WO2020198973A1 - Method for using microwave radar to detect stationary object near to barrier, and millimeter-wave radar - Google Patents

Abstract

A method for using a microwave radar to detect a stationary object near to a barrier, and a millimeter-wave radar. The method comprises: acquiring a barrier dispersion of a current frame (S101); determining, according to the barrier dispersion of the current frame, the probability that a stationary reflection point falls within a barrier region (S102); updating a target evaluation value of the stationary reflection point within the barrier region, according to a target evaluation value of the stationary reflection point within the barrier of the previous frame and the probability that the stationary reflection point of the current frame falls within the barrier region (S103); and determining, according to the updated target evaluation value of the stationary reflection point within the barrier, whether the stationary reflection point in the barrier region is a stationary object (S104). The method accurately detects a stationary object that is not part of a barrier but is located near the barrier, thereby reducing the probability of missed detection by an automatic emergency braking (AEB) system, improving the robustness of ADAS and AD systems overall, and improving user experience.

Description

Method for detecting stationary objects near fence by microwave radar and millimeter wave radar

Manual

Technical field

The present invention generally relates to the field of automatic driving technology, and more particularly relates to a method for microwave radar to detect stationary objects near fences and millimeter wave radar.

Background technique

In recent years, the fields of Advanced Driver Assistant System (ADAS) and Autonomous Driving (AD) have developed rapidly. Millimeter-wave radar is widely used due to its advantages such as all-weather, all-weather, long range, and high speed measurement accuracy. However, distinguishing between fences and stationary vehicles near fences has always been a problem and difficulty in the field of vehicle-mounted millimeter wave radar. Since fences and stationary vehicles are both strongly reflective objects and have no speed, it is very easy to cluster stationary vehicles and adjacent fences into one track when vehicle-mounted radar does object tracking and clustering, making stationary vehicles mistaken for It is part of the fence. In this case, the automatic emergency braking system (AEB) will not be activated normally, resulting in a poor user experience of the ADAS system.

In order to solve the above technical problems, the present invention proposes a new microwave radar method for detecting stationary objects near the fence.

Summary of the invention

The present invention is proposed to solve at least one of the above-mentioned problems. Specifically, one aspect of the present invention provides a method for microwave radar to detect stationary objects near a fence, the method including:

Get the fence dispersion of the current frame;

Determine the probability that the static reflection point falls within the fence area according to the fence dispersion of the current frame;

According to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area, update the static reflection in the fence area Point’s target evaluation value; and

According to the updated target evaluation value of the stationary reflection point in the fence, it is determined whether the stationary reflection point in the fence area is a stationary object.

Exemplarily, the obtaining the fence dispersion of the current frame includes:

Obtain the position information of the static reflection point of the current frame;

Determine the fence fitting straight line according to the position information of the static reflection point in the current frame;

According to the fence fitting straight line and the static reflection points participating in the fitting, the fence dispersion degree of the current frame is calculated.

Exemplarily, the position information of the stationary reflection point is the position information of the stationary reflection point in a Cartesian coordinate system, wherein the Cartesian coordinate system takes the center point of the front of the vehicle as the center of the circle, and takes the forward direction of the vehicle as The y-axis is the x-axis which is perpendicular to the y-axis and parallel to the horizontal plane.

Exemplarily, the fence dispersion of the current frame is determined according to the slope and intercept of the fence fitting straight line, and the longitudinal distance and the lateral distance of the stationary reflection points participating in the fence fitting in the rectangular coordinate system .

Exemplarily, the probability that the static reflection point falls within the fence area is determined according to the dispersion of the fence and the longitudinal distance and the lateral distance of the static reflection point.

Exemplarily, the fence area is updated according to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area The target evaluation value of the static reflection point within includes:

Obtain the tracking result of each stationary reflection point in consecutive multiple frames, and update the target evaluation value of the stationary reflection point in the fence according to the accumulated result of the multiple frames.

Exemplarily, when the target evaluation value is lower than the predetermined threshold and the number of times of detection of the stationary reflection point is greater than the threshold number of times, it is determined that the stationary reflection point is a stationary object.

Exemplarily, the fence area is updated according to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area The target evaluation value of the static reflection point within specifically includes:

If the probability that the static reflection point of the current frame falls in the fence area is greater than the first threshold, the sum of the target evaluation value of the static reflection point in the fence of the previous frame and the first additional value is calculated and the sum is added to The maximum target evaluation value is compared, and the maximum value of the two is the target evaluation value in the fence of the static reflection point of the current frame;

If the probability that the static reflection point of the current frame falls in the fence area is less than the second threshold, the difference between the target evaluation value of the static reflection point in the fence of the previous frame and the second additional value is calculated and the difference The value is compared with the minimum target evaluation value, and the minimum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame.

