Image processing method and device, electronic equipment and vehicle

Abstract

The invention relates to an image processing method and device, electronic equipment and a vehicle, and relates to the technical field of image processing.The method comprises the steps that firstly, environment image information shot around the vehicle is obtained; identifying parking space information in the environment image information, and determining first position information corresponding to the parking space information in a world coordinate system; converting the first position information to obtain second position information corresponding to the parking space information in a pixel coordinate system; rendering and drawing a parking space model corresponding to the parking space information into the environment image information according to the second position information; and displaying the environment image information rendered and drawn by the parking space model. By applying the technical scheme of the invention, the target parking space in the real world can be clearly and accurately transmitted to the user, so that the user can clearly and intuitively know the parking space condition around the vehicle, and the use experience of the user can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to an image processing method, device, electronic equipment and vehicle. Background Art

[0002] As cities continue to expand, the number of motor vehicles has greatly increased, and parking problems have arisen one after another. Accurate identification of parking spaces near vehicles can help users plan parking routes and drive the vehicle into the corresponding parking space.

[0003] At present, environmental parameters around the vehicle can be collected through laser radar and other equipment, such as the size of the parking lot space, the location of the parked vehicles, etc. Then, computer synthesis technology is used to virtually restore the parking space, including 2D restoration or 3D restoration. Then a virtual world environment is established, in which the estimated parking space information is displayed.

[0004] However, in real scenes, there are many obstacles that cause interference, which will affect the accuracy of data collection such as lidar, making it impossible for users to obtain clear and accurate parking space information, thus causing inconvenience to users. Summary of the invention

[0005] In view of this, the present disclosure provides an image processing method, device, electronic device and vehicle, the main purpose of which is to improve the technical problem that the current existing technology makes it impossible for users to obtain clear and accurate parking space information.

[0006] In a first aspect, the present disclosure provides an image processing method, the method comprising:

[0007] Acquire environmental image information captured around the vehicle;

[0008] Identifying parking space information in the environmental image information;

[0009] Determine first position information corresponding to the parking space information in the world coordinate system;

[0010] Converting the first position information to obtain second position information corresponding to the parking space information in a pixel coordinate system;

[0011] According to the second position information, rendering a parking space model corresponding to the parking space information into the environment image information;

[0012] The environment image information after the parking space model is rendered is displayed.

[0013] In a second aspect, the present disclosure provides an image processing device, comprising:

[0014] An acquisition module is configured to acquire environmental image information captured around the vehicle;

[0015] an identification module, configured to identify parking space information in the environment image information, and determine first position information corresponding to the parking space information in a world coordinate system;

[0016] a conversion module, configured to convert the first position information to obtain second position information corresponding to the parking space information in a pixel coordinate system;

[0017] The display module is configured to render and draw the parking space model corresponding to the parking space information into the environmental image information according to the second position information; and display the environmental image information after the parking space model is rendered.

[0018] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the image processing method described in the first aspect.

[0019] In a fourth aspect, the present disclosure provides an electronic device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the image processing method described in the first aspect when executing the computer program.

[0020] In a fifth aspect, the present disclosure provides a vehicle, comprising: the device as described in the second aspect or the electronic device as described in the fourth aspect.

[0021] By means of the above technical scheme, the present disclosure provides an image processing method, device, electronic device and vehicle, firstly obtaining the environmental image information taken around the vehicle; then identifying the parking space information in the environmental image information, and determining the first position information corresponding to the parking space information in the world coordinate system; then converting the first position information to obtain the second position information corresponding to the parking space information in the pixel coordinate system; then rendering and drawing the parking space model corresponding to the parking space information into the environmental image information according to the second position information; and then displaying the environmental image information after the parking space model is rendered. Compared with the current method of establishing a virtual world environment to virtually restore the parking space information, the present disclosure can completely restore the environmental image taken around the vehicle to the real world, because the laser radar and other equipment are easily disturbed by some obstacles during the detection process, and when synthesizing the virtual world environment according to the data collected by these equipment, it will affect the user's recognition accuracy of the parking space information; and the image shooting means will display the obstacle image together with the parking space image in the most intuitive way, which shows the most real on-site environment, and the user can subjectively judge the situation of the parking space, which can effectively reduce the interference caused by obstacles to the recognition of parking space information. Furthermore, the present disclosure can clearly and accurately display the parking space model corresponding to the parking space information in the environmental image around the vehicle, and can clearly and accurately convey the target parking space in the real world to the user, so that the user can clearly and intuitively understand the parking space situation around the vehicle, thereby improving the user's experience.

