Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of embodiments of the invention and not all embodiments of the invention, with the understanding that the invention is not limited to the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the invention described herein without inventive step, shall fall within the scope of protection of the invention.
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art, that the present invention may be practiced without one or more of these specific details. In other instances, well-known features have not been described in order to avoid obscuring the invention.
It is to be understood that the present invention may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term "and/or" includes any and all combinations of the associated listed items.
In the following description, for the purposes of thorough understanding of the present invention, detailed procedures and detailed structures are set forth in order to explain the present invention, but the present invention may be embodied in other specific forms besides those detailed description.
First, an example electronic device 100 of an example electronic device for implementing the millimeter wave radar-based fence detection method and apparatus according to the embodiment of the present invention is described with reference to fig. 1. As shown in FIG. 1, electronic device 100 includes one or more processors 102, one or more memory devices 104, input/output devices 106, a communication interface 108, and a radar sensor 110, which are interconnected via a bus system 112 and/or other form of connection mechanism (not shown). It should be noted that the components and structure of the electronic device 100 shown in fig. 1 are merely exemplary and not limiting, and the electronic device may have other components and structures, or may not include some of the aforementioned components, as desired.
The processor 102 generally represents any type or form of processing unit capable of processing data or interpreting and executing instructions. In general, the processor may be a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), an encoder, an Image Signal Processor (ISP), or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may 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 (FSMs), Digital Signal Processors (DSPs), or a combination thereof. In particular embodiments, processor 102 may receive instructions from a software application or module. The instructions may cause the processor 102 to perform the methods for device hybrid navigation and self-moving devices and methods described and/or illustrated herein.
The storage 104 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. On which one or more computer program instructions may be stored that may be executed by processor 102 to implement client-side functionality (implemented by the processor) and/or other desired functionality in embodiments of the invention described below. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The input/output device 106 may be a device used by a 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, a touch screen, and the like. The output devices may include one or more of a display, speakers, and the like.
Communication interface 108 broadly represents any type or form of adapter or communication device capable of facilitating communication between example electronic device 100 and one or more additional devices. For example, the communication interface 108 may facilitate communication between the electronic device 100 and front-end or accessory electronic devices as well as back-end servers or clouds. Examples of 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 Bus (USB), an HDMI interface, and any other suitable interface. In an embodiment, the communication interface 108 provides direct connection to a remote server/remote head end device through direct connection to a network such as the internet. In particular embodiments, communication interface 108 provides direct connection to a remote server/remote head end device through direct connection to a network, such as a private network. Communication interface 108 may also indirectly provide such connection through any other suitable connection.
The radar sensor 110 may be any suitable radar sensor. In this embodiment, the radar sensor 110 is a millimeter-wave radar sensor, which includes, for example, a line, a transceiver module, and a signal processing module, where the transceiver module includes, for example, a linear VCO, an amplifier, a balanced mixer, etc., and 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, a guard rail beside a road may form a large number of reflection points in the millimeter wave radar, and generally, the millimeter wave radar system is limited in processing capacity and memory capacity, the number of reflection points capable of detecting and outputting is limited, and excessive guard rail scattering points may reduce the detection capability for other interested targets (for example, vehicles located in blind areas). Meanwhile, an excessive number of reflection points may cause a large data output pressure. Based on the method, the guardrail fitting method based on the millimeter wave radar is provided to reduce data output pressure. The millimeter wave radar-based guardrail detection method according to the embodiment of the invention is described below with reference to fig. 2 to 5.
It should be noted that the guardrail in the present application may include continuous obstacles on one side or both sides of a road or on one side or both sides of a middle lane of a road, and specifically may be, for example, stone piers on both sides of a highway, fences partitioned in the middle of a bidirectional lane, continuous warning barriers placed for temporary road maintenance, etc., and the present invention is not limited to the specific form of the guardrail.
FIG. 2 shows a schematic flow diagram of a millimeter wave radar-based fence detection method according to an embodiment of the invention; fig. 3 shows a schematic view of a radar sensor detecting both side fences.
As shown in fig. 2, the method disclosed in this embodiment includes:
step 201, transmitting a millimeter wave radar signal, and receiving an echo signal reflected by a target.
