Vehicle bottom perspective display method, device and computer storage medium

Abstract

The present invention provides a bottom perspective display method and device. The method includes: performing distortion correction processing on a fisheye image taken by a single wide-angle lens; obtaining a corresponding top view through homography matrix mapping of the corrected image; performing real-time splicing and updating of each frame of the top view image to obtain a bottom perspective image; specifically including: determining the coordinate transformation after updating the coordinate system, determining the coordinate position of the pixel point of the previous frame image in the current frame according to the vehicle speed and the front wheel turning angle of the vehicle; judging whether to refresh the display, and refreshing the display when the total displacement of the coordinate axis of the current frame exceeds a first threshold; judging whether to add a new segment, and adding an image segment when the total span of the current frame segment exceeds a second threshold; updating the diagonal coordinates of all segments; inserting a car model image, a background image, a rear view and a segment image into the corresponding position of the bottom perspective image to synthesize the bottom perspective image. The present invention uses a single camera to display the changes in the surrounding environment of the vehicle during the reversing process, eliminate the visual blind spot of the driver, and has low cost, simple operation, avoids complex calibration and registration processes, and has wide applicability.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile assisted driving, and in particular to a vehicle bottom perspective display method, device and computer storage medium. Background Art

[0002] Assisted driving is an important part of the field of vehicle intelligence, and the requirements for vehicle-mounted images are gradually increasing. The most important part of assisted driving is to help the driver clearly observe the blind spots of the vehicle during reversing, view the changes behind and on both sides of the vehicle in real time, and avoid the vehicle from hitting roadside obstacles or colliding with pedestrians. In terms of vehicle-mounted image-assisted driving, the most basic application is to install a wide-angle lens at the rear of the vehicle, capture regional images with a wider viewing angle, and remove distortion to assist the driver in observing the situation behind the vehicle during reversing. This method is low-cost and simple to install, but the range of blind spots that can be removed is small, which is not conducive to the driver's observation of the situation on both sides of the vehicle. In order to solve this problem, a method of installing multiple cameras around the vehicle to obtain a 360-degree panoramic image around the vehicle was subsequently proposed. This method is to install cameras in the front, back, left, and right directions of the car. For large vehicles, it is necessary to consider installing more cameras on both sides according to actual conditions, and splice the images taken by all cameras together to obtain a panoramic image around the vehicle. This method can better reflect the changes in the surrounding environment of the vehicle and remove blind spots, but the cost is high. In addition, it is necessary to splice and align the two cameras, which increases the difficulty of calibration and takes a long time, which is not conducive to widespread promotion and use. Summary of the invention

[0003] In view of this, the present invention provides a vehicle bottom perspective display method, device, computer storage medium and terminal equipment to solve the deficiencies of the prior art.

[0004] In order to achieve the above object, the present invention adopts the following technical scheme:

[0005] An embodiment of the present invention provides a vehicle bottom perspective display method, comprising:

[0006] Perform distortion correction on the fisheye image taken by a single wide-angle lens;

[0007] Obtain the corresponding top view of the corrected image through homography matrix mapping;

[0008] Each frame of the acquired top view image is stitched and updated in real time to obtain a perspective image of the vehicle bottom; specifically, it includes:

[0009] After the coordinate system is updated, the coordinate transformation is determined, and the coordinate position of the pixel point of the previous frame image in the current frame is determined according to the vehicle speed and the front wheel turning angle of the vehicle;

[0010] Determine whether to refresh the display, and refresh the display when the total displacement of the coordinate axis of the current frame exceeds the first threshold;

[0011] Determine whether to add a new segment, and add a new image segment when the total span of the current frame segments exceeds a second threshold;

[0012] Update all fragment diagonal coordinates;

[0013] The vehicle model image, background image, rear view image and fragment image are inserted into corresponding positions of the vehicle bottom perspective image to synthesize the vehicle bottom perspective image.

