direction.
  • Step S2508 When the target object is a static target whose separation distance in the left lane and the right lane along the vehicle's driving direction satisfies the preset second condition, output the separation distance along the vehicle's driving direction in the left lane and the right lane.
  • a static target that presets the second condition.
  • the other static targets in the left lane and the right lane along the vehicle's driving direction are unified and sorted by the interval distances that satisfy the preset second condition, and the static targets are output according to the sorting result.
  • the preset second condition may be based on the current static target, the static target whose distance from the current static target in the driving direction of the vehicle is less than or equal to the separation distance is not output, and the static target whose distance is greater than the separation distance is output.
  • the car radar detects that there are 5 static targets in the left lane and 3 static targets in the right lane at the separation distance that satisfies the preset second condition.
  • the 8 static targets are sorted according to the distance from the vehicle from near to far. , which outputs a set number of static targets.
  • the targets in the left lane and the right lane are screened at 5m intervals along the vehicle's driving direction, and the static targets in the left and right lanes are screened and mixed together, and the targets are screened along the vehicle's driving direction.
  • the distance to the vehicle is sorted from near to far, and static targets (11), (12) and (13) are output.
  • Step S2509 Based on the distances between other dynamic targets in the current lane, the first left lane, the first right lane, the second left lane and the second right lane along the vehicle's driving direction and the vehicle, the The lane and other dynamic targets in the second right lane are sorted, and a second set number of other dynamic targets are output according to the sorting result.
  • the dynamic target (14) is based on the distance from the vehicle along the driving direction of the vehicle, for other dynamics in the own lane, the first left lane, the first right lane, the second left lane and the second right lane.
  • the targets are sorted, and 1 dynamic target is output according to the sorting result.
  • Step S2510 when the target object is a static target whose separation distance along the vehicle's driving direction in the second left lane and the second right lane satisfies the preset third condition, output the separation distance along the vehicle's driving direction in the second left lane and the second right lane.
  • a static target that presets the third condition.
  • the targets in the second left lane and the second right lane are screened at 5m intervals along the vehicle's driving direction, and the static targets in the second left lane and the second right lane are screened and mixed together.
  • the distance to the vehicle is sorted from near to far, and static targets (15) and (16) are output.
  • FIG. 4 is a working schematic diagram of another target screening method for automotive radar provided in Embodiment 2 of the present application.
  • Step S260 judging whether the target object to be output contains duplicate target objects, if the target object to be output contains duplicate target objects, then execute step S270, if the target object to be output does not contain duplicate target objects, execute step S280 .
  • Step S270 output the non-repeated target objects to be output, and select one of the repeated target objects for output.
  • Step S280 output the target object to be output.
  • the embodiment of the present application obtains the state information of the vehicle and the attribute information of the target object, predicts the driving trajectory of the vehicle according to the state information, determines the lane area according to the driving trajectory, determines the type of the target object according to the attribute information, and determines the type of the target object according to the attribute information.
  • FIG. 5 is a flowchart of a target screening method for an automotive radar provided in Embodiment 3 of the present application. This embodiment is described on the basis of the above-mentioned embodiment. As shown in FIG. 5 , the method includes the following steps.
  • Step S310 Periodically acquire the state information of the vehicle and the attribute information of the target object according to a preset threshold.
  • the state information of the vehicle and the attribute information of the target object detected by the automotive radar are periodically obtained according to a preset threshold, for example, the state information of the vehicle and the attribute information of the target object are obtained at a period of 50 milliseconds.
  • the status information of the vehicle and the attribute information of the target object detected by the vehicle radar may also be transmitted through the vehicle Ethernet, which is not limited in this application.
  • Step S320 Predict the driving track of the vehicle according to the state information, and determine the lane area according to the driving track.
  • Step S330 Periodically match the attribute information and the lane area with the preset screening principle according to the preset threshold, and determine the target object to be output according to the matching result.
  • the target object to be output is determined according to the matching result.
  • the status information of the vehicle and the attribute information of the target object are obtained every 50 milliseconds, the driving trajectory of the vehicle is predicted according to the status information, the lane area is determined according to the driving trajectory, a matching is performed according to the preset screening principle, and the matching result is determined.
  • the target object to be output is performed.
  • Step S340 sending the target object to be output to the domain controller.
  • the domain controller can be set up for positioning, path planning, decision control, wireless communication and/or high-speed communication, can have a built-in processor, and can also be connected to multiple cameras, millimeter-wave radar and/or lidar and other devices.
  • the embodiment of the present application periodically obtains the state information of the vehicle and the attribute information of the target object according to the preset threshold, predicts the driving trajectory of the vehicle according to the state information, determines the lane area according to the driving trajectory, and compares the attribute information and the lane area with the preset According to the screening principle of the filter, the matching is performed periodically according to the preset threshold, the target object to be output is determined according to the matching result, and the target object to be output is sent to the domain controller.
  • the target object in the surrounding environment of the vehicle is detected by the car radar, and the target object is screened periodically according to the preset screening principle with a preset threshold value, and the radar data of the target object to be output that conforms to the screening principle is sent to the domain controller.
  • the target object can be screened in real time, the accuracy of target screening is improved, and the obstacle in front of the vehicle can be monitored in real time.
  • FIG. 6 is a schematic structural diagram of a target screening device for an automotive radar provided in Embodiment 4 of the present application.
  • the device can be implemented by software and/or hardware, and can generally be integrated into equipment, and can obtain more effective target objects through target screening of automotive radar under the condition of limited target output. As shown in FIG.
