A method and device for realizing automatic change of viewing angle in a panoramic surround viewing system

Abstract

The present invention provides a method, device and storage medium for realizing automatic change of viewing angle in a panoramic surround view system, which is helpful for displaying and selecting parking spaces. The method comprises the steps of: generating a panoramic image based on a bowl model, obtaining the distance behind a vehicle when the panoramic image is displayed at a conventional viewing angle and the distance behind the vehicle when the panoramic image displays the maximum range behind the vehicle; after the panoramic surround view system is started, the panoramic image is first displayed at a conventional viewing angle, and when a target parking space is identified and the target parking space is located at the lower edge of the panoramic image, and the distance from the target parking space to the rear of the vehicle does not exceed the distance behind the vehicle when the panoramic image displays the maximum range behind the vehicle, the dynamic viewing angle is turned on, and the target parking space is always located at the lower edge of the panoramic image without moving under the dynamic viewing angle, and the vehicle model is correspondingly displayed as moving forward in the panoramic image; when the distance from the target parking space to the rear of the vehicle is greater than or equal to the distance behind the vehicle when the panoramic image displays the maximum range behind the vehicle, the dynamic viewing angle is turned off, and the panoramic image returns to the conventional viewing angle for display.

Description

Technical Field

[0001] The present invention relates to the technical field of 360 panoramic surround view systems, and particularly to a method, device, and storage medium for realizing automatic perspective change in a panoramic surround view system. Background Art

[0002] Nowadays, the 360 panoramic surround view system has been a very mature and widely used technology in the field of assisted driving. In addition to helping drivers view the surrounding environment of the vehicle, with the development of automatic parking technology, the 360 panorama is also used to identify parking spaces and display the identified parking spaces, playing more functions in the field of assisted driving. During the search for a parking space in automatic parking, technicians display the searchable parking spaces on the panoramic view. The driver manually selects the parking space to be parked in and then starts automatic parking.

[0003] Generally, in a 360 panoramic view, the vehicle model is centered. The front and rear display ranges of the vehicle model are about 3 meters, and the left and right display ranges are about 2.5 meters. Such a range can only display a few parking spaces. Moreover, when searching for a parking space, generally, drivers will pay more attention to the parking spaces behind the vehicle for convenient parking. The existing display method of the 360 panoramic view is not conducive to the display and selection of parking spaces. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method, device, and storage medium for realizing automatic perspective change in a panoramic surround view system, which can dynamically adjust the rear range of the vehicle displayed in the panoramic view when a parking space is searched in the panoramic view, increase the rear range displayed in the panoramic view, and the parking spaces searched as the vehicle continues to move remain on the panoramic view, which is helpful for the display and selection of parking spaces.

[0005] The technical solution is as follows: A method for realizing automatic perspective change in a panoramic surround view system, characterized by including the following steps:

[0006] Generate a panoramic view based on a bowl model and obtain the perspective parameters of the panoramic view;

[0007] According to the perspective parameters of the panoramic view, obtain the rear distance of the vehicle when the panoramic view is displayed in a conventional perspective and the rear distance of the vehicle when the panoramic view displays the maximum rear range;

[0008] After the panoramic surround view system is started, the panoramic view is first displayed in a conventional perspective. When a target parking space is recognized in the panoramic view and the target parking space is located at the lower edge of the panoramic view, and it satisfies that the distance from the target parking space to the rear of the vehicle does not exceed the rear distance of the vehicle when the panoramic view displays the maximum rear range, the panoramic surround view system starts a dynamic perspective. Under the dynamic perspective, the target parking space always remains at the lower edge of the panoramic view without moving. As the vehicle moves forward, the vehicle model is correspondingly displayed as moving forward in the panoramic view;

[0009] When the distance from the target parking space to the rear of the vehicle is greater than or equal to the distance behind the vehicle when the panoramic image displays the maximum range behind the vehicle, the dynamic perspective is closed and the panoramic image returns to the normal perspective for display.