[0014] Furthermore, the coordinate transformation after determining the updated coordinate system and determining the coordinate position of the pixel point of the previous frame image in the current frame according to the vehicle speed and the front wheel turning angle of the vehicle specifically includes:

[0015] The body angle is determined based on the front wheel angle and vehicle speed; the following expression is used Among them, angle is the front wheel turning angle, da is the body turning angle, vt is the vehicle speed, H is the distance between the front wheel and the rear wheel, and R is the turning radius;

[0016] Update the coordinate system to determine the pixel displacement of the origin of the coordinate system in the x and y directions between the current frame and the previous frame; use the following expression

[0017] dx=vt*ts*cos(b)

[0018] dy2vt*ts*sin(b)

[0019] Among them, da is the vehicle body angle, vt is the vehicle speed, ts is the time difference between two frames, and h is the pixel distance from the rear wheel of the vehicle to the origin of the coordinate system;

[0020] Calculate and update the coordinates of the pixel point in the previous frame in the current frame; assume that the position coordinates (oldX, oldY) in the previous frame coordinate system, due to the vehicle turning, the corresponding coordinates (newX, newY) in the new coordinate system satisfy the following

[0021] in, da=θ+a, newY=r*sin(a)+dy+SHM

[0022]

[0023]

[0024] da=θ+a;

[0025] Where (SWT / 2, SHM) is the pixel coordinate value of the origin of the coordinate axis in the bottom perspective view of the vehicle.

[0026] Furthermore, the first threshold is 1; the second threshold is -2.

[0027] Furthermore, for the newly added image segment, one line of image information is added in each of the upper and lower lines.

[0028] The embodiment of the present invention further provides a vehicle bottom perspective display device, comprising:

[0029] A distortion correction module is used to perform distortion correction on fisheye images taken by a single wide-angle lens;

[0030] A mapping acquisition module, used for acquiring a corresponding top view angle through homography matrix mapping of the image processed by the distortion correction module;

[0031] The image stitching module is used to stitch and update each frame of the acquired top-view image in real time to obtain a perspective image of the bottom of the vehicle; the image stitching module is specifically used to:

[0032] After the coordinate system is updated, the coordinate transformation is determined, and the coordinate position of the pixel point of the previous frame image in the current frame is determined according to the vehicle speed and the front wheel turning angle of the vehicle;

[0033] Determine whether to refresh the display, and refresh the display when the total displacement of the coordinate axis of the current frame exceeds the first threshold;

[0034] Determine whether to add a new segment, and add a new image segment when the total span of the current frame segments exceeds a second threshold;

[0035] Update all fragment diagonal coordinates;

[0036] The vehicle model image, background image, rear view image and fragment image are inserted into corresponding positions of the vehicle bottom perspective image to synthesize the vehicle bottom perspective image.

[0037] Furthermore, the coordinate transformation after determining the updated coordinate system and determining the coordinate position of the pixel point of the previous frame image in the current frame according to the vehicle speed and the front wheel turning angle of the vehicle specifically includes:

[0038] The body angle is determined based on the front wheel angle and vehicle speed; the following expression is used Among them, angle is the front wheel turning angle, da is the body turning angle, vt is the vehicle speed, H is the distance between the front wheel and the rear wheel, and R is the turning radius;

[0039] Update the coordinate system to determine the pixel displacement of the origin of the coordinate system in the x and y directions between the current frame and the previous frame; use the following expression

[0040] dx=vt*ts*cos(b)

[0041] dy=vt*ts*sin(b)

[0042] Among them, da is the vehicle body angle, vt is the vehicle speed, ts is the time difference between two frames, and h is the pixel distance from the rear wheel of the vehicle to the origin of the coordinate system;

[0043] Calculate and update the coordinates of the pixel point in the previous frame in the current frame; assume that the position coordinates (oldX, oldY) in the previous frame coordinate system, due to the vehicle turning, the corresponding coordinates (newX, newY) in the new coordinate system satisfy the following

[0044] in, da=θ+a,

[0045] newY=r*sin(a)+dy+SHM

[0046]

[0047]

[0048] Where (SWT / 2, SHM) is the pixel coordinate value of the origin of the coordinate axis in the bottom perspective view of the vehicle.

[0049] Furthermore, the first threshold is 1; the second threshold is -2.

[0050] Furthermore, for the newly added image segment, one line of image information is added in each of the upper and lower lines.

[0051] An embodiment of the present invention further provides a computer storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned vehicle bottom perspective display method are implemented.

[0052] An embodiment of the present invention further provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned underbody perspective display method when executing the computer program.