  • the device includes: an information acquisition module 410 configured to acquire the state information of the vehicle and attribute information of the target object; a lane determination module 420 configured to predict the driving trajectory of the vehicle according to the state information, according to The driving track determines the lane area; the target matching module 430 is configured to match the attribute information and the lane area with a preset screening principle, and determine the target object to be output according to the matching result, wherein the preset The screening principle is used to screen the target objects detected by the automotive radar.
  • the lane determination module 420 is configured to: set the boundary located on the left side of the driving trajectory and the distance from the driving trajectory as a first set distance to the boundary located on the right side of the driving trajectory. And the area between the boundaries with the distance from the driving track being the first set distance is determined as the lane; the distance between the left side of the driving track and the driving track is the second set distance.
  • the area between the boundary of the fixed distance and the boundary located on the left side of the driving trajectory and the distance from the driving trajectory is the first set distance is determined as the left lane; the area on the right side of the driving trajectory is determined as the left lane and the distance from the travel track is the second set distance boundary and the area located on the right side of the travel track and the distance from the travel track is the first set distance.
  • the boundary located on the left side of the driving track and the distance from the driving track is the third set distance and the boundary located on the left side of the driving track and between the driving track
  • the area between the boundaries whose distance is the second set distance is determined to be the second left lane
  • the area between the right side of the travel track and the boundary with the distance between the travel track being the second set distance is determined as the second right lane.
  • the target matching module 430 is configured to: determine the type of the target object according to the attribute information, wherein the type of the target object includes: a dynamic target and a static target, and the dynamic target includes a four-wheeled vehicle, a two-wheeled vehicle Types of target objects such as vehicles, pedestrians, or unknown targets; determine the lane where the target object is located according to the distance between the target object and the vehicle; when the target object is the distance from the vehicle in the driving direction of the vehicle in the own lane When there are two nearest vehicle targets, output the two nearest vehicle targets in the vehicle's driving direction in the own lane; When there are 2 dynamic targets, output the 2 dynamic targets closest to the vehicle in the driving direction of the vehicle in the current lane; when the target objects are the two closest dynamic targets to the vehicle in the driving direction of the vehicle When it is a static target, output the 2 static targets closest to the vehicle in the driving direction of the vehicle in the current lane; when the target object is the dynamic target in the left lane along the driving direction of the vehicle closest
  • the information acquisition module 410 is configured to periodically acquire the state information of the vehicle and the attribute information of the target object according to a preset threshold.
  • the target matching module 430 is configured to: periodically match the attribute information and the lane area with a preset screening principle according to a preset threshold, and determine the target object to be output according to the matching result.
  • the apparatus further includes: a target sending module, configured to send the target object to be output to the domain controller after the target object to be output is determined according to the matching result.
  • a target sending module configured to send the target object to be output to the domain controller after the target object to be output is determined according to the matching result.
  • FIG. 7 is a schematic structural diagram of an in-vehicle device provided in Embodiment 5 of the present application.
  • the in-vehicle device may be a car radar, or a radar target screening device that communicates with the car radar through a serial port and is independent of the car radar.
  • the device includes a processor 510, a memory 520, an input device 530 and an output device 540.
  • the number of processors 510 in the device may be one or more, and one processor 510 is taken as an example in FIG. 7 .
  • the processor 510 , the memory 520 , the input device 530 and the output device 540 in the device may be connected by a bus or in other ways, and the connection by a bus is taken as an example in FIG. 7 .
  • the memory 520 can be configured to store software programs, computer-executable programs and modules, such as program instructions/modules corresponding to the target screening method of the automotive radar in the embodiments of the present application (for example, a target screening device).
  • the processor 510 runs the software programs, instructions and modules stored in the memory 520 to perform various functional applications of the device and target screening of the automotive radar, that is, to implement the above-mentioned target screening method for the automotive radar.
  • the memory 520 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Additionally, memory 520 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some instances, memory 520 may also include memory located remotely from processor 510, which may be connected to the device through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the input device 530 may be configured to receive input numerical or character information, and to generate key signal input related to user settings and function control of the device.
  • the output device 540 may include a display device such as a display screen.
  • Embodiment 6 of the present application further provides a storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute a target screening method for an automotive radar when executed by a computer processor, the method comprising: acquiring the vehicle The status information and attribute information of the target object; predict the driving trajectory of the vehicle according to the status information, and determine the lane area according to the driving trajectory; match the attribute information and the lane area with the preset screening principle, and determine the target object to be output according to the matching result. , wherein the preset screening principle is used to screen the target objects detected by the automotive radar.
  • a storage medium containing computer-executable instructions provided by the embodiments of the present application, the computer-executable instructions of which are not limited to the above-mentioned method operations, and can also perform the target screening of the automotive radar provided by any embodiment of the present application. related operations in the method.
  • the present application can be realized by software and general hardware, and of course, the technical solution of the present application can also be realized by hardware and can be embodied in the form of software products, the computer
  • the software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc. , which includes a plurality of instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application.
  • the multiple units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, The names of the multiple functional units are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application.

