A method, apparatus, and autonomous driving device for generating a panoramic image

Abstract

An embodiment of the present application provides a method, an apparatus, and an autonomous driving device for generating a panoramic image, which are applied to the technical field of computer graphics. The method includes: obtaining specified device information of a target driving device; where the specified device information includes the device state and / or road condition information of the driving device; based on the correspondence between the preset specified device information and the parameter adjustment strategy, determining, from the preset parameter adjustment strategies, the parameter adjustment strategy corresponding to the obtained specified device information; where each parameter adjustment strategy is an adjustment strategy for the model parameters of the surround view model; using the determined parameter adjustment strategy to adjust the model parameters of the surround view model to be adjusted in the target driving device to obtain an adjusted surround view model; and using the adjusted surround view model to generate a panoramic image of the target driving device. Through this solution, it is possible to ensure that the panoramic image in the panoramic surround view adapts to different surround view observation requirements.

Description

Technical Field

[0001] This application relates to the technical field of computer graphics, and particularly to a method, device, and autonomous driving device for generating panoramic images. Background Art

[0002] Panoramic surround view is a technology for displaying panoramic images around a moving device. In related technologies, image data of the scene around the moving device is collected by multiple cameras installed around the moving device, and then the image data collected by the multiple cameras is mapped to a fixed surround view model to obtain a panoramic image. Exemplarily, as Figure 1 shown, it is a schematic diagram of a panoramic image.

[0003] In related technologies, since a fixed surround view model is used to map image data, the field of view in each direction of the obtained panoramic image is fixed, which cannot meet the surround view requirements of different angular image fields needed by the driver during the process of driving the moving device in the face of different device states and road conditions. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method, device, and autonomous driving device for generating panoramic images, so that the panoramic images in panoramic surround view can adapt to different surround view observation requirements. The specific technical solutions are as follows:

[0005] In a first aspect, the embodiments of this application provide a method for generating a panoramic image, and the method includes:

[0006] Obtain specified device information of a target moving device; wherein, the specified device information includes the device state of the moving device and / or road condition information;

[0007] Based on the corresponding relationship between the preset specified device information and the parameter adjustment strategy, determine, from the preset parameter adjustment strategies, the parameter adjustment strategy corresponding to the obtained specified device information; wherein each parameter adjustment strategy is an adjustment strategy for the model parameters of the surround view model;

[0008] Use the determined parameter adjustment strategy to adjust the model parameters of the surround view model to be adjusted in the target moving device to obtain an adjusted surround view model;

[0009] Use the adjusted surround view model to generate a panoramic image of the target moving device.

[0010] Optionally, the model parameters include at least one of the length, width, height, model curvature, and point cloud density of the surround view model.

[0011] Optionally, the device state includes at least one of a reverse state, a slow driving state, and a fast driving state; the road condition information includes at least one of a congested road condition, a fast road condition, and an urban road condition; the target driving device includes a front view surround view model, a rear view surround view model, a left view surround view model, and a right view surround view model;

[0012] In the correspondence relationship between the preset specified device information and the parameter adjustment strategy, the parameter adjustment strategy corresponding to the reverse state includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the length and / or the model curvature of the left view surround view model and / or the right view surround view model; increasing the height, width, and / or length of the rear view surround view model;

[0013] The parameter adjustment strategy corresponding to the slow driving state includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the height, width, and / or length of the front view surround view model;

[0014] The parameter adjustment strategy corresponding to the fast driving state includes: increasing the height and / or width of the front view surround view model;

[0015] The parameter adjustment strategy corresponding to the congested road condition includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the model curvature of the left view surround view model and / or the right view surround view model; increasing the height and / or width of the front view surround view model and / or the rear view surround view model;

[0016] The parameter adjustment strategy corresponding to the fast road condition includes: increasing the height and / or width of the front view surround view model;

[0017] The parameter adjustment strategy corresponding to the urban road condition includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the height and / or width of the front view surround view model.

[0018] Optionally, before adjusting the model parameters of the surround view model to be adjusted in the target driving device by using the determined parameter adjustment strategy to obtain the adjusted surround view model, the method includes:

[0019] Determine, from the multiple surround view models included in the target driving device, the surround view model that matches the specified observation angle as the surround view model to be adjusted; wherein, the specified observation angle is the angle for observing the displayed panoramic image.

[0020] Optionally, the multiple panoramic view models include: a front panoramic view model, a rear panoramic view model, a left panoramic view model, and a right panoramic view model;

[0021] Determining, from the multiple panoramic view models included in the target driving device, a panoramic view model that matches a specified viewing angle as the panoramic view model to be adjusted includes:

[0022] When the specified viewing angle is a left viewing angle, determining the front panoramic view model and the right panoramic view model as the panoramic view models to be adjusted from the multiple panoramic view models;

[0023] When the specified viewing angle is a right viewing angle, determining the front panoramic view model and the left panoramic view model as the panoramic view models to be adjusted from the multiple panoramic view models.

[0024] Optionally, obtaining the specified device information of the target driving device includes:

[0025] When the specified device information includes the device state, based on the corresponding relationship between the preset driving speed and the device state, determining the device state corresponding to the current driving speed of the target driving device as the device state of the target driving device;

[0026] When the specified device information includes road condition information, based on the current position of the target driving device, querying the road condition information of the section where the current position of the target driving device is located as the road condition information of the target driving device; and / or, based on the image data collected by the camera carried by the target driving device, identifying the road condition information of the target driving device.

[0027] Optionally, before obtaining the specified device information of the target driving device, the method further includes:

[0028] Determining whether the target driving device is currently in an automatic adjustment mode for the panoramic view model;

[0029] If the target driving device is currently in the automatic adjustment mode, then execute obtaining the specified device information of the target driving device;

[0030] If the target driving device is not currently in the automatic adjustment mode, then based on the received parameter adjustment operation for adjusting the panoramic view model parameters, adjusting the model parameters of the panoramic view model to be adjusted in the target driving device to obtain an adjusted panoramic view model.

