Target object positioning method and apparatus, computer device, and storage medium

Abstract

The positioning method, device, computer device and storage medium of the target object of the application, the method comprises: acquiring object recognition results corresponding to a plurality of sensors in a vehicle respectively; determining a positioning result matched with the object recognition result according to a preset association relationship between the object recognition result and the positioning result; wherein the positioning result comprises that a target object exists in the vehicle and a seat position of the target object; and the target object comprises an object wearing an extended reality device. The scheme can directly and quickly give the positioning result. Subsequently, the user's desired screen projection object can be more accurately determined according to the positioning result.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for locating a target object. Background Technology

[0002] With the development of intelligent vehicles, extended reality (XR, including augmented reality, virtual reality, and mixed reality) technology has been applied to vehicles, greatly enriching their interactive functions. When users interact with the vehicle while wearing extended reality devices (such as XR glasses) (e.g., voice interaction, UI interaction), the vehicle controller, unsure whether the user is wearing an extended reality sensor, may display the corresponding image on the central control screen. However, the user would prefer the image to be displayed on the extended reality sensor. Therefore, it is necessary to accurately locate users wearing extended reality sensors inside the vehicle. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, apparatus, computer device, computer-readable storage medium, and computer program product capable of locating a target object, in order to address the aforementioned technical problems.

[0004] Firstly, this application provides a method for locating a target object. The method is applied to a vehicle controller and includes:

[0005] Obtain object recognition results from various sensors within the vehicle;

[0006] Based on a preset association between object recognition results and positioning results, a positioning result matching the object recognition results is determined; wherein, the positioning result includes the existence of a target object within the vehicle and the seat position of the target object; the target object includes an object wearing an extended reality device.

[0007] In one possible implementation, each of the multiple sensors is assigned a corresponding priority; the positioning result includes "unidentified"; and the acquisition of object identification results corresponding to the multiple sensors within the vehicle includes:

[0008] Obtain the object recognition results from the sensor corresponding to the first priority.

[0009] After determining the location result that matches the object recognition result data based on the preset association relationship between the object recognition result and the location result, the method further includes:

[0010] If the identification result is "unidentifiable", obtain the object identification result of the sensor corresponding to the second priority.

[0011] The object recognition results of the sensor corresponding to the first priority and the object recognition results of the sensor corresponding to the second priority are merged to obtain the merged object recognition result;

[0012] Based on the preset association between the object recognition result and the positioning result, a positioning result that matches the merged object recognition result is determined.

[0013] In one possible implementation, acquiring the object recognition results corresponding to multiple sensors within the vehicle includes:

[0014] Acquire data from various sensors inside the vehicle;

[0015] The collected data is processed according to an object recognition algorithm that matches each of the multiple sensors to obtain the corresponding object recognition result.

[0016] In one possible implementation, the preset association relationship further includes the association relationship between the object recognition result and the positioning rule; determining the positioning result matching the object recognition result based on the preset association relationship between the object recognition result and the positioning result includes:

[0017] Based on the preset association between the object recognition result and the positioning rule, a positioning rule that matches the object recognition result is determined;

[0018] The location result is determined based on the object recognition result and the location rule.

[0019] One possible implementation also includes:

[0020] If the location result indicates that a target object exists within the vehicle, in response to an interactive operation of the target object, a response screen matching the interactive operation is displayed on the extended reality device.

[0021] In one possible implementation, the positioning result further includes the absence of a target object within the vehicle; the method further includes:

[0022] If the positioning result indicates that there is no target object inside the vehicle, in response to the interaction operation of the object inside the vehicle, a response screen matching the interaction operation will be displayed on the vehicle's display screen.

[0023] In one possible implementation, the sensor includes at least one of the following:

[0024] Extended reality sensors, seat sensors, image sensors, and sound sensors.

[0025] Secondly, this application also provides a positioning device for a target object, the device comprising:

[0026] The acquisition module is used to acquire object recognition results corresponding to various sensors inside the vehicle.

