Camera position determination method and device and vehicle

Abstract

The invention provides a method and device for determining the position of a camera and a vehicle, and relates to the technical field of vehicles, and the method comprises the steps: obtaining the position of a preset layout region of the camera in a vehicle cabin and target factor information; wherein the target factor information comprises a target parameter and a target weight value corresponding to the target parameter; the target parameter is a parameter influencing the camera to collect a facial image of the driver; determining a target layout area in the preset layout area based on the target parameter; and determining a target layout position of the camera in the target layout area based on the target parameter and the target weight value. According to the method, the rationality of the layout position of the camera in the vehicle cabin can be improved, and the monitoring effect of the camera is further improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and more specifically, to a method, device and vehicle for determining a camera position in the field of vehicle technology. Background Art

[0002] To ensure driving safety, more and more vehicles are equipped with cameras, such as Driver Monitoring System Camera (DMS Camera), which monitors the driver's driving status in real time to prevent safety hazards such as fatigue driving and distracted driving.

[0003] At present, the layout of cameras mostly relies on manual layout based on human experience; however, this traditional method has some problems, such as non-optimal layout position and unreasonable viewing angle, which leads to poor monitoring effect and makes it difficult to fully play the role of ensuring driving safety.

[0004] Therefore, how to improve the rationality of the layout position of the camera in the cabin, and then improve the monitoring effect of the camera, is a technical problem that urgently needs to be solved. Summary of the invention

[0005] The present application provides a method, device and vehicle for determining the position of a camera. The method can improve the rationality of the layout position of the camera in the cabin, thereby improving the monitoring effect of the camera.

[0006] In a first aspect, a method for determining a camera position is provided, the method comprising: obtaining the position and target factor information of a preset layout area of ​​a camera in a vehicle cabin; wherein the target factor information comprises a target parameter and a target weight value corresponding to the target parameter; the target parameter is a parameter that affects the camera's acquisition of a facial image of the driver; based on the target parameter, determining a target layout area in the preset layout area; based on the target parameter and the target weight value, determining a target layout position of the camera in the target layout area.

[0007] In an embodiment of the present application, the position and target factor information of a preset layout area of ​​a camera in a vehicle cabin are obtained; the target factor information includes a target parameter and a target weight value corresponding to the target parameter; by influencing the target parameter of the camera for collecting the facial image of the driver, the target layout area can be determined in the preset layout area, that is, the approximate layout position of the camera in the preset layout area is preliminarily determined; then, based on the target parameter that affects the camera for collecting the facial image of the driver and the target weight value corresponding to the target parameter, the target layout position for arranging the camera in the target layout area is determined, that is, the target layout position for arranging the camera in the preliminarily determined target layout area is further determined; since the target layout position is determined by the target parameter and the target weight value corresponding to the target parameter ; and the target parameter is a parameter that affects the camera's collection of the driver's facial image, and the target weight value corresponding to the target parameter can reflect the importance of the target parameter in the camera layout; therefore, determining the target layout position based on the target parameter and the target weight value corresponding to the target parameter can further improve the reliability of the layout position of the camera in the cabin; compared with the poor monitoring effect of the camera caused by manual layout of the camera position based on artificial experience in the related art, this scheme can automatically determine the target layout position based on the target parameter and the target weight value corresponding to the target parameter, without relying on artificial experience to manually layout the camera position; therefore, the above scheme can improve the rationality of the layout position of the camera in the cabin, thereby improving the monitoring effect of the camera.

[0008] In combination with the first aspect, in certain implementations of the first aspect, a target layout area in a preset layout area is determined based on the target parameters, including: based on the target parameters, determining target constraints corresponding to the target parameters; and determining an area in the preset layout area that meets the target constraints as the target layout area.

[0009] In an embodiment of the present application, through the target parameters and the target constraints corresponding to the target parameters, the target layout area that meets the target constraints can be accurately screened out from the preset layout area, and then the target layout position can be subsequently determined from the target layout area. This can further improve the rationality of the layout position of the camera in the cabin, thereby improving the monitoring effect of the camera.

[0010] In combination with the first aspect and the above-mentioned implementation methods, in some implementation methods of the first aspect, the target constraint condition includes a target interval corresponding to the target parameter; an area in the preset layout area that satisfies the target constraint condition is determined as the target layout area, including: obtaining multiple layout positions in the preset layout area, and parameter values ​​of the target parameters of each layout position; and determining the layout area corresponding to the first layout position whose parameter value is in the target interval as the target layout area.

[0011] In an embodiment of the present application, the first layout position corresponding to the parameter value in the target interval can be determined through the target interval included in the target constraint condition, and then the target layout area can be quickly and accurately determined from the preset layout area, further improving the rationality of the layout position of the camera in the cabin, thereby improving the monitoring effect of the camera.

[0012] In combination with the first aspect and the above-mentioned implementation methods, in some implementation methods of the first aspect, the target layout position of the camera in the target layout area is determined based on the target parameter and the target weight value, including: obtaining the parameter values ​​of the target parameters of multiple second layout positions in the target layout area; determining the target value of each second layout position based on the target weight value and the parameter value of the target parameter of the second layout position; and determining the second layout position corresponding to the target value that meets the preset conditions among the multiple target values ​​as the target layout position.

[0013] In an embodiment of the present application, the target value of each second layout position is obtained by the parameter value of the target parameter of the second layout position and the target weight value of the target parameter, so that a reasonable comprehensive evaluation can be performed on each second layout position; then, the second layout position corresponding to the target value that meets the preset conditions is determined as the target layout position to determine the appropriate layout position of the camera, thereby improving the rationality of the layout position of the camera in the cabin and the monitoring effect of the camera.

[0014] In combination with the first aspect and the above-mentioned implementation methods, in some implementation methods of the first aspect, the target value of each second layout position is determined based on the target weight value and the parameter value of the target parameter of the second layout position, including: inputting the parameter value of the target parameter of the second layout position into the target model to obtain the target value of the second layout position; wherein the target model includes the target weight value.

[0015] In an embodiment of the present application, by inputting the parameter values ​​of the target parameters of the second layout position into the target model, the target value of each second layout position can be quickly acquired to reduce the calculation time, thereby improving the convenience of subsequent determination of the target layout position, and further improving the rationality of the layout position of the camera in the cabin.

[0016] In combination with the first aspect and the above-mentioned implementation methods, in certain implementation methods of the first aspect, the method provided in the embodiments of the present application also includes: obtaining historical test data and initial weight values ​​of target parameters; wherein the historical test data includes historical target values ​​of the third layout position; adjusting the initial weight value based on the historical target value of the third layout position to obtain the target weight value.

[0017] In an embodiment of the present application, the initial weight value of the target parameter is adjusted through historical test data to obtain the target weight value; since the target weight value can reflect the current importance of the target parameter in determining the target layout position, this can subsequently improve the reliability of the determined target layout position, thereby improving the rationality of the layout position of the camera in the cabin and the monitoring effect of the camera.