[0022] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0025] Figure 1 A schematic diagram of a flow chart of an image processing method provided by an embodiment of the present disclosure is shown;

[0026] Figure 2 A schematic diagram showing a flow chart of another image processing method provided by an embodiment of the present disclosure;

[0027] Figure 3 A schematic structural diagram of an image processing device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0028] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0029] In order to improve the technical problem that the existing technology makes it impossible for users to obtain clear and accurate parking space information. This embodiment provides an image processing method, such as Figure 1 As shown, the method includes:

[0030] Step 101: Acquire environmental image information captured around the vehicle.

[0031] The execution subject of this embodiment may be an image processing device or equipment, which may be configured on the vehicle side, etc. This embodiment may use the camera on the vehicle and / or the camera of some external device to capture the environmental image information around the vehicle. For example, the external device may be a user's mobile phone, a surveillance camera in a parking lot, etc. The vehicle side may obtain the environmental image information captured by these external devices through the server and / or wireless communication established with the external device.

[0032] The environmental image information may be image information captured within a preset range around the vehicle, and the preset range may be set according to actual needs, and the preset range may include a range size and an angle position relative to the vehicle, etc. For example, the preset range may be a circular range with the vehicle as the center and a preset length as the radius, or a square range with the vehicle as the center and a preset length as the side length, etc.

[0033] Step 102: Identify parking space information in the environment image information, and determine first position information corresponding to the parking space information in the world coordinate system.

[0034] This embodiment can perceive and identify the parking space information in the environmental image information based on image recognition technology, such as identifying the position with parking space features in the environmental image information, and then determining the first position information corresponding to the parking space information in the world coordinate system based on the position. The first position information can be the coordinate information corresponding to the parking space in the world coordinate system, that is, the relative position of the parking space relative to the vehicle in the world coordinate system.

[0035] It should be noted that in actual application scenarios, there may be one or more parking spaces around the vehicle. Therefore, this embodiment can identify at least one parking space information in the environmental image information, and determine the first position information corresponding to each parking space information in the world coordinate system, and then execute the processes shown in the following steps 103 to 104 respectively.

[0036] Step 103: convert the first position information to obtain second position information corresponding to the parking space information in the pixel coordinate system.

[0037] For example, based on the world coordinate position corresponding to the parking space information in the world coordinate system, relevant operations of coordinate system conversion are performed, and then converted to the pixel coordinate position corresponding to the parking space information in the pixel coordinate system as the second position information.

[0038] Step 104: Render and draw the parking space model corresponding to the parking space information into the environment image information according to the second position information.

[0039] The parking space model can be drawn according to the parking space information. The specific style of the parking space model is not limited in this embodiment. For example, it can include four borders of the parking space, and the borders can be bold or flashing. In addition, the parking space model can also include an arrow model representing the direction of the parking space, etc. The user can quickly and clearly understand the shape, size and position of the parking space through the parking space model.

[0040] This embodiment can achieve a parking space information display effect like augmented reality (AR). Therefore, in order to achieve this purpose, it is necessary to determine the display position of the parking space model corresponding to the parking space information in the environmental image information, that is, the pixel coordinate position, and then render the parking space model to the position corresponding to the pixel coordinate position in the environmental image information according to the pixel coordinate position. In this way, the target parking space in the real world can be clearly and accurately conveyed to the user, so that the user can clearly and intuitively understand the parking space situation around the vehicle.

[0041] Step 105: Display the environment image information after the parking space model is rendered.

[0042] For example, in the automatic parking scenario of a vehicle, in order to facilitate the user to select a parking space around for automatic parking, the environmental image information containing the parking space information and the parking space model corresponding to the vehicle can be displayed, so that the user can select the target parking space for automatic parking according to their actual needs. In some extremely complex environments, even if there are many continuous and highly consistent parking spaces, the user can intuitively understand the actual situation of each parking space, and then select the parking space according to their actual needs. Furthermore, after the user selects the target parking space in the environmental image information, the image of the target parking space can be enlarged, so that the user can understand the specific situation of the target parking space more intuitively and accurately.