[0027] The positioning module is used to determine a positioning result that matches the object recognition result based on a preset association between the object recognition result and the positioning result; wherein, the positioning result includes the existence of a target object in the vehicle and the seat position of the target object; the target object includes an object wearing an extended reality device.

[0028] In one possible implementation, each of the multiple sensors is assigned a corresponding priority; the positioning result includes unidentifiable data; and the acquisition module includes:

[0029] The first acquisition submodule is used to acquire the object recognition results of the sensor corresponding to the first priority.

[0030] The second acquisition submodule is used to acquire the object recognition result of the sensor corresponding to the second priority when the recognition result is unrecognizable;

[0031] The positioning module further includes:

[0032] The merging submodule is used to merge the object recognition results of the sensor corresponding to the first priority and the object recognition results of the sensor corresponding to the second priority to obtain the merged object recognition result.

[0033] The first determining submodule is used to determine the positioning result that matches the merged object recognition result based on the preset association relationship between the object recognition result and the positioning result.

[0034] In one possible implementation, the acquisition module includes:

[0035] The third acquisition submodule is used to acquire the collected data corresponding to various sensors in the vehicle.

[0036] The processing submodule is used to process the collected data according to the object recognition algorithm matched to each of the multiple sensors to obtain the corresponding object recognition result.

[0037] In one possible implementation, the preset association relationship further includes the association relationship between the object recognition result and the positioning rule; the positioning module includes:

[0038] The second determining submodule is used to determine the positioning rule that matches the object recognition result based on the preset association relationship between the object recognition result and the positioning rule;

[0039] The third determining submodule is used to determine the positioning result based on the object recognition result and the positioning rule.

[0040] In one possible implementation, the device further includes:

[0041] The first display module is used to, when the positioning result indicates the presence of a target object within the vehicle, respond to an interactive operation of the target object and display a response screen matching the interactive operation on the extended reality device.

[0042] In one possible implementation, the positioning result further includes the absence of a target object within the vehicle; the device further includes:

[0043] The second display module is used to display a response screen on the vehicle's display screen in response to the interactive operation of the object inside the vehicle when the positioning result indicates that there is no target object inside the vehicle.

[0044] In one possible implementation, the sensor includes at least one of the following:

[0045] Extended reality sensors, seat sensors, image sensors, and sound sensors.

[0046] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the target object positioning method described in any embodiment of this disclosure.

[0047] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the target object positioning method described in any embodiment of this disclosure.

[0048] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the target object positioning method described in any embodiment of this disclosure.

[0049] The aforementioned target object positioning method, apparatus, computer equipment, storage medium, and computer program product, by establishing a correlation between object recognition results and positioning results from multiple sensors, improves the accuracy of target object recognition and positioning compared to using a single sensor. Furthermore, compared to methods that improve positioning accuracy by increasing the complexity of a single sensor's positioning algorithm, this solution provides positioning results more directly and quickly. Subsequently, based on the positioning results, the desired projection target can be more accurately determined. Attached Figure Description

[0050] Figure 1 This is an application environment diagram of a target object localization method in one embodiment;

[0051] Figure 2 This is a first flowchart illustrating a method for locating a target object in one embodiment.

[0052] Figure 3 This is a second flowchart illustrating the target object localization method in another embodiment;

[0053] Figure 4 This is a structural block diagram of a target object positioning device in one embodiment;

[0054] Figure 5 This is a diagram of the internal structure of the vehicle controller in one embodiment;

[0055] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] The target object positioning method provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown is as follows. The vehicle includes a vehicle controller 101 and various sensors, such as in-vehicle cameras, in-vehicle microphones, seat sensors, and augmented reality sensors. The augmented reality sensors are located on augmented reality devices, which may include augmented reality glasses, wristbands, watches, or other wearable devices. The vehicle controller and the sensors are connected via a network.

[0058] In one embodiment, such as Figure 2 As shown, a method for locating a target object is provided, which can be applied to... Figure 1 Taking the vehicle controller in the example, the explanation includes the following steps:

[0059] Step S201: Obtain object recognition results corresponding to various sensors inside the vehicle.

