WO2020199010A1 - 毫米波雷达的跟踪检测方法、毫米波雷达和车辆 - Google Patents

毫米波雷达的跟踪检测方法、毫米波雷达和车辆 Download PDF

Info

Publication number
WO2020199010A1
WO2020199010A1 PCT/CN2019/080607 CN2019080607W WO2020199010A1 WO 2020199010 A1 WO2020199010 A1 WO 2020199010A1 CN 2019080607 W CN2019080607 W CN 2019080607W WO 2020199010 A1 WO2020199010 A1 WO 2020199010A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
vehicle
tracking
detection
distance
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/CN2019/080607
Other languages
English (en)
French (fr)
Inventor
王宇
戴为龙
陈配涛
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.)
SZ DJI Technology Co Ltd
Original Assignee
SZ DJI Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by SZ DJI Technology Co Ltd filed Critical SZ DJI Technology Co Ltd
Priority to PCT/CN2019/080607 priority Critical patent/WO2020199010A1/zh
Priority to CN201980010373.8A priority patent/CN111699406B/zh
Publication of WO2020199010A1 publication Critical patent/WO2020199010A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S13/00Systems 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
    • G01S13/88Radar or analogous systems specially adapted for specific applications
    • G01S13/93Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S13/00Systems 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
    • G01S13/02Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/50Systems of measurement based on relative movement of target
    • G01S13/58Velocity or trajectory determination systems; Sense-of-movement determination systems
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S13/00Systems 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
    • G01S13/66Radar-tracking systems; Analogous systems
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S13/00Systems 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
    • G01S13/88Radar or analogous systems specially adapted for specific applications
    • G01S13/93Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41Details 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
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S7/00Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/41Details 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
    • G01S7/418Theoretical aspects
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO 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
    • G01S13/00Systems 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
    • G01S13/88Radar or analogous systems specially adapted for specific applications
    • G01S13/93Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G01S2013/9317Driving backwards

