WO2020198973A1 - 微波雷达检测栅栏附近静止物体的方法和毫米波雷达 - Google Patents

微波雷达检测栅栏附近静止物体的方法和毫米波雷达 Download PDF

Info

Publication number
WO2020198973A1
WO2020198973A1 PCT/CN2019/080516 CN2019080516W WO2020198973A1 WO 2020198973 A1 WO2020198973 A1 WO 2020198973A1 CN 2019080516 W CN2019080516 W CN 2019080516W WO 2020198973 A1 WO2020198973 A1 WO 2020198973A1
Authority
WO
WIPO (PCT)
Prior art keywords
fence
reflection point
evaluation value
current frame
static
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/CN2019/080516
Other languages
English (en)
French (fr)
Inventor
李怡强
陆新飞
陈雷
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/CN2019/080516 priority Critical patent/WO2020198973A1/zh
Priority to CN201980010405.4A priority patent/CN111699407B/zh
Publication of WO2020198973A1 publication Critical patent/WO2020198973A1/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
    • 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
    • G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
    • G01S13/04—Systems determining presence of a target
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • 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

Definitions

  • the present invention generally relates to the field of automatic driving technology, and more particularly relates to a method for microwave radar to detect stationary objects near fences and millimeter wave radar.
  • ADAS Advanced Driver Assistant System
  • AD Autonomous Driving
  • Millimeter-wave radar is widely used due to its advantages such as all-weather, all-weather, long range, and high speed measurement accuracy.
  • distinguishing between fences and stationary vehicles near fences has always been a problem and difficulty in the field of vehicle-mounted millimeter wave radar. Since fences and stationary vehicles are both strongly reflective objects and have no speed, it is very easy to cluster stationary vehicles and adjacent fences into one track when vehicle-mounted radar does object tracking and clustering, making stationary vehicles mistaken for It is part of the fence. In this case, the automatic emergency braking system (AEB) will not be activated normally, resulting in a poor user experience of the ADAS system.
  • AEB automatic emergency braking system
  • the present invention proposes a new microwave radar method for detecting stationary objects near the fence.
  • one aspect of the present invention provides a method for microwave radar to detect stationary objects near a fence, the method including:
  • the stationary reflection point in the fence it is determined whether the stationary reflection point in the fence area is a stationary object.
  • the obtaining the fence dispersion of the current frame includes:
  • the fence dispersion degree of the current frame is calculated.
  • the position information of the stationary reflection point is the position information of the stationary reflection point in a Cartesian coordinate system, wherein the Cartesian coordinate system takes the center point of the front of the vehicle as the center of the circle, and takes the forward direction of the vehicle as The y-axis is the x-axis which is perpendicular to the y-axis and parallel to the horizontal plane.
  • the fence dispersion of the current frame is determined according to the slope and intercept of the fence fitting straight line, and the longitudinal distance and the lateral distance of the stationary reflection points participating in the fence fitting in the rectangular coordinate system .
  • the probability that the static reflection point falls within the fence area is determined according to the dispersion of the fence and the longitudinal distance and the lateral distance of the static reflection point.
  • the fence area is updated according to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area
  • the target evaluation value of the static reflection point within includes:
  • the target evaluation value is lower than the predetermined threshold and the number of times of detection of the stationary reflection point is greater than the threshold number of times, it is determined that the stationary reflection point is a stationary object.
  • the fence area is updated according to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area
  • the target evaluation value of the static reflection point within specifically includes:
  • the probability that the static reflection point of the current frame falls in the fence area is greater than the first threshold, the sum of the target evaluation value of the static reflection point in the fence of the previous frame and the first additional value is calculated and the sum is added to The maximum target evaluation value is compared, and the maximum value of the two is the target evaluation value in the fence of the static reflection point of the current frame;
  • the difference between the target evaluation value of the static reflection point in the fence of the previous frame and the second additional value is calculated and the difference The value is compared with the minimum target evaluation value, and the minimum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame.
  • the acquiring position information of the static reflection point of the current frame includes:
  • millimeter wave radar includes:
  • One or more processors working individually or together, and the processors are used to:
  • the stationary reflection point in the fence it is determined whether the stationary reflection point in the fence area is a stationary object.
  • 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.
  • the processor is configured to determine a fence fitting straight line according to the position information of the stationary reflection point of the current frame, and calculate the current frame according to the fence fitting straight line and the stationary reflection points participating in the fitting The fence dispersion.
  • the position information of the stationary reflection point is the position information of the stationary reflection point in a Cartesian coordinate system, wherein the Cartesian coordinate system takes the center point of the front of the vehicle as the center of the circle, and takes the forward direction of the vehicle as The y-axis is the x-axis which is perpendicular to the y-axis and parallel to the horizontal plane.
  • the fence dispersion of the current frame is determined according to the slope and intercept of the fence fitting straight line, and the longitudinal distance and the lateral distance of the stationary reflection points participating in the fence fitting in the rectangular coordinate system .
  • the probability that the static reflection point falls within the fence area is determined according to the dispersion of the fence and the longitudinal distance and the lateral distance of the static reflection point.
  • the processor is further configured to obtain tracking results of consecutive multiple frames of each static reflection point, and update the target evaluation value of the static reflection point in the fence according to the accumulated result of the multiple frames.
  • the processor determines that the stationary reflection point is a stationary object.
  • the processor calculates the target evaluation value of the static reflection point in the fence of the previous frame and the first additional And compare the sum with the maximum target evaluation value, and take the maximum of the two as the target evaluation value in the fence of the static reflection point of the current frame;
  • the processor calculates the difference between the target evaluation value of the static reflection point in the fence of the previous frame and the second additional value The difference is compared with the minimum target evaluation value, and the minimum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame.
  • the processor detects a static reflection point in front of or behind the vehicle based on a millimeter wave radar to obtain the position information of the static reflection point in the current frame.
  • Another aspect of the present invention provides a computer storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the foregoing method is implemented.
  • Another aspect of the present invention provides a vehicle including a vehicle body and the aforementioned millimeter wave radar, the millimeter wave radar being installed on the front side or/and the rear side of the vehicle body.
  • the method of the embodiment of the present invention is based on the target evaluation value of the static reflection point in the fence of the previous frame, and the static reflection point of the current frame falls on the fence Probability in the area, update the target evaluation value of the static reflection point in the fence area, and determine the static reflection in the fence area according to the updated target evaluation value of the static reflection point in the fence Whether the point is a stationary object, so as to accurately detect whether the stationary reflection point in the fence area is a stationary object, and reduce the probability of missed detection of the automatic emergency braking (AEB) system, thereby improving the robustness and improvement of the entire ADAS and AD system user experience.
  • AEB automatic emergency braking
  • Figure 1 shows a schematic flow chart of a method for microwave radar to detect stationary objects near a fence in an embodiment of the present invention
  • Figure 2 shows a schematic diagram of the principle of a method for detecting stationary objects near a fence by a microwave radar in an embodiment of the present invention
  • Fig. 3 shows a schematic block diagram of a millimeter wave radar in an embodiment of the present invention.
  • the current vehicle radar usually adopts the following methods:
