WO2021102689A1 - Procédé et dispositif de détection de glissière de sécurité, support de stockage et plate-forme mobile - Google Patents

Procédé et dispositif de détection de glissière de sécurité, support de stockage et plate-forme mobile Download PDF

Info

Publication number
WO2021102689A1
WO2021102689A1 PCT/CN2019/120981 CN2019120981W WO2021102689A1 WO 2021102689 A1 WO2021102689 A1 WO 2021102689A1 CN 2019120981 W CN2019120981 W CN 2019120981W WO 2021102689 A1 WO2021102689 A1 WO 2021102689A1
Authority
WO
WIPO (PCT)
Prior art keywords
guardrail
distance
reflection point
target
reflection
Prior art date
Application number
PCT/CN2019/120981
Other languages
English (en)
Chinese (zh)
Inventor
卜运成
李怡强
陆新飞
Original Assignee
深圳市大疆创新科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2019/120981 priority Critical patent/WO2021102689A1/fr
Priority to CN201980039524.2A priority patent/CN112313539B/zh
Publication of WO2021102689A1 publication Critical patent/WO2021102689A1/fr

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
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
    • 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
    • G01S2013/932—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles using own vehicle data, e.g. ground speed, steering wheel direction
    • 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
    • G01S2013/9327—Sensor installation details
    • G01S2013/93271—Sensor installation details in the front of the vehicles

