Parking position information acquisition method and device, medium and product

Abstract

The invention discloses a parking position information acquisition method and device, a medium and a product, and belongs to the technical field of vehicles. The method comprises the following steps: in response to a monitored parking intention for a vehicle, executing a first parking space recognition operation according to positioning information and a surrounding environment image of the vehicle to obtain a first parking space recognition result; in response to monitoring that the gear of the vehicle is adjusted to a parking gear, executing a second parking space recognition operation according to the transparent chassis image of the vehicle to obtain a second parking space recognition result; sending a target parking space identification result of the vehicle to user equipment associated with the vehicle; wherein the target parking space recognition result is determined based on the first parking space recognition result and the second parking space recognition result. The parking position information of the vehicle can be accurately acquired and pushed, and a user is assisted in quickly positioning the parking position of the vehicle.

Description

Technical Field

[0001] This application belongs to the field of vehicle technology, and in particular relates to a method, device, medium and product for obtaining parking location information. Background Technology

[0002] With the acceleration of urbanization and the continuous growth of car ownership, parking lots are developing towards larger scale, multi-level, and intelligent designs. Especially in large public facilities such as commercial centers, transportation hubs, and hospitals, multi-level indoor parking lots and large outdoor parking lots have become important infrastructure for alleviating parking pressure. These parking lots are typically characterized by large land areas, a large number of parking spaces, complex internal structures, and a lack of visual references.

[0003] In daily use, drivers often leave their vehicles for extended periods after parking to run errands, shop, or commute. When they return to retrieve their cars, they frequently face difficulties in quickly locating their parking spots due to the high similarity of parking lot environments, a lack of spatial orientation, and fading memory. Therefore, there is an urgent need for a solution that can assist users in quickly locating their parked vehicles. Summary of the Invention

[0004] This application provides a method, device, medium, and product for obtaining parking location information, which can accurately obtain and push vehicle parking location information, and help users quickly locate their own vehicle parking location.

[0005] In a first aspect, embodiments of this application provide a method for obtaining parking location information. The method includes: in response to detecting a parking intention for a vehicle, performing a first parking space recognition operation based on the vehicle's location information and surrounding environment images to obtain a first parking space recognition result; in response to detecting that the vehicle's gear has been adjusted to park, performing a second parking space recognition operation based on a transparent chassis image of the vehicle to obtain a second parking space recognition result; and sending the target parking space recognition result of the vehicle to a user device associated with the vehicle; wherein the target parking space recognition result is determined based on the first parking space recognition result and the second parking space recognition result.

[0006] Secondly, embodiments of this application provide a parking location information acquisition device, the device comprising: a first execution module, configured to, in response to detecting a parking intention for a vehicle, perform a first parking space recognition operation based on the vehicle's location information and surrounding environment images to obtain a first parking space recognition result; a second execution module, configured to, in response to detecting that the vehicle's gear has been adjusted to park, perform a second parking space recognition operation based on a transparent chassis image of the vehicle to obtain a second parking space recognition result; and a sending module, configured to send the target parking space recognition result of the vehicle to a user device associated with the vehicle; wherein the target parking space recognition result is determined based on the first parking space recognition result and the second parking space recognition result.

[0007] Thirdly, embodiments of this application provide a parking location information acquisition device, the device including: a processor and a memory storing computer program instructions; the processor executes the computer program instructions to implement the parking location information acquisition method as described in the first aspect.

[0008] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the parking location information acquisition method as described in the first aspect.

[0009] Fifthly, embodiments of this application provide a computer program product, wherein when the instructions in the computer program product are executed by the processor of a parking location information acquisition device, the parking location information acquisition device performs the parking location information acquisition method as described in the first aspect.

