Optical system data processing method and device, computer equipment and storage medium

Abstract

The invention relates to an optical system data processing method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring an optical system distortion curve function of a target camera in the intelligent driving visual perception system; determining a center view field distortion pixel density and an edge view field distortion pixel density of the target camera according to an optical system distortion curve function; and determining an optical system optimization judgment function according to the center view field distortion pixel density and the edge view field distortion pixel density, and determining whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function. According to the method, whether the optical system distortion curve function of the target camera is optimized or not is determined based on the center field-of-view distortion pixel density and the edge field-of-view distortion pixel density of the target camera, so that the guidance accuracy and guidance efficiency for optimizing the optical system distortion curve function can be improved; therefore, the visual perception collection efficiency and the visual perception view coverage rate are improved.

Description

Technical Field

[0001] The present application relates to the technical field of optical system data processing, and in particular to an optical system data processing method, device, computer equipment and storage medium. Background Art

[0002] With the deepening of the development of intelligent driving, the system form and system complexity of the visual perception system are constantly upgrading in the process of application upgrades of assisted driving, advanced assisted driving, semi-automatic driving and fully automatic driving. As the most mainstream visual perception system solution at present, the optical system of the on-board camera has gradually upgraded from the initial monocular solution to binocular, tri-ocular, penta-ocular, hexa-ocular, and even deca-ocular solutions. Different from the monocular solution, the multi-ocular solution has doubled the information correlation and coupling degree due to the increase in the coverage area of ​​the field of view. The existing multi-channel intelligent driving perception system has the problem of insufficient maximum detectable object distance in the required field of view, as well as low visual perception acquisition efficiency and visual perception field of view coverage. How to make on-board cameras with different installation positions and different usage scenarios interconnected and complementary is an important issue in the high-level development of intelligent driving. Summary of the invention

[0003] Based on this, it is necessary to provide an optical system data processing method, device, computer equipment and storage medium that can interconnect and complement vehicle-mounted cameras in different installation positions and different usage scenarios, and improve the monitoring range of vehicle-mounted cameras in response to the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a method for processing optical system data, the method comprising:

[0005] Obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system;

[0006] Determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function;

[0007] An optical system optimization judgment function is determined according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function.

[0008] In one of the embodiments, determining an optical system optimization judgment function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determining whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function includes:

[0009] Taking the ratio of the central field of view distortion pixel density to the edge field of view distortion pixel density as the target density ratio;

[0010] The target density ratio is used as an optical system optimization judgment function, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function.

[0011] In one embodiment, determining whether the optical system distortion curve function needs to be optimized according to the optical system optimization determination function includes:

[0012] Determining a density ratio condition of the target camera according to a camera identifier of the target camera;

[0013] Determining whether the optical system optimization determination function satisfies the density ratio condition;

[0014] If so, it is determined that the optical system distortion curve function needs to be optimized, and an optical system optimization prompt message is issued.

[0015] In one embodiment, determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function includes:

[0016] Determine the pixel size of the image sensor and the horizontal field of view angle of the optical system of the target camera;

[0017] Determining the central field of view distortion pixel density of the target camera according to the optical system distortion curve function and the image sensor pixel size;

[0018] The edge field of view distortion pixel density of the target camera is determined according to the optical system distortion curve function, the image sensor pixel size and the horizontal field of view angle of the optical system.

[0019] In one embodiment, determining the edge field distortion pixel density of the target camera according to the optical system distortion curve function, the image sensor pixel size and the horizontal field angle of the optical system includes:

[0020] Determining a target angle range according to the horizontal field angle of the optical system;

[0021] The edge field of view distortion pixel density of the target camera is determined according to the target angle range and the ratio between the pixel size of the image sensor and the horizontal field of view angle of the optical system.

[0022] In one embodiment, determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function includes:

[0023] Determining an optical system pixel density curve of the target camera according to the optical system distortion curve function;

[0024] The central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined according to the optical system pixel density curve.

[0025] In one embodiment, determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system pixel density curve includes:

[0026] Determine the corresponding relationship between the optical system half field angle and the camera pixel density of the target camera according to the optical system pixel density curve;

[0027] According to the corresponding relationship between the half field of view angle of the optical system and the pixel density of the camera, the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined.

[0028] In a second aspect, the present application further provides an optical system data processing device, the device comprising:

[0029] A distortion curve function determination module is used to obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system;

[0030] A pixel density determination module, used to determine the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function;

[0031] The system optimization judgment module is used to determine the optical system optimization judgment function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determine whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function.

[0032] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0033] Obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system;

[0034] Determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function;

[0035] An optical system optimization judgment function is determined according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0037] Obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system;

[0038] Determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function;

[0039] An optical system optimization judgment function is determined according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function.