Illustratively, a millimeter wave radar sensor transmits a millimeter wave signal and receives an echo signal reflected by a target, and the detection range of the millimeter wave radar sensor is as shown in fig. 3.
And step 202, processing the echo signal to obtain a guardrail reflection point.
Illustratively, various suitable echo signal processing methods are employed to derive the guardrail reflection points based on the echo signals. The obtained guardrail reflection point can comprise the coordinates of the guardrail in a radar detection coordinate system or the distance between the guardrail and the vehicle.
And 203, determining a guardrail model according to the guardrail reflection points, and further determining and outputting the characterization 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 parameters of the guardrail reflection point, such as data of coordinates, so as to obtain a model for determining the guardrail and parameters of the model, and then characterization parameters of the guardrail are output to represent the current guardrail.
Illustratively, the characterizing parameters include parameters of the guardrail model and coordinates of a starting point and an ending point in the guardrail reflecting points. The parameters of the guardrail model include, for example, the magnitude of each coefficient in the model, illustratively, the guardrail model is a linear line y ═ ax + b, and the parameters of the guardrail include the magnitudes of a and b, and the coordinates of the starting point and the ending point in the reflection points of the guardrail. The shape and position of the current guardrail can be determined according to the guardrail parameters and the coordinates of the starting point and the ending point in the guardrail reflection points. Because the detected guardrail is not required to be represented by outputting all reflection points, the data output pressure is greatly reduced, and the detection capability of the radar sensor on other interested targets is prevented from being influenced.
FIG. 4 shows a schematic flow diagram of a millimeter wave radar-based fence detection method according to another embodiment of the present invention; fig. 5 shows a schematic view of the reflection points of the guard rail present in the radar detection result.
As shown in fig. 4, the method disclosed in this embodiment includes:
step 401, transmitting a millimeter wave radar signal, and receiving an echo signal reflected by a target.
Illustratively, a millimeter wave radar sensor transmits a millimeter wave signal and receives an echo signal reflected by a target, and the detection range of the millimeter wave radar sensor is as shown in fig. 3.
Step 402, processing the echo signal to obtain a detection result of the target, where the detection result includes a plurality of reflection points.
For example, the echo signal may be processed by a processing method commonly used in the art to obtain a detection result of the target, and as shown in fig. 5, the guard rail appears as a large number of reflection points in the detection result of the millimeter wave radar sensor. Some of the reflection points are guardrail reflection points, and some of the reflection points are not guardrail reflection points.
And 403, screening guardrail reflection points from the detection result according to the guardrail characteristics.
After the reflection points are obtained in step 402, the guardrail reflection points need to be screened from the detection result according to the guardrail characteristics.
Illustratively, the method for screening out the guardrail reflection points from the detection result according to the guardrail characteristics comprises the following steps: firstly, whether the reflection point is static relative to the ground is determined according to the information of the echo signal corresponding to the reflection point. Since the guardrail is stationary relative to the ground, the guardrail reflective points are 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 speed of the reflection point relative to the ground is 0, the reflection point is possibly a guardrail reflection point; otherwise, the reflection point is not the guardrail reflection point.
Secondly, whether the distance between the reflection point and the adjacent reflection point is smaller than a set threshold value or not. Because the relative distances between all the reflection points of the guardrail are relatively short, whether the reflection point is a guardrail reflection point can be judged by judging whether the distance between the reflection point and the adjacent reflection point is smaller than a set threshold value. For example, distance information of the reflection point, such as distance information from the vehicle, may be determined according to information of an echo signal corresponding to the reflection point, and then a distance between the reflection point and an adjacent reflection point is obtained according to the distance information of each reflection point, and if the distance between the reflection point and the adjacent reflection point is greater than a set threshold, it indicates that the reflection point is far away from the adjacent reflection point, and may not be a guardrail reflection point, and otherwise, it is more likely to be a guardrail reflection point.
Finally, whether the reflection point is the guardrail reflection point is determined by the analysis. For example, if the reflection point is static relative to the ground and the distance between the reflection point and the adjacent reflection point is less than a set threshold value, the reflection point is determined to be a guardrail reflection point.
And 404, determining a guardrail model according to the guardrail reflection points, and further determining and outputting the characterization parameters of the current guardrail to represent the current guardrail.
