CN113727064B

CN113727064B - Method and device for determining camera field angle

Info

Publication number: CN113727064B
Application number: CN202010455269.4A
Authority: CN
Inventors: 赵长友
Original assignee: Beijing Co Wheels Technology Co Ltd
Current assignee: Beijing Co Wheels Technology Co Ltd
Priority date: 2020-05-26
Filing date: 2020-05-26
Publication date: 2024-03-22
Anticipated expiration: 2040-05-26
Also published as: CN113727064A

Abstract

The embodiment of the disclosure discloses a method and a device for determining a camera field angle, and relates to the technical field of data processing. The main technical scheme of the embodiment of the disclosure comprises: under different angles of view to be selected, controlling the simulation test system to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes, wherein a fixed inter-vehicle distance is reserved between the traffic vehicle and the test vehicle in each simulation road scene; and determining a target field of view angle from the field of view angles based on the fixed distance of travel corresponding to each simulated road scene and the measured distance of travel between the traffic vehicle and the test vehicle in each simulated road scene corresponding to the same field of view angle in the test result of the intelligent driving system, wherein the measured distance of travel is determined based on the simulated road image corresponding to the simulated road scene, which is shot by the camera of the simulated test system at the corresponding field of view angle.

Description

Method and device for determining camera field angle

Technical Field

The embodiment of the disclosure relates to the technical field of data processing, in particular to a method and a device for determining a camera field angle.

Background

Along with the rapid development of automobile technology, intelligent driving systems such as an ADAS (advanced driving assistance system, advanced Driver Assistant System) and the like are commonly applied to automobiles, and the intelligent driving systems such as the ADAS and the like realize functions such as lane departure, front vehicle collision early warning and the like by performing post algorithm processing on road images in front of the automobiles, which are acquired by cameras, so as to assist driving of drivers. Because the intelligent driving system can ensure driving safety to a certain extent, in the development flow of the vehicle or the intelligent driving system, the intelligent driving system is an indispensable link for performing hardware-in-loop simulation tests and other simulation tests.

The intelligent driving system is generally subjected to simulation test by adopting a simulation test system such as a hardware-in-the-loop simulation test system and the like. The existing simulation test system generally comprises display equipment and a camera, wherein the display equipment is used for playing the simulation road image in the simulation road scene, and the camera on the camera simulation test vehicle is used for collecting the simulation road image played by the display equipment. During testing, the camera is used for collecting a simulated road image in a simulated road scene played by the display equipment, and the simulated road image comprises a traffic vehicle. And performing post algorithm processing according to the acquired images so as to test functions such as lane departure, front vehicle collision early warning and the like. At present, a camera in a simulation test system such as a loop simulation test system and the like usually collects images by the view angle of the camera on a real vehicle, but because the difference exists between a simulation road image in a simulation road scene played by display equipment and a real road image in a real driving scene, the difference between the simulation road image collected by the camera on the real vehicle by the view angle of the camera and the real road image is larger, and the difference causes larger test error of the intelligent driving system test, so that the reliability of the intelligent driving system test is lower.

Disclosure of Invention

In view of this, embodiments of the present disclosure provide a method and an apparatus for determining a camera field angle, which are mainly aimed at determining a field angle that is more suitable for an intelligent driving system test performed by a simulation test system, so as to improve the perceived accuracy of the camera in the simulation test, thereby improving the reliability of the simulation test. The main technical scheme comprises the following steps:

in a first aspect, embodiments of the present disclosure provide a method for determining a camera field angle, the method including:

under different angles of view to be selected, controlling a simulation test system to test an intelligent driving system of a test vehicle by using a plurality of simulation road scenes, wherein a fixed inter-vehicle distance is reserved between a traffic vehicle and the test vehicle in each simulation road scene;

and determining a target field of view from each of the candidate field of view based on a fixed distance of view corresponding to each of the candidate field of view and a measured distance of view between the traffic vehicle and the test vehicle in each of the candidate field of view corresponding to the same one of the candidate field of view in a test result of the intelligent driving system, wherein the measured distance of view is determined based on a simulated road image corresponding to the simulated road scene captured by a camera of the simulation test system at the corresponding candidate field of view.

In a second aspect, embodiments of the present disclosure provide a device for determining a camera field angle, the device including:

the test unit is used for controlling the simulation test system to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes under different angles of view to be selected, wherein a fixed distance between the traffic vehicle and the test vehicle is reserved in each simulation road scene;

and a determining unit configured to determine a target field of view from each of the candidate field of view based on a fixed following distance corresponding to each of the simulated road scenes and a measured following distance between the traffic vehicle and the test vehicle in each of the simulated road scenes corresponding to the same candidate field of view in a test result of the intelligent driving system, wherein the measured following distance is determined based on a simulated road image corresponding to the simulated road scene captured by a camera of the simulation test system at the corresponding candidate field of view.

In a third aspect, embodiments of the present disclosure provide a simulation test system, the system comprising: camera, display device, intelligent driving system and camera view angle determining device according to the second aspect;

The display device is used for playing a simulated road image corresponding to any simulated road scene under the control of the camera view angle determining device, wherein a fixed inter-vehicle distance is arranged between the traffic vehicle and the test vehicle in the simulated road scene, and the simulated road image comprises the traffic vehicle;

the camera simulates a camera on the test vehicle and is used for shooting a simulated road image played by the display device according to a to-be-selected field angle set by the camera field angle determining device;

the intelligent driving system is used for obtaining an intelligent driving system test result corresponding to the simulated road scene based on the acquired simulated road image, and feeding back the intelligent driving system test result to the camera view angle determining device so that the camera view angle determining device can determine a target view angle required by the camera when the intelligent driving system test is carried out, wherein the intelligent driving system test result comprises a measured distance between the traffic vehicle and the test vehicle in the simulated road scene based on the simulated road image acquired by the camera.

In a fourth aspect, an embodiment of the present disclosure provides a storage medium, where the storage medium includes a stored program, and when the program runs, the device where the storage medium is controlled to execute the method for determining the camera angle of view according to the first aspect.

In a fifth aspect, embodiments of the present disclosure provide a human-machine interaction device comprising a storage medium coupled to one or more processors configured to execute program instructions stored in the storage medium; and executing the method for determining the camera angle of view according to the first aspect when the program instructions run.