Definitions

  • the present invention generally relates to the technical field of automatic driving, and more specifically to a tracking detection method of millimeter wave radar, millimeter wave radar and vehicle.
  • millimeter-wave radar technology has been increasingly widely used in Advanced Driver Assistant System (ADAS) systems, and will occupy an indispensable position in future autonomous driving systems.
  • ADAS Advanced Driver Assistant System
  • millimeter-wave radar has unique advantages such as all-weather, all-weather, long range, and high speed measurement accuracy.
  • the lateral shuttle obstacle warning (CTA) function is a very important function for driving assistance systems.
  • the ADAS function has higher and higher requirements for the protection of crossing objects, especially the crossing pedestrians in front of and behind the vehicle (especially when reversing). Therefore, the lateral shuttle obstacle warning (CTA) The function also puts forward higher requirements.
  • one aspect of the present invention provides a tracking detection method for millimeter wave radar, the tracking detection method includes:
  • target detection information of a reflective target point where the target detection information includes position information of the reflective target point in a motion direction of the current motion state of the vehicle, wherein the current motion state includes at least one of the following: Gear status, reverse gear status;
  • a processing mode of the reflection target point is determined, wherein the processing mode includes at least one of the following: a clustering target mode and a tracking target mode.
  • the tracking detection method further includes:
  • a corresponding detection mode is activated, and the detection mode includes at least one of the following: a forward gear detection mode and a reverse gear detection mode.
  • the tracking detection method further includes:
  • a preset type of detection target is formed, and the preset type includes at least one of the following: clustering targets and tracking targets;
  • the position information includes at least one of the following: the angular change rate of the target position, the trend of the angular change rate, and the distance change of the target position in the moving direction of the vehicle;
  • the position information includes distance information
  • the processing mode of the reflection target point is determined according to the distance information and a preset distance threshold
  • the processing mode of the reflective target point is the clustering target mode; if the distance information exceeds the distance threshold, the processing mode of the reflective target point is the tracking target mode.
  • cluster the reflection target points to form a cluster target In the cluster target mode, cluster the reflection target points to form a cluster target.
  • target tracking is performed on the reflective target point to form a tracking target.
  • the tracking detection method further includes:
  • the millimeter wave radar is powered on or restarted.
  • the power-on or restart of the millimeter wave radar includes:
  • the millimeter wave radar is powered on and started and initialized the parameter configuration
  • the millimeter wave radar When the vehicle changes forward gear or reverse gear, the millimeter wave radar first stops the radio frequency signal transmission, and restarts to reset the parameter configuration of the millimeter wave radar.
  • the parameter configuration includes at least one of radio frequency parameter configuration, installation parameter configuration, and algorithm parameter configuration.
  • the position information includes the angle change rate, the angle change rate trend of the cluster target, and the distance change of the cluster target in the moving direction of the vehicle.
  • the position information of the cluster target further includes at least one of the center of gravity coordinates and the action range of the cluster target.
  • the detection target is a tracking target
  • the tracking target is classified and aggregated.
  • the classification and aggregation of the tracking target includes:
  • the pedestrian classification and/or the truck composed of multiple points based on the distance and energy to judge the target RCS statistical value.
  • determining whether the preset type of detection target is a laterally moving object according to the position information of the detection target includes:
  • the value of the angle change rate threshold is related to the distance between the detection target and the millimeter wave radar in the direction of movement of the vehicle, and when the distance is greater, the value of the angle change rate threshold The smaller.
  • the determining whether the trend of the angle change rate is increasing or decreasing includes:
  • the moving direction of the detection target in the backward direction of the vehicle it is determined whether the trend of the angle change rate is increasing or decreasing.
  • the determining whether the angle change rate trend is increasing or decreasing according to the direction of movement of the detection target in the backward direction of the vehicle includes:
  • the direction of movement of the detection target in the backward direction of the vehicle is from inside to outside, including the detection target being in the rear of the vehicle to the left and moving outwards and the detection target being in the back of the vehicle to the right and moving outwards ;as well as
  • the movement direction of the detection target in the backward direction of the vehicle is from the outside to the inside, including the detection target being in the left and inward movement after the vehicle and the detection target being in the right and inward movement after the vehicle.
  • the distance change of the target position in the moving direction of the vehicle is the distance change after the vehicle speed compensation is added.
  • the distance of the target position in the lateral direction is the distance in the geodetic coordinate system
  • the distance in the geodetic coordinate system is converted from the distance in the vehicle body coordinate system.
  • tracking and detecting the laterally moving object further includes:
  • the laterally moving object tracking gate parameter For the detection target that is determined to be a laterally moving object, use the laterally moving object tracking gate parameter to track and detect the laterally moving object;
  • the horizontally moving object tracking gate parameter includes a longitudinal distance gate and a lateral distance gate, wherein the range of the longitudinal distance gate is smaller than the range of the lateral distance gate.
  • the clustering target and the tracking target adopt different lateral moving object tracking gate parameters.
  • the laterally moving object tracking gate parameter and the ordinary gate parameter both include a distance gate, a velocity gate, and an angle gate, where the tracking gate parameter of the laterally moving object tracking target
  • the distance gate and the velocity gate are smaller than those of the ordinary gate parameters
  • the angle gate of the laterally moving object tracking gate parameter is larger than the angle gate of the ordinary gate parameter.
  • the determining the current motion state of the vehicle includes:
  • the vehicle body information includes vehicle speed
  • the acquiring vehicle body information and determining the current motion state of the vehicle according to the vehicle body information includes:
  • the vehicle body information includes at least one of vehicle speed, gear position, steering, and yaw rate.
  • the forward mode radio frequency parameter configuration is set to activate the forward gear detection mode.
  • the position information includes original target information obtained after one-dimensional or two-dimensional fast Fourier plus angle measurement, which has not been tracked but has undergone changes in vehicle body coordinates.
  • the position information further includes the movement speed and angle of the reflection target point.
  • the detection distance range of the reverse mode radio frequency parameter configuration is smaller than that of the forward mode radio frequency parameter configuration.
  • the reversing mode radio frequency parameter configuration has a larger field of view than the software filtering of the forward mode radio frequency parameter configuration.
  • the distance resolution of the reverse mode radio frequency parameter configuration is higher than that of the forward mode radio frequency parameter configuration.
  • the forward gear detection mode further includes:
  • the tracking detection method further includes:
  • a millimeter wave radar is arranged behind the vehicle, and the tracking and detecting the laterally moving object includes:
  • millimeter wave radar includes:
  • One or more processors working individually or together, and the processors are used to:
  • target detection information of a reflective target point where the target detection information includes position information of the reflective target point in a motion direction of the current motion state of the vehicle, wherein the current motion state includes at least one of the following: Gear status, reverse gear status;
  • a processing mode of the reflection target point is determined, wherein the processing mode includes at least one of the following: a clustering target mode and a tracking target mode.
  • Antenna device for transmitting millimeter wave signals and receiving reflected signals
  • a signal processing circuit electrically connected to the antenna device, for processing the reflected signal and converting it into a data signal
  • the processor is in communication connection with the signal processing circuit, and is used to process the data signal sent by the signal processing circuit.
  • Another aspect of the present invention provides a vehicle including a vehicle body and the aforementioned millimeter wave radar, and the millimeter wave radar is installed in front or/and rear of the vehicle body.
  • the tracking detection method of the embodiment of the present invention acquires target detection information of a reflective target point, and the target detection information includes position information of the reflective target point in the moving direction of the current state of the vehicle, where the current
  • the motion state includes at least one of the following: a forward gear state, a reverse gear state; a processing mode of the reflection target point is determined according to the position information, wherein the processing mode includes at least one of the following: clustering target mode, tracking Target mode.
  • the tracking detection method performs different processing modes on the reflection target point according to the position information of the reflection target point, so as to ensure that a more accurate processing mode is used to detect and process the detection target.
  • the tracking detection method of the embodiment of the present invention forms a preset type of detection target according to the determined processing mode, and the preset type includes at least one of the following: clustering target, tracking target; calculating the detection target
  • the position information includes at least one of the following: the angular change rate of the target position, the trend of the angular change rate, and the distance change of the target position in the direction of the vehicle's movement; according to the position information of the detection target, determine the Whether the preset type of detection target is a laterally moving object; tracking and detecting the laterally moving object.
  • Fig. 1 shows a schematic flow chart of a method for tracking and detecting millimeter wave radar in an embodiment of the present invention
  • Fig. 2 shows the detection power map of the rearward millimeter wave radar of the vehicle body in an embodiment of the present invention
  • FIG. 3 shows a schematic flow chart of a method for tracking and detecting millimeter wave radar in a specific embodiment of the present invention
  • Figure 4 shows a schematic diagram of a vehicle body coordinate system in an embodiment of the present invention
  • Fig. 5 shows a schematic block diagram of a millimeter wave radar in an embodiment of the present invention.
  • the present invention provides a tracking detection method for millimeter wave radar, as shown in FIG. 1, the method includes:
  • Step S101 Obtain target detection information of a reflective target point, where the target detection information includes position information of the reflective target point in the current motion state of the vehicle in the motion direction, wherein the current motion state includes at least one of the following Types: forward gear state, reverse gear state;
  • Step S102 Determine a processing mode of the reflection target point according to the position information, wherein the processing mode includes at least one of the following: a clustering target mode and a tracking target mode.
  • the tracking detection method performs different processing modes on the reflection target point according to the position information of the reflection target point, so as to ensure that a more accurate processing mode is used to detect and process the detection target.
  • the tracking detection method of the millimeter wave radar includes the following steps:
  • step S101 perform step S101 to obtain target detection information of a reflection target point, the target detection information including position information of the reflection target point in the direction of the vehicle's current motion state, wherein the current motion state includes At least one of the following: forward gear state, reverse gear state.
  • the target detection information of the reflection target point can be obtained by any suitable method, for example, the target detection information of the reflection target point is obtained by detecting the target object based on millimeter wave radar.
  • the millimeter wave radar is installed on a mobile platform, for example, on the body of a vehicle.
  • the vehicle may also include an autonomous vehicle.
  • the millimeter wave radar can be installed on the vehicle body, for example, in the front and/or rear of the vehicle body.
  • a millimeter wave radar is installed behind the vehicle body, for example, two millimeter wave radars are installed.
  • the two millimeter-wave radars cover a field of view (FOV) of approximately 120-270° behind the vehicle.
  • FOV field of view
  • the millimeter wave radar has high accuracy of ranging and speed measurement, and weather and environmental factors such as light and weather basically have no effect on the detection of millimeter radar waves.
  • weather and environmental factors such as light and weather basically have no effect on the detection of millimeter radar waves.
  • the present invention is not limited to the use of millimeter radar waves for target detection. Other methods and means can be used for detection.
  • Millimeter wave radar uses millimeter wave (millimeter wave), usually millimeter wave refers to the frequency domain of 30 to 300 GHz (wavelength is 1 to 10 mm), and millimeter wave is an electromagnetic wave between infrared light wave and microwave frequency band.
  • a millimeter wave radar usually includes an antenna device for transmitting millimeter wave signals and receiving reflected signals.
  • the millimeter wave signal transmitted by the antenna device is reflected by the target and then received by the receiving module of the antenna device to obtain the desired signal.
  • the target detection information of the reflection target point of the test target is obtained.
  • the tracking detection method of the present application first executes the steps of powering on or restarting the millimeter wave radar.
  • the millimeter-wave radar is powered on or restarted, usually in the following scenarios, including:
  • the parameter configuration includes at least one of radio frequency parameter configuration, installation parameter configuration, and algorithm parameter configuration.
  • the parameter configuration may also include other parameter configurations, which are not listed here.
  • the millimeter wave radar first stops the radio frequency signal transmission, and restarts to reset the parameter configuration of the millimeter wave radar.
  • the parameter configuration may include at least one of radio frequency parameter need to be reset and algorithm parameter reset.
  • the goal set in this way is mainly because the vehicle needs to go through different scenarios in the process of forward and backward. For example, the forward speed is generally faster, and the backward speed is slower. The main problems to be solved are also different.
  • the tracking detection method further includes: determining the current motion state of the vehicle; according to the current motion state of the vehicle, initiating a corresponding detection mode, the detection mode including at least one of the following: a forward gear detection mode, Reverse gear detection mode. That is, when the current motion state of the vehicle is the forward gear state, the forward gear detection mode is activated, and when the current motion state of the vehicle is the reverse gear state, the reverse gear detection mode is activated.
  • the method for determining the current motion state of the vehicle includes: acquiring body information, and determining the current motion state of the vehicle according to the body information.
  • the vehicle body information includes at least one of vehicle speed, gear position, steering, and yaw rate.
  • the foregoing information may be obtained from the vehicle body CAN bus according to a protocol, or the foregoing information may be obtained through other suitable methods. .
  • the vehicle body information includes vehicle speed
  • the acquiring vehicle body information and determining the current motion state of the vehicle according to the vehicle body information includes: determining the vehicle speed according to the vehicle speed Whether the current state of the vehicle is in the forward gear state or the reverse state, wherein when the vehicle speed is greater than the threshold vehicle speed, it is determined that the current state of the vehicle is the forward gear state, and when the vehicle speed is less than the threshold vehicle speed, the vehicle is determined The current state of motion is reverse gear.
  • the above-mentioned threshold vehicle speed can be set reasonably according to the empirical value of the actual vehicle motion state, which is not specifically limited here. Since the speed is generally faster when moving forward and slower when moving backward, the current motion state of the vehicle can be determined according to the vehicle speed.
  • the reverse mode radio frequency parameter configuration when the current state of motion of the vehicle is the reverse gear state, the reverse mode radio frequency parameter configuration is set to activate the reverse gear detection mode; when the current state of the vehicle is the forward gear state, Set the forward mode radio frequency parameter configuration to activate the forward gear detection mode.
  • BSD side-to-back blind spot monitoring system
  • LCA assisted lane change
  • RPC Rear Collision Early Warning
  • the detection distance range of the reverse mode radio frequency parameter configuration is smaller than that of the forward mode radio frequency parameter configuration.
  • the reversing mode radio frequency parameter configuration has a larger field of view than the software filtering of the forward mode radio frequency parameter configuration.
  • the distance resolution of the reverse mode radio frequency parameter configuration is higher than that of the forward mode radio frequency parameter configuration.
  • the forward gear detection mode further includes: setting a forward target tracking gate parameter.
  • the vehicle is in the forward gear state, that is, when the vehicle is moving forward, the lateral focus of the backward target is reduced, and the preset forward target tracking gate parameter is compared with the lateral gate distance of the backward motion. Be narrow.
  • the tracking detection method further includes: tracking and detecting a forward moving target based on the forward mode radio frequency parameter configuration and the forward target tracking gate parameter.
  • the reverse gear detection mode is activated, including: setting the reverse mode radio frequency parameter configuration, and then performing reflection target point detection to obtain reflection Target detection information of the target point, where the target detection information includes position information of the reflective target point in the movement direction of the current movement state of the vehicle.
  • the position information includes original target information obtained after one-dimensional or two-dimensional fast Fourier plus angle measurement, which has not been tracked but has undergone changes in vehicle body coordinates.
  • the position information also includes the movement speed and angle of the reflection target point.
  • the position information also includes distance information, which refers to the distance information of the reflective target point in the direction of the vehicle's current motion state, that is, the distance between the reflective target point and the vehicle body millimeter wave radar Distance information in the direction of movement of the current state of the vehicle.
  • the position information can be the position information in the vehicle body coordinate system.
  • the vehicle body coordinate system is established in the manner shown in FIG. 4, and the vehicle body coordinate system is based on the length of the vehicle body (or the forward or backward direction of the vehicle).
  • Is the X axis the width direction of the vehicle body is the Y axis, and the direction perpendicular to both the X axis and the Y axis is the Z axis, where the distance information included in the position information is the distance in the X direction.
  • step S102 is performed to determine a processing mode of the reflective target point according to the position information, wherein the processing mode includes at least one of the following: a clustering target mode and a tracking target mode.
  • the position information includes distance information
  • the processing mode of the reflection target point is determined according to the distance information and a preset distance threshold, wherein if the distance information does not exceed the distance threshold, the The processing mode of the reflective target point is the clustering target mode; if the distance information exceeds the distance threshold, the processing mode of the reflective target point is the tracking target mode.
  • a tracked target point can be used to represent the target at a distance. If the distance information exceeds the distance threshold, the processing mode of the reflected target point In order to track the target mode, it will occupy a large angle when it is close. It is not easy to express the characteristics of the object when using distance, speed, and angle gates. Therefore, algorithm operations such as clustering will be introduced.
  • the processing mode of the reflection target point is the clustering target mode.
  • the tracking detection method further includes: forming a preset type of detection target according to the determined processing mode, and the preset type of detection target includes at least one of the following: clustering target and tracking target.
  • the cluster target is formed according to the cluster target pattern
  • the tracking target is formed according to the tracking target pattern.
  • the reflection target points are clustered to form a clustering target.