[0040] The optical system data processing method, device, computer equipment and storage medium obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system; determine the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function; determine the optical system optimization judgment function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determine whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function. The problem of insufficient maximum detectable object distance of the required field of view, and low visual perception acquisition efficiency and visual perception field of view coverage in the multi-channel vision intelligent driving perception system is solved. The above method determines whether to optimize the optical system distortion curve function of the target camera based on the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera, which can improve the guidance accuracy and guidance efficiency of optimizing the optical system distortion curve function, thereby improving the visual perception acquisition efficiency and visual perception field of view coverage. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is an application environment diagram of an optical system data processing method in one embodiment;

[0042] Figure 2 is a schematic flow chart of an optical system data processing method in one embodiment;

[0043] Figure 3 is an example diagram of three front-view visual perception systems in one embodiment;

[0044] Figure 4 is a flow chart of an optical system data processing method in another embodiment;

[0045] Figure 5 is a flow chart of an optical system data processing method in another embodiment;

[0046] Figure 6 is a flow chart of an optical system data processing method in another embodiment;

[0047] Figure 7 is an example diagram of a pixel density curve of a forward-looking camera optical system in one embodiment;

[0048] Figure 8 is an example diagram of a pixel density curve of a rear-view camera optical system in one embodiment;

[0049] Fig. 9 is an example diagram of a pixel density curve of a front and rear surround view camera optical system in one embodiment;

[0050] Fig.10 is an example diagram of a pixel density curve of a left and right surround view camera optical system in one embodiment;

[0051] Fig.11 is a flow chart of an optical system data processing method in another embodiment;

[0052] Fig.12 is a structural block diagram of an optical system data processing device in one embodiment;

[0053] Fig.13 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] The optical system data processing method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Figure 1A side view of a vehicle 10 is shown, the vehicle 10 being disposed on a travel surface 70 (e.g., a paved road surface) and capable of traversing the travel surface 70. The vehicle 10 may include a vehicle navigation system 24, a computer-readable storage device or medium (memory) 23 storing a digitized road map 25, a spatial monitoring system 100, a vehicle controller 50, a global positioning system (GPS) sensor 52, and a human / machine interface (HMI) device 60. In another embodiment, the vehicle 10 further includes an autonomous controller 65 and a telematics controller 75. Specifically, the vehicle 10 includes, but is not limited to, commercial vehicles, industrial vehicles, agricultural vehicles, passenger vehicles, airplanes, ships, trains, all-terrain vehicles, personal mobile devices, robots, and similar forms of mobile platforms for achieving the purposes of the present application.

[0056] The terminal vehicle can communicate with the server through the network. The data storage system can store data that the server needs to process. The data storage system can be integrated on the server, or it can be placed on the cloud or other network servers. The terminal vehicle can obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system; determine the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function; determine whether the optical system distortion curve function needs to be optimized according to the central field of view distortion pixel density and the edge field of view distortion pixel density. In other embodiments, after determining the target scene image, the terminal vehicle can also send the above target scene image to the server, and the server executes the above acquisition of the optical system distortion curve function of the target camera in the intelligent driving visual perception system; determine the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function; determine whether the optical system distortion curve function needs to be optimized according to the central field of view distortion pixel density and the edge field of view distortion pixel density. Send information on whether the optical system distortion curve function needs to be optimized to the terminal vehicle. The server may be implemented as an independent server or a server cluster consisting of multiple servers.

[0057] In one embodiment, Figure 2 As shown, a method for processing optical system data is provided. This embodiment uses the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server.

[0058] It should be noted that the visual perception systems currently used in the field of intelligent driving have certain shortcomings. Taking private cars as an example, the traditional mainstream typical 6V integrated driving and parking visual perception system in the current intelligent driving industry, the pixel scheme, horizontal field of view angle, the farthest detectable object distance in the center field of view and the farthest detectable object distance in the edge field of view of the six-way vehicle-mounted camera optical system are summarized in Table 1.

[0059] Table 1

[0060]

[0061] The main shortcomings of the current traditional mainstream typical 6V integrated driving and parking visual perception system in the intelligent driving industry are: the maximum detectable object distance of the front camera's central field of view is insufficient, the maximum detectable object distance of the rear camera's central field of view is insufficient, the maximum detectable object distance of the front and rear surround cameras' edge fields of view is insufficient, and the maximum detectable object distance of the left and right surround cameras' central fields of view is insufficient.

[0062] For example, Figure 3 It is a typical three-way forward vision perception system in the current intelligent driving industry, mainly composed of three vehicle-mounted cameras, including a telephoto forward-looking camera, a standard forward-looking camera, and a wide-angle forward-looking camera. The standard forward-looking camera is the main forward-looking camera.