[0031] Optionally, the target driving device is equipped with multiple cameras, and the target driving device includes multiple panoramic view models, and each panoramic view model corresponds to one camera;

[0032] Using the adjusted panoramic view model to generate a panoramic image of the target driving device, the method further includes:

[0033] For each adjusted panoramic view model, using the adjusted panoramic view model to map the image data collected by the camera corresponding to the adjusted panoramic view model, to obtain a mapped image corresponding to the adjusted panoramic view model;

[0034] Performing a stitching process on the mapped images corresponding to the adjusted panoramic view models to obtain a panoramic image of the target driving device.

[0035] In a second aspect, an embodiment of the present application provides a device for generating a panoramic image, the device includes:

[0036] An information acquisition module, configured to acquire specified device information of the target driving device; wherein, the specified device information includes the device state and / or road condition information in which the driving device is located;

[0037] A policy adjustment module, configured to determine, based on the correspondence between the preset specified device information and parameter adjustment policies, a parameter adjustment policy corresponding to the acquired specified device information from the preset parameter adjustment policies; wherein, each parameter adjustment policy is an adjustment policy for the model parameters of the panoramic view model;

[0038] A parameter adjustment module, configured to use the determined parameter adjustment policy to adjust the model parameters of the panoramic view model to be adjusted in the target driving device, to obtain an adjusted panoramic view model;

[0039] An image generation module, configured to use the adjusted panoramic view model to generate a panoramic image of the target driving device.

[0040] In a third aspect, an embodiment of the present application provides an autonomous driving device, including a processor and a machine-readable storage medium, the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to: implement any one of the method steps in the first aspect.

[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, and a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, it implements any one of the method steps in the first aspect.

[0042] Beneficial effects of the embodiments of the present application:

[0043] In the method for generating a panoramic image provided in the embodiment of the present application, the designated device information of the target driving device can be obtained; wherein the designated device information includes the device state and / or road condition information of the driving device, and then based on the correspondence between the preset designated device information and the parameter adjustment strategy, the parameter adjustment strategy corresponding to the acquired designated device information is determined from the preset parameter adjustment strategies, and the determined parameter adjustment strategy is used to adjust the model parameters of the surround view model to be adjusted in the target driving device to obtain the adjusted surround view model, and the adjusted surround view model is used to generate a panoramic image of the target driving device. Since the device state and / or road condition information of the target driving device can be used to determine the parameter adjustment strategy, and the model parameters of the surround view model can be adjusted using the determined parameter adjustment strategy, the adjusted surround view model can be applied to the surround view observation requirements under the device state and / or road condition information of the target driving device, so that the panoramic image generated using the adjusted surround view model can adapt to different surround view observation requirements.

[0044] Furthermore, since the model parameters of the surround view model can be adaptively adjusted, the distortion in the panoramic image generated by using the adjusted surround view model is reduced, thereby solving the distortion and ghosting problem in the panoramic image in the related art.

[0045] Of course, implementing any product or method of the present application does not necessarily require achieving all of the advantages described above at the same time. Beneficial effects of the embodiments of the present application: BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application 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 application. For drivers with ordinary technical skills in this field, other embodiments can also be obtained based on these drawings.

[0047] Figure 1 is a schematic diagram of a panoramic image;

[0048] Figure 2 A flowchart of a method for generating a panoramic image provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of image acquisition provided in an embodiment of the present application;

[0050] Figure 4a A schematic diagram of the first type of image data provided in an embodiment of the present application;

[0051] Figure 4b A schematic diagram of the second type of image data provided in an embodiment of the present application;

[0052] Figure 4c Schematic diagram of the third type of image data provided by the embodiments of the present application;

[0053] Figure 5 Schematic diagram of a surround view model provided by the embodiments of the present application;

[0054] Figure 6 Schematic diagram of a mapping provided by the embodiments of the present application;

[0055] Figure 7 Schematic diagram of a stitching provided by the embodiments of the present application;

[0056] Figure 8 Another flowchart of the method for generating a panoramic image provided by the embodiments of the present application;

[0057] Figure 9a Schematic diagram of an observation perspective provided by the embodiments of the present application;

[0058] Figure 9b Another schematic diagram of an observation perspective provided by the embodiments of the present application;

[0059] Figure 10 Schematic diagram of a panoramic image provided by the embodiments of the present application;

[0060] Figure 11 Schematic diagram of the structure of a device for generating a panoramic image provided by the embodiments of the present application;

[0061] Figure 12 Schematic diagram of the structure of an autonomous driving device provided by the embodiments of the present application. Detailed implementation manners

[0062] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art based on the present application belong to the scope of protection of the present application.

[0063] Panoramic surround view is a technology for displaying panoramic images around a driving device. In related technologies, image data of the scene around the driving device is collected by multiple cameras installed around the driving device, and then the image data collected by the multiple cameras is mapped to a fixed surround view model, and the mapped images are stitched to obtain a panoramic image. Exemplarily, as Figure 1 shown, it is a schematic diagram of a panoramic image.

[0064] In the related art, since a fixed surround view model is used to map image data, the field of view in all directions of the driving device shown in the obtained panoramic image is fixed. However, during the process of driving the driving device, the driver's surround view observation requirements are different for different device states and road conditions. The surround view observation requirement refers to the driver's requirement for the image field of view in different directions of the driving device when observing the panoramic image. Therefore, how to ensure that the panoramic image in the surround view adapts to different surround view observation requirements is a technical problem that needs to be solved urgently.

[0065] At the same time, in different scenarios, the situation of distortion and ghosting in the panoramic image is different. For example, in an open area, the distortion and ghosting in the panoramic image are abnormally light, while in a crowded area, the distortion and ghosting in the panoramic image are abnormally heavy. Since a fixed surround view model is used to map image data in the related art, there are serious distortion and ghosting problems in the surround view image in some specific scenarios.

[0066] In order to make the panoramic image in the surround view adapt to different surround view observation requirements, the embodiments of the present application provide a method, device, and autonomous driving device for generating a panoramic image.