Definitions

  • the invention relates to the technical field of guardrail detection and fitting, and more specifically to a guardrail detection method and equipment based on millimeter wave radar, a storage medium and a movable platform.
  • millimeter-wave radar has been used more and more in the field of auto driving due to its unique all-time and all-weather characteristics, plus the advantages of long range and high speed measurement accuracy.
  • the detection and fitting of the guardrail on both sides of the road by the millimeter wave radar can provide a lot of help for automatic driving or assisted driving, such as the calculation of the probability of the target vehicle in its own lane, the detection of the vehicle passable area, and the reduction of false alarms of targets outside the guardrail.
  • the guardrail appears as a large number of reflection points in the detection result of the millimeter wave radar. If all these guardrail reflection points are output, it will bring greater data output pressure.
  • the shape of the guardrail changes with the curve of the road, so a single guardrail fitting model cannot meet the demand.
  • the present invention is proposed in order to solve at least one of the above-mentioned problems.
  • the present invention provides a guardrail detection method and equipment based on millimeter wave radar, a storage medium and a movable platform, which replace the current guardrail with characterization parameters of the current guardrail, thereby effectively reducing the data output pressure of the guardrail reflection point.
  • the embodiment of the present invention provides a guardrail detection method based on millimeter wave radar, which includes:
  • the guardrail model is determined according to the guardrail reflection point, and then the characteristic parameters of the current guardrail are determined and output to represent the current guardrail.
  • the embodiment of the present invention also provides a guardrail detection device based on millimeter wave radar, which includes:
  • Millimeter wave radar sensor the millimeter wave radar sensor is used to transmit millimeter waves to the target area, and receive the millimeter wave echo signals reflected back by objects in the target area;
  • a processor the processor is configured to process the echo signal to obtain a guardrail reflection point
  • the guardrail model is determined according to the guardrail reflection point, and then the characteristic parameters of the current guardrail are determined and output to represent the current guardrail.
  • An embodiment of the present invention also provides a storage medium, and a computer program is stored on the storage medium, and the computer program executes the above-mentioned method when running.
  • the embodiment of the present invention also provides a movable platform, which includes the guardrail fitting system described above.
  • the embodiment of the present invention provides a guardrail detection method and equipment based on millimeter wave radar, a storage medium, and a movable platform, which replace the current guardrail with the characteristic parameters of the current guardrail, thereby effectively reducing the data output pressure of the guardrail reflection point .
  • Fig. 1 shows a schematic block diagram of an exemplary electronic device for implementing a millimeter-wave radar-based guardrail fitting method and system according to an embodiment of the present invention
  • FIG. 2 shows a schematic flowchart of a guardrail detection method based on millimeter wave radar according to an embodiment of the present invention
  • Figure 3 shows a schematic diagram of radar sensors detecting guardrails on both sides
  • FIG. 4 shows a schematic flowchart of a guardrail detection method based on millimeter wave radar according to another embodiment of the present invention
  • Figure 5 shows a schematic diagram of the reflection points of the guardrail in the radar detection result
  • FIG. 6 shows a schematic flowchart of a guardrail detection method based on millimeter wave radar according to another embodiment of the present invention
  • Fig. 7 shows a schematic diagram of the coordinate system definition in the fitting method shown in Fig. 6;
  • FIG. 8 shows a schematic diagram of calculating the distance and speed of the reflection point of the guardrail in the detection method shown in FIG. 6;
  • FIG. 9 shows a schematic diagram of filtering the guardrail recognition area of the distance Doppler image
  • Fig. 10 shows a schematic diagram of performing coordinate transformation on the filtered pixels in Fig. 9;
  • FIG. 11 shows a schematic flowchart of a method for evaluating a target own lane based on guardrail recognition according to another embodiment of the present invention
  • Fig. 12 shows a schematic block diagram of a guardrail detection device based on millimeter wave radar according to an embodiment of the present invention.
  • the electronic device 100 includes one or more processors 102, one or more storage devices 104, an input/output device 106, a communication interface 108, and a radar sensor 110. These components pass through a bus system 112 and/or other components. A form of connection mechanism (not shown) is interconnected. It should be noted that the components and structure of the electronic device 100 shown in FIG. 1 are only exemplary and not restrictive. According to needs, the electronic device may also have other components and structures, or may not include some of the aforementioned components.
  • the processor 102 generally represents any type or form of processing unit capable of processing data or interpreting and executing instructions.
  • the processor can be a central processing unit (CPU), an image processing unit (GPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), an encoder, an image signal processor (ISP), or Other forms of processing units having data processing capabilities and/or instruction execution capabilities, and can control other components in the electronic device 100 to perform desired functions.
  • the processor 102 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 102 may receive instructions from software applications or modules. These instructions may cause the processor 102 to complete the method described and/or shown herein for hybrid navigation of a degree device and the self-moving device and method.
  • the storage device 104 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the volatile memory may include random access memory, for example
  • the non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, and the like.
  • One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 102 may run the program instructions to implement the client functions (implemented by the processor) in the embodiments of the present invention described below. And/or other desired functions.
  • client functions implemented by the processor
  • Various application programs and various data can also be stored in the computer-readable storage medium.
  • the input/output device 106 may be a device used by the user to input instructions and output various information to the outside.
  • the input device may include one or more of a keyboard, a mouse, a microphone, and a touch screen.
  • the output device may include one or more of a display, a speaker, and the like.
  • the communication interface 108 broadly represents any type or form of adapter or communication device capable of facilitating communication between the example electronic device 100 and one or more additional devices.
  • the communication interface 108 can facilitate communication between the electronic device 100 and a front-end or accessory electronic device, and a back-end server or cloud.
  • Examples of the communication interface 108 include, but are not limited to, a wired network interface (such as a network interface card), a wireless network interface (such as a wireless network interface card), a modem, a universal serial interface (USB), an HDMI interface, and any other suitable interface.
  • the communication interface 108 provides a direct connection to a remote server/remote head-end device through a direct connection to a network such as the Internet.
  • the communication interface 108 provides a direct connection to a remote server/remote front-end device through a direct connection to a network such as a private network.
  • the communication interface 108 may also indirectly provide such a connection through any other suitable connection.
  • the radar sensor 110 may be various suitable radar sensors.
  • the radar sensor 110 is a millimeter wave radar sensor.
  • the millimeter wave radar sensor includes, for example, a line, a transceiver module, and a signal processing module.
  • the transceiver module includes, for example, a linear VCO, an amplifier, a balanced mixer, etc., of course.