[0063] The telephoto front-view camera is installed in the center position behind the front windshield, and is responsible for monitoring vehicles, pedestrians, obstacles and other objects in the distance in front of the vehicle; the standard front-view camera is installed behind the front windshield horizontally and close to the telephoto front-view camera, and is responsible for monitoring vehicles, pedestrians, obstacles and other objects in the middle and distant distance in front of the vehicle; the wide-angle front-view camera is installed behind the front windshield horizontally and close to the telephoto front-view camera at a horizontally symmetrical position relative to the standard front-view camera, and is responsible for monitoring vehicles, pedestrians, obstacles and other objects on both sides of the front of the vehicle.

[0064] Taking private cars as an example, the current traditional mainstream typical three-way forward-looking visual perception system in the intelligent driving industry, the pixel scheme, horizontal field of view angle, the farthest detectable object distance in the center field of view and the farthest detectable object distance in the edge field of view of the three-way vehicle-mounted camera optical system are summarized in Table 2.

[0065]

[0066] The main shortcomings of the current mainstream three-way forward vision perception system in the intelligent driving industry are: the maximum detectable distance of the center field of view of the telephoto forward-looking camera is insufficient, and the maximum detectable distance of the edge field of view of the wide-angle forward-looking camera is insufficient. Therefore, the visual perception system currently used in the field of intelligent driving cannot meet the needs of intelligent driving.

[0067] In this embodiment, the optical system data processing method includes the following steps:

[0068] S210: Obtain an optical system distortion curve function of a target camera in an intelligent driving visual perception system.

[0069] It should be noted that the intelligent driving visual perception system is a vehicle-mounted camera optical system. The intelligent driving visual perception system is composed of multiple groups of vehicle-mounted cameras. The key factors that determine the acquisition capability of the intelligent driving visual perception system are the field of view angle and pixel density. The field of view angle determines the breadth of the monitorable area, and the pixel density determines the depth of the monitorable area. The larger the field of view angle, the wider the monitoring area; the denser the pixel density, the farther the monitoring area. Optical system distortion refers to the image deformation and distortion caused by the propagation of light in the lens or lens in the optical system. The target camera refers to the vehicle-mounted camera on the vehicle. The vehicle-mounted camera can be installed at different positions of the vehicle. The vehicle-mounted cameras at different positions can collect vehicle driving scene images in different areas.

[0070] The target camera includes a front view camera, a rear view camera and a side view camera. For example, the intelligent driving visual perception system can be a 6V integrated driving and parking visual perception system, or a three-dimensional front view visual perception system.

[0071] The front-view camera is installed behind the front windshield, responsible for monitoring objects far in front of the vehicle and on both sides of the front, such as vehicles, pedestrians, obstacles, etc. The rear-view camera is installed on the upper edge of the rear windshield, responsible for monitoring objects far behind the vehicle and on both sides of the rear, such as vehicles, pedestrians, obstacles, etc. The side-view cameras include the front surround camera, the rear surround camera, the left surround camera and the right surround camera. Among them, the front surround camera is installed on the front face of the vehicle, responsible for monitoring objects near the front of the vehicle and on both sides of the front, such as vehicles, pedestrians, obstacles, etc. The rear surround camera is installed on the rear face of the vehicle, responsible for monitoring objects near the rear of the vehicle and on both sides of the rear, such as vehicles, pedestrians, obstacles, etc. The left surround camera is installed on the lower edge of the left rearview mirror of the vehicle, responsible for monitoring objects on the left side of the vehicle, such as vehicles, pedestrians, obstacles, etc. The right surround camera is installed on the lower edge of the right rearview mirror of the vehicle, responsible for monitoring objects on the right side of the vehicle, such as vehicles, pedestrians, obstacles, etc.

[0072] Specifically, a camera identifier of a target camera in an intelligent driving visual perception system is obtained, and an optical system distortion curve function of the target camera is determined according to the camera identifier.

[0073] S220 , determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function.

[0074] Among them, pixel density refers to the number of pixels per unit area. The central field of view is the field of view along the optical axis. The central field of view can clearly see the details of the object. The edge field of view refers to the area outside the central field of view. The details of the edge field of view cannot be clearly seen. The central field of view distortion pixel density refers to the density of distorted pixels in the central field of view, and the edge field of view distortion pixel density refers to the density of distorted pixels in the edge field of view.

[0075] Specifically, the pixel size of the image sensor of the target camera is determined according to the camera identifier of the target camera, and the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined according to the optical system distortion curve function and the pixel size of the image sensor of the target camera.

[0076] S230, determining an optical system optimization determination function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determining whether the optical system distortion curve function needs to be optimized according to the optical system optimization determination function.