[0010] Furthermore, generating a panoramic image based on the bowl model specifically includes the following steps:

[0011] A bowl model was constructed, and the car model was placed at the center of the bottom of the bowl model. The images of the four-way on-board cameras of the panoramic view system were mapped onto the bowl model according to the camera projection relationship, and the panoramic image was drawn using the OPENGL texture mapping function.

[0012] Furthermore, the world coordinate system O-XYZ is set. Both the bowl model and the car model are built in the world coordinate system O-XYZ. The bottom of the bowl is on the XOZ plane, and the center of the bottom of the bowl coincides with the origin O. The car model is at the center of the bottom of the bowl, and the rear of the car faces the positive direction of the Z axis. (eyeX, eyeY, eyeZ) is the position of the camera, and (centerX, centerY, centerZ) is the direction of the camera shooting.

[0013] Furthermore, the distance behind the car when the panorama is displayed at a normal viewing angle is calculated by the corner points of the panorama. The image coordinates of the corner point in the lower right corner of the panorama are (imgH-1, imgW-1), where imgH and imgW are the height and width of the panorama, respectively. According to the mapping relationship between the image coordinates and the world coordinates of OPENGL, the world coordinates of point A are

[0014]

[0015] Among them, fov is the field of view of OPENGL, and the distance behind the car when the panoramic image is displayed at a normal viewing angle is d1=Az.

[0016] Furthermore, when the panoramic image shows the maximum range behind the vehicle, the corner point B of the panoramic image is located on the bowl bottom ellipse of the bowl model, and the distance behind the vehicle when the panoramic image shows the maximum range behind the vehicle is calculated through the corner point of the panoramic image:

[0017] It is known that the short radius length of the bowl bottom ellipse of the bowl model is a, and the long radius length is b. According to the ellipse equation:

[0018] The X and Y coordinates of the corner point B of the panorama are the same as those of the corner point A under the normal viewing angle. The Z coordinate can be solved by the ellipse equation. The coordinates of point B are:

[0019]

[0020] The panoramic image shows the distance d2 = Bz behind the vehicle when the maximum range behind the vehicle is reached.

[0021] Furthermore, when the height coordinate value of the image coordinates of one of the four corner points of the target parking space is equal to imgH-1, and the height coordinate values ​​of the image coordinates of the other three corner points are less than or equal to imgH-1, it is considered that the target parking space satisfies the requirement of being located at the lower edge of the panoramic image, where imgH-1 is the height coordinate value of the image coordinates of the corner point of the panoramic image close to the rear side of the vehicle.

[0022] Furthermore, the distance from the target parking space to the rear of the vehicle is determined by the corner point of the parking space. When the Z-axis coordinate of the world coordinate of the corner point P is greater than or equal to the distance behind the vehicle when the panoramic view displays the maximum range behind the vehicle, the dynamic perspective is closed, and the vehicle model gradually returns to the position in the panoramic view under the normal perspective at a uniform speed.

[0023] Furthermore, after the dynamic perspective is turned on, the Z coordinate of the corner point P of the target parking space at this time is recorded as Z0, and the perspective parameters eyeZ and centerZ at this time are set to eyeZ0, centerZ0; by continuously adjusting the perspective parameters eyeZ and centerZ values, the target parking space is always located at the lower edge of the panoramic image during the vehicle's forward movement.

[0024] As the vehicle moves forward, the z coordinate Pz of the P corner point of the target parking space becomes:

[0025] Pz=z0+Δz

[0026] Then we have:

[0027] eyeZ=eyeZ0+Δz

[0028] centerZ=centerZ0+Δz

[0029] When the z coordinate Pz of the corner point P is greater than or equal to the distance d2 behind the vehicle when the panoramic image displays the maximum range behind the vehicle, the dynamic perspective is turned off, the eyeZ value gradually changes back to 0 at a uniform speed, and the panoramic image returns to the normal perspective for display.

