Processing method and vehicle
By determining the initial landing point of the click position and head position in the transparent window scene, and determining the target close-up position point based on whether the position is a long-range or close-up view, the problem of inaccurate clicks is solved and the accuracy of target object selection is improved Spend.
Patent Information
- Application Number
- CN202411214917.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-12-06
AI Technical Summary
In the transparent window scene, when the user clicks on the outside target object through the window, his eyes are focused on the outside target object, which makes it impossible to see the click position of his finger on the window, resulting in the click position being unable to accurately locate.
By obtaining the target user's click position and head position, determine the initial landing position of the line between the click position and the head position, and determine the target close-up position point based on whether the position is a long-range or close-up position, so as to display it on the car window Information about the target object.
It effectively solves the problem of click inaccuracy caused by parallax, and improves the accuracy of target selection when using transparent display devices.
Smart Images

Figure CN119078506A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of image processing, and in particular to a processing method and a vehicle. Background Art
[0002] As an emerging display device, transparent display has a lot of room for imagination in the application of transparent car window scenarios. One of the potential application scenarios is that after the passenger clicks on the target object outside with his finger, the corresponding target object information is returned. However, in this application scenario, when the user clicks on the target object outside through the car window, because the line of sight is focused on the target object outside, it is impossible to see the click position of the finger on the car window, resulting in the click position not being accurately located on the target object outside. Summary of the invention
[0003] The purpose of the embodiments of the present application is to provide a processing method and a vehicle.
[0004] According to a first aspect of the present application, a processing method is provided, the method comprising:
[0005] Obtaining a click position of a target user on a target vehicle window, wherein the target vehicle window is capable of displaying an image;
[0006] Determine the initial landing point of the line connecting the click position and the target position of the target user's head in the scene outside the vehicle;
[0007] In the case where the initial landing point is a distant view landing point, determining a target near view position point that satisfies a preset position relationship with the initial landing point;
[0008] Determining a target object from the scene outside the vehicle according to the target near-view position point;
[0009] The target information of the target object is displayed on the target vehicle window.
[0010] In some embodiments, the method of determining the initial landing point as the distant landing point includes:
[0011] Acquire a two-dimensional image corresponding to the scene outside the vehicle;
[0012] Determining a near view area and a far view area of the two-dimensional image;
[0013] Mapping the initial landing point position into the two-dimensional image to obtain a mapping position;
[0014] In the case where the mapping position is within the distant view area, the landing position is determined as the distant view landing position.
[0015] In some embodiments, the method of determining the initial landing point as the distant landing point includes:
[0016] Determining a target value of the initial landing point position in a first dimension, wherein the first dimension matches a normal direction of the target vehicle window;
[0017] When the target value is greater than a specific threshold, the initial landing point position is determined as the distant landing point position.
[0018] In some embodiments, determining a target near-view position point that satisfies a preset position relationship with the initial landing point position includes:
[0019] Searching along the first direction and the second direction to determine a plurality of first position points that satisfy a preset position relationship with the initial landing point position;
[0020] A near-view position point among the plurality of first position points is determined as the target near-view position point.
[0021] In some embodiments, satisfying the preset position relationship includes that the distance information corresponding to the initial landing point position is less than a distance threshold, and the method further includes:
[0022] Acquire a target distance between a target position of the target user's head and the target vehicle window;
[0023] The distance threshold is determined according to the target distance.
[0024] In some embodiments, determining a target near-view position point that satisfies a preset position relationship with the initial landing point position includes:
[0025] Determine a mapping position corresponding to the initial landing point position in a two-dimensional image, where the two-dimensional image is an image corresponding to the scene outside the vehicle, and the two-dimensional image is divided into a near-view area and a far-view area;
[0026] The target near-view position point is determined from the two-dimensional image according to the mapping position, and the distance between the target near-view position point and the mapping position is less than a distance threshold.
[0027] In some embodiments, determining a target near-view position point that satisfies a preset position relationship with the initial landing point position includes:
[0028] The target close-view position point is determined from the external vehicle scene, the distance between the target close-view position point and the initial landing point in a second dimension is less than a distance threshold, and the second dimension matches a section of the target vehicle window.