  • the longitudinal distance that is, the distance in the x-direction
  • the reflective target points are usually within a relatively close range.
  • a clustering strategy can be used to cluster the reflective target points to form a clustering target, for example, Clustering algorithms such as DBSCAN, OPTICS, DENCLUE and other algorithms perform clustering.
  • the tracking gate parameters of the laterally moving object include a longitudinal distance gate and a lateral distance gate. For a laterally moving object, the range of the longitudinal distance gate is smaller and the range of the lateral gate is larger, and the range of the longitudinal distance gate is smaller than the range of the transverse gate. The range of the horizontal distance from the gate.
  • the reflection target point set is formed into a point set, that is, a clustering target.
  • the clustering target has parameters such as center of gravity and range. .
  • the position information of the detection target is calculated, and the position information includes at least one of the following: the angular change rate of the target position, the trend of the angular change rate, and the distance change of the target position in the moving direction of the vehicle.
  • the method of calculating the position information of the detection target is different.
  • the position information of the cluster target is calculated, and the position information includes the angle change rate, the angle change rate trend of the cluster target, and The distance change of the clustering target in the moving direction of the vehicle.
  • the position information of the cluster target further includes at least one of the center of gravity coordinate and the action range of the cluster target.
  • the detection target is a tracking target
  • the tracking target is classified and aggregated.
  • the classifying and aggregating the tracking target includes: after the tracking target is formed, identifying at least part of the tracking target, such as pedestrian classification based on distance and energy to judge the RCS statistics of the target And/or trucks composed of multiple points.
  • the tracking target mode target tracking is performed on the reflective target point to form a tracking target.
  • the tracking target mode also refers to the conventional ordinary tracking process, which can include pre-tracking track, mature track and other related processes.
  • the detection target of the preset type for example, a cluster target and a tracking target
  • the angle change rate of the target position is greater than the angle change rate threshold, if otherwise, it is temporarily recognized as a normal target, if it is, it is determined whether the angle change rate trend is increasing or decreasing, if otherwise Tentatively set as a normal target, if yes, determine whether the distance change of the target position in the direction of the vehicle's movement is less than the distance change threshold, if yes, determine that the detection target (such as clustering target and tracking target) is a laterally moving object, if otherwise Tentatively set as a general target.
  • the value of the angle change rate threshold is related to the distance between the detection target and the millimeter wave radar in the direction of movement of the vehicle.
  • the angle change rate threshold is set The smaller the value.
  • the angle change rate of the clustering target can be calculated by obtaining the position information of the clustering target in multiple frames.
  • the angle change rate threshold of the tracking target is also a distance-related value, but since the tracking target is far from the vehicle body, the distance component coefficient here is already relatively small because the basic angle is relatively small relative to nearby objects. Therefore, the threshold of the angle change rate of the tracking target and the threshold of the angle change rate of the cluster target are different parameters.
  • the determining whether the angle change rate trend is increasing or decreasing includes: determining the angle change according to the direction of movement of the detection target (for example, a clustering target or a tracking target) in the backward direction of the vehicle Whether the rate trend is increasing or decreasing.
  • the detection target for example, a clustering target or a tracking target
  • the determining whether the angular change rate trend is increasing or decreasing according to the direction of movement of the detection target in the rear of the vehicle includes: when the direction of movement of the detection target in the rear of the vehicle is from inside to outside When the angle change rate trend is increasing (in the statistical interval, FIFO); when the detection target moves in the backward direction of the vehicle from the outside to the inside, the angle change rate trend is decreasing (In the statistical interval, FIFO).
  • the direction of movement of the detection target in the backward direction of the vehicle is from inside to outside, including the detection target being in the rear of the vehicle to the left and moving outwards and the detection target being in the back of the vehicle to the right and moving out; and
  • the movement direction of the detection target in the backward direction of the vehicle is from the outside to the inside, including the detection target being in the left and inward movement after the vehicle and the detection target being in the right and inward movement after the vehicle.
  • the above-mentioned basically similar logic can be used to determine whether the angle change rate trend is increasing or decreasing.
  • the judgment condition strictness in the statistical interval (FIFO) is weaker than that of aggregation. Class goals.
  • the distance change of the target position in the moving direction of the vehicle is the distance change after the vehicle speed compensation is added.
  • the distance of the target position in the lateral direction is the distance in the geodetic coordinate system, and the distance in the geodetic coordinate system is converted from the distance in the vehicle body coordinate system to reflect the lateral movement.
  • the laterally moving object After determining that the detection target is a laterally moving object (that is, a laterally moving target), the laterally moving object is tracked and detected.
  • a millimeter-wave radar is arranged behind the vehicle, and the tracking and detecting the laterally moving object includes: tracking and detecting the laterally moving object based on the millimeter-wave radar.
  • tracking and detecting the laterally moving object further includes: using the laterally moving object tracking gate parameter to track and detect the laterally moving object for the detection target determined to be a laterally moving object; and For the detection target tentatively designated as a common target, common gate parameters are used.
  • Ordinary target gate parameters are mainly the distance gate and speed gate of ordinary moving targets.
  • the main difference between it and the horizontally moving object is that the horizontally moving object has a small distance from the gate in the longitudinal direction (X direction) and the horizontal (Y direction) )
  • the range of the wave gate is relatively large, that is, the parameters of the laterally moving object tracking wave gate include a longitudinal distance wave gate and a lateral distance wave gate, wherein the range of the longitudinal distance wave gate is smaller than the range of the lateral distance wave gate.
  • the laterally moving object tracking gate parameter and the ordinary gate parameter both include a range gate, a velocity gate, and an angle gate, where the tracking gate parameter of the laterally moving object tracking target The distance gate and the velocity gate are smaller than those of the ordinary gate parameters, and the angle gate of the laterally moving object tracking gate parameter is larger than the angle gate of the ordinary gate parameter.
  • the clustering target and the tracking target adopt different laterally moving object tracking gate parameters.
  • the laterally moving object tracking gate parameter refers to the system gate used in the normal tracking system, including distance, speed and angle, when lateral motion is used At time, the distance and velocity gates become smaller, and the angle gates become larger.
  • the longitudinal direction refers to the x direction in the vehicle body coordinate system
  • the lateral direction refers to the y direction in the vehicle body coordinate system.
  • FIG. 5 shows a schematic block diagram of a millimeter wave radar 300 in an embodiment of the present invention.
  • the millimeter wave radar is used to implement the tracking detection method in the foregoing embodiment.
  • the millimeter wave radar 300 includes one or more processors 303, which work individually or together, and the processors are used to: obtain target detection information of a reflection target point, and the target detection information includes the reflection Position information of the target point in the movement direction of the current movement state of the vehicle, wherein the current movement state includes at least one of the following: a forward gear state, a reverse gear state; and the reflection target is determined according to the position information Point processing mode, wherein the processing mode includes at least one of the following: a clustering target mode and a tracking target mode.
  • the position information includes distance information, and the processing mode of the reflective target point is determined according to the distance information and a preset distance threshold, wherein if the distance information does not exceed the distance threshold, the processing mode of the reflective target point Is the cluster target mode; if the distance information exceeds the distance threshold, the processing mode of the reflected target point is the tracking target mode.
  • the processor 303 may be a central processing unit (CPU), an image processing unit (GPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a data processing capability and/or instruction execution capability. Other forms of processing units, and can control other components in the millimeter wave radar 300 to perform desired functions.
  • the processor can execute the instructions stored in the memory to execute the millimeter wave radar tracking and detection method described herein, and the method will not be repeated here.
  • the processor 303 can include one or more embedded processors, processor cores, microprocessors, logic circuits, hardware finite state machines (FSM), digital signal processors (DSP), or combinations thereof.
  • the processor 303 is further configured to: power on or restart the millimeter wave radar.
  • the processor is further used for: when the vehicle is just powered on, the millimeter-wave radar is powered on and initialized and the parameter configuration is initialized; when the vehicle changes forward or reverse gear, the millimeter-wave radar first stops transmitting radio frequency signals, and Restart to reset the parameter configuration of the millimeter wave radar.
  • the parameter configuration includes at least one of radio frequency parameter configuration, installation parameter configuration, and algorithm parameter configuration.
  • the processor is further configured to: determine the current motion state of the vehicle; according to the current motion state of the vehicle, activate a corresponding detection mode, the detection mode includes at least one of the following: a forward gear detection mode, Reverse gear detection mode. That is, when the current motion state of the vehicle is the forward gear state, the forward gear detection mode is activated, and when the current motion state of the vehicle is the reverse gear state, the reverse gear detection mode is activated.
  • the processor is further configured to obtain vehicle body information, and determine the current motion state of the vehicle according to the vehicle body information.
  • vehicle body information includes at least one of vehicle speed, gear position, steering, and yaw rate
  • the vehicle body information includes a vehicle speed
  • the processor is further configured to determine whether the current state of motion of the vehicle is in a forward gear state or a reverse gear state according to the vehicle speed, wherein, when the vehicle speed is greater than When the threshold vehicle speed is used, it is determined that the current state of motion of the vehicle is a forward gear state, and when the vehicle speed is less than the threshold vehicle speed, it is determined that the current state of motion of the vehicle is a reverse gear state.
  • the processor is further configured to: form a preset type of detection target according to the determined processing mode, and the preset type includes at least one of the following: clustering target, tracking target; calculating the detection target
  • the position information of the target includes at least one of the following: the angle change rate of the target position, the trend of the angle change rate, and the distance change of the target position in the direction of the vehicle's movement; Whether the preset type of detection target is a laterally moving object; and tracking and detecting the laterally moving object.
  • clustering target mode clustering the reflection target points to form a clustering target.
  • tracking target mode target tracking is performed on the reflective target point to form a tracking target.
  • the position information includes the angle change rate of the cluster target, the trend of the angle change rate, and the distance change of the cluster target in the moving direction of the vehicle.
  • the position information of the cluster target further includes at least one of the center of gravity coordinate and the action range of the cluster target.
  • the detection target is a tracking target
  • the tracking target is classified and aggregated.
  • the processor is also used for judging the pedestrian classification of the target RCS statistical value based on distance and energy and/or a truck composed of multiple points.
  • the processor is further configured to determine whether the angle change rate of the target position is greater than the angle change rate threshold; if not, it is temporarily recognized as a normal target; if so, determine whether the angle change rate trend is increasing Or decrementally, if otherwise, it is tentatively set as a normal target, if so, it is determined whether the distance change of the target position in the direction of the vehicle's movement is less than the distance change threshold, if it is, it is determined that the detection target is a laterally moving object, if otherwise, it is tentatively set as a normal target aims.
  • the value of the angle change rate threshold is related to the distance between the detection target and the millimeter wave radar in the moving direction of the vehicle, and when the distance is greater, the value of the angle change rate threshold The smaller.
  • the processor is further configured to determine whether the angle change rate trend is increasing or decreasing according to the direction of movement of the detection target in the backward direction of the vehicle.
  • the processor is further configured to: when the direction of movement of the detection target in the backward direction of the vehicle is from the inside to the outside, the angle change rate trend is increased; when the detection target is in the backward direction of the vehicle When the movement direction is from the outside to the inside, the trend of the angle change rate appears to decrease.
  • the direction of movement of the detection target in the backward direction of the vehicle is from inside to outside, including the detection target being in the rear of the vehicle to the left and moving outwards and the detection target being in the back of the vehicle to the right and moving out; and
  • the movement direction of the detection target in the backward direction of the vehicle is from the outside to the inside, including the detection target being in the left and inward movement after the vehicle and the detection target being in the right and inward movement after the vehicle.
  • the processor is further configured to: for the detection target determined to be a laterally moving object, use the laterally moving object tracking gate parameter to track and detect the laterally moving object;
  • the detection target of adopts ordinary wave gate parameters.
  • the processor is further configured to: when the current motion state of the vehicle is the reverse gear state, set the reverse mode radio frequency parameter configuration to start the reverse gear detection mode; when the current motion state of the vehicle is In the forward gear state, the forward mode radio frequency parameter configuration is set to activate the forward gear detection mode.
  • the processor is further configured to: set forward target tracking gate parameters to perform the forward gear detection mode.
  • the processor is further configured to track and detect a forward moving target based on the forward mode radio frequency parameter configuration and the forward target tracking gate parameter.
  • the millimeter wave radar 300 further includes an antenna device 301, which is used to transmit millimeter wave signals and receive reflected signals; millimeter wave radar uses millimeter waves, usually millimeter waves refer to 30-300 GHz In the frequency domain (wavelength is 1-10mm), millimeter wave is an electromagnetic wave between infrared light wave and microwave frequency band.
  • the millimeter wave radar 300 generally includes an antenna device 301 for transmitting millimeter wave signals and receiving reflected signals.
  • the millimeter wave signals transmitted by the antenna device are reflected by the target and then received by the receiving module of the antenna device to obtain
  • the reflection target point to the target to be measured can also be called a point cloud.
  • the antenna device 301 may include an array antenna (such as a transmitting antenna) dedicated to transmitting millimeter wave signals and an array antenna (such as a receiving antenna) dedicated to receiving reflected signals.
  • the millimeter wave radar 300 further includes a signal processing circuit 302, electrically connected to the antenna device 301, for processing the reflected signal and converting it into a data signal, wherein the processor 303 is connected to the signal
  • the processing circuit 302 is connected in communication and is used to process the data signal sent by the signal processing circuit 302.
  • the signal processing circuit 302 and the processor 303 may communicate in a wired or wireless manner.
  • the signal processing circuit 302 includes an incident wave estimation unit AU.
  • the incident wave estimating unit AU uses a well-known algorithm to infer the distance to the wave source of the incident wave, namely the target, the relative speed of the target, and the orientation (that is, the angle) of the target, and generates a data signal representing the inference result, that is, the signal processing circuit and the target
  • the antenna device is electrically connected to process the reflected signal and convert it into a data signal, and the data signal includes the position information of the reflected target point and the like.
  • the signal processing circuit in the embodiment of the present invention is not limited to a single circuit, and includes a form in which a combination of multiple circuits is generally understood as a functional element.
  • the signal processing circuit 302 can also be implemented by one or more systems on a chip (SoC).
  • SoC systems on a chip
  • a part or all of the signal processing circuit 302 may also be a programmable logic device (PLD), that is, an FPGA (Field-Programmable Gate Array).
  • PLD programmable logic device
  • FPGA Field-Programmable Gate Array
  • the signal processing circuit 302 includes a plurality of arithmetic elements (for example, general logic and multipliers) and a plurality of storage elements (for example, a look-up table or a memory module).
  • the signal processing circuit 302 may also be a collection of a general-purpose processor and a main storage device.
  • the signal processing circuit 302 may also be a circuit including a processor core and a memory. These can function as the
  • the components and structure of the millimeter wave radar 300 shown in FIG. 5 are only exemplary and not restrictive, and the components of the millimeter wave radar 300 may also have other components and structures as required. Among them, the technical features in the aforementioned tracking detection method can also be applied to this embodiment, and the description will not be repeated here.
  • the embodiment of the present invention also provides a computer storage medium on which a computer program is stored.
  • the computer storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk Read-only memory (CD-ROM), USB memory, or any combination of the above storage media.
  • the computer-readable storage medium may be any combination of one or more computer-readable storage media.
  • One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may run the program instructions stored in the memory to implement the functions (implemented by the processor) in the embodiments of the present invention described herein And/or other desired functions, for example, to perform the corresponding steps of the method for detecting stationary objects near a fence by a microwave radar according to an embodiment of the present invention.
  • Various application programs and various data such as various data used and/or generated by the application program, can also be stored in the computer-readable storage medium.
  • an embodiment of the present invention also provides a vehicle, which includes the millimeter wave radar in the foregoing embodiment.
  • the vehicle may include an autonomous vehicle, or other types of vehicles.
  • the vehicle includes a vehicle body, and the millimeter wave radar may be arranged in front and/or rear of the vehicle body, or other suitable positions.
  • one or more millimeter wave radars can be installed on the vehicle body.
  • the aforementioned millimeter-wave radar tracking detection method can be implemented, so as to accurately and effectively determine whether the detection target is a laterally moving object, and track and detect the detection target determined as a laterally moving object, thereby improving the safety of the entire ADAS And robustness, it can more effectively protect lateral shuttle obstacles (such as crossing pedestrians), effectively avoid accidents caused by lateral moving objects during driving, and improve user experience.
  • the disclosed device and method may be implemented in other ways.
  • the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another device, or some features can be ignored or not implemented.
  • the various component embodiments of the present invention may be implemented by hardware, or by software modules running on one or more processors, or by their combination.
  • a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some modules according to the embodiments of the present invention.
  • DSP digital signal processor
  • the present invention can also be implemented as a device program (for example, a computer program and a computer program product) for executing part or all of the methods described herein.
  • Such a program for realizing the present invention may be stored on a computer-readable medium, or may have the form of one or more signals. Such signals can be downloaded from Internet websites, or provided on carrier signals, or provided in any other form.