[0030] Furthermore, when the panoramic image returns to the normal viewing angle, it is continuously determined whether there are other parking spaces that meet the conditions for opening the dynamic viewing angle. If so, the dynamic viewing angle is opened again.

[0031] A computer device, characterized in that it comprises: a processor, a memory and a program;

[0032] The program is stored in the memory, and the processor calls the program stored in the memory to execute the above-mentioned method for realizing automatic change of viewing angle in a panoramic surround view system.

[0033] A computer-readable storage medium, characterized in that: the computer-readable storage medium is used to store a program, and the program is used to execute the method for realizing automatic perspective change in the panoramic surround view system described above.

[0034] The method for realizing automatic perspective change in the panoramic surround view system provided by the present invention dynamically adjusts the panoramic perspective by using the recognized parking space information. When no parking space is recognized, a conventional 360-degree panoramic view is displayed; when a parking space is recognized and the conditions are met, the panoramic perspective is adjusted so that the vehicle model is located above the panoramic image, and the display range behind the vehicle is larger, showing more parking spaces for the driver to choose; as the vehicle moves forward and the parking space disappears, it returns to the conventional 360-degree panoramic view, and the perspective of the panoramic view automatically changes to meet the requirements in different situations, which helps with the display and selection of parking spaces. Description of the Drawings

[0035] Figure 1 It is a schematic diagram of the steps of a method for realizing automatic perspective change in a panoramic surround view system according to an embodiment of the present invention;

[0036] Figure 2 It is a schematic diagram showing that a parking space reaches the lower edge of the panoramic view at time t0;

[0037] Figure 3 It is a schematic diagram of a panoramic view displayed in a conventional perspective at time t1;

[0038] Figure 4 It is a schematic diagram of a panoramic view displayed in a dynamic perspective at time t1;

[0039] Figure 5 It is a side view of a bowl model in a conventional perspective;

[0040] Figure 6 It is a schematic diagram of a panoramic view in a conventional perspective;

[0041] Figure 7 It is a side view of a bowl model in a dynamic perspective;

[0042] Figure 8 It is a schematic diagram of a panoramic view in a dynamic perspective;

[0043] Figure 9 It is a schematic diagram for comparing panoramic views in a conventional perspective and a dynamic perspective;

[0044] Figure 10 It is a schematic diagram of the steps of a method for realizing automatic perspective change in a panoramic surround view system according to another embodiment of the present invention;

[0045] Figure 11 It is an internal structure diagram of a computer device in an embodiment. Detailed Embodiments

[0046] See Figure 1 , a method for automatically changing the viewing angle in a panoramic surround view system according to the present invention at least includes the following steps:

[0047] Step 1: Generate a panoramic image based on the bowl model and obtain the panoramic image viewing angle parameters;

[0048] Step 2: According to the panoramic image viewing angle parameters, obtain the distance behind the vehicle when the panoramic image is displayed in the normal viewing angle and the distance behind the vehicle when the maximum range behind the vehicle is displayed in the panoramic image;

[0049] Step 3: After the panoramic surround view system is started, the panoramic image is first displayed in the normal viewing angle. When a target parking space is recognized in the panoramic image and the target parking space is located at the lower edge of the panoramic image, and it satisfies that the distance from the target parking space to the rear of the vehicle does not exceed the distance behind the vehicle when the maximum range behind the vehicle is displayed in the panoramic image, the panoramic surround view system activates the dynamic viewing angle. In the dynamic viewing angle, the target parking space always remains at the lower edge of the panoramic image without moving. As the vehicle moves forward, the vehicle model is correspondingly displayed as moving forward in the panoramic image;

[0050] Step 4: When the distance from the target parking space to the rear of the vehicle is greater than or equal to the distance behind the vehicle when the maximum range behind the vehicle is displayed in the panoramic image, the dynamic viewing angle is closed, and the panoramic image returns to the normal viewing angle for display.