By means of the technical scheme, the method and the device for determining the camera view angle, provided by the embodiment of the invention, control the simulation test system to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes under different view angles to be selected. And determining the target field angle from the field angles to be selected based on the fixed distance between the traffic vehicles and the test vehicles in the simulated road scenes corresponding to the same field angle to be selected in the test result of the intelligent driving system. Therefore, in the embodiment of the disclosure, the view angle required by the simulation test system for testing the intelligent driving system can be determined in different view angles to be more suitable for the simulation test system based on the test results of the simulation system under different view angles to be selected, so that the perception precision of the camera is improved in the simulation test, and the reliability of the simulation test is improved.

The foregoing description is merely an overview of the technical solutions of the embodiments of the present disclosure, and may be implemented according to the content of the specification in order to make the technical means of the embodiments of the present disclosure more clearly understood, and in order to make the foregoing and other objects, features and advantages of the embodiments of the present disclosure more comprehensible, the following detailed description of the embodiments of the present disclosure.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the embodiments of the disclosure. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:

fig. 1 shows a flowchart of a method for determining a camera angle of view provided by an embodiment of the present disclosure;

FIG. 2 illustrates a schematic view of a camera field angle provided by an embodiment of the present disclosure;

FIG. 3 illustrates a schematic view of another camera field angle provided by an embodiment of the present disclosure;

FIG. 4 illustrates a flowchart of another method for determining camera angle of view provided by embodiments of the present disclosure;

FIG. 5 illustrates a schematic diagram of a simulated road image provided by an embodiment of the present disclosure;

FIG. 6 illustrates a schematic diagram of a bird's eye view of a simulated road image provided by an embodiment of the present disclosure;

FIG. 7 illustrates a schematic diagram of another simulated road image provided by an embodiment of the present disclosure;

FIG. 8 illustrates a schematic diagram of a bird's eye view of another simulated road image provided by an embodiment of the present disclosure;

FIG. 9 shows a schematic diagram of yet another simulated road image provided by an embodiment of the present disclosure;

FIG. 10 illustrates a schematic diagram of a bird's eye view of yet another simulated road image provided by an embodiment of the present disclosure;

fig. 11 shows a block diagram of a camera view angle determining apparatus provided by an embodiment of the present disclosure;

fig. 12 shows a block diagram of another camera angle-of-view determination apparatus provided by an embodiment of the present disclosure;

FIG. 13 illustrates a block diagram of a simulation test system provided by an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The simulation test system described in the embodiments of the present disclosure is used to test an intelligent driving system deployed in a vehicle, and optionally, the simulation test system may be a hardware-in-the-loop simulation test system. The specific type of intelligent driving system described herein may be determined based on business requirements, and the present embodiment is not particularly limited. Alternatively, the intelligent driving system may be any one of the following: ADAS (advanced driving assistance system, advanced Driver Assistant System), partially automated system, highly automated system, and fully automated system. The ADAS is used for providing driving assistance for a driver to give out a warning to remind the driver when the safety risk exists in the vehicle, and the driving assistance system is used for warning of lane departure, early warning of front vehicle collision and the like; part of the automated systems are systems that can automatically intervene when the driver receives a warning but fails to take corresponding action in time, exemplary automatic emergency braking systems, emergency lane assistance systems, and the like; highly automated systems are used to take over the responsibility of operating the vehicle for a period of time instead of the driver, but still require the driver to monitor the driving activity. Fully automated systems are used to replace a driver driving a vehicle when the unmanned vehicle or driver is engaged in other activities unrelated to driving behavior, which is a system that does not require personnel monitoring.

The simulation test system comprises display equipment, a camera and an intelligent driving system. It should be noted that, the simulation test system process may include, in addition to the above three components, a GPS (Global Positioning System ), an IMU (Inertial Measurement Unit, inertial measurement unit), a radar, a sensor, and the like, which are indispensable for the intelligent driving system. The display device is used for playing the simulated road image corresponding to the simulated road scene so as to simulate the driving environment of the test vehicle, wherein the driving environment can include, but is not limited to, traffic vehicles, pedestrians, roads, lane lines, road signboards and the like. The camera simulates a camera on a test vehicle where the intelligent driving system is located, and the camera is used for shooting a simulated road image corresponding to a simulated road scene, which is played by the display equipment, at a certain field angle. The intelligent driving system is used for obtaining an intelligent driving system test result corresponding to the simulated road scene based on the simulated road image acquired by the camera, or obtaining an intelligent driving system test result corresponding to the simulated road scene based on at least one or more of the simulated road image acquired by the camera, the data acquired by the GPS, the data acquired by the IMU, the data acquired by the radar or the data acquired by the sensor.

In the prior art, when the simulation test system tests the intelligent driving system, the camera of the simulation system usually collects images at the angle of view of the camera on the real vehicle, but because the difference exists between the simulated road image in the simulated road scene played by the display device and the real road image in the real driving scene, the difference between the simulated road image collected by the camera at the angle of view of the camera on the real vehicle and the real road image is larger, the difference causes larger test error of the intelligent driving system test, and the reliability of the intelligent driving system test is lower. In order to determine the field angles required by the simulation test system to perform intelligent driving system testing, the embodiment of the disclosure controls the simulation test system to respectively complete testing of the intelligent driving system under different field angles to be selected, and selects the optimal field angle from the field angles to be selected based on the test result. The simulation test system tests the intelligent driving system at the optimal field angle to reduce the difference between the simulation road image acquired by the camera and the real road image in the real driving scene, thereby improving the perception precision of the camera in the simulation test system and further improving the reliability of the simulation test.

In a first aspect, an embodiment of the present disclosure provides a method for determining a camera field angle, as shown in fig. 1, where the method mainly includes:

101. under different angles of view to be selected, the simulation test system is controlled to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes, wherein a fixed inter-vehicle distance is reserved between the traffic vehicle and the test vehicle in each simulation road scene.

The number of the views to be selected in this embodiment may be based on the service requirement, and the number of the views to be selected is not specifically limited in this embodiment. Optionally, the setting method of the angle of view to be selected at least includes at least one of the following:

the method comprises the steps of firstly, obtaining a first sample field angle; based on the first sample field angle, a plurality of different candidate field angles are set at a set first step rate of change.

The first sample field angle in this method is set in two ways: firstly, the first sample field angle is set by the user according to the business requirement of the user, the setting mode is flexible, and the user can flexibly set the first sample field angle according to the requirement of the user. Secondly, the first sample field angle is the field angle of the camera on the real vehicle corresponding to the test vehicle, and in the setting mode, the first sample field angle is the field angle of the camera on the real vehicle, so that the to-be-selected field angle close to the field angle of the camera on the real vehicle can be determined.