[0053] The vehicle bottom perspective display method provided by the present invention uses a single wide-angle camera to splice the updated image content in each frame in real time, so that the driver can obtain and display the changes in the vehicle's surrounding environment during the reversing process, eliminating the driver's visual blind spots; the present invention does not need to install multiple cameras and does not involve alignment between cameras, which not only reduces the production cost and the difficulty and complexity of the algorithm, but also ensures that the driver can clearly observe the environment behind and on both sides of the vehicle, thereby meeting the requirements of assisted driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 is a flow chart of the vehicle bottom perspective display method provided by the present invention;

[0056] Figure 2 It is the image composition diagram of each part of the perspective view of the bottom of the vehicle;

[0057] Figure 3 It is a schematic diagram of the conversion relationship between the front wheel turning angle of the vehicle and the turning angle of the vehicle sound;

[0058] Figure 4 It is a schematic diagram of the change of the origin coordinates after the coordinate system is updated;

[0059] Figure 5 It is a schematic diagram of the coordinate values ​​of the pixel points of the previous frame image in the new coordinate system of the current frame after the coordinate system is updated;

[0060] Figure 6 It is a schematic diagram of the perspective view of the bottom of the vehicle mapped to the fragment according to the diagonal coordinates. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Figure 1 The figure is a flow chart of a vehicle bottom perspective display method provided by an embodiment of the present invention. The method comprises the following steps:

[0063] S101, performing distortion correction processing on a fisheye image captured by a single wide-angle lens.

[0064] The fisheye distorted image captured by a single wide-angle lens is corrected to remove the distortion. The wide-angle lens captures a wide angle of view and can collect a large range of image information behind the vehicle, but there is distortion, which needs to be corrected to restore it to an image that conforms to normal vision. Generally, the Zhang Zhengyou calibration method, the photographic view calibration method, the isometric projection model, etc. can be used to dedistort the image and obtain the corrected image.

[0065] S102, obtaining a corresponding top view of the corrected image through homography matrix mapping.

[0066] Map the correction image to obtain a top view. Mapping the image to the top view perspective can eliminate blind spots to a greater extent and ensure that the surrounding environment changes are reflected in real time during the entire reversing process of the vehicle. The stitching of the bottom perspective image is based on the top view. The top view can well reflect the changes in the ground environment around the vehicle, but because the wide-angle lens is not installed on the vehicle at an angle facing the ground, it is necessary to obtain the corresponding top view through homography matrix mapping.

[0067] The corrected image mapping is used to obtain the top view using the following expression:

[0068]

[0069] Where (u, v) is the coordinate corresponding to the correction image, H is the homography matrix, and (x, y) is the coordinate corresponding to the top view. Through the homography matrix H, the coordinate (u, v) in the correction image corresponding to each point (x, y) in the top view is determined, and the top view is obtained by interpolation.

[0070] S103, performing real-time splicing and updating of each frame of the acquired top-view image to obtain a perspective image of the vehicle bottom.

[0071] Specifically include:

[0072] S1031, determine the coordinate transformation after updating the coordinate system, and determine the coordinate position of the pixel point of the previous frame image in the current frame according to the vehicle speed and the front wheel steering angle of the vehicle.

[0073] Determine the coordinate transformation after updating the coordinate system. During the vehicle movement, the x-axis is always at a fixed position from the rear of the vehicle, which is generally determined during calibration, and the y-axis passes through the center of the vehicle and is parallel to the vehicle. This coordinate axis is used to calculate the displacement of the pixel point. According to the front wheel angle and speed of the vehicle, the coordinate position of the pixel point of the previous frame image in the current frame is calculated.

[0074] Obtain the perspective image of the bottom of the vehicle. Insert each frame of the image captured by the rear-view camera during the reversing process into the corresponding position of the perspective image of the bottom of the vehicle to obtain a panoramic image. Figure 2 As shown, the bottom perspective image of the vehicle mainly consists of four parts: vehicle model image, background image, rear view, and fragment image. Figure 2The image composition of the bottom perspective view of a certain frame in the reversing process is shown. The car model image can be drawn according to the actual vehicle features, or a general vehicle image can be selected. A semi-transparent car model image can be used to avoid affecting the observation of ground pixels. The fragment image is composed of fragments determined by the rear view images of each part in the previous frame. During the reversing process, the position of the fragment image will continue to change, and the fragments will continue to increase, and the fragments will be continuously filled into the bottom perspective view. The background image is the part that has not been filled. It can be replaced by gray pixels. If the reversing distance is long and the fragments accumulate more, the entire background image will be replaced by the fragment image. SWT represents the width of the bottom perspective view. SHM+SHR represents the length of the bottom perspective view, where SHM represents the length from the origin of the coordinate axis to the top of the perspective view, and SHR represents the length from the origin of the coordinate axis to the bottom of the perspective view. The pixel coordinate value of the origin of the coordinate axis in the bottom perspective view is (SWT / 2, SHM).

