A panoramic image generation method, apparatus, system and vehicle

Abstract

The application provides a panoramic image generation method, device, system and vehicle, and belongs to the technical field of vehicles. The method comprises the following steps: acquiring original images of a vehicle at at least four preset orientations; merging the original images at the at least four preset orientations to obtain a target image; and sending the target image to a vehicle controller, so that the vehicle controller generates a panoramic image of the vehicle based on the target image. According to the application, the original images are merged into the target image and sent to the vehicle controller, and the vehicle controller completes the calculation and processing of the panoramic image, so that the computing power pressure of the intelligent driving domain controller can be effectively reduced, the computing power resources are more reasonably allocated, and the imaging effect of the panoramic image can be effectively avoided from being affected by the insufficient resources of the intelligent driving domain controller on the premise of ensuring the realization of the intelligent driving, parking and vehicle functions.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a panoramic image generation method, apparatus, system, and vehicle. Background Technology

[0002] With the development of the automotive industry, cars are increasingly integrated into our daily lives and work. Facing various scenarios, intelligent automotive services are becoming an increasingly important highlight and selling point for vehicles. AVM (Around View Monitor) is part of an automatic parking system and is a highly practical function that can significantly improve user experience and driving safety. AVM uses multiple surround-view cameras, such as four ultra-wide-angle fisheye cameras, to capture images. It then performs distortion correction and stitching on the captured images to create a panoramic image, providing the driver with information about the vehicle's surroundings and thus assisting with parking.

[0003] Reference Figure 1 The current implementation scheme of AVM is as follows: four surround view cameras send the raw image information to the intelligent driving domain controller through the first serializer. The intelligent driving domain controller simultaneously performs parking function algorithm and AVM image algorithm processing, and transmits the processed panoramic image to the vehicle controller through the second serializer. The vehicle controller decodes and outputs the panoramic image to the central control screen to complete the panoramic image display.

[0004] The above solution relies on the computing power of the intelligent driving domain controller and the platform's requirements for intelligent driving functions. For low-to-medium computing power platforms, if advanced and rich intelligent driving functions are to be implemented, the intelligent driving controller needs to bear a large computing power pressure. The GPU (Graphics Processing Unit) of the intelligent driving controller will have insufficient resources and other problems, which will ultimately affect the imaging effect of the panoramic image. Summary of the Invention

[0005] This application provides a panoramic image generation method, apparatus, system, and vehicle to address the problem that insufficient computing power resources of intelligent driving controllers affect the imaging effect of panoramic images.

[0006] To solve the above problems, this application adopts the following technical solution:

[0007] In a first aspect, embodiments of this application provide a panoramic image generation method, applied to an intelligent driving domain controller, the method comprising:

[0008] Acquire raw images of the vehicle from at least four preset locations;

[0009] The original images at the at least four preset locations are merged to obtain the target image;

[0010] The target image is sent to the vehicle control unit so that the vehicle control unit can generate a panoramic image of the vehicle based on the target image.

[0011] In one embodiment of this application, the step of merging the original images at at least four preset orientations to obtain a target image includes:

[0012] Based on the directional markers corresponding to the original images at the at least four preset directional locations, the target region corresponding to each original image in the target image is determined.

[0013] Each of the original images is mapped to its corresponding target region to obtain the target image.

[0014] In one embodiment of this application, the step of sending the target image to the vehicle control unit so that the vehicle control unit generates a panoramic image of the vehicle based on the target image includes:

[0015] Obtain the current resource utilization rate of the graphics processor of the intelligent driving domain controller;

[0016] If the current resource occupancy rate is greater than a specified occupancy rate, the target image is sent to the vehicle controller so that the vehicle controller can generate a panoramic image of the vehicle based on the target image.