[0043] Compared with the current method of establishing a virtual world environment to virtually restore parking space information, this embodiment can completely restore the real world of the environmental images taken around the vehicle, and clearly and accurately display the parking space model corresponding to the parking space information in the environmental images around the vehicle. This can clearly and accurately convey the target parking space in the real world to the user, so that the user can clearly and intuitively understand the parking space situation around the vehicle, thereby improving the user experience.

[0044] Further, as a refinement and extension of the above embodiment, in order to fully illustrate the specific implementation process of the method of this embodiment, this embodiment provides the following Figure 2 The specific method shown comprises the following steps:

[0045] Step 201: Obtain image information of multiple viewing angles captured by multiple fisheye cameras around a vehicle.

[0046] The focal length of a fisheye camera is 16mm or shorter, and its viewing angle is close to or equal to 180°. It is an extreme wide-angle lens, and "fisheye lens" is its common name. In order to maximize the viewing angle of the lens, the front lens of this photographic lens has a very short diameter and protrudes toward the front of the lens in a parabolic shape, which is quite similar to the eyes of a fish, hence the name "fisheye lens". Fisheye lenses are a special type of ultra-wide-angle lenses, and their viewing angle strives to reach or exceed the range that the human eye can see.

[0047] Fisheye cameras can be installed on vehicles, such as installing a fisheye camera at the front, rear, left and right ends of the vehicle. These four fisheye cameras can capture images from the front, rear, left and right perspectives of the vehicle. The images captured by each of the four fisheye cameras can be stitched together to obtain an environmental image captured around the vehicle, i.e., a more comprehensive and accurate environmental image around the vehicle.

[0048] Step 202: Dedistort image information from multiple viewing angles respectively.

[0049] Taking into account the principle of image capture by fisheye cameras, in order to achieve the effect of image stitching, the image information of multiple perspectives can be first dedistorted separately. For example, the image can be dedistorted using the intrinsic and extrinsic data of the fisheye camera, and then image stitching can be performed. This can achieve accurate image stitching of the image information of multiple perspectives captured by multiple fisheye cameras.

[0050] Step 203: stitch the image information of multiple perspectives after the dedistortion processing to obtain the environmental image information captured around the vehicle.

[0051] When stitching images, the image information of multiple viewing angles after dedistortion processing can be stitched in a clockwise or counterclockwise order according to the arrangement positions of the fisheye cameras.

[0052] Step 204: Identify parking space information in the environment image information, and determine first position information corresponding to the parking space information in the world coordinate system.

[0053] In order to quickly and accurately identify the parking space information in the environmental image information, this embodiment can use artificial intelligence (AI) technology for perception and recognition. Accordingly, in some embodiments, step 204 may specifically include: inputting the environmental image information into the recognition model to perform parking space recognition to obtain the parking space information.

[0054] Among them, the recognition model is obtained by training based on different sample image information, and different sample image information corresponds to the marked sample parking space information as a training set. For example, the recognition model can be a machine learning model. First, the machine learning model is constructed, and then based on the training set, the constructed machine learning model is trained. The accuracy of the model calculation results can be verified by the test set. After multiple iterative training, a machine learning model that meets the training standards is finally obtained, that is, the recognition model, which can be used to identify parking space information in image information.

[0055] This embodiment can accurately identify the parking space information in the environmental image information with the help of the recognition model, and then accurately determine the first position information corresponding to the parking space information in the world coordinate system, so as to facilitate the subsequent accurate rendering and superposition of the parking space model to the corresponding position on the environmental image.

[0056] Step 205: convert the first position information to obtain second position information corresponding to the parking space information in the pixel coordinate system.

[0057] In some embodiments, step 205 may specifically include: first obtaining the parameter matrix of the fisheye camera, the parameter matrix including the camera intrinsic parameter matrix (or camera intrinsic parameter matrix) and the camera extrinsic parameter matrix (or camera extrinsic parameter matrix); then using the parameter matrix and the coordinate information (world coordinate position) corresponding to the first position information as parameters, using the transformation formula between the pixel coordinate system and the world coordinate system, calculate the coordinate information (pixel coordinate position) corresponding to the parking space information in the pixel coordinate system as the second position information corresponding to the parking space information in the pixel coordinate system. In this way, the world coordinate position of the parking space information in the world coordinate system can be accurately converted to the pixel coordinate position in the pixel coordinate system, so as to facilitate the subsequent accurate rendering of the parking space model corresponding to the parking space information to the corresponding position in the environmental image information.

