WO2021102689A1 - Guardrail detection method and device, storage medium, and movable platform - Google Patents

Abstract

A millimeter wave radar-based guardrail detection method and device (100), a storage medium, and a movable platform. The guardrail fitting method comprises: emitting a millimeter wave radar signal, and receiving an echo signal reflected by a target (201); processing the echo signal to obtain a guardrail reflection point (202); and determining a guardrail model according to the guardrail reflection point, and then determining and outputting a characterization parameter of the current guardrail for representing the current guardrail (203). According to the method, the current guardrail is represented by the characterization parameter of the current guardrail, so that the data output pressure of the guardrail reflection point can be effectively reduced.

Description

Guardrail detection method and equipment, storage medium and movable platform

Manual

Technical field

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.

Background technique

In recent years, 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. However, 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. On the other hand, the shape of the guardrail changes with the curve of the road, so a single guardrail fitting model cannot meet the demand.

Summary of the invention

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.

Specifically, the embodiment of the present invention provides a guardrail detection method based on millimeter wave radar, which includes:

Transmit millimeter-wave radar signals and receive echo signals reflected by the target;

Processing the echo signal to obtain the reflection point of the guardrail;

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 .

Description of the drawings

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;

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;

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;

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.

Detailed ways

In order to make the objectives, technical solutions, and advantages of the present invention more obvious, the exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited by the exemplary embodiments described herein. Based on the embodiments of the present invention described in the present invention, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present invention.

In the following description, a lot of specific details are given in order to provide a more thorough understanding of the present invention. However, it is obvious to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features known in the art are not described.

It should be understood that the present invention can be implemented in different forms and should not be construed as being limited to the embodiments presented here. On the contrary, the provision of these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the present invention to those skilled in the art.

The purpose of the terms used here is only to describe specific embodiments and not as a limitation of the present invention. When used herein, the singular forms "a", "an" and "the/the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "composition" and/or "including", when used in this specification, determine the existence of the described features, integers, steps, operations, elements and/or components, but do not exclude one or more other The existence or addition of features, integers, steps, operations, elements, parts, and/or groups. As used herein, the term "and/or" includes any and all combinations of related listed items.

In order to thoroughly understand the present invention, detailed steps and detailed structures will be presented in the following description to explain the technical solutions proposed by the present invention. However, in addition to these detailed descriptions, the present invention may also have other embodiments.

First, with reference to FIG. 1, an example electronic device 100 for implementing an example electronic device of a millimeter wave radar-based guardrail detection method and device according to an embodiment of the present invention will be described. As shown in FIG. 1, 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. Generally speaking, 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. For example, 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. In certain embodiments, 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

(RAM) and/or high-speed buffer memory (cache), etc. 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. 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 input/output device 106 may be a device used by the user to input instructions and output various information to the outside. For example, 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. For example, 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. In an embodiment, 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. In a specific embodiment, 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. Exemplarily, in this embodiment, 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.

As mentioned above, the guardrail beside the road will form a large number of reflection points in the millimeter wave radar. Generally speaking, 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. Based on this, 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.

It should be noted that 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.

As shown in Figure 2, the method disclosed in this embodiment includes:

Step 201: Transmit a millimeter wave radar signal, and receive an echo signal reflected by the target.

Exemplarily, 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.

In step 202, the echo signal is processed to obtain the reflection point of the guardrail.

Exemplarily, various suitable echo signal processing methods are used to obtain the guardrail reflection point based on the echo signal. The obtained reflection point of the guardrail 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.

When the guardrail reflection point is obtained in 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.

Exemplarily, 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. Illustratively, the guardrail model is linear y=ax+b, and the guardrail parameters include the sizes of a and b, and the starting point and The coordinates of the end point. 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.

As shown in Figure 4, the method disclosed in this embodiment includes:

Step 401: Transmit a millimeter wave radar signal, and receive an echo signal reflected by the target.

Exemplarily, 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.

Exemplarily, a processing method commonly used in the art can be used to process the echo signal to obtain the detection result of the target. As shown in FIG. 5, 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.

