Road barrier detection method, device, vehicle and medium
By using RV curves to screen effective target points in the road fence detection method, the problems of complex calculations, low recognition rate and poor environmental adaptability in the prior art are solved, and more efficient road fence recognition is achieved.
Patent Information
- Application Number
- CN202111599364.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-24
- Publication Date
- 2025-02-11
- Estimated Expiration
- 2041-12-24
AI Technical Summary
The existing road fence detection method based on vehicle-mounted millimeter wave radar has problems such as complex calculation, low recognition rate and poor environmental adaptability.
By acquiring radar signals, the distance information and speed information of the effective target point are determined, the RV curve relationship of the road fence is determined using the zero-speed point distance and the bicycle speed, the effective target point is screened, the calculation complexity is reduced and the recognition accuracy is improved.
It realizes reducing the computational complexity, improving the accuracy and environmental adaptability of road fence recognition.
Smart Images

Figure CN116338695B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of automatic detection technology, and in particular to a road barrier detection method, device, vehicle and medium. Background Art
[0002] With the development of Advanced Driving Assistance System (ADAS) and autonomous driving technology, the perception of environmental information by cars has become increasingly important, and road barrier detection is one of them. Accurate recognition of road barriers can help cars understand the current traffic environment, so that the algorithm can perform relevant processing for the current environment. On the other hand, it can help the body radar sensor correct the installation error, thereby ensuring that the radar sensor works better. However, in related technologies, the method of barrier detection based on vehicle-mounted millimeter-wave radar has problems such as complex calculation, low recognition rate, and poor environmental adaptability. Summary of the invention
[0003] The present invention aims to solve one of the technical problems in the related art at least to some extent. To this end, the first object of the present invention is to propose a road barrier detection method, which can reduce the computational complexity and improve the recognition rate of road barriers and environmental adaptability.
[0004] A second object of the present invention is to provide a computer-readable storage medium.
[0005] A third object of the present invention is to provide a vehicle.
[0006] A fourth objective of the present invention is to provide a road barrier detection device.
[0007] To achieve the above-mentioned purpose, a first aspect of the present invention proposes a road barrier detection method, including: acquiring a radar signal; determining a valid target point according to the radar signal, and determining the distance information and speed information of the valid target point; determining the RV curve relationship of the road barrier according to the zero-speed point distance and the vehicle speed, and screening the valid target point according to the RV curve of the road barrier, the distance information and speed information of the valid target point to obtain a fence valid point; and identifying the road barrier according to the fence valid point.
[0008] According to the road barrier detection method of the embodiment of the present invention, effective target points are screened through the RV curve of the road barrier to obtain a relatively small number of effective fence points, and then the road barrier is identified on the effective fence points, which can reduce the computational complexity, improve the accuracy of identifying road barriers and enhance environmental adaptability.
[0009] In some embodiments of the present invention, determining the valid target point according to the radar signal includes: performing a fast Fourier transform on the radar signal to generate a two-dimensional amplitude spectrum; and determining the valid target point according to the two-dimensional amplitude spectrum.
[0010] In some embodiments of the present invention, before determining the RV curve relationship of the road barrier according to the zero speed point distance and the vehicle speed, the method further includes: determining the distance of the effective target point with zero speed according to the speed information of the effective target point as the zero speed point distance.
[0011] In some embodiments of the present invention, the RV curve relationship satisfies the following formula: Wherein, V0 is the vehicle speed, and X0 is the zero speed point distance.
[0012] In some embodiments of the present invention, the valid target points are screened according to the RV curve of the road fence, the distance information and the speed information of the valid target points, including: substituting one of the distance information and the speed information of the valid target points into the formula to obtain the other of the distance to be screened and the speed to be screened; comparing the other of the distance to be screened and the speed to be screened with the other of the distance information and the speed information of the valid target points to screen the valid target points.
[0013] In some embodiments of the present invention, identifying a road barrier according to the effective points of the barrier includes: converting the effective points of the barrier to an XY plane for line detection, and determining the road barrier according to the line detection result.
[0014] In some embodiments of the present invention, the method further comprises: calculating the slope and intercept of the road barrier according to the straight line detection result.