  • the millimeter wave radar sensor may also include other structures, and the structure of the radar sensor 110 is not particularly limited in this application.
  • the guardrail beside the road will form a large number of reflection points in the millimeter wave radar.
  • the millimeter wave radar system is limited by the processing power and memory capacity, and the number of reflection points that can detect the output is limited. Scattering points on the guardrail will reduce the ability to detect other objects of interest (for example, vehicles in blind spots). At the same time, too many reflection points will bring greater data output pressure.
  • this application proposes a guardrail fitting method based on millimeter wave radar to reduce data output pressure. The following describes the guardrail detection method based on the millimeter wave radar according to the embodiment of the present invention with reference to FIGS. 2 to 5.
  • the guardrail in this application can include continuous obstacles on one or both sides of the road, or on one or both sides of the middle lane of the road, and specifically can be, for example, stone piers on both sides of a highway,
  • the fences separated in the middle of the two-way lanes, the continuous warning roadblocks placed for temporary road maintenance, etc., the present invention does not limit the specific form of the guardrails.
  • Fig. 2 shows a schematic flowchart of a guardrail detection method based on millimeter wave radar according to an embodiment of the present invention
  • Fig. 3 shows a schematic diagram of a radar sensor detecting guardrails on both sides.
  • the method disclosed in this embodiment includes:
  • Step 201 Transmit a millimeter wave radar signal, and receive an echo signal reflected by the target.
  • the millimeter wave signal is transmitted by the millimeter wave radar sensor and the echo signal reflected by the target is received.
  • the detection range of the millimeter wave radar sensor is shown in FIG. 3.
  • step 202 the echo signal is processed to obtain the reflection point of the guardrail.
  • the guardrail reflection point based on the echo signal may include parameters such as the coordinates of the guardrail in the radar detection coordinate system or the distance from the vehicle.
  • Step 203 Determine the guardrail model according to the guardrail reflection point, and then determine and output the characteristic parameters of the current guardrail to represent the current guardrail.
  • step S202 fitting is performed according to the parameters of the guardrail reflection point, such as coordinates and other data, so as to obtain the determined guardrail model and the parameters of the model, and then output the characteristic parameters of the guardrail to indicate the current guardrail.
  • the parameters of the guardrail reflection point such as coordinates and other data
  • the characterizing parameter includes the parameters of the guardrail model and the coordinates of the starting point and the ending point in the reflection point of the guardrail.
  • the parameters of the guardrail model include, for example, the size of each coefficient in the model.
  • the shape and position of the current guardrail can be determined by the guardrail parameters and the coordinates of the starting point and the end point in the guardrail reflection point. Because there is no need to output all reflection points to indicate the detected guardrail, the data output pressure is greatly reduced to avoid affecting the radar sensor's ability to detect other targets of interest.
  • Fig. 4 shows a schematic flowchart of a guardrail detection method based on millimeter wave radar according to another embodiment of the present invention
  • Fig. 5 shows a schematic diagram of reflection points of the guardrail in the radar detection result.
  • the method disclosed in this embodiment includes:
  • Step 401 Transmit a millimeter wave radar signal, and receive an echo signal reflected by the target.
  • the millimeter wave signal is transmitted by the millimeter wave radar sensor and the echo signal reflected by the target is received.
  • the detection range of the millimeter wave radar sensor is shown in FIG. 3.
  • Step 402 Process the echo signal to obtain a detection result of the target, and the detection result includes a plurality of reflection points.
  • a processing method commonly used in the art can be used to process the echo signal to obtain the detection result of the target.
  • the guardrail appears as a large number of reflection points in the detection result of the millimeter wave radar sensor. . Some of these reflection points are guardrail reflection points, and some are not.
  • Step 403 Filter reflection points of the guardrail from the detection result according to the characteristics of the guardrail.
  • the reflection points of the guardrail need to be filtered from the detection result according to the characteristics of the guardrail.
  • the method for screening the reflection points of the guardrail from the detection results according to the characteristics of the guardrail is as follows: First, determine whether the reflection point is stationary relative to the ground according to the information of the echo signal corresponding to the reflection point. Since the guardrail is stationary relative to the ground, the reflection point of the guardrail is also stationary relative to the ground. The speed of the reflection point can be determined according to the information of the echo signal corresponding to the reflection point, and then the speed of the reflection point relative to the ground can be determined according to the speed and the vehicle speed. If the relative ground speed of the reflection point is 0, it means that the reflection point is 0. The reflection point may be a guardrail reflection point; otherwise, it means that the reflection point is not a guardrail reflection point.
  • the distance information of the reflection point can be determined according to the information of the echo signal corresponding to the reflection point, such as the distance information from the vehicle, and then the distance between the reflection point and the adjacent reflection point can be obtained according to the distance information of each reflection point. If the distance between the reflection point and the adjacent reflection point is greater than the set threshold, it means that the reflection point is far away from the adjacent reflection point, which may not be the reflection point of the guardrail, otherwise it is the possibility of the reflection point of the guardrail Larger.
  • the above analysis is combined to determine whether the reflection point is a guardrail reflection point. For example, if the reflection point is stationary relative to the ground and the distance between the reflection point and the adjacent reflection point is less than a set threshold, it is determined that the reflection point is a guardrail reflection point.
  • Step 404 Determine a guardrail model according to the guardrail reflection point, and then determine and output the characteristic parameters of the current guardrail to represent the current guardrail.
  • step 403 After determining the reflection point of the guardrail from the reflection point, fit according to the parameters of the reflection point of the guardrail, such as coordinates, etc., to obtain the determined guardrail model and the parameters of the model, and then output the characteristic parameters of the guardrail to indicate the current Guardrail.
  • the characterizing parameter includes the parameters of the guardrail model and the coordinates of the starting point and the ending point in the reflection point of the guardrail.
  • the parameters of the guardrail model include, for example, the size of each coefficient in the model.
  • the shape and position of the current guardrail can be determined by the guardrail parameters and the coordinates of the starting point and the end point in the guardrail reflection point. Because there is no need to output all reflection points to indicate the detected guardrail, the data output pressure is greatly reduced to avoid affecting the radar sensor's ability to detect other targets of interest.
  • guardrail models are preset and fitted separately, and then the optimal guardrail model is selected.
  • the method for determining the guardrail model according to the guardrail reflection point is:
  • the screened guardrail reflection points are respectively fitted according to the preset guardrail models to obtain the parameters and fitting residuals of each guardrail model. That is, according to the parameters of the guardrail reflection point, such as coordinates, the preset guardrail models are respectively fitted to obtain the parameters of each guardrail model, and then the fitting residual of each guardrail model is calculated.