[0051] In an embodiment of the present invention, in Step 1, generating a panoramic image based on the bowl model specifically includes the following steps:

[0052] Construct a bowl model, place the vehicle model at the center of the bottom of the bowl of the bowl model, map the images of the four vehicle-mounted cameras of the panoramic surround view system to the bowl model according to the camera projection relationship, and use the OPENGL texture mapping function to draw the panoramic image. Set the world coordinate system O-XYZ. Both the bowl model and the vehicle model are built in the world coordinate system O-XYZ. The bottom of the bowl is on the XOZ plane, and the center of the bottom of the bowl coincides with the origin O; the vehicle model is at the center of the bottom of the bowl, the rear of the vehicle faces the positive direction of the Z axis, (eyeX, eyeY, eyeZ) is the position of the camera, and (centerX, centerY, centerZ) is the direction of the camera shooting.

[0053] As Figure 5 、 6 、shown, in the normal viewing angle, Figure 5In it, the eye is directly above the origin, and the center is at the origin. Looking down vertically from the position of the eye to take a photo, what is captured is the scene at the bottom of the bowl model, that is, the panoramic view. The origin is at the center of the panoramic view, and the car model is also at the center of the panoramic view. (centerX, centerY, centerZ) = (0, 0, 0), and the viewing angle of the 360-degree panoramic view is (eyeX, eyeY, eyeZ) = (0, h, 0), where h is the viewing height. See Figure 6 , when the panoramic view is displayed in a conventional viewing angle, the distance d1 behind the car is calculated starting from the center of the vehicle.

[0054] Since the actual image range that the bowl model can display is larger than the range displayed by the panoramic view, the image displayed by the panoramic view in a conventional viewing angle is only a part of the bowl model, and the maximum range of the car displayed in the panoramic view in the bowl model is larger.

[0055] By adjusting the value of eyeZ and keeping the value of centerZ always consistent with eyeZ, the position of the car model in the panoramic view can be changed. If the value of eyeZ becomes z1, the position of the car model in the panoramic view becomes higher, and the display range behind the car becomes larger, as Figure 7 、 8 shown.

[0056] Because the size of the bowl model is limited, when adjusting eyeZ, the maximum display range behind the car is also limited, as Figure 9 shown. The range of the conventional bowl model showing the area behind the car is d1, which is calculated starting from the center of the car. After adjusting eyeZ, the maximum range that can be shown behind the car is d2, which is calculated starting from the center of the car. Beyond this range of d2, distortion problems will occur in the panoramic view.

[0057] In step 2, according to the viewing angle parameters of the panoramic view, obtain the distance behind the car when the panoramic view is displayed in a conventional viewing angle and the distance behind the car when the panoramic view shows the maximum range behind the car.

[0058] In the embodiment, the distance behind the car when the panoramic view is displayed in a conventional viewing angle is calculated through the corner points of the panoramic view.

[0059] The image coordinate system takes the upper left corner as the coordinate origin, so the pixel coordinates of the upper left corner are (0, 0). When imgH and imgW are the height and width of the panoramic view in the image coordinates respectively, the pixel coordinates of the lower right corner are (imgH - 1, imgW - 1);

[0060] According to the mapping relationship between the image coordinates and the world coordinates of OPENGL, the world coordinates of the corner point A are:

[0061]

[0062] Among them, fov is the field of view of OPENGL, and the distance behind the car when the panoramic image is displayed at a normal viewing angle is d1=Az.

[0063] See Figure 7 , Figure 8 , Figure 9 , Figure 7 In the image, the eye moves to the top of the back of the car, and the center also moves to the back of the car to ensure that the image is always shot vertically downward. At this time, the center of the panorama is the back of the car, and the car model is at the top of the panorama. Regardless of whether it is a regular or dynamic perspective, the above coordinate system and the bowl model car model will not change, only the perspective will change.