Landscapes

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

Abstract

一种汽车雷达的目标筛选方法、装置、设备和存储介质，该方法包括：获取本车的状态信息和目标对象的属性信息（S110）；根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域（S120）；将属性信息和车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象（S130），其中，预设的筛选原则用于对汽车雷达检测到的目标对象进行筛选。

Description

汽车雷达的目标筛选方法、装置、设备和存储介质
本申请要求在2020年07月20日提交中国专利局、申请号为202010697859.8的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及驾驶辅助及自动驾驶技术，例如涉及一种汽车雷达的目标筛选方法、装置、设备和存储介质。
背景技术
由于毫米波雷达具有探测距离远、探测精度高和受环境影响小等特点，因此毫米波雷达在驾驶辅助及自动驾驶领域应用越来越广泛。
相关技术中由于网络传输负载受限，毫米波雷达仅能输出有限数量的目标。一方面，毫米波雷达对目标探测的误报率比较高，对于静态目标探测的误报率更高(由于地面杂波的影响)。另一方面，车载以太网正处于初级阶段，应用刚刚起步，成本较高，毫米波雷达信号传输多采用传统的控制器区域网络(Controller Area Network,CAN)和可变速率的CAN(CAN with Flexible Data-Rate,CAN-FD)通信，由于传输带宽受限，通常雷达只能输出16个目标(输出目标增多会导致网络负载过高造成网络堵塞)。因此，如何在雷达输出的目标的数量有限的情况下，上层系统获得更多有效的目标成为亟待解决的问题。
发明内容
本申请实施例提供一种汽车雷达的目标筛选方法、装置、设备和存储介质，可以实现在雷达输出的目标的数量有限的情况下，能够获得更多有效的目标对象。
本申请实施例提供了一种汽车雷达的目标筛选方法，包括：获取本车的状态信息和目标对象的属性信息；根据所述状态信息预测所述本车的行驶轨迹，根据所述行驶轨迹确定车道区域；将所述属性信息和所述车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，其中，所述预设的筛选原则用于对汽车雷达检测到的所述目标对象进行筛选。
本申请实施例还提供了一种目标筛选装置，包括：信息获取模块，设置为获取本车的状态信息和目标对象的属性信息；车道确定模块，设置为根据所述状态信息预测所述本车的行驶轨迹，根据所述行驶轨迹确定车道区域；目标匹 配模块，设置为将所述属性信息和所述车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，其中，所述预设的筛选原则用于对汽车雷达检测到的所述目标对象进行筛选。
本申请实施例还提供了一种设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如本申请实施例提供的任一所述的汽车雷达的目标筛选方法。
本申请实施例还提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请实施例提供的任一所述的汽车雷达的目标筛选方法。
附图说明
图1为本申请实施例一中提供的一种汽车雷达的目标筛选方法的流程图；
图2是本申请实施例二中提供的一种汽车雷达的目标筛选方法的流程图；
图2a是本申请实施例二中提供的一种汽车雷达的目标筛选方法的筛选原则流程图；
图3是本申请实施例二中提供的一种汽车雷达的目标筛选方法的工作示意图；
图4是本申请实施例二中提供的另一种汽车雷达的目标筛选方法的工作示意图；
图5是本申请实施例三中提供的一种汽车雷达的目标筛选方法的流程图；
图6是本申请实施例四中提供的一种汽车雷达的目标筛选装置的结构示意图；
图7是本申请实施例五中提供的一种车载设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请进行说明。可以理解的是，此处所描述的实施例仅仅用于解释本申请，而非对本申请的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与本申请相关的部分而非全部结构。
实施例一
图1为本申请实施例一中提供的一种汽车雷达的目标筛选方法的流程图。本实施例可适用于驾驶辅助及自动驾驶的筛选障碍物的情况，该方法可以由目标筛选装置来执行，该装置可以采用软件/硬件的方式实现。该装置可配置于车 载设备中。如图1所示，该方法包括如下步骤。
步骤S110、获取本车的状态信息和目标对象的属性信息。
本车的状态信息指本车辆的横摆角速度和方向盘转角等信息，用于预测本车的行驶轨迹。
目标对象指本车前方的目标，可以由前向毫米波雷达探测获得。目标对象的属性信息包括目标对象的类型、运动状态和位置等。目标对象的运动状态包括：动态目标和静态目标。动态目标包括四轮车、二轮车、行人和/或未知目标四类。
步骤S120、根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域。
车辆前方需要进行区域划分，可以按照车道划分，由于雷达无法探测到车道线，目标筛选装置可以根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域，例如，目标筛选装置可以根据汽车雷达获取的本车的横摆角速度和方向盘转角等信息预测本车的行驶轨迹，进而对车道区域进行预测。
车道区域可以包括本车道的区域、与本车道的规定的行驶方向相同的左N车道和右N车道的区域，其中，N为整数。
可选地，根据行驶轨迹确定车道区域，可以包括：将位于行驶轨迹的左侧且与行驶轨迹之间的距离为第一设定距离的边界与位于行驶轨迹的右侧且与行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为本车道；将位于行驶轨迹的左侧且与行驶轨迹之间的距离为第二设定距离的边界与位于行驶轨迹的左侧且与行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为左一车道；将位于行驶轨迹的右侧且与行驶轨迹之间的距离为第二设定距离的边界与位于行驶轨迹的右侧且与行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为右一车道；将位于行驶轨迹的左侧且与行驶轨迹之间的距离为第三设定距离的边界与位于行驶轨迹的左侧且与行驶轨迹之间的距离为第二设定距离的边界之间的区域确定为左二车道；将位于行驶轨迹的右侧且与行驶轨迹之间的距离为第三设定距离的边界与位于行驶轨迹的右侧且与行驶轨迹之间的距离为第二设定距离的边界之间的区域确定为右二车道。例如，将位于本车行驶轨迹的左侧的距离本车行驶轨迹0-1.8m的区域和位于本车行驶轨迹的右侧的距离本车行驶轨迹0-1.8m的区域确定为本车道，将位于本车行驶轨迹的左侧的距离本车行驶轨迹1.8-6m的区域确定为左一车道，将位于本车行驶轨迹的右侧的距离本车行驶轨迹1.8-6m的区域确定为右一车道，将位于本车行驶轨迹的左侧的距离本车行驶轨迹6-10m的区域确定为左二区域，将位于本车行驶轨迹的右 侧的距离本车行驶轨迹6-10m的区域确定为右二车道。
可选地，还可以根据本车的摄像头获取本车的行驶轨迹，并将行驶轨迹发送给汽车雷达，根据行驶轨迹确定车道区域。
步骤S130、将属性信息和车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象。
筛选原则用于对汽车雷达检测到的目标对象进行筛选。由于汽车雷达可以检测本车前方的所有目标对象，但是本车在行驶过程中，汽车雷达能够输出的目标对象的数量有限，因此，根据汽车雷达的物理特点和上层系统的需求，在汽车雷达输出的目标对象数量有限的前提下，需要根据预设的筛选原则输出尽可能多的有效目标对象。