[0077] Specifically, based on the function calculation method of the preset optical system optimization judgment function, the optical system optimization judgment function is determined according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and whether the central field of view distortion pixel density and the edge field of view distortion pixel density meet the preset pixel density conditions according to the optical system optimization judgment function. If so, it is determined that the optical system distortion curve function does not need to be optimized; if not, it is determined that the optical system distortion curve function needs to be optimized. Among them, the pixel density condition can be a preset pixel density value range. For example, the method for optimizing the optical system distortion curve function can be adjusting the installation position of the target camera, adjusting the lens shape of the target camera, and / or adjusting the lens material of the target camera.

[0078] For example, the optical system optimization decision function may be determined by taking a weighted sum of the central field of view distortion pixel density and the edge field of view distortion pixel density.

[0079] In the above optical system data processing method, the optical system distortion curve function of the target camera in the intelligent driving visual perception system is obtained; the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined according to the optical system distortion curve function; the optical system optimization judgment function is determined according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function. The problem of insufficient maximum detectable object distance of the required field of view, and low visual perception acquisition efficiency and visual perception field of view coverage in the multi-channel vision intelligent driving perception system is solved. The above method determines whether to optimize the optical system distortion curve function of the target camera based on the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera, which can improve the guidance accuracy and guidance efficiency of optimizing the optical system distortion curve function, thereby improving the visual perception acquisition efficiency and visual perception field of view coverage.

[0080] In one embodiment, Figure 4 As shown, according to the central field of view distortion pixel density and the edge field of view distortion pixel density, an optical system optimization judgment function is determined, and according to the optical system optimization judgment function, whether the optical system distortion curve function needs to be optimized is determined, including:

[0081] S410: Taking the ratio of the central field of view distortion pixel density to the edge field of view distortion pixel density as the target density ratio.

[0082] Specifically, the calculation formula of the target density ratio is shown in formula (1):

[0083] R=P center (θ) / P edge (θ) (1)

[0084] Among them, P center (θ) is the center field distortion pixel density, P edge (θ) is the edge field distortion pixel density, and R is the target density ratio.

[0085] S420: Using the target density ratio as an optical system optimization determination function, and determining whether the optical system distortion curve function needs to be optimized according to the optical system optimization determination function.

[0086] Specifically, it is determined whether the optical system optimization judgment function satisfies a preset density ratio condition. If so, it is determined that the optical system distortion curve function does not need to be optimized; if not, it is determined that the optical system distortion curve function needs to be optimized. The preset density ratio condition may be that the optical system optimization judgment function is greater than the first density ratio and less than the second density ratio. The first density ratio and the second density ratio may be set according to actual needs, and the first density ratio is less than the second density ratio.

[0087] The above scheme determines whether the distortion curve function of the optical system needs to be optimized according to the ratio of the central field of view distortion pixel density to the edge field of view distortion pixel density, which can realize the quantitative evaluation of the distortion curve function of the optical system and can more accurately guide the staff to optimize the distortion curve function of the optical system.

[0088] Exemplarily, determining whether the optical system distortion curve function needs to be optimized according to the optical system optimization determination function includes:

[0089] The density ratio condition of the target camera is determined according to the camera identification of the target camera; whether the optical system optimization judgment function satisfies the density ratio condition is determined; if so, it is determined that the optical system distortion curve function needs to be optimized, and an optical system optimization prompt message is issued.

[0090] The optical system optimization prompt information may include the central field of view distortion pixel density, the edge field of view distortion pixel density, the target density ratio and the warning information. The warning information may be text information or audio information. The camera attribute of the target camera may be determined according to the camera identification of the target camera. The camera attribute of the target camera may be a front view camera, a rear view camera or a front and rear surround view camera. The density ratio conditions of cameras with different attributes are different.

[0091] For example, if the target camera is determined to be a forward-looking camera according to the camera identifier of the target camera, the density ratio condition for determining the target camera is 6 ≥ R Front ≥3, where R Front is the density ratio of the front-view camera, and R Front =P(θ) Center_Front / P(θ) Edge_Front , P(θ) Center_Front is the center field distortion pixel density of the front-view camera, P(θ) Edge_Front is the edge field distortion pixel density of the front-view camera.

[0092] If the target camera is determined to be a rear-view camera according to the camera identification of the target camera, the density ratio condition for determining the target camera is 5 ≥ R Rear ≥1.5, R Rear is the density ratio of the rear-view camera, and R Rear =P(θ) Center_Rear / P(θ) Edge_Rear , P(θ) Center_Rear is the center field distortion pixel density of the rear-view camera, and P(θ)Edge_Rear is the edge field distortion pixel density of the rear-view camera.