  • the accuracy and resolution of angle measurement can be improved. This can enhance the accuracy of the angle measurement of the vehicle near the fence by the radar, thereby distinguishing between the fence and the stationary vehicle near the fence.
  • this method will greatly increase the complexity of antenna design, antenna size, and the cost of antenna and high-frequency plates.
  • the computational overhead of DOA (direction of arrival) algorithm will increase significantly due to the increase in the number of channels, which will make the hardware of the processor The cost has risen sharply.
  • the present invention provides a microwave radar method for detecting stationary objects near a fence. As shown in FIG. 1, the method includes:
  • Step S101 Obtain the fence dispersion of the current frame
  • Step S102 Determine the probability that the static reflection point falls within the fence area according to the fence dispersion of the current frame
  • Step S103 according to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area, update all the points in the fence area.
  • Step S104 Determine whether the static reflection point in the fence area is a stationary object according to the updated target evaluation value of the static reflection point in the fence.
  • the method of the embodiment of the present invention is based on the target evaluation value of the static reflection point in the fence of the previous frame, and the static reflection point of the current frame falls on the fence Probability in the area, update the target evaluation value of the static reflection point in the fence area, and determine the static reflection in the fence area according to the updated target evaluation value of the static reflection point in the fence Whether the point is a stationary object, so as to accurately detect stationary objects that are not part of the fence but located near the fence, reduce the probability of missed detection by the automatic emergency braking (AEB) system, thereby improving the robustness of the entire ADAS and AD system and improving users Experience.
  • AEB automatic emergency braking
  • the method for detecting stationary objects near a fence by a microwave radar includes the following steps:
  • step S101 perform step S101 to obtain the fence dispersion of the current frame.
  • the fence dispersion of the current frame can be obtained by any suitable method.
  • the obtaining the fence dispersion of the current frame specifically includes: obtaining the position information of the stationary reflection point of the current frame; determining the fence fitting straight line according to the position information of the stationary reflection point of the current frame; The fence is fitted with a straight line and the static reflection points participating in the fitting, and the fence dispersion of the current frame is calculated.
  • the microwave radar includes millimeter wave radar.
  • 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 influence on the detection of millimeter-wave radar, so it is very suitable for the fence detection of the present invention.
  • weather and environmental factors such as light and weather basically have no influence on the detection of millimeter-wave radar, so it is very suitable for the fence detection of the present invention.
  • the present invention is not limited to using millimeter radar waves for target detection, and other methods and means can also 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 reflection point of the measurement target can also be called a point cloud.
  • the reflection point of the target to be measured includes the static reflection point of a stationary object.
  • the reflection point includes position information of the static reflection point.
  • the millimeter wave radar is installed on a mobile platform, such as a vehicle.
  • the vehicle may also include an autonomous vehicle.
  • the position information of the stationary reflection point is the position information of the stationary reflection point in a Cartesian coordinate system, wherein the Cartesian coordinate system takes the center point of the front of the vehicle as the center of the circle, and uses the direction of the front of the vehicle as the y-axis , And the direction perpendicular to the y-axis and parallel to the horizontal plane is the x-axis, as shown in Figure 2 in the rectangular coordinate system.
  • the fence fitting straight line is determined according to the position information of the static reflection point of the current frame.
  • the static reflection point within a predetermined range on one side of the vehicle can be obtained, and according to the adjacent static reflection point within the predetermined range
  • the points are fitted as straight lines.
  • the static reflection points detected within a predetermined range for example, 2-50m
  • the predetermined static reflection point can be determined according to the position information of the static reflection point in the current frame.
  • the neighboring stationary obstacles in the range are used as the basis to determine the fence fitting straight line, as shown in Figure 2. Or other methods that can determine the fence fitting straight line can also be applied to the present invention.
  • the fence dispersion of the current frame is calculated according to the fence fitting straight line and the stationary reflection points participating in the fitting.
  • the fence dispersion of the current frame is calculated according to the slope and the intercept of the fence fitting straight line. Distance, and the vertical and horizontal distances in the Cartesian coordinate system of the stationary reflection points participating in the fence fitting.
  • the fence dispersion ⁇ gr is calculated according to the fence fitting straight line and the reflection points participating in the fence fitting, wherein the calculation formula of the fence dispersion is as follows:
  • k and b are respectively the slope and intercept of the fence fitting straight line in the rectangular coordinate system as shown in Fig. 2, and Ry i and Rx i are the static reflection points involved in the fence fitting at the right angle
  • the longitudinal distance that is, the distance on the y-axis
  • the horizontal distance the distance on the x-axis
  • step S102 is executed to determine the probability that the static reflection point falls within the fence area according to the fence dispersion of the current frame.
  • the probability that the static reflection point falls within the fence area may be determined according to the dispersion of the fence and the longitudinal and lateral distances of the static reflection point.
  • the longitudinal and lateral distances refer to the aforementioned right angles. The distance on the y axis and the distance on the x axis in the coordinate system.
  • using the fence dispersion to estimate the probability of whether the static reflection point falls within the fence area includes: calculating the probability P gr that the static reflection point falls within the fence area based on the fence dispersion, where The probability conforms to the normal distribution, and its standard deviation and mean are denoted as ⁇ and ⁇ , respectively.
  • the calculation formula of the probability P gr is as follows:
  • Rx and Ry are the longitudinal distance and the lateral distance of the static reflection point, respectively, and the dispersion of the ⁇ gr fence.
  • step S103 is executed to update the fence area according to the target evaluation value of the static reflection point in the fence of the previous frame and the probability that the static reflection point of the current frame falls within the fence area The target evaluation value of the static reflection point within.
  • the continuous multiple frames of tracking results of each static reflection point are obtained, and the target evaluation value of the static reflection point in the fence is updated according to the accumulated results of the multiple frames.
  • the first threshold can be set reasonably according to actual needs, or the value of the first threshold can also be set based on prior experience. For example, the first threshold can be set between 50% and 90%. Any value between.
  • the first additional value can be set reasonably according to actual needs.
  • the specific value of the first additional value is not specifically limited here, and the first additional value may also be a value obtained based on prior experience.
  • the target evaluation value in the fence of the static reflection point of each frame can be calculated and updated according to a formula, the formula is as follows:
  • GuardRail n max(GuardRail max ,GuardRail n-1 +GuardRail add )
  • P on represents the first threshold
  • GuardRail n represents the target evaluation value in the fence of the static reflection point of the current frame
  • GuardRail max represents the maximum target evaluation value
  • the maximum target evaluation value can be the value of the static reflection point in the fence of multiple frames
  • the maximum value of the target evaluation value represents the target evaluation value of the static reflection point in the fence of the previous frame
  • GuardRail add represents the first additional value.
  • the probability that the static reflection point of the current frame falls on the fence area is less than the second threshold, calculate the target evaluation value of the static reflection point in the fence of the previous frame and the second additional value. The difference is compared with the minimum target evaluation value, and the minimum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame.