[0075] The rear view is the undistorted top view image of the current frame obtained in step S102. The detailed process of obtaining the bottom perspective view of the vehicle includes:

[0076] The coordinate transformation after the updated coordinate system is determined. The reference coordinate system in the vehicle's motion process is fixed in the vehicle bottom perspective view, as shown in the attached figure. Figure 2 As shown in , the x-axis is the starting position of the rear view. During the calibration process, it is determined according to the vehicle and camera installation positions to ensure that the rear view is valid and clear pixels from the x-axis onwards, and the y-axis passes through the center of the car model image. The position of the vehicle is unchanged in the bottom perspective image, so when inserting a segment, the corresponding coordinates of the pixel points in the segment in the new coordinate system need to be calculated.

[0077] During vehicle movement, the sensor can transmit the front wheel steering angle, which needs to be converted into the body angle, and then the conversion relationship between the previous frame coordinate system and the current frame coordinate system is obtained to determine the coordinate value of each point in the previous frame in the current frame coordinate system.

[0078] (a) The front wheel turning angle is converted into the body turning angle. Figure 3 , determine the relationship between the front wheel turning angle angle and the body turning angle da.

[0079]

[0080]

[0081] Among them, vt is the vehicle speed, H is the distance between the front wheel and the rear wheel, and R is the turning radius.

[0082] (b) Update the coordinate system and determine the displacement of the coordinate origin. Figure 4, taking the right front as an example, the pixel displacement of the origin is (dx,dy). The bicycle model is used to simulate the vehicle motion, that is, the vehicle moves on a two-dimensional plane, the two front wheels have the same turning angle, and the same is true for the two rear wheels. Therefore, the front and rear wheels can be described by one tire, and the front wheel controls the vehicle turning angle.

[0083]

[0084]

[0085] dx=vt*ts*cos(b)

[0086] dy=vt*ts*sin(b)

[0087] Among them, h is the pixel distance from the rear wheel of the vehicle to the origin of the coordinate system, and ts is the time difference between the two frames. The coordinates of the origin of the coordinate system of the previous frame in the current frame are (dx, dy), which determines the pixel displacement of the origin of the coordinate system in the x direction and y direction between the current frame and the previous frame.

[0088] (c) Calculate the updated coordinates. The coordinate position of any point on the previous frame image in the current frame should meet Figure 5 The position coordinates (oldX, oldY) of any point in the image in the previous frame coordinate system, and the corresponding coordinates (newX, newY) in the new coordinate system due to the vehicle turning, take the vehicle moving to the right front as an example:

[0089]

[0090]

[0091] da=θ+a

[0092]

[0093] newY=r*sin(α)+dy+SHM

[0094] Where (SWT / 2, SHM) is the pixel coordinate value of the origin of the coordinate axis in the bottom perspective view of the vehicle.

[0095] S1032, determining whether it is necessary to refresh the display, and refreshing the display when the total displacement of the coordinate axis of the current frame exceeds a first threshold; and returning the total displacement of the coordinate axis of the current frame to zero.

[0096] For a frame of image, instead of calculating the displacement of each pixel point, the displacement of a finite number of representative points on the frame of image can be calculated, and a certain displacement value is selected to determine whether it exceeds a threshold, thereby determining whether it is necessary to refresh the display or add a new segment. In this embodiment, the finite number of representative points are selected as the two points at the leftmost and rightmost ends of the coordinate axis, and the displacements of the leftmost and rightmost endpoints of the coordinate axis are calculated respectively, and the one with the largest displacement is selected as the current frame displacement.

[0097] According to the total displacement of the coordinate axis of the current frame, determine whether the refresh display requirement is met. If the total displacement of the current frame exceeds the first threshold, it means that the vehicle has moved significantly, and the cached fragments need to be redrawn to the specified position of the bottom perspective view of the vehicle; refresh the display. If it does not exceed the threshold, there is no need to refresh, and the fragment image part can still use the previous frame image.