  • the preset guardrail model includes a straight line model, a quadratic polynomial model, a circular curve model, or a clothoid curve model.
  • the guardrail model with the smallest fitting residual is selected from all guardrail models as the currently detected guardrail model. After the fitting residuals of each guardrail model are obtained, the guardrail model with the smallest fitting residual is selected as the previously detected guardrail model.
  • a schematic diagram of the guardrail can be generated based on the parameters of the guardrail model with the smallest fitting residual and the coordinates of the starting point and the end point in the reflection point of the guardrail, thereby facilitating the user
  • the straight pipe knows the shape and position of the guardrail.
  • the guardrail detection method based on millimeter wave radar realizes the parametrization and automation of guardrail fitting, and replaces all guardrail reflection points with guardrail model parameters and the coordinates of the starting point and end point of the guardrail reflection point to represent the guardrail. Effectively reduce the data output pressure of the guardrail reflection point, and preset multiple guardrail models to fit separately and select the optimal model from them.
  • the optimal guardrail fitting model can be automatically selected to adapt to a variety of scenarios and improve the accuracy of guardrail fitting And robustness.
  • the guardrail fitting is mainly by clustering the static reflection points, and then fitting the guardrail curve.
  • the clustering effect of static reflection points is seriously affected by the accuracy of radar angle measurement and multipath effects.
  • the accuracy of the radar angle measurement is not high or there is a multipath effect (the angle measurement results will have a large deviation)
  • the static reflection points are difficult to be clustered, and this will make the guardrail difficult to be identified and fitted.
  • this method first needs to perform CFAR, MUSIC angle measurement, clustering and other algorithms for static reflection points. The computational complexity of these algorithms is high, which will increase the performance requirements of the processor and cause costs. high.
  • the present application also provides a guardrail detection method based on millimeter wave radar, which uses distance Doppler information and the hidden relationship between the guardrail space position and the vehicle speed to detect and fit the guardrail.
  • Using this detection method can greatly improve the radar's ability to detect and fit guardrails without increasing the cost of radar hardware and antenna performance.
  • the computational complexity of the detection method is far less than that of the traditional method.
  • the guardrail detection method will be described below with reference to FIGS. 6 to 10.
  • FIG. 6 shows a schematic flowchart of a guardrail detection method based on millimeter wave radar according to another embodiment of the present invention
  • FIG. 7 shows a schematic diagram of the coordinate system definition in the fitting method shown in FIG. 6
  • Fig. 9 shows a schematic diagram of filtering the guardrail recognition area of the distance Doppler image
  • Fig. 10 shows the coordinate transformation of the filtered pixels in Fig. 9 Schematic.
  • the method for calculating the lateral distance of the guardrail reflection point is:
  • the true relative speed V real between it and the radar is the speed of the vehicle.
  • the size and direction of the vehicle are opposite to the direction of the speed of the vehicle. That is, the following relationship is satisfied:
  • the radar reflection point velocity V doppier actually measured by the radar is the component of V real between the radar center and the reflection point. This velocity is called the radial velocity.
  • the distance R radial of the guardrail reflection point actually measured by the radar is the distance between the guardrail reflection point and the center of the radar. This distance is called the radial distance.
  • the lateral distance R x of the reflection point of the guardrail, the radial distance R radial , the radial speed V doppier and the self-vehicle speed V vehicle satisfy the following relationship (sine and cosine formula)
  • the lateral distance R x can be calculated by the following formula:
  • the method disclosed in this embodiment includes:
  • Step 401 Process the echo signal to obtain a range Doppler image.
  • the range Doppler image is an image obtained by performing two-dimensional FFT processing on the radar receiving end intermediate frequency time domain signal modulated according to the fast sawtooth waveform, as shown in the left image in Figure 9, the horizontal axis represents the distance, The vertical axis represents speed.
  • the x coordinate of each pixel represents the radial distance between the reflection point and the radar, the y coordinate represents the radial relative velocity between the reflection point and the radar (Doppler effect), and the value represents the reflection intensity of the reflection point .
  • the color in the range Doppler image represents the reflection intensity.
  • red and blue are used as an example. The redder means the stronger the reflection intensity, and the bluer means the weaker the reflection intensity.
  • Step 402 Determine a guardrail recognition area on the distance Doppler image based on the vehicle speed.
  • the curve in the box is generated by the guardrail, and the curve equation can be derived from Equation 1.
  • Equation 3 the curve relationship between V doppier and R radial can be obtained. It can also be seen from Equation 3 that the guardrail curve on the range Doppler image is determined by two parameters, R x and V vehicle.
  • the method for determining the guardrail recognition area on the distance Doppler image based on the vehicle speed is: firstly, define the maximum speed of the pixels in the guardrail recognition area based on the vehicle speed; then, based on the vehicle speed Speed defines the minimum speed of pixels in the guardrail recognition area; next, set the maximum distance of pixels in the guardrail recognition area; next, set the minimum distance of pixels in the guardrail recognition area; finally, according to the maximum speed, minimum speed, The maximum distance and the minimum distance determine the guardrail recognition area.
  • the maximum speed V max of the pixel in the guardrail recognition area is the vehicle speed V vehicle minus the preset value V offset
  • the minimum speed is the vehicle speed V vehicle multiplied by the preset value A
  • the set maximum distance and minimum are R max and R min respectively
  • the guardrail recognition area is expressed as:
  • V max V vehicle -V offset
  • V min V vehicle *A
  • V offset , A, B, and C are preset values, which can be determined based on experience or experiment.
  • V offset is set to 2m/s, 3m/s, 4m/s, etc.
  • A is set to 0.4
  • B is 3, 4, 5, 6, and C is 50, 60, 70, 80, etc.
  • the specific values of V offset , A, B, and C are not limited here.
  • the guardrail recognition area can be determined on the distance Doppler image through the above-mentioned relational expression.
  • the box area in the left figure in FIG. 9 is the guardrail recognition area.
  • Some of the pixels in this area are reflection points of the guardrail, and some are not.
  • Step 403 Perform filtering processing on the pixels in the guardrail recognition area on the range Doppler image according to the reflection intensity, so as to retain the pixels whose reflection intensity exceeds a threshold value as the guardrail reflection points.
  • the pixels in the guardrail recognition area are filtered according to the reflection intensity, so as to retain the pixels whose reflection intensity exceeds the threshold as the guardrail Reflection point.
  • the reflection intensity filtering is performed according to the distance-reflection intensity characteristic curve of the guardrail, and only the pixels whose reflection intensity exceeds the threshold are left. point.
  • the guardrail reflection point can be obtained by filtering the pixel points in the guardrail recognition area on the distance Doppler image according to the reflection intensity.
  • Step 404 Map the pixel points whose reflection intensity exceeds the threshold value to map the pixel points whose reflection intensity exceeds the threshold value from the range Doppler coordinate system to the Cartesian coordinate system with the radar as the origin.
  • the reflection point of the guardrail is mapped according to formula 2, and the pixel point representing the reflection point of the guardrail is mapped from the distance Doppler coordinate system to the vehicle-mounted radar as shown in Figure 7.