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)
  • Radar Systems Or Details Thereof (AREA)

Abstract

一种毫米波雷达(300)的跟踪检测方法、毫米波雷达(300)和车辆,方法包括:获取反射目标点的目标检测信息,目标检测信息包括反射目标点在车辆的当前运动状态的运动方向上的位置信息,其中,当前运动状态包括如下至少一种:前进档状态,倒车档状态(S101);根据位置信息,确定反射目标点的处理模式,其中,处理模式包括如下至少一种:聚类目标模式,跟踪目标模式(S102)。能够准确有效的确定检测目标是否为横向运动物体,并对确定为横向运动物体的检测目标进行跟踪检测,提高整个ADAS的安全性和鲁棒性。

Description

毫米波雷达的跟踪检测方法、毫米波雷达和车辆
说明书
技术领域
本发明总地涉及自动驾驶技术领域,更具体地涉及一种毫米波雷达的跟踪检测方法、毫米波雷达和车辆。
背景技术
最近几年汽车毫米波雷达技术越来越广泛地应用在高级辅助驾驶(Advanced Driver Assistant System,ADAS)系统中,并在未来的自动驾驶系统中占据着不可或缺的地位。毫米波雷达相对于视觉和激光雷达等传感器来说,其具有全天时、全天候、作用距离远、测速精度高等独特的优势。
毫米波雷达本身由于物理限制,反射(Reflector)层面上只能检测径向距离和径向速度,缺乏切向物体的检测能力。然而横向穿梭障碍物预警(CTA)功能对于驾驶辅助系统是一项非常重要的功能。在之前24GHz的后向雷达检测系统中,通常只有一些开门预警(DOW),盲点监测系统(BSD),辅助变道(LCA),后方碰撞预警(RPC)等基本功能,这些主要都与雷达的径向检测或者对切向速度的判断能力要求不高。而随着时代的发展,ADAS功能对横穿物体,尤其是车前车后(尤其是倒车时车后)的横穿行人的保护要求越来越高,因此对横向穿梭障碍物预警(CTA)功能也提出了更高的要求。
发明内容
为了解决上述问题中的至少一个而提出了本发明。具体地,本发明一方面提供一种毫米波雷达的跟踪检测方法,所述跟踪检测方法包括:
获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息,其中,所述当前运动状态包括如下至少一种:前进档状态,倒车档状态;
根据所述位置信息,确定所述反射目标点的处理模式,其中,所述处理模式包括如下至少一种:聚类目标模式,跟踪目标模式。
示例性地,所述跟踪检测方法还包括:
确定车辆的当前运动状态;
根据所述车辆的当前运动状态,启动相应的检测模式,所述检测模式包括如下至少一种:前进档检测模式,倒车档检测模式。
示例性地,所述跟踪检测方法还包括:
按照确定的处理模式,形成预设类型的检测目标,所述预设类型包括如下至少一种:聚类目标,跟踪目标;
计算所述检测目标的位置信息,所述位置信息包括如下至少一种:目标位置的角度变化率、角度变化率趋势以及目标位置在车辆的运动方向上的距离变化;
根据所述检测目标的位置信息,确定所述预设类型的检测目标是否为横向运动物体;
对所述横向运动物体进行跟踪检测。
示例性地,所述位置信息包括距离信息,所述反射目标点的处理模式根据所述距离信息以及预设距离门限来确定,
其中,若所述距离信息未超过距离门限,则所述反射目标点的处理模式为所述聚类目标模式;若所述距离信息超过距离门限,则所述反射目标点的处理模式为跟踪目标模式。
示例性地,在所述聚类目标模式时,对所述反射目标点进行聚类以形成聚类目标。
示例性地,在所述跟踪目标模式时,对所述反射目标点进行目标跟踪以形成跟踪目标。
示例性地,在所述确定车辆的当前运动状态之前,所述跟踪检测方法还包括:
所述毫米波雷达上电启动或重新启动。
示例性地,所述毫米波雷达上电启动或重新启动,包括:
车辆刚上电启动时,所述毫米波雷达上电启动并对参数配置进行初始化操作;
车辆更换前进挡或倒挡时,所述毫米波雷达先停止射频信号发射,并重新启动以对毫米波雷达的参数配置进行重置。
示例性地,所述参数配置包括射频参数配置、安装参数配置和算法参数 配置中的至少一种。
示例性地,若所述检测目标为聚类目标,则所述位置信息包括所述聚类目标的角度变化率、角度变化率趋势以及聚类目标在车辆的运动方向上的距离变化。
示例性地,所述聚类目标的位置信息还包括所述聚类目标的重心坐标和作用范围中的至少一种。
示例性地,若所述检测目标为跟踪目标,对所述跟踪目标进行分类和聚合。
示例性地,所述对所述跟踪目标进行分类和聚合,包括:
根据依据距离和能量判断目标RCS统计值的行人分类和/或多个点组成的卡车。
示例性地,根据所述检测目标的位置信息,确定所述预设类型的检测目标是否为横向运动物体,包括:
确定目标位置的角度变化率是否大于角度变化率门限,若否则暂时认定为普通目标,若是,则确定所述角度变化率趋势是否呈现为递增或递减,若否则暂定为普通目标,若是,则确定目标位置在车辆的运动方向上的距离变化是否小于距离变化门限,若是则确定所述检测目标为横向运动物体,若否则暂定为普通目标。
示例性地,所述角度变化率门限的取值与所述检测目标和所述毫米波雷达在车辆的运动方向上的距离相关,当该距离越大时,所述角度变化率门限的取值越小。
示例性地,所述确定所述角度变化率趋势是否呈现为递增或递减,包括:
根据所述检测目标在车辆后向的运动方向,确定所述角度变化率趋势是否呈现为递增或递减。
示例性地,所述根据所述检测目标在车辆后向的运动方向,确定所述角度变化率趋势是否呈现为递增或递减,包括:
当所述检测目标在车辆后向的运动方向为从内向外运动时,所述角度变化率趋势呈现为递增;
当所述检测目标在所述车辆后向的运动方向为从外向内运动时,所述角度变化率趋势呈现为递减。
示例性地,所述检测目标在车辆后向的运动方向为从内向外运动包括所述检测目标处于车辆后向左侧且向外运动和所述检测目标处于车辆后向右侧且向外运动;以及
所述检测目标在车辆后向的运动方向为从外向内运动包括所述检测目标处于车辆后向左侧且向内运动和所述检测目标处于车辆后向右侧且向内运动。
示例性地,目标位置在车辆的运动方向上的距离变化为加入车速补偿后的距离变化。
示例性地,在车辆运动时,目标位置在横向上的距离为大地坐标系中的距离,该大地坐标系中的距离由车体坐标系中的距离转换而来。
示例性地,对所述横向运动物体进行跟踪检测,还包括:
对确定是横向运动物体的所述检测目标,采用横向运动物体跟踪波门参数对所述横向运动物体进行跟踪检测;以及
对暂定为普通目标的所述检测目标,采用普通波门参数。
示例性地,所述横向运动物体跟踪波门参数包括纵向距离波门和横向距离波门,其中,所述纵向距离波门的范围小于所述横向距离波门的范围。
示例性地,所述聚类目标和所述跟踪目标采用不同的横向运动物体跟踪波门参数。
示例性地,所述横向运动物体跟踪波门参数和所述普通波门参数均包括距离波门、速度波门和角度波门,其中,对于所述跟踪目标的横向运动物体跟踪波门参数的距离波门和速度波门小于普通波门参数的距离波门和速度波门,而横向运动物体跟踪波门参数的角度波门大于所述普通波门参数的角度波门。
示例性地,所述确定车辆的当前运动状态,包括:
获取车身信息,根据所述车身信息确定所述车辆的当前运动状态。
示例性地,所述车身信息包括车速,其中,所述获取车身信息,根据所述车身信息确定所述车辆的当前运动状态,包括:
根据所述车速确定所述车辆的当前运动状态是处于前进档状态还是倒车档状态,其中,在车速大于阈值车速时,确定所述车辆的当前运动状态为前进档状态,在所述车速小于阈值车速时,确定所述车辆的当前运动状态为倒车档状态。
示例性地,所述车身信息包括车速、档位、转向、横摆角速度中的至少一种。
示例性地,在所述车辆的当前运动状态为倒车档状态时,设置倒车模式射频参数配置,以启动倒车档检测模式;
在所述车辆的当前运动状态为前进档状态时,设置前向模式射频参数配置,以启动所述前进档检测模式。
示例性地,所述位置信息包括一维或二维快速傅里叶加上测角后获得的未经跟踪处理但已经经过车身坐标发生变化的原始目标信息。
示例性地,所述位置信息还包括所述反射目标点的运动速度和角度。
示例性地,所述倒车模式射频参数配置相比所述前向模式射频参数配置的检测距离范围更小。
示例性地,所述倒车模式射频参数配置相比所述前向模式射频参数配置的软件过滤的视场角更大。
示例性地,所述倒车模式射频参数配置相比所述前向模式射频参数配置的距离分辨率更高。
示例性地,所述前进档检测模式还包括:
设置前向目标跟踪波门参数。
示例性地,所述跟踪检测方法还包括:
基于所述前向模式射频参数配置和所述前向目标跟踪波门参数对前向运动目标进行跟踪检测。
示例性地,所述车辆后方设置有毫米波雷达,所述对所述横向运动物体进行跟踪检测,包括:
基于所述毫米波雷达对所述横向运动物体进行跟踪检测。
本发明再一方面提供一种毫米波雷达,所述毫米波雷达包括:
一个或多个处理器,单独地或共同地工作,所述处理器用于:
获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息,其中,所述当前运动状态包括如下至少一种:前进档状态,倒车档状态;
根据所述位置信息,确定所述反射目标点的处理模式,其中,所述处理模式包括如下至少一种:聚类目标模式,跟踪目标模式。
示例性地,还包括:
天线装置,用于发射毫米波信号以及接收反射信号;以及
信号处理电路,与所述天线装置电连接,用于处理所述反射信号,并转换为数据信号,
其中,所述处理器与所述信号处理电路通讯连接,用于处理所述信号处理电路发送的数据信号。
本发明又一方面提供一种车辆,所述车辆包括车身以及前述的毫米波雷达,所述毫米波雷达安装在所述车身的前方或/及后方。
本发明实施例的跟踪检测方法通过获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息,其中,所述当前运动状态包括如下至少一种:前进档状态,倒车档状态;根据所述位置信息,确定所述反射目标点的处理模式,其中,所述处理模式包括如下至少一种:聚类目标模式,跟踪目标模式。该跟踪检测方法根据反射目标点的位置信息,对反射目标点进行不同的处理模式,以保证采用更准确的处理模式对检测目标进行检测和处理。
更进一步地,本发明实施例的跟踪检测方法,按照确定的处理模式,形成预设类型的检测目标,所述预设类型包括如下至少一种:聚类目标,跟踪目标;计算所述检测目标的位置信息,所述位置信息包括如下至少一种:目标位置的角度变化率、角度变化率趋势以及目标位置在车辆的运动方向上的距离变化;根据所述检测目标的位置信息,确定所述预设类型的检测目标是否为横向运动物体;对所述横向运动物体进行跟踪检测。从而准确有效的确定检测目标是否为横向运动物体,并对确定为横向运动物体的检测目标进行跟踪检测,提高整个ADAS的安全性和鲁棒性,能够更有效的对横向穿梭障碍物(例如横穿行人)进行保护,有效避免驾驶过程中由于横向运动物体而导致的事故发生,提升用户体验。
附图说明
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性 劳动性的前提下,还可以根据这些附图获得其他的附图。
图1示出了本发明一个实施例中的毫米波雷达的跟踪检测方法的示意性流程图;
图2示出了本发明一个实施例中的车身后向毫米波雷达的探测威力图;
图3示出了本发明一个具体实施例中的毫米波雷达的跟踪检测方法的示意性流程图;
图4示出了本发明一个实施例中的车体坐标系的示意图;
图5示出了本发明一个实施例中的毫米波雷达的示意性框图。
具体实施方式
为了使得本发明的目的、技术方案和优点更为明显,下面将参照附图详细描述根据本发明的示例实施例。显然,所描述的实施例仅仅是本发明的一部分实施例,而不是本发明的全部实施例,应理解,本发明不受这里描述的示例实施例的限制。基于本发明中描述的本发明实施例,本领域技术人员在没有付出创造性劳动的情况下所得到的所有其它实施例都应落入本发明的保护范围之内。
在下文的描述中,给出了大量具体的细节以便提供对本发明更为彻底的理解。然而,对于本领域技术人员而言显而易见的是,本发明可以无需一个或多个这些细节而得以实施。在其他的例子中,为了避免与本发明发生混淆,对于本领域公知的一些技术特征未进行描述。
应当理解的是,本发明能够以不同形式实施,而不应当解释为局限于这里提出的实施例。相反地,提供这些实施例将使公开彻底和完全,并且将本发明的范围完全地传递给本领域技术人员。
在此使用的术语的目的仅在于描述具体实施例并且不作为本发明的限制。在此使用时,单数形式的“一”、“一个”和“所述/该”也意图包括复数形式,除非上下文清楚指出另外的方式。还应明白术语“组成”和/或“包括”,当在该说明书中使用时,确定所述特征、整数、步骤、操作、元件和/或部件的存在,但不排除一个或更多其它的特征、整数、步骤、操作、元件、部件和/或组的存在或添加。在此使用时,术语“和/或”包括相关所列项目的任何及所有组合。
为了彻底理解本发明,将在下列的描述中提出详细的结构,以便阐释本 发明提出的技术方案。本发明的可选实施例详细描述如下,然而除了这些详细描述外,本发明还可以具有其他实施方式。
针对横向穿行物体(也即横向运动物体)的检测机制(CTA类应用),本发明提供了一种毫米波雷达的跟踪检测方法,如图1所示,所述方法包括:
步骤S101,获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息,其中,所述当前运动状态包括如下至少一种:前进档状态,倒车档状态;