After determining the guardrail reflection points from the reflection points in step 403, fitting is performed according to parameters of the guardrail reflection points, such as coordinates, so as to obtain a model of the guardrail and parameters of the model, and then characterizing parameters of the guardrail are output to represent the current guardrail.
Illustratively, the characterizing parameters include parameters of the guardrail model and coordinates of a starting point and an ending point in the guardrail reflecting points. The parameters of the guardrail model include, for example, the magnitude of each coefficient in the model, illustratively, the guardrail model is a linear line y ═ ax + b, and the parameters of the guardrail include the magnitudes of a and b, and the coordinates of the starting point and the ending point in the reflection points of the guardrail. The shape and position of the current guardrail can be determined according to the guardrail parameters and the coordinates of the starting point and the ending point in the guardrail reflection points. Because the detected guardrail is not required to be represented by outputting all reflection points, the data output pressure is greatly reduced, and the detection capability of the radar sensor on other interested targets is prevented from being influenced.
Further, in this embodiment, in order to avoid the problem that a single guardrail model has poor applicability, in this embodiment, multiple guardrail models are preset and respectively fitted, and then an optimal guardrail model is selected from the guardrail models.
Illustratively, the method for determining the guardrail model according to the guardrail reflection points comprises the following steps:
firstly, fitting the screened guardrail reflection points respectively according to a preset guardrail model to obtain parameters and fitting residual errors of each guardrail model. Namely, the preset guardrail models are respectively fitted according to parameters of the guardrail reflection points, such as data of coordinates and the like, so that the parameters of each guardrail model are obtained, and then the fitting residual error of each guardrail model is calculated. Illustratively, the preset guardrail model includes a straight line model, a quadratic polynomial model, a circular curve model or a clothoid model.
And secondly, selecting the guardrail model with the minimum fitting residual error from all guardrail models as the model of the currently detected guardrail. And after the fitting residual error of each guardrail model is obtained, selecting the guardrail model with the minimum fitting residual error as the model of the guardrail detected before.
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 minimum fitting residual error and the coordinates of the starting point and the ending point in the reflection points of the guardrail, so that the shape and the position of the guardrail can be known conveniently by the straight tube of the user.
According to the millimeter wave radar-based guardrail detection method, parameterization and automation of guardrail fitting are achieved, all guardrail reflection points are replaced by guardrail model parameters and coordinates of a starting point and a terminal point in the guardrail reflection points to represent guardrails, accordingly, the data output pressure of the guardrail reflection points can be effectively reduced, an optimal model is selected by presetting various guardrail models to respectively fit and select the optimal model, the optimal guardrail fitting model can be automatically selected to adapt to various scenes, and the accuracy and the robustness of guardrail fitting are improved.
Further, in the above embodiment, the fitting of the guard rail is mainly performed by clustering the stationary reflection points and then fitting a guard rail curve. However, the clustering effect of the static reflection points is seriously influenced by the radar angle measurement precision and the multipath effect. When the radar angle measurement precision is not high or the radar angle measurement effect is multipath effect (the angle measurement result can be greatly deviated), the static reflection points are difficult to cluster, and the guardrail is difficult to identify and fit. And the method has the problem of high computational complexity, because the method firstly needs to perform algorithms such as CFAR (computational fluid dynamics), MUSIC (multiple-order angular measurement), clustering and the like on the static reflection point, the computational complexity of the algorithms is high, the performance requirement on a processor is increased, and further the cost is high.
In view of this, the present application further provides a guardrail detection method based on millimeter wave radar, which performs detection and fitting of a guardrail by using range-doppler information and a hidden relationship between a spatial position of the guardrail and a self-vehicle speed. By using the detection method, the detection and fitting capability of the radar to the guardrail can be greatly improved under the condition that the hardware cost and the antenna performance of the radar are not increased. Meanwhile, the calculation complexity of the detection method is far less than that of the traditional method. The guardrail detecting method will be described below with reference to fig. 6 to 10.
FIG. 6 shows a schematic flow diagram of a millimeter wave radar-based fence detection method according to yet another embodiment of the present invention; FIG. 7 is a schematic diagram illustrating the coordinate system definition in the fitting method shown in FIG. 6; FIG. 8 is a schematic diagram illustrating the calculation of the distance and velocity of the reflecting points of the guardrail in the fitting method shown in FIG. 6; FIG. 9 shows a schematic diagram of filtering a fence identification area of a range-Doppler image; fig. 10 shows a schematic diagram of the coordinate transformation of the filtered pixels in fig. 9.