[0017] Secondly, based on the same inventive concept, embodiments of this application provide a panoramic image generation method, applied to a vehicle infotainment controller, the method comprising:

[0018] Acquire a target image sent by the intelligent driving domain controller. The target image is obtained by the intelligent driving domain controller acquiring original images of the vehicle in at least four preset positions and merging the original images in the at least four preset positions.

[0019] A panoramic image of the vehicle is generated based on the target image.

[0020] In one embodiment of this application, the step of generating a panoramic image of the vehicle based on the target image includes:

[0021] The target image is split to obtain the original images at the at least four preset locations;

[0022] A panoramic image of the vehicle is generated based on the original images from at least four preset orientations.

[0023] In one embodiment of this application, the step of splitting the target image to obtain the original images at at least four preset orientations includes:

[0024] Obtain the directional identifiers corresponding to different target regions in the target image;

[0025] Based on the directional markers corresponding to different target regions in the target image, the target image is split to obtain the original image corresponding to each target region.

[0026] In one embodiment of this application, after the step of generating a panoramic image of the vehicle based on the target image, the method further includes:

[0027] The panoramic image is sent to the central control screen for display.

[0028] Thirdly, based on the same inventive concept, embodiments of this application provide a panoramic image generation device, applied to an intelligent driving domain controller, the device comprising:

[0029] The first acquisition module is used to acquire original images of the vehicle in at least four preset positions;

[0030] An image merging module is used to merge the original images at at least four preset locations to obtain a target image;

[0031] An image sending module is used to send the target image to the vehicle control unit, so that the vehicle control unit can generate a panoramic image of the vehicle based on the target image.

[0032] In one embodiment of this application, the image merging module includes:

[0033] The target region determination submodule is used to determine the target region corresponding to each of the original images in the target image based on the directional identifiers corresponding to the original images at the at least four preset directional positions.

[0034] The image merging submodule is used to map each of the original images to its corresponding target region to obtain the target image.

[0035] In one embodiment of this application, the image sending module includes:

[0036] The resource utilization rate acquisition submodule is used to acquire the current resource utilization rate of the graphics processor of the intelligent driving domain controller;

[0037] The image sending submodule is used to send the target image to the vehicle controller when the current resource occupancy rate is greater than a specified occupancy rate, so that the vehicle controller can generate a panoramic image of the vehicle based on the target image.

[0038] Fourthly, based on the same inventive concept, embodiments of this application provide a panoramic image generation device for use in a vehicle control unit, the device comprising:

[0039] The second acquisition module is used to acquire the target image sent by the intelligent driving domain controller. The target image is obtained by the intelligent driving domain controller acquiring the original images of the vehicle in at least four preset positions and merging the original images in the at least four preset positions.

[0040] An image generation module is used to generate a panoramic image of the vehicle based on the target image.

[0041] In one embodiment of this application, the image generation module includes:

[0042] The splitting submodule is used to split the target image to obtain the original images at the at least four preset positions;

[0043] The image generation submodule is used to generate a panoramic image of the vehicle based on the original images from at least four preset orientations.

[0044] In one embodiment of this application, the splitting submodule includes:

[0045] A directional identifier acquisition unit is used to acquire the directional identifiers corresponding to different target regions in the target image.

[0046] The splitting unit is used to split the target image based on the directional identifiers corresponding to different target regions in the target image, so as to obtain the original image corresponding to each target region.

[0047] In one embodiment of this application, the panoramic image generation device further includes:

[0048] The display module is used to generate a panoramic image of the vehicle based on the target image, and then send the panoramic image to the central control screen for display.

[0049] Fifthly, based on the same inventive concept, embodiments of this application provide an image generation system, the system comprising an intelligent driving domain controller, a vehicle infotainment controller, and surround-view cameras respectively disposed at at least four preset locations on the vehicle; wherein,

[0050] The surround-view camera is used to capture raw images of the vehicle in at least four preset directions and send the raw images in at least four preset directions to the intelligent driving domain controller;

[0051] The intelligent driving domain controller is used to acquire the original images from the at least four preset directions, merge the original images from the at least four preset directions to obtain the target image, and send the target image to the vehicle controller.

