阅读说明：本技术 一种角度自标定方法、汽车雷达系统以及汽车 (Angle self-calibration method, automobile radar system and automobile ) 是由 陈承文 周珂 朱涛 方勇军 朱信鹏 于 2020-04-30 设计创作，主要内容包括：本发明实施例涉及汽车雷达技术领域,公开了一种角度自标定方法、汽车雷达系统以及汽车。其中,所述角度自标定方法应用于汽车雷达系统,包括汽车雷达,所述汽车雷达系统安装于汽车,所述方法包括：检测所述汽车是否处于直线驾驶状态；若是,标记所述汽车雷达当前采集的目标点形成的目标列表中的若干个基准点；检测所述若干个基准点在实际场景中是否位于一条直线；若是,根据所述若干个基准点,计算所述汽车雷达的偏移角；根据所述偏移角,补偿所述汽车雷达。通过上述方式,本发明实施例能够实现汽车雷达的角度自标定。(The embodiment of the invention relates to the technical field of automobile radars, and discloses an angle self-calibration method, an automobile radar system and an automobile. The angle self-calibration method is applied to an automobile radar system comprising an automobile radar, the automobile radar system is installed on an automobile, and the method comprises the following steps: detecting whether the automobile is in a straight line driving state; if yes, marking a plurality of datum points in a target list formed by target points currently collected by the automobile radar; detecting whether the plurality of reference points are positioned on a straight line in an actual scene; if so, calculating the offset angle of the automobile radar according to the plurality of reference points; and compensating the automobile radar according to the deviation angle. Through the mode, the embodiment of the invention can realize the angle self-calibration of the automobile radar.)

1. An angle self-calibration method is applied to an automobile radar system, comprises an automobile radar, and is characterized in that the method comprises the following steps:

detecting whether the automobile is in a straight line driving state;

if yes, marking a plurality of datum points in a target list formed by target points currently collected by the automobile radar;

detecting whether the plurality of reference points are positioned on a straight line in an actual scene;

if so, calculating the offset angle of the automobile radar according to the plurality of reference points;

and compensating the automobile radar according to the deviation angle.

2. The method of claim 1, wherein the automotive radar system further comprises a yaw angle sensor;

the detecting whether the automobile is in a straight line driving state comprises the following steps:

and detecting whether the automobile is in a straight line driving state or not through the yaw angle sensor.

3. The method of claim 1, wherein said marking a number of fiducial points in a target list formed from target points currently acquired by said automotive radar comprises:

acquiring a target list formed by target points currently acquired by the automobile radar;

marking a number of fiducial points in the target list based on a deep learning algorithm.

4. The method of claim 3, wherein the detecting whether the plurality of reference points are located in a straight line in the actual scene comprises:

and detecting whether the plurality of reference points are positioned on a straight line in the actual scene according to the deep learning algorithm.

5. The method of claim 1, wherein said calculating an offset angle of said automotive radar from said plurality of reference points comprises:

performing first-order linear fitting on the plurality of datum points by adopting a least square method to obtain datum straight lines;

acquiring a center normal of the automobile;

and calculating the offset angle of the automobile radar according to the reference straight line and the central normal line.

6. The method of claim 5, wherein calculating the offset angle of the automotive radar from the reference line and the center normal comprises:

calculating an included angle between the reference straight line and the central normal line;

and taking the included angle as the offset angle of the automobile radar.

7. The method according to any one of claims 1-6, further comprising:

the opening angle self-calibration function.

8. An automotive radar system mounted to an automobile, the system comprising:

the yaw angle sensor is used for detecting whether the automobile is in a linear driving state or not;

an automotive radar electrically connected to the yaw angle sensor, the automotive radar comprising:

an antenna;

a transmitter for transmitting a radar signal via the antenna;

the receiver is used for receiving a reflected signal of the radar signal after acting on a target point through the antenna;

at least one processor communicatively coupled to the receiver; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the angle self-calibration method of any one of claims 1-7.