Exemplarily, the acquiring position information of the static reflection point of the current frame includes:

Based on millimeter wave radar to detect static reflection points in front of or behind the vehicle to obtain the position information of the static reflection points in the current frame.

Another aspect of the present invention provides a millimeter wave radar, the millimeter wave radar includes:

One or more processors, working individually or together, and the processors are used to:

Get the fence dispersion of the current frame;

Determine the probability that the static reflection point falls within the fence area according to the fence dispersion of the current frame;

According to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area, update the static reflection in the fence area Point’s target evaluation value; and

According to the updated target evaluation value of the stationary reflection point in the fence, it is determined whether the stationary reflection point in the fence area is a stationary object.

Exemplarily, it also includes:

Antenna device for transmitting millimeter wave signals and receiving reflected signals; and

A signal processing circuit, electrically connected to the antenna device, for processing the reflected signal and converting it into a data signal,

Wherein, the processor is in communication connection with the signal processing circuit, and is used to process the data signal sent by the signal processing circuit.

Exemplarily, the processor is configured to determine a fence fitting straight line according to the position information of the stationary reflection point of the current frame, and calculate the current frame according to the fence fitting straight line and the stationary reflection points participating in the fitting The fence dispersion.

Exemplarily, the position information of the stationary reflection point is the position information of the stationary reflection point in a Cartesian coordinate system, wherein the Cartesian coordinate system takes the center point of the front of the vehicle as the center of the circle, and takes the forward direction of the vehicle as The y-axis is the x-axis which is perpendicular to the y-axis and parallel to the horizontal plane.

Exemplarily, the fence dispersion of the current frame is determined according to the slope and intercept of the fence fitting straight line, and the longitudinal distance and the lateral distance of the stationary reflection points participating in the fence fitting in the rectangular coordinate system .

Exemplarily, the probability that the static reflection point falls within the fence area is determined according to the dispersion of the fence and the longitudinal distance and the lateral distance of the static reflection point.

Exemplarily, the processor is further configured to obtain tracking results of consecutive multiple frames of each static reflection point, and update the target evaluation value of the static reflection point in the fence according to the accumulated result of the multiple frames.

Exemplarily, when the target evaluation value is lower than the predetermined threshold and the number of times of detection of the stationary reflection point is greater than the threshold number of times, the processor determines that the stationary reflection point is a stationary object.

Exemplarily, if the probability that the static reflection point of the current frame falls in the fence area is greater than the first threshold, the processor calculates the target evaluation value of the static reflection point in the fence of the previous frame and the first additional And compare the sum with the maximum target evaluation value, and take the maximum of the two as the target evaluation value in the fence of the static reflection point of the current frame;

If the probability that the static reflection point of the current frame falls in the fence area is less than the second threshold, the processor calculates the difference between the target evaluation value of the static reflection point in the fence of the previous frame and the second additional value The difference is compared with the minimum target evaluation value, and the minimum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame.

Exemplarily, the processor detects a static reflection point in front of or behind the vehicle based on a millimeter wave radar to obtain the position information of the static reflection point in the current frame.

Another aspect of the present invention provides a computer storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the foregoing method is implemented.

Another aspect of the present invention provides a vehicle including a vehicle body and the aforementioned millimeter wave radar, the millimeter wave radar being installed on the front side or/and the rear side of the vehicle body.

The method of the embodiment of the present invention, without increasing the hardware cost, is based on the target evaluation value of the static reflection point in the fence of the previous frame, and the static reflection point of the current frame falls on the fence Probability in the area, update the target evaluation value of the static reflection point in the fence area, and determine the static reflection in the fence area according to the updated target evaluation value of the static reflection point in the fence Whether the point is a stationary object, so as to accurately detect whether the stationary reflection point in the fence area is a stationary object, and reduce the probability of missed detection of the automatic emergency braking (AEB) system, thereby improving the robustness and improvement of the entire ADAS and AD system user experience.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative labor.

Figure 1 shows a schematic flow chart of a method for microwave radar to detect stationary objects near a fence in an embodiment of the present invention;

Figure 2 shows a schematic diagram of the principle of a method for detecting stationary objects near a fence by a microwave radar in an embodiment of the present invention;

Fig. 3 shows a schematic block diagram of a millimeter wave radar in an embodiment of the present invention.

detailed description

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

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

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

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

In order to thoroughly understand the present invention, a detailed structure will be proposed in the following description to explain the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows. However, in addition to these detailed descriptions, the present invention may also have other embodiments.