可选地，筛选原则可以包括车道划分维度、目标动静态类别维度和/或静态目标稀疏处理维度等。车道划分维度指根据本车和目标对象所在车道区域输出目标对象，例如，输出本车道内沿车辆行驶方向的距离本车最近的目标对象，输出左一车道和/或右一车道内沿车辆行驶方向的距离本车最近的目标对象，或者输出左二车道和/或右二车道内沿车辆行驶方向的距离本车最近的目标对象。目标动静态类别维度指根据目标对象的动静状态输出目标对象，可以是优先输出动态目标，然后输出静态目标，例如，优先对动态目标进行输出，同时为避免车辆撞上前方最危险的静态障碍物，需要确保本车道内距离本车最近的静态目标的有效输出。静态目标稀疏处理维度指输出本车道相邻车道和/或本车道内沿车辆行驶方向的间隔距离满足一定条件的静态目标，例如，输出本车道内沿车辆行驶方向的间隔距离满足预设第一条件的静态目标，输出左一车道和右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的静态目标，和/或输出左二车道和右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标。由于汽车雷达主要负责车辆前方的目标探测，因此基于车道划分维度能够直接输出本车前方的距离本车最近的目标对象，基于目标动静态类别维度能够根据汽车雷达的目标探测特性、动态目标误报率低和静态目标误报高的特点，以及本车在道路行驶时，动态目标是车辆关注的重点等因素输出目标对象。针对道路边缘的护栏或树木，汽车雷达会接连输出很多目标对象，如果不加以抑制，有限的目标对象将会很快被填满，而稍远处的动态目标会被漏掉，静态目标稀疏处理维度能够控制静态目标的输出数量，在汽车雷达输出的目标对象的数量有限的情况下，能够获得更多有效目标对象。
可选地，筛选原则还可以包括动态目标分类维度。动态目标可以分为四轮车、二轮车、行人和未知目标四类，由于车辆目标的雷达反射面积大，因此，汽车雷达对车辆目标的探测误报率较低，在道路上行驶的车辆重点关注车辆目 标。动态目标分类维度指优先输出车辆目标，例如，优先输出四轮车。
可选地，筛选原则还可以包括前方危险车辆维度，其中，前方危险车辆指本车前方最危险的车辆目标。前方危险车辆维度指优先输出本车道内距离本车最近的车辆目标。
可选地，筛选原则可以包括以下按照优先级排序的原则中的至少之一：输出本车道内沿车辆行驶方向的距离本车最近的2个车辆目标；输出本车道内沿车辆行驶方向的距离本车最近的2个动态目标；输出本车道内沿车辆行驶方向的距离本车最近的2个静态目标；输出左一车道内沿车辆行驶方向的距离本车最近的1个动态目标；输出右一车道内沿车辆行驶方向的距离本车最近的1个动态目标；基于本车道、左一车道和右一车道内沿车辆行驶方向的其它动态目标与本车的距离，对本车道、左一车道和右一车道内的其它动态目标进行排序，根据排序结果输出第一设定数量的其它动态目标；输出本车道内沿车辆行驶方向的间隔距离满足预设第一条件的其它静态目标；输出左一车道和右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的静态目标；基于本车道、左一车道、右一车道、左二车道和右二车道内沿车辆行驶方向的其它动态目标与本车的距离，对本车道、左一车道、右一车道、左二车道和右二车道内的其它动态目标进行排序，根据排序结果输出第二设定数量的其它动态目标；输出左二车道和右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标；其中，如果基于上述原则筛选出重复的目标对象，则输出重复的目标对象中的一个。
筛选原则还包括：在本车的移动过程中，匹配检测到的静态目标与已输出的静态目标，根据匹配结果确定检测到的已输出的静态目标，输出检测到的已输出的静态目标。对于静态目标的输出，在本车移动过程中，确保距离本车最近的静态目标的输出，已输出的静态目标如果没有消失就不要删除，在已输出的静态目标的基础上继续检测静态目标，并输出检测到的已输出的静态目标。
本申请实施例通过获取本车的状态信息，预测本车的行驶轨迹，根据行驶轨迹确定车道区域，将获取到的目标对象的属性信息和车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，在汽车雷达输出的目标对象的数量有限的情况下，能够获得更多有效的目标对象，避免过多不受关注的目标对象占据有限的网络资源。
实施例二
图2是本申请实施例二中提供的一种汽车雷达的目标筛选方法的流程图。本实施例在上述实施例的基础上进行说明，如图2所示，该方法包括如下步骤。
步骤S210、获取本车的状态信息和目标对象的属性信息。
步骤S220、根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域。
将位于行驶轨迹的左侧的且与行驶轨迹之间的距离为第一设定距离的边界与位于行驶轨迹的右侧且与行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为本车道；将位于行驶轨迹的左侧且与行驶轨迹之间的距离为第二设定距离的边界与位于行驶轨迹的左侧且与行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为左一车道；将位于行驶轨迹的右侧且与行驶轨迹之间的距离为第二设定距离的边界与位于行驶轨迹的右侧且与行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为右一车道；将位于行驶轨迹的左侧且与行驶轨迹之间的距离第三设定距离的边界与位于行驶轨迹的左侧且与行驶轨迹之间的距离为第二设定距离的边界之间的区域确定为左二车道；将位于行驶轨迹的右侧且与行驶轨迹之间的距离为第三设定距离的边界与位于行驶轨迹的右侧且与行驶轨迹之间的距离为第二设定距离的边界之间的区域确定为右二车道。
步骤S230、根据属性信息确定目标对象的类型。
目标对象的类型包括：动态目标和静态目标。动态目标包括四轮车、二轮车、行人和/或未知目标等目标对象类型。
步骤S240、根据目标对象与本车的横向距离确定目标对象所在车道。
根据目标对象与本车的行驶轨迹的左右横向距离确定目标对象所在车道。图3是本申请实施例二中提供的一种汽车雷达的目标筛选方法的工作示意图。如图3所示，将位于本车行驶轨迹的左侧的距离本车行驶轨迹0-1.8m的区域和位于本车行驶轨迹的右侧的距离本车行驶轨迹0-1.8m的区域确定为本车道，将位于本车行驶轨迹的左侧的距离本车行驶轨迹1.8-6m的区域确定为左一车道，将位于本车行驶轨迹的右侧的距离本车行驶轨迹1.8-6m的区域确定为右一车道，将位于本车行驶轨迹的左侧的距离本车行驶轨迹6-10m的区域确定为左二区域，将位于本车行驶轨迹的右侧的距离本车行驶轨迹6-10m的区域确定为右二车道。如果目标对象位于本车行驶轨迹的左侧的距离本车行驶轨迹1m的区域，则确定该目标对象所在车道为本车道；如果目标对象位于本车行驶轨迹的右侧的距离本车行驶轨迹3m的区域，则确定该目标对象所在车道为右一车道；如果目标对象位于本车行驶轨迹的左侧的距离本车行驶轨迹8m的区域，则确定该目标对象所在车道为左二车道。
步骤S250、基于目标对象的类型和所在车道，根据预设的筛选原则从目标 对象中选择待输出目标对象。
图2a是本申请实施例二中提供的一种汽车雷达的目标筛选方法的筛选原则流程图。如图2a所示，步骤S250可以包括如下步骤。
步骤S2501、当目标对象为本车道内沿车辆行驶方向的距离本车最近的2个车辆目标时，输出本车道内沿车辆行驶方向的距离本车最近的2个车辆目标。
示例性地，如图3所示，车辆目标(1)和(2)为本车道内沿车辆行驶方向距离本车最近的2个车辆目标，依次输出车辆目标(1)和(2)。
步骤S2502、当目标对象为本车道内沿车辆行驶方向的距离本车最近的2个动态目标时，输出本车道内沿车辆行驶方向的距离本车最近的2个动态目标。
示例性地，如图3所示，动态目标(3)和(4)为本车道内沿车辆行驶方向距离本车最近的2个动态目标，依次输出动态目标(3)和(4)。
步骤S2503、当目标对象为本车道内沿车辆行驶方向的距离本车最近的2个静态目标时，输出本车道内沿车辆行驶方向的距离本车最近的2个静态目标。
示例性地，如图3所示，静态目标(5)和(6)为本车道内沿车辆行驶方向距离本车最近的2个静态目标，依次输出静态目标(5)和(6)。
步骤S2504、当目标对象为左一车道的沿车辆行驶方向的距离本车最近的1个动态目标时，输出左一车道的沿车辆行驶方向的距离本车最近的1个动态目标。
示例性地，如图3所示，动态目标(7)为左一车道的沿车辆行驶方向距离本车最近的1个动态目标，输出动态目标(7)。