[0058] For example, as shown in Formula 1, it is a transformation formula between the pixel coordinate system (pixel) and the world coordinate system (world).

[0059]

[0060] In formula 1, (u, v) represents the pixel coordinates corresponding to the parking space information in the pixel coordinate system, and (x, y, z) represents the world coordinates corresponding to the parking space information in the world coordinate system; represents the camera intrinsic parameter matrix, f x and f y represents the focal length, c x and c y Indicates the image offset from the pixel coordinate system to the camera; represents the camera extrinsic parameter matrix, where represents the rotation matrix, Represents the translation matrix.

[0061] In this embodiment, the relative position coordinates (x, y, z) of the parking space information based on the vehicle in the world coordinate system can be obtained through the above step 204. After conversion by the above formula 1, the pixel coordinates (u, v) of the parking space information in the environmental image information can be obtained.

[0062] Step 206: Render and draw the parking space model corresponding to the parking space information into the environment image information according to the second position information.

[0063] In some embodiments, step 206 may specifically include: first obtaining the parking space size (such as width w and height h), parking space inclination angle and parking space orientation corresponding to the parking space information; then drawing a parking space model corresponding to the parking space size, parking space inclination angle and parking space orientation; and then integrating the parking space model into the position corresponding to the second position information in the environmental image information through rendering technology.

[0064] For example, according to the width w and height h of the parking space size and the parking space orientation, a rectangular model with a width w*height h is established, and according to the parking space position information (u, v), it is fused to the corresponding position in the environmental image information through rendering technology.

[0065] Step 207: display the environment image information after the parking space model is rendered.

[0066] Compared with the current method of establishing a virtual world environment to virtually restore parking space information, this embodiment can completely restore the real world of the environmental images taken around the vehicle, and clearly and accurately display the parking space model corresponding to the parking space information in the environmental images around the vehicle. This can clearly and accurately convey the target parking space in the real world to the user, so that the user can clearly and intuitively understand the parking space situation around the vehicle, thereby improving the user experience.

[0067] Furthermore, in order to enrich the displayed content, in some embodiments, before step 207, the method of this embodiment may also include: identifying target object information in the environmental image information, wherein the target object information includes: limiter information (such as a limiter of a parking space) and / or obstacle information (such as obstacles inside and / or around the parking space, etc.); then determining the third position information corresponding to the target object information in the world coordinate system; converting the third position information to obtain the fourth position information corresponding to the target object information in the pixel coordinate system; and then rendering the object model corresponding to the target object information into the environmental image information according to the fourth position information.

[0068] Accordingly, step 207 may specifically include: displaying the environment image information after the parking space model and the object model are rendered. For example, in addition to displaying the parking space model in the environment image, the parking space limiter model and the obstacle model inside and / or around the parking space may also be displayed, so that the user can more intuitively understand the more comprehensive situation of each parking space, thereby facilitating the user to make corresponding parking space selection.

[0069] In some examples, in order to quickly and accurately identify the target object information in the environmental image information, similarly, this embodiment can also use AI technology for perception recognition. For example, the above-mentioned identification of the target object information in the environmental image information can specifically include: inputting the environmental image information into a target model (which may be the same as or different from the above-mentioned recognition model) for recognition calculation to obtain the target object information in the environmental image information.

[0070] The target model is obtained by training based on different sample image information and sample object information (such as sample stopper information and / or sample obstacle information) marked corresponding to different sample image information as a training set. For example, the target model can be a machine learning model. The machine learning model is first constructed, and then the constructed machine learning model is trained based on the training set, wherein the accuracy of the model calculation results can be verified by the test set. After multiple iterations of training, a machine learning model that meets the training standards is finally obtained, that is, the target model, which can be used to identify the stopper information and / or obstacle information in the image information.

[0071] This embodiment can accurately identify the limiter information and / or obstacle information in the environment image information with the help of the recognition model, so as to facilitate the subsequent accurate rendering and superposition of the limiter model and / or obstacle model to the corresponding position on the environment image.