The definition of the coordinate system in the present embodiment is described first with reference to fig. 7. As shown in fig. 7, in the present embodiment, since the vehicle-mounted radar is installed directly in front of the vehicle, a cartesian coordinate system is established in a right-hand system with the center of the vehicle-mounted radar as the origin and the normal direction of the radar transmission beam as the positive y-axis direction.
Next, as shown in fig. 8, in this embodiment, the method for calculating the lateral distance of the guardrail reflective point includes:
since the reflecting point of the guardrail is static to the ground, the real relative speed V between the reflecting point and the radarrealThe size is the vehicle speed VvehicleThe size and the direction are opposite to the vehicle speed direction of the vehicle. Namely, the following relation is satisfied:
Vreal=-Vvehicle
guardrail reflection point speed V actually measured by radardoppierIs VrealThe component between the radar center and the reflection point, this velocity is called the radial velocity.
Guard rail reflection point distance R actually measured by radarradialIs the distance between the reflecting point of the guardrail and the center of the radar, theThe distance is referred to as the radial distance.
Transverse distance R of guardrail reflection pointxRadial distance RradialRadial velocity VdoppierAnd the speed V of the vehiclevehicleSatisfy the following relation (sine and cosine formula)
(Rx/R _ radial) ^2+ (V _ doppler/V _ vehicle) ^2 ^ 1 (formula 1)
So that the transverse distance RxCan be calculated from the following formula:
based on the above definition, the guardrail detecting method of the present embodiment will be described next with reference to fig. 6 and fig. 9 and 10.
As shown in fig. 6, the method disclosed in this embodiment includes:
step 401, processing 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 a radar receiving end intermediate-frequency time domain signal modulated according to a fast sawtooth waveform, as shown in the left diagram in fig. 9, a horizontal axis of the range-doppler image represents a distance, and a vertical axis of the range-doppler image represents a speed. The x coordinate of each pixel point represents the radial distance between the reflection point and the radar, the y coordinate represents the radial relative speed (Doppler effect) between the reflection point and the radar, and the numerical value represents the reflection intensity of the reflection point. Illustratively, colors in the range-doppler image represent the reflection intensities, for example, red and blue, with red indicating stronger reflection intensity and blue indicating weaker reflection intensity.
Step 402, determining a guardrail identification area on the range-doppler image based on vehicle speed.
As shown in the left diagram of fig. 9, the curve in the box is generated by the guardrail, and the curve equation can be derived from equation 1.
From formula 3, V can be obtaineddoppierAnd RradialThe curve relationship of (1). From equation 3, it can also be known that the guardrail curve on the range-doppler image is represented by RxAnd VvehicleTwo parameters.
In this embodiment, the method for determining the guardrail recognition area on the range-doppler image based on the vehicle speed is as follows: firstly, defining the maximum speed of pixel points in a guardrail identification area based on the vehicle speed; then, defining the minimum speed of pixel points in the guardrail identification area based on the vehicle speed; then, setting the maximum distance of pixel points in the guardrail identification area; then, setting the minimum distance of pixel points in the guardrail identification area; and finally, determining a guardrail identification area according to the maximum speed, the minimum speed, the maximum distance and the minimum distance.
Illustratively, maximum velocity V of a pixel point in a guardrail recognition region, for examplemaxAs the vehicle speed VvehicleMinus a predetermined value VoffsetMinimum speed is vehicle speed VvehicleMultiplying by a preset value A, and respectively setting the maximum distance and the minimum distance to be RmaxAnd RminThe guardrail identification area is expressed as:
Vmax=Vvehicle-Voffset,
Vmin=Vvehicle*A,
Rmin=B
Rmax=C
wherein, VoffsetA, B, C are preset values which can be determined empirically or experimentally, for example, VoffsetV is 2m/s, 3m/s, 4m/s, etc., A is 0.4, 0.5, 0.6, etc., B is 3, 4, 5, 6, C is 50, 60, 70, 80, etc., and V is a pair of VoffsetSpecific values of A, B, C are not limited.