步骤S2505、当目标对象为右一车道的沿车辆行驶方向的距离本车最近的1个动态目标时，输出右一车道的沿车辆行驶方向的距离本车最近的1个动态目标。
示例性地，如图3所示，动态目标(8)为右一车道的沿车辆行驶方向距离本车最近的1个动态目标，输出动态目标(8)。
步骤S2506、基于本车道、左一车道和右一车道内沿车辆行驶方向的其它动态目标与本车的距离，对本车道、左一车道和右一车道内的其它动态目标进行排序，根据排序结果输出第一设定数量的其它动态目标。
示例性地，如图3所示，动态目标(9)为基于本车道、左一车道和右一车道内沿车辆行驶方向的其它动态目标与本车的距离，对本车道、左一车道和右一车道内的其它动态目标进行排序，根据排序结果输出的1个动态目标。
步骤S2507、当目标对象为本车道内沿车辆行驶方向的间隔距离满足预设第 一条件的其它静态目标时，输出本车道内沿车辆行驶方向的间隔距离满足预设第一条件的其它静态目标。
预设第一条件可以为以当前的静态目标为基点，沿车辆行驶方向的与当前的静态目标间的距离小于或等于间隔距离的静态目标不输出，大于间隔距离的静态目标输出。
示例性地，如图3所示，沿车辆行驶方向以2m的间隔输出本车道内的其它静态目标(10)。即以当前的静态目标为基点，沿车辆行驶方向的与当前的静态目标的距离在大于0且小于或等于2m的静态目标不输出，与当前的静态目标间的距离大于2m的静态目标输出，此前输出的本车道的2个静态目标也适用于本步骤。
可选地，预设第一条件还可以为以当前的静态目标为基点，沿车辆行驶方向判断有无间隔距离存在，若沿车辆行驶方向存在该间隔距离，则沿车辆行驶方向的与当前的静态目标的距离小于或等于间隔距离的静态目标不输出，大于间隔距离的静态目标输出；若沿车辆行驶方向不存在该间隔距离，则沿车辆行驶方向由近及远输出静态目标。例如，以2m为间隔距离，沿车辆行驶方向，若静态目标间的间隔距离存在2m，则将与当前静态目标的距离在大于0且小于或等于2m的静态目标不输出，大于2m的静态目标输出，若静态目标间的间隔距离不存在2m，则沿车辆行驶方向由近及远输出静态目标。
步骤S2508、当目标对象为左一车道和右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的静态目标时，输出左一车道和右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的静态目标。
将左一车道和右一车道内沿车辆行驶方向中的其它静态目标统一以满足预设第二条件的间隔距离进行排序，根据排序结果输出静态目标。预设第二条件可以为以当前的静态目标为基点，沿车辆行驶方向于当前静态目标的距离小于或等于间隔距离的静态目标不输出，大于间隔距离的静态目标输出。例如，汽车雷达以满足预设第二条件的间隔距离探测到左一车道有5个静态目标，右一车道有3个静态目标，将这8个静态目标按照距离本车由近及远进行排序，输出设定数量的静态目标。
示例性地，如图3所示，将左一车道和右一车道内沿车辆行驶方向以5m间隔筛选目标，将左一车道和右一车道的静态目标筛选后混在一起，按照沿车辆行驶方向距离本车由近及远进行排序，输出静态目标(11)、(12)和(13)。
步骤S2509、基于本车道、左一车道、右一车道、左二车道和右二车道内沿车辆行驶方向的其它动态目标与本车的距离，对本车道、左一车道、右一车道、 左二车道和右二车道内的其它动态目标进行排序，根据排序结果输出第二设定数量的其它动态目标。
示例性地，如图3所示，动态目标(14)为基于沿车辆行驶方向的与本车的距离，对本车道、左一车道、右一车道、左二车道和右二车道内的其它动态目标进行排序，根据排序结果输出的1个动态目标。
步骤S2510、当目标对象为左二车道和右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标时，输出左二车道和右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标。
示例性地，如图3所示，将左二车道和右二车道内沿车辆行驶方向以5m间隔筛选目标，将左二车道和右二车道的静态目标筛选后混在一起，按照沿车辆行驶方向距离本车由近及远进行排序，输出静态目标(15)和(16)。
可选地，在本车的移动过程中，匹配检测到的静态目标与已输出的静态目标，根据匹配结果确定检测到的已输出的静态目标，输出检测到的已输出的静态目标。对于静态目标的输出，在本车移动过程中，确保距离本车最近的静态目标的输出，已输出的静态目标如果没有消失就不要删除，在已输出的静态目标的基础上继续检测静态目标，并输出检测到的已输出的静态目标。图4是本申请实施例二中提供的另一种汽车雷达的目标筛选方法的工作示意图。如图4所示，在t1时刻，输出距离本车最近的1个静态目标a和距离a大于5m的其它静态目标b和距离b大于5m的其它静态目标c，对于距离a等于3m的静态目标d和距离d等于3m的静态目标e不输出；在t2时刻，本车在移动过程中，原本在t1时刻没有输出的静态目标d为距离本车最近的1个静态目标，则输出静态目标d，已输出的b不删除，静态目标e由于与b间距小于5m不输出，c按规则输出。
步骤S260、判断待输出目标对象中是否包含重复的目标对象，若待输出目标对象中包含重复的目标对象，则执行步骤S270，若待输出目标对象中不包含重复的目标对象，则执行步骤S280。
步骤S270、输出未重复的待输出目标对象，并选择重复的目标对象中的一个进行输出。
步骤S280、输出待输出目标对象。
本申请实施例通过获取本车的状态信息和目标对象的属性信息，根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域，根据属性信息确定目标对象的类型，根据目标对象与本车的距离确定目标对象所在车道，将目标对象的类型和所在车道与预设的筛选原则进行匹配，根据匹配结果确定待输出目 标对象，在有限的目标输出情况下，能够获得更多有效的目标对象，避免过多不受关注的目标对象占据有限的网络资源。
实施例三
图5是本申请实施例三中提供的一种汽车雷达的目标筛选方法的流程图。本实施例在上述实施例的基础上进行说明，如图5所述，该方法包括如下步骤。
步骤S310、按照预设阈值周期性地获取本车的状态信息和目标对象的属性信息。
按照预设阈值周期性地获取本车的状态信息和汽车雷达探测到的目标对象的属性信息，例如，按照50毫秒的周期获取本车的状态信息和目标对象的属性信息。
可选地，还可以通过车载以太网传输本车的状态信息和汽车雷达探测到的目标对象的属性信息，本申请对此不作限定。
步骤S320、根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域。
步骤S330、将属性信息和车道区域与预设的筛选原则按照预设阈值周期性地进行匹配，根据匹配结果确定待输出目标对象。
按照预设阈值每获得一次目标对象的属性信息与车道区域，按照预设的筛选原则进行一次匹配，根据匹配结果确定待输出目标对象。例如，每50毫秒获取一次本车的状态信息和目标对象的属性信息，根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域，按照预设的筛选原则进行一次匹配，根据匹配结果确定待输出目标对象。
步骤S340、发送待输出目标对象给域控制器。
域控制器可以设置为定位、路径规划、决策控制、无线通讯和/或高速通讯，可以内置处理器，还可以外接多个摄像头、毫米波雷达和/或激光雷达等设备。
本申请实施例按照预设阈值周期性地获取本车的状态信息和目标对象的属性信息，根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域，将属性信息和车道区域与预设的筛选原则按照预设阈值周期性地进行匹配，根据匹配结果确定待输出目标对象，发送待输出目标对象给域控制器。通过汽车雷达探测到本车周围环境中的目标对象，以预设阈值周期地按照预设的筛选原则对目标对象进行筛选，将符合筛选原则的待输出目标对象的雷达数据发送给域控制器，能够实时地对目标对象进行筛选，提高了目标筛选的准确度，有利于实时监测本车前方的障碍物。
实施例四