[0072] By applying the above technical solution of the present embodiment, based on the stitched image synthesized by the four fisheye cameras on the vehicle, the parking space, limiter, obstacle and other information acquired by visual perception can be integrated and drawn into the stitched image after coordinate conversion. Since the camera image is a complete restoration of the real world, the parking space information based on the solution of the present embodiment is clearly conveyed to the user, avoiding the technical problems caused by fuzzy pointing in traditional technologies.

[0073] Further, as Figure 1 and Figure 2 The specific implementation of the method shown in the embodiment provides an image processing device, such as Figure 3 As shown, the device includes: an acquisition module 31, an identification module 32, a conversion module 33, and a display module 34.

[0074] An acquisition module 31 is configured to acquire environmental image information captured around the vehicle;

[0075] The recognition module 32 is configured to recognize the parking space information in the environment image information and determine the first position information corresponding to the parking space information in the world coordinate system;

[0076] A conversion module 33 is configured to convert the first position information to obtain second position information corresponding to the parking space information in a pixel coordinate system;

[0077] The display module 34 is configured to render and draw the parking space model corresponding to the parking space information into the environmental image information according to the second position information; and display the environmental image information after the parking space model is rendered.

[0078] In some embodiments, the display module 34 is specifically configured to obtain the parking space size, parking space inclination angle and parking space orientation corresponding to the parking space information; draw a parking space model corresponding to the parking space size, parking space inclination angle and parking space orientation; and integrate the parking space model into the position corresponding to the second position information in the environmental image information through rendering technology.

[0079] In some embodiments, the acquisition module 31 is specifically configured to acquire image information of multiple perspectives captured by multiple fisheye cameras around the vehicle; perform de-distortion processing on the image information of the multiple perspectives respectively; and perform image stitching on the image information of the multiple perspectives after de-distortion processing to obtain the environmental image information.

[0080] In some embodiments, the conversion module 33 is specifically configured to obtain a parameter matrix of the fisheye camera, wherein the parameter matrix includes a camera intrinsic parameter matrix and a camera extrinsic parameter matrix; using the parameter matrix and the coordinate information corresponding to the first position information as parameters, and using the transformation formula between the pixel coordinate system and the world coordinate system, the coordinate information corresponding to the parking space information in the pixel coordinate system is calculated as the second position information.

[0081] In some embodiments, the recognition module 32 is specifically configured to input the environmental image information into a recognition model to perform parking space recognition to obtain the parking space information, wherein the recognition model is based on different sample image information, and the different sample image information respectively corresponds to the marked sample parking space information as a training set for training.

[0082] In some embodiments, the recognition module 32 is further configured to recognize target object information in the environment image information, wherein the target object information includes: limiter information and / or obstacle information; determine third position information corresponding to the target object information in the world coordinate system;

[0083] The conversion module 33 is further configured to convert the third position information to obtain fourth position information corresponding to the target object information in a pixel coordinate system;

[0084] The display module 34 is further configured to render and draw the object model corresponding to the target object information into the environmental image information according to the fourth position information; and display the parking space model and the environmental image information after the object model is rendered.

[0085] It should be noted that for other corresponding descriptions of the functional units involved in the image processing device provided in this embodiment, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0086] Based on the above Figure 1 and Figure 2 The method shown in the figure, accordingly, the embodiment of the present disclosure also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The method shown.

[0087] Based on this understanding, the technical solution of this embodiment can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each implementation scenario of this embodiment.

[0088] Based on the above Figure 1 and Figure 2 The method shown, and Figure 3 In order to achieve the above-mentioned purpose, the embodiment of the present disclosure also provides an electronic device, which can be configured on the vehicle (such as a new energy vehicle or a traditional vehicle) side, and the device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 and Figure 2 The method shown.

[0089] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0090] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0091] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0092] Based on the above electronic device, the embodiment of the present disclosure further provides a vehicle, which may specifically include: Figure 3 The image processing device shown, or the electronic device described above. The vehicle may be a new energy vehicle, or a traditional vehicle, etc.