The guardrail identification area can be determined on the range-doppler image through the above relational expression, for example, the square area of the left image in fig. 9 is the guardrail identification area. Some of the pixels in the area are guardrail reflection points, and some of the pixels are not guardrail reflection points.
Step 403, performing filtering processing on the pixel points in the guardrail identification area on the range-doppler image according to the reflection intensity, so as to reserve the pixel points with the reflection intensity exceeding the threshold value as guardrail reflection points.
After the guardrail identification area on the range-doppler image is determined in step 402, filtering is performed on the pixel points in the guardrail identification area according to the reflection intensity, so as to reserve the pixel points with the reflection intensity exceeding the threshold value as guardrail reflection points.
For example, as shown in fig. 9, for pixel points in the identification area of the fence on the range-doppler image, reflection intensity filtering is performed according to the distance-reflection intensity characteristic curve of the fence, and only pixel points with reflection intensity exceeding the threshold are left.
And filtering the pixel points in the guardrail identification area on the distance Doppler image according to the reflection intensity to obtain guardrail reflection points.
Step 404, mapping the pixel points with the reflection intensity exceeding the threshold value so as to map the pixel points with the reflection intensity exceeding the threshold value from a range-doppler coordinate system to a cartesian coordinate system with the radar as an origin.
When the guardrail reflection point is obtained from the range-doppler image, the guardrail reflection point is mapped according to the formula two, and the pixel point representing the guardrail reflection point is mapped into the cartesian coordinate system established by the vehicle-mounted radar shown in fig. 7 from the range-doppler coordinate system, so that curve fitting is finally performed on the mapped pixel point to perform guardrail fitting.
Specifically, the transverse distance R of the guardrail reflecting point in a Cartesian coordinate system with the radar as an origin is determined according to the speed of the guardrail reflecting point measured by the radar, the running speed of the vehicle and the distance between the guardrail reflecting point measured by the radar and the center of the radarxAnd a longitudinal distance Ry。
Illustratively, the lateral distance R of each guardrail reflection point in a Cartesian coordinate system with the radar as the origin is determined according to the following formulax,
According to the formula
Determining the transverse distance R of each guardrail reflection point in a Cartesian coordinate system taking a radar as an origin
y,
Wherein R isradialV is the radial distance of the guardrail reflection point in a Cartesian coordinate system taking the radar as an origin (namely the distance from the guardrail reflection point measured by the radar to the center of the radar), anddoppiervelocity of guardrail reflecting points, V, measured for radarvehicleIs the running speed of the vehicle.
And 405, performing guardrail fitting according to the transverse distance and the longitudinal distance of the guardrail reflection point in a Cartesian coordinate system with the radar as the origin to determine a guardrail model.
Illustratively, the curve model may select a straight line, a circle, or a clothoid, for example, using a least squares curve fit.
According to the guardrail detection method, the detection and identification of the radar on the guardrail can be realized under the condition that the hardware cost of the radar and the design complexity of the antenna are not increased. Compared with the traditional method, the scheme has the advantages of low calculation complexity, strong robustness, independence on angle measurement precision and the like, and can greatly improve the detection capability of the radar on the guardrail. Compared with the traditional method, the guardrail fitting method provided by the embodiment has the advantages that the detection precision of the guardrail is greatly improved, and the calculation complexity is greatly reduced.
Further, in the practical application of the vehicle-mounted millimeter wave radar, it is the competitive power of the millimeter wave radar to accurately judge whether the target vehicle is in the self lane, however, in the case of a curve, the millimeter wave radar cannot accurately judge whether the target vehicle is in the self lane due to the bend-in and bend-out hysteresis effect, the accuracy of the vehicle sensor and the like. And the false alarm and missing detection rate of the ADAS system and the AD system under the condition of curve are greatly increased, so that potential safety hazards are brought. In view of this, the present application provides a new method for determining whether a target is in a self-lane by an on-board millimeter wave radar, which greatly improves the accuracy of determining whether the target is in the self-lane in a curve by using detection and identification information of the millimeter wave radar on a guardrail or a road edge on the basis of not adding additional radar hardware and a processor and without depending on other sensors (e.g., a visual sensor such as a camera). An object self-lane evaluation method based on guardrail recognition according to an embodiment of the invention is described below with reference to fig. 11.