[0064] When the panoramic image shows the maximum range behind the car, the corner point B of the panoramic image is located on the bowl bottom ellipse of the bowl model. The distance behind the car when the panoramic image shows the maximum range behind the car is calculated through the corner point of the panoramic image:

[0065] It is known that the short radius length of the bowl bottom ellipse of the bowl model is a, and the long radius length is b. According to the ellipse equation:

[0066] The X and Y coordinates of the corner point B of the panorama are the same as those of the corner point A under the normal viewing angle. The Z coordinate can be solved by the ellipse equation. The coordinates of point B are:

[0067]

[0068] The panoramic image shows the distance d2 = Bz behind the vehicle when the maximum range behind the vehicle is reached.

[0069] In step 3, after the panoramic view system is started, it first displays the panoramic view in a conventional perspective. When the target parking space is identified in the panoramic view and the target parking space is located at the lower edge of the panoramic view, and the distance from the target parking space to the rear of the vehicle does not exceed the distance behind the vehicle when the panoramic view displays the maximum range behind the vehicle, the panoramic view system starts the dynamic perspective.

[0070] Specifically in the embodiment, when the height coordinate value of the image coordinates of one corner point P of the four corner points of the target parking space is equal to imgH-1, and the height coordinate values ​​of the image coordinates of the other three corner points are less than or equal to imgH-1, it is considered that the target parking space satisfies the requirement of being located at the lower edge of the panoramic image, where imgH-1 is the height coordinate value of the image coordinates of the corner point of the panoramic image close to the rear side of the vehicle.

[0071] Further, after enabling the dynamic perspective, record the Z coordinate of the corner point P of the target parking space at this time as Z0, and the perspective parameters eyeZ and centerZ at this time, denoted as eyeZ0 and centerZ0; by continuously adjusting the values of the perspective parameters eyeZ and centerZ, ensure that the target parking space is always located at the lower edge of the panoramic view during the vehicle's forward movement.

[0072] As the vehicle moves forward, the z coordinate Pz of the P corner point of the target parking space becomes:

[0073] Pz = z0 + Δz

[0074] Then there is:

[0075] eyeZ = eyeZ0 + Δz

[0076] centerZ = centerZ0 + Δz

[0077] In step 4, the distance from the target parking space to the rear of the vehicle is judged by the corner points of the parking space. When the Z-axis coordinate of the world coordinate of the corner point P is greater than or equal to the distance to the rear of the vehicle when the maximum range behind the vehicle is displayed in the panoramic view, the dynamic perspective is turned off, and the vehicle model gradually returns to its position in the panoramic view under the normal perspective at a constant speed.

[0078] In the embodiment, when the z coordinate Pz of the corner point P is greater than or equal to the distance d2 to the rear of the vehicle when the maximum range behind the vehicle is displayed in the panoramic view, the dynamic perspective is turned off, and the value of eyeZ gradually returns to 0 at a constant speed, and the panoramic view returns to the normal perspective for display.

[0079] In addition, in an embodiment of the present invention, step 5 is further included: during the process of the panoramic view returning to the normal perspective, continue to judge whether there are other parking spaces that meet the conditions for enabling the dynamic perspective. If so, enable the dynamic perspective again.

[0080] The following combines the attached Figures 2 to 4 Describe the use of the method of the present invention:

[0081] Figure 2 Shows that at time t0, a parking space reaches the lower edge of the panoramic view. Normally, as the vehicle continues to move, as Figure 3 shown, at time t1, when using the normal panoramic view, because the vehicle is moving forward, parking space 1 will quickly move out of the panoramic view and cannot be seen in the panoramic view screen. If the driver wants to park in parking space 1 at this time, they need to readjust the vehicle position again and cannot select parking space 1 with the help of the current panoramic view display result.

[0082] If the method of the present invention is adopted, after detecting the target parking space at time t0, the panoramic surround view system activates the dynamic perspective. In the dynamic perspective, the target parking space always remains at the lower edge of the panoramic view without moving. As the vehicle moves forward, the perspective parameter of the panoramic view is continuously adjusted so that the vehicle model is correspondingly displayed as moving forward in the panoramic view; as Figure 4 shown, the display range behind the vehicle becomes relatively larger, and more parking spaces behind the vehicle can be displayed. Parking space 1 can continue to be displayed in the panoramic image, so that parking space 1 is displayed in the panoramic view for a longer time, enabling the driver to have more parking spaces to choose from.