9. An automobile, comprising:

the automotive radar system of claim 8;

the automobile control circuit is electrically connected with the automobile radar system and used for outputting an alarm signal according to the environment information around the automobile detected by the automobile radar system and the speed of the automobile;

the alarm device is electrically connected with the automobile control circuit and is used for working in an opening state according to the alarm signal;

and the braking device is electrically connected with the automobile control circuit and used for braking the automobile according to the alarm signal.

10. A non-transitory computer-readable storage medium storing computer-executable instructions for enabling an automotive radar to perform the angle self-calibration method as recited in any one of claims 1-7.

Technical Field

The invention relates to the technical field of automobile radars, in particular to an angle self-calibration method, an automobile radar system and an automobile.

Background

Automotive radars are radars for automobiles or other ground based motor vehicles, including various radars based on different technologies (e.g., laser, ultrasonic, microwave), and may be used for obstacle finding, collision prediction, adaptive cruise control, and the like. When the automobile radar is installed on an automobile for the first time, angle calibration can be carried out once. However, as the automobile travels for a long time, the installation angle of the automobile radar may be horizontally displaced due to a bump or the like, and the angle data of the target point around the automobile detected by the automobile radar may also be horizontally displaced. When the horizontal deviation of the installation angle of the automobile radar is large, the automobile radar can even generate false reports and false reports. Therefore, when the installation angle of the automobile radar is horizontally deviated, the automobile radar needs to be calibrated in time to maintain the normal use of the automobile radar.

However, in the process of implementing the invention, the inventor finds that the prior art has the following problems: at present, after initial calibration, the horizontal installation angle of the automobile radar is usually calibrated manually, and the angle self-calibration of the automobile radar cannot be realized.

Disclosure of Invention

The embodiment of the invention aims to provide an angle self-calibration method, an automobile radar system and an automobile, which can realize the angle self-calibration of an automobile radar.

In order to solve the above technical problems, embodiments of the present invention provide the following technical solutions:

in a first aspect, an embodiment of the present invention provides an angle self-calibration method, which is applied to an automotive radar system including an automotive radar, where the automotive radar system is installed in an automobile, and the method includes:

detecting whether the automobile is in a straight line driving state;

if yes, marking a plurality of datum points in a target list formed by target points currently collected by the automobile radar;

detecting whether the plurality of reference points are positioned on a straight line in an actual scene;

if so, calculating the offset angle of the automobile radar according to the plurality of reference points;

and compensating the automobile radar according to the deviation angle.

In some embodiments, the automotive radar system further comprises a yaw angle sensor;

the detecting whether the automobile is in a straight line driving state comprises the following steps:

and detecting whether the automobile is in a straight line driving state or not through the yaw angle sensor.

In some embodiments, the marking of the number of reference points in a target list formed by target points currently acquired by the automotive radar includes:

acquiring a target list formed by target points currently acquired by the automobile radar;

marking a number of fiducial points in the target list based on a deep learning algorithm.

In some embodiments, the detecting whether the plurality of reference points are located in a straight line in the actual scene includes:

and detecting whether the plurality of reference points are positioned on a straight line in the actual scene according to the deep learning algorithm.

In some embodiments, said calculating an offset angle of said automotive radar from said number of reference points comprises:

performing first-order linear fitting on the plurality of datum points by adopting a least square method to obtain datum straight lines;

acquiring a center normal of the automobile;

and calculating the offset angle of the automobile radar according to the reference straight line and the central normal line.

In some embodiments, the calculating an offset angle of the automotive radar according to the reference straight line and the center normal includes:

calculating an included angle between the reference straight line and the central normal line;

and taking the included angle as the offset angle of the automobile radar.

In some embodiments, the method further comprises:

the opening angle self-calibration function.

In a second aspect, an embodiment of the present invention provides an automotive radar system, which is installed in an automobile, and includes:

the yaw angle sensor is used for detecting whether the automobile is in a linear driving state or not;

the automobile radar is electrically connected with the yaw angle sensor and comprises a sensor module;

an antenna;

a transmitter for transmitting a radar signal via the antenna;

the receiver is used for receiving a reflected signal of the radar signal after acting on a target point through the antenna;

at least one processor communicatively coupled to the receiver; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the angle self-calibration method as defined in any one of the above.