[0010] In this embodiment, firstly, in response to detecting a parking intention for the vehicle, a first parking space identification is performed based on the vehicle's location information and surrounding environment images to obtain a first parking space identification result. Secondly, in response to the vehicle shifting to park, a second parking space identification is performed based on the vehicle's transparent chassis image to obtain a second parking space identification result. Then, the first and second parking space identification results are combined to determine the vehicle's target parking space identification result, thereby improving the accuracy of parking space acquisition. Finally, the target parking space identification result can be sent to the user device associated with the vehicle to assist the user in quickly locating the vehicle's parking position. Thus, this embodiment enables accurate acquisition and push of vehicle parking location information, assisting users in quickly locating their own vehicle's parking position. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating the parking location information acquisition method provided in an embodiment of this application; Figure 2 This is one of the schematic diagrams of the dialog box provided in the embodiments of this application; Figure 3 This is a second schematic diagram of the dialog box provided in the embodiments of this application; Figure 4 This is the third schematic diagram of the dialog box provided in the embodiments of this application; Figure 5This is a schematic diagram illustrating the output of parking location information provided in an embodiment of this application; Figure 6 This is a schematic diagram of the parking location information acquisition device provided in the embodiments of this application; Figure 7 This is a schematic diagram of the parking location information acquisition device provided in the embodiments of this application. Detailed Implementation

[0013] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0014] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0015] The parking location information acquisition method of this application embodiment can be applied to a parking location acquisition device. In practical applications, the parking location acquisition device can be a vehicle or an in-vehicle terminal. Specifically, the method can be executed by the parking location acquisition device, or by a component of the parking location acquisition device, such as the processor, chip, or chip system of the parking location acquisition device, or by a logic module or software that implements all or part of the functions of the parking location acquisition device.

[0016] The method for obtaining parking location information provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0017] See Figure 1 , Figure 1 This is a flowchart of a parking location information acquisition method provided in an embodiment of this application. Figure 1As shown, the method for obtaining parking location information may include the following steps: Step 101: In response to the detection of parking intention for the vehicle, perform the first parking space recognition operation based on the vehicle's location information and surrounding environment image to obtain the first parking space recognition result.

[0018] The parking intention of a vehicle refers to the behavioral tendency of a vehicle to stop during driving, based on driver operation, environmental perception information, or preset parking instructions. In the embodiments of this application, the triggering condition for the parking space recognition operation includes detecting a parking intention. That is, if a parking intention is detected, i.e., the vehicle is about to stop, the recognition of the parking space can be triggered, and the first parking space recognition operation can be executed.

[0019] In practice, the first parking space recognition operation can be performed based on the vehicle's location information and surrounding environment images to obtain the first parking space recognition result.

[0020] It's understandable that the parking space recognition operation may succeed or fail.

[0021] For successful parking space identification, to assist users in accurately locating their vehicle's parking position, the parking space identification result may include, but is not limited to, at least one of the following: parking space number and parking space features. That is, in some embodiments, the first parking space identification result may include at least one of the following: parking space number and parking space features; and / or, the second parking space identification result may include at least one of the following: parking space number and parking space features.

[0022] Parking space features are a set of information characterizing the attributes of a parking space and the state of its surrounding environment. They can be used for parking space identification and matching, and may include, but are not limited to, at least one of the following: features of the parking space itself, and features of the surrounding environment. Features of the parking space itself cover the inherent attributes of the parking space, such as physical size, shape, and marking specifications, and are the basis for parking space identification. Features of the surrounding environment include surrounding signs and the association attributes of adjacent parking spaces, which can supplement the environmental reference information for parking space identification, help eliminate identification interference, and improve the accuracy and robustness of parking space identification.

[0023] If parking space recognition fails, the result may be: No parking space number was identified.

[0024] It should be noted that the vehicle's location information includes at least the location information of the vehicle after the parking location information acquisition device detects the parking intention. In some embodiments, the vehicle's location information may also include the location information of the vehicle before the parking location information acquisition device detects the parking intention. That is to say, the acquisition of the vehicle's location information may not depend on the detection of the parking intention, and the two can be independent of each other.

[0025] Vehicle location information can be obtained, but is not limited to, through GPS. When location information is obtained through GPS, it can be called GPS information.

[0026] The image of the vehicle's surrounding environment refers to the visual data acquired by the vehicle's onboard camera to characterize the spatial scene surrounding the vehicle, and may include, but is not limited to, at least one of the following: front view image, rear view image, left view image, right view image and surround view image of the vehicle.