图6是本申请实施例四中提供的一种汽车雷达的目标筛选装置的结构示意图。该装置可由软件和/或硬件实现，一般可集成在设备中，可以通过汽车雷达的目标筛选在有限的目标输出情况下，能够获得更多有效的目标对象。如图6所示，该装置包括：信息获取模块410，设置为获取本车的状态信息和目标对象的属性信息；车道确定模块420，设置为根据所述状态信息预测本车的行驶轨迹，根据所述行驶轨迹确定车道区域；目标匹配模块430，设置为将所述属性信息和所述车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，其中，所述预设的筛选原则用于对汽车雷达检测到的所述目标对象进行筛选。
可选地，所述车道确定模块420是设置为：将位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为第一设定距离的边界与位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为本车道；将位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为第二设定距离的边界与位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为左一车道；将位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为第二设定距离的边界与位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为第一设定距离的边界之间的区域确定为右一车道；将位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为第三设定距离的边界与位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为第二设定距离的边界之间的区域确定为左二车道；将位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为第三设定距离的边界与位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为第二设定距离的边界之间的区域确定为右二车道。
可选地，所述目标匹配模块430是设置为：根据所述属性信息确定所述目标对象的类型，其中，目标对象的类型包括：动态目标和静态目标，动态目标包括四轮车、二轮车、行人或未知目标等目标对象类型；根据所述目标对象与所述本车的距离确定所述目标对象所在车道；当所述目标对象为所述本车道内沿车辆行驶方向的距离本车最近的2个车辆目标时，输出所述本车道内沿车辆行驶方向的距离本车最近的2个车辆目标；当所述目标对象为所述本车道内沿车辆行驶方向的距离本车最近的2个动态目标时，输出所述本车道内沿车辆行驶方向的距离本车最近的2个动态目标；当所述目标对象为所述本车道内沿车辆行驶方向的距离本车最近的2个静态目标时，输出所述本车道内沿车辆行驶方向的距离本车最近的2个静态目标；当所述目标对象为所述左一车道内沿车辆行驶方向的距离本车最近的1个动态目标时，输出所述左一车道内沿车辆行驶方向的距离本车最近的1个动态目标；当所述目标对象为所述右一车道内沿车辆行驶方向的距离本车最近的1个动态目标时，输出所述右一车道内沿车辆 行驶方向的距离本车最近的1个动态目标；基于所述本车道、左一车道和右一车道内沿车辆行驶方向的其它动态目标与本车的距离，对所述本车道、左一车道和右一车道内的其它动态目标进行排序，根据排序结果输出第一设定数量的其它动态目标；当所述目标对象为所述本车道内沿车辆行驶方向的间隔距离满足预设第一条件的其它静态目标时，输出所述本车道内沿车辆行驶方向的间隔距离满足预设第一条件的其它静态目标；当所述目标对象为所述左一车道和右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的静态目标时，输出所述左一车道和右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的静态目标；基于所述本车道、左一车道、右一车道、左二车道和右二车道内沿车辆行驶方向的其它动态目标与本车的距离，对所述本车道、左一车道、右一车道、左二车道和右二车道内的其它动态目标进行排序，根据排序结果输出第二设定数量的其它动态目标；当所述目标对象为所述左二车道和右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标时，输出所述左二车道和右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标；其中，如果筛选出重复的目标对象，则输出所述重复的目标对象中的一个。
可选地，所述信息获取模块410是设置为：按照预设阈值周期性地获取本车的状态信息和目标对象的属性信息。所述目标匹配模块430是设置为：将所述属性信息和所述车道区域与预设的筛选原则按照预设阈值周期性地进行匹配，根据匹配结果确定待输出目标对象。
可选地，该装置还包括：目标发送模块，设置为在根据匹配结果确定待输出目标对象之后，发送所述待输出目标对象给域控制器。
实施例五
图7是本申请实施例五中提供的一种车载设备的结构示意图。例如，车载设备可以是汽车雷达，或者，与汽车雷达通过串口通信且独立于该汽车雷达的雷达目标筛选设备，如图7所示，该设备包括处理器510、存储器520、输入装置530和输出装置540。设备中处理器510的数量可以是一个或多个，图7中以一个处理器510为例。设备中的处理器510、存储器520、输入装置530和输出装置540可以通过总线或其它方式连接，图7中以通过总线连接为例。
存储器520作为一种计算机可读存储介质，可设置为存储软件程序、计算机可执行程序以及模块，如本申请实施例中的汽车雷达的目标筛选方法对应的程序指令/模块(例如，目标筛选装置中的信息获取模块410、请求获取模块420和请求判断模块430)。处理器510通过运行存储在存储器520中的软件程序、指令以及模块，从而执行设备的多种功能应用以及汽车雷达的目标筛选，即实现上述的汽车雷达的目标筛选方法。
存储器520可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据终端的使用所创建的数据等。此外，存储器520可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其它非易失性固态存储器件。在一些实例中，存储器520还可包括相对于处理器510远程设置的存储器，这些远程存储器可以通过网络连接至设备。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置530可设置为接收输入的数字或字符信息，以及产生与设备的用户设置以及功能控制有关的键信号输入。输出装置540可包括显示屏等显示设备。
实施例六
本申请实施例六还提供一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种汽车雷达的目标筛选方法，该方法包括：获取本车的状态信息和目标对象的属性信息；根据状态信息预测本车的行驶轨迹，根据行驶轨迹确定车道区域；将属性信息和车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，其中，预设的筛选原则用于对汽车雷达检测到的目标对象进行筛选。
当然，本申请实施例所提供的一种包含计算机可执行指令的存储介质，其计算机可执行指令不限于如上所述的方法操作，还可以执行本申请任意实施例所提供的汽车雷达的目标筛选方法中的相关操作。
通过以上关于实施方式的描述，所属领域的技术人员可以了解到，本申请可借助软件及通用硬件来实现，当然也可以通过硬件实现本申请的技术方案可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如计算机的软盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、闪存(FLASH)、硬盘或光盘等，包括多个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)执行本申请多个实施例所述的方法。
值得注意的是，上述目标筛选装置的实施例中，所包括的多个单元和模块只是按照功能逻辑进行划分的，但并不局限于上述的划分，只要能够实现相应的功能即可；另外，多个功能单元的名称也只是为了便于相互区分，并不用于限制本申请的保护范围。