In a third aspect, an embodiment of the present invention provides an automobile, including:

the automotive radar system as described above;

the automobile control circuit is electrically connected with the automobile radar system and used for outputting an alarm signal according to the environment information around the automobile detected by the automobile radar system and the speed of the automobile;

the alarm device is electrically connected with the automobile control circuit and is used for working in an opening state according to the alarm signal;

and the braking device is electrically connected with the automobile control circuit and used for braking the automobile according to the alarm signal.

In a fourth aspect, the embodiment of the present invention further provides a non-volatile computer-readable storage medium, where the computer-readable storage medium stores computer-executable instructions for enabling an automotive radar to execute the angle self-calibration method described above.

The embodiment of the invention has the beneficial effects that: different from the prior art, the angle self-calibration method, the automobile radar system and the automobile provided by the embodiment of the invention detect whether the automobile is in a linear driving state or not; if yes, marking a plurality of datum points in a target list formed by target points currently collected by the automobile radar; detecting whether the plurality of reference points are positioned on a straight line in an actual scene; if yes, calculating the offset angle of the automobile radar according to the plurality of datum points; according to the offset angle, the automobile radar is compensated, so that the angle self-calibration of the automobile radar can be realized.

Drawings

One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.

Fig. 1 is an application scenario diagram of the angle self-calibration method according to the embodiment of the present invention;

FIG. 2 is a schematic structural diagram of an automobile according to an embodiment of the present invention;

FIG. 3 is a schematic structural diagram of an automotive radar system according to an embodiment of the present invention;

FIG. 4 is a flowchart of a method of self-calibration of an angle according to an embodiment of the present invention;

FIG. 5 is a flowchart of a method of step S42 of FIG. 4 according to an embodiment of the present invention;

FIG. 6 is a flowchart of a method of step S44 of FIG. 4 according to an embodiment of the present invention;

FIG. 7 is a flowchart of a method of step S443 of FIG. 6 according to an embodiment of the present invention;

FIG. 8 is a flow chart of a method of another angle self-calibration method provided by an embodiment of the present invention;

FIG. 9 is a flow chart illustrating a structure of an angle self-calibration apparatus according to an embodiment of the present invention;

fig. 10 is a schematic structural diagram of an automotive radar in fig. 3 according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that although functional blocks are partitioned in a schematic diagram of an apparatus and a logical order is shown in a flowchart, in some cases, the steps shown or described may be performed in a different order than the partitioning of blocks in the apparatus or the order in the flowchart. Furthermore, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.

In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

The angle self-calibration method provided by the embodiment of the invention can be applied to an application scene shown in fig. 1, wherein the application scene shown in fig. 1 comprises an automobile 1 and a target point 11, the target point 11 is distributed in an environment around the automobile 1, and the target point 11 comprises a general target point 11a and a reference point 11 b. The automobile 1 is in a straight-line driving state, and a plurality of reference points 11b currently acquired by the automobile 1 are located on a straight line. By detecting the target point 11, information such as a relative distance, a relative speed, and a relative angle between the target point 11 and the automobile 1 can be obtained.

The target point 11 currently acquired by the automobile 1 changes with the change of the driving environment of the automobile 1. In other words, the target point 11 currently acquired by the automobile 1 is temporal and spatial. The target point 11 may be in an absolute stationary state, a relative stationary state, or a moving state, including trees, rocks, manhole covers, road signs, street lights, railings, buildings, walls, pedestrians, animals, other motorized or non-motorized vehicles, and so forth.

As shown in fig. 2, the automobile 1 includes the automobile radar system 100, the automobile control circuit 200, the alarm device 300, and the brake device 400 according to the embodiment of the present invention.

The automotive radar system 100 is mounted on an automobile 1, and as shown in fig. 3, the automotive radar system 100 includes a yaw angle sensor 10 and an automotive radar 20.

The yaw angle sensor 10 is used to detect whether the automobile 1 is in a straight-driving state.