[0015] To achieve the above objectives, a second aspect of the present invention provides a computer-readable storage medium on which a road barrier detection program is stored. When the road barrier detection program is executed by a processor, the road barrier detection method described in any of the above embodiments is implemented.
[0016] According to the computer-readable storage medium of the embodiment of the present invention, by screening valid target points through the RV curve of the road fence, a relatively small number of effective fence points are obtained, and then the road fence is identified on the effective fence points, which can reduce the computational complexity, improve the accuracy of identifying road fences and enhance environmental adaptability.
[0017] To achieve the above-mentioned purpose, a third aspect of the present invention proposes a vehicle, which includes a memory, a processor, and a road barrier detection program stored in the memory and executable on the processor. When the processor executes the road barrier detection program, the road barrier detection method described in any of the above-mentioned embodiments is implemented.
[0018] According to the vehicle of the embodiment of the present invention, by screening effective target points through the RV curve of the road fence, a relatively small number of effective fence points are obtained, and then the road fence is identified on the effective fence points, which can reduce the computational complexity, improve the accuracy of identifying road fences and enhance environmental adaptability.
[0019] To achieve the above-mentioned purpose, the fourth aspect of the present invention proposes a road fence detection device including an acquisition module, a determination module, a screening module and an identification module. The acquisition module is used to acquire radar signals. The determination module is used to determine the effective target point according to the radar signal, and to determine the distance information and speed information of the effective target point. The screening module is used to determine the RV curve relationship of the road fence according to the zero speed point distance and the vehicle speed, and to screen the effective target point according to the RV curve of the road fence, the distance information and speed information of the effective target point, to obtain the effective point of the fence. The identification module is used to identify the road fence according to the effective point of the fence.
[0020] According to the road barrier detection device of the embodiment of the present invention, effective target points are screened through the RV curve of the road barrier to obtain a relatively small number of effective fence points, and then the road barrier is identified on the effective fence points, which can reduce the calculation complexity, improve the accuracy of identifying road barriers and enhance environmental adaptability.
[0021] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 is a schematic flow chart of a road barrier detection method according to an embodiment of the present invention;
[0023] Figure 2 is a schematic diagram of a scene of a road barrier detection method according to an embodiment of the present invention;
[0024] Figure 3 is a schematic diagram of a sequence signal of a millimeter wave radar of a road barrier detection method according to an embodiment of the present invention;
[0025] Figure 4 is a schematic flow chart of a road barrier detection method according to another embodiment of the present invention;
[0026] Figure 5is a schematic diagram of a fast Fourier transform process of a road barrier detection method according to an embodiment of the present invention;
[0027] Figure 6 is a schematic diagram of a two-dimensional amplitude spectrum of a road barrier detection method according to an embodiment of the present invention;
[0028] Figure 7 is a schematic flow chart of a road barrier detection method according to another embodiment of the present invention;
[0029] Figure 8 is a schematic diagram of an RV curve according to a road barrier detection method according to an embodiment of the present invention;
[0030] Fig. 9 is a schematic diagram of an RV curve according to a road barrier detection method according to another embodiment of the present invention;
[0031] Fig.10 is a schematic flow chart of a road barrier detection method according to another embodiment of the present invention;
[0032] Fig.11 is a schematic flow chart of a road barrier detection method according to another embodiment of the present invention;
[0033] Fig.12 is a schematic flow chart of a road barrier detection method according to another embodiment of the present invention;
[0034] Fig.13 is a structural block diagram of a vehicle according to an embodiment of the present invention;
[0035] Fig.14 4 is a structural block diagram of a road barrier detection device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0036] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.
[0037] See also Figure 1 The present invention proposes a road barrier detection method, comprising:
[0038] S11: Acquire radar signal;
[0039] S13: determining a valid target point according to the radar signal, and determining distance information and speed information of the valid target point;
[0040] S15: determining the RV curve relationship of the road fence according to the zero speed point distance and the vehicle speed, and screening the valid target points according to the RV curve of the road fence, the distance information and the speed information of the valid target points to obtain the effective points of the fence;
[0041] S17: Identify road barriers based on effective points of the barriers.