[0018] In combination with the first aspect and the above-mentioned implementation methods, in some implementation methods of the first aspect, obtaining the position and target factor information of the preset layout area of ​​the camera in the vehicle cabin includes: obtaining a three-dimensional model corresponding to the vehicle cabin; wherein the three-dimensional model is used to represent the layout information in the vehicle cabin; based on the three-dimensional model, obtaining the positions and target factor information of multiple layout areas; and in response to a selection operation, determining the position of the preset layout area from the positions of the multiple layout areas.

[0019] In an embodiment of the present application, the layout information in the cabin can be obtained through the three-dimensional model corresponding to the cabin, and then the location of the layout area in the cabin and the target parameter information corresponding to the layout position in each layout area can be obtained, thereby providing reliable data support for the subsequent determination of the target layout position, further improving the rationality of the layout position of the camera in the cabin, and thereby improving the monitoring effect of the camera.

[0020] In combination with the first aspect and the above-mentioned implementation methods, in some implementation methods of the first aspect, the target parameter includes at least one of the following parameters: a first target parameter, a second target parameter and a third target parameter; wherein the first target parameter is used to indicate the viewing angle of the camera when capturing the driver's face; the second target parameter is used to indicate the relative position of the camera when capturing the driver's face; and the third target parameter is used to indicate the image proportion of the driver's face in the image captured by the camera.

[0021] In an embodiment of the present application, the rationality of the camera layout can be evaluated from multiple different dimensions through target parameters to determine the appropriate location for installing the camera in the preset layout area. This can further improve the rationality of the layout position of the camera in the cabin and thereby improve the monitoring effect of the camera.

[0022] In a second aspect, a device for determining a camera position is provided, the device comprising:

[0023] An acquisition module, used to acquire the position of a preset layout area of ​​the camera in the vehicle cabin and target factor information; wherein the target factor information includes a target parameter and a target weight value corresponding to the target parameter; the target parameter is a parameter that affects the camera to collect the driver's facial image;

[0024] A determination module, used for determining a target layout area in a preset layout area based on a target parameter;

[0025] The determination module is also used to determine the target layout position of the camera in the target layout area based on the target parameters and the target weight value.

[0026] In a possible implementation, the determination module is specifically configured to determine, based on the target parameters, a target constraint condition corresponding to the target parameter; and determine an area in the preset layout area that satisfies the target constraint condition as the target layout area.

[0027] In a possible implementation, the determination module is specifically used to obtain multiple layout positions in a preset layout area and parameter values ​​of target parameters of each layout position; and determine the layout area corresponding to the first layout position whose parameter value is in the target interval as the target layout area.

[0028] In one possible implementation, a determination module is specifically used to obtain parameter values ​​of target parameters of multiple second layout positions in a target layout area; determine the target value of each second layout position based on a target weight value and the parameter value of the target parameter of the second layout position; and determine the second layout position corresponding to a target value that meets a preset condition among the multiple target values ​​as the target layout position.

[0029] In a possible implementation, the device further includes an input module, specifically configured to input a parameter value of a target parameter of the second layout position into a target model to obtain a target value of the second layout position; wherein the target model includes a target weight value.

[0030] In one possible implementation, the acquisition module is also used to obtain historical test data and initial weight values ​​of target parameters; wherein the historical test data includes historical target values ​​of the third layout position; and the initial weight values ​​are adjusted based on the historical target values ​​of the third layout position to obtain the target weight values.

[0031] In one possible implementation, the acquisition module is specifically used to acquire a three-dimensional model corresponding to the vehicle cabin; wherein the three-dimensional model is used to represent the layout information in the vehicle cabin; based on the three-dimensional model, the positions and target factor information of multiple layout areas are acquired; and in response to a selection operation, the position of a preset layout area is determined from the positions of the multiple layout areas.

[0032] In a third aspect, a vehicle is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the vehicle executes the method in the first aspect or any possible implementation of the first aspect.

[0033] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0034] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a structural schematic diagram of a vehicle cabin provided in an embodiment of the present application;

[0036] Figure 2 is a schematic flow chart of a method for determining a camera position provided in an embodiment of the present application;

[0037] Figure 3 is a schematic diagram of a layout area provided in an embodiment of the present application;

[0038] Figure 4 is a schematic diagram of a three-dimensional model provided in an embodiment of the present application;

[0039] Figure 5 is a schematic diagram of a target model provided in an embodiment of the present application;

[0040] Figure 6 is a schematic flow chart of a method for determining a camera position provided in an embodiment of the present application;

[0041] Figure 7 is a structural schematic diagram of a device for determining a camera position provided in an embodiment of the present application;

[0042] Figure 8 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0044] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0045] Before introducing the embodiments of the present application, the relevant terms involved in the present application are first explained as follows:

[0046] (1) Driver Monitoring System Camera (DMS Camera): A device specially installed in the vehicle cabin to monitor the driver's status. It captures the driver's facial image or video to analyze the driver's fatigue level, concentration and other information in real time. The DMS camera uses computer vision, artificial intelligence and sensor technology to capture and analyze the driver's facial features, eye movements, head posture and other information to determine whether the driver is in a state of fatigue, distraction or danger.

[0047] (2) A-pillar: A part of the vehicle body structure, located between the front windshield and the front door, which mainly supports the top of the cockpit and withstands frontal impact.

[0048] (3) Steering wheel guard: A steering wheel guard is a protective component covering the outside of the steering wheel, which is usually used to improve driving comfort and aesthetics, and to protect the steering wheel from damage to a certain extent.

[0049] (4) Interior rearview mirror area: refers to the area inside the car, located above the driver's head and in front of the windshield, mainly used to install the interior rearview mirror. This area can be used to arrange the driver monitoring camera, and care must be taken to prevent the camera's field of view from being blocked by the rearview mirror.

[0050] (5) Pitch: The angle of rotation of the face in the vertical direction around the horizontal axis, that is, the degree to which the face is raised or lowered. In a three-dimensional space coordinate system, the pitch angle is the angle of rotation around the X-axis (pointing to the right side of the face).

[0051] (6) Yaw: The angle at which the face rotates horizontally around the vertical axis, that is, the degree to which the face turns left or right. In a three-dimensional space coordinate system, the yaw angle is the angle of rotation around the Y axis (pointing downwards from the face).

[0052] (7) Roll angle: The angle at which a face rotates around the line of sight on a horizontal plane, that is, the degree of rotation of the face photo relative to the frontal perspective. In a three-dimensional space coordinate system, the roll angle is the angle of rotation around the Z axis (pointing to the front of the face).

[0053] (8) Face pixel ratio: The ratio of the number of pixels occupied by the face in an image to the number of pixels in the entire image, used to measure the clarity and size of the face in the image. The higher this ratio is, the clearer and more prominent the face is in the image.

[0054] (9) Optical axis center position: The optical axis center of the camera refers to the origin of the camera coordinate system, which is located at the center of the lens. In the camera coordinate system, the optical axis center determines the imaging quality and shooting effect of the lens. The accuracy of the optical axis center position is crucial to ensure image quality.