The car radar 20 is electrically connected to the yaw angle sensor 10.

The automotive radar 20 is a radar for the automobile 1 or other ground motor vehicles, and the present invention is explained by taking a millimeter wave radar as an example, and accordingly, the millimeter wave radar and the yaw angle sensor 10 constitute a millimeter wave radar system.

The millimeter wave radar is a radar which works in a millimeter wave band for detection, the frequency domain of the millimeter wave is usually 30-300GHz, and the wavelength of a millimeter wave signal transmitted and received by the millimeter wave radar is between microwave and centimeter wave. According to the wave propagation theory, the higher the frequency, the shorter the wavelength, the higher the resolution, and the stronger the penetration ability, but the larger the loss in the propagation process, the shorter the transmission distance; in contrast, the lower the frequency, the longer the wavelength, the stronger the diffraction power, and the further the transmission distance. Compared with microwave, the millimeter wave has high resolution, good directivity, strong anti-interference capability and good detection performance. Compared with infrared, the millimeter wave has the advantages of small atmospheric attenuation, better penetrability to smoke dust and small influence of weather. These characteristics determine the full-time and all-weather operation capability of the millimeter-wave radar. Therefore, with the excellent distance and speed measurement capability and all-weather characteristics, the millimeter wave radar is widely used in the functions of an automobile ADAS (advanced driving Assistance System) such as ACC (Adaptive Cruise Control), FCW (Forward Collision Warning), AEB (automatic Emergency Braking), and the like.

When the ADAS functions of the automobiles such as ACC, FCW, AEB, and the like are implemented, a millimeter wave radar is installed in front of the automobile 1 to detect environmental information in front of the automobile, and is mainly used to acquire relative distance and relative speed information of the front vehicle. Generally, in order to meet the detection requirements of different distance ranges, a plurality of short-range, medium-range and long-range millimeter wave radars are installed on one automobile. The 24GHz millimeter wave radar system mainly realizes short-range detection below 60 meters, and the 77GHz millimeter wave radar system mainly realizes medium-range detection of about 100 meters and long-range detection above 200 meters.

The automobile control circuit 200 is electrically connected to the automobile radar system 100, and is configured to output an alarm signal according to the environmental information around the automobile 1 and the speed of the automobile 1 detected by the automobile radar system 100.

The operating condition information of the automobile 1 detected by the millimeter wave radar system and other sensors is transmitted to the automobile control circuit 200 (i.e., the electronic control unit) through the input interface in real time. When receiving the information, the vehicle control circuit 200 makes a corresponding decision and process according to a pre-programmed control program, and outputs a control signal to a corresponding actuator through an output interface thereof, and the actuator executes a corresponding action after receiving the control signal, thereby realizing a certain predetermined function.

The alarm device 300 is electrically connected to the vehicle control circuit 200, and is configured to operate in an on state according to the alarm signal.

The alarm device 300 is an information display device indicating that a malfunction, accident, or dangerous situation has occurred. According to the characteristics of the code used and the nature of the sensory channel receiving the information, there are classified visual alarm, auditory alarm, tactile alarm, olfactory alarm, etc. In order to enhance the reliability of the display, a double display is sometimes adopted, such as a visual signal and an audible signal simultaneously displaying the occurrence of a certain malfunction or accident. In the present embodiment, the warning device 300 includes a crescent lamp for outputting an acoustic signal and a light signal to prompt the driver.

The braking device 400 is electrically connected with the automobile control circuit 200 and is used for braking the automobile 1 according to the alarm signal.

The braking device 400 is a series of special devices that apply a certain force to certain parts (mainly wheels) of the automobile 1, thereby performing a certain degree of forced braking thereon. The braking device 400 functions as: the running automobile 1 is forced to decelerate or even stop according to the requirement of a driver; the parked automobile 1 is stably parked under various road conditions (including on a slope); the speed of the vehicle 1 running downhill is kept stable.