  • the Cartesian coordinate system in order to finally do curve fitting to the mapped pixels for guardrail fitting.
  • the lateral distance of the guardrail reflection point in the Cartesian coordinate system with the radar as the origin is determined according to the speed of the guardrail reflection point measured by the radar, the driving speed of the vehicle, and the distance between the guardrail reflection point measured by the radar and the radar center.
  • R x and the longitudinal distance R y are determined according to the speed of the guardrail reflection point measured by the radar, the driving speed of the vehicle, and the distance between the guardrail reflection point measured by the radar and the radar center.
  • the lateral distance R x of each guardrail reflection point in the Cartesian coordinate system with the radar as the origin is determined according to the following formula,
  • R radial is the radial distance of the guardrail reflection point in the Cartesian coordinate system with the radar as the origin (that is, the distance from the guardrail reflection point to the radar center measured by the radar), and V doppier is the speed of the guardrail reflection point measured by the radar , V vehicle is the driving speed of the vehicle.
  • Step 405 Fit the guardrail according to the lateral distance and the longitudinal distance of the guardrail reflection point in the Cartesian coordinate system with the radar as the origin to determine the guardrail model.
  • the curve model can be a straight line, a circle, or a clothoid curve.
  • the guardrail detection method according to this embodiment can realize the detection and recognition of the guardrail by the radar without increasing the cost of radar hardware and the complexity of antenna design. Compared with traditional methods, this scheme has the advantages of low computational complexity, strong robustness, and does not rely on angle measurement accuracy, and can greatly improve the radar's ability to detect guardrails. Compared with the traditional method, the guardrail fitting method according to this embodiment greatly increases the detection accuracy of the guardrail and greatly reduces the computational complexity.
  • this application proposes a new vehicle-mounted millimeter-wave radar to determine whether the target is in its own lane, without adding radar hardware and processors, and without relying on other sensors (such as visual sensors such as cameras)
  • the vehicle-mounted millimeter-wave radar can greatly improve the accuracy of determining whether the target is in the lane in a curve.
  • FIG. 11 shows a schematic flowchart of a method for evaluating a target own lane based on guardrail recognition according to another embodiment of the present invention.
  • the method disclosed in this embodiment includes:
  • step 501 the curve parameter is obtained by fitting a cyclotron curve model according to the reflection point of the guardrail.
  • the guardrail reflection point can be obtained based on the radar echo signal according to the method disclosed in the foregoing embodiment or other methods.
  • the curve parameters are obtained by fitting according to the cyclotron curve model.
  • the curve parameters are obtained by performing curve fitting, for example, by the least square method or the like.
  • each guardrail reflection point in the Cartesian coordinate system of the car body (the center of the front is the origin, the forward direction of the car is the positive direction of the y-axis, and the right side of the car is the positive direction of the x-axis to establish the coordinate system) and
  • the number of reflection points of the guardrail is fitted according to the cyclotron curve model to obtain the curve parameters a, b and c.
  • Step 502 Calculate the distance between the vehicle and the guardrail fitting curve.
  • the distance between the vehicle and the guardrail fitting curve is determined according to the curve parameter.
  • the distance between the vehicle and the guardrail fitting curve is equal to the curve equal to c.
  • Step 503 Calculate the distance between the target and the fitting curve of the guardrail.
  • the distance between the target and the fitting curve of the guardrail is determined according to the clothoid curve model and curve parameters, as well as the ordinate and abscissa of the target.
  • Step 504 Calculate the current cycle lane evaluation value of the target according to the distance between the vehicle and the guardrail fitting curve and the distance between the target and the guardrail fitting curve.
  • the vehicle lane evaluation value of the current update cycle of the target is determined according to the distance between the vehicle and the guardrail fitting curve, the distance between the target and the guardrail fitting curve, and the lane distance determination threshold.
  • the threshold for determining the distance of the self-lane can be determined based on experience, such as 1.5 meters, 1.64 meters, 1.75 meters, 1.82 meters, and so on.
  • Step 505 Smooth the evaluation value of the target's current cycle self-lane to obtain the target current cycle smooth value.
  • the smoothing coefficient can be determined empirically, for example, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8 or 0.9.
  • Step 506 Determine whether the target is in the lane where the vehicle is located according to the current cycle smooth value of the target.
  • the target current cycle smoothing value is greater than the set threshold, it is determined that the target is in the lane where the vehicle is located, otherwise it is considered that the target is not in the lane where the vehicle is located.
  • the set threshold can be determined based on experience or experiment, for example, it can be 50, 60, 70, or 80.
  • the ability to judge whether the target is in the own lane in a curve scene has been greatly improved, and the rate of false alarms and missed detections has been greatly reduced. That is, the vehicle-mounted millimeter-wave radar has greatly increased its ability to judge whether the target is in its own lane when turning, thereby improving the robustness of the entire ADAS and AD system and improving the user experience.
  • Fig. 12 shows a schematic block diagram of a guardrail detection device based on millimeter wave radar according to an embodiment of the present invention.
  • the guardrail detection device 600 based on millimeter wave radar of this embodiment includes a millimeter wave radar sensor 610, a memory 620 and a processor 630.
  • the millimeter wave radar sensor 610 is used to transmit millimeter waves to the target area and receive the millimeter wave echo signals reflected by objects in the target area.
  • the millimeter wave radar sensor 610 can also process the echo signal to obtain the detection result or the reflection point of the guardrail.
  • the millimeter wave radar sensor 610 includes, for example, a line, a transceiver module, and a signal processing module.
  • the transceiver module includes, for example, a linear VCO, an amplifier, a balanced mixer, and the like.
  • the millimeter wave radar sensor may also include other structures.
  • One or more memories 620 are used to store one or more computer programs.
  • the one or more memories 530 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory.
  • the volatile memory may include random access memory (RAM) and/or cache memory (cache), for example.
  • the non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory and other permanent memories.
  • One or more computer program instructions can be stored on the computer-readable storage medium, and the processor can run the program instructions to implement the control method in the above-mentioned embodiment of the present invention (implemented by the processor) and / Or other desired functions.
  • 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.
  • the one or more processors 630 may be a central processing unit (CPU) or other forms of processing units with data processing capability and/or instruction execution capability, such as a microcontroller (MCU), and may control the guardrail fitting system 600 Other components to perform the desired functions.
  • CPU central processing unit
  • MCU microcontroller
  • the processor 630 may be the processor of the millimeter-wave radar sensor 610 itself; and in some embodiments, the processor 630 may also be a processor external to the millimeter-wave radar sensor 610, which is different from the millimeter wave radar sensor 610.
  • the wave radar sensor 610 is connected and processes the data generated by the millimeter wave radar sensor 610.
  • the processor 630 is the processor of the vehicle itself, rather than the processor inside the millimeter wave radar sensor 610.
  • the one or more processors 630 execute the following steps:
  • the guardrail model is determined according to the guardrail reflection point, and then the characteristic parameters of the current guardrail are determined and output to represent the current guardrail.
  • determining the guardrail model according to the guardrail reflection point includes:
  • the guardrail model with the smallest fitting residual is selected from all guardrail models as the currently detected guardrail model.
  • the characterizing parameter includes the parameters of the guardrail model and the coordinates of the starting point and the ending point in the reflection point of the guardrail.
  • processing the echo signal to obtain the reflection point of the guardrail includes:
  • the reflection points of the guardrail are screened out from the detection results according to the characteristics of the guardrail.
  • screening out the reflection points of the guardrail from the detection result according to the characteristics of the guardrail includes:
  • the reflection point is stationary with respect to the ground and the distance between the reflection point and the adjacent reflection point is less than the set threshold, it is determined that the reflection point is a guardrail reflection point.
  • processing the echo signal to obtain the reflection point of the guardrail includes:
  • Filtering processing is performed on the pixel points in the guardrail recognition area on the distance Doppler image according to the reflection intensity, so as to retain the pixel points whose reflection intensity exceeds a threshold value as the guardrail reflection point.
  • determining the guardrail recognition area on the distance Doppler image based on the vehicle speed includes:
  • the guardrail recognition area is determined according to the maximum speed, minimum speed, maximum distance and minimum distance.
  • the pixel points whose reflection intensity exceeds the threshold value are mapped to map the pixel points whose reflection intensity exceeds the threshold value from the range Doppler coordinate system to the Cartesian coordinate system with the radar as the origin.
  • mapping the pixel points whose reflection intensity exceeds the threshold value from the range Doppler coordinate system to the Cartesian coordinate system with the radar as the origin includes:
  • the method further includes: fitting the guardrail according to the lateral distance and the longitudinal distance of the guardrail reflection point in the Cartesian coordinate system with the radar as the origin to determine the guardrail model.
  • the processor is further configured to:
  • the curve parameters are obtained by fitting the cyclotron curve model
  • the target current cycle smoothing value is greater than the set threshold, it is determined that the target is in the lane where the vehicle is located, otherwise it is considered that the target is not in the lane where the vehicle is located.
  • the curve parameters are obtained by fitting according to the cyclotron curve model
  • the distance between the target and the fitting curve of the guardrail is determined according to the clothoid curve model and curve parameters, as well as the ordinate and abscissa of the target.
  • the self-lane evaluation value of the current update cycle of the target is determined according to the distance between the vehicle and the guardrail fitting curve, the distance between the target and the guardrail fitting curve, and the self-lane distance determination threshold.
  • the target current period smoothing value is determined according to the evaluation value of the own lane in the current update period, the smooth value of the previous period, and the smoothing coefficient.
  • the preset guardrail model includes a straight line model, a quadratic polynomial model, a circular curve model or a clothoid curve model.
  • the processor is further configured to:
  • a schematic diagram of the guardrail is generated based on the parameters of the guardrail model with the smallest fitting residual and the coordinates of the start point and the end point in the reflection point of the guardrail.
  • the current guardrail is represented by the characteristic parameters of the current guardrail, so that the data output pressure of the reflection point of the guardrail can be effectively reduced.
  • the guardrail detection device can realize effective radar detection of the guardrail, the detection accuracy response is improved, and the calculation complexity response is reduced.
  • the detection device has a great improvement in its ability to judge whether the target is in its own lane in a curve scene, and the rate of false alarms and missed detections has been greatly reduced.
  • a guardrail detection device based on millimeter wave radar includes a storage device and a processor.
  • a computer program run by the processor, and the computer program executes the method provided in the foregoing embodiment of the present invention when the computer program is run by the processor.
  • a storage medium on which program instructions are stored, which are used to execute the control method of the embodiment of the present invention when the program instructions are run by a computer or a processor.
  • the corresponding steps are used to implement the corresponding modules in the devices of the control system according to the embodiment of the present invention.
  • the 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.
  • the computer program instructions execute the following steps when run by the computer: transmit millimeter wave radar signals and receive echo signals reflected by the target; process the echo signals to obtain the guardrail reflection point;
  • the guardrail model is determined according to the guardrail reflection point, and then the characteristic parameters of the current guardrail are determined and output to represent the current guardrail.
  • the computer program instructions execute the following steps when being run by a computer: process the echo signal to obtain a range Doppler image; determine guardrail recognition on the range Doppler image based on the vehicle speed Area; filtering the pixels in the guardrail recognition area on the distance Doppler image according to the reflection intensity, so as to retain the pixel points whose reflection intensity exceeds a threshold value as the guardrail reflection point.
  • the computer program instructions execute the following steps when being run by a computer: according to the reflection point of the guardrail, fitting the curve model to obtain the curve parameters; calculating the distance between the vehicle and the guardrail fitting curve; calculating the target and the guardrail simulation Calculate the current cycle self-lane evaluation value of the target according to the distance between the vehicle and the guardrail fitting curve and the distance between the target and the guardrail fitting curve; smooth the current cycle self-lane evaluation value P of the target to obtain the current cycle of the target Smoothing value; judge whether the target is in the lane where the vehicle is located according to the current period smooth value of the target. If the current period smoothing value of the target is greater than the set threshold, it is determined that the target is in the lane where the vehicle is located, otherwise the target is considered not where the vehicle is located On the driveway.
  • the modules in the control system according to the embodiment of the present invention can be implemented by the processor of the electronic device according to the embodiment of the present invention running computer program instructions stored in the memory, or can be implemented in the computer program product according to the embodiment of the present invention.
  • the computer instructions stored in the computer-readable storage medium are implemented when the computer runs.
  • a movable platform which includes the guardrail fitting system or guardrail fitting device according to the embodiment of the present invention.
  • the movable platform includes a car.
  • the current guardrail is represented by the current guardrail characteristic parameters, thereby effectively reducing the data output pressure of the guardrail reflection point.
  • the disclosed device and method may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • 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 can 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 a combination of them.
  • a microprocessor or a digital signal processor may be used in practice to implement some or all of the functions of some modules according to the embodiments of the present invention.
  • 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.
  • 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 a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