[0029] In some embodiments, determining a target object from the scene outside the vehicle according to the target near-view position point includes:
[0030] Inputting the two-dimensional image corresponding to the target near-view position point and the scene outside the vehicle into the target model;
[0031] receiving a target segmentation image corresponding to a single object segmented from the two-dimensional image by a target model based on the target near-view position point;
[0032] The target object is determined according to the target segmentation image.
[0033] In some embodiments, determining a target object from the scene outside the vehicle according to the target near-view position point includes:
[0034] Obtaining a two-dimensional image corresponding to the scene outside the vehicle, wherein the two-dimensional image is segmented into a plurality of segmented images corresponding to a single object;
[0035] Determining a target segmented image from the multiple segmented images according to the target near-view position point;
[0036] The target object is determined according to the target segmentation image.
[0037] According to a second aspect of the present application, a vehicle is provided, the vehicle comprising:
[0038] Vehicle body;
[0039] A target vehicle window, the vehicle window being capable of displaying an image and having a touch layer, capable of obtaining a click position on the target vehicle window;
[0040] A target acquisition device, used to acquire the target position of the head of the target user;
[0041] A processing device, the processing device comprising:
[0042] A click position acquisition module, used to obtain the click position of the target user on the target vehicle window, where the target vehicle window can display an image;
[0043] An initial landing point determination module is used to determine the initial landing point of the line connecting the click position and the target position of the target user's head in the scene outside the vehicle;
[0044] A target near-view position determination module, used to determine a target near-view position point that satisfies a preset position relationship with the initial landing point when the initial landing point position is a far-view landing point position;
[0045] A target object determination module, used to determine the target object from the scene outside the vehicle according to the target close-up position point;
[0046] The display module is used to display the target information of the target object on the target vehicle window. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 A schematic diagram of a processing method flow chart of an embodiment of the present application;
[0048] Figure 2 A schematic diagram of another processing method of an embodiment of the present application;
[0049] Figure 3 A schematic diagram of a target close-up object obtained by a processing method of the present application;
[0050] Figure 4 This is a schematic diagram of the image segmentation effect of this application;
[0051] Figure 5 This is a schematic diagram of the structure of the processing device of this application.
[0052] Reference numerals:
[0053] 1000, processing device; 1001, click position acquisition module; 1002, initial landing point position determination module; 1003, target close-up position determination module; 1004, target object determination module; 1005, display module; 1100, bus; 1200, processor; 1300, memory; 1400, other circuits. DETAILED DESCRIPTION
[0054] Various aspects and features of the present application are described herein with reference to the accompanying drawings.
[0055] It should be understood that various modifications may be made to the embodiments of the present application. Therefore, the above description should not be considered as limiting, but only as an example of an embodiment. Other modifications within the scope and spirit of the present application will occur to those skilled in the art.
[0056] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the present application and, together with the general description of the present application given above and the detailed description of the embodiments given below, serve to explain the principles of the present application.
[0057] These and other characteristics of the present application will become apparent from the following description of a preferred form of embodiment given as a non-limiting example with reference to the accompanying drawings.
[0058] It should also be understood that although the present application has been described with reference to some specific examples, those skilled in the art will be able to readily implement many other equivalent forms of the present application.
[0059] According to at least one embodiment of the present application, a processing method is provided, such as Figure 1 As shown, the processing method may include the following steps:
[0060] S101, obtaining a click position of a target user on a target vehicle window, and the target vehicle window can display an image;
[0061] S102, determining an initial landing point position of a line connecting a click position and a target position of a target user's head in a scene outside the vehicle;
[0062] S103, when the initial landing point is a distant view landing point, determining a target near view position point that satisfies a preset position relationship with the initial landing point;
[0063] S104, determining a target object from the scene outside the vehicle according to the target near-view position point;
[0064] S105: Displaying target information of the target object on the target vehicle window.
[0065] For ease of understanding, the following takes the processing method applied to a vehicle as an example for explanation. The vehicle has a target window and the window is transparent, and the user can see the external scene outside the window through the target window. Figure 2 The schematic diagram of FIG. 1 is used to illustrate each of the above steps.