[0060] Specifically, the various sensors in the vehicle can include a variety of in-vehicle sensors, such as in-vehicle cameras, in-vehicle microphones, seat sensors, and extended reality sensors. Some sensors have relatively simple functions; for example, a seat sensor detects whether there is an object on the corresponding seat. Other sensors have more diverse functions; for example, an in-vehicle camera captures images inside the vehicle, processes them using a pre-defined algorithm, and the resulting identification can include whether an object inside the vehicle is wearing glasses, asleep, or not wearing a seatbelt. This application only selects the identification results corresponding to wearing an extended reality device. In this embodiment, the object can include a passenger or other pre-defined objects. The target object includes an object wearing an extended reality device.

[0061] Step S203: Based on the preset association between the object recognition result and the positioning result, determine the positioning result that matches the object recognition result; wherein, the positioning result includes the existence of a target object in the vehicle and the seat position of the target object; the target object includes an object wearing an extended reality device.

[0062] Specifically, embodiments of this disclosure pre-establish the association between object recognition results and positioning results of each sensor, thereby determining the positioning result based on the sensor type and the corresponding object recognition result. In an exemplary embodiment, the positioning result includes the presence of a target object within the vehicle and the seat position of the target object. In an exemplary embodiment, a proximity sensor in the augmented reality glasses detects that an object is using the glasses; therefore, the object recognition result of the augmented reality glasses includes: one object is using the glasses. Another sensor, such as a seat sensor, detects that an object has sat down; therefore, the object recognition result of the seat sensor includes: one object has sat down. In the pre-defined association, the positioning result matching the object recognition results of the above sensors includes: a target object exists within the vehicle, and the target object is located at the position detected by the seat sensor. In another exemplary embodiment, the object recognition result of the augmented reality glasses includes: one object is using the glasses. Another sensor, such as a seat sensor, detects: two objects have sat down. Yet another sensor, such as a vehicle camera sensor, detects that an object is wearing glasses. In the preset association relationships, the positioning results that match the object recognition results of the aforementioned sensors include: the presence of a target object within the vehicle, and the target object being located at the seat position detected by the vehicle-mounted camera where the object wearing glasses is located. It should be noted that the preset association relationships can be set in ways not limited to the examples above. For instance, increasing the types of sensors or subdividing the sensor recognition results, and other modifications may be made by those skilled in the art based on the essence of this application's technology. However, as long as the functions and effects achieved are the same as or similar to those of this application, they should all be covered within the scope of protection of this application.

[0063] The aforementioned target object localization method, by establishing a correlation between object recognition results and localization results from multiple sensors, improves the accuracy of target object recognition and localization compared to using a single sensor. Furthermore, compared to methods that increase the complexity of localization algorithms for single sensors to improve accuracy, this method provides localization results more directly and quickly. Subsequently, based on the localization results, the desired projection target can be more accurately determined.

[0064] In one possible implementation, each of the multiple sensors is assigned a corresponding priority; the positioning result includes "unidentified"; and the acquisition of object identification results corresponding to the multiple sensors within the vehicle includes:

[0065] Obtain the object recognition results from the sensor corresponding to the first priority.

[0066] After determining the location result that matches the object recognition result data based on the preset association relationship between the object recognition result and the location result, the method further includes:

[0067] If the identification result is "unidentifiable", obtain the object identification result of the sensor corresponding to the second priority.

[0068] The object recognition results of the sensor corresponding to the first priority and the object recognition results of the sensor corresponding to the second priority are merged to obtain the merged object recognition result;

[0069] Based on the preset association between the object recognition result and the positioning result, a positioning result that matches the merged object recognition result is determined.

[0070] Specifically, a priority can be set for each sensor, with higher-priority sensors taking priority in using their object recognition results. In an exemplary embodiment, sensor priorities can be determined based on the complexity of the algorithm for calculating object recognition results and the complexity of interacting with the object. For example, the lower the complexity of the algorithm for calculating object recognition results or the lower the complexity of interacting with the object, the higher the sensor's priority. For instance, the object recognition result obtained by the proximity sensor in extended reality glasses does not require complex calculations and does not require interaction with the object, so the priority of this proximity sensor can be set relatively high. On the other hand, an in-vehicle microphone sensor requires voice interaction with the user to determine the location of the target object, so a lower priority can be set.