  • the specific value of the second threshold can be set reasonably according to actual needs, or the value of the second threshold can also be set based on prior experience, for example, the second threshold can be set at 10%-50 Any value between %, or the aforementioned first threshold and second threshold may also be the same value.
  • the second additional value can be set reasonably according to actual needs.
  • the specific value of the second additional value is not specifically limited here, and the second additional value may also be a value obtained based on prior experience.
  • the target evaluation value in the fence of the static reflection point of each frame can be calculated and updated according to a formula, the formula is as follows:
  • GuardRail n min (GuardRail min ,GuardRail n-1 -GuardRail minus )
  • GuardRail n represents the target evaluation value of the current frame of the static reflection point
  • GuardRail min represents the minimum target evaluation value of the static reflection point
  • GuardRail minus represents the second additional value, which can be obtained based on prior experience
  • GuardRail n-1 Represents the target evaluation value of the previous frame
  • P off represents the second threshold.
  • the target evaluation value of the static reflection point in the fence of the current frame can be calculated, and the target evaluation value can be used to evaluate whether the static reflection point is a static reflection point in the fence.
  • step S104 is executed to determine whether the stationary reflection point in the fence area is a stationary object according to the updated target evaluation value of the stationary reflection point in the fence.
  • the stationary reflection point in the fence area is a stationary object, for example, when the target evaluation value is lower than a predetermined threshold and static reflection
  • the predetermined threshold can be obtained based on prior experience, and is not specifically limited here.
  • the target evaluation value When the target evaluation value is lower than the predetermined threshold, it indicates that the static reflection point is not part of the fence, but is the static reflection point on other stationary objects near the fence.
  • the number of detections of static reflection points should be greater than the threshold number of times to avoid too large errors in the target evaluation value due to too few detection times, thereby affecting the judgment of stationary objects.
  • the method of the embodiment of the present invention is based on the target evaluation value of the static reflection point in the fence of the previous frame and the static reflection point of the current frame.
  • the target evaluation value of the static reflection point in the fence area is updated, and the fence is determined according to the updated target evaluation value of the static reflection point in the fence Whether the static reflection point in the area is a static object, so that it can accurately detect the static object that does not belong to the fence but is located near the fence, reducing the probability of missed detection by the automatic emergency braking (AEB) system, thereby improving the robustness of the entire ADAS and AD system Great, enhance user experience.
  • AEB automatic emergency braking
  • FIG. 3 shows a schematic block diagram of a millimeter wave radar 300 in an embodiment of the present invention.
  • the millimeter wave radar 300 includes one or more processors 303, which work individually or together, and the processors are used to: obtain the fence dispersion of the current frame; according to the fence dispersion of the current frame, Determine the probability that the static reflection point falls within the fence area; according to the target evaluation value of the static reflection point in the fence of the previous frame, and the static reflection point of the current frame falls within the fence area Update the target evaluation value of the static reflection point in the fence area; and determine the static reflection point in the fence area according to the updated target evaluation value of the static reflection point in the fence Whether it is a stationary object.
  • 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 method for detecting stationary objects near a fence by a microwave radar described herein.
  • 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 configured to determine a fence fitting straight line according to the position information of the stationary reflection point of the current frame, and according to the fence fitting straight line and the stationary reflection points participating in the fitting, Calculate the fence dispersion of the current frame.
  • the position information of the stationary reflection point is the position information of the stationary reflection point in a Cartesian coordinate system, wherein the Cartesian coordinate system takes the center point of the front of the vehicle as the center of the circle, and the forward direction of the vehicle is The y-axis is the x-axis which is perpendicular to the y-axis and parallel to the horizontal plane.
  • the fence dispersion of the current frame is based on the slope and intercept of the fence fitting straight line, and the longitudinal distance and the lateral distance of the stationary reflection points involved in the fence fitting in the rectangular coordinate system. determine.
  • the probability that the static reflection point falls within the fence area is determined according to the dispersion of the fence and the longitudinal distance and the lateral distance of the static reflection point.
  • the processor 303 is further configured to obtain the tracking result of each stationary reflection point in consecutive multiple frames, and update the target evaluation value of the stationary reflection point in the fence according to the accumulated result of the multiple frames.
  • the processor 303 determines that the stationary reflection point is a stationary object.
  • the processor calculates the target evaluation value of the static reflection point in the fence of the previous frame and the first Add the sum of additional values and compare the sum with the maximum target evaluation value, and take the maximum of the two as the target evaluation value within the fence of the static reflection point of the current frame; if the static reflection point of the current frame falls on the fence area If the probability is less than the second threshold, the processor calculates the difference between the target evaluation value of the stationary reflection point in the fence of the previous frame and the second additional value and compares the difference with the minimum target evaluation value , Take the minimum of the two as the target evaluation value in the fence of the static reflection point of the current frame.
  • the processor 303 detects a static reflection point in front of or behind the vehicle based on a millimeter wave radar to obtain position information of the static reflection point in the current frame.
  • 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 (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.
  • 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 point to the target to be measured can also be called a point cloud.
  • the reflection point of the target to be measured includes the static reflection point of a stationary object.
  • the reflection point includes position information of the static reflection point.
  • 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 infers the distance to the source of the incident wave, namely the target, the relative velocity of the target, and the orientation of the target through a well-known algorithm, and generates a data signal representing the estimation result, that is, the signal processing circuit is electrically connected to the antenna device , Used to process the reflected signal and convert it into a data signal, the data signal including the position information of the static reflection point, etc.
  • the signal processing circuit in the embodiment of the present invention is not limited to a single circuit, but also includes a form in which a combination of multiple circuits is generally understood as a functional element.
  • the signal processing circuit 302 may 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 components and structure of the millimeter wave radar 300 shown in FIG. 3 are only exemplary and not restrictive, and the components of the millimeter wave radar 300 may also have other components and structures as required.
  • 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 installed on the front side or/and the rear side of the vehicle body, or other suitable positions. Among them, one or more millimeter wave radars can be installed on the vehicle body.
  • the aforementioned microwave radar method for detecting stationary objects near the fence can be realized, so that without increasing the hardware cost, according to the target evaluation value of the stationary reflection point in the fence in the previous frame, and According to the probability that the static reflection point of the current frame falls within the fence area, the target evaluation value of the static reflection point in the fence area is updated according to the updated value of the static reflection point in the fence.
  • the target evaluation value is used to determine whether the static reflection point in the fence area is a static object, so as to accurately detect the static object that does not belong to the fence but is located near the fence, reducing the probability of missed detection by the automatic emergency braking (AEB) system, thereby Improve the robustness of the entire ADAS and AD system and enhance user experience.
  • AEB automatic emergency braking
  • 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