[0093] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present disclosure can be implemented by means of software plus the necessary general hardware platform, or by hardware. By applying the solution of the embodiment of the present disclosure, audio, text, and picture multimodal information can be used to determine whether the user's voice request requires clicking on the content on the page. By applying the technical solution of this embodiment, first obtain the environmental image information shot around the vehicle; then identify the parking space information in the environmental image information, and determine the first position information corresponding to the parking space information in the world coordinate system; then convert the first position information to obtain the second position information corresponding to the parking space information in the pixel coordinate system; then render and draw the parking space model corresponding to the parking space information into the environmental image information according to the second position information; and then display the environmental image information after the parking space model is rendered. Compared with the current method of establishing a virtual world environment to virtually restore parking space information, this embodiment can completely restore the real world of the environmental image captured around the vehicle, because laser radar and other equipment can be easily disturbed by some obstacles during the detection process. When synthesizing the virtual world environment based on the data collected by these devices, it will affect the user's recognition accuracy of parking space information; and the image shooting method will display the obstacle image together with the parking space image in the most intuitive way, showing the most realistic on-site environment, and the user's subjective judgment of the parking space situation can effectively reduce the interference caused by obstacles to the recognition of parking space information. In addition, the present disclosure can clearly and accurately display the parking space model corresponding to the parking space information in the environmental image around the vehicle, and can realize the clear and accurate communication of the target parking space in the real world to the user, so that the user can clearly and intuitively understand the parking space situation around the vehicle, which can improve the user's experience.

[0094] 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 such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0095] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features applied herein.

Claims

1. An image processing method, characterized in that: include: Acquire environmental image information captured around the vehicle; Identify parking space information in the environment image information, and determine first position information corresponding to the parking space information in a world coordinate system; Converting the first position information to obtain second position information corresponding to the parking space information in a pixel coordinate system; According to the second position information, rendering a parking space model corresponding to the parking space information into the environment image information; The environment image information after the parking space model is rendered is displayed.

2. The method according to claim 1, characterized in that: The step of rendering the parking space model corresponding to the parking space information into the environment image information according to the second position information includes: Obtaining a parking space size, a parking space inclination angle, and a parking space orientation corresponding to the parking space information; Draw a parking space model corresponding to the parking space size, parking space inclination angle and parking space orientation; The parking space model is integrated into the position corresponding to the second position information in the environmental image information through rendering technology.

3. The method according to claim 1, characterized in that The step of obtaining environmental image information captured around the vehicle includes: Acquire image information of multiple perspectives captured by multiple fisheye cameras around the vehicle; Performing dedistortion processing on the image information of the multiple perspectives respectively; The image information of multiple viewing angles after dedistortion processing is stitched to obtain the environmental image information.

4. The method according to claim 3, characterized in that The converting the first position information to obtain second position information corresponding to the parking space information in a pixel coordinate system includes: Obtaining a parameter matrix of the fisheye camera, wherein the parameter matrix includes a camera intrinsic parameter matrix and a camera extrinsic parameter matrix; The parameter matrix and the coordinate information corresponding to the first position information are used as parameters, and the transformation formula between the pixel coordinate system and the world coordinate system is used to calculate the coordinate information corresponding to the parking space information in the pixel coordinate system as the second position information.

5. The method according to claim 1, characterized in that The identifying the parking space information in the environment image information includes: The environmental image information is input into a recognition model to perform parking space recognition to obtain the parking space information, wherein the recognition model is trained based on different sample image information and sample parking space information marked corresponding to the different sample image information as a training set.

6. The method according to claim 1, characterized in that Before displaying the environment image information after rendering the parking space model, the method further includes: Identifying target object information in the environmental image information, wherein the target object information includes: limiter information and / or obstacle information; Determine third position information corresponding to the target object information in the world coordinate system; Converting the third position information to obtain fourth position information corresponding to the target object information in a pixel coordinate system; According to the fourth position information, rendering and drawing the object model corresponding to the target object information into the environment image information; The displaying of the environment image information after the parking space model is rendered includes: The environment image information after rendering the parking space model and the object model is displayed.

7. An image processing device, characterized in that: The device comprises: An acquisition module is configured to acquire environmental image information captured around the vehicle; an identification module, configured to identify parking space information in the environment image information, and determine first position information corresponding to the parking space information in a world coordinate system; a conversion module, configured to convert the first position information to obtain second position information corresponding to the parking space information in a pixel coordinate system; The display module is configured to render and draw the parking space model corresponding to the parking space information into the environmental image information according to the second position information; and display the environmental image information after the parking space model is rendered.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

10. A vehicle, characterized in that: include: The device as claimed in claim 7 or the electronic device as claimed in claim 9.

Images