[0071] In this embodiment, the object recognition result of the first priority is used more preferentially than the object recognition result of the second priority. In an exemplary embodiment, the object recognition result of the sensor corresponding to the first priority is obtained. For example, the object recognition result of the proximity sensor for augmented reality glasses includes: two or more objects wearing augmented reality glasses. The object recognition result of the seat sensor includes: two or more objects are seated. When the number of objects recognized by the two sensors is not equal, it is impossible to give a positioning result by relying solely on these two sensors. Therefore, the object recognition result of the sensor corresponding to the second priority is obtained. For example, the object recognition result of the vehicle camera includes: one object wearing glasses. The object recognition results of the first priority sensor and the second priority sensor are merged to obtain a merged object recognition result. In the preset association relationship, the positioning result that matches the merged object recognition result includes: there is one target object, and the position of the target object is located at the position of the object wearing glasses detected by the vehicle camera.

[0072] It should be noted that the priority in this embodiment is not limited to two levels; it can also be three or more levels. In an exemplary embodiment, for example, the object recognition result corresponding to the first priority sensor includes: the object recognition result of the proximity sensor of the augmented reality glasses includes: one object wearing the augmented reality glasses; the object recognition result of the seat sensor includes: two or more objects sitting down. Based on the object recognition result corresponding to the first priority, the preset association relationship cannot provide a positioning result. At this time, it is necessary to further obtain the object recognition result corresponding to the second priority sensor, for example: the object recognition result of the vehicle camera includes two or more objects wearing glasses. At this time, based on the object recognition result corresponding to the first priority and the object recognition result corresponding to the second priority, the preset association relationship still cannot provide a positioning result. At this time, it is necessary to further obtain the object recognition result corresponding to the third priority sensor, for example, obtaining the object recognition result of the microphone sensor, for example, sending voice to the user to request the target object to reply with voice, so as to determine its location through sound source localization.

[0073] In this embodiment of the disclosure, by setting priorities for sensors and prioritizing the object recognition results of high-priority sensors, the number of complex object recognition result calculations can be reduced, and the accuracy of locating the target object can be improved without the object being perceived, thereby enhancing the user experience.

[0074] In one possible implementation, acquiring the object recognition results corresponding to multiple sensors within the vehicle includes:

[0075] Acquire data from various sensors inside the vehicle;

[0076] The collected data is processed according to an object recognition algorithm that matches each of the multiple sensors to obtain the corresponding object recognition result.

[0077] Specifically, data collected from various sensors within the vehicle is acquired. For example, sensors for the augmented reality device may include infrared sensors and radar sensors. A preset object recognition algorithm is used to calculate whether an object is wearing the augmented reality device. Another example is the data collected from the vehicle's camera, which includes image data. An object recognition algorithm, such as an image segmentation algorithm, is used to identify objects wearing glasses in the image. Alternatively, the above data can be used to directly identify objects wearing augmented reality glasses using more computationally complex object recognition algorithms, but these algorithms are time-consuming and not within the scope of this solution. In other embodiments, for example, a seat sensor uses a corresponding object recognition algorithm (pressure sensing) to determine whether there is an object on the corresponding seat. It should be noted that the types of preset sensors are not limited to the examples above, and the object recognition algorithms for the sensor object recognition results may also differ. Those skilled in the art may make other modifications based on the essence of this application, but as long as the functions and effects achieved are the same as or similar to those of this application, they should be covered within the scope of protection of this application. In an exemplary embodiment, the object recognition results of each sensor can also be completed by other sub-controllers and directly transmitted to the vehicle controller.

[0078] In the above embodiments, the collected data is processed according to an object recognition algorithm matched to each sensor to obtain object recognition results. Some object recognition results can also be used for other functions, improving the utilization rate of object recognition results.