步骤S102,根据所述位置信息,确定所述反射目标点的处理模式,其中,所述处理模式包括如下至少一种:聚类目标模式,跟踪目标模式。
该跟踪检测方法根据反射目标点的位置信息,对反射目标点进行不同的处理模式,以保证采用更准确的处理模式对检测目标进行检测和处理。
下面结合附图,对本申请的一种毫米波雷达的跟踪检测方法进行详细说明。在不冲突的情况下,下述的实施例及实施方式中的特征可以相互组合。
在如图1所示的实施例中,毫米波雷达的跟踪检测方法包括以下步骤:
首先,执行步骤S101,获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息,其中,所述当前运动状态包括如下至少一种:前进档状态,倒车档状态。
可以通过任意适合的方法获取反射目标点的目标检测信息,例如基于毫米波雷达探测目标物,而获得反射目标点的目标检测信息。毫米波雷达安装于移动平台上,例如安装于车辆的车身上,该车辆还可以包括自动驾驶车辆。该毫米波雷达可以安装于车辆的车身上,例如安装于车身的前方和/或后方,如图2所示的示例中,在车身的后方安装有毫米波雷达,例如安装有两个毫米波雷达,该两个毫米波雷达覆盖车辆后方大概120-270°的视场角(FOV)。
毫米波雷达的测距测速精度高,并且光线、天气等天气环境因素对毫米雷达波的检测基本没有影响,当然本领域技术人员能够理解,本发明不限于使用毫米雷达波来进行目标检测,也可以使用其他的方式和手段来进行检测。
毫米波雷达使用毫米波(millimeter wave)通常毫米波是指30~300GHz频域(波长为1~10mm)的,毫米波是一种介于红外光波和微波频段之间的电磁波。
在一个示例中,毫米波雷达通常包括天线装置,用于发射毫米波信号以及 接收反射信号,天线装置发射的毫米波信号经目标反射后,又被天线装置的接收模块所接收,从而获取到待测目标的反射目标点的目标检测信息。
更具体地,如图2所示,本申请的跟踪检测方法首先执行毫米波雷达上电启动或重新启动的步骤。该毫米波雷达上电启动或重新启动,通常发生于以下场景,包括:
场景1、车辆刚上电启动时,所述毫米波雷达上电启动并对参数配置进行初始化操作,以正常启动毫米波雷达的探测功能。所述参数配置包括射频参数配置、安装参数配置和算法参数配置中的至少一种。该参数配置还可以包括其他的参数配置,在此不一一列举。
场景2、车辆更换前进挡或倒挡时,所述毫米波雷达先停止射频信号发射,并重新启动以对毫米波雷达的参数配置进行重置。该参数配置可以包括射频参数需要重置和算法参数重置中的至少一种。这样设置的目标主要是因为车辆在前进和后退的过程,所需要经历的场景不同,比如前进是速度一般较快,而后退是速度较慢,要解决的主要问题也不同,前进时主要关注后向来车,比如侧后向盲点监测系统(BSD),辅助变道(LCA)和正后向的后方碰撞预警(RPC);后退时更加关注横向穿越的人和车的倒车预警系统(RCTA)。由于场景不同和主要解决的问题不同,毫米波雷达的参数配置也会不同,因此,需要在车辆更换前进挡或倒挡时重新启动以对毫米波雷达的参数配置进行重置。
在一个示例中,所述跟踪检测方法还包括:确定车辆的当前运动状态;根据所述车辆的当前运动状态,启动相应的检测模式,所述检测模式包括如下至少一种:前进档检测模式,倒车档检测模式。也即在车辆的当前运动状态为前进挡状态时,启动前进挡检测模式,在车辆的当前运动状态为倒车档状态时,启动倒车档检测模式。
可以采用任意适合的方法确定车辆的当前运动状态,在本发明的一个实施例中,确定车辆的当前运动状态的方法包括:获取车身信息,根据所述车身信息确定所述车辆的当前运动状态。可选地,所述车身信息包括车速、档位、转向、横摆角速度中的至少一种,上述信息可以这些信息可以依据协议从车身CAN总线获取,或者也可以通过其他适合的方式获取上述信息。
在一个具体示例中,如图3所示,所述车身信息包括车速,其中,所述 获取车身信息,根据所述车身信息确定所述车辆的当前运动状态,包括:根据所述车速确定所述车辆的当前运动状态是处于前进档状态还是倒车档状态,其中,在车速大于阈值车速时,确定所述车辆的当前运动状态为前进档状态,在所述车速小于阈值车速时,确定所述车辆的当前运动状态为倒车档状态。上述阈值车速可以根据实际车辆的运动状态的经验值进行合理设定,在此不对其进行具体限定。由于通常前进时速度一般较快,而后退时速度较慢,从而可以依据车速来判定车辆的当前运动状态。
进一步,如图3所示,在所述车辆的当前运动状态为倒车档状态时,设置倒车模式射频参数配置,以启动倒车档检测模式;在所述车辆的当前运动状态为前进档状态时,设置前向模式射频参数配置,以启动所述前进档检测模式。由于后退时速度较慢,更加关注横向运动物体,例如横向穿越的人和车,而前进时速度一般较快,主要关注后向来车,比如侧后向盲点监测系统(BSD),辅助变道(LCA)和正后向的后方碰撞预警(RPC),因此,需要采用不同模式的射频参数配置,以实现不同的功能。
可选地,所述倒车模式射频参数配置相比所述前向模式射频参数配置的检测距离范围更小。可选地,所述倒车模式射频参数配置相比所述前向模式射频参数配置的软件过滤的视场角更大。可选地,所述倒车模式射频参数配置相比所述前向模式射频参数配置的距离分辨率更高。
在一个示例中,如图3所示,所述前进档检测模式还包括:设置前向目标跟踪波门参数。在车辆处于前进档状态时,也即前向运动状态时,后向的目标横向关注度降低,其预设的前向目标跟踪波门参数的横向波门相比后向运动的横向波门距离要窄。
进一步,如图3所示,所述跟踪检测方法还包括:基于所述前向模式射频参数配置和所述前向目标跟踪波门参数对前向运动目标进行跟踪检测。
在一个示例中,如图3所示,在确定车辆的当前运动状态为倒退档状态后,启动倒车档检测模式,包括:设置倒车模式射频参数配置,之后,进行反射目标点检测,以获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息。可选地,所述位置信息包括一维或二维快速傅里叶加上测角后获得的未经跟踪处理但已经经过车身坐标发生变化的原始目标信息。例如,所述位置信息还 包括所述反射目标点的运动速度和角度。所述位置信息还包括距离信息,该距离信息是指所述反射目标点在所述车辆的当前运动状态的运动方向上的距离信息,也即反射目标点与车身毫米波雷达之间在所述车辆的当前运动状态的运动方向上的距离信息。
该位置信息可以是车体坐标系中的位置信息,例如按照图4所示的方式建立车体坐标系,该车体坐标系以车身的长度延伸方向(也可以是车辆的前进或后退方向),为X轴,以车身的宽度方向为Y轴,以与X轴和Y轴均垂直的方向为Z轴,其中,位置信息包括的距离信息为X方向的距离。
接着,如图1所示,执行步骤S102,根据所述位置信息,确定所述反射目标点的处理模式,其中,所述处理模式包括如下至少一种:聚类目标模式,跟踪目标模式。
在一个具体示例中,所述位置信息包括距离信息,所述反射目标点的处理模式根据所述距离信息以及预设距离门限来确定,其中,若所述距离信息未超过距离门限,则所述反射目标点的处理模式为所述聚类目标模式;若所述距离信息超过距离门限,则所述反射目标点的处理模式为跟踪目标模式。由于目标比如汽车等大物体在远处和近处的特点不同,在远处时通常可以使用一个跟踪的目标点来表示,若所述距离信息超过距离门限,则所述反射目标点的处理模式为跟踪目标模式,而在近处时会占据很大的角度,在使用距离、速度、加角度波门时不太容易表示出该物体的特性,因此会引入聚类这样的算法操作,也即在所述距离信息未超过距离门限,则所述反射目标点的处理模式为所述聚类目标模式。
进一步,所述跟踪检测方法还包括:按照确定的处理模式,形成预设类型的检测目标,所述预设类型的检测目标包括如下至少一种:聚类目标,跟踪目标。例如,在按照聚类目标模式形成聚类目标,按照跟踪目标模式形成跟踪目标。
具体地,如图3所示,在所述聚类目标模式时,对所述反射目标点进行聚类以形成聚类目标。当纵向距离(也即x方向上的距离)小于门限时,反射目标点通常在相对比较近的范围内,可以采用聚类策略对所述反射目标点进行聚类以形成聚类目标,例如采用聚类算法DBSCAN,OPTICS,DENCLUE等算法进行聚类,聚类时会有x,y方向的距离门限,该门限可以根据检测目 标是横向运动物体还是普通目标而进行调整,当目标使用过程中,所述横向运动物体跟踪波门参数包括纵向距离波门和横向距离波门,横向运动物体在纵向距离波门范围较小而横向波门范围较大,所述纵向距离波门的范围小于所述横向距离波门的范围。
进一步,在通过聚类目标模式对反射目标点进行处理后,例如使用聚类算法后,反射目标点集合形成为一个点集,也即聚类目标,该聚类目标具有重心和范围等参数指标。
在一个示例中,计算所述检测目标的位置信息,所述位置信息包括如下至少一种:目标位置的角度变化率、角度变化率趋势以及目标位置在车辆的运动方向上的距离变化。根据检测目标的预设类型不同,计算检测目标的位置信息的方式则不同。
在一个示例中,如图3所示,若所述检测目标为聚类目标,则计算聚类目标的位置信息,所述位置信息包括所述聚类目标的角度变化率、角度变化率趋势以及聚类目标在车辆的运动方向上的距离变化。所述聚类目标的位置信息还包括所述聚类目标的重心坐标和作用范围中的至少一种。
在一个示例中,如图3所示,若所述检测目标为跟踪目标,对所述跟踪目标进行分类和聚合。可选地,所述对所述跟踪目标进行分类和聚合,包括:在跟踪目标形成后,会对跟踪目标中的至少部分目标进行识别,比如根据依据距离和能量判断目标RCS统计值的行人分类和/或多个点组成的卡车。
在所述跟踪目标模式时,对所述反射目标点进行目标跟踪以形成跟踪目标。在本文中,跟踪目标模式也即是指常规的普通跟踪过程,其可以包括预跟踪航迹,成熟航迹等关联过程。
随后,根据所述检测目标的位置信息,确定所述预设类型的检测目标(例如聚类目标和跟踪目标)是否为横向运动物体。具体地,如图3所示,确定目标位置的角度变化率是否大于角度变化率门限,若否则暂时认定为普通目标,若是,则确定所述角度变化率趋势是否呈现为递增或递减,若否则暂定为普通目标,若是,则确定目标位置在车辆的运动方向上的距离变化是否小于距离变化门限,若是则确定所述检测目标(例如聚类目标和跟踪目标)为横向运动物体,若否则暂定为普通目标。
在一个示例中,所述角度变化率门限的取值与所述检测目标和所述毫米 波雷达在车辆的运动方向上的距离相关,当该距离越大时,所述角度变化率门限的取值越小。其中可以通过获取聚类目标多帧的位置信息,而计算获得聚类目标的角度变化率。
其中,对于跟踪目标的角度变化率门限,其也是与距离相关的值,但由于跟踪目标距离车身较远,其此处的距离分量系数已经比较小,因为基本角度相对于近处物体比较小。因此,跟踪目标的角度变化率门限与聚类目标的角度变化率的门限是不同的参数。
在一个示例中,所述确定所述角度变化率趋势是否呈现为递增或递减,包括:根据所述检测目标(例如聚类目标或跟踪目标)在车辆后向的运动方向,确定所述角度变化率趋势是否呈现为递增或递减。
进一步,所述根据所述检测目标在车辆后向的运动方向,确定所述角度变化率趋势是否呈现为递增或递减,包括:当所述检测目标在车辆后向的运动方向为从内向外运动时,所述角度变化率趋势呈现为递增(在统计区间内,FIFO);当所述检测目标在所述车辆后向的运动方向为从外向内运动时,所述角度变化率趋势呈现为递减(在统计区间内,FIFO)。其中,所述检测目标在车辆后向的运动方向为从内向外运动包括所述检测目标处于车辆后向左侧且向外运动和所述检测目标处于车辆后向右侧且向外运动;以及所述检测目标在车辆后向的运动方向为从外向内运动包括所述检测目标处于车辆后向左侧且向内运动和所述检测目标处于车辆后向右侧且向内运动。
针对聚类目标和跟踪目标可以采用上述基本类似的逻辑确定所述角度变化率趋势是否呈现为递增或递减,而对于跟踪目标,其在在统计区间(FIFO)内判断条件严格度要弱于聚类目标。
可选地,目标位置在车辆的运动方向上的距离变化为加入车速补偿后的距离变化。在车辆运动时,目标位置在横向上的距离为大地坐标系中的距离,该大地坐标系中的距离由车体坐标系中的距离转换而来,从而体现横向运动。
在确定所述检测目标为横向运动物体(也即横向运动目标)之后,对所述横向运动物体进行跟踪检测。在一个示例中,所述车辆后方设置有毫米波雷达,所述对所述横向运动物体进行跟踪检测,包括:基于所述毫米波雷达对所述横向运动物体进行跟踪检测。
如图3所示,对所述横向运动物体进行跟踪检测,还包括:对确定是横 向运动物体的所述检测目标,采用横向运动物体跟踪波门参数对所述横向运动物体进行跟踪检测;以及对暂定为普通目标的所述检测目标,采用普通波门参数。
普通目标波门参数主要是普通类运动目标的距离波门和速度波门,其与横向运动物体的主要差异为,横向运动物体在纵向(X方向)距离波门范围较小而横向(Y方向)波门范围较大,也即所述横向运动物体跟踪波门参数包括纵向距离波门和横向距离波门,其中,所述纵向距离波门的范围小于所述横向距离波门的范围。
可选地,所述横向运动物体跟踪波门参数和所述普通波门参数均包括距离波门、速度波门和角度波门,其中,对于所述跟踪目标的横向运动物体跟踪波门参数的距离波门和速度波门小于普通波门参数的距离波门和速度波门,而横向运动物体跟踪波门参数的角度波门大于所述普通波门参数的角度波门。
可选地,所述聚类目标和所述跟踪目标采用不同的横向运动物体跟踪波门参数。其中,对于确定为横向运动物体的跟踪目标,横向运动物体跟踪波门参数横向运动物体跟踪波门参数指的是正常跟踪系统中使用的系统波门,包含距离,速度和角度,当采用横向运动时,距离和速度波门变小,角度波门变大。在本文中,纵向是指车体坐标系中的x方向,而横向则指车体坐标系中的y方向。