[0052] The vehicle controller is used to acquire the target image and generate a panoramic image of the vehicle based on the target image.

[0053] Sixthly, based on the same inventive concept, embodiments of this application provide a vehicle, including an image generation system proposed in the fifth aspect of this application.

[0054] Compared with the prior art, this application has the following advantages:

[0055] This application provides a panoramic image generation method that acquires original images of a vehicle from at least four preset orientations; merges the original images from the at least four preset orientations to obtain a target image; and sends the target image to the vehicle controller, enabling the vehicle controller to generate a panoramic image of the vehicle based on the target image. This application, by merging the original images into a target image and sending it to the vehicle controller, which then performs the panoramic image processing, effectively reduces the computational burden on the intelligent driving domain controller. This results in a more rational allocation of computational resources and, while ensuring the implementation of intelligent driving and parking functions, effectively avoids the impact of insufficient resources in the intelligent driving domain controller on the imaging effect of the panoramic image. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a schematic diagram of data transmission in the current AVM implementation scheme.

[0058] Figure 2 A flowchart illustrating the steps of a panoramic image generation method provided in this application embodiment.

[0059] Figure 3 A flowchart illustrating the steps of another panoramic image generation method provided in this application embodiment.

[0060] Figure 4 This is a schematic diagram of the functional modules of a panoramic image generation device provided in an embodiment of this application.

[0061] Figure 5This is a schematic diagram of the functional modules of another panoramic image generation device provided in an embodiment of this application.

[0062] Figure 6 This is a schematic diagram of the structure of an image generation system provided in an embodiment of this application.

[0063] Figure 7 This is a schematic diagram of the workflow of an image generation system provided in an embodiment of this application.

[0064] Figure 8 This is a structural schematic diagram of the vehicle provided in an embodiment of this application. Detailed Implementation

[0065] The technical solutions in this embodiment will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0066] It's important to note that with the development of the intelligent driving industry, intelligent driving functions are becoming increasingly complex, leading to a significant increase in the demand for intelligent architecture and algorithm computing power in automobiles. This is driving a rapid shift in automotive chips from traditional MCU chips to those equipped with more powerful SoC chips. MCU chips, also known as microcontrollers, typically contain only one processor unit: the CPU (i.e., MCU = CPU + storage + interface unit). SoC, on the other hand, is a system-on-a-chip, generally containing multiple processor units, such as CPU + GPU + DSP + NPU + storage + interface unit.

[0067] The intelligent driving domain controller described in this application is a SoC chip, which not only undertakes the data processing and computing power required for autonomous driving, including but not limited to the data processing of devices such as millimeter-wave radar, cameras, lidar, GPS, and inertial navigation, but also undertakes the security of underlying core data and network data under autonomous driving.

[0068] As the demand for intelligent driving functions in automobiles continues to increase, the computing power pressure on intelligent driving domain controllers is also increasing. For intelligent driving domain controllers with low to medium computing power, problems such as insufficient resources are likely to occur.

[0069] Currently, the implementation schemes of AVM all involve the intelligent driving domain controller performing AVM image algorithm processing, and then sending the processed AVM image to the vehicle controller for display. This approach increases the algorithmic pressure on the intelligent driving domain controller and wastes the computing resources of the vehicle controller, resulting in unreasonable allocation of computing resources. When the computing power resources of the intelligent driving domain controller are insufficient, it can easily affect the imaging effect of the panoramic image.

[0070] To address the shortcomings of the aforementioned background technology, this application aims to provide a panoramic image generation method that, without altering the system hardware structure, allows the vehicle controller to perform the computational processing of the panoramic image. This effectively reduces the computational burden on the intelligent driving domain controller, makes the allocation of computational resources more reasonable, and effectively avoids the impact of insufficient resources of the intelligent driving domain controller on the imaging effect of the panoramic image.