[0079] The preset association relationship also includes the association relationship between object recognition results and positioning rules; based on the preset association relationship between object recognition results and positioning results, determining the positioning result that matches the object recognition result includes:

[0080] Based on the preset association between the object recognition result and the positioning rule, a positioning rule that matches the object recognition result is determined;

[0081] The location result is determined based on the object recognition result and the location rule.

[0082] Specifically, the preset association between object recognition results and positioning results can include a preset association between object recognition results and positioning results, as well as a preset association between object recognition results and positioning rules. In some complex cases, the preset association may not directly provide a positioning result. In such cases, the positioning rule matching the object recognition result can be determined through the preset association between the object recognition result and the positioning rule. In an exemplary embodiment, for example, the object recognition result of the proximity sensor of an augmented reality device includes: one object is wearing augmented reality glasses; the object recognition result of the seat sensor includes: two or more objects are seated; the object recognition result of the vehicle camera includes: two or more objects are wearing glasses. In this case, since it is impossible to distinguish which of the two or more objects is wearing augmented reality glasses, it is not yet possible to determine which seat the target object is located in. Through the positioning rules given in the preset association, for example, by prompting the target object with a voice: "Was the above interaction operation made by the target object?", when the target object replies "yes" or "no", the specific seat position of the target object can be determined through a preset sound source localization algorithm.

[0083] In the above embodiments, in more complex application scenarios, a preset association between object recognition results and positioning rules can be added to accurately identify and locate target objects.

[0084] In one possible implementation, the method further includes:

[0085] If the positioning result includes the presence of a target object within the vehicle, in response to an interactive operation of the target object, a response screen matching the interactive operation is displayed on the extended reality sensor.

[0086] Specifically, after identifying the target object and its specific seat position, if the target object initiates an interactive operation with the vehicle, such as playing a video, the vehicle controller displays the identified content on the target object's extended reality device. In another exemplary embodiment, when multiple target objects are identified, for example, target object A and target object B each initiate an interactive operation with the vehicle controller, target object A performs a first interactive operation, and target object B performs a second interactive operation, the vehicle controller displays the corresponding response screen on target object A's extended reality device based on the specific content of the first interactive operation. The vehicle controller displays the corresponding response screen on target object B's extended reality device based on the specific content of the second interactive operation.

[0087] In the above embodiments, by determining the location of the target object, when the target object interacts with the vehicle, the corresponding response screen is displayed on the extended reality device, avoiding display on the vehicle's display screen and better meeting the user's needs.

[0088] In one possible implementation, the positioning result further includes the absence of a target object within the vehicle; the method further includes:

[0089] If the positioning result indicates that there is no target object inside the vehicle, in response to the interaction operation of the object inside the vehicle, a response screen matching the interaction operation is displayed on the vehicle's display screen.

[0090] Specifically, the location result may also include the absence of a target object inside the vehicle. For example, the object recognition result of the extended reality device includes: 0 objects using the extended reality device; the object recognition result of the seat sensor includes: 1 object is seated. In the preset association relationship, the location result matching the object recognition result includes: 0 objects wearing extended reality devices, i.e., no target object exists. In this case, when an interaction operation is received from an object inside the vehicle, the response screen matching the interaction operation will be displayed on the vehicle's display screen.

[0091] In the above embodiments, a preset association relationship is established to determine whether a target object exists in the vehicle. When no target object exists in the vehicle, a response screen matching the interactive operation is displayed on the vehicle's display screen, which better meets the user's needs.

[0092] Figure 3 This is a second flowchart illustrating the target object localization method in another embodiment; see reference. Figure 3 As shown, the method includes:

[0093] Step S301: Acquire the data collected by various sensors inside the vehicle.

[0094] Step S303: Process the collected data according to the object recognition algorithm matched with each of the multiple sensors to obtain the corresponding object recognition result.

[0095] Specifically, data collected from various sensors within the vehicle is acquired. For example, the sensors for the augmented reality device may include infrared sensors and radar sensors. A preset object recognition algorithm is used to calculate whether an object is wearing the augmented reality device. Another example is the data collected by the vehicle's camera, which includes image data. An object recognition algorithm, such as an image segmentation algorithm, is used to identify objects wearing glasses in the image. In other embodiments, such as seat sensors, a corresponding object recognition algorithm (pressure sensing) is used to determine whether an object is on the corresponding seat.