[0093] If the target camera is determined to be a front and rear view camera according to the camera identification of the target camera, the density ratio condition for determining the target camera is 0.3≤R F_R_AVC ≤0.8, RF_R_AVC is the density ratio of the front and rear surround cameras, and R F_R_AVC =P(θ) Center_F_R_AVC / P(θ) Edge_F_R_AVC , P(θ) Center_F_R_AVC is the central field of view distortion pixel density of the front and rear surround cameras, P(θ) Edge_F_R_AVC is the edge field distortion pixel density of the front and rear surround cameras.

[0094] If the target camera is determined to be a left-right surround camera based on the camera identification of the target camera, the density ratio condition for determining the target camera is 2 ≥ R R_L_AVC ≥1.2, R R_L_AVC is the density ratio of the left and right surround cameras, and R R_L_AVC =P(θ) Center_R_L_AVC / P(θ) Edge_R_L_AVC , P(θ) Center_R_L_AVC is the central field of view distortion pixel density of the left and right surround cameras, P(θ) Edge_R_L_AVC is the edge field distortion pixel density of the left and right surround cameras.

[0095] The above scheme determines the density ratio condition of the target camera according to the camera identifier of the target camera, and determines whether the optical system distortion curve function needs to be optimized according to the density ratio condition of the target camera and the optical system optimization judgment function. It can specifically configure the distortion pixel density of each vehicle-mounted camera optical system for multiple different vehicle-mounted camera optical systems, and compensate the pixel density of the non-critical field of view area to the critical field of view area. It realizes the optimization of the intelligent driving visual perception system based on the specific configuration of the distortion pixel density of the optical system of multiple vehicle-mounted cameras, improves the visual perception acquisition efficiency of intelligent vehicles, and improves the visual perception field coverage rate.

[0096] In one embodiment, Figure 5 As shown, the center field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined according to the optical system distortion curve function, including:

[0097] S510 , determining the pixel size of the image sensor of the target camera and the horizontal field of view angle of the optical system.

[0098] Among them, in the optical system, the angle formed by the two edges of the maximum imaging range of the lens with the lens as the vertex is called the field of view angle, and the horizontal field of view angle of the target camera is the field of view angle of the target camera in the horizontal direction. The pixel is the smallest unit of the image and the smallest particle that can be displayed independently in the image.

[0099] S520: Determine the central field of view distortion pixel density of the target camera according to the optical system distortion curve function and the image sensor pixel size.

[0100] Specifically, the calculation formula of the central field of view distortion pixel density of the target camera is shown in formula (2):

[0101]

[0102] Where D(θ) is the distortion curve function of the optical system, and P is the pixel size of the image sensor.

[0103] S530 , determining the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function, the image sensor pixel size, and the optical system horizontal field of view angle.

[0104] Exemplarily, a specific method for determining the edge field of view distortion pixel density of the target camera may be: determining the target angle range based on the horizontal field of view angle of the optical system; determining the edge field of view distortion pixel density of the target camera based on the target angle range and the ratio between the pixel size of the image sensor and the horizontal field of view angle of the optical system.

[0105] Specifically, the target angle range can be HFOV refers to the horizontal field of view of the optical system. The calculation formula for the edge field of view distortion pixel density of the target camera is shown in formula (3):

[0106]

[0107] The above scheme, when determining the central field of view distortion pixel density of the target camera, takes into account the image of the optical system distortion curve function and the image sensor pixel size on the central field of view distortion pixel density, thereby improving the accuracy of the central field of view distortion pixel density. When determining the edge field of view distortion pixel density of the target camera, the scheme takes into account the image of the optical system distortion curve function, the image sensor pixel size and the optical system horizontal field of view angle on the edge field of view distortion pixel density, thereby improving the accuracy of the edge field of view distortion pixel density.

[0108] The above scheme provides a method for quantitatively calculating the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function and the image sensor pixel size, which can improve the calculation efficiency of the central field of view distortion pixel density and the edge field of view distortion pixel density.

[0109] In one embodiment, Figure 6 As shown, the center field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined according to the optical system distortion curve function, including:

[0110] S610 . Determine an optical system pixel density curve of a target camera according to an optical system distortion curve function.

[0111] Specifically, an optical system pixel density curve of the target camera is drawn according to the optical system distortion curve function, the abscissa of the optical system pixel density curve is the optical system half field angle, and the ordinate is the optical system pixel density of the target camera.

[0112] For example, the pixel density curve of the front-view camera optical system is as follows: Figure 7 As shown, the pixel density curve of the optical system of the rear-view camera is as follows Figure 8 As shown in Figure 2, the optical system pixel density curves of the front and rear surround view cameras are as follows: Fig. 9 As shown in Figure 2, the pixel density curves of the optical system of the left and right surround view cameras are as follows: Fig.10 shown.

[0113] S620: Determine the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system pixel density curve.