一种微波雷达检测栅栏附近静止物体的方法和毫米波雷达，该方法包括：获取当前帧的栅栏离散度(S101)；根据当前帧的栅栏离散度，确定静止反射点落在栅栏区域内的概率(S102)；根据上一帧的栅栏内的静止反射点的目标评价值，以及当前帧的静止反射点落在栅栏区域内的概率，更新栅栏区域内的静止反射点的目标评价值(S103)；以及根据更新后的栅栏内的静止反射点的目标评价值，确定栅栏区域内的静止反射点是否为静止物体(S104)。该方法能够准确的检测出不属于栅栏而位于栅栏附近的静止物体，减少自动紧急制动(AEB)系统漏检概率，从而提高整个ADAS和AD系统的鲁棒性、提升用户体验。

Description

微波雷达检测栅栏附近静止物体的方法和毫米波雷达
说明书
技术领域
本发明总地涉及自动驾驶技术领域，更具体地涉及一种微波雷达检测栅栏附近静止物体的方法和毫米波雷达。
背景技术
近年来高级辅助驾驶(Advanced Driver Assistant System,ADAS)和自动驾驶(Autonomous Driving,AD)领域发展迅速，毫米波雷达因其全天时、全天候、作用距离远、测速精度高等优点而被广泛使用。然而区分栅栏和栅栏附近静止车辆一直是车载毫米波雷达领域的问题与难点。由于栅栏和静止车辆都是强反射物体，且都没有速度，所以在车载雷达做物体跟踪聚类时，非常容易将静止车辆与相邻的栅栏聚类成一个航迹，使得静止车辆被误认为是栅栏的一部分。这种情况下，自动紧急制动系统(AEB)将无法正常启用，从而导致ADAS系统的用户体验很差。
为了解决上述技术问题，本发明提出了一种新的微波雷达检测栅栏附近静止物体的方法。
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微波雷达检测栅栏附近静止物体的方法，所述方法包括：
获取当前帧的栅栏离散度；
根据当前帧的所述栅栏离散度，确定静止反射点落在栅栏区域内的概率；
根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值；以及
根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体。
示例性地，所述获取当前帧的栅栏离散度，包括：
获取当前帧的静止反射点的位置信息；
根据当前帧的所述静止反射点的位置信息，确定栅栏拟合直线；
根据所述栅栏拟合直线和参与所述拟合的静止反射点，计算当前帧的栅栏离散度。
示例性地，所述静止反射点的位置信息为所述静止反射点在直角坐标系下的位置信息，其中，所述直角坐标系以车辆的车头中心点为圆心，以车辆的运行前方方向为y轴，以与y轴垂直且与水平面平行的方向为x轴。
示例性地，所述当前帧的栅栏离散度根据所述栅栏拟合直线的斜率和截距，以及参与栅栏拟合的静止反射点的在所述直角坐标系内的纵向距离和横向距离来确定。
示例性地，所述静止反射点落在栅栏区域内的概率根据所述栅栏离散度以及所述静止反射点的纵向距离和横向距离确定。
示例性地，所述根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值，包括：
获取每个静止反射点的连续多帧的跟踪结果，根据多帧累积的结果，更新栅栏内的所述静止反射点的目标评价值。
示例性地，当目标评价值低于预定阈值且静止反射点的检测次数大于阈值次数时，则确定该静止反射点是静止物体。
示例性地，所述根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值，具体包括：
如果当前帧的静止反射点落在栅栏区域的概率大于第一阈值，则计算上 一帧的所述栅栏内的所述静止反射点的目标评价值与第一附加值之和并将该和与最大目标评价值进行比较，取两者中的最大值为当前帧的静止反射点的栅栏内的目标评价值；
如果当前帧的静止反射点落在栅栏区域的概率小于第二阈值，则计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第二附加值的差值并将该差值与最小目标评价值进行比较，取两者中的最小值为当前帧的静止反射点的栅栏内的目标评价值。
示例性地，所述获取当前帧的静止反射点的位置信息，包括：
基于毫米波雷达检测车辆前方或后方的静止反射点，以获取当前帧的静止反射点的位置信息。
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：
获取当前帧的栅栏离散度；
根据当前帧的所述栅栏离散度，确定所述静止反射点落在栅栏区域内的概率；
根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值；以及
根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体。
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。
示例性地，所述处理器用于根据当前帧的所述静止反射点的位置信息，确定栅栏拟合直线，并且根据所述栅栏拟合直线和参与所述拟合的静止反射点，计算当前帧的栅栏离散度。
示例性地，所述静止反射点的位置信息为所述静止反射点在直角坐标系下的位置信息，其中，所述直角坐标系以车辆的车头中心点为圆心，以车辆的运行前方方向为y轴，以与y轴垂直且与水平面平行的方向为x轴。
示例性地，所述当前帧的栅栏离散度根据所述栅栏拟合直线的斜率和截距，以及参与栅栏拟合的静止反射点的在所述直角坐标系内的纵向距离和横向距离来确定。
示例性地，所述静止反射点落在栅栏区域内的概率根据所述栅栏离散度以及所述静止反射点的纵向距离和横向距离确定。
示例性地，所述处理器进一步用于获取每个静止反射点的连续多帧的跟踪结果，根据多帧累积的结果，更新栅栏内的所述静止反射点的目标评价值。
示例性地，当目标评价值低于预定阈值且静止反射点的检测次数大于阈值次数时，则所述处理器确定该静止反射点是静止物体。
示例性地，如果当前帧的静止反射点落在栅栏区域的概率大于第一阈值，则所述处理器计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第一附加值之和并将该和与最大目标评价值进行比较，取两者中的最大值为当前帧的静止反射点的栅栏内的目标评价值；
如果当前帧的静止反射点落在栅栏区域的概率小于第二阈值，则所述处理器计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第二附加值的差值并将该差值与最小目标评价值进行比较，取两者中的最小值为当前帧的静止反射点的栅栏内的目标评价值。
示例性地，所述处理器基于毫米波雷达检测车辆前方或后方的静止反射点，以获取当前帧的静止反射点的位置信息。
本发明另一方面提供一种计算机存储介质，其上存储有计算机程序，其 特征在于，所述程序被处理器执行时实现前述的方法。
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于所述车身的前侧或/及后侧。
本发明实施例的方法，在不增加硬件成本的前提下，根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值，根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体，从而能够准确的检测出栅栏区域内的静止反射点是否为静止物体，减少自动紧急制动(AEB)系统漏检概率，从而提高整个ADAS和AD系统的鲁棒性、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微波雷达检测栅栏附近静止物体的方法的示意性流程图；