[0071] Reference Figure 2 The diagram illustrates a flowchart of a panoramic image generation method according to this application. Specifically, the method may include the following steps:

[0072] S201: Acquire raw images of the vehicle in at least four preset orientations.

[0073] It should be noted that the implementing entity in this embodiment is the intelligent driving domain controller. Specifically, the intelligent driving domain controller can acquire original images of the vehicle in at least four preset locations using surround-view cameras installed at at least four preset locations. These four preset locations can be set according to actual needs. For example, the four preset locations can be the front, rear, left, and right directions of the vehicle, i.e., the front direction, the rear direction, and the sides. Correspondingly, the surround-view cameras can be installed at the front bumper, trunk, left rearview mirror, and right rearview mirror, respectively.

[0074] In this embodiment, to acquire more information about objects around the vehicle, the surround-view camera can be a fisheye camera, such as a four-way fisheye camera. It should be noted that a fisheye camera is an ultra-wide-angle lens; its field of view can reach or exceed the range visible to the human eye, thus enabling comprehensive acquisition of environmental information from all directions around the vehicle. However, this also leads to unavoidable "barrel distortion." Therefore, when generating panoramic images, the original image needs to be processed using an AVM image algorithm, including distortion correction.

[0075] S202: Merge the original images from at least four preset orientations to obtain the target image.

[0076] In this embodiment, the intelligent driving domain controller will no longer perform AVM image algorithm processing. That is, there is no need to perform complex operations such as distortion correction, joint calibration of four fisheye cameras, projection transformation, bird's-eye view fine-tuning, stitching and fusion, and 3D model texture mapping on the original image. Instead, it only needs to consume a small amount of computing power to merge the original images from at least four preset positions. This not only does not affect the intelligent driving domain controller's original intelligent driving and parking functions, but also effectively saves the computing power space of the intelligent driving domain controller and reduces the computing power pressure on the intelligent driving domain controller.

[0077] S203: Send the target image to the vehicle controller so that the vehicle controller can generate a panoramic image of the vehicle based on the target image.

[0078] In this embodiment, after the intelligent driving domain controller sends the target image to the vehicle controller, the vehicle controller can process the target image according to the preset AVM image algorithm, and then synthesize a panoramic image of the vehicle to improve the imaging performance of the panoramic image.

[0079] In this embodiment, the intelligent driving domain controller only needs to merge the original images. The relatively complex AVM image algorithm is completed by the vehicle controller, which has more computing power. This allows for a more reasonable allocation of computing resources between the intelligent driving domain controller and the vehicle controller, without requiring any changes to the existing hardware structure, resulting in low modification costs. While ensuring the implementation of intelligent driving parking and AVM functions, it improves the overall vehicle resource utilization efficiency. At the same time, since the computing power pressure on the intelligent driving domain controller is relieved, it can also effectively improve the efficiency of subsequent design and development of the intelligent driving domain controller, making it easier to implement more advanced and richer intelligent driving functions.

[0080] In one feasible implementation, S202 may specifically include the following sub-steps:

[0081] S202-1: Based on the directional markers corresponding to the original images at at least four preset orientations, determine the target region corresponding to each original image in the target image.

[0082] In this embodiment, the surround-view cameras installed at various preset locations on the vehicle add corresponding location markers to the original images they acquire at those locations. After acquiring the original images, the intelligent driving domain controller can parse the location markers corresponding to the original images and then determine the target areas corresponding to the original images. In other words, the target image consists of a preset number of target areas, and these preset number of target areas correspond one-to-one with the original images at at least four preset locations.

[0083] S202-1: Map each original image to its corresponding target region to obtain the target image.

[0084] In this embodiment, for any original image, after determining the target region corresponding to the original image, the original image can be mapped to the target region to complete the merging of the original images.