[0066] For step S101, assuming that the scene outside the vehicle window may include the blue sky, white clouds, the Oriental Pearl TV Tower, the Huangpu River and other buildings, in the above step S101, the target user is located on the inside of the vehicle window. When the target user attempts to click on an object outside the window on the target window with a finger, a click operation is performed to generate a click position.
[0067] In the above step S102, first, the target head position between the two eyes of the target user is obtained, and then, based on the target head position and the click position obtained in the above step S101, a straight line can be determined, and the straight line forms an intersection with the external scene outside the car window, and the intersection is determined as the initial landing point. The target head position can include at least one of the center of the eyebrows, the left eye, and the right eye. For example, Figure 2 The initial landing point position in is a certain position in the blue sky, and the initial landing point position is recorded as position A (the position A in other places in this article refers to the same). Through the vehicle-mounted sensor device, a three-dimensional scene coordinate system can be established, so that the external scene and the objects and windows in the vehicle are in the same three-dimensional scene coordinate system, so that the initial landing point position can be calculated through the three-dimensional scene coordinate system.
[0068] For step S103, first, the near view and the far view are defined as follows: the object in the scene outside the window that is relatively close to the vehicle window is the near view, and the object in the scene outside the window that is relatively far from the vehicle window is the far view. In the above step S103, it is determined whether the initial landing point is the far view landing point. If the initial landing point is the far view landing point, a target near view position point that satisfies a preset position relationship with the initial landing point is determined. Figure 3The initial landing point position in is a certain position in the blue sky, namely, position A. Since there are other buildings such as the Oriental Pearl TV Tower in the scene outside the window that are closer to the target user than the blue sky, the initial landing point position (position A) is a distant landing point position. Since the purpose of the user's click behavior is to select the target object in the near view, such as the Oriental Pearl TV Tower in the near view, at this time, it is necessary to determine the target near view position point that meets the preset position relationship with the initial landing point position (position A), such as Figure 2 The positions are shown in FIG. 1 and are marked by several five-pointed stars.
[0069] In the above step S104, based on the target near-view point position determined in the above step S103, the target object to which the near-view point position belongs can be determined. For example, the near-view point position of the initial landing position (position A) may be within the building range of the Oriental Pearl Tower, so the target object can be determined to be the Oriental Pearl Tower based on the near-view point position.
[0070] In the above step S105, the target information of the target object, the Oriental Pearl Tower, determined in the above step S104, is displayed on the vehicle window.
[0071] The processing method provided by the present application first determines the initial landing point position through the head target position and the click position, and then, when the initial landing point position is not in the target foreground area, determines the target foreground landing point through the initial landing point position, and then determines the target object in the target foreground, which effectively solves the problem of inaccurate clicks on the target object due to user parallax, and improves the accuracy of user selection of the target object when using a transparent display device.
[0072] In some embodiments, in the above step S103, the method of determining the initial landing point position as the distant view landing point position may include:
[0073] Obtain a two-dimensional image corresponding to the scene outside the vehicle;
[0074] Determine a near view area and a far view area of a two-dimensional image;
[0075] Map the initial landing point position into the two-dimensional image to obtain the mapping position;
[0076] When the mapping position is in the distant view area, the landing position is determined as the distant view landing position.
[0077] For ease of understanding, the processing method is applied to a vehicle for further explanation. First, an image outside the vehicle window is obtained. The image is a two-dimensional image. The image can be obtained by an image acquisition device, such as a camera. Second, the near view and the far view in the two-dimensional image are determined. Specifically, the near view area and the far view area of the two-dimensional image can be obtained by an image segmentation method. Figure 4The effect of image segmentation on the two-dimensional image of the scene outside the car window is shown. Figure 4 It can be seen that various buildings including the Oriental Pearl TV Tower are divided into one area, namely the near view area with a smaller gray value, and objects such as blue sky and white clouds are divided into another area, namely the distant view area with a larger gray value. Then, the initial landing point position (position A) obtained in the above step S102 is mapped in the two-dimensional image to obtain the mapping position of the initial landing point position in the two-dimensional image. Finally, it is determined whether the mapping position is in the two-dimensional image, that is, whether the mapping position is in the distant view area or the near view area. Since the near view area and the distant view area of the two-dimensional image have been obtained by image segmentation, the area to which the position A belongs can be determined by the mapping position of position A in the two-dimensional image. If it is in the distant view area, the initial landing point position is determined as the distant view landing point position. Among them, the above image segmentation can be semantically segmented by a deep learning algorithm, and the deep learning algorithm can be, for example, a SAM method. After image segmentation, the distant view area and the near view area of the two-dimensional image are obtained.