图2示出了本发明一个实施例中的微波雷达检测栅栏附近静止物体的方法的原理示意图；
图3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。
目前的车载雷达为了解决栅栏附近的静止车辆会被误识别为栅栏的一部分这一问题通常采取以下方法：
1、通过增加接收天线通道数，从而提高测角精度和分辨能力，这样可以增强雷达对栅栏附近车辆角度测量的精确度，从而区分栅栏和栅栏附近的静止车辆。但是这种方法将大幅增加天线设计复杂度、天线尺寸和天线以及高频板材的成本，同时由于通道数的增加DOA(到来波方向)算法的计算开销将大幅上升，这将使得处理器的硬件成本大幅上升。
2、通过缩小雷达航迹跟踪管理中横向距离的关联波门大小。虽然可以一定程度上解决此问题。但是这将导致车辆或栅栏航迹分裂的概率大幅上升。这将是一种得不偿失的结果。
因此，为了解决上述问题，本发明提供了一种微波雷达检测栅栏附近静止物体的方法，如图1所示，所述方法包括：
步骤S101，获取当前帧的栅栏离散度；
步骤S102，根据当前帧的所述栅栏离散度，确定静止反射点落在栅栏区域内的概率；
步骤S103，根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值；以及
步骤S104，根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体。
本发明实施例的方法，在不增加硬件成本的前提下，根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值，根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体，从而能够准确的检测出不属于栅栏而位于栅栏附近的静止物体，减少自动紧急制动(AEB)系统漏检概率，从而提高整个ADAS和AD系统的鲁棒性、提升用户体验。
下面结合附图，对本申请的一种微波雷达检测栅栏附近静止物体的方法进行详细说明。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，微波雷达检测栅栏附近静止物体的方法，所述方法包括以下步骤：
首先，执行步骤S101，获取当前帧的栅栏离散度。
可以通过任意适合的方法获取当前帧的栅栏离散度。在一个具体示例中，所述获取当前帧的栅栏离散度，具体包括：获取当前帧的静止反射点的位置信息；根据当前帧的所述静止反射点的位置信息，确定栅栏拟合直线；根据所述栅栏拟合直线和参与所述拟合的静止反射点，计算当前帧的栅栏离散度。
基于微波雷达检测车辆前方或后方的静止反射点，以获取当前帧的静止反射点的位置信息。其中，该微波雷达包括毫米波雷达。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，因此十分适合于本发明的栅栏检测。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点，也可以称之为点云。待测目标的反射点包括静止物体的静止反射点。该反射点包括静止反射点的位置信息。
毫米波雷达安装于移动平台上，例如安装于车辆上，该车辆还可以包括自动驾驶车辆。可选地，所述静止反射点的位置信息为所述静止反射点在直角坐标系下的位置信息，其中，直角坐标系以车辆的车头中心点为圆心，以车辆的运行前方方向为y轴，以与y轴垂直且与水平面平行的方向为x轴，如图2所示的在直角坐标系。
在一个示例中，根据当前帧的所述静止反射点的位置信息，确定栅栏拟合直线，例如，可以获得车辆一侧的预定范围内的静止反射点，并根据在预 定范围内的邻近静止反射点拟合为直线。例如，通常在车辆行驶中，车辆两侧预定范围内(例如2-50m)检测到的静止反射点通常为栅栏的反射点，因此可以根据当前帧的所述静止反射点的位置信息，将预定范围内的邻近静止障碍物作为基础，确定栅栏拟合直线，如图2所示。或者其他能够确定栅栏拟合直线的方法同样也可以适用于本发明。
在一个示例中，根据所述栅栏拟合直线和参与所述拟合的静止反射点，计算当前帧的栅栏离散度，例如，当前帧的栅栏离散度根据所述栅栏拟合直线的斜率和截距，以及参与栅栏拟合的静止反射点的在所述直角坐标系内的纵向距离和横向距离来确定。
具体地，根据栅栏拟合直线和参与栅栏拟合的反射点计算所述栅栏离散度σ gr，其中，所述栅栏离散度的计算公式如下：
Figure PCTCN2019080516-appb-000001
其中，k、b分别为在如图2所示的直角坐标系内所述栅栏拟合直线的斜率和截距，Ry i、Rx i分别为参与栅栏拟合的静止反射点的在所述直角坐标系内的纵向距离(也即y轴上的距离)和横向距离(x轴上的距离)。
上述公式仅作为栅栏离散度计算的一个具体示例，对于其他的栅栏离散度的计算方法也同样可以适用于本发明实施例中。
接着，执行步骤S102，根据当前帧的所述栅栏离散度，确定静止反射点落在栅栏区域内的概率。
在一个示例中，所述静止反射点落在栅栏区域内的概率可以根据所述栅栏离散度以及所述静止反射点的纵向距离和横向距离确定，该纵向距离和横向距离是指在前述的直角坐标系中y轴上的距离和x轴上的距离。
具体地，利用所述栅栏离散度对静止反射点是否落在栅栏区域内做概率估计，包括：以所述栅栏离散度为基础，计算静止反射点落在栅栏区域的概率P gr，其中，所述概率符合正态分布，其标准差和均值分别记作σ和μ，所述 概率P gr的计算公式如下：
μ＝k*Rx+b
σ＝σ gr
Figure PCTCN2019080516-appb-000002
其中Rx、Ry分别是静止反射点的纵向距离和横向距离，σ gr栅栏离散度。
接着，执行步骤S103，根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值。
具体地，获取每个静止反射点的连续多帧的跟踪结果，根据多帧累积的结果，更新栅栏内的所述静止反射点的目标评价值。
在一个示例中，如果当前帧的静止反射点落在栅栏区域的概率大于第一阈值，则计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第一附加值之和并将该和与最大目标评价值进行比较，取两者中的最大值为当前帧的静止反射点的栅栏内的目标评价值。其中，第一阈值的具体数值可以根据实际的需要合理设定，或者，还可以根据先验经验设定该第一阈值的值，例如，该第一阈值可以设定在50％-90％之间的任意一个值。
而第一附加值可以根据实际需要进行合理设定，在此不对该第一附加值的具体数值做具体限定，该第一附加值还可以是根据先验经验获得的值。
具体地，可以按照公式计算和更新每帧静止反射点的栅栏内的目标评价值，所述公式如下：
如果P gr>P on
GuardRail n＝max(GuardRail max,GuardRail n-1+GuardRail add)
其中，P on表示第一阈值，GuardRail n表示当前帧的静止反射点的栅栏内的目标评价值，GuardRail max表示最大目标评价值，该最大目标评价值可以 是多帧静止反射点的栅栏内的目标评价值的最大值，GuardRail n-1表示上一帧的所述栅栏内的所述静止反射点的目标评价值，GuardRail add表示第一附加值。