[0027] The front view, rear view, left view, and right view of the vehicle are environmental visual data for a single direction. The front view image is captured by the vehicle's front-view camera, covering a horizontal field of view of 120°–150° directly in front of the vehicle and an area of ​​0–50 meters from the front of the vehicle. It includes features such as ground-level parking lines along the road ahead and the edges of parking spaces on the side of the road. The rear view image is captured by the vehicle's rear-view camera, covering a horizontal field of view of 120°–140° directly behind the vehicle and an area of ​​0–20 meters from the rear of the vehicle. It includes features such as ground-level parking lines along the road behind the vehicle and the edges of parking spaces on the side of the road. The left view image is captured by the vehicle's left-side camera, covering a horizontal field of view of 80°–100° to the left of the vehicle and an area of ​​0–10 meters from the left side of the vehicle. It includes features such as ground-level parking lines along the road to the left of the vehicle and the edges of parking spaces on the side of the road. The right view image is captured by the vehicle's right-side camera, covering a horizontal field of view of 80°–100° to the right of the vehicle and an area of ​​0–10 meters from the right side of the vehicle. It includes features such as ground-level parking lines along the road to the right of the vehicle and the edges of parking spaces on the side of the road.

[0028] The vehicle's surround view image is a panoramic visual data of the vehicle's circumferential environment. The field of view can cover a 360° omnidirectional view centered on the vehicle, with a radius of 0–15 meters. The content can include global features such as ground parking lines around the vehicle and the borders of parking spaces on the side of the road. In some embodiments, the surround view image can be acquired by the vehicle's Around View Monitor (AVM) camera; in other embodiments, the vehicle's surround view image can be obtained by stitching together the front view image, rear view image, left view image, and right view image through distortion correction, feature point matching, and image fusion algorithms.

[0029] In step 101, the vehicle's surround view image can be obtained after the parking location information acquisition device detects the parking intention. That is, after detecting the parking intention, the parking location information acquisition device can call the vehicle camera to obtain the vehicle's surround view image.

[0030] In some embodiments, when performing the first parking space identification operation, the parking space can be coarsely located based on the vehicle's positioning information, and then the parking space can be locked based on the surrounding environment image of the vehicle based on the coarse positioning result to obtain the first parking space identification result. In this way, the accuracy of parking space identification can be improved.

[0031] In some embodiments, parking space identification can be performed using a machine learning model. Optionally, the first parking space identification operation can be performed by a large model in the vehicle's AIBOX, which can be, but is not limited to, a Vision-Language Model (VLM). In this optional embodiment, the vehicle's location information and surrounding environment images can be input into the large model, and the large model can perform the first parking space identification operation based on the vehicle's location information and surrounding environment images, outputting the first parking space identification result.

[0032] In some embodiments, if a parking intention is detected, parking space boundary recognition can be performed based on the surrounding environment image of the vehicle before parking space recognition. If the parking space boundary is recognized, parking space recognition can be triggered; otherwise, it can be left untriggered. This reduces the false trigger rate of parking space recognition and improves its effectiveness.

[0033] In some implementations, optical character recognition (OCR) technology can be used to identify whether the vehicle's surrounding environment image includes the parking space border.

[0034] In other implementations, parking space bounding box recognition can be performed using machine learning models. Optionally, parking space bounding box recognition can be performed using a small model in the vehicle's Desktop Head Unit (DHU). In this optional embodiment, an image of the vehicle's surrounding environment can be input into the small model, which then performs parking space bounding box recognition based on the image, yielding the parking space bounding box recognition result.

[0035] Step 102: In response to the vehicle's gear being adjusted to parking, perform a second parking space recognition operation based on the vehicle's transparent chassis image to obtain the second parking space recognition result.

[0036] After detecting a parking intention, the parking location information acquisition device can monitor the vehicle's gear to determine whether the vehicle has completed parking. If the device detects that the vehicle has shifted to Park (P), it can confirm that the vehicle has completed parking and trigger the identification of the parking space again.

[0037] In practice, a second parking space recognition operation can be performed based on the transparent chassis image of the vehicle to obtain the second parking space recognition result.

[0038] The transparent chassis image of the vehicle is calculated by extending radially outwards from the vehicle's chassis projection area by 0.5 meters. A top-down view image with a range of 2m can cover the following areas: the projection area of ​​the chassis structure under the vehicle itself; and the ground area around the vehicle adjacent to the chassis projection area.

[0039] This application does not limit the method of acquiring the transparent chassis image of a vehicle. In some embodiments, the transparent chassis image of a vehicle can be directly acquired by a dedicated chassis camera installed at the bottom of the vehicle.