[0078] The present application can map the initial landing point position in a two-dimensional image, and use the mapping position in the two-dimensional image to determine whether it is a distant or near-field landing point, and then further approach the required near-field object in subsequent processing to facilitate user clicks and selections, which helps to improve the user's click accuracy on the target object.
[0079] In some embodiments, in the above step S103, the method of determining the initial landing point position as the distant view landing point position may further include:
[0080] A target value of the initial landing point position in the first dimension is determined, and the first dimension matches the normal direction of the target window; the coordinate axis of the first dimension in the three-dimensional coordinate system extends away from the target window.
[0081] When the target value is greater than a certain threshold, the initial landing point position is determined as the distant landing point position.
[0082] For ease of understanding, the processing method is applied to vehicles for further explanation. First, the straight line formed by the head target position and the click position passes through the target window. In the normal direction of the target window, the initial landing point position (position A) will form a corresponding coordinate value, which is used as the target value; then, a specific threshold is preset, and the relationship between the target value and the specific threshold is judged. When the target value is greater than the threshold, position A is determined as the distant view landing point position, otherwise, position A is the near view landing point position.
[0083] The present application determines whether the initial landing point is at a distant view landing point by comparing a preset threshold with a target value of the initial landing point in the first dimension, thereby solving the problem of judging whether the initial landing point is a near view or a distant view.
[0084] In some embodiments, in the above step S103, determining a target near-view position point that satisfies a preset position relationship with the initial landing point position includes:
[0085] Search along the first direction and the second direction to determine multiple first position points that satisfy a preset position relationship with the initial landing point; wherein the first position points are all landing points in the external scene of a line connecting the target position of the target user's head and a point on the target car window.
[0086] A near-view position point among the plurality of first position points is determined as a target near-view position point.
[0087] For ease of understanding, the following examples are used for explanation. Since the initial landing point position is not necessarily the near-view landing point position that the user expects to click, it is necessary to further approximate the near-view that the user expects to click on the basis of the initial landing point position, and from the user's perspective relative to the car window, the expected near-view landing point position can be in several directions of up, down, left, and right relative to the initial landing point position. For example, when the first direction and the second direction are the left and right directions of the initial landing point position (position A), first, the preset position range is determined from the left and right directions of the initial landing point position, and the point falling within the preset range is determined as the first position point, and there can be multiple first position points. Then, it is determined whether the multiple first position points are near-view position points. If they are near-view position points, the first position point is determined as the target near-view position point. It should be noted that the first direction and the second direction can also be the upward or downward directions, and the corresponding method for determining the target near-view position point is similar to the above method, which will not be repeated here.
[0088] The present application searches for a foreground position point within a preset position range in different directions of the initial landing point, and then determines the foreground target object based on the foreground position point, thereby assisting the user to improve the click accuracy and solving the problem of inaccurate clicks on the initial landing point position caused by parallax.
[0089] In some embodiments, satisfying the preset position relationship includes that the distance information corresponding to the initial landing point position is less than a distance threshold, and the method further includes:
[0090] Obtain the target distance between the target user's head target position and the target car window;
[0091] Determine the distance threshold based on the target distance.
[0092] For ease of understanding, we will continue to explain the application of this processing method to a vehicle, including two cases. The first case: First, obtain the target distance between the target position of the target user's head and the target window; then, map the initial landing point in the two-dimensional image to obtain the mapping position of the initial landing point in the two-dimensional image, and determine the distance threshold of the mapping position in the two-image based on the target distance. The second case: First, obtain the target distance between the target position of the target user's head and the target window; then, map the initial landing point in the 3D space, and determine the distance threshold of the mapping position in the two-image based on the target distance.