[0055] like Figure 1 As shown, Figure 1 A schematic diagram of a vehicle cabin structure provided in an embodiment of the present application. The vehicle cabin 100 includes: a main driving seat 101, a steering wheel 102, a dashboard 103, a center console 104, a camera 105, etc. Usually, the driver can drive the vehicle in the main driving seat 101. The camera 105 can be a driver monitoring camera.

[0056] In order to ensure driving safety, more and more vehicles are equipped with cameras, such as driver monitoring cameras, which monitor the driver's driving status in real time to prevent safety hazards such as fatigue driving and distracted driving.

[0057] At present, the layout of cameras mostly relies on manual layout based on human experience; however, this traditional method has some problems, such as non-optimal layout position and unreasonable viewing angle, which leads to poor monitoring effect and makes it difficult to fully play the role of ensuring driving safety.

[0058] Therefore, how to improve the rationality of the layout position of the camera in the cabin, and then improve the monitoring effect of the camera, is a technical problem that urgently needs to be solved.

[0059] In view of this, the embodiments of the present application provide a method, device and vehicle for determining the position of a camera. Unlike the manual arrangement method in the related art that requires relying on human experience, the present solution determines the target layout area in the preset layout area based on the target parameters; and determines the target layout position of the camera in the target layout area based on the target parameters and the target weight value; therefore, the present solution can improve the rationality of the layout position of the camera in the cabin, thereby improving the monitoring effect of the camera.

[0060] In order to illustrate the technical solution described in this application, the following is a description through specific embodiments. Figures 2 to 6 The method for determining the camera position provided in an embodiment of the present application is described in detail.

[0061] It should be understood that the embodiments of the present application do not specifically limit the subject of executing the method for determining the camera position, as long as the program that records the code of the method for determining the camera position of the embodiments of the present application can be run to communicate according to the method for determining the camera position of the embodiments of the present application. For example, the subject of executing the method for determining the camera position provided in the embodiments of the present application may be a vehicle, or a method for determining the position of a cabin camera used in a vehicle, such as a chip.

[0062] Figure 2 It is a flowchart of a method for determining a camera position provided in an embodiment of the present application.

[0063] S201. Obtain the position and target factor information of the preset layout area of ​​the camera in the vehicle cabin.

[0064] The target factor information includes target parameters and target weight values ​​corresponding to the target parameters; the target parameters are parameters that affect the camera's acquisition of the driver's facial image.

[0065] Exemplarily, the preset layout area may refer to a specific area selected in the cabin where a camera (e.g., a driver monitoring camera) is to be installed. The preset layout area may be a layout area determined manually or by other means (e.g., a layout area determined by a recommendation algorithm), and the present application embodiment does not impose any specific restrictions on this. In addition, the present application embodiment does not impose any specific restrictions on the shape and size of the layout area.

[0066] For example, the preset layout area can be the A-pillar area in the vehicle cabin or a part of the preset area of ​​the A-pillar area, the steering wheel cover area or a part of the preset area of ​​the steering wheel cover, the rearview mirror area or a part of the preset area of ​​the rearview mirror area, etc.

[0067] Exemplarily, the cameras arranged in the preset layout area can be used to monitor the driver's driving status; for example, by collecting the driver's facial image to determine whether the current driver is in a fatigued state, whether he is driving under the influence, etc.

[0068] Exemplarily, the target factor information may be used to detect whether it is feasible to install a camera in a preset layout area; and through the target factor information, a suitable location for installing the camera in the preset layout area may be determined.

[0069] Exemplarily, the target parameters may refer to parameters that affect the quality, viewing angle, clarity, distance, etc. of the driver's facial image captured by the camera, thereby affecting the rationality of the camera layout; in other words, the target parameters can provide reference indicators for the arrangement of the cameras in the preset layout area to ensure that the camera can capture accurate and reliable driver's facial images.

[0070] As an example, the target parameter includes at least one of the following parameters: a first target parameter, a second target parameter, and a third target parameter.

[0071] Among them, the first target parameter is used to indicate the viewing angle of the camera when capturing the driver's face; the second target parameter is used to indicate the relative position of the camera when capturing the driver's face; and the third target parameter is used to indicate the image proportion of the driver's face in the image captured by the camera.

[0072] Exemplarily, the first target parameter may include a pitch angle, a yaw angle, and a roll angle of the driver relative to the camera. The first target parameter may be used to affect the shape, size, and clarity of the facial image captured by the camera.

[0073] Exemplarily, the second target parameter may include the center position of the optical axis, the distance between the camera lens and the driver's face (hereinafter, the distance between the camera lens and the driver's face is described as the lens distance). The change in relative position will affect the size, pixel density, and detail expression of the facial image captured by the camera. Therefore, by controlling the distance between the camera and the driver's face, it can be ensured that the camera can capture a facial image of the appropriate size, avoiding pixel blur due to an image that is too large or detail loss due to an image that is too small.

[0074] Exemplarily, the third target parameter may include face pixel ratio and field of view occlusion surface gap. The third target parameter may be used to reflect the proportion of the driver's facial image in the total image. The size of the image proportion will directly affect the richness of the facial information captured by the camera, and thus affect the reliability of monitoring the driver's status.

[0075] It can be understood that the rationality of the camera layout can be evaluated from multiple different dimensions through target parameters to determine the appropriate location for installing the camera in the preset layout area. This can further improve the rationality of the layout position of the camera in the cabin and thus improve the monitoring effect of the camera.

[0076] Exemplarily, the target weight value corresponding to the target parameter can be used to indicate the relative importance value of the target parameter; in other words, the target weight value can be used to measure the influence of the target parameter on the final camera layout position when determining the camera layout position; the higher the target weight value, the higher the importance of the target parameter corresponding to the target weight value in determining the camera layout position.

[0077] For example: the target parameters include target parameter 1, target parameter 2, target parameter 3 and target parameter 4. The target weight value 1 corresponding to target parameter 1 is 0.2, the target weight value 2 corresponding to target parameter 2 is 0.1, the target weight value 3 corresponding to target parameter 3 is 0.05, and the target weight value 4 corresponding to target parameter 4 is 0.4. Then, the target weight values ​​of the target parameters are ranked from large to small (that is, relative importance): target weight value 4, target weight value 1, target weight value 2, target weight value 3. Of course, the specific values ​​of the above target weight values ​​are only for illustrative purposes, and the specific values ​​can refer to the actual application scenarios.

[0078] For a detailed description of S201, please refer to the following embodiments, which will not be described again here.

[0079] S202. Determine a target layout area in a preset layout area based on the target parameter.

[0080] For example, the preset layout area may refer to a layout area that may be used to arrange the camera, which is determined in the preliminary stage based on factors such as the type of vehicle cabin, the arrangement requirements of the camera, etc. The target layout area may refer to an actual feasible layout area obtained by further analyzing the preset layout area based on the target parameters.