[0083] In an embodiment of the present invention, a computer device is further provided, which includes: a processor, a memory, and a program;

[0084] The program is stored in the memory, and the processor calls the program stored in the memory to execute the method for realizing automatic perspective change in the panoramic surround view system described above.

[0085] The computer device may be a terminal, and its internal structure diagram may be as Figure 11 shown. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a bus. Among them, 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 network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, realizes the method for realizing automatic perspective change in the panoramic surround view system. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0086] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electric Erasable Programmable Read-Only Memory (EEPROM), etc. Among them, the memory is used to store programs, and the processor executes the programs after receiving execution instructions.

[0087] The processor can be an integrated circuit chip with the ability to process signals. The above-mentioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc. The processor can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0088] Those skilled in the art can understand that Figure 11 the structure shown in

[0089] In the embodiments of the present invention, a computer-readable storage medium is also provided. The computer-readable storage medium is used to store a program, and the program is used to execute the method for realizing automatic perspective change in the panoramic surround view system described above.

[0090] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a computer device, or a computer program product. Therefore, the embodiments of the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0091] The embodiments of the present invention are described with reference to the flowcharts of the methods, computer devices, or computer program products according to the embodiments of the present invention. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing terminal devices generate a device for realizing the functions specified in the flowcharts.

[0092] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that realizes the functions specified in the flowcharts.

[0093] The above has introduced in detail the application of the method, system, computer device, and computer-readable storage medium for realizing automatic perspective change in a panoramic surround view system provided by the present invention. Specific examples are used in this article to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for automatically changing the viewing angle in a panoramic surround view system, characterized in that, it includes the following steps: Generate a panoramic image based on the bowl model and obtain the viewing angle parameters of the panoramic image; According to the viewing angle parameters of the panoramic image, obtain the distance behind the vehicle when the panoramic image is displayed in the conventional viewing angle and the distance behind the vehicle when the panoramic image displays the maximum range behind the vehicle; After the panoramic surround view system is started, the panoramic image is first displayed in the conventional viewing angle. When a target parking space is recognized in the panoramic image and the target parking space is located at the lower edge of the panoramic image, and it satisfies that the distance from the target parking space to the rear of the vehicle does not exceed the distance behind the vehicle when the panoramic image displays the maximum range behind the vehicle, the panoramic surround view system activates the dynamic viewing angle. Under the dynamic viewing angle, the target parking space always remains at the lower edge of the panoramic image without moving. As the vehicle moves forward, the vehicle model is correspondingly displayed as moving forward in the panoramic image; When the distance from the target parking space to the rear of the vehicle is greater than or equal to the distance behind the vehicle when the panoramic image displays the maximum range behind the vehicle, the dynamic viewing angle is turned off, and the panoramic image returns to the conventional viewing angle for display.

2. The method for automatically changing the viewing angle in a panoramic surround view system according to claim 1, characterized in that, generating a panoramic image based on the bowl model specifically includes the following steps: Construct a bowl model, place the vehicle model at the center of the bottom of the bowl, map the images of the four vehicle-mounted cameras of the panoramic surround view system onto the bowl model according to the camera projection relationship, and use the OPENGL texture mapping function to draw to obtain the panoramic image.

3. The method for automatically changing the viewing angle in a panoramic surround view system according to claim 2, characterized in that: Set the world coordinate system O-XYZ. Both the bowl model and the vehicle model are built in the world coordinate system O-XYZ. The bottom of the bowl is on the XOZ plane, and the center of the bottom of the bowl coincides with the origin O; the vehicle model is at the center of the bottom of the bowl, the rear of the vehicle faces the positive direction of the Z axis, (eyeX, eyeY, eyeZ) is the position of the camera, and (centerX, centerY, centerZ) is the shooting direction of the camera.