[0042] According to the road barrier detection method of the embodiment of the present invention, effective target points are screened through the RV curve of the road barrier to obtain a relatively small number of effective fence points, and then the road barrier is identified on the effective fence points, which can reduce the computational complexity, improve the accuracy of identifying road barriers and enhance environmental adaptability.
[0043] It can be understood that in the related art, the method of detecting road barriers by radar is implemented by the following steps: detecting the distance information, radial velocity information, and angle of the target point by radar; calculating the x-coordinate and y-coordinate of the target point based on the distance information and angle information, and calculating the speed of the target point corresponding to the driving direction of the vehicle based on the radial velocity information and angle; screening all stationary target points in the road environment by obtaining the speed of the vehicle (the speed of the stationary target point is the same as the speed of the vehicle, but in the opposite direction, and the stationary target point is the target point corresponding to the stationary object outside the vehicle); combining the x-coordinate and y-coordinate of all stationary target points to identify the road barriers, that is, judging whether there are multiple points on a straight line by Hough transform or other fitting methods, and then judging whether there is a barrier. However, the road barrier detection method of the above-mentioned related technology has the following problems: on the one hand, since the radial velocity information of all stationary target points needs to be converted into the speed corresponding to the driving direction of the vehicle, and the conversion requires computing time, and the radar detection angle accuracy requirement is relatively high, inaccurate angles will lead to speed calculation deviations, and then lead to inaccurate target screening, affecting subsequent judgments; on the other hand, for judging whether a stationary target point is a point on the fence, whether it is Hough transform or other fitting algorithms, the more target points involved in the calculation, the more complex the calculation, and the longer the calculation time. Due to the large number of all stationary target points in the road environment, complex calculations are required and a lot of time is consumed when identifying road barriers.
[0044] The road barrier detection method provided by the present invention is directly based on (radial) speed information for screening, and does not need to convert the radial speed information of the target point into the speed corresponding to the driving direction of the vehicle based on the angle. On the one hand, it can reduce the amount of calculation, and on the other hand, it can avoid the calculation error caused by inaccurate angle information. In addition, since the method of the present invention does not directly identify the road barrier based on all the stationary target points in the road environment, but first selects the effective target points that meet certain characteristics from all the target points, and then selects the effective target points through the RV curve to obtain the effective fence points. The effective fence points are the target points corresponding to the road fence and the target points corresponding to the stationary objects outside the vehicle near the road fence. The number of effective fence points is far less than the number of all the stationary target points in the road environment. Finally, the effective fence points are used for road barrier identification, which greatly reduces the number of target points involved in the calculation during the road barrier identification process and reduces the complexity of the calculation.
[0045] In addition, the effective target points are screened through the RV curve of the road fence. Since the characteristics of the effective points of the fence are obvious, the screening is easy to achieve, and the screening results are accurate, which can better identify the road fence.
[0046] Specifically, the vehicle can be equipped with several millimeter-wave radars. Figure 2 In the illustrated embodiment, the vehicle includes a front radar installed at the front of the vehicle and two rear corner radars installed at the rear of the vehicle, so that the vehicle's external environment within a larger range can be detected. It can be understood that when the front radar is used for detection, the speed of the stationary object outside the vehicle is close to the front radar, and when the rear radar is used for detection, the speed of the stationary object outside the vehicle is away from the rear radar, but the speed direction is different. The calculation process is the same. For the convenience of description, the following description is taken as an example of the rear radar. In some embodiments of the present invention, before step S11, the method also includes: controlling the millimeter-wave radar of the vehicle to emit a sequence signal of a preset waveform. In this way, the distance information, speed information, angle information, etc. of the target outside the vehicle can be determined based on the millimeter-wave radar signal reflected from the received target outside the vehicle. The preset waveform may include a sawtooth wave. The sequence signal may include a chirp sequence signal. The sequence signal may differ due to the need to resolve speed ambiguity or anti-interference. The sequence signal may be an equidistant signal or an unequally spaced signal; the starting frequency and frequency modulation slope of the sequence signal may be the same or different, which is not limited here. In one example, the millimeter-wave radar of the vehicle is controlled to emit a sequence signal such as Figure 3 The equally spaced chirp signals are shown.