[0114] Exemplarily, a method for determining the central field of view distortion pixel density and the edge field of view distortion pixel density of a target camera may be: determining the correspondence between the optical system half field of view angle and the camera pixel density of the target camera according to an optical system pixel density curve; determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the correspondence between the optical system half field of view angle and the camera pixel density.

[0115] The central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined through the correspondence between the half field of view angle of the optical system of the target camera and the camera pixel density, so that the reliability of the central field of view distortion pixel density and the edge field of view distortion pixel density can be improved.

[0116] The above scheme determines the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system pixel density curve, which can improve the accuracy of the central field of view distortion pixel density and the edge field of view distortion pixel density.

[0117] For example, Fig.11 As shown, based on the above embodiment, the optical system data processing method includes:

[0118] The vehicle cameras of the intelligent driving visual perception system are counted. There are N vehicle cameras, and the optical system distortion curve functions of the vehicle cameras are read in sequence starting from the first vehicle camera. Assuming that the optical system distortion curve function of the target camera is being read, the target camera is the X-th vehicle camera, 1≤X≤N, and the optical system distortion curve function D(θ) of the target camera is determined.

[0119] Determine the pixel size P of the image sensor of the target camera, the horizontal field of view HFOV of the optical system of the target camera, and the central field of view distortion pixel density P of the target camera.center (θ) is: The pixel density P of the edge field of view distortion of the target camera edge (θ) is:

[0120] If the target camera is a forward-looking camera, the central field of view distortion pixel density of the target camera is P(θ) Center_Front ,and P Front is the pixel size of the image sensor of the front-view camera optical system, D Front (θ) is the distortion curve function of the optical system of the forward-looking camera; the edge field distortion pixel density of the target camera is P(θ) Edge_Front , and P(θ) Edge_Front The calculation formula is shown in formula (4):

[0121]

[0122] Among them, HFOV Front is the horizontal field of view of the forward-looking camera optical system.

[0123] If the target camera is a rear-view camera, the central field of view distortion pixel density of the target camera is P(θ) Center_Rear , and P(θ) Center_Rear The calculation formula is shown in formula (5):

[0124]

[0125] Among them, P Rear is the pixel size of the image sensor in the rearview camera optical system, D Rear (θ) is the distortion curve function of the rearview camera optical system.

[0126] The pixel density of the edge field of view distortion of the target camera is P(θ) Edge_Rear , and P(θ) Edge_Rear The calculation formula is shown in formula (6):

[0127]

[0129] Among them, HFOV Rear is the horizontal field of view of the rearview camera optical system.

[0130] If the target camera is a side-view camera, the central field of view distortion pixel density of the target camera is P(θ) Center_Side , and P(θ) Center_Side The calculation formula is shown in formula (7):

[0131]

[0132] Among them, P Side is the pixel size of the image sensor of the side-view camera optical system, D Side (θ) is the distortion curve function of the side-view camera optical system.

[0133] The pixel density of the edge field of view distortion of the target camera is P(θ) Edge_Side , and P(θ) Edge_Side The calculation formula is shown in formula (8):

[0134]

[0135] Among them, HFOV Side is the horizontal field of view of the side-view camera optical system.

[0136] According to the ratio R of the central field of view distortion pixel density and the edge field of view distortion pixel density, determine whether the optical system distortion curve function of the target camera needs to be optimized, R = P center (θ) / P edge (θ). If R meets the preset pixel density ratio condition, it is determined that the optical system distortion curve function of the target camera does not need to be optimized, and the staff is reminded to optimize the optical perception system of the target camera to optimize the optical system distortion curve function of the target camera; if R does not meet the pixel density ratio condition, it is determined that the optical system distortion curve function of the target camera needs to be optimized. This process continues until it is determined that the optical system distortion curve functions of the N vehicle-mounted cameras meet the requirements.

[0137] In the above optical system data processing method, the optical system distortion curve function of the target camera in the intelligent driving visual perception system is obtained; the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined according to the optical system distortion curve function; the optical system optimization judgment function is determined according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function. The problem of insufficient maximum detectable object distance of the required field of view, and low visual perception acquisition efficiency and visual perception field of view coverage in the multi-channel vision intelligent driving perception system is solved. The above method determines whether to optimize the optical system distortion curve function of the target camera based on the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera, which can improve the guidance accuracy and guidance efficiency of optimizing the optical system distortion curve function, thereby improving the visual perception acquisition efficiency and visual perception field of view coverage.