[0067] It should be noted that in specific applications, the embodiments of the present application can be applied to various autonomous driving devices, such as personal computers, servers, mobile phones, and other devices with data processing capabilities. Moreover, the method for generating a panoramic image provided by the embodiments of the present application can be implemented in a software, hardware, or a combination of software and hardware manner.

[0068] Optionally, in one embodiment, when the driving device is a vehicle, the embodiments of the present application can be applied to vehicle-mounted devices, such as vehicle-mounted central control devices, etc.

[0069] Among them, the method for generating a panoramic image provided by the embodiments of the present application may include:

[0070] Obtain the specified device information of the target driving device; where the specified device information includes the device state and / or road condition information of the driving device;

[0071] Based on the correspondence between the preset specified device information and the parameter adjustment strategy, determine the parameter adjustment strategy corresponding to the obtained specified device information from the preset parameter adjustment strategies; where each parameter adjustment strategy is an adjustment strategy for the model parameters of the surround view model;

[0072] Use the determined parameter adjustment strategy to adjust the model parameters of the surround view model to be adjusted in the target driving device to obtain an adjusted surround view model;

[0073] Use the adjusted surround view model to generate a panoramic image of the target driving device.

[0074] In the above solution of the embodiment of the present application, since the device state and / or road condition information of the target driving device can be used to determine the parameter adjustment strategy, and then the model parameters of the surround view model are adjusted by using the determined parameter adjustment strategy, the adjusted surround view model can be applicable to the surround view observation requirements under the device state and / or road condition information of the target driving device, so that the panoramic image generated by using the adjusted surround view model can adapt to different surround view observation requirements. Further, since the model parameters of the surround view model can be adaptively adjusted, the distortion in the panoramic image generated by using the adjusted surround view model is smaller, and the problem of distortion and ghosting in the panoramic image in the related art is solved.

[0075] Next, the method for generating a panoramic image provided by the embodiment of the present application will be elaborated in detail with reference to the accompanying drawings of the specification.

[0076] As Figure 2 shown, the embodiment of the present application provides a method for generating a panoramic image, including steps S201 - S204, where:

[0077] S201, obtaining specified device information of the target driving device; where the specified device information includes the device state and / or road condition information of the driving device;

[0078] Among them, the above driving device can be a vehicle, a robot, a floor sweeper, or other mobile devices that can drive. When the driving device is a vehicle, the driving device can be an autonomous driving device, or of course a non-autonomous driving device, which is acceptable. The above device state can be the driving state of the driving device, such as a slow driving state, a fast driving state, etc. When the driving device is a vehicle, the above driving state can also be a reverse state, etc. The above road condition information can be the information of the road condition where the driving device is located, such as a congested road condition, a fast road condition, an urban road condition, a highway road condition, etc.

[0079] Generally speaking, when the driving device is in different device states and / or road condition information, the driver's surround view observation requirements are different. Taking the driving device as a vehicle as an example, when the driving device is in the reverse state, the driver needs to observe the road conditions near the left and right wheels and the rear view direction, that is, the surround view observation requirement when the driving device is in the reverse state is to observe the road conditions near the left and right wheels and the rear view direction. When the driving device is in the slow driving state, the driver needs to observe the road conditions near the left and right wheels and the front view direction, that is, the surround view observation requirement when the driving device is in the slow driving state is to observe the road conditions near the left and right wheels and the front view direction. Another example is when the driving device is in a congested road condition, the driver observes the road conditions near the left and right wheels and the front and rear view directions, and the surround view observation requirement when the driving device is in a congested road condition is to observe the road conditions near the left and right wheels and the front view direction.

[0080] Therefore, in order to accurately know the current panoramic observation needs of the driver, the embodiments of the present application may first obtain the specified device information of the target driving device.

[0081] In one implementation manner, when the specified device information includes the device status, the device status corresponding to the current driving speed of the target driving device may be determined based on the preset correspondence between the driving speed and the device status, as the device status of the target driving device. Among them, the correspondence between the driving speed and the device status may be determined based on the actual scenario and requirements. For example, a negative driving speed corresponds to the reverse state; a driving speed of zero corresponds to the stationary state; a driving speed greater than zero and less than the specified speed threshold corresponds to the slow state; a driving speed greater than or equal to the specified speed threshold corresponds to the fast state, etc. Among them, the specified speed threshold may be determined according to requirements. For example, the specified speed threshold is 30 Km / h. When it is necessary to determine the device status of the target driving device, the current driving speed of the target driving device may be read, and then based on the correspondence between the driving speed and the device status, the device status corresponding to the current driving speed of the target driving device may be determined.

[0082] In another implementation manner, when the specified device information includes the road condition information, the road condition information where the target driving device is located may be obtained based on the preset road condition information acquisition method. Among them, the specific method for acquiring the road condition information may include various types. Optionally, it may include at least one of the following methods:

[0083] In the first road condition information acquisition method, the road condition information of the section where the current position of the target driving device is located may be queried based on the current position of the target driving device, as the road condition information where the target driving device is located. For example, when the current position of the target driving device is on a highway, it is determined that it is in a highway road condition. When the current position of the target driving device is in a city, it is determined that it is in a city road condition.

[0084] In the second road condition information acquisition method, the road condition information where the target driving device is located may be identified based on the image data collected by the camera carried by the target driving device. As Figure 3 shown, the embodiments of the present application provide a schematic diagram of image acquisition. Four fisheye cameras are deployed around the target driving device. Figure 3 Among them, the front view, rear view, left view, and right view respectively represent the front view camera, rear view camera, left view camera, and right view camera deployed in the target driving device. Each camera can obtain the image data of the environment where the target driving device is located in real time, and then the road condition information where the target driving device is located may be identified by using the obtained image data.