After the reflection points are obtained in step 402, the reflection points of the guardrail need to be filtered from the detection result according to the characteristics of the guardrail.

Exemplarily, 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.

Secondly, whether the distance between the reflection point and the adjacent reflection point is less than a set threshold. Since the relative distances between all reflection points of the guardrail are relatively close, it can be judged whether the reflection point is a guardrail reflection point by judging whether the distance between the reflection point and the adjacent reflection point is less than a set threshold. Exemplarily, 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.

Finally, 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.

When in 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.

Exemplarily, 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. Illustratively, the guardrail model is linear y=ax+b, and the guardrail parameters include the sizes of a and b, and the starting point and The coordinates of the end point. 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.

Further, in this embodiment, in order to avoid the problem of poor applicability of a single guardrail model, in this embodiment, multiple guardrail models are preset and fitted separately, and then the optimal guardrail model is selected.

Exemplarily, the method for determining the guardrail model according to the guardrail reflection point is:

First, 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. Exemplarily, the preset guardrail model includes a straight line model, a quadratic polynomial model, a circular curve model, or a clothoid curve model.

Secondly, 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.

Further, in this embodiment, after the guardrail model is determined, 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 according to this embodiment 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.

Further, in the above-mentioned embodiment, the guardrail fitting is mainly by clustering the static reflection points, and then fitting the guardrail curve. However, the clustering effect of static reflection points is seriously affected by the accuracy of radar angle measurement and multipath effects. When 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. And there is the problem of high computational complexity, because 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.

In view of this, 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. At the same time, 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.

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.

First, the definition of the coordinate system in this embodiment will be described with reference to FIG. 7. As shown in Figure 7, in this embodiment, since the vehicle-mounted radar is installed directly in front of the vehicle, the center of the vehicle-mounted radar is taken as the origin, and the normal direction of the radar beam is the positive direction of the y-axis, and then the right-hand system is established. Cartesian coordinate system.

Next, as shown in Figure 8, in this embodiment, the method for calculating the lateral distance of the guardrail reflection point is:

Since the reflection point of the guardrail is stationary to the ground, 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:

V _real ＝-V _vehicle

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)

(Rx/R_radial)^2+(V_doppler/V_vehicle)^2=1 (Equation 1)

Therefore, the lateral distance R _x can be calculated by the following formula:

Based on the above definition, the guardrail detection method of this embodiment will be described in conjunction with FIG. 6 and FIG. 9 and FIG. 10.

As shown in FIG. 6, the method disclosed in this embodiment includes:

Step 401: Process the echo signal to obtain a range Doppler image.

Specifically, 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 . Exemplarily, the color in the range Doppler image represents the reflection intensity. For example, 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.

As shown in the left figure of Figure 9, the curve in the box is generated by the guardrail, and the curve equation can be derived from Equation 1.

From 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.

Exemplarily, in this embodiment, 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.

Exemplarily, for example, 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 The distances are R _max and R _{min respectively} , and the guardrail recognition area is expressed as:

V _{max =} V _vehicle -V _offset ,

V _{min =} V _vehicle *A,

R _min ＝B

R _max ＝C

Among them, V _offset , A, B, and C are preset values, which can be determined based on experience or experiment. For example, for example, V _{offset is set to} 2m/s, 3m/s, 4m/s, etc., and A is set to 0.4 , 0.5, 0.6, etc., 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. For example, 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.

After the guardrail recognition area on the distance Doppler image is determined in step 402, 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.

Exemplarily, as shown in FIG. 9, for the pixels in the guardrail recognition area on the distance Doppler image, 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.

When the guardrail reflection point is obtained from the distance Doppler image, 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. In the Cartesian coordinate system, in order to finally do curve fitting to the mapped pixels for guardrail fitting.

Specifically, 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 .

_{Exemplarily, 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,

According to the formula

_{Determine the lateral distance R y of} each guardrail reflection point in the Cartesian coordinate system with the radar as the origin,

Among them, 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.

Exemplarily, for example, using the least squares method for curve fitting, 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.