In the method, after the first sample view angle is acquired, a plurality of different candidate view angles are set at a set first step change rate. When setting a plurality of different angles of view to be selected at the set first step change rate, the angles of view may be set in three ways: first, setting a plurality of different angles of view to be selected with a first step change rate in an increasing trend based on a first sample angle of view, and setting 5 angles of view to be selected as "30 °, 31 °, 32 °, 33 °, 34 °", by way of example, the first sample angle of view is 30 ° and the first step change rate is 1 °. Secondly, setting a plurality of different candidate angles of view with a first step change rate according to a decreasing trend by taking the first sample angle of view as a reference, wherein the first sample angle of view is 30 degrees, and the first step change rate is 1 degree, and the set 5 candidate angles of view are 30 degrees, 29 degrees, 28 degrees, 27 degrees and 26 degrees. Third, setting a plurality of different candidate angles of view with a first step change rate based on the first sample angle of view, and setting 5 candidate angles of view to be "30 °, 29 °, 28 °, 31 °, 32 °", with the first step change rate being 1 ° for the first sample angle of view.

And secondly, acquiring a plurality of different first sample angles of view, and determining the acquired first sample angles of view as angles of view to be selected.

The plurality of first sample angles of view in this method are user-determined and can be read from a user terminal or a user-specified storage location with a specific interface.

It should be noted that, no matter what method is adopted in the first method and the second method, the determined angle of view should ensure that the image shot by the camera only includes the simulated road image, but not other things. In addition, it should be noted that the first sample field angle may be: a horizontal angle of view, a vertical angle of view, and a combined angle of view (the combined angle of view is a diagonal angle of view). When the first sample angle of view is not the integrated sample angle of view but a horizontal angle of view and/or a vertical angle of view, it is necessary to convert the horizontal angle of view and/or the vertical angle of view into the integrated angle of view and then determine the angle of view to be selected. Illustratively, as shown in fig. 2, 11 is a simulated road image displayed by a display device, 12 is a camera, angle aoc is a horizontal angle of view, and angle doc is a vertical angle of view. As shown in fig. 3, 11 is a simulated road image displayed by a display device, 12 is a camera, and angle boa is a combined field angle.

The number of the simulated road scenes described in the present embodiment may be determined based on the service requirement, and the number is not specifically limited in the present embodiment. The simulated road scene comprises at least the following: the simulated road scene is a horizontal straight road or a road with a curve, a traffic vehicle exists in the simulated road scene, the traffic vehicle and the test vehicle are positioned in the same lane or different lanes, the traffic vehicle and the test vehicle run at a constant speed, and a fixed inter-vehicle distance is reserved between the traffic vehicle and the test vehicle, namely the traffic vehicle and the test vehicle are kept relatively static. And secondly, a road with a curve is a horizontal straight line road or a straight line road with a curve in a simulated road scene, a traffic vehicle exists in the simulated road scene, the traffic vehicle and the test vehicle are positioned in the same lane or different lanes, the traffic vehicle and the test vehicle have a speed change condition, and a fixed distance between the traffic vehicle and the test vehicle is reserved in the simulated road scene no matter the traffic vehicle and the test vehicle are in uniform speed running or speed change running, that is to say, the traffic vehicle and the test vehicle are kept relatively static.

Under different angles of view to be selected, simulated road scenes used for controlling the simulated test system to test the intelligent driving system can be different or identical. The view angle to be selected includes a view angle to be selected 1 and a view angle to be selected 2, wherein the simulated road scenes used for controlling the simulated test system to test the intelligent driving system under the view angle to be selected 1 are a simulated road scene 1 and a simulated road scene 2, and the simulated road scenes used for controlling the simulated test system to test the intelligent driving system under the view angle to be selected 1 are a simulated road scene 3 and a simulated road scene 4. The view angles to be selected include a view angle to be selected 1 and a view angle to be selected 2, wherein under the view angles to be selected 1 and 2, simulated road scenes used for controlling the simulation test system to test the intelligent driving system are a simulated road scene 1 and a simulated road scene 2. In order to increase mutual comparability between test results corresponding to all the candidate angles of view, simulation road scenes used by the simulation test system for testing the intelligent driving system under different candidate angles of view are the same.

In this embodiment, the multiple simulated road scenes used for testing the intelligent driving system may be the same kind of scene or different kinds of scene. The simulation road scenes used for testing the intelligent driving system comprise a simulation road scene 5 and a simulation road scene 6, wherein the simulation road scene 5 is a horizontal straight line road, a traffic vehicle exists in the simulation road scene, the traffic vehicle and the test vehicle are positioned in the same lane, the traffic vehicle and the test vehicle travel at a constant speed, and a fixed distance between the traffic vehicle and the test vehicle is provided. The simulated road scene 6 is a horizontal straight line road, in which there is a traffic vehicle in the same lane as the test vehicle, the traffic vehicle and the test vehicle have a speed change condition, in which there is no matter whether the traffic vehicle and the test vehicle are traveling at a constant speed or at a variable speed, and a fixed inter-vehicle distance is provided between the traffic vehicle and the test vehicle. The simulation road scenes used for testing the intelligent driving system comprise a simulation road scene 7 and a simulation road scene 8, wherein the simulation road scene 7 is a horizontal straight line road, a traffic vehicle exists in the simulation road scene, the traffic vehicle and the test vehicle are positioned in the same lane, the traffic vehicle and the test vehicle travel at a constant speed, and a fixed distance between the traffic vehicle and the test vehicle is provided. The simulated road scene 8 is a horizontal straight line road, and in the simulated road scene, a traffic vehicle is arranged, the traffic vehicle and the test vehicle are positioned in the same lane or different lanes, the traffic vehicle and the test vehicle run at a constant speed, and a fixed inter-vehicle distance is arranged between the traffic vehicle and the test vehicle. The simulated road scene 7 differs from the simulated road scene 8 only in the fixed inter-vehicle distance between the traffic vehicle and the test vehicle.

In this embodiment, if the multiple simulated road scenes used for testing the intelligent driving system are all the same type of simulated road scenes, only the fixed inter-vehicle distances between the traffic vehicle and the test vehicle in the simulated road scenes are different. Optionally, the rate of change of the fixed inter-vehicle distance in different simulated road scenes is a set step size. If the multiple simulated road scenes used for testing the intelligent driving system are different types of simulated road scenes, the fixed inter-vehicle distances between the traffic vehicles and the test vehicles in the simulated road scenes can be the same or different. In order to increase mutual comparability between test results corresponding to the angles of view to be selected, the plurality of simulated road scenes are the same type of simulated road scenes, and only fixed inter-vehicle distances between the traffic vehicles and the test vehicles in the simulated road scenes are different.