[0098] To determine whether to refresh the display, the change value (xDummy, yDummy) of the coordinate axis of the previous frame within the perspective view of the vehicle bottom can be calculated according to step S1031, and the displacement value rDummy of the current frame is:

[0099]

[0100] The total displacement of the current frame is composed of the current frame displacement value rDummy and the previous accumulated displacement. If the total displacement value of the current frame is greater than the first threshold value, in the present invention, the first threshold value is 1, indicating that the image pixel change caused by the vehicle movement accumulated to the current frame exceeds one row of pixels, and the display needs to be refreshed. Otherwise, it means that the accumulated vehicle displacement to this frame is not obvious, the image has not changed significantly, and there is no need to refresh the display.

[0101] The total displacement of the current frame is composed of the current frame displacement and the cumulative displacement of the previous frame. If the threshold is reached, it means that a refresh is required, and the cumulative displacement value of the frame is reset to 0 for use in the calculation of the next frame. If the threshold is not reached, the total displacement of the current frame is used as the cumulative displacement of the previous frame for the next frame calculation and judgment.

[0102] A similar processing method is used to determine whether to add a new segment.

[0103] S1033, determining whether to add a new segment, and adding a new image segment when the total span of the current frame segments exceeds a second threshold; and returning the total span of the current frame segments to zero.

[0104] Determine whether to add a new fragment. Compare the current frame with the previous frame. Only some pixels are new image information. When the accumulated new image information is large, this part constitutes a new fragment. Whether to add a new fragment is determined by the displacement of the current frame and the accumulated fragment span of the previous frame. If a new fragment is needed, calculate the height of the new fragment and record the brightness information, diagonal coordinates and fragment height value of the fragment in the memory.

[0105] Determine whether to add a new segment. Compare the current frame with the previous frame. Only some pixels are new image information. When the accumulated new image information is large, this part constitutes a new segment. Whether to generate a new segment depends mainly on the current frame displacement in step (2) and the accumulated segment span of the previous frame. If the total span of the current frame segment reaches the threshold, it means that a new segment needs to be added. In the present invention, the threshold can be set to -2, and a negative value indicates reversing. The height h of the newly added segment generally needs to meet the following points: first, h must be greater than or equal to the total span of the current frame, that is, the segment height must completely cover the newly added image information; secondly, in order to avoid gaps caused by image jitter, one more line of image information can be added to the newly added segment in each of the upper and lower lines; since the image is a YCbCr image, the segment height should be an even number to avoid missing pixel information. In addition to the segment height, the brightness value of each pixel in the newly added segment, the diagonal coordinates of the entire segment and other information must also be recorded in the memory.

[0106] Similarly, whether there are new fragments is also determined based on the current frame displacement calculated above and the cumulative fragment span of the previous frame. If the result exceeds the threshold, it means that a new fragment is needed, then the cumulative fragment span of the previous frame and the displacement of this frame are used to calculate the fragment height, so there is no cumulative span of the previous frame for the next frame, that is, for the next frame, the cumulative span of the previous frame = 0; if the threshold is not reached, then the cumulative span value of the previous frame must be updated to (the cumulative span of the previous frame + the displacement of this frame), which is used to determine whether the total span reaches the threshold in the next frame. The fragment height is to ensure that all updated rows are covered, so it is actually slightly larger than the total displacement.

[0107] S1034. Update the diagonal coordinates of all segments.

[0108] Update the diagonal coordinates of all fragments. For each fragment, its diagonal coordinate data needs to be recorded so that it can be mapped to the specified position when the fragment is inserted into the bottom perspective view of the vehicle. The diagonal coordinates are constantly changing with the movement of the vehicle, so the diagonal coordinates of all fragments need to be updated in each frame according to the vehicle speed and turning angle to ensure the mapping accuracy.

[0109] Update the diagonal coordinates of all fragments. The turning angle and speed of the vehicle are constantly changing during the movement of the vehicle, and the position of the fragments filled into the bottom perspective view is also changing. Therefore, the diagonal coordinates of all fragments need to be updated according to the speed and turning angle in each frame to ensure the accuracy of the mapping. Figure 6 In the figure, a segment with a height of h moves according to the current frame, and the corresponding diagonal coordinates are shown in the figure. For all segments, the new diagonal coordinate values ​​need to be recalculated.