In order to solve the problem that stationary vehicles near the fence will be misidentified as part of the fence, the current vehicle radar usually adopts the following methods:

1. By increasing the number of receiving antenna channels, the accuracy and resolution of angle measurement can be improved. This can enhance the accuracy of the angle measurement of the vehicle near the fence by the radar, thereby distinguishing between the fence and the stationary vehicle near the fence. However, this method will greatly increase the complexity of antenna design, antenna size, and the cost of antenna and high-frequency plates. At the same time, the computational overhead of DOA (direction of arrival) algorithm will increase significantly due to the increase in the number of channels, which will make the hardware of the processor The cost has risen sharply.

2. By reducing the size of the associated gate of the horizontal distance in the radar track tracking management. Although this problem can be solved to a certain extent. But this will lead to a significant increase in the probability of splitting the track of the vehicle or fence. This will be a result that is not worth the loss.

Therefore, in order to solve the above-mentioned problems, the present invention provides a microwave radar method for detecting stationary objects near a fence. As shown in FIG. 1, the method includes:

Step S101: Obtain the fence dispersion of the current frame;

Step S102: Determine the probability that the static reflection point falls within the fence area according to the fence dispersion of the current frame;

Step S103, according to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area, update all the points in the fence area. The target evaluation value of the static reflection point; and

Step S104: Determine whether the static reflection point in the fence area is a stationary object according to the updated target evaluation value of the static reflection point in the fence.

The method of the embodiment of the present invention, without increasing the hardware cost, is based on the target evaluation value of the static reflection point in the fence of the previous frame, and the static reflection point of the current frame falls on the fence Probability in the area, update the target evaluation value of the static reflection point in the fence area, and determine the static reflection in the fence area according to the updated target evaluation value of the static reflection point in the fence Whether the point is a stationary object, so as to accurately detect stationary objects that are not part of the fence but located near the fence, reduce the probability of missed detection by the automatic emergency braking (AEB) system, thereby improving the robustness of the entire ADAS and AD system and improving users Experience.

In the following, in conjunction with the accompanying drawings, a method for detecting stationary objects near a fence by a microwave radar of the present application will be described in detail. In the case of no conflict, the following embodiments and features in the implementation can be combined with each other.

In the embodiment shown in FIG. 1, the method for detecting stationary objects near a fence by a microwave radar includes the following steps:

First, perform step S101 to obtain the fence dispersion of the current frame.

The fence dispersion of the current frame can be obtained by any suitable method. In a specific example, the obtaining the fence dispersion of the current frame specifically includes: obtaining the position information of the stationary reflection point of the current frame; determining the fence fitting straight line according to the position information of the stationary reflection point of the current frame; The fence is fitted with a straight line and the static reflection points participating in the fitting, and the fence dispersion of the current frame is calculated.

Based on microwave radar to detect static reflection points in front of or behind the vehicle to obtain the position information of the static reflection points in the current frame. Among them, the microwave radar includes millimeter wave radar. The millimeter-wave radar has high accuracy of ranging and speed measurement, and weather and environmental factors such as light and weather basically have no influence on the detection of millimeter-wave radar, so it is very suitable for the fence detection of the present invention. Of course, those skilled in the art can understand that the present invention is not limited to using millimeter radar waves for target detection, and other methods and means can also be used for detection.

Millimeter wave radar uses millimeter wave (millimeter wave), usually millimeter wave refers to the frequency domain of 30 to 300 GHz (wavelength is 1 to 10 mm), and millimeter wave is an electromagnetic wave between infrared light wave and microwave frequency band.

In an example, a millimeter wave radar usually includes an antenna device for transmitting millimeter wave signals and receiving reflected signals. The millimeter wave signal transmitted by the antenna device is reflected by the target and then received by the receiving module of the antenna device to obtain the desired signal. The reflection point of the measurement target can also be called a point cloud. The reflection point of the target to be measured includes the static reflection point of a stationary object. The reflection point includes position information of the static reflection point.

The millimeter wave radar is installed on a mobile platform, such as a vehicle. The vehicle may also include an autonomous vehicle. Optionally, the position information of the stationary reflection point is the position information of the stationary reflection point in a Cartesian coordinate system, wherein the Cartesian coordinate system takes the center point of the front of the vehicle as the center of the circle, and uses the direction of the front of the vehicle as the y-axis , And the direction perpendicular to the y-axis and parallel to the horizontal plane is the x-axis, as shown in Figure 2 in the rectangular coordinate system.