In summary, the environment information around the automobile 1 detected by the millimeter wave radar system, the speed of the automobile 1 acquired by the On-board diagnostics (OBD) interface of the automobile 1, and the environment information around the automobile 1 and the speed of the automobile 1 are transmitted to the automobile control circuit 200 in real time through the input interface. When receiving the information, the automobile control circuit 200 makes a corresponding decision and process according to a pre-programmed control program, and outputs an alarm signal to the alarm device 300 and the brake device 400 through an output interface thereof, after receiving the alarm signal, the alarm device 300 works in an on state to prompt a driver with at least one of a visual signal, an auditory signal, a tactile signal and an olfactory signal, and after receiving the alarm signal, the brake device 400 brakes the automobile 1 to avoid an abrupt dangerous condition and reduce the occurrence of road traffic accidents.

Fig. 4 is a flowchart of an angle self-calibration method according to an embodiment of the present invention, which can be applied to the automotive radar system 100 shown in fig. 2, where the angle self-calibration method S400 includes:

and S41, detecting whether the automobile is in a straight driving state.

Wherein the automotive radar system comprises a yaw angle sensor. The detecting whether the automobile is in a straight line driving state comprises the following steps: and detecting whether the automobile is in a straight line driving state or not through the yaw angle sensor.

In the present embodiment, the driving state of the automobile includes a straight driving state and a non-straight driving state. And detecting the yaw angle between the automobile body of the automobile and the target driving course by taking the course corresponding to the linear driving of the automobile as the target driving course. If the angle of the yaw angle is equal to 0 degree, the automobile is in a linear driving state, and if the angle of the yaw angle is not equal to 0 degree, the automobile is in a non-linear driving state.

In some embodiments, it may be detected whether the car 1 is in a straight driving state by monitoring the angle of rotation of the steering wheel. Specifically, if the angle of rotation of the steering wheel is equal to 0 degrees, the vehicle is in a linear driving state, and if the angle of rotation of the steering wheel is not equal to 0 degrees, the vehicle is in a non-linear driving state.

And S42, if yes, marking a plurality of reference points in a target list formed by the target points currently acquired by the automobile radar.

As shown in fig. 5, the marking of several reference points in a target list formed by target points currently acquired by the automotive radar includes:

and S421, acquiring a target list formed by target points currently acquired by the automobile radar.

S422, marking a plurality of reference points in the target list based on a deep learning algorithm.

In this embodiment, the reference points are rail points, and the plurality of reference points correspond to rails (generally, columnar) on one side or both sides of the driving road of the automobile. In some embodiments, when a straight line formed by trees, street lamps, buildings or walls on one side or two sides of the vehicle is long, that is, when the number of target points corresponding to trees, street lamps, buildings or walls in a target list formed by target points currently acquired by the vehicle radar is large, the trees, street lamps, buildings or walls in the target list are marked as reference points based on a deep learning algorithm.

And starting a millimeter wave radar, scanning a target point of the surrounding environment of the automobile, carrying out signal processing on the target point to obtain target point information, and generating a target list according to the target point information. The target list includes a target point ID of the target point and target point information including a relative distance, a relative speed, and a relative angle between the target point and the automobile. And importing the target list into a classifier based on deep learning of the millimeter wave radar, training target point data in the target list, and accurately marking a plurality of reference points in the target list. For example, based on a deep learning algorithm, target point data in a target list is trained, railing points in the target list are identified, and marked with red points.

And S43, detecting whether the plurality of reference points are positioned on a straight line in the actual scene.

Wherein, the detecting whether the plurality of reference points are located on a straight line in the actual scene includes: and detecting whether the plurality of reference points are positioned on a straight line in the actual scene according to the deep learning algorithm.

As described above, based on the deep learning algorithm, a plurality of balustrade points in the target list are marked, and meanwhile, whether the balustrade points corresponding to the plurality of balustrade points in the actual scene are straight or not can be judged. When the reference points are located on a straight line in an actual scene, the railings on one side or two sides of the driving road of the automobile extend straightly.