[0085] Optionally, in this method, the distribution of each specified object in the image data can be recognized, and then based on the object distribution, the road condition information of the target driving device can be determined. The above-mentioned specified objects can be driving devices, roads, buildings, etc. As Figure 4a shown, the embodiment of the present application provides a schematic diagram of the first type of image data. There are many driving devices in the figure, which is a congested road condition. As Figure 4b shown, the embodiment of the present application provides a schematic diagram of the second type of image data. The figure contains a road, and the pixel displacement between adjacent image data is large, which is a fast road condition. As Figure 4c shown, the embodiment of the present application provides a schematic diagram of the third type of image data. There are many urban buildings in the figure, which is an urban road condition.

[0086] Optionally, in this method, the obtained image data can also be input into a pre-trained image semantic segmentation training model to identify the road condition information of the target driving device.

[0087] S202. Based on the corresponding relationship between the preset specified device information and the parameter adjustment strategy, determine the parameter adjustment strategy corresponding to the obtained specified device information from the preset parameter adjustment strategies;

[0088] Among them, each parameter adjustment strategy is an adjustment strategy for the model parameters of the surround view model. Among them, the surround view models included in the target driving device can include various types of surround view models, such as a front surround view model, a rear surround view model, a left surround view model, and a right surround view model. The model parameters of each surround view model can include at least one of the length, width, height, model curvature, and point cloud density of the surround view model. Exemplarily, as Figure 5 shown, the embodiment of the present application provides a schematic diagram of a surround view model. The length, width, height, and curvature (i.e., model curvature) of the surround view model are marked in the figure. The point cloud density of the surround view model can be understood as the sparsity of the grid of the surround view model in the figure.

[0089] Each specified device information has a corresponding parameter adjustment strategy. In the present application, the corresponding relationship between the specified device information and the parameter adjustment strategy is pre-constructed. The parameter adjustment strategy corresponding to each specified device information can be determined according to the surround view observation requirements under this specified device information.

[0090] In the corresponding relationship between the preset specified device information and the parameter adjustment strategy, the following situations may be included:

[0091] A. The parameter adjustment strategy corresponding to the reverse state includes at least one of the following adjustment methods:

[0092] A1. Reduce the width of the left surround view model and / or the right surround view model;

[0093] In this method, the width of the left panoramic view model and / or the right panoramic view model can be adjusted to a preset low width value, or a specified width value can be decreased based on the current width. The specified width value can be a preset value or data determined according to the current width, such as 1% of the current width value.

[0094] A2. Increase the length and / or the model curvature of the left panoramic view model and / or the right panoramic view model;

[0095] In one implementation, increasing the length of the left panoramic view model and / or the right panoramic view model may include: adjusting the length of the left panoramic view model and / or the right panoramic view model to a preset high length value, or increasing a specified length value based on the current length. The specified length value can be a fixed value or data determined according to the current length, for example, 1% of the current length value.

[0096] In one implementation, increasing the model curvature of the left panoramic view model and / or the right panoramic view model may include: adjusting the model curvature of the left panoramic view model and / or the right panoramic view model to a preset high curvature value, or increasing a specified curvature value based on the current model curvature. The specified curvature value can be a fixed value or data determined according to the current model curvature, for example, 1% of the current model curvature value.

[0097] A3. Increase the height, width, and / or length of the rear panoramic view model;

[0098] In this method, the rear panoramic view model can be adjusted to a preset high height value, high width value, and / or high length value, or a specified height value, specified width value, and / or specified length value can be increased based on the current height, width, and / or length. The specified height, specified width value, and / or specified length value can be a preset value or data determined according to the current height, current width, and / or current length, such as 1% of the current height, current width, and / or current length value.

[0099] B. The parameter adjustment strategy corresponding to the slow driving state includes at least one of the following adjustment methods:

[0100] B1. Reduce the relatively narrow width of the left panoramic view model and / or the right panoramic view model;

[0101] In this method, the left panoramic view model and / or the right panoramic view model can be adjusted to a preset low width value, or a specified width value can be decreased based on the current width.

[0102] B2. Increase the height, width, and / or length of the front panoramic view model;

[0103] In this method, the height, width, and / or length of the front view panoramic model can be adjusted to a preset higher height value, higher width value, and / or higher length value, or on the basis of the current height, width, and / or length, increase the specified height value, specified width value, and / or specified length value.

[0104] C. The parameter adjustment strategy corresponding to the fast driving state includes: increasing the height and / or width of the front view panoramic model;

[0105] In this method, the height and / or width of the front view panoramic model can be adjusted to a preset higher height value and / or higher width value, or on the basis of the current height / or current width, increase the specified height value and / or specified width value.

[0106] D. The parameter adjustment strategy corresponding to the congested road condition includes at least one of the following adjustment methods:

[0107] D1. Reduce the width of the left view panoramic model and / or the right view panoramic model;

[0108] In this method, the left view panoramic model and / or the right view panoramic model can be adjusted to a preset low width value, or on the basis of the current width, reduce the specified width value.

[0109] D2. Increase the model curvature of the left view panoramic model and / or the right view panoramic model;

[0110] In this method, the model curvature of the left view panoramic model and / or the right view panoramic model can be adjusted to a preset high curvature value, or on the basis of the current model curvature, increase the specified curvature value.

[0111] D3. Increase the height and / or width of the front view panoramic model and / or the rear view panoramic model;

[0112] In this method, the height and / or width of the front view panoramic model and / or the rear view panoramic model can be adjusted to a preset higher height value and / or higher width value, or on the basis of the current height / or current width, increase the specified height value and / or specified width value.

[0113] E. The parameter adjustment strategy corresponding to the fast road condition includes: increasing the height and / or width of the front view panoramic model;

[0114] In this method, the height and / or width of the front view panoramic model can be adjusted to a preset higher height value and / or higher width value, or on the basis of the current height / or current width, increase the specified height value and / or specified width value. The specified height value and / or specified width value can be determined according to the density of vehicles in the environment and / or the current vehicle speed. Optionally, the greater the density and the higher the vehicle speed, the greater the specified height value and / or specified width value.