In an example, the fence fitting straight line is determined according to the position information of the static reflection point of the current frame. For example, the static reflection point within a predetermined range on one side of the vehicle can be obtained, and according to the adjacent static reflection point within the predetermined range The points are fitted as straight lines. For example, usually when a vehicle is driving, the static reflection points detected within a predetermined range (for example, 2-50m) on both sides of the vehicle are usually reflection points of a fence. Therefore, the predetermined static reflection point can be determined according to the position information of the static reflection point in the current frame. The neighboring stationary obstacles in the range are used as the basis to determine the fence fitting straight line, as shown in Figure 2. Or other methods that can determine the fence fitting straight line can also be applied to the present invention.

In one example, the fence dispersion of the current frame is calculated according to the fence fitting straight line and the stationary reflection points participating in the fitting. For example, the fence dispersion of the current frame is calculated according to the slope and the intercept of the fence fitting straight line. Distance, and the vertical and horizontal distances in the Cartesian coordinate system of the stationary reflection points participating in the fence fitting.

Specifically, the fence dispersion σ _gr is calculated according to the fence fitting straight line and the reflection points participating in the fence fitting, wherein the calculation formula of the fence dispersion is as follows:

Where k and b are respectively the slope and intercept of the fence fitting straight line in the rectangular coordinate system as shown in Fig. 2, and Ry _i and Rx _i are the static reflection points involved in the fence fitting at the right angle The longitudinal distance (that is, the distance on the y-axis) and the horizontal distance (the distance on the x-axis) in the coordinate system.

The above formula is only used as a specific example for calculating the dispersion of the fence, and other calculation methods for the dispersion of the fence can also be applied to the embodiment of the present invention.

Next, step S102 is executed to determine the probability that the static reflection point falls within the fence area according to the fence dispersion of the current frame.

In an example, the probability that the static reflection point falls within the fence area may be determined according to the dispersion of the fence and the longitudinal and lateral distances of the static reflection point. The longitudinal and lateral distances refer to the aforementioned right angles. The distance on the y axis and the distance on the x axis in the coordinate system.

Specifically, using the fence dispersion to estimate the probability of whether the static reflection point falls within the fence area includes: calculating the probability P _gr that the static reflection point falls within the fence area based on the fence dispersion, where The probability conforms to the normal distribution, and its standard deviation and mean are denoted as σ and μ, respectively. The calculation formula of the probability P _gr is as follows:

μ=k*Rx+b

σ=σ _gr

Among them, Rx and Ry are the longitudinal distance and the lateral distance of the static reflection point, respectively, and the dispersion of the σ _gr fence.

Then, step S103 is executed to update the fence area according to the target evaluation value of the static reflection point in the fence of the previous frame and the probability that the static reflection point of the current frame falls within the fence area The target evaluation value of the static reflection point within.

Specifically, the continuous multiple frames of tracking results of each static reflection point are obtained, and the target evaluation value of the static reflection point in the fence is updated according to the accumulated results of the multiple frames.

In an example, if the probability that the static reflection point of the current frame falls in the fence area is greater than the first threshold, the sum of the target evaluation value of the static reflection point in the fence of the previous frame and the first additional value is calculated The sum is compared with the maximum target evaluation value, and the maximum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame. The specific value of the first threshold can be set reasonably according to actual needs, or the value of the first threshold can also be set based on prior experience. For example, the first threshold can be set between 50% and 90%. Any value between.

The first additional value can be set reasonably according to actual needs. The specific value of the first additional value is not specifically limited here, and the first additional value may also be a value obtained based on prior experience.

Specifically, the target evaluation value in the fence of the static reflection point of each frame can be calculated and updated according to a formula, the formula is as follows:

If P _gr >P _on

GuardRail _n = max(GuardRail _max ,GuardRail _n-1 +GuardRail _add )

Among them, P _on represents the first threshold, GuardRail _n represents the target evaluation value in the fence of the static reflection point of the current frame, GuardRail _max represents the maximum target evaluation value, and the maximum target evaluation value can be the value of the static reflection point in the fence of multiple frames The maximum value of the target evaluation value, GuardRail _n-1 represents the target evaluation value of the static reflection point in the fence of the previous frame, and GuardRail _add represents the first additional value.