[0040] In other embodiments, the vehicle's chassis image can be synthesized from images captured by AVM cameras. In one example, the raw image data of the transparent chassis image can be captured by four AVM cameras. Optionally, AVM camera 1 can be mounted in the center of the front bumper grille, facing directly forward of the vehicle, with a field of view covering the front chassis projection area and its forward extension area, providing image data of the area below the front of the vehicle and the parking space markings in front; AVM camera 2 can be mounted near the license plate frame of the rear bumper, facing directly rear of the vehicle, with a field of view covering the rear chassis projection area and its rearward extension area, providing image data of the area below the rear of the vehicle and the parking space markings in the rear; AVM camera 3 can be mounted below the left rearview mirror housing, facing the lower left of the vehicle, with a field of view covering the left chassis projection area and its leftward extension area, providing image data of the left side of the vehicle and the parking space markings on the left; AVM camera 4 can be mounted below the right rearview mirror housing, facing the lower right of the vehicle, with a field of view covering the right chassis projection area and its rightward extension area, providing image data of the right side of the vehicle and the parking space markings on the right.

[0041] The fields of view of each camera overlap under and around the vehicle. By using image stitching and distortion correction algorithms, the four image data are fused into a unified top-down transparent chassis image, forming complete coverage of the core area and the extended area.

[0042] Since the transparent chassis image of a vehicle can show the chassis projection area under the vehicle and the ground conditions around the vehicle, and the parking space number is usually recorded inside or around the parking space, the parking space number can be obtained by identifying the parking space based on the transparent chassis image of the vehicle.

[0043] In step 102, the transparent chassis image of the vehicle can be acquired when / after the vehicle is in Park gear.

[0044] In some embodiments, characters in a transparent chassis image of a vehicle can be identified based on OCR technology to obtain a second parking space recognition result.

[0045] In some embodiments, parking space recognition can be performed using a machine learning model. Optionally, a second parking space recognition operation can be performed using a large model in AIBOX. In this optional embodiment, a transparent chassis image of the vehicle can be input into the large model, and the large model can perform a second parking space recognition operation based on the transparent chassis image of the vehicle, outputting a second parking space recognition result.

[0046] Furthermore, in the scheme of parking space identification using machine learning models, the first parking space identification operation and the second parking space identification operation can be executed by the same model or by different models, depending on the actual needs. This application embodiment does not limit this.

[0047] Step 103: Send the target parking space identification result of the vehicle to the user equipment associated with the vehicle; wherein the target parking space identification result is determined based on the first parking space identification result and the second parking space identification result.

[0048] In practice, after obtaining the first parking space identification result and the second parking space identification result, the parking location information acquisition device can determine the target parking space identification result based on the first parking space identification result and the second parking space identification result, thereby improving the accuracy of vehicle parking space acquisition.

[0049] Next, the target parking space identification result is sent to the user device associated with the vehicle. The user device associated with the vehicle can be the driver's / user's device, so that the driver / user can quickly locate the vehicle's parking position by viewing the target parking space identification result received by their own device.

[0050] The parking location information acquisition method of this application embodiment firstly detects a parking intention for a vehicle and performs a first parking space identification based on the vehicle's location information and surrounding environment images to obtain a first parking space identification result. Secondly, in response to the vehicle shifting to park, a second parking space identification is performed based on the vehicle's transparent chassis image to obtain a second parking space identification result. Then, the first and second parking space identification results are combined to determine the vehicle's target parking space identification result, thereby improving the accuracy of parking space acquisition. Finally, the target parking space identification result can be sent to the user device associated with the vehicle to assist the user in quickly locating the vehicle's parking position. Thus, this application embodiment can accurately acquire and push vehicle parking location information, assisting users in quickly locating their own vehicle's parking position.

[0051] In some embodiments, performing a first parking space recognition operation based on the vehicle's location information and surrounding environment images to obtain a first parking space recognition result may include: Based on the vehicle's location information, determine the list of candidate parking space numbers; The parking space features associated with each parking space number in the candidate parking space number list are matched with the target parking space features in the surrounding environment image of the vehicle to obtain the matching degree corresponding to each parking space number. The parking space number corresponding to the highest matching degree is determined as the first parking space identification result.