[0138] For example, if the intelligent driving visual perception system is a three-way forward visual perception system, the three-way vehicle-mounted cameras have the following characteristics respectively:

[0139] If the target camera is a telephoto forward-looking camera in a three-dimensional forward-looking visual perception system, the density ratio condition of the target camera is 1.5 ≥ R Far_Front ≥1, R Far_Front is the ratio of the central field of view distortion pixel density to the edge field of view distortion pixel density of the telephoto forward-looking camera, and R Far_Front =P(θ) Center_Far_Front / P(θ) Edge_Far_Front , P(θ) Center_Far_Front is the pixel density of the central field of view distortion of the telephoto forward-looking camera optical system, P(θ) Edge_Far_Front is the pixel density of the edge field of view distortion of the telephoto forward-looking camera optical system, and P(θ) Center_Far_Front The calculation formula of is shown in formula (9), P(θ) Edge_Far_Front The calculation formula is shown in formula (10):

[0140]

[0141]

[0142] Where D Far_Front (θ) is the distortion curve function of the telephoto forward-looking camera optical system, HFOV Far_Front is the horizontal field of view of the telephoto forward-looking camera optical system, P Far_Front is the pixel size of the image sensor in the telephoto forward-looking camera optical system.

[0143] If the target camera is a standard forward-looking camera in a three-dimensional forward-looking visual perception system, the density ratio condition of the target camera is 1.1 ≥ R Middle_Front ≥0.9, R Middle_Front is the ratio of the center field distortion pixel density to the edge field distortion pixel density of the standard forward-looking camera, and R Middle_Front =P(θ) Center_Middle_Front / P(θ) Edge_Middle_Front , P(θ) Center_Middle_Front is the pixel density of the central field of view distortion of the standard forward-looking camera optical system, P(θ) Edge_Middle_Front is the pixel density of the edge field of view distortion of the standard forward-looking camera optical system, P(θ) Center_Middle_Front The calculation formula of is shown in formula (11), P(θ) Edge_Middle_Front The calculation formula is shown in formula (12):

[0144]

[0145]

[0146] Among them, D Middle_Front(θ) is the distortion curve function of the standard forward-looking camera optical system, HFOV Middle_Front is the horizontal field of view of the standard forward-looking camera optical system, P Middle_Front is the pixel size of the image sensor of a standard forward-looking camera optical system.

[0147] If the target camera is a wide-angle forward-looking camera in a three-dimensional forward-looking visual perception system, the density ratio condition of the target camera is 0.4≤R Wide_Front ≤1, R Wide_Front is the ratio of the central field of view distortion pixel density to the edge field of view distortion pixel density of the wide-angle front-view camera, and R Wide_Front =P(θ) Center_Wide_Front / P(θ) Edge_Wide_Front , P(θ) Center_Wide_Front is the pixel density of the central field of view distortion of the wide-angle forward-looking camera optical system, P(θ) Edge_Wide_Front is the pixel density of the edge field of view distortion of the wide-angle forward-looking camera optical system, P(θ) Center_Wide_Front The calculation formula of is shown in formula (13), P(θ) Edge_Wide_Front The calculation formula is shown in formula (14):

[0148]

[0149]

[0150] Among them, D Wide_Front (θ) is the distortion curve function of the wide-angle forward-looking camera optical system, HFOV Wide_Front is the horizontal field of view of the wide-angle forward-looking camera optical system, P Wide_Front is the pixel size of the image sensor in the wide-angle forward-looking camera optical system.

[0151] Based on the specific configuration of the distorted pixel density of the three-way vehicle-mounted camera optical system, an innovative and optimized three-way forward-looking visual perception system was obtained, which improved the visual perception acquisition efficiency and enhanced the visual perception field of view coverage.

[0152] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0153] Based on the same inventive concept, the embodiment of the present application also provides an optical system data processing device for implementing the optical system data processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more optical system data processing device embodiments provided below can refer to the limitations of the optical system data processing method above, and will not be repeated here.

[0154] In one embodiment, Fig.12 As shown, an optical system data processing device is provided, comprising: a distortion curve function determination module 701, a pixel density determination module 702 and a system optimization judgment module 703, wherein:

[0155] The distortion curve function determination module 701 is used to obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system;

[0156] The pixel density determination module 702 is used to determine the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function;

[0157] The system optimization judgment module 703 is used to determine the optical system optimization judgment function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determine whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function.

[0158] Exemplarily, the system optimization determination module 703 is specifically used for:

[0159] The ratio of the central field of view distortion pixel density to the edge field of view distortion pixel density is taken as the target density ratio;

[0160] The target density ratio is used as an optical system optimization judgment function, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function.

[0161] Exemplarily, the system optimization determination module 703 is further specifically used for:

[0162] Determine a density ratio condition of the target camera according to the camera identification of the target camera;

[0163] Determine whether the optical system optimization judgment function satisfies the density ratio condition;

[0164] If so, it is determined that the optical system distortion curve function needs to be optimized, and an optical system optimization prompt message is issued.