[0081] For example, Figure 3 As shown, Figure 3 A schematic diagram of a layout area provided in an embodiment of the present application. Figure 3 Taking the A-pillar as an example, Figure 3 In (a), the A-pillar may include a preset layout area 310 and a target layout area 320 in the preset layout area 310 .

[0082] It is understandable that based on the target parameters, a more reasonable target layout area can be further screened out in the preset layout area, and the determination range can be narrowed down to a more likely to find a suitable layout position, thereby reducing unnecessary data processing in the later stage.

[0083] For a detailed description of S202, please refer to the following embodiments, which will not be described again here.

[0084] S203. Determine the target layout position of the camera in the target layout area based on the target parameters and the target weight value.

[0085] Exemplarily, the target layout area may include multiple different layout positions; the layout positions may be represented by coordinates (e.g., three-dimensional coordinates). The number of layout positions in the target layout area may be determined according to actual installation accuracy requirements, etc. For example, a layout position may be determined for each preset offset distance (e.g., 1 mm) in the target layout area.

[0086] For example, Figure 3 As shown in (b) of FIG. 8 , the A-pillar may include a preset layout area 310 and a target layout position 330 in the preset layout area 310 .

[0087] Exemplarily, multiple layout positions in the target layout area may be evaluated based on the target parameter and the target weight value, and then the target layout position may be determined from the multiple layout positions.

[0088] It can be understood that by quantifying the arrangement effect in the form of target factor information, the credibility and versatility of the arrangement of cameras can be improved. In addition, by arranging cameras at the target layout position, the quality of the image information of the driver collected can be improved; for example, the driver's facial information can be collected, so that the driver's current driving state can be accurately analyzed, thereby improving the monitoring effect of the camera.

[0089] For a detailed description of S203, please refer to the following embodiments, which will not be described again here.

[0090] In an embodiment of the present application, the position and target factor information of a preset layout area of ​​a camera in a vehicle cabin are obtained; the target factor information includes a target parameter and a target weight value corresponding to the target parameter; by influencing the target parameter of the camera for collecting the facial image of the driver, the target layout area can be determined in the preset layout area, that is, the approximate layout position of the camera in the preset layout area is preliminarily determined; then, based on the target parameter that affects the camera for collecting the facial image of the driver and the target weight value corresponding to the target parameter, the target layout position for arranging the camera in the target layout area is determined, that is, the target layout position for arranging the camera in the preliminarily determined target layout area is further determined; since the target layout position is determined by the target parameter and the target weight value corresponding to the target parameter ; and the target parameter is a parameter that affects the camera's collection of the driver's facial image, and the target weight value corresponding to the target parameter can reflect the importance of the target parameter in the camera layout; therefore, determining the target layout position based on the target parameter and the target weight value corresponding to the target parameter can further improve the reliability of the layout position of the camera in the cabin; compared with the poor monitoring effect of the camera caused by manual layout of the camera position based on artificial experience in the related art, this scheme can automatically determine the target layout position based on the target parameter and the target weight value corresponding to the target parameter, without relying on artificial experience to manually layout the camera position; therefore, the above scheme can improve the rationality of the layout position of the camera in the cabin, thereby improving the monitoring effect of the camera.

[0091] In actual scenarios, since the layouts of different types of cabins may be different, it is difficult to inspect the specific layout of the cabin on site. Therefore, in order to accurately obtain the layout information in the cabin and obtain the location and target factor information of the preset layout area in the cabin, the following embodiments may be referred to:

[0092] In a possible embodiment of the present application, the above S201 includes: obtaining a three-dimensional model corresponding to the vehicle cabin; based on the three-dimensional model, obtaining the positions and target factor information of multiple layout areas; in response to a selection operation, determining the position of a preset layout area from the positions of multiple layout areas.

[0093] Among them, the three-dimensional model is used to represent the layout information in the cabin.

[0094] For example, the three-dimensional model may be a three-dimensional model describing the layout of the vehicle cabin. Figure 4 The schematic diagram of the three-dimensional model shown in FIG. 4 shows a schematic diagram of the three-dimensional model, and the three-dimensional model may include a simulated driver 410, a main driving seat 420, an A-pillar 430, etc. Optionally, the three-dimensional model may also include key components such as a steering wheel, an instrument panel, a steering wheel, a center console, a camera, and a camera field of view. In this way, the layout information in the cabin can be accurately obtained.

[0095] As an example, a three-dimensional model corresponding to the vehicle cabin can be constructed and obtained through three-dimensional modeling application software according to the design of the vehicle and actual measurement data.

[0096] As another example, the three-dimensional model corresponding to the cabin may also be directly obtained from the cloud or the storage module of the vehicle.

[0097] Exemplarily, based on the three-dimensional model, it is possible to determine which layout areas are possible layout areas for installing driver monitoring cameras, and determine the locations of these layout areas and target factor information related to the camera layout. For example, through the three-dimensional model, the layout information and cabin structure of the cabin can be intuitively understood, and then multiple possible layout areas (for example, A-pillars, around the steering wheel guard, interior rearview mirror area, etc.) can be determined. Then, for each layout area, its location information (for example, three-dimensional coordinates used to represent the layout area) and target factor information (such as pitch angle, yaw angle, roll angle, face pixel ratio, etc.) are collected.

[0098] Exemplarily, the selection operation may be that the user operates on the interactive interface and then selects the position of the preset layout area from the positions of multiple layout areas.

[0099] It should be understood that after obtaining the positions and target factor information of multiple layout areas, the most suitable area can be selected as the preset layout area according to actual needs and design requirements.

[0100] For example, when multiple layout areas include the A-pillar, the area around the steering wheel cover, and the interior rearview mirror area, factors such as the camera's field of view requirements (for example, clearly capturing the driver's facial features), installation convenience (relatively easy to install and fix the camera), and the impact on the driver's line of sight (the camera installation position will not block the driver's line of sight) can be taken into consideration, and in response to a selection operation, the A-pillar is determined as the preset layout area, and the position of the A-pillar is determined.

[0101] In an embodiment of the present application, the layout information in the cabin can be obtained through the three-dimensional model corresponding to the cabin, and then the location of the layout area in the cabin and the target parameter information corresponding to the layout position in each layout area can be obtained, thereby providing reliable data support for the subsequent determination of the target layout position, further improving the rationality of the layout position of the camera in the cabin, and thereby improving the monitoring effect of the camera.

[0102] In the case where the preset layout area is large, if the target layout position of the camera is determined directly from the preset layout area, there may be a lot of unnecessary data processing, thereby reducing the accuracy of the camera layout; therefore, the present application provides an embodiment to improve the accuracy of the camera layout, and the specific reference is as follows:

[0103] In a possible embodiment of the present application, the above S202 includes: determining a target constraint condition corresponding to the target parameter based on the target parameter; and determining an area in the preset layout area that meets the target constraint condition as the target layout area.

[0104] Exemplarily, the target constraint condition may be a specific restriction set based on the target parameter to screen the layout area that meets the target constraint condition.