[0052] In these embodiments, parking spaces can be coarsely located based on the vehicle's location information to obtain a list of candidate parking space numbers.

[0053] Next, the surrounding environment image of the vehicle can be analyzed to obtain the parking space features in the surrounding environment image (called the target parking space features); then the target parking space features are matched with the parking space features associated with each parking space number in the candidate parking space numbers, and the parking space feature with the highest matching degree with the target parking space features is found, and its associated candidate parking space number is used as the first parking space identification result.

[0054] Therefore, by first filtering parking space numbers using the vehicle's location information, the efficiency of parking space identification can be improved while ensuring the accuracy of parking space identification. Then, by locking the parking space number based on the parking space features in the surrounding environment image of the vehicle, the parking space number can be accurately obtained.

[0055] In some embodiments, determining a list of candidate parking space numbers based on vehicle location information may include: Based on the vehicle's location information, determine the target parking zone where the vehicle is located, and the target driving trajectory of the vehicle within the target parking zone. Based on the historical parking space identification results associated with the target driving trajectory, a list of candidate parking space numbers is determined.

[0056] To make it easier for users to find parking spaces, parking lots can be divided into multiple zones, such as Zone A, Zone B, etc.

[0057] In these embodiments, the vehicle's location information includes: the vehicle's location information after the parking location information acquisition device detects the parking intention, and the vehicle's location information before the parking location information acquisition device detects the parking intention.

[0058] In practice, the target parking zone where the vehicle is located can be determined based on the positioning information obtained by the vehicle's parking location information acquisition device after detecting the parking intention, so as to narrow down the parking space identification range.

[0059] Then, by combining the vehicle's location information before the parking intention is detected by the parking location information acquisition device, the target driving trajectory of the vehicle in the target parking zone can be determined, and a list of candidate parking space numbers can be determined based on the target driving trajectory.

[0060] In some implementations, for each parking zone, the driving trajectory of each vehicle within that parking zone and its parking space identification results can be acquired and stored for subsequent parking space identification. In these implementations, determining the candidate parking space number list based on the target driving trajectory may include: matching the target driving trajectory with historical driving trajectories stored in the target parking zone, finding all historical driving trajectories with a matching degree greater than a preset value, then using the parking space identification results associated with these historical driving trajectories as the historical parking space identification results associated with the target driving trajectory, and determining the candidate parking space number list based on the historical parking space identification results associated with the target driving trajectory.

[0061] It should be noted that the historical parking space identification results associated with the target driving trajectory may include the historical parking space identification results of the vehicle itself and / or other vehicles. The specific results can be determined based on the actual situation, and this application embodiment does not limit this.

[0062] In other implementations, for each parking space, all possible driving trajectories of a vehicle to that parking space can be pre-simulated and stored, associated with the parking space number, for subsequent parking space identification. In these implementations, determining the candidate parking space number list based on the target driving trajectory may include: matching the target driving trajectory with the possible driving trajectories associated with each parking space number within the target parking area; finding all possible driving trajectories with a matching degree greater than a preset value; then using the parking space numbers associated with these possible driving trajectories as candidate parking space numbers; and determining the candidate parking space number list based on these candidate parking space numbers.

[0063] Based on this, the list of candidate parking space numbers determined according to the target driving trajectory may include at least one of the following: parking space numbers from historical parking space identification results associated with the target driving trajectory; and candidate parking space numbers.

[0064] In these embodiments, the target parking zone where the vehicle is located and the target driving trajectory of the vehicle in the target parking zone can be determined first based on the vehicle's positioning information. Then, a list of candidate parking space numbers can be determined based on the target driving trajectory. In this way, candidate parking spaces that match the vehicle's positioning information can be accurately locked, thereby improving the accuracy of parking space identification.

[0065] Of course, in other embodiments, all parking space numbers within the target parking zone can be directly used as parking space numbers in the candidate parking space numbers.

[0066] In some embodiments, before sending the target parking space identification result of the vehicle to the user equipment associated with the vehicle, the method may further include: In response to the fact that the parking space numbers of the first parking space identification result and the second parking space identification result are different, the second parking space identification result is determined as the target parking space identification result.