[0165] Exemplarily, the pixel density determination module 702 is specifically used for:

[0166] Determine the pixel size of the image sensor of the target camera and the horizontal field of view of the optical system;

[0167] Determine the distortion pixel density of the central field of view of the target camera according to the distortion curve function of the optical system and the pixel size of the image sensor;

[0168] The edge field distortion pixel density of the target camera is determined according to the optical system distortion curve function, the image sensor pixel size and the horizontal field angle of the optical system.

[0169] Exemplarily, the pixel density determination module 702 is further specifically configured to:

[0170] Determine the target angle range based on the horizontal field of view of the optical system;

[0171] The edge field of view distortion pixel density of the target camera is determined based on the target angle range and the ratio between the image sensor pixel size and the horizontal field of view angle of the optical system.

[0172] Exemplarily, the pixel density determination module 702 is further specifically configured to:

[0173] Determine the optical system pixel density curve of the target camera according to the optical system distortion curve function;

[0174] The central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined according to the optical system pixel density curve.

[0175] Exemplarily, the pixel density determination module 702 is further specifically configured to:

[0176] Determine the corresponding relationship between the optical system half-field angle and the camera pixel density of the target camera according to the optical system pixel density curve;

[0177] According to the corresponding relationship between the half field of view angle of the optical system and the pixel density of the camera, the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined.

[0178] Each module in the optical system data processing device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0179] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.13 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an optical system data processing method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0180] Those skilled in the art will understand that Fig.13 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0181] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0182] Step 1: Obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system;

[0183] Step 2: Determine the center field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function;

[0184] Step 3: Determine the optical system optimization judgment function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determine whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function.

[0185] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0186] Step 1: Obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system;

[0187] Step 2: Determine the center field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function;

[0188] Step 3: Determine the optical system optimization judgment function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determine whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function.

[0189] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0190] Step 1: Obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system;

[0191] Step 2: Determine the center field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function;

[0192] Step 3: Determine the optical system optimization judgment function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determine whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function.

[0193] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0194] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0195] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0196] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing optical system data, It is characterized in that include: Obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system; Determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function; An optical system optimization judgment function is determined according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function.

2. The method according to claim 1, It is characterized in that Determining an optical system optimization determination function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determining whether the optical system distortion curve function needs to be optimized according to the optical system optimization determination function, including: Taking the ratio of the central field of view distortion pixel density to the edge field of view distortion pixel density as the target density ratio; The target density ratio is used as an optical system optimization judgment function, and whether the optical system distortion curve function needs to be optimized is determined according to the optical system optimization judgment function.

3. The method according to claim 2, It is characterized in that Determining whether the optical system distortion curve function needs to be optimized according to the optical system optimization determination function includes: Determining a density ratio condition of the target camera according to a camera identifier of the target camera; Determining whether the optical system optimization determination function satisfies the density ratio condition; If so, it is determined that the optical system distortion curve function needs to be optimized, and an optical system optimization prompt message is issued.

4. The method according to claim 1, It is characterized in that Determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function includes: Determine the pixel size of the image sensor and the horizontal field of view angle of the optical system of the target camera; Determining the central field of view distortion pixel density of the target camera according to the optical system distortion curve function and the image sensor pixel size; The edge field of view distortion pixel density of the target camera is determined according to the optical system distortion curve function, the image sensor pixel size and the horizontal field of view angle of the optical system.

5. The method according to claim 4, It is characterized in that Determining the edge field distortion pixel density of the target camera according to the optical system distortion curve function, the image sensor pixel size and the horizontal field angle of the optical system includes: Determining a target angle range according to the horizontal field angle of the optical system; The edge field of view distortion pixel density of the target camera is determined according to the target angle range and the ratio between the pixel size of the image sensor and the horizontal field of view angle of the optical system.

6. The method according to claim 1, It is characterized in that Determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function includes: Determining an optical system pixel density curve of the target camera according to the optical system distortion curve function; The central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined according to the optical system pixel density curve.

7. The method according to claim 6, It is characterized in that Determining the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system pixel density curve includes: Determine the corresponding relationship between the optical system half field angle and the camera pixel density of the target camera according to the optical system pixel density curve; According to the corresponding relationship between the half field of view angle of the optical system and the pixel density of the camera, the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera are determined.

8. An optical system data processing device, It is characterized in that The optical system data processing device comprises: A distortion curve function determination module is used to obtain the optical system distortion curve function of the target camera in the intelligent driving visual perception system; A pixel density determination module, used to determine the central field of view distortion pixel density and the edge field of view distortion pixel density of the target camera according to the optical system distortion curve function; The system optimization judgment module is used to determine the optical system optimization judgment function according to the central field of view distortion pixel density and the edge field of view distortion pixel density, and determine whether the optical system distortion curve function needs to be optimized according to the optical system optimization judgment function.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images