在另一个示例中，如果当前帧的静止反射点落在栅栏区域的概率小于第二阈值，则计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第二附加值的差值并将该差值与最小目标评价值进行比较，取两者中的最小值为当前帧的静止反射点的栅栏内的目标评价值。其中，所述第二阈值的具体数值可以根据实际的需要合理设定，或者，还可以根据先验经验设定该第二阈值的值，例如，该第二阈值可以设定在10％-50％之间的任意一个值，或者，前述的第一阈值和第二阈值也可以是相同的值。
而第二附加值可以根据实际需要进行合理设定，在此不对该第二附加值的具体数值做具体限定，该第二附加值还可以是根据先验经验获得的值。
具体地，可以按照公式计算和更新每帧静止反射点的栅栏内的目标评价值，所述公式如下：
如果P gr<P off
GuardRail n＝min(GuardRail min,GuardRail n-1-GuardRail minus)
其中，GuardRail n表示静止反射点的当前帧的目标评价值，GuardRail min表示静止反射点的最小目标评价值，GuardRail minus表示第二附加值，该附加值可依据先验经验获得，GuardRail n-1表示上一帧的目标评价值，P off表示第二阈值。
其中，如图2所示，通过静止反射点落在栅栏区域的概率分布，可以将不在栅栏区域的静止物体(如图2所示的静止车辆)排除在栅栏区域之外。
通过上述方法即可计算当前帧的静止反射点的栅栏内的目标评价值，该目标评价值可以用于评价该静止反射点是否为栅栏内的静止反射点。
进一步，执行步骤S104，根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体。
具体地，根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体，例如，当目标评价值低于预定阈值且静止反射点的检测次数大于阈值次数时，则确定该静止反射点是静止物体，也即确定该静止反射点是栅栏附近的静止物体，例如静止车辆。其中，该预定阈值可以根据先验经验而获得，在此不做具体限定。
当目标评价值低于预定阈值，则表明静止反射点不属于栅栏的一部分，而是栅栏附近其他的静止物体上的静止反射点。同时静止反射点的检测次数要大于阈值次数，以避免由于检测次数过少而导致目标评价值的误差过大，从而影响对静止物体的判断。
综上所述，本发明实施例的方法，在不增加硬件成本的前提下，根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值，根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体，从而能够准确的检测出不属于栅栏而位于栅栏附近的静止物体，减少自动紧急制动(AEB)系统漏检概率，从而提高整个ADAS和AD系统的鲁棒性、提升用户体验。
图3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。
如图3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：获取当前帧的栅栏离散度；根据当前帧的所述栅栏离散度，确定所述静止反射点落在栅栏区域内的概率；根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值；以及根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体。
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，以执行本文描述的微波雷达检测栅栏附近静止物体的方法。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。
在一个示例中，所述处理器303用于根据当前帧的所述静止反射点的位置信息，确定栅栏拟合直线，并且根据所述栅栏拟合直线和参与所述拟合的静止反射点，计算当前帧的栅栏离散度。可选地，所述静止反射点的位置信息为所述静止反射点在直角坐标系下的位置信息，其中，所述直角坐标系以车辆的车头中心点为圆心，以车辆的运行前方方向为y轴，以与y轴垂直且与水平面平行的方向为x轴。
在一个示例中，所述当前帧的栅栏离散度根据所述栅栏拟合直线的斜率和截距，以及参与栅栏拟合的静止反射点的在所述直角坐标系内的纵向距离和横向距离来确定。
可选地，所述静止反射点落在栅栏区域内的概率根据所述栅栏离散度以及所述静止反射点的纵向距离和横向距离确定。
在一个示例中，所述处理器303进一步用于获取每个静止反射点的连续多帧的跟踪结果，根据多帧累积的结果，更新栅栏内的所述静止反射点的目标评价值。可选地，当目标评价值低于预定阈值且静止反射点的检测次数大于阈值次数时，则所述处理器303确定该静止反射点是静止物体。
在一个示例中，如果当前帧的静止反射点落在栅栏区域的概率大于第一阈值，则所述处理器计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第一附加值之和并将该和与最大目标评价值进行比较，取两者中的最大值为当前帧的静止反射点的栅栏内的目标评价值；如果当前帧的静止反射点落在栅栏区域的概率小于第二阈值，则所述处理器计算上一帧的所述栅栏内 的所述静止反射点的目标评价值与第二附加值的差值并将该差值与最小目标评价值进行比较，取两者中的最小值为当前帧的静止反射点的栅栏内的目标评价值。
在一个示例中，所述处理器303基于毫米波雷达检测车辆前方或后方的静止反射点，以获取当前帧的静止反射点的位置信息。
如图3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点，也可以称之为点云。待测目标的反射点包括静止物体的静止反射点。该反射点包括静止反射点的位置信息。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，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，该数据信号包括静止反射点的位置信息等。
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3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。
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，毫米波雷达可以安装于所述车身的前侧或/及后 侧，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微波雷达检测栅栏附近静止物体的方法，从而在不增加硬件成本的前提下，根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值，根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体，从而能够准确的检测出不属于栅栏而位于栅栏附近的静止物体，减少自动紧急制动(AEB)系统漏检概率，从而提高整个ADAS和AD系统的鲁棒性、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 (21)