In this embodiment, after determining a plurality of different angles of view to be selected and a plurality of simulated road scenes, the simulated test system is controlled to test the intelligent driving system of the test vehicle using the plurality of simulated road scenes under the different angles of view to be selected. Illustratively, the candidate view angles include a candidate view angle 1 and a candidate view angle 2, and the simulated road scene includes a simulated road scene 1 and a simulated road scene 2. The simulation test system is controlled to test the intelligent driving system under the angle of view 1 to be selected by using the simulation road scene 1 and the simulation road scene 2 respectively, and the simulation test system is controlled to test the intelligent driving system under the angle of view 2 to be selected by using the simulation road scene 1 and the simulation road scene 2 respectively.

102. And determining a target field of view from each of the candidate field of view based on a fixed distance of view corresponding to each of the candidate field of view and a measured distance of view between the traffic vehicle and the test vehicle in each of the candidate field of view corresponding to the same one of the candidate field of view in a test result of the intelligent driving system, wherein the measured distance of view is determined based on a simulated road image corresponding to the simulated road scene captured by a camera of the simulation test system at the corresponding candidate field of view.

In this embodiment, the process of determining the target field angle from the to-be-selected field angles based on the fixed distance between rows corresponding to the to-be-selected field angles and the measured distance between rows of vehicles and test vehicles in the to-be-selected field angles in the test result of the intelligent driving system, which corresponds to the same to-be-selected field angle, specifically includes the following steps:

step one, determining errors between measured inter-vehicle distances between the traffic vehicle and the test vehicle and corresponding fixed inter-vehicle distances in each simulated road scene corresponding to the same visual field angle to be selected.

Specifically, the specific form of the error between the measured following distance and the corresponding fixed following distance between the traffic vehicle and the test vehicle is not specifically limited in this embodiment, and may be an absolute error or a relative error. The absolute error is calculated as follows:

d＝|L _True -L _Test |

d represents an absolute error between a measured inter-vehicle distance between the traffic vehicle and the test vehicle in any simulated road scene b and a corresponding fixed inter-vehicle distance; l (L) _Test Representing the measured inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene b; l (L) _True And representing the fixed inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene b.

The calculation formula of the relative error is as follows:

c represents an absolute error between a measured inter-vehicle distance between the traffic vehicle and the test vehicle in any simulated road scene b and a corresponding fixed inter-vehicle distance; l (L) _Test Representing the measured inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene b; l (L) _True And representing the fixed inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene b.

Illustratively, the fixed inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene 1 is 10, and the fixed inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene 2 is 8. And controlling the simulation test system to test the intelligent driving system by using the simulation road scene 1 under the field angle 1 to be selected, wherein the measured inter-vehicle distance before the traffic vehicle and the test vehicle in the obtained simulation road scene 1 is 9, and the relative error between the measured inter-vehicle distance 9 between the traffic vehicle and the test vehicle and the corresponding fixed inter-vehicle distance 10 in the simulation road scene 1 corresponding to the field angle 1 to be selected is 10. And controlling the simulation test system to test the intelligent driving system by using the simulation road scene 2 under the to-be-selected view angle 1, wherein the obtained measured inter-vehicle distance before the traffic vehicle and the test vehicle in the simulation road scene 2 is 7, and the relative error between the measured inter-vehicle distance 7 between the traffic vehicle and the test vehicle and the corresponding fixed inter-vehicle distance 8 in the simulation road scene 2 corresponding to the to-be-selected view angle 1 is 12.5%.

Specifically, the corresponding errors of each simulated road scene under different view angles can be obtained through the steps.

And step two, determining a target field angle from the field angles based on the errors corresponding to the field angles to be selected.

The specific implementation method of the second step at least comprises the following steps:

firstly, summing all errors corresponding to the same angle of view to be selected to obtain error sum values of the angles of view to be selected respectively; and determining the target field angle based on the magnitude of the error addition value of each candidate field angle.

Specifically, the error addition value corresponding to the same view angle to be selected is calculated by the following formula:

wherein, p1 ensures the error addition value of any angle b to be selected, n represents the total number of simulation road scenes used by the simulation test system for testing the intelligent driving system under the angle b to be selected; i represents an ith simulation road scene in the used simulation road scenes; m is m _i Characterization simulation test system pair intelligent drivingAfter the ith simulated road scene used in the system test, the obtained error between the measured inter-vehicle distance between the traffic vehicle and the test vehicle in the ith simulated road scene and the corresponding fixed inter-vehicle distance is an absolute error or a relative error.

The error addition value of all the angles of view to be selected can be obtained through the formula.

Specifically, after the error addition value of the view angles to be selected is obtained, a target view angle can be determined according to the magnitude of the error addition value of each view angle to be selected, wherein the target view angle is the view angle required by the camera of the simulation test system when the simulation test system tests the intelligent driving system, and the simulation road image which can be acquired by the camera under the target view angle is close to the real road scene, so that the test accuracy of the simulation test system can be improved.

Specifically, the candidate field angle with the smallest error addition value is determined as the target candidate field angle from the candidate field angles, and because the error addition value is smallest, the camera is based on the simulated road image which can be acquired by the candidate field angle and is closest to the real road scene, that is, the error between the acquired simulated road image and the real road image is smallest.

Secondly, multiplying the errors corresponding to the same angle of view to be selected to obtain error product values of the angles of view to be selected respectively; and determining the target field angle based on the magnitude of the error product value of each candidate field angle.

Specifically, the error product value corresponding to the same angle of view to be selected is calculated by the following formula:

wherein, p2 guarantees the error product value of any angle b to be selected, n represents the total number of simulation road scenes used by the simulation test system of the angle b to be selected when testing the intelligent driving system; i represents an ith simulation road scene in the used simulation road scenes; m is m _i Characterization simulation testAfter the test system tests the ith simulated road scene used in the intelligent driving system, the obtained error between the measured inter-vehicle distance between the traffic vehicle and the test vehicle in the ith simulated road scene and the corresponding fixed inter-vehicle distance is an absolute error or a relative error.