[0047] Furthermore, the radar signal can be understood as the signal after the serial signal emitted by the millimeter-wave radar of the vehicle is reflected by the object outside the vehicle. Objects outside the vehicle may include other vehicles, pedestrians, road fences, roadside trees, etc. The acquired radar signal can be converted into an intermediate frequency output by the front-end processing module of the radar, and then converted into a digital signal through analog / digital converter (ADC) sampling, and then provided to the processor for data processing. According to the radar signal, multiple target points corresponding to the objects outside the vehicle can be determined. It should be noted that the radar signal needs to contain the angle information of the target point, so at least one of the radar receiving antennas or transmitting antennas is greater than 1.
[0048] Valid target points are not all target points corresponding to stationary external objects. Most of the valid target points are target points corresponding to road fences. In addition, some are target points corresponding to moving external objects and stationary external objects other than road fences. It is necessary to further screen the target points corresponding to stationary external objects among the valid target points through the RV curve. The velocity information of the valid target point is the radial velocity information of the valid target point relative to the radar. The distance information of the valid target point is the distance information between the valid target point and the radar.
[0049] The RV curve relationship is the curve relationship between distance information R and speed information V. Figure 2 , the straight line A in the direction of the radar signal transmission can be perpendicular to the straight line B corresponding to the road fence, and the radial velocity of the point on the road fence corresponding to the foot of the perpendicular is 0, and the point on the road fence corresponding to the foot of the perpendicular is the zero velocity point. The distance between the zero velocity point and the radar is the zero velocity point distance. When the effective target point on the road fence is below the vertical line A, the farther the effective target point is, the closer the radial velocity is to the driving speed of the vehicle. When the effective target point on the road fence is located on the vertical line A, the radial velocity is 0. When the effective target point on the road fence is located above the vertical line A, the velocity direction changes.
[0050] See also Figure 4 In some embodiments of the present invention, the step of “determining a valid target point according to a radar signal” in step S13 includes:
[0051] S131: performing fast Fourier transform (FFT) on the radar signal to generate a two-dimensional amplitude spectrum;
[0052] S133: Determine the effective target point according to the two-dimensional amplitude spectrum.
[0053] In this way, the effective target point, as well as the speed information and distance information of the effective target point can be determined more accurately through the received radar signal. It can be understood that the road barrier detection method in the related art calculates the x-coordinates and y-coordinates of all effective target points based on the detected distance information and angle information, and performs screening of effective fence points and straight line detection on the XY plane, while the road barrier detection method provided by the present invention directly screens effective fence points on the calculation result of the two-dimensional amplitude spectrum, that is, the RV coordinate axis, and then performs straight line detection on the XY plane.
[0054] Specifically, please combine Figure 5 , perform an FFT on each chirp intermediate frequency output signal corresponding to the radar signal, and you can get a one-dimensional FFT of each chirp intermediate frequency output signal. This FFT is a one-dimensional FFT, also known as a distance FFT. Further, perform another FFT on the same index point of each one-dimensional FFT to get a two-dimensional FFT. During the calculation process, the input data of the FFT can be windowed or pre-processed by filtering or other methods, so that the interference between multiple signals can be suppressed, and better calculation results can be obtained when the number of signals is large.
[0055] In one example, the acquired radar signal may include 64 chirp signals. By performing an FFT on the 64 chirp signals, 64 one-dimensional FFTs of the chirp signals can be obtained, wherein each one-dimensional FFT of the chirp signal may include 128 points arranged from left to right. The first point arranged from left to right in the one-dimensional FFT of each chirp signal is taken out and an FFT is performed again to obtain an Index two-dimensional FFT; the second point arranged from left to right in the one-dimensional FFT of each chirp signal is taken out and an FFT is performed again to obtain another Index two-dimensional FFT; and so on, all two-dimensional FFTs can be obtained.