  1. 一种微波雷达检测栅栏附近静止物体的方法，其特征在于，所述方法包括：
    获取当前帧的栅栏离散度；
    根据当前帧的所述栅栏离散度，确定静止反射点落在栅栏区域内的概率；
    根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值；以及
    根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体。
  2. 如权利要求1所述的方法，其特征在于，所述获取当前帧的栅栏离散度，包括：
    获取当前帧的静止反射点的位置信息；
    根据当前帧的所述静止反射点的位置信息，确定栅栏拟合直线；
    根据所述栅栏拟合直线和参与所述拟合的静止反射点，计算当前帧的栅栏离散度。
  3. 如权利要求2所述的方法，其特征在于，所述静止反射点的位置信息为所述静止反射点在直角坐标系下的位置信息，其中，所述直角坐标系以车辆的车头中心点为圆心，以车辆的运行前方方向为y轴，以与y轴垂直且与水平面平行的方向为x轴。
  4. 如权利要求3所述的方法，其特征在于，所述当前帧的栅栏离散度根据所述栅栏拟合直线的斜率和截距，以及参与栅栏拟合的静止反射点的在所述直角坐标系内的纵向距离和横向距离来确定。
  5. 如权利要求1所述的方法，其特征在于，所述静止反射点落在栅栏区域内的概率根据所述栅栏离散度以及所述静止反射点的纵向距离和横向距离确定。
  6. 如权利要求1所述的方法，其特征在于，所述根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值，包括：
    获取每个静止反射点的连续多帧的跟踪结果，根据多帧累积的结果，更新栅栏内的所述静止反射点的目标评价值。
  7. 如权利要求1或6所述的方法，其特征在于，当目标评价值低于预定阈值且静止反射点的检测次数大于阈值次数时，则确定该静止反射点是静止物体。
  8. 如权利要求1所述的方法，其特征在于，所述根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值，具体包括：
    如果当前帧的静止反射点落在栅栏区域的概率大于第一阈值，则计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第一附加值之和并将该和与最大目标评价值进行比较，取两者中的最大值为当前帧的静止反射点的栅栏内的目标评价值；
    如果当前帧的静止反射点落在栅栏区域的概率小于第二阈值，则计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第二附加值的差值并将该差值与最小目标评价值进行比较，取两者中的最小值为当前帧的静止反射点的栅栏内的目标评价值。
  9. 如权利要求2所述的方法，其特征在于，所述获取当前帧的静止反射点的位置信息，包括：
    基于毫米波雷达检测车辆前方或后方的静止反射点，以获取当前帧的静止反射点的位置信息。
  10. 一种毫米波雷达，其特征在于，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：
    获取当前帧的栅栏离散度；
    根据当前帧的所述栅栏离散度，确定所述静止反射点落在栅栏区域内的概率；
    根据上一帧的所述栅栏内的所述静止反射点的目标评价值，以及所述当前帧的所述静止反射点落在栅栏区域内的概率，更新所述栅栏区域内的所述静止反射点的目标评价值；以及
    根据更新后的所述栅栏内的所述静止反射点的目标评价值，确定所述栅栏区域内的静止反射点是否为静止物体。
  11. 如权利要求10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。
  12. 如权利要求10所述的毫米波雷达，其特征在于，所述处理器用于根据当前帧的所述静止反射点的位置信息，确定栅栏拟合直线，并且根据所述栅栏拟合直线和参与所述拟合的静止反射点，计算当前帧的栅栏离散度。
  13. 如权利要求12所述的毫米波雷达，其特征在于，所述静止反射点的位置信息为所述静止反射点在直角坐标系下的位置信息，其中，所述直角坐标系以车辆的车头中心点为圆心，以车辆的运行前方方向为y轴，以与y轴垂直且与水平面平行的方向为x轴。
  14. 如权利要求13所述的毫米波雷达，其特征在于，所述当前帧的栅栏离散度根据所述栅栏拟合直线的斜率和截距，以及参与栅栏拟合的静止反射点的在所述直角坐标系内的纵向距离和横向距离来确定。
  15. 如权利要求11所述的毫米波雷达，其特征在于，所述静止反射点落 在栅栏区域内的概率根据所述栅栏离散度以及所述静止反射点的纵向距离和横向距离确定。
  16. 如权利要求11所述的毫米波雷达，其特征在于，所述处理器进一步用于获取每个静止反射点的连续多帧的跟踪结果，根据多帧累积的结果，更新栅栏内的所述静止反射点的目标评价值。
  17. 如权利要求11或16所述的毫米波雷达，其特征在于，当目标评价值低于预定阈值且静止反射点的检测次数大于阈值次数时，则所述处理器确定该静止反射点是静止物体。
  18. 如权利要求11所述的毫米波雷达，其特征在于，
    如果当前帧的静止反射点落在栅栏区域的概率大于第一阈值，则所述处理器计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第一附加值之和并将该和与最大目标评价值进行比较，取两者中的最大值为当前帧的静止反射点的栅栏内的目标评价值；
    如果当前帧的静止反射点落在栅栏区域的概率小于第二阈值，则所述处理器计算上一帧的所述栅栏内的所述静止反射点的目标评价值与第二附加值的差值并将该差值与最小目标评价值进行比较，取两者中的最小值为当前帧的静止反射点的栅栏内的目标评价值。
  19. 如权利要求12所述的毫米波雷达，其特征在于，所述处理器基于毫米波雷达检测车辆前方或后方的静止反射点，以获取当前帧的静止反射点的位置信息。
  20. 一种计算机存储介质，其上存储有计算机程序，其特征在于，所述程序被处理器执行时实现权利要求1至9中任一项所述的方法。
  21. 一种车辆，其特征在于，所述车辆包括车身以及权利要求10～19任一项所述的毫米波雷达，所述毫米波雷达安装于所述车身的前侧或/及后侧。
PCT/CN2019/080516 2019-03-29 2019-03-29 微波雷达检测栅栏附近静止物体的方法和毫米波雷达 Ceased WO2020198973A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/080516 WO2020198973A1 (zh) 2019-03-29 2019-03-29 微波雷达检测栅栏附近静止物体的方法和毫米波雷达
CN201980010405.4A CN111699407B (zh) 2019-03-29 2019-03-29 微波雷达检测栅栏附近静止物体的方法和毫米波雷达