Furthermore, in the practical application of vehicle-mounted millimeter-wave radar, it is the core competitiveness of millimeter-wave radar to accurately determine whether the target is in its own lane. However, in the case of a curve, the delay effect of entering and exiting the curve and the accuracy of the vehicle's sensor are caused by the millimeter wave. The radar cannot accurately determine whether the target vehicle is in its own lane. This will lead to a significant increase in the false alarm and missed detection rates of the ADAS system and the AD system in the case of a curve, which will bring safety hazards. In view of this, 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) In the case of using millimeter-wave radar to detect and identify guardrails or roadsides, the vehicle-mounted millimeter-wave radar can greatly improve the accuracy of determining whether the target is in the lane in a curve. In the following, a method for evaluating a target own lane based on guardrail recognition according to an embodiment of the present invention will be described with reference to FIG. 11.

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.

As shown in FIG. 11, the method disclosed in this embodiment includes:

In 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. After the guardrail reflection point is obtained, the curve parameters are obtained by fitting according to the cyclotron curve model. Exemplarily, the curve parameters are obtained by performing curve fitting, for example, by the least square method or the like.

Exemplarily, the clothoid curve model is expressed as y=a*x ³ +b*x ² +c;

According to the vertical and horizontal coordinates of 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.

Specifically, the distance between the vehicle and the guardrail fitting curve is determined according to the curve parameter. Illustratively, taking y=a*x ³ +b*x ² +c as an example, for example, 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.

Specifically, 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.

Specifically, 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. , Where 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.

Determine the target current period smoothing value 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. Wherein, 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.

Among them, if 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.

According to the method for evaluating a target's own lane based on guardrail recognition according to an embodiment of the present invention, 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.

As shown in FIG. 12, 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. Of course, 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.

It should be understood that in some embodiments, 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. For example, the processor 630 is the processor of the vehicle itself, rather than the processor inside the millimeter wave radar sensor 610.

When the one or more computer programs are executed by the one or more processors 630, the one or more processors 630 execute the following steps:

Processing the echo signal to obtain the reflection point of the guardrail;

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.

Exemplarily, determining the guardrail model according to the guardrail reflection point includes:

Fit the screened guardrail reflection points separately according to the preset guardrail model to obtain the parameters and fitting residuals of each guardrail model;

The guardrail model with the smallest fitting residual is selected from all guardrail models as the currently detected guardrail model.

Exemplarily, 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.

Exemplarily, processing the echo signal to obtain the reflection point of the guardrail includes:

Processing the echo signal to obtain a detection result of the target, and the detection result includes a plurality of reflection points;

The reflection points of the guardrail are screened out from the detection results according to the characteristics of the guardrail.

Exemplarily, screening out the reflection points of the guardrail from the detection result according to the characteristics of the guardrail includes:

Determining whether the reflection point is stationary relative to the ground according to the information of the echo signal corresponding to the reflection point; and

Whether the distance between the reflection point and the adjacent reflection point is less than a set threshold,

If 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.

Exemplarily, processing the echo signal to obtain the reflection point of the guardrail includes:

Processing the echo signal to obtain a range Doppler image;

Determining a guardrail recognition area on the distance Doppler image based on the vehicle speed;

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.

Exemplarily, determining the guardrail recognition area on the distance Doppler image based on the vehicle speed includes:

Define the maximum speed of pixels in the guardrail recognition area based on the vehicle speed;

Define the minimum speed of pixels in the guardrail recognition area based on the vehicle speed;

Set the maximum distance of pixels in the guardrail recognition area;

Set the minimum distance of pixels in the guardrail recognition area; and

The guardrail recognition area is determined according to the maximum speed, minimum speed, maximum distance and minimum distance.

Exemplarily, it also includes:

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.

Exemplarily, 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:

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 horizontal distance and the longitudinal distance of the guardrail reflection point in the Cartesian coordinate system with the radar as the origin are determined . Exemplarily, 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.