Fig. 11 illustrates a schematic flowchart of an object self-lane evaluation method based on guardrail recognition according to still another embodiment of the present invention.
As shown in fig. 11, the method disclosed in this embodiment includes:
and step 501, fitting according to the guardrail reflection points and a clothoid model to obtain curve parameters.
The guardrail reflection points can be obtained based on radar echo signals according to the method disclosed by the embodiment or other methods, and curve parameters are obtained by fitting according to a clothoid model after the guardrail reflection points are obtained. Illustratively, the curve parameters are obtained by curve fitting, for example, by the least squares method or the like.
Exemplarily, the clothoid model is represented as y ═ a × x3+b*x2+c;
And fitting according to the ordinate and the abscissa of each guardrail reflection point in a Cartesian coordinate system of the vehicle body (a coordinate system is established by taking the right center of the vehicle head as an origin, the forward direction of the vehicle as the positive direction of the y axis and the right side of the vehicle as the positive direction of the x axis) and the number of the guardrail reflection points according to a clothoid model to obtain curve parameters a, b and c.
Step 502, calculating the distance between the vehicle and the guardrail fitting curve.
Specifically, the distance of the vehicle from the guardrail fitting curve is determined according to the curve parameters. Exemplarily, y ═ a × x3+b*x2+ c is an example, e.g. the distance of the vehicle from the guardrail fitted curve is equal to the curve equal to c.
Step 503, calculating the distance between the target and the guardrail fitting curve.
Specifically, the distance between the target and the guardrail fitting curve is determined according to the clothoid curve model and the curve parameters as well as the ordinate and the abscissa of the target.
And step 504, calculating 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.
Specifically, 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 lane distance determination threshold. Wherein the self-lane distance decision threshold may be empirically determined, e.g. 1.5 meters, 1.64 meters, 1.75 meters, 1.82 meters, etc.
And 505, smoothing the self lane evaluation value of the current period of the target to obtain a smooth value of the current period of the target.
And determining a target current period smooth value according to the self lane evaluation value of the current updating period, the smooth value of the previous period and the smooth coefficient. The smoothing factor may be empirically determined, for example, to be 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, or 0.9.
Step 506, judging whether the target is on the lane where the vehicle is located according to the target current period smooth value,
and if the current cycle smooth value of the target is larger than the set threshold, determining that the target is on the lane where the vehicle is located, and otherwise, determining that the target is not on the lane where the vehicle is located. The set threshold may be determined empirically or experimentally and may be, for example, 50, 60, 70 or 80.
According to the target self-lane evaluation method based on guardrail recognition, the judgment capability of judging whether the target is in the lane or not in a curve scene is greatly improved, and the false alarm rate and the missing detection rate are greatly reduced. Namely, the judgment capability of the vehicle-mounted millimeter wave radar on whether the target is in the self lane during turning is greatly improved, so that the robustness of the whole ADAS and AD system is improved, and the user experience is improved.
Fig. 12 shows a schematic block diagram of a millimeter wave radar-based fence detection apparatus according to an embodiment of the present invention.
As shown in fig. 12, the millimeter wave radar-based fence detection device 600 of the present embodiment includes a millimeter wave radar sensor 610, a memory 620, and a processor 630.
The millimeter wave radar sensor 610 is configured to emit millimeter waves to a target area and receive a millimeter wave echo signal reflected by an object in the target area. The millimeter wave radar sensor 610 may further process the echo signal to obtain a detection result or a guardrail reflection point. The millimeter-wave radar sensor 610 includes, for example, a line, a transceiver module including, for example, a linear VCO, an amplifier, a balanced mixer, and the like, and a signal processing module, but may also include other structures.
The 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 that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, a Read Only Memory (ROM), hard disk, flash memory, or other persistent storage. On which one or more computer program instructions may be stored that may be executed by a processor to implement the control methods (implemented by the processor) of the embodiments of the invention described above and/or other desired functions. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The one or more processors 630 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, such as a pico controller (MCU), and may control other components in the guardrail fitting system 600 to perform desired functions.
It should be appreciated that in some embodiments, processor 630 may be a processor of millimeter-wave radar sensor 610 itself; in some embodiments, processor 630 may also be a processor external to millimeter-wave radar sensor 610, coupled to millimeter-wave radar sensor 610, that processes data generated by millimeter-wave radar sensor 610, e.g., processor 630 may be a processor of the vehicle itself, rather than a processor internal to millimeter-wave radar sensor 610.