图5示出了本发明一个实施例中的毫米波雷达300的示意性框图。该毫米波雷达用于执行前述实施例中的跟踪检测方法。
如图5所示,毫米波雷达300包括一个或多个处理器303,单独地或共同地工作,所述处理器用于:获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息,其中,所述当前运动状态包括如下至少一种:前进档状态,倒车档状态;根据所述位置信息,确定所述反射目标点的处理模式,其中,所述处理模式包括如下至少一种:聚类目标模式,跟踪目标模式。所述位置信息包括距离信息,所述反射目标点的处理模式根据所述距离信息以及预设距离门限来确定,其中,若所述距离信息未超过距离门限,则所述反射目标点的处理模式为所述聚类目标模式;若所述距离信息超过距离门限,则所述反射目标 点的处理模式为跟踪目标模式。
进一步,所述处理器303可以是中央处理单元(CPU)、图像处理单元(GPU)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者具有数据处理能力和/或指令执行能力的其它形式的处理单元,并且可以控制毫米波雷达300中的其它组件以执行期望的功能。所述处理器能够执行所述存储器中存储的所述指令,以执行本文描述的毫米波雷达的跟踪检测方法,在此不对该方法做重复描述。例如,处理器303能够包括一个或多个嵌入式处理器、处理器核心、微型处理器、逻辑电路、硬件有限状态机(FSM)、数字信号处理器(DSP)或它们的组合。
所述处理器303还用于:上电启动或重新启动所述毫米波雷达。处理器进一步用于:车辆刚上电启动时,所述毫米波雷达上电启动并对参数配置进行初始化操作;车辆更换前进挡或倒挡时,所述毫米波雷达先停止射频信号发射,并重新启动以对毫米波雷达的参数配置进行重置。所述参数配置包括射频参数配置、安装参数配置和算法参数配置中的至少一种。
在一个示例中,所述处理器还用于:确定车辆的当前运动状态;根据所述车辆的当前运动状态,启动相应的检测模式,所述检测模式包括如下至少一种:前进档检测模式,倒车档检测模式。也即在车辆的当前运动状态为前进挡状态时,启动前进挡检测模式,在车辆的当前运动状态为倒车档状态时,启动倒车档检测模式。
在本发明的一个实施例中,所述处理器还用于:获取车身信息,根据所述车身信息确定所述车辆的当前运动状态。可选地,所述车身信息包括车速、档位、转向、横摆角速度中的至少一种
在一个具体示例中,所述车身信息包括车速,其中,所述处理器进一步用于:根据所述车速确定所述车辆的当前运动状态是处于前进档状态还是倒车档状态,其中,在车速大于阈值车速时,确定所述车辆的当前运动状态为前进档状态,在所述车速小于阈值车速时,确定所述车辆的当前运动状态为倒车档状态
在一个具体示例中,所述处理器还用于:按照确定的处理模式,形成预设类型的检测目标,所述预设类型包括如下至少一种:聚类目标,跟踪目标;计算所述检测目标的位置信息,所述位置信息包括如下至少一种:目标位置 的角度变化率、角度变化率趋势以及目标位置在车辆的运动方向上的距离变化;根据所述检测目标的位置信息,确定所述预设类型的检测目标是否为横向运动物体;对所述横向运动物体进行跟踪检测。
在所述聚类目标模式时,对所述反射目标点进行聚类以形成聚类目标。在所述跟踪目标模式时,对所述反射目标点进行目标跟踪以形成跟踪目标。
可选地,若所述检测目标为聚类目标,则所述位置信息包括所述聚类目标的角度变化率、角度变化率趋势以及聚类目标在车辆的运动方向上的距离变化。所述聚类目标的位置信息还包括所述聚类目标的重心坐标和作用范围中的至少一种。
可选地,若所述检测目标为跟踪目标,对所述跟踪目标进行分类和聚合。所述处理器还用于:根据依据距离和能量判断目标RCS统计值的行人分类和/或多个点组成的卡车。
在一个示例中,所述处理器进一步还用于:确定目标位置的角度变化率是否大于角度变化率门限,若否则暂时认定为普通目标,若是,则确定所述角度变化率趋势是否呈现为递增或递减,若否则暂定为普通目标,若是,则确定目标位置在车辆的运动方向上的距离变化是否小于距离变化门限,若是则确定所述检测目标为横向运动物体,若否则暂定为普通目标。可选地,所述角度变化率门限的取值与所述检测目标和所述毫米波雷达在车辆的运动方向上的距离相关,当该距离越大时,所述角度变化率门限的取值越小。
在一个示例中,所述处理器还用于:根据所述检测目标在车辆后向的运动方向,确定所述角度变化率趋势是否呈现为递增或递减。所述处理器更进一步用于:当所述检测目标在车辆后向的运动方向为从内向外运动时,所述角度变化率趋势呈现为递增;当所述检测目标在所述车辆后向的运动方向为从外向内运动时,所述角度变化率趋势呈现为递减。
其中,所述检测目标在车辆后向的运动方向为从内向外运动包括所述检测目标处于车辆后向左侧且向外运动和所述检测目标处于车辆后向右侧且向外运动;以及所述检测目标在车辆后向的运动方向为从外向内运动包括所述检测目标处于车辆后向左侧且向内运动和所述检测目标处于车辆后向右侧且向内运动。
在一个示例中,所述处理器还用于:对确定是横向运动物体的所述检测 目标,采用横向运动物体跟踪波门参数对所述横向运动物体进行跟踪检测;以及对暂定为普通目标的所述检测目标,采用普通波门参数。
在一个示例中,所述处理器还用于:在所述车辆的当前运动状态为倒车档状态时,设置倒车模式射频参数配置,以启动倒车档检测模式;在所述车辆的当前运动状态为前进档状态时,设置前向模式射频参数配置,以启动所述前进档检测模式。
进一步,所述处理器还用于:设置前向目标跟踪波门参数,以进行所述前进档检测模式。所述处理器更进一步用于:基于所述前向模式射频参数配置和所述前向目标跟踪波门参数对前向运动目标进行跟踪检测。
如图5所示,所述毫米波雷达300还包括天线装置301,天线装置301用于发射毫米波信号以及接收反射信号;毫米波雷达使用毫米波(millimeter wave)通常毫米波是指30~300GHz频域(波长为1~10mm)的,毫米波是一种介于红外光波和微波频段之间的电磁波。
在一个示例中,毫米波雷达300通常包括天线装置301,用于发射毫米波信号以及接收反射信号,天线装置发射的毫米波信号经目标反射后,又被天线装置的接收模块所接收,从而获取到待测目标的反射目标点,也可以称之为点云。其中,所述天线装置301可以包括发射毫米波信号专用的阵列天线(例如发送天线)和接收反射信号专用的阵列天线(例如接收天线)。
在一个示例中,毫米波雷达300还包括信号处理电路302,与所述天线装置301电连接,用于处理所述反射信号,并转换为数据信号,其中,所述处理器303与所述信号处理电路302通讯连接,用于处理所述信号处理电路302发送的数据信号。信号处理电路302和处理器303之间可以通过有线或者无线方式的通信。
信号处理电路302包括入射波推断单元AU。入射波推断单元AU通过公知的算法推断到入射波的波源即目标的距离、目标的相对速度以及目标的方位(也即角度),并生成表示推断结果的数据信号,也即信号处理电路与所述天线装置电连接,用于处理所述反射信号,并转换为数据信号,该数据信号包括反射目标点的位置信息等。
本发明实施例中的信号处理电路并不限定于单独的电路,也包括将多个电路的组合概括地理解为一个功能元件的形态。信号处理电路302也可以通 过一个或多个片上系统(SoC)实现。例如,信号处理电路302的一部分或全部也可以为可编程逻辑设备(PLD)、即FPGA(Field-Programmable Gate Array:现场可编程门阵列)。在该情况下,信号处理电路302包含多个运算元件(例如,通用逻辑以及乘法器)以及多个存储元件(例如,查询表或存储模块)。或者,信号处理电路302也可以为通用处理器以及主存储装置的集合。信号处理电路302也可以为包含处理器内核和存储器的电路。这些能够作为信号处理电路302发挥功能。
应当注意,图5所示的毫米波雷达300的组件和结构只是示例性的,而非限制性的,根据需要,毫米波雷达300的组件也可以具有其他组件和结构。其中,对于前述跟踪检测方法中的技术特征也同样可以应用于本实施例,在此不再重复描述。
另外,本发明实施例还提供了一种计算机存储介质,其上存储有计算机程序。当所述计算机程序由处理器执行时,可以实现本发明实施例的微波雷达检测栅栏附近静止物体的方法。例如,所述计算机存储介质例如可以包括智能电话的存储卡、平板电脑的存储部件、个人计算机的硬盘、只读存储器(ROM)、可擦除可编程只读存储器(EPROM)、便携式紧致盘只读存储器(CD-ROM)、USB存储器、或者上述存储介质的任意组合。所述计算机可读存储介质可以是一个或多个计算机可读存储介质的任意组合。在所述计算机可读存储介质上可以存储一个或多个计算机程序指令,处理器可以运行存储器存储的所述程序指令,以实现本文所述的本发明实施例中(由处理器实现)的功能以及/或者其它期望的功能,例如以执行根据本发明实施例的微波雷达检测栅栏附近静止物体的方法的相应步骤。在所述计算机可读存储介质中还可以存储各种应用程序和各种数据,例如所述应用程序使用和/或产生的各种数据等。
另外,本发明实施例还提供了一种车辆,该车辆包括前述实施例中的毫米波雷达。该车辆可以包括自动驾驶车辆,或者其他类型的车辆。
具体地,车辆包括车身,毫米波雷达可以设置在车身的前方和/或后方,或者,其他适合的位置。其中,可以在车身上设置一个或者多个毫米波雷达。基于该毫米波雷达可实现前述的毫米波雷达的跟踪检测方法,从而准确有效的确定检测目标是否为横向运动物体,并对确定为横向运动物体的检测目标 进行跟踪检测,提高整个ADAS的安全性和鲁棒性,能够更有效的对横向穿梭障碍物(例如横穿行人)进行保护,有效避免驾驶过程中由于横向运动物体而导致的事故发生,提升用户体验。
尽管这里已经参考附图描述了示例实施例,应理解上述示例实施例仅仅是示例性的,并且不意图将本发明的范围限制于此。本领域普通技术人员可以在其中进行各种改变和修改,而不偏离本发明的范围和精神。所有这些改变和修改意在被包括在所附权利要求所要求的本发明的范围之内。
本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及算法步骤,能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本发明的范围。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备和方法,可以通过其它的方式实现。例如,以上所描述的设备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,例如多个单元或组件可以结合或者可以集成到另一个设备,或一些特征可以忽略,或不执行。
在此处所提供的说明书中,说明了大量具体细节。然而,能够理解,本发明的实施例可以在没有这些具体细节的情况下实践。在一些实例中,并未详细示出公知的方法、结构和技术,以便不模糊对本说明书的理解。
类似地,应当理解,为了精简本发明并帮助理解各个发明方面中的一个或多个,在对本发明的示例性实施例的描述中,本发明的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而,并不应将该本发明的方法解释成反映如下意图:即所要求保护的本发明要求比在每个权利要求中所明确记载的特征更多的特征。更确切地说,如相应的权利要求书所反映的那样,其发明点在于可以用少于某个公开的单个实施例的所有特征的特征来解决相应的技术问题。因此,遵循具体实施方式的权利要求书由此明确地并入该具体实施方式,其中每个权利要求本身都作为本发明的单独实施例。
本领域的技术人员可以理解,除了特征之间相互排斥之外,可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征 以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述,本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的替代特征来代替。
此外,本领域的技术人员能够理解,尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征,但是不同实施例的特征的组合意味着处于本发明的范围之内并且形成不同的实施例。例如,在权利要求书中,所要求保护的实施例的任意之一都可以以任意的组合方式来使用。
本发明的各个部件实施例可以以硬件实现,或者以在一个或者多个处理器上运行的软件模块实现,或者以它们的组合实现。本领域的技术人员应当理解,可以在实践中使用微处理器或者数字信号处理器(DSP)来实现根据本发明实施例的一些模块的一些或者全部功能。本发明还可以实现为用于执行这里所描述的方法的一部分或者全部的装置程序(例如,计算机程序和计算机程序产品)。这样的实现本发明的程序可以存储在计算机可读介质上,或者可以具有一个或者多个信号的形式。这样的信号可以从因特网网站上下载得到,或者在载体信号上提供,或者以任何其他形式提供。
应该注意的是上述实施例对本发明进行说明而不是对本发明进行限制,并且本领域技术人员在不脱离所附权利要求的范围的情况下可设计出替换实施例。在权利要求中,不应将位于括号之间的任何参考符号构造成对权利要求的限制。本发明可以借助于包括有若干不同元件的硬件以及借助于适当编程的计算机来实现。在列举了若干装置的单元权利要求中,这些装置中的若干个可以是通过同一个硬件项来具体体现。单词第一、第二、以及第三等的使用不表示任何顺序。可将这些单词解释为名称。