In another example, if the probability that the static reflection point of the current frame falls on the fence area is less than the second threshold, calculate the target evaluation value of the static reflection point in the fence of the previous frame and the second additional value. The difference is compared with the minimum target evaluation value, and the minimum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame. Wherein, the specific value of the second threshold can be set reasonably according to actual needs, or the value of the second threshold can also be set based on prior experience, for example, the second threshold can be set at 10%-50 Any value between %, or the aforementioned first threshold and second threshold may also be the same value.

The second additional value can be set reasonably according to actual needs. The specific value of the second additional value is not specifically limited here, and the second additional value may also be a value obtained based on prior experience.

Specifically, the target evaluation value in the fence of the static reflection point of each frame can be calculated and updated according to a formula, the formula is as follows:

If P _gr <P _off

GuardRail _n = min (GuardRail _min ,GuardRail _n-1 -GuardRail _minus )

Among them, GuardRail _n represents the target evaluation value of the current frame of the static reflection point, GuardRail _min represents the minimum target evaluation value of the static reflection point, GuardRail _minus represents the second additional value, which can be obtained based on prior experience, GuardRail _n-1 Represents the target evaluation value of the previous frame, and P _off represents the second threshold.

Among them, as shown in FIG. 2, through the probability distribution of the static reflection point falling on the fence area, stationary objects that are not in the fence area (a stationary vehicle as shown in FIG. 2) can be excluded from the fence area.

Through the above method, the target evaluation value of the static reflection point in the fence of the current frame can be calculated, and the target evaluation value can be used to evaluate whether the static reflection point is a static reflection point in the fence.

Further, step S104 is executed to determine whether the stationary reflection point in the fence area is a stationary object according to the updated target evaluation value of the stationary reflection point in the fence.

Specifically, according to the updated target evaluation value of the stationary reflection point in the fence, it is determined whether the stationary reflection point in the fence area is a stationary object, for example, when the target evaluation value is lower than a predetermined threshold and static reflection When the number of detection times of the point is greater than the threshold number of times, it is determined that the stationary reflection point is a stationary object, that is, it is determined that the stationary reflection point is a stationary object near the fence, such as a stationary vehicle. Wherein, the predetermined threshold can be obtained based on prior experience, and is not specifically limited here.

When the target evaluation value is lower than the predetermined threshold, it indicates that the static reflection point is not part of the fence, but is the static reflection point on other stationary objects near the fence. At the same time, the number of detections of static reflection points should be greater than the threshold number of times to avoid too large errors in the target evaluation value due to too few detection times, thereby affecting the judgment of stationary objects.

In summary, the method of the embodiment of the present invention, without increasing the hardware cost, is based on the target evaluation value of the static reflection point in the fence of the previous frame and the static reflection point of the current frame. For the probability that the reflection point falls within the fence area, the target evaluation value of the static reflection point in the fence area is updated, and the fence is determined according to the updated target evaluation value of the static reflection point in the fence Whether the static reflection point in the area is a static object, so that it can accurately detect the static object that does not belong to the fence but is located near the fence, reducing the probability of missed detection by the automatic emergency braking (AEB) system, thereby improving the robustness of the entire ADAS and AD system Great, enhance user experience.

FIG. 3 shows a schematic block diagram of a millimeter wave radar 300 in an embodiment of the present invention.

As shown in FIG. 3, the millimeter wave radar 300 includes one or more processors 303, which work individually or together, and the processors are used to: obtain the fence dispersion of the current frame; according to the fence dispersion of the current frame, Determine the probability that the static reflection point falls within the fence area; according to the target evaluation value of the static reflection point in the fence of the previous frame, and the static reflection point of the current frame falls within the fence area Update the target evaluation value of the static reflection point in the fence area; and determine the static reflection point in the fence area according to the updated target evaluation value of the static reflection point in the fence Whether it is a stationary object.

Further, the processor 303 may be a central processing unit (CPU), an image processing unit (GPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a data processing capability and/or instruction execution capability. Other forms of processing units, and can control other components in the millimeter wave radar 300 to perform desired functions. The processor can execute the instructions stored in the memory to execute the method for detecting stationary objects near a fence by a microwave radar described herein. For example, the processor 303 can include one or more embedded processors, processor cores, microprocessors, logic circuits, hardware finite state machines (FSM), digital signal processors (DSP), or combinations thereof.

In an example, the processor 303 is configured to determine a fence fitting straight line according to the position information of the stationary reflection point of the current frame, and according to the fence fitting straight line and the stationary reflection points participating in the fitting, Calculate the fence dispersion of the current frame. Optionally, the position information of the stationary reflection point is the position information of the stationary reflection point in a Cartesian coordinate system, wherein the Cartesian coordinate system takes the center point of the front of the vehicle as the center of the circle, and the forward direction of the vehicle is The y-axis is the x-axis which is perpendicular to the y-axis and parallel to the horizontal plane.