4. The method for automatically changing the viewing angle in a panoramic surround view system according to claim 3, characterized in that: The distance behind the vehicle when the panoramic image is displayed in the conventional viewing angle is calculated through the corner points of the panoramic image. The image coordinates of the lower right corner point of the panoramic image are (imgH - 1, imgW - 1), where imgH and imgW are the height and width of the panoramic image respectively. According to the mapping relationship between the image coordinates and the world coordinates of OPENGL, the world coordinates of point A are where fov is the field of view angle of OPENGL, and the distance behind the vehicle d1 = Az when the panoramic image is displayed in the conventional viewing angle; When the panoramic image displays the maximum range behind the vehicle, the corner point B of the panoramic image is located on the bottom ellipse of the bowl model. The distance behind the vehicle when the panoramic image displays the maximum range behind the vehicle is calculated through the corner points of the panoramic image: The length of the minor semi - axis of the bottom ellipse of the known bowl model is \(a\), and the length of the major semi - axis is \(b\). According to the ellipse equation: The X and Y axis coordinates of the corner point B of the panoramic image are the same as those of the corner point A in the conventional viewing angle, and the Z axis coordinate can be solved through the ellipse equation. The coordinates of point B are: The distance behind the vehicle d2 = Bz when the panoramic image displays the maximum range behind the vehicle.

5. A method for realizing automatic perspective change in a panoramic surround view system according to claim 4, characterized in that: When the height coordinate value of the image coordinate of one of the four corner points of the target parking space, namely corner point P, is equal to imgH - 1, and the height coordinate values of the image coordinates of the other three corner points are less than or equal to imgH - 1, it is considered that the target parking space is located at the lower edge of the panoramic view, where imgH - 1 is the height coordinate value of the image coordinate of the corner point of the panoramic view near the rear of the vehicle.

6. A method for realizing automatic perspective change in a panoramic surround view system according to claim 5, characterized in that: The distance from the target parking space to the rear of the vehicle is judged by the corner points of the parking space. When the Z - axis coordinate of the world coordinate of corner point P is greater than or equal to the rear - vehicle distance when the maximum range behind the vehicle is displayed in the panoramic view, the dynamic perspective is turned off, and the vehicle model gradually returns to its position in the panoramic view under the normal perspective at a uniform speed.

7. A method for realizing automatic perspective change in a panoramic surround view system according to claim 6, characterized in that: After starting the dynamic perspective, record the Z - coordinate of corner point P of the target parking space at this time as Z0, and the perspective parameters eyeZ and centerZ at this time, denoted as eyeZ0 and centerZ0; by continuously adjusting the values of the perspective parameters eyeZ and centerZ, during the vehicle's forward movement, the target parking space is always located at the lower edge of the panoramic view; As the vehicle moves forward, the z - coordinate Pz of corner point P of the target parking space becomes: Pz = z0 + Δz Then there is: eyeZ = eyeZ0 + Δz centerZ = centerZ0 + Δz When the z - coordinate Pz of corner point P is greater than or equal to the rear - vehicle distance d2 when the maximum range behind the vehicle is displayed in the panoramic view, the dynamic perspective is turned off, and the eyeZ value gradually returns to 0 at a uniform speed, and the panoramic view returns to the normal perspective for display. Δz is the component of the vehicle's movement amount on the Z - axis.

8. A method for realizing automatic perspective change in a panoramic surround view system according to claim 6, characterized in that: During the process of the panoramic view returning to the normal perspective, continue to judge whether there are other parking spaces that meet the conditions for starting the dynamic perspective. If so, start the dynamic perspective again.

9. A computer device, characterized in that, it includes: a processor, a memory, and a program; The program is stored in the memory, and the processor calls the program stored in the memory to execute the method for realizing automatic perspective change in a panoramic surround view system according to any one of claims 1 to 8.

10. A computer - readable storage medium, characterized in that: The computer - readable storage medium is used to store a program, and the program is used to execute the method for realizing automatic perspective change in a panoramic surround view system according to any one of claims 1 to 8.

Images