[0105] For example, taking the target parameters of pitch angle and face pixel ratio as an example, the pitch angle needs to be within the range set by the target constraint conditions, the face pixel ratio needs to reach a certain standard, and the driver's face in the installation position needs to occupy a certain proportion of the entire captured image.

[0106] Exemplarily, it may be possible to check whether each area in the preset layout area satisfies the target constraint condition, and determine the area satisfying the target constraint condition as the target layout area.

[0107] Exemplarily, an area that satisfies a target constraint condition may refer to an area in which all target parameters satisfy the target constraint condition. For example, the target parameters include target parameter 1, target parameter 2, target parameter 3, and target parameter 4. Target parameter 1 corresponds to target constraint condition 1, target parameter 2 corresponds to target constraint condition 2, target parameter 3 corresponds to target constraint condition 3, and target parameter 4 corresponds to target constraint condition 4. When target parameter 1 corresponding to the area satisfies target constraint condition 1, target parameter 2 corresponding to the area satisfies target constraint condition 2, target parameter 3 corresponding to the area satisfies target constraint condition 3, and target parameter 4 corresponding to the area satisfies target constraint condition 4, the area can be described as a target layout area.

[0108] Optionally, the region satisfying the target constraint condition may refer to a preset number of target parameters in the region satisfying the target constraint condition. For example, continuing to take the above target parameters including target parameter 1, target parameter 2, target parameter 3 and target parameter 4 as an example: the preset number is 3. In the case where there are three target parameters (e.g., target parameter 2, target parameter 3 and target parameter 4) among target parameter 1, target parameter 2, target parameter 3 and target parameter 4 that satisfy the corresponding target constraint condition, it can be described that the region is a target layout region.

[0109] In an embodiment of the present application, through the target parameters and the target constraints corresponding to the target parameters, the target layout area that meets the target constraints can be accurately screened out from the preset layout area, and then the target layout position can be subsequently determined from the target layout area. This can further improve the rationality of the layout position of the camera in the cabin, thereby improving the monitoring effect of the camera.

[0110] When obtaining the target layout area from the preset layout area, the target layout area can be quickly and accurately screened out from the preset layout area by setting the target constraint condition. For details, please refer to the following embodiments:

[0111] In a possible embodiment of the present application, an area in a preset layout area that meets the target constraint conditions is determined as a target layout area, including: obtaining multiple layout positions in the preset layout area, and parameter values ​​of target parameters of each layout position; and determining a layout area corresponding to a first layout position whose parameter value is in a target interval as the target layout area.

[0112] Among them, the target constraint condition includes the target interval corresponding to the target parameter.

[0113] Exemplarily, the target constraint condition can be determined by a target interval corresponding to a target parameter to determine whether each layout position satisfies the target constraint condition.

[0114] For example, taking the pitch angle as the target parameter: the pitch angle between the camera and the driver's face is within a certain range [-20°, 20°] to ensure that the camera can accurately capture the driver's facial features. In other words, the target interval corresponding to the pitch angle is [-20°, 20°].

[0115] For another example, taking the target parameter as lens distance: the distance between the camera lens and the driver's face is within a certain range [30cm, 120cm] to ensure that the driver can clearly capture the driver's facial features. In other words, the target interval corresponding to the lens distance is [30cm, 120cm].

[0116] For another example, take the target parameter as the face pixel ratio: the face pixel ratio captured by the camera is not less than a certain threshold (such as 70%) to ensure the reliability of the image recognition algorithm. In other words, the target interval corresponding to the face pixel ratio is [0.7, 1].

[0117] Exemplarily, multiple layout positions in a preset layout area can be used to indicate the location where the camera is installed and to obtain parameter values ​​of target parameters of each layout area.

[0118] For example, the multiple layout positions in the preset layout area include layout position A, layout position B, layout position C, layout position D, and layout position E. Taking the target parameters including pitch angle, face pixel ratio and lens distance as an example: the parameter value 1 of the pitch angle of layout position A is 10°, the parameter value 1 of the lens distance is 50 cm, and the parameter value 1 of the face pixel ratio is 0.75; the parameter value 2 of the pitch angle of layout position B is 30°, the parameter value 2 of the lens distance is 55 cm, and the parameter value 2 of the face pixel ratio is 0.80; the parameter value 3 of the pitch angle of layout position C is 18°, the parameter value 3 of the lens distance is 80 cm, and the parameter value 3 of the face pixel ratio is 0.90; the parameter value 4 of the pitch angle of layout position D is -30°, the parameter value 4 of the lens distance is 50 cm, and the parameter value 4 of the face pixel ratio is 0.5; the parameter value 5 of the pitch angle of layout position E is 15°, the parameter value 5 of the lens distance is 90 cm, and the parameter value 5 of the face pixel ratio is 0.8. Since parameter value 1 of the pitch angle, parameter value 1 of the lens distance and parameter value 1 of the face pixel ratio of layout position A are within the target interval corresponding to the target parameters, parameter value 3 of the pitch angle, parameter value 3 of the lens distance and parameter value 3 of the face pixel ratio of layout position C are within the target interval corresponding to the target parameters, and parameter value 5 of the pitch angle, parameter value 5 of the lens distance and parameter value 5 of the face pixel ratio of layout position E are within the target interval corresponding to the target parameters; therefore, layout position A, layout position B, layout position C, layout position D and layout position E can be determined as the first layout position; the layout area corresponding to layout position A, layout position C and layout position E is the target layout area.

[0119] In an embodiment of the present application, the first layout position corresponding to the parameter value in the target interval can be determined through the target interval included in the target constraint condition, and then the target layout area can be quickly and accurately determined from the preset layout area, further improving the rationality of the layout position of the camera in the cabin, thereby improving the monitoring effect of the camera.

[0120] It is understandable that in order to reasonably obtain the target layout position of the camera from the target layout area, it can be determined according to the target parameters and target weight values ​​of each second layout position in the target layout area. The specific implementation method can refer to the following embodiments:

[0121] In a possible embodiment of the present application, the above S203 includes: obtaining parameter values ​​of target parameters of multiple second layout positions in the target layout area; determining the target value of each second layout position based on the target weight value and the parameter value of the target parameter of the second layout position; and determining the second layout position corresponding to the target value that meets the preset conditions among the multiple target values ​​as the target layout position.

[0122] Exemplarily, multiple specific second layout positions and parameter values ​​of the target parameters of each second layout position can be further determined in the target layout area. The second layout position can be the first layout position described above. Since each target parameter is assigned a target weight value, this can reflect the importance of each target parameter in evaluating the target layout position.

[0123] Continuing with the above example: Layout positions A, C and E are the second layout positions, and the target parameters include pitch angle, face pixel ratio and lens distance. Among them, the target weight value of the pitch angle is 0.3, the target weight value of the face pixel ratio is 0.5, and the target weight value of the lens distance is 0.2.