[0115] F. The parameter adjustment strategy corresponding to urban road conditions includes at least one of the following adjustment methods:

[0116] F1. Reduce the width of the left-looking panoramic view model and / or the right-looking panoramic view model;

[0117] In this method, the left-looking panoramic view model and / or the right-looking panoramic view model can be adjusted to a preset low width value, or on the basis of the current width, a specified width value can be reduced.

[0118] F2. Increase the height and / or width of the front-looking panoramic view model.

[0119] In this method, the height and / or width of the front-looking panoramic view model can be adjusted to a preset higher height value and / or higher width value, or on the basis of the current height / or the sum of the current width, a specified height value and / or a specified width value can be increased.

[0120] It should be noted that the above methods of increasing or decreasing the height, width, length, and / or model curvature can be determined by linear increase or linear decrease. Further, the amplitude of linear increase or linear decrease can be further determined in combination with information such as road section congestion, specified observation angle, road section vehicle density, and current vehicle speed.

[0121] In one implementation, it can also be achieved by switching models. Optionally, when the specified device information includes the device status, as shown in Table 1 below, the corresponding parameter adjustment strategy can be:

[0122] Table 1

[0123]

[0124]

[0125] When the specified device information includes road condition information, as shown in Table 2 below, the corresponding parameter adjustment strategy can be:

[0126] Table 2

[0127]

[0128] The above-mentioned specified observation angle is the angle for observing the displayed panoramic image, and the embodiments of the present application will be described in subsequent embodiments.

[0129] S203. Using the determined parameter adjustment strategy, adjust the model parameters of the panoramic view model to be adjusted in the target driving device to obtain an adjusted panoramic view model;

[0130] After the parameter adjustment strategy is determined, the model parameters of the surround view model to be adjusted in the target driving device can be adjusted to obtain the adjusted surround view model. Optionally, the spatial coordinate position (x, y, z) of each point cloud in the surround view model can be calculated in parallel based on the adjusted model parameters of each surround view model. Optionally, the following formula can be used for calculation:

[0131]

[0132] Among them, a is the length of the model, b is the width of the model, c is the height of the model, r represents the model curvature of the model, k represents the distribution density of the model point cloud, the x value range is [-a / 2, a / 2], and the y value range is [-b / 2, b / 2].

[0133] S204: Generate a panoramic image of the target driving device using the adjusted surround view model.

[0134] After obtaining the adjusted surround view model, the adjusted surround view model can be used to generate a panoramic image of the target driving device. In one case, the target driving device can carry multiple cameras, and the surround view model used by the target driving device includes multiple types of surround view models, and each type of surround view model corresponds to one camera;

[0135] At this time, for each type of adjusted surround view model, the adjusted surround view model can be used to map the image data collected by the camera corresponding to the adjusted surround view model to obtain the mapped image corresponding to the adjusted surround view model, and then the mapped images corresponding to each adjusted surround view model can be spliced ​​to obtain a panoramic image of the target driving equipment.

[0136] like Figure 6 As shown, an embodiment of the present application provides a mapping schematic diagram. The camera coordinate system in the image is the coordinate system of the camera that collects the image data, the image coordinate system is the imaging coordinate system of the image data, and the world coordinate system can be the coordinate system where the surround view model is located. The figure shows the mapping process from the camera coordinate system to the imaging coordinate system and the world coordinate system. After obtaining the image data, the image data (generally the original image data collected by the fisheye camera) can be mapped to the surround view model based on the internal and external parameters of the camera and the spatial coordinate distribution of the adjusted surround view model, using the Zhang calibration method of the imaging of the pinhole camera and the distortion correction algorithm. Optionally, the coordinates of the adjusted surround view model in the world coordinate system can be first converted to the coordinates in the camera coordinate system of the camera, and then converted to the image coordinates in the image coordinate system, so as to realize the mapping of three-dimensional space coordinate points to two-dimensional image pixel point coordinates.

[0137] After the mapping is completed, the image data after different mappings can be spliced. Figure 7As shown in the figure, an embodiment of the present application provides a splicing schematic diagram. After the front view surround view model, the rear view surround view model, the left view surround view model, and the right view surround view model are sequentially constructed and image mapped on a GPU (Graphics Processing Unit), image fusion is performed in ways such as overlapping coverage, overlapping transparent blending, and overlapping color blending. For example, for the overlapping area of the four-way surround view model images, image fusion is performed using a gradient transparency value to quickly output a complete panoramic image under the currently specified observation angle.

[0138] In the above solution of the embodiment of the present application, since the device state and / or road condition information of the target driving device can be used to determine a parameter adjustment strategy, and then the determined parameter adjustment strategy is used to adjust the model parameters of the surround view model, the adjusted surround view model can be adapted to the surround view observation requirements under the device state and / or road condition information of the target driving device, so that the panoramic image generated using the adjusted surround view model can adapt to different surround view observation requirements.

[0139] In one embodiment, the surround view models used by the above target driving device include multiple types of surround view models, and each parameter adjustment strategy includes multiple parameter adjustment strategies for each type of surround view model;

[0140] At this time, as Figure 8 shown, an embodiment of the present application provides a method for generating a panoramic image, including steps S801 - S805:

[0141] S801, obtain the specified device information of the target driving device; wherein, the specified device information includes the device state and / or road condition information where the driving device is located;

[0142] This step is the same as or similar to step S201, and the specific implementation manner can refer to the relevant description of step S201. The embodiments of the present application will not elaborate herein.

[0143] S802, determine the surround view model to be adjusted from the multiple types of surround view models included in the target driving device as the surround view model to be adjusted;

[0144] There are various ways to determine the surround view model to be adjusted from the multiple types of surround view models used by the target driving device. Optionally, at least one of the following two ways is included:

[0145] In the first surround view model determination method, multiple types of surround view models included in the target driving device can be used as the surround view models to be adjusted.

[0146] In the second way of determining the panoramic view model, a panoramic view model that matches the specified observation angle can be determined from various types of panoramic view models included in the target driving device as the panoramic view model to be adjusted.