[0085] For example, if the original image is an image of the vehicle in four preset directions (front, back, left, right), the directional labels corresponding to the original images in the four preset directions are "front", "back", "left" and "right", which correspond to the upper left, lower left, upper right and lower right regions of the target image, respectively. By stitching each original image to the corresponding target region, a grid-like target image can be obtained, and each grid in the target image corresponds to one original image.

[0086] In one feasible implementation, S203 may specifically include the following sub-steps:

[0087] S203-1: Obtain the current resource utilization of the graphics processor of the intelligent driving domain controller.

[0088] In this embodiment, in order to allocate the computing power of the intelligent driving domain controller and the vehicle controller more rationally and meet the application scenarios of intelligent driving domain controllers with different computing power levels, the intelligent driving domain controller can also determine whether the vehicle controller needs to complete the generation of the panoramic image by detecting the current resource utilization rate of its own GPU.

[0089] S203-2: When the current resource occupancy rate is greater than the specified occupancy rate, the target image is sent to the vehicle controller so that the vehicle controller can generate a panoramic image of the vehicle based on the target image.

[0090] In this embodiment, if the current resource utilization rate of the GPU is detected to be less than or equal to the specified utilization rate, it indicates that the computing power of the intelligent driving domain controller is sufficient and the panoramic image will be generated locally; if the current resource utilization rate of the GPU is detected to be greater than the specified utilization rate, it indicates that the computing power of the intelligent driving domain controller is insufficient to ensure the effective presentation of the panoramic image, and the generation of the panoramic image will be handed over to the vehicle controller.

[0091] In this embodiment, a comprehensive judgment can also be made by combining the current resource utilization rate of the GPU of the vehicle controller. That is, by comparing the current resource utilization rates of the GPUs of the intelligent driving domain controller and the vehicle controller, the controller with the smaller current resource utilization rate is determined as the target controller, and the target controller completes the generation of the panoramic image.

[0092] In this embodiment, the target controller for generating the panoramic image is determined based on the current resource utilization rate of the graphics processor of the intelligent driving domain controller. This enables reasonable allocation of the controller's computing resources, ensuring that the imaging performance of the panoramic image is guaranteed regardless of whether the intelligent driving domain controller and vehicle control system used in the vehicle are high-performance or medium-to-low-performance platforms.

[0093] Secondly, referring to Figure 3 Based on the same inventive concept, another panoramic image generation method provided in this application is applied to a vehicle control unit, and the method may specifically include the following steps:

[0094] S301: Obtain the target image sent by the intelligent driving domain controller. The target image is obtained by the intelligent driving domain controller by acquiring the original images of the vehicle in at least four preset positions and merging the original images in at least four preset positions.

[0095] S301: Generate a panoramic image of the vehicle based on the target image.

[0096] In this embodiment, after the vehicle controller receives the target image sent by the intelligent driving domain controller, it will process the target image according to the preset AVM image algorithm to generate a panoramic image of the vehicle.

[0097] In this embodiment, the vehicle controller generates the panoramic image instead of the intelligent driving domain controller, which can effectively reduce the computing power pressure on the intelligent driving domain controller. While ensuring that the intelligent driving domain controller can realize intelligent driving and parking functions, it can effectively avoid the impact of insufficient resources of the intelligent driving domain controller on the imaging effect of the panoramic image.

[0098] In one feasible implementation, S301 may specifically include the following sub-steps:

[0099] S301-1: Segment the target image to obtain original images in at least four preset orientations.

[0100] In this embodiment, the vehicle controller will first split the target image to restore the original image at least in four preset positions, so as to facilitate the implementation of the AVM image algorithm.

[0101] In the specific implementation, the vehicle controller can obtain the directional identifiers corresponding to different target regions in the target image by parsing the target image. Then, based on the directional identifiers corresponding to different target regions in the target image, the target image is split to obtain the original image corresponding to each target region.