[0067] In these embodiments, the identification result of the first parking space can be verified by the identification result of the second parking space, thereby determining the identification result of the target parking space.

[0068] In practice, if the parking space number of the first parking space identification result is the same as that of the second parking space identification result, this parking space number can be directly used as the target parking space identification result.

[0069] If only one of the first and second parking space identification results contains a parking space number, this parking space number can be directly used as the target parking space identification result.

[0070] If the parking space numbers of the first parking space identification result and the second parking space identification result are different, considering that the second parking space identification result is obtained based on the transparent chassis image of the vehicle and its reliability is higher than that of the first parking space identification result, the confidence level of the second parking space identification result can be set to be higher than that of the first parking space identification result, and the second parking space identification result can be used as the target parking space identification result.

[0071] In these embodiments, the accuracy of the first parking space identification result can be verified by the second parking space identification result, thereby improving the accuracy of parking space identification.

[0072] In some embodiments, the first parking space identification result is obtained through a machine learning model; after determining the second parking space identification result as the target parking space identification result, the method may further include: The machine learning model is post-trained based on location information, surrounding environment images, and target parking space recognition results.

[0073] In these embodiments, the parking space numbers of the first parking space identification result and the second parking space identification result are different, and the second parking space identification result obtained based on the transparent chassis image of the vehicle is used as the target parking space identification result. Since the first parking space identification result is obtained through a machine learning model, it can be determined that the parking space identification accuracy of this machine learning model is low, and it can be post-trained.

[0074] In practice, the location information, surrounding environment images, and target parking space recognition results can be used as training samples to post-train the machine learning model, thereby improving the accuracy of subsequent parking space recognition.

[0075] In other embodiments, if the parking space number of the first parking space identification result is different from that of the second parking space identification result, a prompt message can be output to prompt the user to determine the parking space number of the vehicle. The parking space number entered by the user is then determined as the target parking space identification result. The location information, surrounding environment image and target parking space identification result are then used as training samples to post-train the machine learning model to improve the accuracy of subsequent parking space identification by the machine learning model.

[0076] A vehicle's parking intention refers to its behavioral tendency to stop during operation, based on driver input, environmental perception, or pre-set parking commands. Therefore, parking intention can be monitored through various methods.

[0077] In some embodiments, it can be determined whether a parking intention has been detected by judging whether a preset parking instruction has been received. Specifically, if a user parking instruction is received, it can be determined that a parking intention has been detected.

[0078] In other embodiments, the method may also include any of the following: In response to the detection that a vehicle has entered the parking lot and that the vehicle's speed is less than a preset value, the system determines that the vehicle intends to park. In response to the detection that the vehicle speed is less than a preset value, the system identifies the parking space boundary based on the surrounding environment image of the vehicle and detects a turning signal, thus determining that the vehicle intends to park.

[0079] In these embodiments, different parking intent monitoring methods are provided for different parking scenarios to adapt to the parking characteristics of different parking scenarios, thereby improving the reliability of parking intent recognition.

[0080] Parking scenarios may include, but are not limited to: parking within a parking lot, such as an indoor or outdoor parking lot; and parking outside a parking lot, such as parking in a roadside parking space.

[0081] For parking scenarios within a parking lot, the system can first identify whether a vehicle has entered the parking lot. If the vehicle has entered, its speed can be further monitored. If the speed is less than a preset value, a parking intention can be confirmed. The preset value can be set based on actual needs; in one example, the preset value could be 5 km / h, but it is not limited to this.

[0082] In some embodiments, whether a vehicle has entered a parking lot is identified as follows: If the first condition is met, the parking lot entrance detection is triggered. If navigation is not enabled, the first condition can be that the vehicle speed is less than a preset value. If navigation is enabled, the first condition can include: the navigation destination is the parking lot, the vehicle has arrived at the navigation destination, and the vehicle speed is less than a preset value. If the parking lot entrance is detected within the preset time period, it can be determined that the vehicle has entered the parking lot. If no parking lot entrance is detected within the preset time period, it can be determined that the vehicle has not entered the parking lot.

[0083] The preset duration can be set based on actual needs. In one example, the preset duration can be 5 minutes, but it is not limited to this.

[0084] In some embodiments, vehicle location information can be used to determine whether a vehicle has entered a parking lot.