In an example, the fence dispersion of the current frame is based on the slope and intercept of the fence fitting straight line, and the longitudinal distance and the lateral distance of the stationary reflection points involved in the fence fitting in the rectangular coordinate system. determine.

Optionally, the probability that the static reflection point falls within the fence area is determined according to the dispersion of the fence and the longitudinal distance and the lateral distance of the static reflection point.

In an example, the processor 303 is further configured to obtain the tracking result of each stationary reflection point in consecutive multiple frames, and update the target evaluation value of the stationary reflection point in the fence according to the accumulated result of the multiple frames. Optionally, when the target evaluation value is lower than a predetermined threshold and the number of detections of the stationary reflection point is greater than the threshold number of times, the processor 303 determines that the stationary reflection point is a stationary object.

In an example, if the probability that the static reflection point of the current frame falls in the fence area is greater than the first threshold, the processor calculates the target evaluation value of the static reflection point in the fence of the previous frame and the first Add the sum of additional values and compare the sum with the maximum target evaluation value, and take the maximum of the two as the target evaluation value within the fence of the static reflection point of the current frame; if the static reflection point of the current frame falls on the fence area If the probability is less than the second threshold, the processor calculates the difference between the target evaluation value of the stationary reflection point in the fence of the previous frame and the second additional value and compares the difference with the minimum target evaluation value , Take the minimum of the two as the target evaluation value in the fence of the static reflection point of the current frame.

In an example, the processor 303 detects a static reflection point in front of or behind the vehicle based on a millimeter wave radar to obtain position information of the static reflection point in the current frame.

As shown in FIG. 3, the millimeter wave radar 300 further includes an antenna device 301, which is used to transmit millimeter wave signals and receive reflected signals; millimeter wave radar uses millimeter waves (millimeter waves), usually millimeter waves refer to 30-300 GHz In the frequency domain (wavelength is 1-10mm), millimeter wave is an electromagnetic wave between infrared light wave and microwave frequency band.

In one example, the millimeter wave radar 300 generally includes an antenna device 301 for transmitting millimeter wave signals and receiving reflected signals. The millimeter wave signals transmitted by the antenna device are reflected by the target and then received by the receiving module of the antenna device to obtain The reflection point to the target to be measured can also be called a point cloud. The reflection point of the target to be measured includes the static reflection point of a stationary object. The reflection point includes position information of the static reflection point. Wherein, the antenna device 301 may include an array antenna (such as a transmitting antenna) dedicated to transmitting millimeter wave signals and an array antenna (such as a receiving antenna) dedicated to receiving reflected signals.

In an example, the millimeter wave radar 300 further includes a signal processing circuit 302, electrically connected to the antenna device 301, for processing the reflected signal and converting it into a data signal, wherein the processor 303 is connected to the signal The processing circuit 302 is connected in communication and is used to process the data signal sent by the signal processing circuit 302. The signal processing circuit 302 and the processor 303 may communicate in a wired or wireless manner.

The signal processing circuit 302 includes an incident wave estimation unit AU. The incident wave estimating unit AU infers the distance to the source of the incident wave, namely the target, the relative velocity of the target, and the orientation of the target through a well-known algorithm, and generates a data signal representing the estimation result, that is, the signal processing circuit is electrically connected to the antenna device , Used to process the reflected signal and convert it into a data signal, the data signal including the position information of the static reflection point, etc.

The signal processing circuit in the embodiment of the present invention is not limited to a single circuit, but also includes a form in which a combination of multiple circuits is generally understood as a functional element. The signal processing circuit 302 may also be implemented by one or more systems on a chip (SoC). For example, a part or all of the signal processing circuit 302 may also be a programmable logic device (PLD), that is, an FPGA (Field-Programmable Gate Array). In this case, the signal processing circuit 302 includes a plurality of arithmetic elements (for example, general logic and multipliers) and a plurality of storage elements (for example, a look-up table or a memory module). Alternatively, the signal processing circuit 302 may also be a collection of a general-purpose processor and a main storage device. The signal processing circuit 302 may also be a circuit including a processor core and a memory. These can function as the signal processing circuit 302.

It should be noted that the components and structure of the millimeter wave radar 300 shown in FIG. 3 are only exemplary and not restrictive, and the components of the millimeter wave radar 300 may also have other components and structures as required.