[0102] For example, when the target image is a grid image composed of four rectangular squares, the vehicle controller can parse the target image to obtain the directional markers corresponding to different target areas. These include the upper left, lower left, upper right, and lower right areas of the target image, which correspond to the original images of the front, rear, left, and right sides of the vehicle, respectively. After obtaining the original images from each direction, the AVM image algorithm can be used to generate a panoramic image of the vehicle.

[0103] In this embodiment, after generating a panoramic image of the vehicle, the vehicle controller will send the panoramic image to the central control screen for display, providing the driver with information about the surroundings of the vehicle to assist the driver in parking and other operations.

[0104] S301-2: Generate a panoramic image of the vehicle based on the original images from at least four preset orientations.

[0105] In this embodiment, after obtaining original images from at least four preset locations, the original images will be processed according to a preset AVM image algorithm. Specifically, this includes operations such as distortion correction, joint calibration of the four fisheye cameras, projection transformation, bird's-eye view fine-tuning, stitching and fusion, and 3D model texture mapping. It should be noted that the AVM image algorithm is a mature existing image processing algorithm, and its specific workflow will not be described in detail in this embodiment.

[0106] Thirdly, based on the same inventive concept, and referring to... Figure 4 This application provides a panoramic image generation device 400, which is used in an intelligent driving domain controller. The panoramic image generation device 400 includes:

[0107] The first acquisition module 401 is used to acquire original images of the vehicle in at least four preset orientations.

[0108] The image merging module 402 is used to merge the original images at at least four preset positions to obtain the target image.

[0109] The image sending module 403 is used to send the target image to the vehicle controller so that the vehicle controller can generate a panoramic image of the vehicle based on the target image.

[0110] In one feasible implementation, the image merging module 402 includes:

[0111] The target region determination submodule is used to determine the target region corresponding to each original image in the target image based on the directional markers corresponding to the original images at at least four preset orientations.

[0112] The image merging submodule is used to map each original image to its corresponding target region to obtain the target image.

[0113] In one feasible implementation, the image sending module 403 includes:

[0114] The resource utilization rate acquisition submodule is used to obtain the current resource utilization rate of the graphics processor of the intelligent driving domain controller.

[0115] The image sending submodule is used to send the target image to the vehicle controller when the current resource occupancy rate is greater than a specified occupancy rate, so that the vehicle controller can generate a panoramic image of the vehicle based on the target image.

[0116] It should be noted that the specific implementation of the panoramic image generation device 400 in this application embodiment refers to the panoramic image generation method proposed in the first aspect of the aforementioned application embodiment, and will not be repeated here.

[0117] Fourthly, refer to Figure 5 Based on the same inventive concept, this application provides another panoramic image generation device 500, used in a vehicle infotainment controller. The panoramic image generation device 500 includes:

[0118] The second acquisition module 501 is used to acquire the target image sent by the intelligent driving domain controller. The target image is obtained by the intelligent driving domain controller acquiring the original images of the vehicle in at least four preset positions and merging the original images in at least four preset positions.

[0119] Image generation module 502 is used to generate a panoramic image of the vehicle based on the target image.

[0120] In one feasible implementation, the image generation module 502 includes:

[0121] The splitting submodule is used to split the target image to obtain the original image in at least four preset orientations.

[0122] The image generation submodule is used to generate a panoramic image of the vehicle based on the original images from at least four preset orientations.

[0123] In one feasible implementation, the sub-modules include:

[0124] The orientation identifier acquisition unit is used to acquire the orientation identifiers corresponding to different target regions in the target image.

[0125] The splitting unit is used to split the target image based on the directional labels corresponding to different target regions in the target image, so as to obtain the original image corresponding to each target region.

[0126] In one feasible implementation, the panoramic image generation device 500 further includes:

[0127] The display module is used to generate a panoramic image of the vehicle based on the target image, and then send the panoramic image to the central control screen for display.