[0147] Among them, the specified observation angle is the angle used to observe the displayed panoramic image. In one implementation, the panoramic view models used by the target driving device include: a front panoramic view model, a rear panoramic view model, a left panoramic view model, and a right panoramic view model. At this time, when the specified observation angle is the left observation angle, the front panoramic view model and the right panoramic view model can be determined from various types of panoramic view models as the panoramic view models to be adjusted; when the specified observation angle is the right observation angle, the front panoramic view model and the left panoramic view model are determined from various types of panoramic view models as the panoramic view models to be adjusted.

[0148] The user can adjust the three-dimensional observation angle in the panoramic view to observe the environment around the vehicle body from different angles. At different angles, the requirements for the observation field of the panoramic view model are different. For example Figure 9a As shown, the embodiment of the present application provides a schematic diagram of an observation angle. The specified observation angle mainly observes the front view and the right view images. At this time, the fields of view of the front view and the right view models need to be adjusted; as Figure 9b shown, the embodiment of the present application provides another schematic diagram of an observation angle. The specified observation angle mainly observes the front view and the left view images. At this time, the fields of view of the front view and the left view models need to be adjusted.

[0149] S803. Based on the correspondence relationship between the preset specified device information and the parameter adjustment strategy, determine the parameter adjustment strategy corresponding to the obtained specified device information from the preset parameter adjustment strategies.

[0150] In this step, after determining the panoramic view model to be adjusted, only the model parameters of the panoramic view model to be adjusted can be adjusted. Optionally, based on the correspondence relationship between the preset specified device information and the parameter adjustment strategy, the parameter adjustment strategy corresponding to the obtained specified device information can be determined from the multiple parameter adjustment strategies for the panoramic view model to be adjusted. Therefore, compared with the method of adjusting all panoramic view models, computing power can be saved, thereby improving the efficiency of panoramic image generation.

[0151] S804. Use the determined parameter adjustment strategy to adjust the model parameters of the panoramic view model to be adjusted in the target driving device to obtain the adjusted panoramic view model.

[0152] This step is the same as or similar to step S203. The specific implementation method can refer to the relevant description of step S203, and the embodiments of the present application will not be elaborated here.

[0153] S805. Use the adjusted panoramic view model to generate the panoramic image of the target driving device.

[0154] This step is the same as or similar to step S204. For the specific implementation method, reference can be made to the relevant description of step S204, and it will not be elaborated in this embodiment of the present application.

[0155] In the above solution of this embodiment of the present application, the panoramic image can be adapted to different surround-view observation requirements, and at the same time, the surround-view model to be adjusted can be determined from various types of surround-view models included in the target driving device, so that a parameter adjustment strategy corresponding to the obtained specified device information can be determined. Compared with the method of adjusting all surround-view models, it can save computing power and thus improve the efficiency of panoramic image generation.

[0156] In one embodiment, before obtaining the specified device information of the target driving device, it can also be determined whether the target driving device is currently in the automatic adjustment mode for the surround-view model; if the target driving device is currently in the automatic adjustment mode, then obtain the specified device information of the target driving device.

[0157] Based on this, in one embodiment, before generating the panoramic image of the target driving device using the adjusted surround-view model, if the target driving device is not currently in the automatic adjustment mode, the model parameters of the surround-view model to be adjusted in the target driving device can be adjusted based on the received parameter adjustment operation for adjusting the surround-view model parameters to obtain the adjusted surround-view model.

[0158] At this time, the driver can manually set parameters such as the length, width, height, and curvature of each model according to the current specified observation angle and field of view requirements. For example, when the user observes the front view and wants to increase the front view field of view, the height and width of the front surround-view model can be manually increased to observe a higher and wider field of view scene at the current specified observation angle.

[0159] In one implementation, the adjustment methods of the surround-view model can be divided into three types, namely manual mode, fixed mode, and adaptive mode.

[0160] 1. Manual mode:

[0161] The user can manually set parameters such as the length, width, height, and curvature of each model according to the current specified observation angle and field of view requirements. For example, when the user observes the front view and wants to increase the front view field of view, the height and width of the front surround-view model can be manually increased to observe a higher and wider field of view scene at the current specified observation angle.

[0162] 2. Fixed mode:

[0163] The surround-view model can match a fixed mode according to the device state of the target driving device to assist the driver in observing the road conditions around the vehicle body.

[0164] 3. Adaptive mode:

[0165] In the adaptive mode, parameters such as the length, width, height, and curvature of the surround view model can be automatically adjusted according to road condition information and a specified observation perspective.

[0166] Among them, the specific implementation manners of the fixed mode and the adaptive mode have been described in the foregoing embodiments and will not be elaborated herein.

[0167] In the above solution of the embodiment of the present application, the panoramic image can adapt to different surround view observation requirements. At the same time, a manual model parameter adjustment mode is also provided, thereby enriching the adjustment methods of the parameter mode and enabling the user to adjust the parameters of the surround view model according to their own needs.

[0168] As Figure 10 shown, the embodiment of the present application provides a schematic diagram of a panoramic image generated by using the solution of the embodiment of the present application. Compared with Figure 1 that, the distortion in the image of the panoramic image generated by using the solution of the embodiment of the present application is smaller, and the field of view range more meets the current needs of the user.

[0169] Corresponding to the panoramic image generation method provided in the above embodiment of the present application, as Figure 11 shown, the embodiment of the present application further provides a panoramic image generation device, and the device includes:

[0170] A vehicle information acquisition module 1101, configured to acquire specified device information of a target driving device; wherein, the specified device information includes the device state and / or road condition information of the driving device;

[0171] A strategy adjustment module 1102, configured to determine, based on the correspondence between the preset specified device information and parameter adjustment strategies, a parameter adjustment strategy corresponding to the acquired specified device information from the preset parameter adjustment strategies; wherein each parameter adjustment strategy is an adjustment strategy for the model parameters of the surround view model;

[0172] A parameter adjustment module 1103, configured to adjust the model parameters of the surround view model to be adjusted in the target driving device by using the determined parameter adjustment strategy to obtain an adjusted surround view model;

[0173] An image generation module 1104, configured to generate a panoramic image of the target driving device by using the adjusted surround view model.