[0124] Exemplarily, the method of determining the target value of each second layout position based on the target weight value and the parameter value of the target parameter of the second layout position may include: using a target algorithm to combine the target weight value and the parameter value of the target parameter of the second layout position to determine the target value of each second layout position. The target algorithm may be any one of the following algorithms: a weighted sum algorithm, a weighted average algorithm, a least squares estimation algorithm, a maximum likelihood estimation algorithm, and a Bayesian estimation algorithm.

[0125] For example, the formula for the weighted sum algorithm can be: Among them, G is the target value, n is the number of target parameters, A is the target weight value of the target parameter, and X is the key value of the target parameter (that is, the value converted from the parameter value).

[0126] Exemplarily, satisfying the preset condition may mean that the target value reaches a preset threshold; or the ranking in multiple second layout positions is within a preset ranking (for example, the top two), etc., and the embodiments of the present application do not impose specific limitations on this.

[0127] Exemplarily, the number of target placement positions may be one or more, and the embodiments of the present application do not impose any specific limitation on this.

[0128] Continuing with the above example: When the target algorithm is the weighted sum algorithm, since the parameter value 1 of the pitch angle of layout position A is 10° (assuming it is converted to 80 after being converted to a score), the parameter value 1 of the lens distance is 50 cm (assuming it is converted to 50), and the parameter value 1 of the face pixel ratio is 0.75 (assuming it is converted to 75), the target value A of layout position A is 80*0.3+50*0.5+75*0.2=24+25+15=64. Since the parameter value 3 of the pitch angle of layout position C is 18° (assuming it is converted to 75), the parameter value 3 of the lens distance is 80 cm (assuming it is converted to 70), and the parameter value 3 of the face pixel ratio is 0.9 (assuming it is converted to 90), the target value C of layout position C is 75*0.3+80*0.5+90*0.2=22.5+10+18=50.5. Since the parameter value 5 of the pitch angle of layout position E is 15° (assuming conversion to 70), the parameter value 5 of the lens distance is 90 cm (assuming conversion to 80), and the parameter value 5 of the face pixel ratio is 0.8 (assuming conversion to 80), the target value E of layout position E = 70*0.3+80*0.5+80*0.2=21+40+16=80. In summary, the target value A of layout position A is 64, the target value C of layout position C is 50.5, and the target value E of layout position E is 80. Assuming that satisfying the preset condition means that the target value is the largest, the target layout position is layout position E. Assuming that satisfying the preset condition makes the target value reach the preset threshold of 60 points, the target layout positions include layout position A and layout position E.

[0129] In an embodiment of the present application, the target value of each second layout position is obtained by the parameter value of the target parameter of the second layout position and the target weight value of the target parameter, so that a reasonable comprehensive evaluation can be performed on each second layout position; then, the second layout position corresponding to the target value that meets the preset conditions is determined as the target layout position to determine the appropriate layout position of the camera, thereby improving the rationality of the layout position of the camera in the cabin and the monitoring effect of the camera.

[0130] However, in actual scenarios, if the target value of each second layout position in the target layout area is calculated in turn, a lot of computing time may be required; therefore, in a possible embodiment of the present application, the above S203 includes: inputting the parameter value of the target parameter of the second layout position into the target model to obtain the target value of the second layout position; wherein the target model includes a target weight value.

[0131] Exemplarily, the target model may be used to determine an intelligent model of a target value of the second layout position.

[0132] Exemplarily, the target model may adjust the target weight value of each target parameter in real time according to historical sample data to improve the rationality of determining the target value of the second layout position.

[0133] Exemplarily, the target model can utilize an unsupervised machine learning algorithm. It should be noted that unsupervised learning is a learning method that does not require labeled data and can automatically discover hidden patterns or structures from input data.

[0134] For example, Figure 5 A schematic diagram of a target model provided by an embodiment of the present application is shown, in which parameter values ​​of target parameters of a second layout position are input into the target model, such as the parameter value of target parameter 1, the parameter value of target parameter 2, and the parameter value of target parameter 3; the target model outputs the target value of the second layout position.

[0135] For example: the target model includes parameters such as pitch angle, yaw angle, roll angle, face pixel ratio, optical axis center position, lens distance, and field of view occlusion surface gap. If the pitch angle of layout position X is 30°, yaw angle is 10°, roll angle is 5°, face pixel ratio is 80%, optical axis center position is (x1, y1, z1), face and camera distance is d1, and field of view occlusion surface gap is g1. Layout position Y: pitch angle is 25°, yaw angle is 15°, roll angle is 4°, face pixel ratio is 85%, optical axis center position is (x2, y2, z2), face and camera distance is d2, and field of view occlusion surface gap is g2. Assume that the target model is an algorithm based on weighted summation, where the weight values ​​are: pitch angle = 0.2, yaw angle = 0.15, roll angle = 0.1, face pixel ratio = 0.25, optical axis center position = 0.1, face-to-camera distance = 0.1, and field of view occlusion surface gap = 0.1. Input the parameter value of the target parameter at layout position X into the target model to obtain the target value X; input the parameter value of the target parameter at layout position Y into the target model to obtain the target value Y.

[0136] In an embodiment of the present application, by inputting the parameter values ​​of the target parameters of the second layout position into the target model, the target value of each second layout position can be quickly acquired to reduce the calculation time, thereby improving the convenience of subsequent determination of the target layout position, and further improving the rationality of the layout position of the camera in the cabin.

[0137] It is understandable that since the weight values ​​of the target parameters are set based on experience and preliminary analysis, they may not fully reflect the importance of different parameters in actual situations; therefore, before determining the target layout position of the camera in the target layout area, it is necessary to adjust the initial weight value of each target parameter to obtain the target weight value, thereby improving the rationality of the layout position of the camera in the cabin. For details, please refer to the following embodiments:

[0138] In a possible embodiment of the present application, the method provided in the embodiment of the present application also includes: obtaining historical test data and initial weight values ​​of target parameters; adjusting the initial weight values ​​based on the historical target values ​​of the first layout position to obtain the target weight values.

[0139] The historical test data includes the historical target value of the third layout position.

[0140] Illustratively, the third layout position may be the first layout position, or may be any layout position in other layout areas.

[0141] It is understandable that historical test data can be used to adjust the initial weight values ​​of the target parameters, and then obtain the target weight values, which can improve the reliability of the target values ​​obtained later.

[0142] It should be understood that since the initial weight values ​​are set based on experience and preliminary analysis, they may not fully reflect the importance of different parameters in actual situations; by adjusting the initial weight values ​​through historical target values, the importance of each target parameter in determining the target layout location can be adjusted.

[0143] Exemplarily, historical test data refers to data recorded in camera layout tests conducted in the past, which includes information on the monitoring effect, installation convenience, cost, etc. of cameras at different layout positions. For example, the historical target value of the third layout position included in the historical test data can be calculated by inputting the parameter value of the target parameter of the third layout position into a certain evaluation model (which may be a preliminary target model or an empirical model). The historical target value reflects the comprehensive performance of the third layout position in past tests.