The error product value of all the angles of view to be selected can be obtained through the formula.

Specifically, after the error product value of the angles of view to be selected is obtained, a target angle of view, which is the angle of view required by the camera of the simulation test system when the simulation test system tests the intelligent driving system, can be determined according to the magnitude of the error product value of each angle of view to be selected, and the simulated road image which can be acquired by the camera under the target angle of view is close to the real road scene, so that the test accuracy of the simulation test system can be improved.

Specifically, the candidate field angle with the smallest error product value is determined as the target candidate field angle from the candidate field angles, and the camera is based on the simulated road image which can be acquired by the candidate field angle and is closest to the real road scene, that is, the error between the acquired simulated road image and the real road image is the smallest because the error product value is the smallest.

Thirdly, distributing corresponding weights for the errors corresponding to the same angle of view to be selected, and summing the products of the errors and the weights of the errors to obtain the sum of the products of the angles of view to be selected respectively; the target field angle is determined based on the magnitude of the product addition value of each candidate field angle.

Specifically, the corresponding weights may be assigned to the errors corresponding to the same candidate field angle based at least on the following principle:

and in principle, corresponding to each error of the same visual field angle to be selected, distributing weight to each error according to the fixed distance between the two vehicles corresponding to each error.

Specifically, during the running of the vehicle, the closer the following distance between the vehicle and the preceding vehicle is, the higher the probability of an accident such as a rear-end collision of the vehicle, that is, the closer the following distance between the vehicles is, the higher the shooting accuracy of the camera is, and the smaller the fixed following distance corresponding to the error is, the larger the weight allocated to the fixed following distance is.

Of course, if there is a requirement for the service, when the probability of danger is higher as the distance between vehicles is larger under certain driving conditions, the larger the fixed following distance corresponding to the error is, the larger the weight allocated to the fixed following distance is.

And secondly, distributing weights for the errors corresponding to the errors of the same vision angle to be selected according to the fixed distance between the vehicles and the requirements of the test working conditions corresponding to the errors, wherein the test working conditions are related to the driving danger degree.

Specifically, when weighting each error, a fixed following distance and a driving danger level corresponding to the error need to be comprehensively considered, wherein the driving danger level is related to the function of the tested intelligent driving system.

For example, the function of the intelligent driving system tested is automatic emergency braking, and the smaller the fixed following distance corresponding to the error is, the larger the weight allocated to the fixed following distance is.

Whichever principle is adopted to assign weights to errors, the product sum corresponding to the same candidate angle of view can be calculated by the following formula:

wherein, p3 guarantees the product sum of any angle b to be selected, n represents the total number of simulation road scenes used by the simulation test system of the angle b to be selected when testing the intelligent driving system; i represents an ith simulation road scene in the used simulation road scenes; m is m _i After representing an ith simulation road scene used when the simulation test system tests the intelligent driving system, obtaining an error between a measured inter-vehicle distance between a traffic vehicle and a test vehicle in the ith simulation road scene and a corresponding fixed inter-vehicle distance, wherein the error is an absolute error or a relative error; h is a _i Characterizing an ith simulated road scene used by a simulated test system to test an intelligent driving systemAnd then, obtaining the weight corresponding to the error between the measured inter-vehicle distance between the traffic vehicle and the test vehicle in the ith simulated road scene and the corresponding fixed inter-vehicle distance.

The product addition value of all the angles of view to be selected can be obtained through the formula.

Specifically, after the product addition value of the angles of view to be selected is obtained, a target angle of view, which is the angle of view required by the camera of the simulation test system when the simulation test system tests the intelligent driving system, can be determined according to the magnitude of the product addition value of each angle of view to be selected, and the simulated road image which can be acquired by the camera under the target angle of view is close to the real road scene, so that the test accuracy of the simulation test system can be improved.

Specifically, the candidate field angle with the smallest product addition value is determined from the candidate field angles as the target candidate field angle, and because the product addition value is smallest, the camera is based on the simulated road image which can be acquired by the candidate field angle and is closest to the real road scene, that is, the error between the acquired simulated road image and the real road image is smallest.

According to the method for determining the camera view angle, provided by the embodiment of the disclosure, under different view angles to be selected, the simulation test system is controlled to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes. And determining the target field angle from the field angles to be selected based on the fixed distance between the traffic vehicles and the test vehicles in the simulated road scenes corresponding to the same field angle to be selected in the test result of the intelligent driving system. Therefore, in the embodiment of the disclosure, the view angle required by the simulation test system for testing the intelligent driving system can be determined in different view angles to be more suitable for the simulation test system based on the test results of the simulation test system under different view angles to be selected, so that the perception precision of the camera is improved in the simulation test, and the reliability of the simulation test is improved.

In a second aspect, the method for determining a camera angle of view according to the embodiments of the present disclosure may be applied to an independent host computer, where the host computer is connected to a simulation test system, and the host computer determines a target angle of view for the simulation test system by applying the method for determining a camera angle of view according to the embodiments of the present disclosure. The method for determining the camera angle of view according to the embodiment of the present disclosure may also be directly applied to any element in a simulation test system, where the element determines the target angle of view for the simulation test system by applying the method for determining the camera angle of view according to the embodiment of the present disclosure. According to the method of the first aspect, another embodiment of the present disclosure further provides a method for determining a camera field angle, as shown in fig. 4, where the method mainly includes:

201. Setting a plurality of different angles of view to be selected and a plurality of simulated road scenes, wherein a fixed inter-vehicle distance is reserved between a traffic vehicle and a test vehicle in each simulated road scene.

Specifically, the setting method of the angle of view to be selected and the simulated road scene in this step is substantially the same as that described in the first aspect, and therefore will not be described here again.

Illustratively, the determined candidate field angles include 30 ° and 31 °. 3 simulated road scenes are determined, wherein the fixed inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene 1 is 10 meters, the fixed inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene 2 is 20 meters, and the fixed inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene 3 is 30 meters.

202. For each candidate field angle, performing: adjusting the view angle of the camera to be a view angle to be selected, and controlling display equipment of the simulation test system to sequentially play simulation road images corresponding to a plurality of simulation road scenes; when the display equipment plays the simulated road image corresponding to any simulated road scene, controlling a camera of the simulated test system to acquire the simulated road image; and obtaining an intelligent driving system test result corresponding to the simulated road scene based on the acquired simulated road image.