[0096] Step S305: Determine the positioning result that matches the object recognition result based on the preset association relationship between the object recognition result and the positioning result.

[0097] In one exemplary embodiment, the positioning result includes the presence of a target object within the vehicle and the seat position of the target object. In one exemplary embodiment, a proximity sensor in the augmented reality glasses detects that an object is using the glasses; therefore, the object recognition result of the augmented reality glasses includes: one object is using the glasses. Another sensor, such as a seat sensor, detects that an object has sat down; therefore, the object recognition result of the seat sensor includes: one object has sat down. In a preset association, the positioning result matching the object recognition results of the above sensors includes: a target object exists within the vehicle, and the target object is located at the position detected by the seat sensor. In another exemplary embodiment, the positioning result includes that no target object exists within the vehicle. For example, the object recognition result of the augmented reality device includes: zero objects are using the augmented reality device; the object recognition result of the seat sensor includes: one object has sat down. In a preset association, the positioning result matching the object recognition result includes: zero objects are wearing augmented reality devices, i.e., no target object exists.

[0098] Step S307: If the positioning result indicates that a target object exists within the vehicle, in response to the interactive operation of the target object, a response screen matching the interactive operation is displayed on the extended reality device.

[0099] Specifically, once the target object and its specific seat position are identified, if the target object initiates an interactive operation with the vehicle, such as playing a video, the vehicle controller will display the identified content on the target object's extended reality device.

[0100] Step S309: If the positioning result indicates that there is no target object inside the vehicle, in response to the interaction operation of the object inside the vehicle, a response screen matching the interaction operation is displayed on the vehicle's display screen.

[0101] Based on preset associations, it determines whether the target object exists inside the vehicle. When the target object does not exist, a response screen matching the interactive operation is displayed on the vehicle's display screen, which better meets the user's needs.

[0102] In one possible implementation, Table 1 provides preset associations between object recognition results and positioning results for various sensors. (Refer to Table 1 for details.)

[0103]

[0104] Referring to Table 1, in case 1, when both the XR glasses (extended reality glasses) and the seat sensor's object recognition result is 0, the location result is "no target object found." In case 2, when both the XR glasses and the seat sensor's object recognition result is 1, the location result is "no target object found," but the XR glasses' recognition result may be a false trigger. In case 3, when both the XR glasses and the seat sensor's object recognition result is 1, the location result is "no target object found." In case 4, when both the XR glasses and the seat sensor's object recognition result is 1, the location result is "one target object found," and the target object's position matches the seat sensor's position. In case 5, when both the XR glasses and the seat sensor's object recognition result is 0, the location result is "no target object found." In case 6, when both the XR glasses and the seat sensor's object recognition result is 0, and the OMS sensor (vehicle camera)'s object recognition result is 1, the location result is "no target object found." When the sequence number is 7, the XR glasses' object recognition result is 1, the seat sensor's object recognition result is 2 or more, and the OMS sensor's object recognition result is 1. Therefore, the positioning result is that a target object exists, and the target object's position is the same as the position of the object detected by the OMS sensor. When the sequence number is 8, the XR glasses' object recognition result is 2 or more, the seat sensor's positioning recognition result is 2 or more, and the OMS sensor's object recognition result is 1. Therefore, the positioning result is that a target object exists, and the target object's position is the same as the position of the object detected by the OMS sensor. When the sequence number is 9, the XR glasses' object recognition result is 0, the seat sensor's positioning recognition result is 2 or more, and the OMS sensor's object recognition result is 2 or more. Therefore, the positioning result is that no target object exists. When the sequence number is 10, the XR glasses' object recognition result is 1, the seat sensor's positioning recognition result is 2 or more, the XR glasses' object recognition result is 2 or more, and the sound source localization sensor's object recognition result is 1. Therefore, the positioning result is 1 target object, and its position is the location of the sound source localization. When the sequence number is 11, the XR glasses have more than 2 object recognition results, the seat sensor has more than 2 positioning recognition results, the OMS sensor has more than 2 object recognition results, and the sound source localization sensor has more than 2 object recognition results. At this time, the situation is more complicated. Set the corresponding positioning rules and further locate the target object according to the positioning rules.