[0056] A two-dimensional amplitude spectrum can be generated based on the obtained two-dimensional FFT. The two-dimensional amplitude spectrum can also be understood as the two-dimensional FFT amplitude spectrum of the radar signal. In the two-dimensional FFT amplitude spectrum, the horizontal direction represents speed information, the vertical direction represents distance information, and the speed corresponding to the horizontal center position of the two-dimensional FFT amplitude spectrum is 0, the speed corresponding to the left side of the horizontal center position is a negative value, and the speed corresponding to the right side of the horizontal center position is a positive value. The road fence has a specific shape in the two-dimensional amplitude spectrum. The CFAR algorithm or other methods of screening targets can be used to identify the two-dimensional amplitude spectrum, and the points that constitute the specific shape in the two-dimensional amplitude spectrum are determined as valid target points.
[0057] In one example, the two-dimensional FFT amplitude spectrum generated based on the radar signal received by the rear corner radar of the vehicle is as follows: Figure 6As shown, the target point in the reverse "L" area shown is determined as a valid target point. Please combine it with Figure 2 and Figure 6 , the speed of the target point at the horizontal center position O of the two-dimensional FFT amplitude spectrum is 0, corresponding to the zero speed point; the target points to the left of the horizontal center position O of the two-dimensional FFT amplitude spectrum have different speeds and slightly different distances. These target points can represent points on the road fence above the vertical line A; the target points to the right of the horizontal center position O of the two-dimensional FFT amplitude spectrum, as the speed increases, the distance gradually increases, and these target points gradually move away from the vehicle. These target points can represent points on the road fence below the vertical line A.
[0058] See also Figure 7 In some embodiments of the present invention, before step S15, the method further includes:
[0059] S19: Determine the distance of the effective target point with zero speed according to the speed information of the effective target point as the zero speed point distance.
[0060] In this way, the zero speed point distance can be quickly determined.
[0061] In some embodiments of the present invention, the RV curve relationship satisfies the following formula: Among them, V0 is the vehicle speed, X0 is the distance to the zero speed point (such as Figure 2 shown).
[0062] In this way, the shape of the RV curve is basically the same as the shape of the effective target points in the two-dimensional amplitude spectrum. By screening the effective target points through the RV curve, the effective fence points can be obtained more accurately, which can further reduce the number of effective target points used for subsequent identification of road fences.
[0063] Specifically, the vehicle speed can be obtained through the information output by the vehicle, and the zero speed point distance can be determined by step S19. When the vehicle speed and the zero speed point distance are known, the following can be generated: Figure 8 If the road fence detected by the radar is tilted due to radar installation error or other reasons, the RV curve will be offset, such as Fig. 9 As shown, the RV curves of road fences with inclinations of 5 degrees, -5 degrees, and 0 degrees, respectively. The three RV curves have the same trend and are close in value.
[0064] It should be pointed out that the number of zero-speed points may be greater than one. For example, the road fence may include a left fence located on the left side of the vehicle and a right fence located on the right side of the vehicle and parallel to the left fence. In order to accurately identify each road fence, it is necessary to calculate the RV curve for each X0.
[0065] See also Fig.10In some embodiments of the present invention, the step S15 of “screening valid target points according to the RV curve of the road fence, the distance information and the speed information of the valid target points” includes:
[0066] S151: Substitute one of the distance information and the speed information of the valid target point into the formula to obtain the other of the distance to be screened and the speed to be screened;
[0067] S153: Compare the other of the distance to be screened and the speed to be screened with the other of the distance information and the speed information of the valid target point to screen the valid target point.
[0068] In this way, effective target points within a certain range of the RV curve can be quickly determined.
[0069] Specifically, in step S13, the distance information and speed information of the effective target point are determined, and a plurality of target points (R1, V1), (R2, V2), ..., (Rn, Vn) can be obtained.
[0070] In some embodiments, the distance information R of the effective target point is substituted into the formula of the RV curve, that is, R1, R2, ..., Rn are substituted into the formula of the RV curve respectively to calculate V'1, V'2, ..., V'n, and then V'1 is compared with V1, V'2 is compared with V2, ..., V'n is compared with Vn, and the effective point whose speed error does not exceed the first threshold interval (for example, [-1km / h, 1km / h]) is used as the effective point of the fence.