Specifically, a to-be-selected field angle is selected, the driving device is controlled to adjust the field angle of the camera to the to-be-selected field angle, and then the display device is controlled to sequentially play the simulated road images corresponding to the simulated road scenes. When the display equipment plays the simulated road image corresponding to any simulated road scene, in order to ensure that the simulated road image acquired by the camera is accurate, the camera acquires the simulated road image after the display equipment plays the simulated road image for a certain period of time. For example, after the display device plays the traffic vehicle and the test vehicle while traveling at a constant speed of 50km/h for 30 seconds, the camera collects the simulated road image.

For example, taking a to-be-selected field angle as an example, the following describes that under the to-be-selected field angle, the control simulation test system uses a plurality of simulation road scenes to test the intelligent driving system of the test vehicle respectively:

the simulation test system comprises a camera, a display device and an intelligent driving system, and in addition, a convex lens can be arranged between the display device and the camera in order to adjust the focal length of the camera. The test process of the vision angle to be selected is 30 degrees: the view angle of the camera is adjusted to 30 degrees, firstly, a simulated road image corresponding to a simulated road scene 1 is played on a display device, the simulated road image is shown in fig. 5 (a vehicle A in fig. 5 is a traffic vehicle), the camera is controlled to acquire a simulated road image ' fig. 5 ', an intelligent driving system test result corresponding to the simulated road scene is obtained based on the acquired simulated road image ' fig. 5 ', the test result comprises a measured inter-vehicle distance between the traffic vehicle A and a test vehicle B, and the test inter-vehicle distance is determined by converting the simulated road image shot by the camera at the corresponding view angle to be selected of 30 degrees into a bird's eye view as shown in fig. 6 by a simulated test system. After the test for the simulated road scene 1 is completed, playing a simulated road image corresponding to the simulated road scene on a display device, wherein the simulated road image is shown in fig. 7 (a vehicle A in fig. 7 is a traffic vehicle), controlling a camera to acquire a simulated road image ' fig. 7 ', and obtaining an intelligent driving system test result corresponding to the simulated road scene based on the acquired simulated road image ' fig. 7 ', wherein the test result comprises a measured inter-vehicle distance between the traffic vehicle A and a test vehicle B, and the measured inter-vehicle distance is determined by converting the simulated road image shot by the camera at a corresponding field angle to be selected by the simulated test system into a bird's eye view as shown in fig. 8. After the test for the simulated road scene 2 is completed, playing a simulated road image corresponding to the simulated road scene 3 on a display device, wherein the simulated road image is shown in fig. 9 (a vehicle A in fig. 9 is a traffic vehicle), controlling a camera to acquire a simulated road image ' fig. 9 ', and obtaining an intelligent driving system test result corresponding to the simulated road scene based on the acquired simulated road image ' fig. 9 ', wherein the test result comprises a measured inter-vehicle distance between the traffic vehicle A and a test vehicle B, and the test inter-vehicle distance is determined by converting the simulated road image shot by the camera at a corresponding field angle to be selected into a bird's eye view as shown in fig. 10 by a simulated test system.

203. And determining errors between the measured inter-vehicle distances between the traffic vehicle and the test vehicle and the corresponding fixed inter-vehicle distances in each simulated road scene corresponding to the same visual field angle to be selected.

The error determination process is described below by taking a candidate angle of view as an example: corresponding to the angle of view to be selected of 30 degrees, the measured inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene 1 is 9 meters, the measured inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene 1 is 19 meters, and the measured inter-vehicle distance between the traffic vehicle and the test vehicle in the simulated road scene 1 is 28 meters.

In the simulation road scene 1, the error between the measured inter-vehicle distance between the traffic vehicle and the test vehicle and the corresponding fixed inter-vehicle distance is determined as follows:

in the determined simulation road scene 2, the error between the measured inter-vehicle distance between the traffic vehicle and the test vehicle and the corresponding fixed inter-vehicle distance is as follows:

in the determined simulation road scene 3, the error between the measured inter-vehicle distance between the traffic vehicle and the test vehicle and the corresponding fixed inter-vehicle distance is as follows:

204. and determining the target view angle from the view angles to be selected based on the errors corresponding to the view angles to be selected.

Specifically, corresponding weights are allocated to the errors corresponding to the same angle of view to be selected, and products of the errors and the weights are summed to obtain product summation values of the angles of view to be selected. The target field angle is determined based on the magnitude of the product addition value of each candidate field angle.

Illustratively, the following description is made with an alternative field angle of 30 °:

corresponding to the angle of view to be selected 30 °, the corresponding product sum is:

p3＝10％×0.5+5％×0.3+6％×0.2＝0.077

similarly, the product addition value corresponding to the field angle to be selected 31 ° is determined to be 0.11 by way of example.

Since 0.11 of the product addition value of 31 ° of the angle of view to be selected is greater than 0.077 of the product addition value of 30 ° of the angle of view to be selected, it is determined that 30 ° of the angle of view to be selected is the target angle of view to be selected.

205. Determining whether the target field angle meets the requirements, and if so, executing 208; otherwise, 206 is performed.

Specifically, to ensure that the target angle of view is the most accurate angle of view, it is necessary to determine whether the target angle of view meets the requirements, and 208 is only performed if the target angle of view meets the requirements. When the target field of view does not meet the requirements, 206 is performed.

Specifically, the method for determining whether the target field angle meets the requirement may be: and determining the cumulative determination times of the target field angle, determining whether the cumulative determination times reach a time threshold, if so, indicating that the target field angle meets the test requirement of the intelligent driving system, and executing 208. If the number of times threshold is not reached, it is indicated that the target field angle does not meet the test requirement for the intelligent driving system, and 206 is performed.

206. The target field of view is determined as the second sample field of view.

207. Resetting a plurality of different angles of view to be selected at a set second step rate of change based on the second sample angle of view, and executing 202.

Specifically, in order to improve the accuracy of determining the target angle of view, the second step rate of change for resetting the angle of view to be selected should be smaller than the step rate of change between the angles of view to be selected with respect to the target angle of view.

Illustratively, the target field of view relates to a candidate field of view of 30 ° and 31 ° with a step rate of change therebetween of 1 °. In order to improve the accuracy of determination of the target angle of view, the second step rate of change for resetting the angle of view to be selected may be set to 05 °.

It should be noted that, based on the second sample angle of view, the process of resetting the plurality of different angles of view to be selected at the set second step rate of change is substantially the same as the above-mentioned process of setting the plurality of angles of view to be selected based on the first sample angle of view, and therefore will not be described in detail.