[0093] In some embodiments, the larger the target distance is, the smaller the distance threshold is. Specifically, since the user's line of sight is focused on objects in the external scene, the finger clicking on the car window will be perceived as two separated fingers in the user's field of vision, that is, the double image of the finger will be seen. At this time, the larger the target distance is, the farther the user is from the car window, and the smaller the distance between the two separated fingers perceived by the user is, that is, the smaller the impact on the user's inaccurate clicking. Therefore, the distance threshold can be adjusted down to reduce the problem of matching non-target objects due to excessively large distance thresholds.
[0094] In some embodiments, determining a target near-view position point that satisfies a preset position relationship with the initial landing point position includes:
[0095] Determine a mapping position corresponding to the initial landing point position in the two-dimensional image, where the two-dimensional image is an image corresponding to the scene outside the vehicle, and the two-dimensional image is divided into a near-view area and a far-view area;
[0096] A target near-view position point is determined from the two-dimensional image according to the mapping position, and a distance between the target near-view position point and the mapping position is less than a distance threshold.
[0097] As an example, continue with Figure 2 When the initial landing point position is determined, the mapping position corresponding to the initial landing point position (position A) in the two-dimensional image is determined, and at the same time, a distance threshold is preset, and the position point whose distance from the mapping position is less than the distance threshold is determined as the target near-view position point.
[0098] In some embodiments, determining a target close-up position point that satisfies a preset position relationship with an initial landing point position includes: determining the target close-up position point from a scene outside the vehicle, wherein the distance between the target close-up position point and the initial landing point position in a second dimension is less than a distance threshold, and the second dimension matches a cross-section of the target vehicle window.
[0099] As an example, the cross-section of the target window is taken as the second dimension, and based on the range of the second dimension, the distance value between the target near point and the initial landing point (position A) is calculated. If the calculated distance value is less than the preset distance threshold, the target near point is determined to be the location point of the target object.
[0100] In some embodiments, determining a target object from a scene outside the vehicle according to a near-view position point of the target may include:
[0101] Inputting the two-dimensional images corresponding to the near-view position points of the target and the scene outside the vehicle into the target model;
[0102] receiving a target segmentation image corresponding to a single object segmented from a two-dimensional image by a target model based on a near-view position point of the target;
[0103] Determine the target object based on the target segmentation image.
[0104] In some embodiments, determining the target object from the scene outside the vehicle according to the target near-view position point may further include:
[0105] A two-dimensional image corresponding to an external scene of the vehicle is obtained, and the two-dimensional image is segmented into a plurality of segmented images corresponding to a single object;
[0106] Determine a target segmented image from a plurality of segmented images according to a near-view position point of the target;
[0107] Determine the target object based on the target segmentation image.
[0108] For ease of understanding, the following example is used for explanation. First, a two-dimensional image corresponding to the scene outside the vehicle is obtained, and the two-dimensional image is segmented using an image segmentation method. After segmentation, segmented images of several single objects can be obtained. For example, Figure 2 When the two-dimensional image contains multiple objects such as blue sky, white clouds, Oriental Pearl TV Tower, Huangpu River and other buildings, the multiple segmented images after image segmentation respectively include blue sky, white clouds, Oriental Pearl TV Tower, Huangpu River or other buildings; then, the target segmented image is determined according to the target close-up position point in the above step S103. For example, when Figure 2 When the target near-sighted spot in the image falls on the Oriental Pearl TV Tower, the segmentation result image containing the Oriental TV Tower is used as the target segmentation image; finally, the target object contained in the target segmentation image is determined based on the target segmentation image, for example, the target object is the Oriental Pearl TV Tower, Figure 3 The figure shows the effect after segmentation when the Oriental Pearl TV Tower is used as the target object.