Exemplarily, the processor is further configured to:

According to the reflection point of the guardrail, the curve parameters are obtained by fitting the cyclotron curve model;

Calculate the distance between the vehicle and the guardrail fitting curve;

Calculate the distance between the target and the fitting curve of the guardrail;

According to the distance between the vehicle and the guardrail fitting curve and the distance between the target and the guardrail fitting curve, calculate the target's current cycle lane evaluation value;

Smoothing the evaluation value of the target's current cycle self-lane to obtain the target current cycle smoothing value Pn;

Determine whether the target is in the lane of the vehicle according to the current cycle smooth value of the target,

Among them, if 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.

Exemplarily, according to the ordinate and abscissa of each guardrail reflection point in the Cartesian coordinate system of the vehicle body and the number of guardrail reflection points, the curve parameters are obtained by fitting according to the cyclotron curve model,

Determine the distance between the vehicle and the guardrail fitting curve according to the curve parameters.

Exemplarily, 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.

Exemplarily, 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.

Exemplarily, 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.

Exemplarily, the preset guardrail model includes a straight line model, a quadratic polynomial model, a circular curve model or a clothoid curve model.

Exemplarily, 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.

According to the guardrail fitting system of this embodiment, 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.

Further, the guardrail detection device according to this embodiment can realize effective radar detection of the guardrail, the detection accuracy response is improved, and the calculation complexity response is reduced.

Furthermore, the detection device according to this embodiment 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.

In addition, according to an embodiment of the present invention, there is also provided a guardrail detection device based on millimeter wave radar. The 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.

In addition, according to an embodiment of the present invention, there is also provided 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.

In one embodiment, 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.

In one embodiment, 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.

In one embodiment, 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.

In addition, according to an embodiment of the present invention, a movable platform is also provided, which includes the guardrail fitting system or guardrail fitting device according to the embodiment of the present invention. The movable platform includes a car.

According to the millimeter-wave radar-based guardrail detection method and device, storage medium, and movable platform according to the embodiment of the present invention, the current guardrail is represented by the current guardrail characteristic parameters, thereby effectively reducing the data output pressure of the guardrail reflection point.

Although the exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above-described exemplary embodiments are merely exemplary, and are not intended to limit the scope of the present invention thereto. Those of ordinary skill in the art can make various changes and modifications therein without departing from the scope and spirit of the present invention. All these changes and modifications are intended to be included within the scope of the present invention as claimed in the appended claims.

A person of ordinary skill in the art may realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered as going beyond the scope of the present invention.

In the several embodiments provided in this application, it should be understood that the disclosed device and method may be implemented in other ways. For example, the device embodiments described above are only 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 can be combined or It can be integrated into another device, or some features can be ignored or not implemented.

In the instructions provided here, a lot of specific details are explained. However, it can be understood that the embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures, and technologies are not shown in detail, so as not to obscure the understanding of this specification.

Similarly, it should be understood that in order to simplify the present invention and help understand one or more of the various aspects of the invention, in the description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together into a single embodiment. , Or in its description. However, the method of the present invention should not be interpreted as reflecting the intention that the claimed present invention requires more features than those explicitly stated in each claim. More precisely, as reflected in the corresponding claims, the point of the invention is that the corresponding technical problems can be solved with features that are less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are thus explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present invention.

Those skilled in the art can understand that, in addition to mutual exclusion between the features, any combination of all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and any method or device disclosed in this way can be used in any combination. Processes or units are combined. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

In addition, those skilled in the art can understand that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments means that they are within the scope of the present invention. Within and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

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. Those skilled in the art should understand that a microprocessor or a digital signal processor (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. 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 a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the present invention, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be constructed as a limitation to the claims. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims listing several devices, several of these devices may be embodied in the same hardware item. The use of the words first, second, and third, etc. do not indicate any order. These words can be interpreted as names.