Claims (73)

  1. 一种毫米波雷达的跟踪检测方法,其特征在于,所述跟踪检测方法包括:
    获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息,其中,所述当前运动状态包括如下至少一种:前进档状态,倒车档状态;
    根据所述位置信息,确定所述反射目标点的处理模式,其中,所述处理模式包括如下至少一种:聚类目标模式,跟踪目标模式。
  2. 如权利要求1所述的跟踪检测方法,其特征在于,所述跟踪检测方法还包括:
    确定车辆的当前运动状态;
    根据所述车辆的当前运动状态,启动相应的检测模式,所述检测模式包括如下至少一种:前进档检测模式,倒车档检测模式。
  3. 如权利要求1所述的跟踪检测方法,其特征在于,所述跟踪检测方法还包括:
    按照确定的处理模式,形成预设类型的检测目标,所述预设类型包括如下至少一种:聚类目标,跟踪目标;
    计算所述检测目标的位置信息,所述位置信息包括如下至少一种:目标位置的角度变化率、角度变化率趋势以及目标位置在车辆的运动方向上的距离变化;
    根据所述检测目标的位置信息,确定所述预设类型的检测目标是否为横向运动物体;
    对所述横向运动物体进行跟踪检测。
  4. 如权利要求1所述的跟踪检测方法,其特征在于,所述位置信息包括距离信息,所述反射目标点的处理模式根据所述距离信息以及预设距离门限来确定,
    其中,若所述距离信息未超过距离门限,则所述反射目标点的处理模式为所述聚类目标模式;若所述距离信息超过距离门限,则所述反射目标点的处理模式为跟踪目标模式。
  5. 如权利要求1所述的跟踪检测方法,其特征在于,在所述聚类目标模 式时,对所述反射目标点进行聚类以形成聚类目标。
  6. 如权利要求1所述的跟踪检测方法,其特征在于,在所述跟踪目标模式时,对所述反射目标点进行目标跟踪以形成跟踪目标。
  7. 如权利要求2所述的跟踪检测方法,其特征在于,在所述确定车辆的当前运动状态之前,所述跟踪检测方法还包括:
    所述毫米波雷达上电启动或重新启动。
  8. 如权利要求7所述的跟踪检测方法,其特征在于,所述毫米波雷达上电启动或重新启动,包括:
    车辆刚上电启动时,所述毫米波雷达上电启动并对参数配置进行初始化操作;
    车辆更换前进挡或倒挡时,所述毫米波雷达先停止射频信号发射,并重新启动以对毫米波雷达的参数配置进行重置。
  9. 如权利要求8所述的跟踪检测方法,其特征在于,所述参数配置包括射频参数配置、安装参数配置和算法参数配置中的至少一种。
  10. 如权利要求3所述的跟踪检测方法,其特征在于,若所述检测目标为聚类目标,则所述位置信息包括所述聚类目标的角度变化率、角度变化率趋势以及聚类目标在车辆的运动方向上的距离变化。
  11. 如权利要求10所述的跟踪检测方法,其特征在于,所述聚类目标的位置信息还包括所述聚类目标的重心坐标和作用范围中的至少一种。
  12. 如权利要求3所述的跟踪检测方法,其特征在于,若所述检测目标为跟踪目标,对所述跟踪目标进行分类和聚合。
  13. 如权利要求12所述的跟踪检测方法,其特征在于,所述对所述跟踪目标进行分类和聚合,包括:
    根据依据距离和能量判断目标RCS统计值的行人分类和/或多个点组成的卡车。
  14. 如权利要求3所述的跟踪检测方法,其特征在于,根据所述检测目标的位置信息,确定所述预设类型的检测目标是否为横向运动物体,包括:
    确定目标位置的角度变化率是否大于角度变化率门限,若否则暂时认定为普通目标,若是,则确定所述角度变化率趋势是否呈现为递增或递减,若否则暂定为普通目标,若是,则确定目标位置在车辆的运动方向上的距离变 化是否小于距离变化门限,若是则确定所述检测目标为横向运动物体,若否则暂定为普通目标。
  15. 如权利要求14所述的跟踪检测方法,其特征在于,所述角度变化率门限的取值与所述检测目标和所述毫米波雷达在车辆的运动方向上的距离相关,当该距离越大时,所述角度变化率门限的取值越小。
  16. 如权利要求14所述的跟踪检测方法,其特征在于,所述确定所述角度变化率趋势是否呈现为递增或递减,包括:
    根据所述检测目标在车辆后向的运动方向,确定所述角度变化率趋势是否呈现为递增或递减。
  17. 如权利要求16所述的跟踪检测方法,其特征在于,所述根据所述检测目标在车辆后向的运动方向,确定所述角度变化率趋势是否呈现为递增或递减,包括:
    当所述检测目标在车辆后向的运动方向为从内向外运动时,所述角度变化率趋势呈现为递增;
    当所述检测目标在所述车辆后向的运动方向为从外向内运动时,所述角度变化率趋势呈现为递减。
  18. 如权利要求17所述的跟踪检测方法,其特征在于,所述检测目标在车辆后向的运动方向为从内向外运动包括所述检测目标处于车辆后向左侧且向外运动和所述检测目标处于车辆后向右侧且向外运动;以及
    所述检测目标在车辆后向的运动方向为从外向内运动包括所述检测目标处于车辆后向左侧且向内运动和所述检测目标处于车辆后向右侧且向内运动。
  19. 如权利要求3所述的跟踪检测方法,其特征在于,目标位置在车辆的运动方向上的距离变化为加入车速补偿后的距离变化。
  20. 如权利要求3所述的跟踪检测方法,其特征在于,在车辆运动时,目标位置在横向上的距离为大地坐标系中的距离,该大地坐标系中的距离由车体坐标系中的距离转换而来。
  21. 如权利要求3所述的跟踪检测方法,其特征在于,对所述横向运动物体进行跟踪检测,还包括:
    对确定是横向运动物体的所述检测目标,采用横向运动物体跟踪波门参数对所述横向运动物体进行跟踪检测;以及
    对暂定为普通目标的所述检测目标,采用普通波门参数。
  22. 如权利要求21所述的跟踪检测方法,其特征在于,所述横向运动物体跟踪波门参数包括纵向距离波门和横向距离波门,其中,所述纵向距离波门的范围小于所述横向距离波门的范围。
  23. 如权利要求21所述的跟踪检测方法,其特征在于,所述聚类目标和所述跟踪目标采用不同的横向运动物体跟踪波门参数。
  24. 如权利要求21所述的跟踪检测方法,其特征在于,所述横向运动物体跟踪波门参数和所述普通波门参数均包括距离波门、速度波门和角度波门,其中,对于所述跟踪目标的横向运动物体跟踪波门参数的距离波门和速度波门小于普通波门参数的距离波门和速度波门,而横向运动物体跟踪波门参数的角度波门大于所述普通波门参数的角度波门。
  25. 如权利要求2所述的跟踪检测方法,其特征在于,所述确定车辆的当前运动状态,包括:
    获取车身信息,根据所述车身信息确定所述车辆的当前运动状态。
  26. 如权利要求25所述的跟踪检测方法,其特征在于,所述车身信息包括车速,其中,所述获取车身信息,根据所述车身信息确定所述车辆的当前运动状态,包括:
    根据所述车速确定所述车辆的当前运动状态是处于前进档状态还是倒车档状态,其中,在车速大于阈值车速时,确定所述车辆的当前运动状态为前进档状态,在所述车速小于阈值车速时,确定所述车辆的当前运动状态为倒车档状态。
  27. 如权利要求25所述的跟踪检测方法,其特征在于,所述车身信息包括车速、档位、转向、横摆角速度中的至少一种。
  28. 如权利要求2所述的跟踪检测方法,其特征在于,在所述车辆的当前运动状态为倒车档状态时,设置倒车模式射频参数配置,以启动倒车档检测模式;
    在所述车辆的当前运动状态为前进档状态时,设置前向模式射频参数配置,以启动所述前进档检测模式。
  29. 如权利要求1所述的跟踪检测方法,其特征在于,所述位置信息包括一维或二维快速傅里叶加上测角后获得的未经跟踪处理但已经经过车身坐 标发生变化的原始目标信息。
  30. 如权利要求1所述的跟踪检测方法,其特征在于,所述位置信息还包括所述反射目标点的运动速度和角度。
  31. 如权利要求28所述的跟踪检测方法,其特征在于,所述倒车模式射频参数配置相比所述前向模式射频参数配置的检测距离范围更小。
  32. 如权利要求28所述的跟踪检测方法,其特征在于,所述倒车模式射频参数配置相比所述前向模式射频参数配置的软件过滤的视场角更大。
  33. 如权利要求28所述的跟踪检测方法,其特征在于,所述倒车模式射频参数配置相比所述前向模式射频参数配置的距离分辨率更高。
  34. 如权利要求28所述的跟踪检测方法,其特征在于,所述前进档检测模式还包括:
    设置前向目标跟踪波门参数。
  35. 如权利要求34所述的跟踪检测方法,其特征在于,所述跟踪检测方法还包括:
    基于所述前向模式射频参数配置和所述前向目标跟踪波门参数对前向运动目标进行跟踪检测。
  36. 如权利要求3所述的跟踪检测方法,其特征在于,所述车辆后方设置有毫米波雷达,所述对所述横向运动物体进行跟踪检测,包括:
    基于所述毫米波雷达对所述横向运动物体进行跟踪检测。
  37. 一种毫米波雷达,其特征在于,包括:
    一个或多个处理器,共同地或单独地工作,所述处理器用于:
    获取反射目标点的目标检测信息,所述目标检测信息包括所述反射目标点在所述车辆的当前运动状态的运动方向上的位置信息,其中,所述当前运动状态包括如下至少一种:前进档状态,倒车档状态;
    根据所述位置信息,确定所述反射目标点的处理模式,其中,所述处理模式包括如下至少一种:聚类目标模式,跟踪目标模式。
  38. 如权利要求37所述的毫米波雷达,其特征在于,还包括:
    天线装置,用于发射毫米波信号以及接收反射信号;以及
    信号处理电路,与所述天线装置电连接,用于处理所述反射信号,并转换为数据信号,
    其中,所述处理器与所述信号处理电路通讯连接,用于处理所述信号处理电路发送的数据信号。
  39. 如权利要求37所述的毫米波雷达,其特征在于,所述处理器还用于:
    确定车辆的当前运动状态;
    根据所述车辆的当前运动状态,启动相应的检测模式,所述检测模式包括如下至少一种:前进档检测模式,倒车档检测模式。
  40. 如权利要求37所述的毫米波雷达,其特征在于,所述处理器还用于:
    按照确定的处理模式,形成预设类型的检测目标,所述预设类型包括如下至少一种:聚类目标,跟踪目标;
    计算所述检测目标的位置信息,所述位置信息包括如下至少一种:目标位置的角度变化率、角度变化率趋势以及目标位置在车辆的运动方向上的距离变化;
    根据所述检测目标的位置信息,确定所述预设类型的检测目标是否为横向运动物体;
    对所述横向运动物体进行跟踪检测。
  41. 如权利要求37所述的毫米波雷达,其特征在于,所述位置信息包括距离信息,所述反射目标点的处理模式根据所述距离信息以及预设距离门限来确定,
    其中,若所述距离信息未超过距离门限,则所述反射目标点的处理模式为所述聚类目标模式;若所述距离信息超过距离门限,则所述反射目标点的处理模式为跟踪目标模式。
  42. 如权利要求37所述的毫米波雷达,其特征在于,在所述聚类目标模式时,对所述反射目标点进行聚类以形成聚类目标。
  43. 如权利要求37所述的毫米波雷达,其特征在于,在所述跟踪目标模式时,对所述反射目标点进行目标跟踪以形成跟踪目标。
  44. 如权利要求39所述的毫米波雷达,其特征在于,所述处理器还用于:
    上电启动或重新启动所述毫米波雷达。
  45. 如权利要求44所述的毫米波雷达,其特征在于,所述处理器还用于:
    车辆刚上电启动时,所述毫米波雷达上电启动并对参数配置进行初始化操作;
    车辆更换前进挡或倒挡时,所述毫米波雷达先停止射频信号发射,并重新启动以对毫米波雷达的参数配置进行重置。
  46. 如权利要求45所述的毫米波雷达,其特征在于,所述参数配置包括射频参数配置、安装参数配置和算法参数配置中的至少一种。
  47. 如权利要求40所述的毫米波雷达,其特征在于,若所述检测目标为聚类目标,则所述位置信息包括所述聚类目标的角度变化率、角度变化率趋势以及聚类目标在车辆的运动方向上的距离变化。
  48. 如权利要求47所述的毫米波雷达,其特征在于,所述聚类目标的位置信息还包括所述聚类目标的重心坐标和作用范围中的至少一种。
  49. 如权利要求40所述的毫米波雷达,其特征在于,若所述检测目标为跟踪目标,对所述跟踪目标进行分类和聚合。
  50. 如权利要求49所述的毫米波雷达,其特征在于,所述处理器还用于:
    根据依据距离和能量判断目标RCS统计值的行人分类和/或多个点组成的卡车。
  51. 如权利要求40所述的毫米波雷达,其特征在于,所述处理器还用于:
    确定目标位置的角度变化率是否大于角度变化率门限,若否则暂时认定为普通目标,若是,则确定所述角度变化率趋势是否呈现为递增或递减,若否则暂定为普通目标,若是,则确定目标位置在车辆的运动方向上的距离变化是否小于距离变化门限,若是则确定所述检测目标为横向运动物体,若否则暂定为普通目标。
  52. 如权利要求51所述的毫米波雷达,其特征在于,所述角度变化率门限的取值与所述检测目标和所述毫米波雷达在车辆的运动方向上的距离相关,当该距离越大时,所述角度变化率门限的取值越小。
  53. 如权利要求51所述的毫米波雷达,其特征在于,所述处理器还用于:
    根据所述检测目标在车辆后向的运动方向,确定所述角度变化率趋势是否呈现为递增或递减。
  54. 如权利要求53所述的毫米波雷达,其特征在于,所述处理器还用于:
    当所述检测目标在车辆后向的运动方向为从内向外运动时,所述角度变化率趋势呈现为递增;
    当所述检测目标在所述车辆后向的运动方向为从外向内运动时,所述角 度变化率趋势呈现为递减。
  55. 如权利要求54所述的毫米波雷达,其特征在于,所述检测目标在车辆后向的运动方向为从内向外运动包括所述检测目标处于车辆后向左侧且向外运动和所述检测目标处于车辆后向右侧且向外运动;以及
    所述检测目标在车辆后向的运动方向为从外向内运动包括所述检测目标处于车辆后向左侧且向内运动和所述检测目标处于车辆后向右侧且向内运动。
  56. 如权利要求40所述的毫米波雷达,其特征在于,目标位置在车辆的运动方向上的距离变化为加入车速补偿后的距离变化。
  57. 如权利要求40所述的毫米波雷达,其特征在于,在车辆运动时,目标位置在横向上的距离为大地坐标系中的距离,该大地坐标系中的距离由车体坐标系中的距离转换而来。
  58. 如权利要求40所述的毫米波雷达,其特征在于,所述处理器还用于:
    对确定是横向运动物体的所述检测目标,采用横向运动物体跟踪波门参数对所述横向运动物体进行跟踪检测;以及
    对暂定为普通目标的所述检测目标,采用普通波门参数。
  59. 如权利要求58所述的毫米波雷达,其特征在于,所述横向运动物体跟踪波门参数包括纵向距离波门和横向距离波门,其中,所述纵向距离波门的范围小于所述横向距离波门的范围。
  60. 如权利要求58所述的毫米波雷达,其特征在于,所述聚类目标和所述跟踪目标采用不同的横向运动物体跟踪波门参数。
  61. 如权利要求58所述的毫米波雷达,其特征在于,所述横向运动物体跟踪波门参数和所述普通波门参数均包括距离波门、速度波门和角度波门,其中,对于所述跟踪目标的横向运动物体跟踪波门参数的距离波门和速度波门小于普通波门参数的距离波门和速度波门,而横向运动物体跟踪波门参数的角度波门大于所述普通波门参数的角度波门。
  62. 如权利要求39所述的毫米波雷达,其特征在于,所述处理器还用于:
    获取车身信息,根据所述车身信息确定所述车辆的当前运动状态。
  63. 如权利要求62所述的毫米波雷达,其特征在于,所述车身信息包括车速,所述处理器还用于:
    根据所述车速确定所述车辆的当前运动状态是处于前进档状态还是倒车 档状态,其中,在车速大于阈值车速时,确定所述车辆的当前运动状态为前进档状态,在所述车速小于阈值车速时,确定所述车辆的当前运动状态为倒车档状态。
  64. 如权利要求62所述的毫米波雷达,其特征在于,所述车身信息包括车速、档位、转向、横摆角速度中的至少一种。
  65. 如权利要求39所述的毫米波雷达,其特征在于,所述处理器还用于:在所述车辆的当前运动状态为倒车档状态时,设置倒车模式射频参数配置,以启动倒车档检测模式;
    在所述车辆的当前运动状态为前进档状态时,设置前向模式射频参数配置,以启动所述前进档检测模式。
  66. 如权利要求37所述的毫米波雷达,其特征在于,所述位置信息包括一维或二维快速傅里叶加上测角后获得的未经跟踪处理但已经经过车身坐标发生变化的原始目标信息。
  67. 如权利要求37所述的毫米波雷达,其特征在于,所述位置信息还包括所述反射目标点的运动速度和角度。
  68. 如权利要求65所述的毫米波雷达,其特征在于,所述倒车模式射频参数配置相比所述前向模式射频参数配置的检测距离范围更小。
  69. 如权利要求65所述的毫米波雷达,其特征在于,所述倒车模式射频参数配置相比所述前向模式射频参数配置的软件过滤的视场角更大。
  70. 如权利要求65所述的毫米波雷达,其特征在于,所述倒车模式射频参数配置相比所述前向模式射频参数配置的距离分辨率更高。
  71. 如权利要求65所述的毫米波雷达,其特征在于,所述处理器还用于:
    设置前向目标跟踪波门参数,以进行所述前进档检测模式。
  72. 如权利要求71所述的毫米波雷达,其特征在于,所述处理器还用于:
    基于所述前向模式射频参数配置和所述前向目标跟踪波门参数对前向运动目标进行跟踪检测。
  73. 一种车辆,其特征在于,所述车辆包括车身以及权利要求37至72任一项所述的毫米波雷达,所述毫米波雷达安装在所述车身的前方或/及后方。
PCT/CN2019/080607 2019-03-29 2019-03-29 毫米波雷达的跟踪检测方法、毫米波雷达和车辆 Ceased WO2020199010A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/080607 WO2020199010A1 (zh) 2019-03-29 2019-03-29 毫米波雷达的跟踪检测方法、毫米波雷达和车辆
CN201980010373.8A CN111699406B (zh) 2019-03-29 2019-03-29 毫米波雷达的跟踪检测方法、毫米波雷达和车辆