Landscapes

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

Abstract

La présente invention concerne un procédé et un dispositif (100) de détection de glissière de sécurité faisant appel à un radar à ondes millimétriques, un support de stockage et une plate-forme mobile. Le procédé d'adaptation de glissière de sécurité comprend les étapes consistant à : émettre un signal radar à ondes millimétriques, et recevoir un signal d'écho réfléchi par une cible (201) ; traiter le signal d'écho pour obtenir un point de réflexion de glissière de sécurité (202) ; et déterminer un modèle de glissière de sécurité en fonction du point de réflexion de glissière de sécurité, puis déterminer et délivrer en sortie un paramètre de caractérisation de la glissière de sécurité actuelle pour représenter la glissière de sécurité actuelle (203). Grâce au procédé, la glissière de sécurité actuelle est représentée par le paramètre de caractérisation de la glissière de sécurité actuelle, de sorte que la pression de sortie de données du point de réflexion de glissière de sécurité peut être efficacement réduite.
PCT/CN2019/120981 2019-11-26 2019-11-26 Procédé et dispositif de détection de glissière de sécurité, support de stockage et plate-forme mobile WO2021102689A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/120981 WO2021102689A1 (fr) 2019-11-26 2019-11-26 Procédé et dispositif de détection de glissière de sécurité, support de stockage et plate-forme mobile
CN201980039524.2A CN112313539B (zh) 2019-11-26 2019-11-26 护栏检测方法及设备、存储介质和可移动平台