[0174] Optionally, the model parameters include at least one of the length, width, height, model curvature, and point cloud density of the surround view model.

[0175] Optionally, the device status includes at least one of a reverse state, a slow driving state, and a fast driving state; the road condition information includes at least one of a congested road condition, a fast road condition, and an urban road condition; the target driving device includes a front view surround view model, a rear view surround view model, a left view surround view model, and a right view surround view model;

[0176] In the correspondence relationship between the preset specified device information and the parameter adjustment strategy, the parameter adjustment strategy corresponding to the reverse state includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the length and / or the model curvature of the left view surround view model and / or the right view surround view model; increasing the height, width, and / or length of the rear view surround view model;

[0177] The parameter adjustment strategy corresponding to the slow driving state includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the height, width, and / or length of the front view surround view model;

[0178] The parameter adjustment strategy corresponding to the fast driving state includes: increasing the height and / or width of the front view surround view model;

[0179] The parameter adjustment strategy corresponding to the congested road condition includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the model curvature of the left view surround view model and / or the right view surround view model; increasing the height and / or width of the front view surround view model and / or the rear view surround view model;

[0180] The parameter adjustment strategy corresponding to the fast road condition includes: increasing the height and / or width of the front view surround view model;

[0181] The parameter adjustment strategy corresponding to the urban road condition includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the height and / or width of the front view surround view model.

[0182] Optionally, the device further includes:

[0183] A model determination module, configured to determine, before the parameter adjustment module executes the adjustment of the model parameters of the surround view model to be adjusted in the target driving device by using the determined parameter adjustment strategy to obtain the adjusted surround view model, a surround view model that matches the specified observation perspective from among the multiple surround view models included in the target driving device as the surround view model to be adjusted; wherein the specified observation perspective is the perspective for observing the displayed panoramic image.

[0184] Optionally, the multiple panoramic view models include: a front panoramic view model, a rear panoramic view model, a left panoramic view model, and a right panoramic view model;

[0185] The model determination module is specifically configured to, when the specified observation angle is the left observation angle, determine the front panoramic view model and the right panoramic view model as the panoramic view models to be adjusted from the multiple panoramic view models; when the specified observation angle is the right observation angle, determine the front panoramic view model and the left panoramic view model as the panoramic view models to be adjusted from the multiple panoramic view models.

[0186] Optionally, the vehicle information acquisition module is specifically configured to, when the specified device information includes the device status, determine the device status corresponding to the current driving speed of the target driving device based on the preset correspondence between the driving speed and the device status as the device status of the target driving device; when the specified device information includes the road condition information, query the road condition information of the section where the current position of the target driving device is located based on the current position of the target driving device as the road condition information of the target driving device; and / or identify the road condition information of the target driving device based on the image data collected by the camera carried by the target driving device.

[0187] Optionally, the device further includes:

[0188] A mode determination module, configured to determine whether the target driving device is currently in an automatic adjustment mode for the panoramic view model; if the target driving device is currently in the automatic adjustment mode, then execute the step of calling the vehicle information acquisition module to acquire the specified device information of the target driving device; if the target driving device is not currently in the automatic adjustment mode, then adjust the model parameters of the panoramic view model to be adjusted in the target driving device based on the received parameter adjustment operation for adjusting the panoramic view model parameters to obtain the adjusted panoramic view model.

[0189] Optionally, the target driving device is equipped with multiple cameras, and the target driving device includes multiple panoramic view models, and each panoramic view model corresponds to one camera;

[0190] The image generation module is specifically configured to, for each adjusted panoramic view model, use the adjusted panoramic view model to map the image data collected by the camera corresponding to the adjusted panoramic view model to obtain the mapped image corresponding to the adjusted panoramic view model; perform stitching processing on the mapped images corresponding to the adjusted panoramic view models to obtain the panoramic image of the target driving device.

[0191] In the above scheme of the embodiment of the present application, since the device status and / or road condition information of the target driving device can be used to determine the parameter adjustment strategy, and then the model parameters of the surround view model are adjusted using the determined parameter adjustment strategy, the adjusted surround view model can be suitable for the surround view observation requirements under the device status and / or road condition information of the target driving device, so that the panoramic image generated by using the adjusted surround view model can adapt to different surround view observation requirements.

[0192] The present application also provides an automatic driving device, such as Figure 12 As shown, it includes a processor 1201 and a machine-readable storage medium 1202, wherein the machine-readable storage medium 1202 stores machine-executable instructions that can be executed by the processor 1201, and the processor 1201 is prompted by the machine-executable instructions to implement the following steps:

[0193] Acquire designated device information of the target driving device; wherein the designated device information includes device status and / or road condition information of the driving device;

[0194] Based on the correspondence between the preset designated device information and the parameter adjustment strategy, determine the parameter adjustment strategy corresponding to the acquired designated device information from the preset parameter adjustment strategies; wherein each parameter adjustment strategy is an adjustment strategy for the model parameters of the surround view model;

[0195] Using the determined parameter adjustment strategy, adjusting the model parameters of the surround view model to be adjusted in the target driving device to obtain an adjusted surround view model;

[0196] The adjusted surround view model is used to generate a panoramic image of the target driving device.

[0197] The above-mentioned autonomous driving equipment may be, but is not limited to, robots, sweepers, autonomous driving vehicles, etc.

[0198] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0199] In another embodiment provided by the present application, a computer-readable storage medium is further provided. A computer program is stored in the computer-readable storage medium. When the computer program is executed by a processor, the steps of any of the above panoramic image generation methods are implemented.

[0200] In another embodiment provided by the present application, a computer program product including instructions is further provided. When it runs on a computer, the computer is made to execute the panoramic image generation method in any of the above embodiments.

[0201] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).