The one or more computer programs, when executed by the one or more processors 630, cause the one or more processors 630 to perform the steps of:
processing the echo signal to obtain a guardrail reflection point;
and determining a guardrail model according to the guardrail reflection points, and further determining and outputting the characterization parameters of the current guardrail to represent the current guardrail.
Illustratively, determining a guardrail model from the guardrail reflection points comprises:
fitting the screened guardrail reflection points according to a preset guardrail model respectively to obtain parameters and fitting residual errors of each guardrail model;
and selecting the guardrail model with the minimum fitting residual error from all guardrail models as the model of the currently detected guardrail.
Illustratively, the characterizing parameters include parameters of the guardrail model and coordinates of a starting point and an ending point in the guardrail reflecting points.
Illustratively, processing the echo signal to obtain a guardrail reflection point comprises:
processing the echo signal to obtain a detection result of a target, wherein the detection result comprises a plurality of reflection points;
and screening out guardrail reflection points from the detection result according to the guardrail characteristics.
Illustratively, the screening of the guardrail reflection points from the detection results according to the guardrail characteristics comprises the following steps:
determining whether the reflection point is static relative to the ground or not 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 value,
and if the reflection point is static relative to the ground and the distance between the reflection point and the adjacent reflection point is less than a set threshold value, judging that the reflection point is a guardrail reflection point.
Illustratively, processing the echo signal to obtain a guardrail reflection point comprises:
processing the echo signal to obtain a range-Doppler image;
determining a guardrail identification area on the range-doppler image based on vehicle speed;
and filtering the pixel points in the guardrail identification area on the distance Doppler image according to the reflection intensity, so as to reserve the pixel points with the reflection intensity exceeding a threshold value as guardrail reflection points.
Illustratively, determining a guardrail identification area on the range-doppler image based on vehicle speed comprises:
defining the maximum speed of pixel points in the guardrail identification area based on the vehicle speed;
defining the minimum speed of pixel points in the guardrail identification area based on the vehicle speed;
setting the maximum distance of pixel points in the guardrail identification area;
setting the minimum distance of pixel points in the guardrail identification area; and
and determining a guardrail identification area according to the maximum speed, the minimum speed, the maximum distance and the minimum distance.
Exemplarily, the method further comprises the following steps:
and mapping the pixel points with the reflection intensity exceeding the threshold value so as to map the pixel points with the reflection intensity exceeding the threshold value into a Cartesian coordinate system with the radar as an origin from a range-Doppler coordinate system.
Illustratively, mapping the pixel point with the reflection intensity exceeding the threshold value from a range-doppler coordinate system to a cartesian coordinate system with a radar as an origin includes:
and determining the transverse distance and the longitudinal distance of the guardrail reflecting point in a Cartesian coordinate system with the radar as an origin according to the speed of the guardrail reflecting point measured by the radar, the running speed of the vehicle and the distance between the guardrail reflecting point measured by the radar and the center of the radar. Exemplarily, the method further comprises the following steps: and carrying out guardrail fitting according to the transverse distance and the longitudinal distance of the guardrail reflection point in a Cartesian coordinate system with the radar as the origin to determine a guardrail model.
Illustratively, the processor is further configured to:
fitting according to the guardrail reflection point and a clothoid model to obtain curve parameters;
calculating the distance between the vehicle and the guardrail fitting curve;
calculating the distance between the target and the guardrail fitting curve;
calculating the current period 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;
smoothing the self lane evaluation value of the current period of the target to obtain a smooth value Pn of the current period of the target;
judging whether the target is on the lane where the vehicle is located according to the target current period smooth value,
and if the current cycle smooth value of the target is larger than the set threshold, determining that the target is on the lane where the vehicle is located, and otherwise, determining that the target is not on the lane where the vehicle is located.
Illustratively, curve parameters are obtained by fitting according to the ordinate and the abscissa of each guardrail reflection point in a Cartesian coordinate system of the vehicle body and the number of the guardrail reflection points according to a clothoid model,
and determining the distance between the vehicle and the guardrail fitting curve according to the curve parameters.