Claims (10)

  1. 一种汽车雷达的目标筛选方法，包括：
    获取本车的状态信息和目标对象的属性信息；
    根据所述状态信息预测所述本车的行驶轨迹，根据所述行驶轨迹确定车道区域；
    将所述属性信息和所述车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，其中，所述预设的筛选原则用于对汽车雷达检测到的所述目标对象进行筛选。
  2. 根据权利要求1所述的方法，其中，所述根据所述行驶轨迹确定车道区域，包括：
    将位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为第一设定距离的边界与位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为所述第一设定距离的边界之间的区域确定为本车道；
    将位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为第二设定距离的边界与位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为所述第一设定距离的边界之间的区域确定为左一车道；
    将位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为所述第二设定距离的边界与位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为所述第一设定距离的边界之间的区域确定为右一车道；
    将位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为第三设定距离的边界与位于所述行驶轨迹的左侧且与所述行驶轨迹之间的距离为所述第二设定距离的边界之间的区域确定为左二车道；
    将位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为所述第三设定距离的边界与位于所述行驶轨迹的右侧且与所述行驶轨迹之间的距离为所述第二设定距离的边界之间的区域确定为右二车道；
    其中，所述第二设定距离大于所述第一设定距离且小于所述第三设定距离。
  3. 根据权利要求2所述的方法，其中，所述预设的筛选原则包括以下按照优先级排序的原则中的至少之一：
    输出所述本车道内沿车辆行驶方向的距离所述本车最近的2个车辆目标；
    输出所述本车道内沿车辆行驶方向的距离所述本车最近的2个动态目标；
    输出所述本车道内沿车辆行驶方向的距离所述本车最近的2个静态目标；
    输出所述左一车道内沿车辆行驶方向的距离所述本车最近的1个动态目标；
    输出所述右一车道内沿车辆行驶方向的距离所述本车最近的1个动态目标；
    基于所述本车道、所述左一车道和所述右一车道内沿车辆行驶方向的其它动态目标与所述本车的距离，对所述本车道、所述左一车道和所述右一车道内的所述其它动态目标进行排序，根据排序结果输出第一设定数量的其它动态目标；
    输出所述本车道内沿车辆行驶方向的间隔距离满足预设第一条件的其它静态目标；
    输出所述左一车道和所述右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的其它静态目标；
    基于所述本车道、所述左一车道、所述右一车道、所述左二车道和所述右二车道内沿车辆行驶方向的其它动态目标与所述本车的距离，对所述本车道、所述左一车道、所述右一车道、所述左二车道和所述右二车道内的所述其它动态目标进行排序，根据排序结果输出第二设定数量的其它动态目标；
    输出所述左二车道和右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标；
    其中，在基于上述原则筛选出重复的目标对象的情况下，输出所述重复的目标对象中的一个。
  4. 根据权利要求3所述的方法，其中，所述筛选原则还包括：在所述本车的移动过程中，匹配检测到的静态目标与已输出的静态目标，根据匹配结果确定检测到的已输出的静态目标，输出所述检测到的已输出的静态目标。
  5. 根据权利要求3所述的方法，其中，所述将所述属性信息和所述车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，包括：
    根据所述属性信息确定所述目标对象的类型，其中，所述目标对象的类型包括：动态目标和静态目标；其中，所述动态目标包括四轮车、二轮车、行人和未知目标中的至少之一；
    根据所述目标对象与所述本车的横向距离确定所述目标对象所在车道；
    在所述目标对象包括所述本车道内沿车辆行驶方向的距离所述本车最近的2个车辆目标的情况下，输出所述本车道内沿车辆行驶方向的距离所述本车最近的2个车辆目标；
    在所述目标对象包括所述本车道内沿车辆行驶方向的距离所述本车最近的2个动态目标的情况下，输出所述本车道内沿车辆行驶方向的距离所述本车最近的2个动态目标；
    在所述目标对象包括所述本车道内沿车辆行驶方向的距离所述本车最近的2个静态目标的情况下，输出所述本车道内沿车辆行驶方向的距离所述本车最近的2个静态目标；
    在所述目标对象包括所述左一车道内沿车辆行驶方向的距离所述本车最近的1个动态目标的情况下，输出所述所述左一车道内沿车辆行驶方向的距离所述本车最近的1个动态目标；
    在所述目标对象包括所述右一车道内沿车辆行驶方向的距离本车最近的1个动态目标的情况下，输出所述右一车道内沿车辆行驶方向的距离所述本车最近的1个动态目标；
    基于所述本车道、所述左一车道和所述右一车道内沿车辆行驶方向的其它动态目标与所述本车的距离，对所述本车道、所述左一车道和所述右一车道内的所述其它动态目标进行排序，根据排序结果输出第一设定数量的其它动态目标；
    在所述目标对象包括所述本车道内沿车辆行驶方向的间隔距离满足预设第一条件的其它静态目标的情况下，输出所述本车道内沿车辆行驶方向的间隔距离满足预设第一条件的其它静态目标；
    在所述目标对象包括所述左一车道和所述右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的静态目标的情况下，输出所述左一车道和所述右一车道内沿车辆行驶方向的间隔距离满足预设第二条件的静态目标；
    基于所述本车道、所述左一车道、所述右一车道、所述左二车道和所述右二车道内沿车辆行驶方向的其它动态目标与所述本车的距离，对所述本车道、所述左一车道、所述右一车道、所述左二车道和所述右二车道内的所述其它动态目标进行排序，根据排序结果输出第二设定数量的其它动态目标；
    在所述目标对象包括所述左二车道和所述右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标的情况下，输出所述左二车道和所述右二车道内沿车辆行驶方向的间隔距离满足预设第三条件的静态目标；
    其中，在筛选出重复的目标对象的情况下，输出所述重复的目标对象中的一个。
  6. 根据权利要求1所述的方法，其中，所述获取本车的状态信息和目标对象的属性信息，包括：
    按照预设阈值周期性地获取所述本车的状态信息和所述目标对象的属性信息；
    所述将所述属性信息和所述车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，包括：
    将所述属性信息和所述车道区域与所述预设的筛选原则按照所述预设阈值周期性地进行匹配，根据所述匹配结果确定所述待输出目标对象。
  7. 根据权利要求1所述的方法，在根据所述匹配结果确定所述待输出目标对象之后，还包括：
    发送所述待输出目标对象给域控制器。
  8. 一种目标筛选装置，包括：
    信息获取模块，设置为获取本车的状态信息和目标对象的属性信息；
    车道确定模块，设置为根据所述状态信息预测所述本车的行驶轨迹，根据所述行驶轨迹确定车道区域；
    目标匹配模块，设置为将所述属性信息和所述车道区域与预设的筛选原则进行匹配，根据匹配结果确定待输出目标对象，其中，所述预设的筛选原则用于对汽车雷达检测到的所述目标对象进行筛选。
  9. 一种设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现如权利要求1-7中任一所述的汽车雷达的目标筛选方法。
  10. 一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现如权利要求1-7中任一所述的汽车雷达的目标筛选方法。
PCT/CN2021/105182 2020-07-20 2021-07-08 汽车雷达的目标筛选方法、装置、设备和存储介质 Ceased WO2022017189A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010697859.8A CN111856470A (zh) 2020-07-20 2020-07-20 一种汽车雷达的目标筛选方法、装置、设备和存储介质
CN202010697859.8 2020-07-20