[0105] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0106] Based on the same inventive concept, this application also provides a target object positioning device for implementing the target object positioning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more target object positioning device embodiments provided below can be found in the limitations of the target object positioning method described above, and will not be repeated here.

[0107] In one embodiment, such as Figure 4 As shown, a target object positioning device is provided, the device 400 including:

[0108] The acquisition module 401 is used to acquire the object recognition results corresponding to various sensors in the vehicle.

[0109] The positioning module 403 is used to determine a positioning result that matches the object recognition result based on a preset association relationship between the object recognition result and the positioning result; wherein, the positioning result includes the existence of a target object in the vehicle and the seat position of the target object; the target object includes an object wearing an extended reality device.

[0110] In one possible implementation, each of the multiple sensors is assigned a corresponding priority; the positioning result includes unidentifiable data; and the acquisition module includes:

[0111] The first acquisition submodule is used to acquire the object recognition results of the sensor corresponding to the first priority.

[0112] The second acquisition submodule is used to acquire the object recognition result of the sensor corresponding to the second priority when the recognition result is unrecognizable;

[0113] The positioning module further includes:

[0114] The merging submodule is used to merge the object recognition results of the sensor corresponding to the first priority and the object recognition results of the sensor corresponding to the second priority to obtain the merged object recognition result.

[0115] The first determining submodule is used to determine the positioning result that matches the merged object recognition result based on the preset association relationship between the object recognition result and the positioning result.

[0116] In one possible implementation, the acquisition module includes:

[0117] The third acquisition submodule is used to acquire the collected data corresponding to various sensors in the vehicle.

[0118] The processing submodule is used to process the collected data according to the object recognition algorithm matched to each of the multiple sensors to obtain the corresponding object recognition result.

[0119] In one possible implementation, the preset association relationship further includes the association relationship between the object recognition result and the positioning rule; the positioning module includes:

[0120] The second determining submodule is used to determine the positioning rule that matches the object recognition result based on the preset association relationship between the object recognition result and the positioning rule;

[0121] The third determining submodule is used to determine the positioning result based on the object recognition result and the positioning rule.

[0122] In one possible implementation, the device further includes:

[0123] The first display module is used to, when the positioning result indicates the presence of a target object within the vehicle, respond to an interactive operation of the target object and display a response screen matching the interactive operation on the extended reality device.

[0124] In one possible implementation, the positioning result further includes the absence of a target object within the vehicle; the device further includes:

[0125] The second display module is used to display a response screen on the vehicle's display screen in response to the interactive operation of the object inside the vehicle when the positioning result indicates that there is no target object inside the vehicle.

[0126] In one possible implementation, the sensor includes at least one of the following:

[0127] Extended reality sensors, seat sensors, image sensors, and sound sensors.

[0128] Each module in the aforementioned target object positioning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0129] Figure 5 This is a diagram illustrating the internal structure of the vehicle controller in one embodiment. (Reference) Figure 5 As shown, XR glasses, as an extended reality device, transmit object recognition results to the vehicle controller via their proximity sensors. Seat sensors transmit object recognition results to the policy center via the vehicle control service; these results can also provide data to the vehicle control service. OMS cameras (in-vehicle cameras) capture image data inside the vehicle, obtain object recognition results through the OMS algorithm (object recognition algorithm), and transmit these results to the policy center via the OMS service. These OMS object recognition results can also provide object recognition results to the OMS service for other uses. Sound data collected by the microphone array is used to determine the location of the speaker through a sound source localization algorithm, and the object recognition results are sent to the policy center via the voice service. The policy center stores preset associations between the object recognition results and location results of each sensor. Based on these preset associations, the policy center determines a location result that matches the object recognition result; this location result includes whether a target object exists within the vehicle and the seat location of the target object; it may also include cases where no target object exists within the vehicle.