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/080607 WO2020199010A1 (zh) 2019-03-29 2019-03-29 毫米波雷达的跟踪检测方法、毫米波雷达和车辆

Publications (1)

Publication Number Publication Date
WO2020199010A1 true WO2020199010A1 (zh) 2020-10-08

Family

ID=72476414

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/080607 Ceased WO2020199010A1 (zh) 2019-03-29 2019-03-29 毫米波雷达的跟踪检测方法、毫米波雷达和车辆

Country Status (2)

Country Link
CN (1) CN111699406B (zh)
WO (1) WO2020199010A1 (zh)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114631035A (zh) * 2020-12-29 2022-06-14 深圳市大疆创新科技有限公司 获取点云聚类波门的方法、雷达、可移动平台和存储介质
CN114670851A (zh) * 2022-04-20 2022-06-28 北京理工大学重庆创新中心 基于寻优跟踪算法的辅助驾驶系统、方法、终端及介质
CN115346093A (zh) * 2022-07-18 2022-11-15 岚图汽车科技有限公司 基于多传感器融合的断检目标车辆创建方法及装置
CN116184385A (zh) * 2021-11-26 2023-05-30 现代摩比斯株式会社 基于车辆运动特性的道路设施跟踪方法与装置
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
CN116953691A (zh) * 2023-07-26 2023-10-27 成都市卡蛙科技有限公司 基于毫米波雷达的目标跟踪方法、装置、车辆及存储介质
CN118311562A (zh) * 2024-06-07 2024-07-09 河北工业职业技术学院 一种乘用车辆车门开启监测系统及方法

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI793518B (zh) * 2021-02-05 2023-02-21 為昇科科技股份有限公司 多模態偵測雷達裝置
CN113791409A (zh) * 2021-08-04 2021-12-14 南京市德赛西威汽车电子有限公司 一种基于毫米波雷达的静止目标提取方法及系统
CN113734046B (zh) * 2021-08-17 2023-09-19 江苏星图智能科技有限公司 基于雷达的车内位置分区人员检测方法、装置以及设备
WO2023178533A1 (zh) * 2022-03-22 2023-09-28 北京小米移动软件有限公司 通感业务的处理方法、装置、通信设备及存储介质
CN114779230B (zh) * 2022-03-22 2024-03-08 福瑞泰克智能系统有限公司 一种对象跟踪方法、装置、电子设备及车辆
CN115586528A (zh) * 2022-09-08 2023-01-10 森思泰克河北科技有限公司 避障报警方法、装置、计算机设备和存储介质
CN115236627B (zh) * 2022-09-21 2022-12-16 深圳安智杰科技有限公司 一种基于多帧多普勒速度扩维的毫米波雷达数据聚类方法
CN115808682B (zh) * 2023-01-17 2023-05-09 湖北工业大学 基于车载毫米波雷达的稳定多目标跟踪方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107458361A (zh) * 2017-08-10 2017-12-12 南京超靖界智能科技有限公司 车辆安全辅助系统及其控制方法
JP2018080938A (ja) * 2016-11-14 2018-05-24 株式会社デンソーテン レーダ装置および物標検知方法
CN108638967A (zh) * 2018-06-15 2018-10-12 轩辕智驾科技(深圳)有限公司 一种基于毫米波雷达的汽车预警系统及预警方法
CN108845321A (zh) * 2018-04-19 2018-11-20 北京三快在线科技有限公司 目标对象的识别方法、装置及无人驾驶智能设备
CN109061600A (zh) * 2018-09-28 2018-12-21 上海市刑事科学技术研究院 一种基于毫米波雷达数据的目标识别方法
CN109188382A (zh) * 2018-07-27 2019-01-11 惠州华阳通用电子有限公司 一种基于毫米波雷达的目标识别方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090167514A1 (en) * 2007-12-31 2009-07-02 Brian Lickfelt Combined Radar Backup Assist and Blindspot Detector and Method
US20130181860A1 (en) * 2012-01-16 2013-07-18 Ford Global Technologies, Llc Radar based multifunctional safety system
EP3370085B1 (en) * 2017-03-01 2021-10-13 Aptiv Technologies Limited Method of tracking a plurality of objects in the vicinity of a host vehicle
CN109358322B (zh) * 2018-10-25 2020-10-16 森思泰克河北科技有限公司 前向目标检测雷达和方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2018080938A (ja) * 2016-11-14 2018-05-24 株式会社デンソーテン レーダ装置および物標検知方法
CN107458361A (zh) * 2017-08-10 2017-12-12 南京超靖界智能科技有限公司 车辆安全辅助系统及其控制方法
CN108845321A (zh) * 2018-04-19 2018-11-20 北京三快在线科技有限公司 目标对象的识别方法、装置及无人驾驶智能设备
CN108638967A (zh) * 2018-06-15 2018-10-12 轩辕智驾科技(深圳)有限公司 一种基于毫米波雷达的汽车预警系统及预警方法
CN109188382A (zh) * 2018-07-27 2019-01-11 惠州华阳通用电子有限公司 一种基于毫米波雷达的目标识别方法
CN109061600A (zh) * 2018-09-28 2018-12-21 上海市刑事科学技术研究院 一种基于毫米波雷达数据的目标识别方法

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114631035A (zh) * 2020-12-29 2022-06-14 深圳市大疆创新科技有限公司 获取点云聚类波门的方法、雷达、可移动平台和存储介质
CN116184385A (zh) * 2021-11-26 2023-05-30 现代摩比斯株式会社 基于车辆运动特性的道路设施跟踪方法与装置
US12491889B2 (en) 2021-11-26 2025-12-09 Hyundai Mobis Co., Ltd. Method and apparatus for tracking road facility based on vehicle motion characteristics
CN114670851A (zh) * 2022-04-20 2022-06-28 北京理工大学重庆创新中心 基于寻优跟踪算法的辅助驾驶系统、方法、终端及介质
CN115346093A (zh) * 2022-07-18 2022-11-15 岚图汽车科技有限公司 基于多传感器融合的断检目标车辆创建方法及装置
CN115346093B (zh) * 2022-07-18 2026-04-17 岚图汽车科技股份有限公司 基于多传感器融合的断检目标车辆创建方法及装置
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
CN116953691A (zh) * 2023-07-26 2023-10-27 成都市卡蛙科技有限公司 基于毫米波雷达的目标跟踪方法、装置、车辆及存储介质
CN118311562A (zh) * 2024-06-07 2024-07-09 河北工业职业技术学院 一种乘用车辆车门开启监测系统及方法

Also Published As

Publication number Publication date
CN111699406A (zh) 2020-09-22
CN111699406B (zh) 2024-04-30

Similar Documents

Publication Publication Date Title
CN111699406B (zh) 毫米波雷达的跟踪检测方法、毫米波雷达和车辆
JP5991332B2 (ja) 衝突回避制御装置
US11027653B2 (en) Apparatus, system and method for preventing collision
US11733375B2 (en) Apparatus and method for controlling radar
CN107408348B (zh) 车辆控制装置以及车辆控制方法
US11208085B2 (en) Automotive braking control system, apparatus, and method considering weather condition
US10371810B2 (en) Radar device
US10585188B2 (en) Broadside detection system and techniques for use in a vehicular radar
CN111699407B (zh) 微波雷达检测栅栏附近静止物体的方法和毫米波雷达
CN111699408A (zh) 隧道场景检测方法及毫米波雷达
CN104773171A (zh) 车辆碰撞预警装置与方法
CN108859952B (zh) 车辆变道预警方法、装置和雷达
JP7401273B2 (ja) 移動体の制御装置及び方法
EP4667971A1 (en) Meteorological information processing method and processing apparatus
WO2021164311A1 (zh) 一种探测方法和装置
JP2016070772A (ja) レーダ装置、車両制御システム、および、信号処理方法
WO2020156084A1 (zh) 无线电信号发送方法和装置
CN111537993B (zh) 拖车检测系统以及方法
WO2021098320A1 (zh) 一种道路约束确定方法及装置
JP2008082974A (ja) 物体検出装置、物体検出方法、およびコンピュータが実行するためのプログラム
CN111016885B (zh) 自动泊车车位探测方法、电子雷达系统以及存储介质
CN114690183A (zh) 基于多个模式检测对象的雷达装置及方法
WO2023171072A1 (ja) 障害物検知装置、障害物検知方法及びプログラム
JP7847467B2 (ja) レーダ装置、報知判定方法及びプログラム
JP4644590B2 (ja) 周辺車両位置検出装置および周辺車両位置検出方法

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: 19923446

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: 19923446

Country of ref document: EP

Kind code of ref document: A1