[0071] In some embodiments, the speed information V of the effective target point is substituted into the formula of the RV curve, that is, V1, V2, ..., Vn are substituted into the formula of the RV curve respectively to calculate R'1, R'2, ..., R'n, and then R'1 is compared with R1, R'2 is compared with R2, ..., R'n is compared with Rn, and the effective point whose distance error does not exceed the second threshold interval (for example, [-0.3m, 0.3m]) is used as the effective point of the fence.
[0072] See also Fig.11 In some embodiments of the present invention, step S17 includes:
[0073] S171: Convert the effective points of the fence to the XY plane for straight line detection, and determine the road fence according to the straight line detection result.
[0074] In this way, the straight fence can be accurately identified. It can be understood that in this embodiment, the straight fence is mainly identified. Since the number of effective fence points is much less than that of effective target points by using the method of step S151 and step S153, executing step S171 based on the effective fence points can greatly reduce the amount of calculation.
[0075] Specifically, the radar can be used as the coordinate origin, the x-axis can be determined along the width direction of the vehicle, and the y-axis can be determined along the length direction of the vehicle, so as to establish a rectangular coordinate system, and determine the rectangular coordinates of each effective point of the fence in the rectangular coordinate system, thereby facilitating straight line detection in the XY plane.
[0076] Furthermore, the angle information monitored by the radar can be used to convert each effective point of the fence to the XY plane, and straight line detection can be performed on the effective points of the fence on the XY plane. The detection method can use Hough transform to determine the number of clustered points, or use an algorithm to eliminate outliers for straight line fitting, etc., to determine whether the effective points of the fence meet the straight line characteristics.
[0077] In an example, the number of effective fence points is 11. The Hough transform is used to perform a calculation for every two effective fence points, for a total of 55 calculations. If the number of clustered points obtained is greater than 45, it can be determined that the effective fence points satisfy the straight line feature, that is, it is determined that there is a straight fence.
[0078] It should be noted that the specific numerical values mentioned above are only used as examples to illustrate the implementation of the present invention in detail, and should not be understood as limiting the present invention. In other examples or implementations or embodiments, other numerical values can be selected according to the present invention, and are not specifically limited here.
[0079] See also Fig.12 In some embodiments of the present invention, the method further comprises:
[0080] S21: Calculate the slope and intercept of the road barrier according to the straight line detection result.
[0081] In this way, it is convenient to determine the actual installation angle or installation angle deviation of the radar according to the slope and intercept of the road fence, so that the installation angle deviation of the radar can be corrected to make the identified fence parallel to the driving direction of the vehicle. It can be understood that when the road fence is a straight fence, due to the installation angle deviation of the radar or other reasons, the identified straight fence may not be parallel to the driving direction of the vehicle, but may be deflected to a certain extent, which needs to be corrected.
[0082] Specifically, when the effective points of the fence meet the characteristics of straight line detection, the slope and intercept of the road fence can be obtained by curve fitting or by calculating the slope k and intercept b values of the straight line between the effective points of the fence and averaging them.
[0083] The present invention proposes a computer-readable storage medium on which a road barrier detection program is stored. When the road barrier detection program is executed by a processor, the road barrier detection method of any of the above embodiments is implemented.
[0084] According to the computer-readable storage medium of the embodiment of the present invention, by screening valid target points through the RV curve of the road fence, a relatively small number of effective fence points are obtained, and then the road fence is identified on the effective fence points, which can reduce the computational complexity, improve the accuracy of identifying road fences and enhance environmental adaptability.
[0085] For example, when the program is executed by the processor, the following steps of the road barrier detection method are implemented:
[0086] S11: Acquire radar signal;
[0087] S13: determining a valid target point according to the radar signal, and determining distance information and speed information of the valid target point;
[0088] S15: determining the RV curve relationship of the road fence according to the zero speed point distance and the vehicle speed, and screening the valid target points according to the RV curve of the road fence, the distance information and the speed information of the valid target points to obtain the effective points of the fence;
[0089] S17: Identify road barriers based on effective points of the barriers.