[0130] In one embodiment, a computer device is provided, which may be a terminal, such as a vehicle, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for locating a target object. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0131] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0132] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0133] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0134] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for locating a target object, characterized in that, The method is applied to a vehicle controller and includes: Obtain the object recognition results from the sensor corresponding to the first priority. Based on the preset association relationship between the object recognition result and the positioning rule, a positioning rule matching the object recognition result is determined; wherein, the preset association relationship between the object recognition result and the positioning result includes the preset association relationship between the object recognition result and the positioning result, as well as the preset association relationship between the object recognition result and the positioning rule; The location result is determined based on the object recognition result and the location rule; If the identification result is "unidentifiable", obtain the object identification result of the sensor corresponding to the second priority. The object recognition results of the sensor corresponding to the first priority and the object recognition results of the sensor corresponding to the second priority are merged to obtain the merged object recognition result; Based on the preset association between the object recognition result and the positioning result, a positioning result that matches the merged object recognition result is determined.

2. The method according to claim 1, characterized in that, The step of obtaining the object recognition result of the sensor corresponding to the first priority includes: Acquire data from various sensors inside the vehicle; The collected data is processed according to an object recognition algorithm that matches each of the multiple sensors to obtain the corresponding object recognition result.

3. The method according to claim 1, characterized in that, Also includes: If the location result indicates that a target object exists within the vehicle, in response to an interactive operation of the target object, a response screen matching the interactive operation is displayed on the extended reality device.

4. The method according to claim 1, characterized in that, The location result also includes the absence of a target object inside the vehicle; the method further includes: If the positioning result indicates that there is no target object inside the vehicle, in response to the interaction operation of the object inside the vehicle, a response screen matching the interaction operation will be displayed on the vehicle's display screen.

5. The method according to any one of claims 1 to 4, characterized in that, The sensor includes at least one of the following: Extended reality sensors, seat sensors, image sensors, and sound sensors.

6. A positioning device for a target object, characterized in that, The device includes: The first acquisition submodule is used to acquire the object recognition results of the sensor corresponding to the first priority. The positioning module is used to determine a positioning rule that matches the object recognition result based on a preset association relationship between the object recognition result and the positioning rule; and to determine a positioning result based on the object recognition result and the positioning rule; wherein the preset association relationship between the object recognition result and the positioning result includes a preset association relationship between the object recognition result and the positioning result, and a preset association relationship between the object recognition result and the positioning rule. The second acquisition submodule is used to acquire the object recognition result of the sensor corresponding to the second priority when the recognition result is unrecognizable; The merging submodule is used to merge the object recognition results of the sensor corresponding to the first priority and the object recognition results of the sensor corresponding to the second priority to obtain the merged object recognition result. The first determining submodule is used to determine the positioning result that matches the merged object recognition result based on the preset association relationship between the object recognition result and the positioning result.

7. The apparatus according to claim 6, characterized in that, The first acquisition submodule includes: The third acquisition submodule is used to acquire the collected data corresponding to various sensors in the vehicle. The processing submodule is used to process the collected data according to the object recognition algorithm matched to each of the multiple sensors to obtain the corresponding object recognition result.

8. The apparatus according to claim 6, characterized in that, The device further includes: The first display module is used to, in the case that the positioning result indicates the presence of a target object within the vehicle, respond to the interactive operation of the target object and display a response screen matching the interactive operation on the extended reality device.

9. The apparatus according to claim 6, characterized in that, The location result also includes the absence of a target object inside the vehicle; the device further includes: The second display module is used to display a response screen on the vehicle's display screen in response to the interactive operation of the object inside the vehicle when the positioning result indicates that there is no target object inside the vehicle.

10. The apparatus according to any one of claims 6 to 9, characterized in that, The sensor includes at least one of the following: Extended reality sensors, seat sensors, image sensors, and sound sensors.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the target object positioning method according to any one of claims 1 to 5.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the target object positioning method according to any one of claims 1 to 5.

13. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method for locating the target object as described in any one of claims 1 to 5.

Images