[0109] The present application also provides a vehicle, which may include: a vehicle body, a target window, a target acquisition device and a processing device, wherein the target window can display an image and has a touch layer, and can obtain a click position on the target window, and the target acquisition device is used to acquire the target position of the head of the target user. Figure 5 The processing device is described. The processing device 1000 may include a click position acquisition module 1001, an initial landing position determination module 1002, a target near-view position determination module 1003, a target object determination module 1004 and a display module 1005. The click position acquisition module 1001 is used to obtain the click position of the target user on the target window, and the target window can display an image. The initial landing position determination module 1002 is used to determine the initial landing position of the line connecting the click position and the target position of the target user's head in the scene outside the vehicle. The target near-view position determination module 1003 is used to determine the target near-view position point that meets a preset position relationship with the initial landing position when the initial landing position is a distant landing position. The target object determination module 1004 is used to determine the target object from the scene outside the vehicle based on the target near-view position point. The display module 1005 is used to display the target information of the target object on the target window.
[0110] It should be noted that the various processing modules of the processing device 1000 correspond to the processing methods provided in this application, which will not be described one by one here.
[0111] The vehicle provided in the present application, because the vehicle is equipped with the processing method, can improve the user's click accuracy rate on the target object in the 3D scene outside the window of the vehicle using the transparent window, thereby improving the user experience of the vehicle.
[0112] Figure 5 An example diagram of a processing device structure using a hardware implementation of a processing system is shown. The processing device may include a corresponding module for executing each or several steps in the above flowchart. Therefore, each step or several steps in the above flowchart can be executed by a corresponding module, and the device may include one or more modules in these modules. The module may be one or more hardware modules specially configured to execute the corresponding steps, or implemented by a processor configured to execute the corresponding steps, or stored in a computer-readable medium for implementation by a processor, or implemented by some combination.
[0113] The hardware structure can be implemented using a bus architecture. The bus architecture can include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus 1100 connects various circuits including one or more processors 1200, memory 1300, and / or hardware modules together. The bus 1100 can also connect various other circuits 1400 such as peripherals, voltage regulators, power management circuits, external antennas, etc.
[0114] The bus 1100 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the figure only uses one connecting line, but does not mean that there is only one bus or one type of bus.
[0115] The processor 1200 may be a general purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof. The general purpose processor may be a microprocessor or any conventional processor.
[0116] Any process or method description in the flowchart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including performing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by a person skilled in the art of the technical field to which the embodiments of the present application belong. The processor performs the various methods and processes described above. For example, the method implementation in the present application can be implemented as a software program, which is tangibly contained in a machine-readable medium, such as a memory. In some embodiments, part or all of the software program can be loaded and / or installed via a memory and / or a communication interface. When the software program is loaded into the memory and executed by the processor, one or more steps in the method described above can be performed. Alternatively, in other embodiments, the processor can be configured to perform one of the above methods in any other appropriate manner (e.g., by means of firmware).
[0117] The logic and / or steps represented in the flowchart or otherwise described herein may be embodied in any readable storage medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions on an instruction execution system, apparatus, or device), or in combination with such instruction execution systems, apparatuses, or devices.
[0118] For the purposes of this specification, a "readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use with or in conjunction with an instruction execution system, device or apparatus. More specific examples of readable storage media (a non-exhaustive list) include the following: an electrical connection with one or more wirings (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), a fiber optic device, and a portable read-only memory (CDROM). In addition, the readable storage medium may even be paper or other suitable medium on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a memory.
[0119] It should be understood that the various parts of the present application can be implemented by hardware, software or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0120] A person skilled in the art may understand that all or part of the steps of implementing the above-mentioned implementation method may be completed by instructing related hardware through a program, and the program may be stored in a readable storage medium, which, when executed, includes one or a combination of the steps of the implementation method.
[0121] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a readable storage medium. The storage medium may be a read-only memory, a disk or an optical disk, etc.
[0122] In the description of this specification, the description with reference to the terms "one embodiment / method", "some embodiments / methods", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment / method or example are included in at least one embodiment / method or example of the present application. In this specification, the schematic representations of the above terms are not necessarily the same embodiment / method or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments / methods or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments / methods or examples described in this specification and the features of the different embodiments / methods or examples, unless they are contradictory.