[0128] It should be noted that the specific implementation of the panoramic image generation device 500 in this application embodiment refers to the panoramic image generation method proposed in the second aspect of the aforementioned application embodiment, and will not be repeated here.

[0129] Fifthly, refer to Figure 6 This application provides an image generation system 600, which includes an intelligent driving domain controller 602, a vehicle infotainment controller 603, and surround-view cameras 601 respectively disposed at at least four preset locations on the vehicle.

[0130] The surround-view camera 601 is used to acquire raw images of the vehicle in at least four preset positions and send the raw images in at least four preset positions to the intelligent driving domain controller 602.

[0131] The intelligent driving domain controller 602 is used to acquire raw images from at least four preset orientations, merge the raw images from at least four preset orientations to obtain a target image, and send the target image to the vehicle controller 603.

[0132] The vehicle control unit 603 is used to acquire the target image and generate a panoramic image of the vehicle based on the target image.

[0133] For example, refer to Figure 7The diagram illustrates the workflow of the image generation system provided in this embodiment. In this embodiment, four surround-view cameras 601 are connected to one end of the intelligent driving domain controller 602 via a serializer, and the other end of the intelligent driving domain controller 602 is connected to the vehicle controller 603 via another serializer. The four surround-view cameras 601 transmit their acquired raw image information in parallel to the serializer in the form of electrical signals through the built-in ISP (Image Signal Processing) module. The serializer converts the four parallel signals transmitted by the surround-view cameras 601 into serial signals and sends them to the intelligent driving domain controller 602. The intelligent driving domain controller 602 can parse the serial signals to obtain the raw images corresponding to the four directions of "front", "rear", "left" and "right", and merge the four raw images into a grid-like target image. The target image is then sent to the vehicle controller 603 through another serializer. The vehicle controller 603 splits the target image to obtain the raw images corresponding to the four directions of "front", "rear", "left" and "right", and then synthesizes the four raw images into a panoramic image of the vehicle based on a preset AVM image algorithm.

[0134] It should be noted that the specific implementation of the image generation system 600 in this application refers to the specific implementation of the panoramic image generation method proposed in the first aspect of the present application and the other panoramic image generation method proposed in the second aspect of the present application, and will not be repeated here.

[0135] Sixthly, refer to Figure 8 This application provides a vehicle 800, which includes a panoramic image generation system 600 proposed in the fifth aspect of this application.

[0136] It should be noted that the specific implementation of the vehicle 800 in this application embodiment refers to the specific implementation of the panoramic image generation system 600 proposed in the fifth aspect of the aforementioned application embodiment, and will not be repeated here.

[0137] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0139] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0141] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0142] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the element.

[0143] The panoramic image generation method, apparatus, system, and vehicle provided by the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A panoramic image generation method characterized by, The method applied to an intelligent driving domain controller comprises: acquiring original images of a vehicle at at least four preset orientations; merging the original images at the at least four preset orientations to obtain a target image; acquiring a current resource occupancy rate of a graphics processor of the intelligent driving domain controller; in a case where the current resource occupancy rate is greater than a specified occupancy rate, sending the target image to a vehicle controller to enable the vehicle controller to generate a panoramic image of the vehicle based on the target image; the method further comprises: in a case where the current resource occupancy rate is less than or equal to the specified occupancy rate, generating the panoramic image of the vehicle locally by the intelligent driving domain controller based on the target image; the merging of the original images at the at least four preset orientations to obtain the target image comprises: determining a respective target area of each of the original images in the target image based on a respective orientation identifier of each of the original images at the at least four preset orientations; mapping each of the original images to the respective target area to obtain the target image.