In addition, the embodiment of the present invention also provides a computer storage medium on which a computer program is stored. When the computer program is executed by the processor, the method for detecting stationary objects near the fence by the microwave radar of the embodiment of the present invention can be realized. For example, the computer storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk Read-only memory (CD-ROM), USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may run the program instructions stored in the memory to implement the functions (implemented by the processor) in the embodiments of the present invention described herein And/or other desired functions, for example, to perform the corresponding steps of the method for detecting stationary objects near a fence by a microwave radar according to an embodiment of the present invention. Various application programs and various data, such as various data used and/or generated by the application program, can also be stored in the computer-readable storage medium.

In addition, an embodiment of the present invention also provides a vehicle, which includes the millimeter wave radar in the foregoing embodiment. The vehicle may include an autonomous vehicle, or other types of vehicles.

Specifically, the vehicle includes a vehicle body, and the millimeter-wave radar may be installed on the front side or/and the rear side of the vehicle body, or other suitable positions. Among them, one or more millimeter wave radars can be installed on the vehicle body.

Based on this millimeter-wave radar, the aforementioned microwave radar method for detecting stationary objects near the fence can be realized, so that without increasing the hardware cost, according to the target evaluation value of the stationary reflection point in the fence in the previous frame, and According to the probability that the static reflection point of the current frame falls within the fence area, the target evaluation value of the static reflection point in the fence area is updated according to the updated value of the static reflection point in the fence. The target evaluation value is used to determine whether the static reflection point in the fence area is a static object, so as to accurately detect the static object that does not belong to the fence but is located near the fence, reducing the probability of missed detection by the automatic emergency braking (AEB) system, thereby Improve the robustness of the entire ADAS and AD system and enhance user experience.

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

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

In the several embodiments provided in this application, it should be understood that the disclosed device and method may be implemented in other ways. For example, the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another device, or some features can be ignored or not implemented.

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

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

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

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

The various component embodiments of the present invention may be implemented by hardware, or by software modules running on one or more processors, or by their combination. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some modules according to the embodiments of the present invention. The present invention can also be implemented as a device program (for example, a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may have the form of one or more signals. Such signals can be downloaded from Internet websites, or provided on carrier signals, or provided in any other form.

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

Claims (21)

1. A method for microwave radar to detect stationary objects near a fence, characterized in that the method includes:

   Get the fence dispersion of the current frame;

   Determine the probability that the static reflection point falls within the fence area according to the fence dispersion of the current frame;

   According to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area, update the static reflection in the fence area Point’s target evaluation value; and

   According to the updated target evaluation value of the stationary reflection point in the fence, it is determined whether the stationary reflection point in the fence area is a stationary object.
2. The method according to claim 1, wherein the obtaining the fence dispersion of the current frame comprises:

   Obtain the position information of the static reflection point of the current frame;

   Determine the fence fitting straight line according to the position information of the static reflection point in the current frame;

   According to the fence fitting straight line and the static reflection points participating in the fitting, the fence dispersion degree of the current frame is calculated.
3. The method of claim 2, wherein the position information of the static reflection point is the position information of the static reflection point in a rectangular coordinate system, wherein the rectangular coordinate system is based on the center point of the front of the vehicle. The center of the circle is the y-axis in the forward direction of the vehicle, and the x-axis in the direction perpendicular to the y-axis and parallel to the horizontal plane.
4. The method of claim 3, wherein the fence dispersion of the current frame is based on the slope and intercept of the fence fitting straight line, and the position of the stationary reflection points involved in the fence fitting in the rectangular coordinate system The longitudinal distance and the lateral distance within are determined.
5. The method according to claim 1, wherein the probability that the static reflection point falls within the fence area is determined according to the dispersion degree of the fence and the longitudinal distance and the lateral distance of the static reflection point.
6. The method according to claim 1, wherein the target evaluation value of the static reflection point in the fence according to the previous frame, and the static reflection point of the current frame falls in the fence area Update the target evaluation value of the static reflection point in the fence area, including:

   Obtain the tracking result of each stationary reflection point in consecutive multiple frames, and update the target evaluation value of the stationary reflection point in the fence according to the accumulated result of the multiple frames.
7. The method according to claim 1 or 6, wherein when the target evaluation value is lower than a predetermined threshold and the number of detections of the stationary reflection point is greater than the threshold number of times, it is determined that the stationary reflection point is a stationary object.
8. The method according to claim 1, wherein the target evaluation value of the static reflection point in the fence according to the previous frame, and the static reflection point of the current frame falls in the fence area The update of the target evaluation value of the static reflection point in the fence area specifically includes:

   If the probability that the static reflection point of the current frame falls in the fence area is greater than the first threshold, the sum of the target evaluation value of the static reflection point in the fence of the previous frame and the first additional value is calculated and the sum is added to The maximum target evaluation value is compared, and the maximum value of the two is the target evaluation value in the fence of the static reflection point of the current frame;

   If the probability that the static reflection point of the current frame falls in the fence area is less than the second threshold, the difference between the target evaluation value of the static reflection point in the fence of the previous frame and the second additional value is calculated and the difference The value is compared with the minimum target evaluation value, and the minimum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame.
9. 3. The method according to claim 2, wherein said obtaining the position information of the static reflection point of the current frame comprises:

   Based on millimeter wave radar to detect static reflection points in front of or behind the vehicle to obtain the position information of the static reflection points in the current frame.
10. A millimeter wave radar, characterized in that the millimeter wave radar includes:

    One or more processors, working individually or together, and the processors are used to:

    Get the fence dispersion of the current frame;

    Determine the probability that the static reflection point falls within the fence area according to the fence dispersion of the current frame;

    According to the target evaluation value of the static reflection point in the fence of the previous frame, and the probability that the static reflection point of the current frame falls within the fence area, update the static reflection in the fence area Point’s target evaluation value; and

    According to the updated target evaluation value of the stationary reflection point in the fence, it is determined whether the stationary reflection point in the fence area is a stationary object.
11. The millimeter wave radar of claim 10, further comprising:

    Antenna device for transmitting millimeter wave signals and receiving reflected signals; and

    A signal processing circuit, electrically connected to the antenna device, for processing the reflected signal and converting it into a data signal,

    Wherein, the processor is in communication connection with the signal processing circuit, and is used to process the data signal sent by the signal processing circuit.
12. The millimeter wave radar of claim 10, wherein the processor is configured to determine a fence fitting straight line according to the position information of the static reflection point of the current frame, and according to the fence fitting straight line and the participating positions According to the fitted static reflection point, calculate the fence dispersion of the current frame.
13. The millimeter-wave radar according to claim 12, wherein the position information of the stationary reflection point is the position information of the stationary reflection point in a rectangular coordinate system, wherein the rectangular coordinate system is based on the center of the front of the vehicle. The point is the center of the circle, and the direction in front of the vehicle is the y axis, and the direction perpendicular to the y axis and parallel to the horizontal plane is the x axis.
14. The millimeter-wave radar according to claim 13, wherein the fence dispersion of the current frame is based on the slope and intercept of the fence fitting line, and the position of the stationary reflection point participating in the fence fitting at the right angle The vertical distance and horizontal distance in the coordinate system are determined.
15. The millimeter wave radar according to claim 11, wherein the probability that the static reflection point falls within the fence area is determined according to the dispersion of the fence and the longitudinal distance and the lateral distance of the static reflection point.
16. The millimeter-wave radar according to claim 11, wherein the processor is further configured to obtain the tracking results of each static reflection point in consecutive multiple frames, and update the static tracking results in the fence according to the accumulated results of the multiple frames. The target evaluation value of the reflection point.
17. The millimeter-wave radar according to claim 11 or 16, wherein when the target evaluation value is lower than a predetermined threshold and the number of detections of the stationary reflection point is greater than the threshold number of times, the processor determines that the stationary reflection point is a stationary object .
18. The millimeter wave radar according to claim 11, wherein:

    If the probability that the static reflection point of the current frame falls in the fence area is greater than the first threshold, the processor calculates the sum of the target evaluation value of the static reflection point in the fence of the previous frame and the first additional value Compare the sum with the maximum target evaluation value, and take the maximum of the two as the target evaluation value in the fence of the static reflection point of the current frame;

    If the probability that the static reflection point of the current frame falls in the fence area is less than the second threshold, the processor calculates the difference between the target evaluation value of the static reflection point in the fence of the previous frame and the second additional value The difference is compared with the minimum target evaluation value, and the minimum of the two is taken as the target evaluation value in the fence of the static reflection point of the current frame.
19. The millimeter wave radar according to claim 12, wherein the processor detects a static reflection point in front or behind the vehicle based on the millimeter wave radar to obtain the position information of the static reflection point in the current frame.
20. A computer storage medium having a computer program stored thereon, characterized in that the method according to any one of claims 1 to 9 is implemented when the program is executed by a processor.
21. A vehicle, characterized in that the vehicle comprises a vehicle body and the millimeter wave radar according to any one of claims 10 to 19, and the millimeter wave radar is installed on the front side or/and the rear side of the vehicle body.

Images