[0144] For example: Take the pitch angle and face pixel ratio as examples: the initial weight value of the pitch angle is 0.3, and the initial weight value of the face pixel ratio is 0.25; the target value 1 of the third arrangement position is determined by the initial weight values ​​of these target parameters; then, the target value 1 is compared with the historical target value, and the initial weight value of the pitch angle and the initial weight value of the face pixel ratio are adjusted. Finally, when the weight value of the pitch angle is 0.4 and the weight value of the face pixel ratio is 0.1, the target value 2 obtained is equal to the historical target value. Then, the weight value of the pitch angle of 0.4 is used as the target weight value of the pitch angle; the weight value of the face pixel ratio of 0.1 is used as the target weight value of the face pixel ratio.

[0145] Of course, if among the multiple target parameters there are one or more target parameters whose initial weight values ​​have not been adjusted, then the initial weight values ​​of these target parameters may be used as target weight values.

[0146] In an embodiment of the present application, the initial weight value of the target parameter is adjusted through historical test data to obtain the target weight value; since the target weight value can reflect the current importance of the target parameter in determining the target layout position, this can subsequently improve the reliability of the determined target layout position, thereby improving the rationality of the layout position of the camera in the cabin and the monitoring effect of the camera.

[0147] Figure 6 It is a schematic flowchart of another method for determining the camera position provided in an embodiment of the present application.

[0148] For example, Figure 6 The method for determining the camera position shown may be executed by the vehicle, or may be executed by a camera position determination device in the vehicle, such as a chip.

[0149] like Figure 6 As shown, the method for determining the camera position includes S601 to S610, and S601 to S610 are described in detail below.

[0150] S601. Construct a three-dimensional model corresponding to the vehicle cabin.

[0151] For example, the three-dimensional model can be used to describe the three-dimensional model of the layout in the cabin. The three-dimensional model can include key components such as the simulated driver, the main driving seat, the steering wheel, the A-pillar, the instrument panel, the steering wheel, the center console, the camera, and the camera field of view. In this way, the layout information in the cabin can be accurately obtained.

[0152] S602. Based on the three-dimensional model, obtain the three-dimensional coordinates and multiple key parameters of multiple layout areas in the cabin, as well as the weight value of each key parameter.

[0153] For descriptions related to three-dimensional coordinates, please refer to the above layout positions; for descriptions of key parameters, please refer to the above target parameters; no further details will be given here.

[0154] S603. In response to a selection operation by the user, a preset layout area is determined from a plurality of layout areas.

[0155] Exemplarily, the selection operation may be that the user operates on the interactive interface and then selects the position of the preset layout area from the positions of multiple layout areas.

[0156] It should be understood that after obtaining the positions and target factor information of multiple layout areas, the most suitable area can be selected as the preset layout area according to actual needs and design requirements.

[0157] S604. Based on the key parameters, determine target constraints of the key parameters.

[0158] Exemplarily, the target constraint condition may be a specific restriction set based on the target parameter to screen the layout area that meets the target constraint condition.

[0159] Exemplarily, the target constraint condition includes a target interval corresponding to the target parameter. The target constraint condition can determine whether each layout position satisfies the target constraint condition by the target interval corresponding to the target parameter.

[0160] S605. Obtain multiple target three-dimensional coordinates in the preset layout area that meet target constraint conditions of key parameters.

[0161] S606. Determine the parameter value of the key parameter corresponding to each target three-dimensional coordinate.

[0162] S607. Determine whether there is a target model. If yes, execute S608; if no, execute S609.

[0163] Exemplarily, the target model may be used to determine an intelligent model of a target value of the second layout position.

[0164] Exemplarily, the target model may adjust the target weight value of each target parameter in real time according to historical sample data to improve the reliability of determining the target value of the second layout position.

[0165] Exemplarily, the target model can utilize an unsupervised machine learning algorithm. It should be noted that unsupervised learning is a learning method that does not require labeled data and can automatically discover hidden patterns or structures from input data.

[0166] S608. Input multiple target three-dimensional coordinates into the target model to obtain multiple target values.

[0167] S609. Based on a weighted summation algorithm, multiple target values ​​are obtained by combining the parameter values ​​of the key parameters corresponding to the target three-dimensional coordinates and the weight values ​​of the key parameters.

[0168] For example, the formula for the weighted sum algorithm can be: Among them, G is the target value, n is the number of target parameters, A is the target weight value of the target parameter, and X is the key value of the target parameter (that is, the value converted from the parameter value).

[0169] S610. Determine the three-dimensional coordinates corresponding to the target values ​​satisfying the preset conditions among the multiple target values ​​as the target layout coordinates.

[0170] Exemplarily, satisfying the preset condition may mean that the target value reaches a preset threshold; or the ranking in multiple second layout positions is within a preset ranking (for example, the top two), etc., and the embodiments of the present application do not impose specific limitations on this.

[0171] For detailed description of S601 to S610, please refer to Figures 2 to 5 The relevant descriptions will not be repeated here.

[0172] The present application provides a method for determining the position of a camera, which obtains the three-dimensional coordinates of multiple layout areas and multiple key parameters affecting the layout effect, as well as the weight value of each key parameter based on a three-dimensional model; through the three-dimensional model corresponding to the cabin, the layout information in the cabin can be obtained, and then the three-dimensional coordinates of the layout area in the cabin and the key parameters corresponding to the layout position in each layout area and the weight values ​​of the key parameters can be obtained, so as to provide accurate data support for the subsequent determination of the target layout position, and further improve the rationality of the layout position of the camera in the cabin; finally obtain the target value by means of a target model or a weighted summation algorithm; and determine the three-dimensional coordinates corresponding to the target value that meets the preset conditions among the multiple target values ​​as the target layout coordinates, so that the appropriate layout position can be effectively determined, and the reliability of the layout position of the camera in the cabin can be further improved; therefore, the above scheme can improve the rationality of the layout position of the camera in the cabin, and then improve the monitoring effect of the camera.

[0173] It should be understood that the above examples are intended to help those skilled in the art understand the embodiments of the present application, rather than to limit the embodiments of the present application to the specific numerical values ​​or specific scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the above examples, and such modifications or changes also fall within the scope of the embodiments of the present application.

[0174] Combination of the above Figures 2 to 6 The method for determining the camera position provided in the embodiment of the present application is described in detail; Figure 7 and Figure 8 The device embodiments of the present application are described in detail. It should be understood that the device in the embodiments of the present application can execute the various methods of the aforementioned embodiments of the present application, that is, the specific working processes of the following various products can refer to the corresponding processes in the aforementioned method embodiments.

[0175] Combine the following Figure 7 The device for determining the camera position provided in an embodiment of the present application is described in detail.

[0176] like Figure 7 As shown, Figure 7 It is a structural schematic diagram of a camera position determination device provided in an embodiment of the present application.