Publications (1)

Publication Number Publication Date
WO2022017189A1 true WO2022017189A1 (zh) 2022-01-27

Family

ID=73002097

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/105182 Ceased WO2022017189A1 (zh) 2020-07-20 2021-07-08 汽车雷达的目标筛选方法、装置、设备和存储介质

Country Status (2)

Country Link
CN (1) CN111856470A (zh)
WO (1) WO2022017189A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114735018A (zh) * 2022-05-06 2022-07-12 上海智驾汽车科技有限公司 一种基于单雷达的前方最危险目标车辆的筛选判断方法
CN115042819A (zh) * 2022-07-04 2022-09-13 小米汽车科技有限公司 车辆控制方法、装置、介质、设备、芯片和车辆

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111856470A (zh) * 2020-07-20 2020-10-30 中国第一汽车股份有限公司 一种汽车雷达的目标筛选方法、装置、设备和存储介质
WO2022183329A1 (zh) * 2021-03-01 2022-09-09 华为技术有限公司 一种智能驾驶方法、装置、存储介质及计算机程序
CN114706052A (zh) * 2022-03-11 2022-07-05 中国第一汽车股份有限公司 车辆行驶前方人物的分类识别的方法、装置、设备和介质
CN114994686A (zh) * 2022-06-23 2022-09-02 深圳市道通智能汽车有限公司 车辆雷达预警方法、装置、系统及车辆
CN115561750B (zh) * 2022-09-02 2025-06-24 上海无线电设备研究所 毫米波雷达车型分类方法
CN116299280A (zh) * 2023-02-24 2023-06-23 合肥保航汽车科技有限公司 一种车辆状态识别方法、系统、设备以及介质
CN116749963A (zh) * 2023-06-21 2023-09-15 上海科博达智能科技有限公司 用于智能驾驶的目标筛选方法、装置及其车辆

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108226924A (zh) * 2018-01-11 2018-06-29 李烜 基于毫米波雷达的汽车行驶环境探测方法、装置及其应用
US20190071072A1 (en) * 2017-09-04 2019-03-07 Samsung Electronics Co., Ltd. Method and apparatus for controlling vehicle
CN110007305A (zh) * 2019-04-15 2019-07-12 北京行易道科技有限公司 车辆前方目标确定方法、装置、服务器及存储介质
CN110834630A (zh) * 2019-10-22 2020-02-25 中国第一汽车股份有限公司 一种车辆的驾驶控制方法、装置、车辆及存储介质
CN111856470A (zh) * 2020-07-20 2020-10-30 中国第一汽车股份有限公司 一种汽车雷达的目标筛选方法、装置、设备和存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2463621C2 (ru) * 2007-05-14 2012-10-10 Рэйтеон Компани Способы и устройство для выбора цели из данных радиолокационного сопровождения
CN206734295U (zh) * 2016-12-21 2017-12-12 驭势科技（北京）有限公司 一种用于探测车辆周围目标的探测系统以及其应用
CN109035868B (zh) * 2018-09-26 2021-01-05 吉林大学 一种在无车道线情况下自动驾驶车辆进行车道划分的方法
CN109835348B (zh) * 2019-01-25 2021-04-23 中国汽车技术研究中心有限公司 一种道路交通危险场景的筛选方法和装置
CN110889409B (zh) * 2019-11-29 2023-06-02 安徽江淮汽车集团股份有限公司 汽车雷达监测优化方法、装置、设备及存储介质
CN110940982B (zh) * 2019-11-29 2023-09-12 径卫视觉科技（上海）有限公司 一种车辆前方目标识别方法以及相应的设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190071072A1 (en) * 2017-09-04 2019-03-07 Samsung Electronics Co., Ltd. Method and apparatus for controlling vehicle
CN108226924A (zh) * 2018-01-11 2018-06-29 李烜 基于毫米波雷达的汽车行驶环境探测方法、装置及其应用
CN110007305A (zh) * 2019-04-15 2019-07-12 北京行易道科技有限公司 车辆前方目标确定方法、装置、服务器及存储介质
CN110834630A (zh) * 2019-10-22 2020-02-25 中国第一汽车股份有限公司 一种车辆的驾驶控制方法、装置、车辆及存储介质
CN111856470A (zh) * 2020-07-20 2020-10-30 中国第一汽车股份有限公司 一种汽车雷达的目标筛选方法、装置、设备和存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114735018A (zh) * 2022-05-06 2022-07-12 上海智驾汽车科技有限公司 一种基于单雷达的前方最危险目标车辆的筛选判断方法
CN115042819A (zh) * 2022-07-04 2022-09-13 小米汽车科技有限公司 车辆控制方法、装置、介质、设备、芯片和车辆

Also Published As

Publication number Publication date
CN111856470A (zh) 2020-10-30

Similar Documents

Publication Publication Date Title
WO2022017189A1 (zh) 汽车雷达的目标筛选方法、装置、设备和存储介质
US11107356B2 (en) Cellular network-based assisted driving method and traffic control unit
EP3249630B1 (en) Object detection apparatus, and storage medium
US12254680B2 (en) Traffic flow machine-learning modeling system and method applied to vehicles
US20210107487A1 (en) Apparatus for controlling lane change of autonomous vehicle and method thereof
JP6556939B2 (ja) 車両制御装置
US11288964B2 (en) Driving assistance device and driving assistance method
US10726727B2 (en) In-vehicle device, information processing system, and information processing method
CN111231982A (zh) 一种智能驾驶的障碍物识别方法、装置、车辆和存储介质
US10482332B2 (en) Pedestrian determining apparatus for determining whether an object is a pedestrian crossing ahead of an own vehicle
US12344255B2 (en) Detection of abnormal driving based on behavior profiles
CN111796286A (zh) 一种制动等级的评估方法、装置、车辆和存储介质
JP6717240B2 (ja) 物標検出装置
KR20150028258A (ko) 정보 이용을 위한 방법 및 시스템
JP2016148547A (ja) 検知装置
CN110261856A (zh) 一种基于多雷达协同探测的雷达探测方法及装置
WO2016003475A1 (en) Vehicle radar methods and systems
CN110705445A (zh) 拖车及盲区目标检测方法和装置
KR20200101302A (ko) 도로 위험 행위 경고 방법, 장치, 서버 및 시스템
CN115635963A (zh) 目标对象筛选方法、装置、电子装置、存储介质和车辆
CN111932884A (zh) 一种交通拥堵的识别方法、装置、车辆和存储介质
CN114675272A (zh) 一种雷达监测优化方法、装置和车辆
CN113393675A (zh) 一种车辆id确定方法、装置、设备和介质
JP7254243B2 (ja) 物体検知システムおよび物体検知方法
CN110834626A (zh) 行车障碍预警方法、装置、车辆和存储介质

Legal Events

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

Ref document number: 21846428

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: 21846428

Country of ref document: EP

Kind code of ref document: A1