[0110] After updating the diagonal coordinates, if the fragment exceeds the image range, the fragment is invalid. If the number of stored fragments or the cumulative number of stored pixel rows exceeds the memory setting, the earliest stored image fragment is deleted.

[0111] S1035, inserting the vehicle model image, the background image, the rear view image and the fragment image into corresponding positions of the vehicle bottom perspective image to synthesize the vehicle bottom perspective image.

[0112] Synthesize the bottom perspective view of the vehicle. In the bottom perspective view of the vehicle, insert the car model image, background image, rear view image and fragments into the corresponding positions of the bottom perspective view of the vehicle. The rear view is the top view obtained after the image taken by the wide-angle lens installed at the rear of the vehicle is calibrated and homographically transformed. The fragment image is refreshed or not, and the fragment image of the previous frame is selected or each fragment in the memory is mapped to the specified position of the bottom perspective view in sequence.

[0113] Synthesize the bottom perspective view. The image captured by the camera in the bottom perspective view mainly consists of the fragment image and the rear view. The rear view is the current frame that is corrected by the fisheye and mapped into the top view. This part is to fill the complete rear view camera image into the bottom perspective view after correction and mapping. If the display needs to be refreshed, the fragment image is mapped to the bottom perspective view after all the fragments update the diagonal coordinates. If no refresh is required, this part can be the previous frame image. The car model image is drawn to a fixed position in the bottom perspective view. A semi-transparent image can be used to avoid the fragment occupying the original car model position during the reversing process, which affects the image display. The other parts are background images. Initially, there is no image content and it can be filled with gray. As the reversing process progresses, new fragments are continuously added to the image, which can gradually replace the background points.

[0114] The embodiment of the present invention further provides a vehicle bottom perspective display device, comprising:

[0115] A distortion correction module is used to perform distortion correction on fisheye images taken by a single wide-angle lens;

[0116] A mapping acquisition module, used for acquiring a corresponding top view angle through homography matrix mapping of the image processed by the distortion correction module;

[0117] The image stitching module is used to stitch and update each frame of the acquired top-view image in real time to obtain a perspective image of the bottom of the vehicle; the image stitching module is specifically used to:

[0118] After the coordinate system is updated, the coordinate transformation is determined, and the coordinate position of the pixel point of the previous frame image in the current frame is determined according to the vehicle speed and the front wheel turning angle of the vehicle;

[0119] Determine whether to refresh the display, and refresh the display when the total displacement of the coordinate axis of the current frame exceeds the first threshold;

[0120] Determine whether to add a new segment, and add a new image segment when the total span of the current frame segments exceeds a second threshold;

[0121] Update all fragment diagonal coordinates;

[0122] The vehicle model image, background image, rear view image and fragment image are inserted into corresponding positions of the vehicle bottom perspective image to synthesize the vehicle bottom perspective image.

[0123] It should be noted that: when the vehicle bottom perspective display device provided in the above embodiment is calibrated, only the division of the above program modules is used as an example. In actual application, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the above-described processing. In addition, the vehicle bottom perspective display device provided in the above embodiment and the vehicle bottom perspective display method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, and the beneficial effects are the same as the method embodiment, which will not be repeated here.

[0124] The embodiment of the present invention further provides a computer storage medium, which is a computer-readable storage medium, on which a computer program is stored, and the computer program can be executed by a processor of a computer device to complete the steps of the above-mentioned vehicle bottom perspective display method. The computer-readable storage medium can be a magnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disk, or a compact disk read-only memory (CD-ROM) and the like.

[0125] An embodiment of the present invention further provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned underbody perspective display method when executing the computer program.