208. And determining the target field angle as the field angle required by the camera when the simulation test system performs the test.

Specifically, the target field angle is a field angle required by the camera when the simulation test system performs a formal test on the intelligent driving system. The target field angle is selected based on the test results of the simulation test system under different field angles, so that the target field angle meets the test requirement of the simulation test system on the intelligent driving system.

In a third aspect, according to the method shown in fig. 1 or fig. 4, another embodiment of the present disclosure further provides a device for determining a camera field angle, as shown in fig. 11, where the device mainly includes:

the test unit 31 is configured to control the simulation test system to test the intelligent driving system of the test vehicle using a plurality of simulation road scenes under different angles of view to be selected, where a fixed inter-vehicle distance is provided between the traffic vehicle and the test vehicle in each of the simulation road scenes;

and a determining unit 32 configured to determine a target field angle from each of the candidate field angles based on a fixed following distance corresponding to each of the simulated road scenes and a measured following distance between the traffic vehicle and the test vehicle in each of the simulated road scenes corresponding to the same one of the candidate field angles in a test result of the intelligent driving system, wherein the measured following distance is determined based on a simulated road image corresponding to the simulated road scene captured by a camera of the simulation test system at the corresponding candidate field angle.

According to the camera view angle determining device provided by the embodiment of the disclosure, under different view angles to be selected, the simulation test systems are controlled to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes respectively. And determining the target field of view from the field of view to be selected based on the fixed distance of travel corresponding to the field of view to be selected and the measured distance of travel between the traffic vehicle and the test vehicle in the field of view to be selected corresponding to the same field of view in the test result of the intelligent driving system. Therefore, in the embodiment of the disclosure, the view angle required by the simulation test system for testing the intelligent driving system can be determined in different view angles to be more suitable for the simulation test system based on the test results of the simulation test system under different view angles to be selected, so that the perception precision of the camera is improved in the simulation test, and the reliability of the simulation test is improved.

In some embodiments, as shown in fig. 12, the determining unit 32 includes:

a first determining module 321, configured to determine an error between a measured inter-vehicle distance between the traffic vehicle and the test vehicle and a corresponding fixed inter-vehicle distance in each of the simulated road scenes corresponding to the same view angle to be selected;

a second determining module 322, configured to determine the target field angle from the candidate field angles based on respective errors corresponding to the candidate field angles.

In some embodiments, as shown in fig. 12, the second determining module 322 is configured to sum errors corresponding to the same angle of view to be selected to obtain error sum values of the angles of view to be selected respectively; and determining the target field angle based on the magnitude of the error addition value of each candidate field angle.

In some embodiments, as shown in fig. 12, the second determining module 322 is configured to multiply errors corresponding to the same angle of view to be selected, so as to obtain error product values of the angles of view to be selected respectively; and determining the target field angle based on the magnitude of the error product value of each candidate field angle.

In some embodiments, as shown in fig. 12, the second determining module 322 is configured to assign a corresponding weight to each error corresponding to the same angle of view to be selected, and sum products of each error and its respective weight to obtain a sum of products of each angle of view to be selected; and determining the target field angle based on the magnitude of the product sum value of the candidate field angles.

Further, corresponding to each error of the same view angle to be selected, weight is distributed to each error according to the fixed inter-vehicle distance corresponding to each error;

or, corresponding to each error of the same vision angle to be selected, distributing weight for each error according to the fixed distance between the vehicles and the requirement of the test working condition corresponding to each error, wherein the test working condition is related to the driving danger degree.

In some embodiments, the error between the measured following distance between the traffic vehicle and the test vehicle and the corresponding fixed following distance is: relative error or absolute error.

In some embodiments, as shown in fig. 12, the test unit 31 is configured to perform, for each of the candidate angles of view: adjusting the field angle of a camera of the simulation test system to be the field angle to be selected, and controlling a display device of the simulation test system to sequentially play simulation road images corresponding to a plurality of simulation road scenes; when the display equipment plays the simulated road image corresponding to any simulated road scene, controlling the camera to acquire the simulated road image; and obtaining an intelligent driving system test result corresponding to the simulated road scene based on the acquired simulated road image.

In some embodiments, as shown in fig. 12, the device for determining a camera field angle further includes:

an acquisition unit 33 for acquiring a first sample field angle;

a first setting unit 34 for setting a plurality of different angles of view to be selected at a set first step change rate based on the first sample angle of view.

a second setting unit 35 for determining the target angle of view determined by the determining unit 32 as a second sample angle of view; and resetting a plurality of different angles of view to be selected according to the set second step change rate based on the second sample angle of view, and continuously controlling a simulation test system to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes under the different angles of view to be selected.

The determining device of the camera angle of view provided by the embodiment of the third aspect may be used to perform the determining method of the camera angle of view provided by the embodiment of the first aspect or the second aspect, and the related meaning and specific implementation manner of the determining device of the camera angle of view may be referred to the related description in the embodiment of the first aspect or the second aspect, which are not described in detail herein.

In a fourth aspect, another embodiment of the present disclosure further provides a simulation test system, as shown in fig. 13, the system mainly including: a camera 41, a display device 42, an intelligent driving system 43, and a camera angle-of-view determining apparatus 44 according to claim 11;

the display device 42 is configured to play, under control of the determining device of the field angle of the camera 41, a simulated road image corresponding to any simulated road scene, where a fixed inter-vehicle distance is provided between a traffic vehicle and a test vehicle in the simulated road scene, and the simulated road image includes the traffic vehicle;

the camera 41 simulates a camera on the test vehicle, and is used for shooting a simulated road image played by the display device 42 at a field angle to be selected set by the camera field angle determining device 44;

the intelligent driving system 43 is configured to obtain an intelligent driving system test result corresponding to the simulated road scene based on the collected simulated road image, and feed back the intelligent driving system test result to the camera view angle determining device 44, so that the camera view angle determining device 44 determines a target view angle required by the camera when the intelligent driving system test is performed, where the intelligent driving system test result includes obtaining a measured driving distance between the traffic vehicle and the test vehicle in the simulated road scene based on the simulated road image collected by the camera 41.

According to the simulation test system provided by the embodiment of the disclosure, under different angles of view to be selected, the simulation test system is controlled to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes respectively. And determining the target field angle from the field angles to be selected based on the fixed distance between the traffic vehicles and the test vehicles in the simulated road scenes corresponding to the same field angle to be selected in the test result of the intelligent driving system. Therefore, in the embodiment of the disclosure, the view angle required by the simulation test system for testing the intelligent driving system can be determined in different view angles to be more suitable for the simulation test system based on the test results of the simulation test system under different view angles to be selected, so that the perception precision of the camera is improved in the simulation test, and the reliability of the simulation test is improved.