The above are only specific embodiments of the present invention or descriptions of specific embodiments. The protection scope of the present invention is not limited thereto. Any person skilled in the art can easily fall within the technical scope disclosed by the present invention. Any change or replacement should be included in the protection scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (37)

1. A guardrail detection method based on millimeter wave radar, which is characterized in that it includes:

   Transmit millimeter-wave radar signals and receive echo signals reflected by the target;

   Processing the echo signal to obtain the reflection point of the guardrail;

   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.
2. The method according to claim 1, wherein determining the guardrail model according to the guardrail reflection point comprises:

   Fit the screened guardrail reflection points separately according to the preset guardrail model to obtain the parameters and fitting residuals of each guardrail model;

   The guardrail model with the smallest fitting residual is selected from all guardrail models as the currently detected guardrail model.
3. The method according to claim 1, wherein the characterizing parameters include the parameters of the guardrail model and the coordinates of the starting point and the ending point in the reflection point of the guardrail.
4. The method according to claim 1, wherein processing the echo signal to obtain a reflection point of a guardrail comprises:

   Processing the echo signal to obtain a detection result of the target, and the detection result includes a plurality of reflection points;

   The reflection points of the guardrail are screened out from the detection results according to the characteristics of the guardrail.
5. The method according to claim 4, wherein the screening of the reflection points of the guardrail from the detection result according to the characteristics of the guardrail comprises:

   Determining whether the reflection point is stationary relative to the ground according to the information of the echo signal corresponding to the reflection point; and

   Whether the distance between the reflection point and the adjacent reflection point is less than a set threshold,

   If 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.
6. The method according to claim 1, wherein processing the echo signal to obtain a reflection point of a guardrail comprises:

   Processing the echo signal to obtain a range Doppler image;

   Determining a guardrail recognition area on the distance Doppler image based on the vehicle speed;

   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.
7. The method according to claim 6, characterized in that determining the guardrail recognition area on the distance Doppler image based on the vehicle speed comprises:

   Define the maximum speed of pixels in the guardrail recognition area based on the vehicle speed;

   Define the minimum speed of pixels in the guardrail recognition area based on the vehicle speed;

   Set the maximum distance of pixels in the guardrail recognition area;

   Set the minimum distance of pixels in the guardrail recognition area; and

   The guardrail recognition area is determined according to the maximum speed, minimum speed, maximum distance and minimum distance.
8. The method according to claim 6, further comprising:

   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.
9. 8. The method according to claim 8, wherein the mapping of the pixel points whose reflection intensity exceeds a threshold value from a range Doppler coordinate system to a Cartesian coordinate system with a radar as the origin comprises:

   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 horizontal distance and the longitudinal distance of the guardrail reflection point in the Cartesian coordinate system with the radar as the origin are determined .
10. The method according to claim 9, further comprising:

    Fit the guardrail according to the horizontal 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.
11. The method according to claim 1, further comprising:

    According to the reflection point of the guardrail, the curve parameters are obtained by fitting the cyclotron curve model;

    Calculate the distance between the vehicle and the guardrail fitting curve;

    Calculate the distance between the target and the fitting curve of the guardrail;

    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;

    Smooth the evaluation value of the target's current cycle of the self-lane to obtain the target's current cycle smooth value;

    Determine whether the target is in the lane of the vehicle according to the current cycle smooth value of the target,

    Among them, if 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.
12. The method of claim 11, wherein:

    According to the ordinate and abscissa of each guardrail reflection point in the cartesian coordinate system of the car body and the number of guardrail reflection points, the curve parameters are obtained by fitting according to the cyclotron curve model.

    Determine the distance between the vehicle and the guardrail fitting curve according to the curve parameters.
13. The method of claim 12, wherein:

    Determine the distance between the target and the fitting curve of the guardrail according to the clothoid curve model and curve parameters, as well as the ordinate and abscissa of the target.
14. The method of claim 13, wherein:

    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 judgment threshold, the self-lane evaluation value of the current update cycle of the target is determined.
15. The method of claim 14, wherein:

    Determine the target current period smoothing value 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.
16. The method according to claim 1, wherein the preset guardrail model includes a straight line model, a quadratic polynomial model, a circular curve model, or a clothoid curve model.
17. The method according to claim 1, further comprising:

    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.
18. A guardrail detection device based on millimeter wave radar, which is characterized in that it comprises:

    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.
19. The system according to claim 18, wherein determining the guardrail model according to the guardrail reflection point comprises:

    Fit the screened guardrail reflection points separately according to the preset guardrail model to obtain the parameters and fitting residuals of each guardrail model;

    The guardrail model with the smallest fitting residual is selected from all guardrail models as the currently detected guardrail model.
20. The system according to claim 18, wherein the characterizing parameters include the parameters of the guardrail model and the coordinates of the starting point and the ending point in the reflection point of the guardrail.
21. The system according to claim 18, wherein processing the echo signal to obtain a reflection point of a guardrail comprises:

    Processing the echo signal to obtain a detection result of the target, and the detection result includes a plurality of reflection points;

    The reflection points of the guardrail are screened out from the detection results according to the characteristics of the guardrail.
22. The system according to claim 21, wherein the screening of the reflection points of the guardrail from the detection result according to the characteristics of the guardrail comprises:

    Determining whether the reflection point is stationary relative to the ground according to the information of the echo signal corresponding to the reflection point; and

    Whether the distance between the reflection point and the adjacent reflection point is less than a set threshold,

    If 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.
23. The system according to claim 18, wherein processing the echo signal to obtain a reflection point of a guardrail comprises:

    Processing the echo signal to obtain a range Doppler image;

    Determining a guardrail recognition area on the distance Doppler image based on the vehicle speed;

    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 pixels whose reflection intensity exceeds a threshold value as the guardrail reflection point.
24. The system according to claim 23, wherein determining the guardrail recognition area on the distance Doppler image based on the vehicle speed comprises:

    Define the maximum speed of pixels in the guardrail recognition area based on the vehicle speed;

    Define the minimum speed of pixels in the guardrail recognition area based on the vehicle speed;

    Set the maximum distance of pixels in the guardrail recognition area;

    Set the minimum distance of pixels in the guardrail recognition area; and

    The guardrail recognition area is determined according to the maximum speed, minimum speed, maximum distance and minimum distance.
25. The system according to claim 23, further comprising:

    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.
26. The system according to claim 25, wherein the mapping of 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 comprises:

    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 horizontal distance and the longitudinal distance of the guardrail reflection point in the Cartesian coordinate system with the radar as the origin are determined .
27. The system according to claim 26, further comprising:

    Fit the guardrail according to the horizontal 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.
28. The system according to claim 18, wherein the processor is further configured to:

    According to the reflection point of the guardrail, the curve parameters are obtained by fitting the cyclotron curve model;

    Calculate the distance between the vehicle and the guardrail fitting curve;

    Calculate the distance between the target and the fitting curve of the guardrail;

    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;

    Smooth the evaluation value of the target's current cycle of the self-lane to obtain the target's current cycle smooth value;

    Determine whether the target is in the lane of the vehicle according to the current cycle smooth value of the target,

    Among them, if 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.
29. The system of claim 28, wherein:

    According to the ordinate and abscissa of each guardrail reflection point in the cartesian coordinate system of the car body and the number of guardrail reflection points, the curve parameters are obtained by fitting according to the cyclotron curve model.

    Determine the distance between the vehicle and the guardrail fitting curve according to the curve parameters.
30. The system of claim 29, wherein:

    Determine the distance between the target and the fitting curve of the guardrail according to the clothoid curve model and curve parameters, as well as the ordinate and abscissa of the target.
31. The system of claim 30, wherein:

    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 judgment threshold, the self-lane evaluation value of the current update cycle of the target is determined.
32. The system of claim 31, wherein:

    Determine the target current period smoothing value 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.
33. The system according to claim 18, wherein the preset guardrail model includes a straight line model, a quadratic polynomial model, a circular curve model, or a clothoid curve model.
34. The system according to claim 18, wherein 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.
35. A storage medium, characterized in that a computer program is stored on the storage medium, and the computer program executes the method according to any one of claims 1-17 when running.
36. A movable platform, characterized by comprising: the guardrail fitting device according to any one of claims 17-34.
37. The movable platform of claim 36, wherein the movable platform comprises a car.

Images