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/120981 WO2021102689A1 (fr) 2019-11-26 2019-11-26 Procédé et dispositif de détection de glissière de sécurité, support de stockage et plate-forme mobile

Publications (1)

Publication Number Publication Date
WO2021102689A1 true WO2021102689A1 (fr) 2021-06-03

Family

ID=74336557

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/120981 WO2021102689A1 (fr) 2019-11-26 2019-11-26 Procédé et dispositif de détection de glissière de sécurité, support de stockage et plate-forme mobile

Country Status (2)

Country Link
CN (1) CN112313539B (fr)
WO (1) WO2021102689A1 (fr)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113167886B (zh) * 2021-03-02 2022-05-31 华为技术有限公司 目标检测方法和装置
CN113033434A (zh) * 2021-03-30 2021-06-25 重庆长安汽车股份有限公司 一种道路点云中的护栏提取方法、装置、控制器及汽车
CN113514825A (zh) * 2021-04-23 2021-10-19 芜湖森思泰克智能科技有限公司 道路边缘的获取方法、装置和终端设备
JP2022176641A (ja) * 2021-05-17 2022-11-30 日立Astemo株式会社 レーダ装置
WO2023236112A1 (fr) * 2022-06-08 2023-12-14 华为技术有限公司 Procédé, appareil et terminal de détermination de type de fausse alarme cible

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000105276A (ja) * 1998-09-29 2000-04-11 Mitsubishi Electric Corp ミリ波レーダ装置
CN104937436A (zh) * 2013-02-01 2015-09-23 三菱电机株式会社 雷达装置
CN105000019A (zh) * 2014-04-15 2015-10-28 通用汽车环球科技运作有限责任公司 用于检测、追踪和估计静止的路边物体的方法和系统
CN109035759A (zh) * 2018-06-13 2018-12-18 重庆邮电大学 一种护栏检测评估方法
CN109254289A (zh) * 2018-11-01 2019-01-22 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

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
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
CN110058239B (zh) * 2019-04-29 2023-08-01 上海保隆汽车科技股份有限公司 一种车载毫米波雷达装置及目标探测方法
CN110146899A (zh) * 2019-05-28 2019-08-20 许灵男 一种路端雷达障碍物感知系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000105276A (ja) * 1998-09-29 2000-04-11 Mitsubishi Electric Corp ミリ波レーダ装置
CN104937436A (zh) * 2013-02-01 2015-09-23 三菱电机株式会社 雷达装置
CN105000019A (zh) * 2014-04-15 2015-10-28 通用汽车环球科技运作有限责任公司 用于检测、追踪和估计静止的路边物体的方法和系统
CN109035759A (zh) * 2018-06-13 2018-12-18 重庆邮电大学 一种护栏检测评估方法
CN109254289A (zh) * 2018-11-01 2019-01-22 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

Also Published As

Publication number Publication date
CN112313539B (zh) 2024-03-15
CN112313539A (zh) 2021-02-02

Similar Documents

Publication Publication Date Title
WO2021102689A1 (fr) Procédé et dispositif de détection de glissière de sécurité, support de stockage et plate-forme mobile
WO2020007235A1 (fr) Procédé et appareil de détection de place de stationnement, et support et dispositif
US9563808B2 (en) Target grouping techniques for object fusion
Kellner et al. Instantaneous lateral velocity estimation of a vehicle using Doppler radar
WO2021097618A1 (fr) Procédé et système de segmentation de nuage de points, et support d'enregistrement informatique
US9298992B2 (en) Geographic feature-based localization with feature weighting
WO2018177026A1 (fr) Dispositif et procédé de détermination d'un bord de route
US11960028B2 (en) Determining specular reflectivity characteristics using LiDAR
CN112562314B (zh) 基于深度融合的路端感知方法、装置、路端设备和系统
CN108859952B (zh) 车辆变道预警方法、装置和雷达
JP6659367B2 (ja) 物体検出装置および物体検出方法
US20150120244A1 (en) Method and apparatus for road width estimation
Han et al. Road boundary detection and tracking for structured and unstructured roads using a 2D lidar sensor
WO2020199010A1 (fr) Procédé de détection de suivi basé sur un radar à ondes millimétriques, radar à ondes millimétriques et véhicule
CN110632617A (zh) 一种激光雷达点云数据处理的方法及装置
CA3050586A1 (fr) Detection d'objet fondee sur l'intensite du lidar
CN113391305B (zh) 多雷达融合的虚假目标抑制方法、装置及终端设备
JP6411933B2 (ja) 車両状態判定装置
CN109871659B (zh) 一种超声波雷达的仿真方法及系统
CN108693517B (zh) 车辆定位方法、装置和雷达
JP6919764B2 (ja) レーダ画像処理装置、レーダ画像処理方法、および、プログラム
CN114550142A (zh) 基于4d毫米波雷达和图像识别融合的车位检测方法
CN111413701A (zh) 一种障碍物距离的确定方法、装置、车载设备及存储介质
US11681038B2 (en) Reducing radar signal interference based on semi-random and random configuration
CN117169848A (zh) 过滤玻璃噪点的方法、激光雷达及机器人

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: 19953751

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: 19953751

Country of ref document: EP

Kind code of ref document: A1