In some embodiments, the method further comprises: detecting the number of the plurality of railing points; if the number is greater than the preset threshold, triggering to enter step S44; if the number is smaller than the preset threshold, the process returns to step S42. The length of the railing rod and the number of the reference points form a positive correlation relationship, the longer the railing rod is, the more the railing points currently collected by the millimeter wave radar are, the more the deviation angles of the automobile radar obtained through calculation based on the plurality of railing points are, and the calibration effect of the automobile radar is further improved.

And S44, if yes, calculating the offset angle of the automobile radar according to the plurality of reference points.

As shown in fig. 6, the calculating the offset angle of the automotive radar according to the plurality of reference points includes:

and S441, performing first-order linear fitting on the plurality of reference points by adopting a least square method to obtain a reference straight line.

Least squares (also known as the least squares method) is a mathematical optimization technique that finds the best functional match of the data by minimizing the sum of the squares of the errors. A first order linear fit is a form of curve fitting, assuming that x and y are both quantities being observed, and y is a function of x: and y is f (x; b), the curve fitting is to find the optimal estimated value of the parameter b through the observed values of x and y, and to find the optimal theoretical curve y is f (x; b). When the function y is a linear function of i with respect to b, such a curve fit is said to be a linear fit.

Wherein, a plurality of datum points are discrete points. And calculating the residual square sum of a plurality of reference points by using a regression model of a least square method, determining the position of the reference straight line according to the minimum principle of the residual square sum, and drawing the reference straight line. Generally, most of the reference points are evenly distributed around the reference straight line.

And S442, acquiring the central normal of the automobile.

And S443, calculating an offset angle of the automobile radar according to the reference straight line and the center normal.

As shown in fig. 7, the calculating an offset angle of the automotive radar according to the reference straight line and the center normal includes:

s4431, calculating an included angle between the reference straight line and the center normal line.

S4432, taking the included angle as a deviation angle of the automobile radar.

And performing first-order linear fitting on all target points marked as railing points by adopting a least square method to obtain a reference straight line, wherein the included angle between the reference straight line and the normal of the center of the automobile is the offset angle of the central position for installing the millimeter wave radar. If the reference straight line coincides with the normal line of the center of the automobile, there is no horizontal deviation in the center position where the millimeter wave radar is installed, and it is not necessary to perform step S45.

And S45, compensating the automobile radar according to the deviation angle.

In conclusion, when the automobile is in a straight-line driving state and a plurality of reference points currently collected by the automobile are located on a straight line, the offset angle of the millimeter wave radar is calculated according to the plurality of reference points, and the offset angle is automatically compensated to the millimeter wave radar, so that the angle self-calibration of the millimeter wave radar is realized, and the complicated manual angle calibration process is avoided. Referring to fig. 8, in some embodiments, the angle self-calibration method S500 further includes:

and S51, opening angle self-calibration function.

And when the angle self-calibration function is started, triggering to enter a step of detecting whether the automobile is in a linear driving state.

The angle self-calibration method provided by the embodiment of the invention detects whether the automobile is in a straight driving state; if yes, marking a plurality of datum points in a target list formed by target points currently collected by the automobile radar; detecting whether the plurality of reference points are positioned on a straight line in an actual scene; if yes, calculating the offset angle of the automobile radar according to the plurality of datum points; according to the offset angle, the automobile radar is compensated, so that the angle self-calibration of the automobile radar can be realized.

Accordingly, as shown in fig. 9, an embodiment of the present invention further provides an angle self-calibration apparatus, which may be applied to the automotive radar system 100 shown in fig. 2, where the angle self-calibration apparatus 600 includes:

the first detection unit 601 is configured to detect whether the vehicle is in a straight driving state.

The marking unit 602 is configured to mark a plurality of reference points in a target list formed by target points currently acquired by the automotive radar if the automobile is in a straight-line driving state.

A second detecting unit 603, configured to detect whether the plurality of reference points are located in a straight line in the actual scene.

A calculating unit 604, configured to calculate, according to the plurality of reference points, a deviation angle of the automotive radar if the plurality of reference points are located in a straight line in an actual scene.

And a compensation unit 605, configured to compensate the automotive radar according to the offset angle.

In some embodiments, the automotive radar system comprises a yaw angle sensor, and the first detection unit 601 is specifically configured to detect whether the automobile is in a straight driving state through the yaw angle sensor.