[0177] For example, Figure 7 As shown, the device comprises:

[0178] The acquisition module 710 is used to acquire the position of the preset layout area of ​​the camera in the vehicle cabin and the target factor information; wherein the target factor information includes a target parameter and a target weight value corresponding to the target parameter; the target parameter is a parameter that affects the camera to collect the driver's facial image;

[0179] A determination module 720, configured to determine a target layout area in a preset layout area based on a target parameter;

[0180] The determination module 720 is further configured to determine a target layout position of the camera in the target layout area based on the target parameter and the target weight value.

[0181] In a possible implementation, the determination module 720 is specifically configured to determine, based on the target parameter, a target constraint condition corresponding to the target parameter; and determine an area in the preset layout area that meets the target constraint condition as the target layout area.

[0182] In a possible implementation, the determination module 720 is specifically configured to obtain multiple layout positions in a preset layout area and parameter values ​​of target parameters of each layout position; and determine the layout area corresponding to the first layout position whose parameter value is in the target interval as the target layout area.

[0183] In one possible implementation, the determination module 720 is specifically used to obtain parameter values ​​of target parameters of multiple second layout positions in the target layout area; determine the target value of each second layout position based on the target weight value and the parameter value of the target parameter of the second layout position; and determine the second layout position corresponding to the target value that meets the preset conditions among the multiple target values ​​as the target layout position.

[0184] In a possible implementation, the device further includes an input module, specifically configured to input a parameter value of a target parameter of the second layout position into a target model to obtain a target value of the second layout position; wherein the target model includes a target weight value.

[0185] In one possible implementation, the acquisition module 710 is also used to obtain historical test data and initial weight values ​​of target parameters; wherein the historical test data includes historical target values ​​of the third layout position; and the initial weight values ​​are adjusted based on the historical target values ​​of the third layout position to obtain the target weight values.

[0186] In one possible implementation, the acquisition module 710 is specifically used to obtain a three-dimensional model corresponding to the cabin; wherein the three-dimensional model is used to represent the layout information in the cabin; based on the three-dimensional model, the positions and target factor information of multiple layout areas are obtained; in response to a selection operation, the position of a preset layout area is determined from the positions of the multiple layout areas.

[0187] It should be noted that the camera position determination device provided in the above embodiment only uses the division of the above-mentioned functional modules as an example when executing the camera position determination method. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0188] In addition, the camera position determination device and camera position determination method embodiments provided in the above embodiments belong to the same concept. Therefore, for details not disclosed in the device embodiments of this specification, please refer to the camera position determination method embodiments described above in this specification, and no further details will be given here.

[0189] Figure 8 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application.

[0190] For example, Figure 8 As shown, the vehicle 800 includes: a memory 801 and a processor 802, wherein the memory 801 stores an executable program code 803, and the processor 802 is used to call and execute the executable program code 803 to perform a method for determining a camera position.

[0191] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a method for determining a camera position provided in an embodiment of the present application.

[0192] In this embodiment, the functional modules of the device can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0193] In the case of dividing each functional module according to each function, the device may also include an acquisition module, a detection module, a processing module, a control module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.

[0194] It should be understood that the device provided in this embodiment is used to execute the above-mentioned method for determining the position of a camera, and thus can achieve the same effect as the above-mentioned implementation method.

[0195] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a vehicle, the processing module may be used to control and manage the actions of the vehicle. The storage module may be used to support the vehicle in executing related program codes, etc.

[0196] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits shown in conjunction with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0197] In addition, the device provided in the embodiments of the present application may specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a method for determining the camera position provided in the above embodiments.

[0198] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a method for determining a camera position provided in the above embodiment.

[0199] This embodiment also provides a computer program product. When the computer program product runs on a computer, it enables the computer to execute the above-mentioned related steps to implement a method for determining a camera position provided in the above embodiment.

[0200] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0201] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0202] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0203] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining a camera position, characterized in that: The method comprises: Acquire the position and target factor information of the preset layout area of ​​the camera in the cabin; wherein the target factor information includes a target parameter and a target weight value corresponding to the target parameter; the target parameter is a parameter that affects the camera to collect the driver's facial image; Based on the target parameter, determining a target layout area in the preset layout area; Based on the target parameter and the target weight value, a target layout position of the camera in the target layout area is determined.

2. The method according to claim 1, characterized in that The determining, based on the target parameter, a target layout area in the preset layout area comprises: Based on the target parameter, determining a target constraint condition corresponding to the target parameter; An area in the preset layout area that meets the target constraint condition is determined as the target layout area.

3. The method according to claim 2, characterized in that The target constraint condition includes a target interval corresponding to the target parameter; The step of determining the area in the preset layout area that satisfies the target constraint condition as the target layout area comprises: Acquire a plurality of layout positions in the preset layout area, and a parameter value of the target parameter of each of the layout positions; A layout area corresponding to a first layout position where the parameter value is located in the target interval is determined as the target layout area.

4. The method according to any one of claims 1 to 3, characterized in that The determining the target layout position of the camera in the target layout area based on the target parameter and the target weight value includes: Acquire parameter values ​​of the target parameters of a plurality of second layout positions in the target layout area; determining a target value for each of the second layout positions based on the target weight value and a parameter value of the target parameter of the second layout position; A second layout position corresponding to a target value that meets a preset condition among the multiple target values ​​is determined as the target layout position.

5. The method according to claim 4, characterized in that The determining the target value of each second layout position based on the target weight value and the parameter value of the target parameter of the second layout position comprises: Inputting the parameter value of the target parameter of the second layout position into a target model to obtain the target value of the second layout position; wherein the target model includes the target weight value.

6. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Acquire historical test data and initial weight values ​​of the target parameters; wherein the historical test data includes historical target values ​​of the third layout position; The initial weight value is adjusted based on the historical target value of the third layout position to obtain the target weight value.

7. The method according to any one of claims 1 to 3, characterized in that The obtaining of the position and target factor information of the preset layout area in the vehicle cabin includes: Acquire a three-dimensional model corresponding to the vehicle cabin; wherein the three-dimensional model is used to represent layout information in the vehicle cabin; Based on the three-dimensional model, obtaining positions of multiple layout areas and the target factor information; In response to a selection operation, a position of the preset layout area is determined from positions of a plurality of the layout areas.

8. The method according to any one of claims 1 to 3, characterized in that The target parameter includes at least one of the following parameters: a first target parameter, a second target parameter, and a third target parameter; Among them, the first target parameter is used to indicate the viewing angle of the camera when capturing the driver's face; the second target parameter is used to indicate the relative position of the camera when capturing the driver's face; and the third target parameter is used to indicate the image proportion of the driver's face in the image captured by the camera.

9. A device for determining a camera position, characterized in that: The device comprises: An acquisition module, used to acquire the position of a preset layout area of ​​a camera in the vehicle cabin and target factor information; wherein the target factor information includes a target parameter and a target weight value corresponding to the target parameter; the target parameter is a parameter that affects the camera to collect a facial image of the driver; A determination module, configured to determine a target layout area in the preset layout area based on the target parameter; The determination module is further configured to determine a target layout position of the camera in the target layout area based on the target parameter and the target weight value.

10. A vehicle, characterized in that: The vehicle comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 8.

Images