[0126] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and intelligent devices can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0127] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0128] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A vehicle bottom perspective display method, characterized in that: include: Perform distortion correction on the fisheye image taken by a single wide-angle lens; The corresponding top view is obtained by mapping the corrected image through the homography matrix; Each frame of the acquired top-view image is stitched and updated in real time to obtain a perspective image of the vehicle bottom; Specifically include: After the coordinate system is updated, the coordinate transformation is performed to determine the coordinate position of the pixel point of the previous frame image in the current frame according to the vehicle speed and the front wheel turning angle of the vehicle, specifically including: determining the body turning angle according to the front wheel turning angle of the vehicle and the vehicle speed; using the following expression Where angle is the front wheel angle, da is the body angle, vt is the vehicle speed, H is the distance between the front wheel and the rear wheel, and R is the turning radius; update the coordinate system to determine the pixel displacement of the origin of the coordinate system in the x and y directions between the current frame and the previous frame; use the following expression dx=vt*ts*cos(b) dy=vt*ts*sin(b) Where da is the body angle, vt is the vehicle speed, ts is the time difference between two frames, and h is the pixel distance from the rear wheel of the vehicle to the origin of the coordinate system; calculate and update the coordinate value of the pixel point of the previous frame image in the current frame; assume that the position coordinate (oldX, oldY) in the coordinate system of the previous frame, due to the vehicle turning, the corresponding coordinate (newX, newY) in the new coordinate system satisfies the following Among them, da = θ + a, newY = r * sin(a) + dy + SHM da=θ+a;wherein (SWT / 2,SHM) is the pixel coordinate value of the origin of the coordinate axis in the bottom perspective view of the vehicle; Determine whether to refresh the display, and refresh the display when the total displacement of the coordinate axis of the current frame exceeds the first threshold; Determine whether to add a new segment, and add a new image segment when the total span of the current frame segments exceeds a second threshold; Update all fragment diagonal coordinates; Insert the car model image, background image, rear view image and fragment image into corresponding positions of the vehicle bottom perspective image to synthesize the vehicle bottom perspective image.

2. The method according to claim 1, characterized in that The first threshold is 1; the second threshold is -2.

3. The method according to claim 1, characterized in that For the newly added image segment, one line of image information is added in each of the uplink and downlink.

4. A vehicle bottom perspective display device, characterized in that: include: A distortion correction module is used to perform distortion correction on fisheye images taken by a single wide-angle lens; A mapping acquisition module, used for acquiring a corresponding top view angle through homography matrix mapping of the image processed by the distortion correction module; The image stitching module is used to stitch and update each frame of the acquired top-view image in real time to obtain a perspective image of the bottom of the vehicle; the image stitching module is specifically used to: After the coordinate system is updated, the coordinate transformation is determined, and the coordinate position of the pixel point of the previous frame image in the current frame is determined according to the vehicle speed and the front wheel turning angle of the vehicle; specifically, the body turning angle is determined according to the front wheel turning angle and the vehicle speed; the following expression is used Where angle is the front wheel angle, da is the body angle, vt is the vehicle speed, H is the distance between the front wheel and the rear wheel, and R is the turning radius; update the coordinate system to determine the pixel displacement of the origin of the coordinate system in the x and y directions between the current frame and the previous frame; use the following expression dx=vt*ts*cos(b) dy=vt*ts*sin(b) Where da is the body angle, vt is the vehicle speed, ts is the time difference between two frames, and h is the pixel distance from the rear wheel of the vehicle to the origin of the coordinate system; calculate and update the coordinate value of the pixel point of the previous frame image in the current frame; assume that the position coordinate (oldX, oldY) in the coordinate system of the previous frame, due to the vehicle turning, the corresponding coordinate (newX, newY) in the new coordinate system satisfies the following Among them, da = θ + a, newY = r * sin(a) + dy + SHM da=θ+a;wherein (SWT / 2,SHM) is the pixel coordinate value of the origin of the coordinate axis in the bottom perspective view of the vehicle; Determine whether to refresh the display, and refresh the display when the total displacement of the coordinate axis of the current frame exceeds the first threshold; Determine whether to add a new segment, and add a new image segment when the total span of the current frame segments exceeds a second threshold; Update all fragment diagonal coordinates; The vehicle model image, background image, rear view image and fragment image are inserted into corresponding positions of the vehicle bottom perspective image to synthesize the vehicle bottom perspective image.

5. The device according to claim 4, characterized in that The first threshold is 1; the second threshold is -2.

6. The device according to claim 4, characterized in that For the newly added image segment, one line of image information is added in each of the uplink and downlink.

7. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle bottom perspective display method according to any one of claims 1 to 3 is implemented.

8. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the vehicle bottom perspective display method according to any one of claims 1 to 3 is implemented.

Images