[0090] It can be understood that the road barrier detection program includes the road barrier detection program code. The road barrier detection program code can be in source code form, object code form, executable file or some intermediate form, etc. Computer readable storage media can include: any entity or device that can carry the road barrier detection program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), and software distribution medium, etc. The processor can be a central processing unit, and can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
[0091] In order to implement the above embodiments, the present invention also provides a vehicle, which can implement the road barrier detection method of any of the above embodiments. Fig.13 As shown, the vehicle 100 proposed by the present invention includes a memory 102, a processor 104, and a road barrier detection program 106 stored in the memory 102 and executable on the processor 104. When the processor 104 executes the road barrier detection program 106, the road barrier detection method of any of the above embodiments is implemented.
[0092] According to the vehicle 100 of the embodiment of the present invention, by screening effective target points through the RV curve of the road fence, a relatively small number of effective fence points are obtained, and then the effective fence points are used to identify the road fence, which can reduce the computational complexity, improve the accuracy of identifying the road fence and enhance the environmental adaptability.
[0093] Specifically, the vehicle 100 includes but is not limited to a pure electric vehicle, a hybrid electric vehicle, an extended-range electric vehicle, a fuel vehicle, and the like.
[0094] It should be noted that the above explanations of the implementation and beneficial effects of the road barrier detection method are also applicable to the vehicle 100 of this embodiment, and will not be elaborated in detail here to avoid redundancy.
[0095] In order to implement the above embodiments, the present invention also provides a road barrier detection device, which can implement the road barrier detection method of any of the above embodiments. Fig.14 As shown, the road barrier detection device 200 proposed by the present invention includes an acquisition module 202, a determination module 204, a screening module 206 and an identification module 208. The acquisition module 202 is used to acquire radar signals. The determination module 204 is used to determine the effective target point according to the radar signal, and determine the distance information and speed information of the effective target point. The screening module 206 is used to determine the RV curve relationship of the road barrier according to the zero speed point distance and the vehicle speed, and screen the effective target point according to the RV curve of the road barrier, the distance information and speed information of the effective target point, and obtain the effective point of the barrier. The identification module 208 is used to identify the road barrier according to the effective point of the barrier.
[0096] According to the road barrier detection device 200 of the embodiment of the present invention, effective target points are screened through the RV curve of the road barrier to obtain a relatively small number of effective fence points, and then the effective fence points are used to identify the road barriers, which can reduce the computational complexity, improve the accuracy of identifying road barriers, and enhance environmental adaptability.
[0097] In some embodiments of the present invention, the determination module 204 includes a generation unit and a determination unit. The generation unit is used to perform a fast Fourier transform on the radar signal to generate a two-dimensional amplitude spectrum. The determination unit is used to determine the valid target point according to the two-dimensional amplitude spectrum.
[0098] In some embodiments of the present invention, the road barrier detection device 200 further includes a determining module, which is used to determine the distance of the effective target point with zero speed according to the speed information of the effective target point as the zero speed point distance.
[0099] In some embodiments of the present invention, the RV curve relationship satisfies the following formula: Among them, V0 is the vehicle speed, and X0 is the distance to the zero speed point.
[0100] In some embodiments of the present invention, the screening module 206 includes a substitution unit and a comparison unit. The substitution unit is used to substitute one of the distance information and the speed information of the valid target point into the formula to obtain the other of the distance to be screened and the speed to be screened. The comparison unit is used to compare the other of the distance to be screened and the speed to be screened with the other of the distance information and the speed information of the valid target point to screen the valid target point.
[0101] In some embodiments of the present invention, the recognition module 208 is used to convert the effective points of the fence to the XY plane for line detection, and determine the road fence according to the line detection result.
[0102] In some embodiments of the present invention, the road barrier detection device 200 further includes a calculation module, and the calculation module is used to calculate the slope and intercept of the road barrier according to the straight line detection result.
[0103] It should be noted that the above explanations of the implementation and beneficial effects of the road barrier detection method are also applicable to the road barrier detection device 200 of this embodiment, and will not be elaborated here in detail to avoid redundancy.