In some embodiments, the marking unit 602 is specifically configured to: acquiring a target list formed by target points currently acquired by the automobile radar; marking a number of fiducial points in the target list based on a deep learning algorithm.

In some embodiments, the second detection unit 603 is specifically configured to: and detecting whether the plurality of reference points are positioned on a straight line in the actual scene according to the deep learning algorithm.

In some embodiments, the computing unit 604 is specifically configured to: performing first-order linear fitting on the plurality of datum points by adopting a least square method to obtain datum straight lines; acquiring a center normal of the automobile; and calculating the offset angle of the automobile radar according to the reference straight line and the central normal line.

Wherein, according to the reference straight line and the center normal line, calculating the offset angle of the automobile radar, comprises: calculating an included angle between the reference straight line and the central normal line; and taking the included angle as the offset angle of the automobile radar.

As one embodiment of the present invention, the angle self-calibration apparatus 600 further includes an opening unit for opening the angle self-calibration function.

It should be noted that the above-mentioned apparatus can execute the method provided by the embodiments of the present application, and has corresponding functional modules and beneficial effects for executing the method. For technical details which are not described in detail in the device embodiments, reference is made to the methods provided in the embodiments of the present application.

Fig. 10 is a schematic structural diagram of the automotive radar in fig. 3 according to an embodiment of the present invention, and as shown in fig. 10, the automotive radar 20 includes an antenna 201, a transmitter 202, a receiver 203, at least one processor 204, and a memory 205 communicatively connected to the at least one processor 204, where one processor 204 is taken as an example in fig. 10.

The antenna 201 is a transformer that transforms a guided wave on a transmission line into an electromagnetic wave propagating in an unbounded medium or vice versa. The transmitter 202 is used to transmit radar signals via the antenna 201. The receiver 203 is configured to receive a reflected signal of the radar signal after acting on a target point via the antenna 201. At least one processor 204 is communicatively coupled to the receiver 203. The memory 205 stores instructions executable by the at least one processor 204 to enable the at least one processor 204 to perform the angle self-calibration method according to the embodiments of the present invention.

In the present embodiment, the radar signal is a millimeter wave signal. The emitter 202 emits the millimeter wave signal to a certain direction through the antenna 201, if the millimeter wave signal encounters a target point in the propagation process, the millimeter wave signal is reflected, the antenna 201 receives the reflected signal after the millimeter wave signal acts on the target point, and the reflected signal is sent to at least one processor 204 in communication connection with the antenna, so that information transmission between the target point and the millimeter wave radar is realized. The reflected signal received by the antenna 201 is processed to obtain the target point information of the target point.

The processor 204 and the memory 205 may be connected by a bus or other means, and fig. 10 illustrates the connection by the bus as an example.

The memory 205, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the angle self-calibration method in the embodiment of the present invention, for example, the modules shown in fig. 9. The processor 204 executes various functional applications and data processing of the server by executing the nonvolatile software programs, instructions and modules stored in the memory 205, so as to implement the angle self-calibration method described in the above method embodiment.

The memory 205 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the angle self-calibration apparatus, and the like. Further, the memory 205 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 205 may optionally include memory located remotely from the processor 204, which may be connected via a network to a device that controls the unmanned vehicle. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The one or more modules are stored in the memory 205 and, when executed by the one or more processors 204, perform the angle self-calibration method in any of the method embodiments described above, e.g., perform the method steps of fig. 4-8 described above, to implement the functions of the modules and units in fig. 9.

Embodiments of the present invention also provide a non-transitory computer-readable storage medium, where computer-executable instructions are stored in the computer-readable storage medium and executed by one or more processors, where the computer-executable instructions are configured to enable an automotive radar to perform the angle self-calibration method according to any of the above embodiments.

Embodiments of the present invention also provide a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the angle self-calibration method according to any of the above method embodiments, for example, to perform the method steps of fig. 4 to 8 described above, and to implement the functions of the modules and units in fig. 9.

It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; within the idea of the invention, also technical features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.