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/080516 WO2020198973A1 (zh) 2019-03-29 2019-03-29 微波雷达检测栅栏附近静止物体的方法和毫米波雷达

Publications (1)

Publication Number Publication Date
WO2020198973A1 true WO2020198973A1 (zh) 2020-10-08

Family

ID=72476437

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/080516 Ceased WO2020198973A1 (zh) 2019-03-29 2019-03-29 微波雷达检测栅栏附近静止物体的方法和毫米波雷达

Country Status (2)

Country Link
CN (1) CN111699407B (zh)
WO (1) WO2020198973A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116699595A (zh) * 2023-05-17 2023-09-05 北京经纬恒润科技股份有限公司 车载雷达运动速度确定方法、装置及设备

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114779242B (zh) * 2021-01-22 2025-08-12 中寰卫星导航通信有限公司 地图栅栏的获取方法、系统、地图、存储介质和设备
CN114488072B (zh) * 2021-06-09 2025-10-31 深圳市速腾聚创科技有限公司 障碍物检测方法、装置及存储介质
US11624831B2 (en) 2021-06-09 2023-04-11 Suteng Innovation Technology Co., Ltd. Obstacle detection method and apparatus and storage medium
CN114460547B (zh) * 2021-12-23 2025-05-23 北京遥测技术研究所 一种基于doa聚类算法的被动雷达抗有源诱偏方法
CN115032630B (zh) * 2022-05-31 2025-07-11 南京市德赛西威汽车电子有限公司 一种基于bsd雷达的网格化栏杆检测方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030222812A1 (en) * 2002-06-04 2003-12-04 Fujitsu Ten Limited Method of storing data in radar used for vehicle
JP2011123551A (ja) * 2009-12-08 2011-06-23 Toyota Central R&D Labs Inc 死角領域推定装置及びプログラム
CN103176185A (zh) * 2011-12-26 2013-06-26 上海汽车集团股份有限公司 用于检测道路障碍物的方法及系统
CN105911553A (zh) * 2016-04-15 2016-08-31 北京信息科技大学 一种道路可行域确定方法及系统
CN108344997A (zh) * 2018-01-16 2018-07-31 华域汽车系统股份有限公司 一种基于点迹特征的道路护栏快速检测方法
CN109407097A (zh) * 2018-10-30 2019-03-01 北京润科通用技术有限公司 一种车辆可行驶区域的检测方法及装置

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4698048B2 (ja) * 2001-03-19 2011-06-08 富士通テン株式会社 Ｆｍ−ｃｗレーダの路上静止物検知方法
JP2004171295A (ja) * 2002-11-20 2004-06-17 Matsushita Electric Works Ltd 障害物検知方法及び車載用レーダ装置
JP4385064B2 (ja) * 2007-09-06 2009-12-16 本田技研工業株式会社 制御対象認識装置
WO2011075639A1 (en) * 2009-12-18 2011-06-23 Christopher Gary Sentelle Moving entity detection
JP5989353B2 (ja) * 2012-02-13 2016-09-07 株式会社デンソー レーダ装置
JP6020321B2 (ja) * 2013-04-11 2016-11-02 株式会社デンソー 物標検出装置及び車両制御システム
US9834207B2 (en) * 2014-04-15 2017-12-05 GM Global Technology Operations LLC Method and system for detecting, tracking and estimating stationary roadside objects
CN105044712B (zh) * 2015-08-27 2017-06-16 电子科技大学 一种微波栅栏雷达装置与目标检测方法
JP2017223461A (ja) * 2016-06-13 2017-12-21 パナソニックＩｐマネジメント株式会社 レーダ装置および検出方法
CN106127113A (zh) * 2016-06-15 2016-11-16 北京联合大学 一种基于三维激光雷达的道路车道线检测方法
JP2017227529A (ja) * 2016-06-22 2017-12-28 パナソニックＩｐマネジメント株式会社 レーダ装置および追従対象決定方法
JP6970936B2 (ja) * 2016-12-20 2021-11-24 パナソニックＩｐマネジメント株式会社 物体検出装置、物体検出プログラム、および記録媒体
US10222803B2 (en) * 2017-06-02 2019-03-05 Aptiv Technologies Limited Determining objects of interest for active cruise control
JP7103759B2 (ja) * 2017-06-16 2022-07-20 株式会社デンソーウェーブ 車両認識装置、車両認識システム、車両認識プログラム
CN108909721B (zh) * 2018-04-28 2021-04-23 南通职业大学 一种基于毫米波雷达的车辆偏航角计算方法
CN108960183B (zh) * 2018-07-19 2020-06-02 北京航空航天大学 一种基于多传感器融合的弯道目标识别系统及方法
CN109254289B (zh) * 2018-11-01 2021-07-06 百度在线网络技术（北京）有限公司 道路护栏的检测方法和检测设备
CN109444839B (zh) * 2018-11-29 2020-10-13 北京行易道科技有限公司 目标轮廓的获取方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030222812A1 (en) * 2002-06-04 2003-12-04 Fujitsu Ten Limited Method of storing data in radar used for vehicle
JP2011123551A (ja) * 2009-12-08 2011-06-23 Toyota Central R&D Labs Inc 死角領域推定装置及びプログラム
CN103176185A (zh) * 2011-12-26 2013-06-26 上海汽车集团股份有限公司 用于检测道路障碍物的方法及系统
CN105911553A (zh) * 2016-04-15 2016-08-31 北京信息科技大学 一种道路可行域确定方法及系统
CN108344997A (zh) * 2018-01-16 2018-07-31 华域汽车系统股份有限公司 一种基于点迹特征的道路护栏快速检测方法
CN109407097A (zh) * 2018-10-30 2019-03-01 北京润科通用技术有限公司 一种车辆可行驶区域的检测方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116699595A (zh) * 2023-05-17 2023-09-05 北京经纬恒润科技股份有限公司 车载雷达运动速度确定方法、装置及设备

Also Published As

Publication number Publication date
CN111699407A (zh) 2020-09-22
CN111699407B (zh) 2024-08-02

Similar Documents

Publication Publication Date Title
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
CN112995899B (zh) 车路协同定位方法、装置、车载定位系统及路侧设备
WO2020199010A1 (zh) 毫米波雷达的跟踪检测方法、毫米波雷达和车辆
WO2021008202A1 (zh) 一种基于毫米波雷达点云特征的核支持向量机目标分类方法
WO2021217518A1 (zh) 雷达点云聚类方法和装置
WO2020186420A1 (zh) 一种目标检测方法、设备、毫米波雷达及可移动平台
CN113391270B (zh) 多雷达点云融合的虚假目标抑制方法、装置及终端设备
WO2023071992A1 (zh) 多传感器信号融合的方法、装置、电子设备及存储介质
WO2021102689A1 (zh) 护栏检测方法及设备、存储介质和可移动平台
KR102818482B1 (ko) 타겟 개수 추정 장치 및 방법
US20190033442A1 (en) Broadside detection system and techniques for use in a vehicular radar
CN109188382B (zh) 一种基于毫米波雷达的目标识别方法
CN111045023A (zh) 一种基于光检测和测距的车辆追踪方法和系统
WO2025025648A1 (zh) 多径识别方法、装置、车辆及介质
CN114495512B (zh) 一种车辆信息检测方法、系统、电子设备及可读存储介质
CN110794392A (zh) 车辆定位方法、装置、车辆及存储介质
WO2021098320A1 (zh) 一种道路约束确定方法及装置
CN115792953B (zh) 一种基于激光雷达的定位方法、系统及可读存储介质
CN108693517B (zh) 车辆定位方法、装置和雷达
CN113514825B (zh) 道路边缘的获取方法、装置和终端设备
US11983937B2 (en) Intersecting road estimation device
CN116047442A (zh) 一种检测目标角度的方法、装置及电子设备
CN113631948B (zh) 物体检测装置
CN116027288A (zh) 生成数据的方法、装置、电子设备及存储介质
CN114488115A (zh) 一种目标检测方法、装置、计算机设备及可读存储介质

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: 19923295

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: 19923295

Country of ref document: EP

Kind code of ref document: A1