[0202] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0203] Each embodiment in this specification is described in a relevant manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, the autonomous driving device, the computer-readable storage medium, and the computer program product, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0204] The above are only the preferred embodiments of the present application and are not intended to limit the protection scope of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application are all included in the protection scope of the present application.

Claims

1. A method for generating a panoramic image, characterized in that, The method includes: Obtaining specified device information of a target driving device; wherein, the specified device information includes the device state and / or road condition information of the driving device, and the road condition information includes at least one of congested road conditions, fast road conditions, and urban road conditions; Based on the corresponding relationship between the preset specified device information and the parameter adjustment strategy, determining, from the preset parameter adjustment strategies, the parameter adjustment strategy corresponding to the obtained specified device information; wherein, each parameter adjustment strategy is an adjustment strategy for the model parameters of the surround view model; Using the determined parameter adjustment strategy to adjust the model parameters of the surround view model to be adjusted in the target driving device, obtaining an adjusted surround view model; Using the adjusted surround view model to generate a panoramic image of the target driving device.

2. The method according to claim 1, characterized in that, The model parameters include at least one of the length, width, height, model curvature, and point cloud density of the surround view model, and the driving device includes at least one of a vehicle, a robot, and a floor sweeper.

3. The method according to claim 2, wherein The device state includes at least one of a reverse state, a slow driving state, and a fast driving state; the target driving device includes a front view surround view model, a rear view surround view model, a left view surround view model, and a right view surround view model; In the corresponding relationship between the preset specified device information and the parameter adjustment strategy, the parameter adjustment strategy corresponding to the reverse state includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the length and / or model curvature of the left view surround view model and / or the right view surround view model; increasing the height, width, and / or length of the rear view surround view model; The parameter adjustment strategy corresponding to the slow driving state includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; Increasing the height, width, and / or length of the front view surround view model; The parameter adjustment strategy corresponding to the fast driving state includes: increasing the height and / or width of the front view surround view model; The parameter adjustment strategy corresponding to the congested road condition includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the model curvature of the left view surround view model and / or the right view surround view model; increasing the height and / or width of the front view surround view model and / or the rear view surround view model; The parameter adjustment strategy corresponding to the fast road condition includes: increasing the height and / or width of the front view surround view model; The parameter adjustment strategy corresponding to the urban road condition includes at least one of the following adjustment methods: reducing the width of the left view surround view model and / or the right view surround view model; increasing the height and / or width of the front view surround view model.

4. The method according to any one of claims 1-3, characterized in that, Before using the determined parameter adjustment strategy to adjust the model parameters of the surround view model to be adjusted in the target driving device to obtain an adjusted surround view model, the method includes: Determine, from multiple surround-view models included in the target driving device, a surround-view model that matches a specified observation view as the surround-view model to be adjusted; wherein, the specified observation view is a view for observing the displayed panoramic image.

5. The method according to claim 4, characterized in that, The multiple surround-view models include: a front-view surround-view model, a rear-view surround-view model, a left-view surround-view model, and a right-view surround-view model; The determining, from multiple surround-view models included in the target driving device, a surround-view model that matches a specified observation view as the surround-view model to be adjusted includes: When the specified observation view is a left-side observation view, determine, from the multiple surround-view models, the front-view surround-view model and the right-view surround-view model as the surround-view models to be adjusted; When the specified observation view is a right-side observation view, determine, from the multiple surround-view models, the front-view surround-view model and the left-view surround-view model as the surround-view models to be adjusted.

6. The method according to any one of claims 1 to 3, characterized in that, The obtaining of the specified device information of the target driving device includes: When the specified device information includes the device state, based on the corresponding relationship between the preset driving speed and the device state, determine the device state corresponding to the current driving speed of the target driving device as the device state of the target driving device; When the specified device information includes road condition information, based on the current position of the target driving device, query the road condition information of the section where the current position of the target driving device is located as the road condition information of the target driving device; and / or, based on the image data collected by the camera carried by the target driving device, identify the road condition information of the target driving device.

7. The method according to any one of claims 1-3, characterized in that, Before the obtaining of the specified device information of the target driving device, the method further includes: Determine whether the target driving device is currently in an automatic adjustment mode for the surround-view model; If the target driving device is currently in the automatic adjustment mode, then execute the obtaining of the specified device information of the target driving device; If the target driving device is currently not in the automatic adjustment mode, then based on the received parameter adjustment operation for adjusting the surround-view model parameters, adjust the model parameters of the surround-view model to be adjusted in the target driving device to obtain an adjusted surround-view model.

8. The method according to any one of claims 1 to 3, characterized in that, The target driving device carries multiple cameras, and the target driving device includes multiple surround-view models, and each surround-view model corresponds to one camera; When generating the panoramic image of the target driving device by using the adjusted surround-view model, the method further includes: For each adjusted surround-view model, use the adjusted surround-view model to map the image data collected by the camera corresponding to the adjusted surround-view model to obtain the mapped image corresponding to the adjusted surround-view model; Perform stitching processing on the mapped images corresponding to the adjusted surround-view models to obtain the panoramic image of the target driving device.

9. An apparatus for generating a panoramic image, characterized in that, The device includes: A vehicle information acquisition module, used to acquire designated device information of a target driving device; wherein the designated device information includes a device state and / or road condition information of the driving device, and the road condition information includes at least one of a congested road condition, a fast road condition, and an urban road condition; A strategy adjustment module, for determining, from among the preset parameter adjustment strategies, a parameter adjustment strategy corresponding to the acquired designated device information based on a correspondence between the preset designated device information and the parameter adjustment strategy; wherein each parameter adjustment strategy is an adjustment strategy for a model parameter of a surround view model; A parameter adjustment module, used to adjust the model parameters of the surround view model to be adjusted in the target driving device by using the determined parameter adjustment strategy to obtain an adjusted surround view model; An image generation module is used to generate a panoramic image of the target driving device using the adjusted surround view model.

10. An autonomous driving device, characterized in that, The method comprises a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to implement the method steps described in any one of claims 1 to 8.

Images