[0123] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0124] Those skilled in the art should understand that the above embodiments are only for the purpose of clearly illustrating the present application, and are not intended to limit the scope of the present application. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present application.
Claims
1. A processing method, the method include: Obtaining a click position of a target user on a target vehicle window, wherein the target vehicle window is capable of displaying an image; Determine the initial landing point of the line connecting the click position and the target position of the target user's head in the scene outside the vehicle; In the case where the initial landing point is a distant view landing point, determining a target near view position point that satisfies a preset position relationship with the initial landing point; Determining a target object from the scene outside the vehicle according to the target near-view position point; The target information of the target object is displayed on the target vehicle window.
2. The method according to claim 1, wherein the initial landing point is determined as the distant landing point. include: Acquire a two-dimensional image corresponding to the scene outside the vehicle; Determining a near view area and a far view area of the two-dimensional image; Mapping the initial landing point position into the two-dimensional image to obtain a mapping position; In the case where the mapping position is within the distant view area, the landing position is determined as the distant view landing position.
3. The method according to claim 1, wherein the initial landing point is determined as the distant landing point. include: Determining a target value of the initial landing point position in a first dimension, wherein the first dimension matches a normal direction of the target vehicle window; When the target value is greater than a specific threshold, the initial landing point position is determined as the distant landing point position.
4. The method according to claim 1, wherein the determining of the target near-view position point that satisfies a preset position relationship with the initial landing point position, include: Searching along the first direction and the second direction to determine a plurality of first position points that satisfy a preset position relationship with the initial landing point position; A near-view position point among the plurality of first position points is determined as the target near-view position point.
5. The method according to claim 1, wherein the satisfying the preset position relationship comprises that the distance information corresponding to the initial landing point position is less than a distance threshold, and the method further include: Acquire a target distance between a target position of the target user's head and the target vehicle window; The distance threshold is determined according to the target distance.
6. The method according to claim 1, wherein the determining of the target near-view position point that satisfies a preset position relationship with the initial landing point position, include: Determine a mapping position corresponding to the initial landing point position in a two-dimensional image, where the two-dimensional image is an image corresponding to the scene outside the vehicle, and the two-dimensional image is divided into a near-view area and a far-view area; The target near-view position point is determined from the two-dimensional image according to the mapping position, and the distance between the target near-view position point and the mapping position is less than a distance threshold.
7. The method according to claim 1, wherein the determining of a target near-view position point that satisfies a preset position relationship with the initial landing point position, include: The target close-view position point is determined from the external vehicle scene, the distance between the target close-view position point and the initial landing point in a second dimension is less than a distance threshold, and the second dimension matches a section of the target vehicle window.
8. The method according to claim 1, wherein the target object is determined from the scene outside the vehicle according to the near-view position point of the target, include: Inputting the two-dimensional image corresponding to the target near-view position point and the scene outside the vehicle into the target model; receiving a target segmentation image corresponding to a single object segmented from the two-dimensional image by a target model based on the target near-view position point; The target object is determined according to the target segmentation image.
9. The method according to claim 1, determining a target object from the scene outside the vehicle according to the target near-view position point, include: Obtaining a two-dimensional image corresponding to the scene outside the vehicle, wherein the two-dimensional image is segmented into a plurality of segmented images corresponding to a single object; Determining a target segmented image from the multiple segmented images according to the target near-view position point; The target object is determined according to the target segmentation image.
10. A vehicle, include: Vehicle body; A target vehicle window, the vehicle window being capable of displaying an image and having a touch layer, capable of obtaining a click position on the target vehicle window; A target acquisition device, used to acquire the target position of the head of the target user; as well as A processing device, the processing device comprising: A click position acquisition module, used to obtain the click position of the target user on the target vehicle window, where the target vehicle window can display an image; An initial landing point determination module is used to determine the initial landing point of the line connecting the click position and the target position of the target user's head in the scene outside the vehicle; A target near-view position determination module, used to determine a target near-view position point that satisfies a preset position relationship with the initial landing point when the initial landing point position is a far-view landing point position; A target object determination module, used to determine the target object from the scene outside the vehicle according to the target close-up position point; The display module is used to display the target information of the target object on the target vehicle window.