2. A panoramic image generation method characterized by, The method applied to a vehicle controller comprises: in a case where a current resource occupancy rate of a graphics processor of an intelligent driving domain controller is greater than a specified occupancy rate, acquiring a target image sent by the intelligent driving domain controller, the target image being obtained by the intelligent driving domain controller by acquiring original images of a vehicle at at least four preset orientations, determining a respective target area of each of the original images in the target image based on a respective orientation identifier of each of the original images at the at least four preset orientations, and mapping each of the original images to the respective target area; generating a panoramic image of the vehicle based on the target image; the method further comprises: in a case where the current resource occupancy rate is less than or equal to the specified occupancy rate, generating the panoramic image of the vehicle locally by the intelligent driving domain controller based on the target image.

3. The panoramic image generation method according to claim 2, characterized by, The step of generating the panoramic image of the vehicle based on the target image comprises: splitting the target image to obtain the original images at the at least four preset orientations; generating the panoramic image of the vehicle based on the original images at the at least four preset orientations.

4. The panoramic image generation method according to claim 3, characterized by, The step of splitting the target image to obtain the original images at the at least four preset orientations comprises: acquiring respective orientation identifiers of different target areas in the target image; splitting the target image based on the respective orientation identifiers of the different target areas in the target image to obtain a respective original image of each of the target areas.

5. An apparatus for generating a panoramic image, characterized by comprising: The apparatus applied to an intelligent driving domain controller comprises: a first acquiring module configured to acquire original images of a vehicle at at least four preset orientations; an image merging module configured to merge the original images at the at least four preset orientations to obtain a target image; An image sending module is used to obtain the current resource utilization rate of the graphics processor of the intelligent driving domain controller; when the current resource utilization rate is greater than a specified utilization rate, the target image is sent to the vehicle controller so that the vehicle controller can generate a panoramic image of the vehicle based on the target image. The image merging module includes: The target region determination submodule is used to determine the target region corresponding to each original image in the target image based on the directional markers corresponding to the original images at at least four preset directional locations. The image merging submodule is used to map each original image to its corresponding target region to obtain the target image; The device is also configured to, when the current resource occupancy rate is less than or equal to a specified occupancy rate, generate a panoramic image of the vehicle locally by the intelligent driving domain controller based on the target image.

6. An apparatus for generating a panoramic image, characterized by comprising: The device, used in vehicle infotainment controllers, includes: The second acquisition module is used to acquire a target image sent by the intelligent driving domain controller when the current resource utilization rate of the graphics processor of the intelligent driving domain controller is greater than a specified utilization rate. The target image is obtained by the intelligent driving domain controller acquiring original images of the vehicle in at least four preset directions, and determining the target area corresponding to each original image in the target image based on the orientation identifiers corresponding to the original images in the at least four preset directions, and mapping each original image to its corresponding target area. When the current resource utilization rate is less than or equal to the specified utilization rate, the intelligent driving domain controller generates a panoramic image of the vehicle locally based on the target image. An image generation module is used to generate a panoramic image of the vehicle based on the target image.

7. An image generation system characterized by comprising: The system includes an intelligent driving domain controller, a vehicle infotainment controller, and surround-view cameras respectively installed at at least four preset locations on the vehicle; wherein, The surround-view camera is used to capture original images of the vehicle in at least four preset directions and send the original images in at least four preset directions to the intelligent driving domain controller; The intelligent driving domain controller is configured to acquire original images from at least four preset orientations, and based on the orientation identifiers corresponding to each of the original images from the at least four preset orientations, determine the target region corresponding to each original image in the target image, map each original image to its corresponding target region to obtain the target image, and send the target image to the vehicle controller when the current resource utilization rate of the graphics processor of the intelligent driving domain controller is greater than a specified utilization rate, and when the current resource utilization rate is less than or equal to the specified utilization rate, generate a panoramic image of the vehicle locally by the intelligent driving domain controller based on the target image; The vehicle controller is used to acquire the target image and generate a panoramic image of the vehicle based on the target image.

8. A vehicle characterized by comprising: Including the image generation system as described in claim 7.

Images