In some embodiments, the intelligent driving system 43 is an advanced driving assistance system.

The simulation test system provided by the embodiment of the fourth aspect may be used to perform the method for determining the camera angle of view provided by the embodiment of the first aspect or the second aspect, and the related meaning and specific implementation manner may be referred to the related description in the embodiment of the first aspect or the second aspect, which are not described in detail herein.

In a fifth aspect, an embodiment of the present disclosure provides a storage medium, where the storage medium includes a stored program, and when the program runs, controls a device in which the storage medium is located to execute the method for determining the camera angle of view according to the first aspect or the second aspect.

The storage medium may include volatile memory, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

In a sixth aspect, embodiments of the present disclosure provide a human-machine interaction device comprising a storage medium coupled to one or more processors configured to execute program instructions stored in the storage medium; the program instructions, when executed, perform the method of determining a camera angle of view of any one of the first or second aspects.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

It will be apparent to those skilled in the art that embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, embodiments of the present disclosure may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

It will be appreciated by those skilled in the art that embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, embodiments of the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, embodiments of the present disclosure may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A method for determining a camera field angle, the method comprising:

and determining a target field angle from the to-be-selected field angles based on a fixed distance between driving wheels corresponding to the to-be-selected field angles and a measured distance between the traffic vehicle and the test vehicle in each simulated road scene corresponding to the same to-be-selected field angle in a test result of the intelligent driving system, wherein the measured distance between driving wheels is determined based on a simulated road image corresponding to the simulated road scene, which is shot by a camera of the simulation testing system at the corresponding to-be-selected field angle, and the target field angle is a field angle required by the camera when the intelligent driving system is tested by the simulation testing system.

2. The method of claim 1, wherein determining a target field of view from each of the candidate field of view based on a fixed inter-vehicle distance corresponding to each of the simulated road scenes and a measured inter-vehicle distance between the vehicle and the test vehicle within each of the simulated road scenes corresponding to the same one of the candidate field of view in a test result of an intelligent driving system, comprises:

determining errors between measured inter-vehicle distances between the traffic vehicle and the test vehicle and corresponding fixed inter-vehicle distances in each simulated road scene corresponding to the same field angle to be selected;

and determining the target view angle from the view angles to be selected based on the errors corresponding to the view angles to be selected.

3. The method of claim 2, wherein determining the target field of view from each of the candidate field of view based on respective errors corresponding to each of the candidate field of view comprises:

summing the errors corresponding to the same angle of view to be selected to obtain error sum values of the angles of view to be selected respectively;

and determining the target field angle based on the magnitude of the error addition value of each candidate field angle.

4. The method of claim 2, wherein determining the target field of view from each of the candidate field of view based on respective errors corresponding to each of the candidate field of view comprises:

multiplying the errors corresponding to the same angle of view to be selected to obtain error product values of the angles of view to be selected respectively;

and determining the target field angle based on the magnitude of the error product value of each candidate field angle.

5. The method of claim 2, wherein determining the target field of view from each of the candidate field of view based on respective errors corresponding to each of the candidate field of view comprises:

distributing corresponding weights for the errors corresponding to the same angle of view to be selected, and summing the products of the errors and the weights of the errors to be selected to obtain the sum of the products of the angles of view to be selected;

and determining the target field angle based on the magnitude of the product sum value of the candidate field angles.

6. The method of claim 5, wherein each error corresponding to the same angle of view to be selected is assigned a weight based on a fixed inter-vehicle distance corresponding to each error;

7. The method according to any one of claims 3 to 5, wherein an error between the measured following distance between the traffic vehicle and the test vehicle and the corresponding fixed following distance is: relative error or absolute error.

8. The method of any one of claims 1-6, wherein controlling the simulated test system to test the intelligent driving system of the test vehicle using a plurality of simulated road scenes at different angles of view to be selected comprises:

performing for each of the candidate angles of view: adjusting the field angle of a camera of the simulation test system to be the field angle to be selected, and controlling a display device of the simulation test system to sequentially play simulation road images corresponding to a plurality of simulation road scenes; when the display equipment plays the simulated road image corresponding to any simulated road scene, controlling the camera to acquire the simulated road image; and obtaining an intelligent driving system test result corresponding to the simulated road scene based on the acquired simulated road image.

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

acquiring a first sample field angle;

and setting a plurality of different angles of view to be selected at a set first step change rate based on the first sample angle of view.

10. The method of any of claims 1-6, wherein after determining a target field of view from each of the candidate field of view, the method further comprises:

determining the target field of view as a second sample field of view;

and resetting a plurality of different angles of view to be selected according to the set second step change rate based on the second sample angle of view, and continuously controlling the simulation test system to test the intelligent driving system of the test vehicle by using a plurality of simulation road scenes under the different angles of view to be selected.

11. A camera view angle determining apparatus, the apparatus comprising:

And a determining unit configured to determine a target field of view from each of the candidate field of view based on a fixed following distance corresponding to each of the simulated road scenes and a measured following distance between the traffic vehicle and the test vehicle in each of the simulated road scenes corresponding to the same candidate field of view in a test result of the intelligent driving system, wherein the measured following distance is determined based on a simulated road image corresponding to the simulated road scene captured by a camera of the simulation test system at the corresponding candidate field of view, and the target field of view is a field of view required by the camera when the intelligent driving system is tested by the simulation test system.

12. A simulation test system, comprising: a camera, a display device, an intelligent driving system, and the camera view angle determining apparatus of claim 11;

the display device is used for playing a simulated road image corresponding to any simulated road scene under the control of the camera view angle determining device, wherein a fixed distance between a traffic vehicle and a test vehicle in the simulated road scene is reserved, and the traffic vehicle is included in the simulated road image;

13. The system of claim 12, wherein the intelligent driving system is an advanced driving assistance system.

14. A storage medium comprising a stored program, wherein the program, when run, controls a device in which the storage medium is located to perform the method of determining the camera angle of view of any one of claims 1 to 10.

15. A human-machine interaction device, the device comprising a storage medium coupled to one or more processors configured to execute program instructions stored in the storage medium; the program instructions, when executed, perform the method of determining camera angle of view of any one of claims 1 to 10.