Illustratively, the distance of the target from the guardrail fitting curve is determined from the clothoid model and the curve parameters and the ordinate and abscissa of the target.
Illustratively, 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.
Illustratively, the target current-cycle smoothing value is determined from the own-lane evaluation value of the current update cycle, the smoothing value of the previous cycle, and the smoothing coefficient.
Illustratively, the preset guardrail model includes a straight line model, a quadratic polynomial model, a circular curve model or a clothoid model.
Illustratively, the processor is further configured to:
and generating a schematic diagram of the guardrail based on the parameters of the guardrail model with the minimum fitting residual error and the coordinates of the starting point and the ending point in the reflection points of the guardrail.
According to the guardrail fitting system, the current guardrail is represented by the characterization parameters of the current guardrail, so that the data output pressure of the guardrail reflection points can be effectively reduced.
Further, the guardrail detection equipment according to the embodiment can realize effective detection of the radar on the guardrail, detection precision is improved in reply, and calculation complexity is reduced in reply.
Furthermore, the ability of judging whether the target is in the lane or not in a curve scene by the detection device according to the embodiment is greatly improved, and the false alarm rate and the missing rate are greatly reduced.
In addition, according to an embodiment of the present invention, there is also provided a guard rail detection apparatus based on millimeter wave radar, where the guard rail detection apparatus based on millimeter wave radar includes a storage device and a processor, and the storage device stores thereon a computer program executed by the processor, and the computer program, when executed by the processor, performs the method provided by the above-mentioned embodiment of the present invention.
Furthermore, according to an embodiment of the present invention, there is also provided a storage medium on which program instructions are stored, which when executed by a computer or a processor are used for executing the corresponding steps of the control method according to the embodiment of the present invention and for implementing 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 disc read only memory (CD-ROM), a 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, when executed by a computer, perform the steps of: transmitting a millimeter wave radar signal and receiving an echo signal reflected by a target; processing the echo signal to obtain a guardrail reflection point; and determining a guardrail model according to the guardrail reflection points, and further determining and outputting the characterization parameters of the current guardrail to represent the current guardrail.
In one embodiment, the computer program instructions, when executed by a computer, perform the steps of: processing the echo signal to obtain a range-Doppler image; determining a guardrail identification area on the range-doppler image based on vehicle speed; and filtering the pixel points in the guardrail identification area on the distance Doppler image according to the reflection intensity, so as to reserve the pixel points with the reflection intensity exceeding a threshold value as guardrail reflection points.
In one embodiment, the computer program instructions, when executed by a computer, perform the steps of: fitting according to the guardrail reflection point and a clothoid model to obtain curve parameters; calculating the distance between the vehicle and the guardrail fitting curve; calculating the distance between the target and the guardrail fitting curve; calculating the current period 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; smoothing the current period self lane evaluation value P of the target to obtain a current period smooth value of the target; and judging whether the target is on the lane where the vehicle is located according to the target current cycle smooth value, wherein if the target current cycle smooth value is larger than a set threshold value, the target is judged to be on the lane where the vehicle is located, otherwise, the target is not on the lane where the vehicle is located.
The modules in the control system according to an embodiment of the present invention may be implemented by a processor of the electronic device according to an embodiment of the present invention running computer program instructions stored in a memory, or may be implemented when computer instructions stored in a computer-readable storage medium of a computer program product according to an embodiment of the present invention are run by a computer.
In addition, according to the embodiment of the invention, a movable platform is further provided, and the movable platform comprises the guardrail fitting system or the guardrail fitting device according to the embodiment of the invention. The movable platform comprises an automobile.
According to the millimeter wave radar-based guardrail detection method and equipment, the storage medium and the movable platform, the current guardrail is represented by the characterization parameters of the current guardrail, so that the data output pressure of the reflection point of the guardrail can be effectively reduced.
Although the illustrative embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the foregoing illustrative embodiments are merely exemplary and are not intended to limit the scope of the invention thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the scope or spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as set forth in the appended claims.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another device, or some features may be omitted, or not executed.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the method of the present invention should not be construed to reflect the intent: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
It will be understood by those skilled in the art that all of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where such features are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some of the modules according to embodiments of the present invention. The present invention may also be embodied as apparatus programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The above description is only for the specific embodiment of the present invention or the description thereof, and the protection scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the protection scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.