[0104] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0105] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only used for descriptive purposes and should not be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in the present embodiment. Therefore, the features defined by the terms "first", "second", etc. in the embodiments of the present invention can explicitly or implicitly indicate that the embodiment includes at least one of the features. In the description of the present invention, the word "multiple" means at least two or two or more, such as two, three, four, etc., unless otherwise clearly and specifically defined in the embodiments.
[0106] In the present invention, unless otherwise clearly specified or limited in the embodiments, the terms "installed", "connected", "connected" and "fixed" etc. in the embodiments should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integrated connection. It can be understood that it can also be a mechanical connection, an electrical connection, etc.; of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal connection of two elements, or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific implementation situation.
[0107] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A road barrier detection method, characterized in that: include: Acquire radar signals; Determine a valid target point according to the radar signal, and determine distance information and speed information of the valid target point; Determine the distance of the effective target point with zero speed according to the speed information of the effective target point as the zero speed point distance; Determine the RV curve relationship of the road fence according to the zero speed point distance and the vehicle speed, and screen the valid target point according to the RV curve of the road fence, the distance information and the speed information of the valid target point to obtain the fence valid point; wherein R is the distance information; V is the speed information; Performing road fence identification according to the effective points of the fence; The RV curve relationship satisfies the following formula: Wherein, V0 is the vehicle speed, X0 is the zero speed point distance; The valid target point is screened according to the RV curve of the road fence, the distance information and the speed information of the valid target point, including: Substituting one of the distance information and the speed information of the effective target point into the formula to obtain the other of the distance to be screened and the speed to be screened; The other of the distance to be screened and the speed to be screened is compared with the other of the distance information and the speed information of the valid target point to screen the valid target point.
2. The road barrier detection method according to claim 1, characterized in that: Determining a valid target point according to the radar signal includes: Performing a fast Fourier transform on the radar signal to generate a two-dimensional amplitude spectrum; The effective target point is determined according to the two-dimensional amplitude spectrum.
3. The road barrier detection method according to claim 1, characterized in that: The road fence recognition is performed according to the effective fence points, including: The effective points of the fence are converted to the XY plane for straight line detection, and the road fence is determined according to the straight line detection result.
4. The road barrier detection method according to claim 3, characterized in that: The method further comprises: The slope and intercept of the road barrier are calculated according to the straight line detection result.
5. A computer-readable storage medium, characterized in that: A road barrier detection program is stored thereon, and when the road barrier detection program is executed by a processor, the road barrier detection method according to any one of claims 1 to 4 is implemented.
6. A vehicle, characterized in that: The invention comprises a memory, a processor and a road barrier detection program stored in the memory and executable on the processor. When the processor executes the road barrier detection program, the road barrier detection method according to any one of claims 1 to 4 is implemented.
7. A road barrier detection device, characterized in that: include: An acquisition module, used for acquiring radar signals; A determination module, used to determine a valid target point according to the radar signal, and to determine distance information and speed information of the valid target point; A determination module is used to determine the distance of the effective target point with zero speed according to the speed information of the effective target point as the zero speed point distance; A screening module is used to determine the RV curve relationship of the road fence according to the zero speed point distance and the vehicle speed, and screen the effective target point according to the RV curve of the road fence, the distance information and the speed information of the effective target point to obtain the effective point of the fence; wherein R is the distance information; V is the speed information; An identification module, used for identifying road barriers according to the effective points of the barriers; The RV curve relationship satisfies the following formula: Wherein, V0 is the vehicle speed, X0 is the zero speed point distance; The screening module includes a substitution unit and a comparison unit; the substitution unit is used to substitute one of the distance information and the speed information of the valid target point into the formula to obtain the other of the distance to be screened and the speed to be screened; the comparison unit is used to compare the other of the distance to be screened and the speed to be screened with the other of the distance information and the speed information of the valid target point to screen the valid target point.
Citation Information
Patent Citations
Vehicle-mounted millimeter wave radar device and target detection method
CN110058239A
Guardrail detection method and device, storage medium and movable platform
CN112313539A