[0085] For parking scenarios outside parking lots, the vehicle speed can be monitored first. If the vehicle speed is less than a preset value, the parking space border can be identified based on the surrounding environment image. If the parking space border is identified, the vehicle's steering wheel signal can be monitored. If the steering signal is detected, the parking intention can be determined.

[0086] In this way, accurate monitoring of parking intentions in different parking scenarios can be achieved, thereby improving the reliability of parking intention recognition.

[0087] In some embodiments, when sending the target parking space identification result of the vehicle to the user equipment associated with the vehicle, the method may further include: Send the target parking area identification result of the vehicle to the user terminal associated with the vehicle; the target parking area identification result is obtained by performing a parking area identification operation based on the vehicle's location information and front view image after detecting the parking intention; The target parking area identification result includes at least one of the parking floor identification result and the parking zone identification result; the parking location information also includes the target parking area identification result.

[0088] In these embodiments, the parking location information acquisition device can further send the vehicle's parking area identification result to the user equipment associated with the vehicle. The parking area identification result may include parking floor identification result and / or parking zone identification result; that is, the parking area can be defined by parking floors and / or parking zones. These embodiments are applicable, but not limited to, the aforementioned parking scenarios within parking lots.

[0089] In practice, parking areas can be identified based on the vehicle's location information and / or forward view images.

[0090] In some implementations, the parking floor and / or parking area of ​​a vehicle can be located using the vehicle's location information.

[0091] In some implementations, after a vehicle enters a parking lot, the vehicle's front-view camera can be triggered to capture a front view image. Then, based on OCR technology, characters in the front view image can be recognized to obtain the vehicle's parking level and / or parking zone.

[0092] In some implementations, the parking area identification operation may include: Optical character recognition is performed on the front view image of the vehicle to obtain the initial parking area recognition result; In response to the initial parking area identification result being empty, the parking area identification result is filled in based on the vehicle's location information to obtain the target parking area identification result.

[0093] In these implementation methods, an initial parking area identification result can be obtained based on the vehicle's front view image. Then, the initial parking area identification result can be improved based on the vehicle's positioning information to obtain the target parking area identification result. This can improve the reliability of the vehicle's parking area identification result.

[0094] Of course, in other implementations, independent parking area identification results can be determined based on the vehicle's location information and the forward view image, respectively. These two parking area identification results can then be cross-verified to obtain the target parking area identification result. Specifically, if the two parking area identification results are the same, that result is directly used as the target parking area identification result; if the parking floors and / or parking zones of the two parking area identification results are different, the user can be prompted to decide on the target parking area identification result, thereby improving the reliability of the vehicle's parking area identification results.

[0095] In some embodiments, the acquisition of parking location information can be performed in the background by a parking location information acquisition device, without the user's awareness. In other embodiments, the method may further include: In response to the detection of a parking intention, a dialog box between the first and second agents is displayed on the vehicle's screen; The first intelligent agent is used to input instructions in the dialog box to instruct the second intelligent agent to perform target recognition operations, including parking space recognition operations; further, the target recognition operations may also include the aforementioned parking area recognition operations.

[0096] The second agent is used to invoke the machine learning model to perform target recognition operations and input the recognition results in the dialog box.

[0097] In these embodiments, the parking location information acquisition device can "live stream" the process of acquiring parking location information through the vehicle's display screen.

[0098] In practice, a dialog box can be displayed on the vehicle's screen, where the first agent and the second agent communicate. The first agent acts as the "instructor," entering instructions and related information in the dialog box to direct the second agent to perform the parking space recognition and / or parking area recognition operations. The second agent acts as the "instructor," calling the corresponding machine learning model to perform the parking space recognition and / or parking area recognition operations based on the instructions and related information entered by the first agent, and then entering the recognition results in the dialog box.

[0099] For easier understanding, please refer to Figure 2 and Figure 3 .exist Figure 2 and Figure 3 In this context, the first intelligent agent is represented by the parking memory agent, and the second intelligent agent is represented by the AI.

[0100] like Figure 2 As shown, in response to detecting a parking intention for a vehicle, the parking memory agent can input the first instruction 21 "Perform the first parking space recognition operation based on the vehicle's location information and the following surrounding environment image" and the surrounding environment image 22 in the dialog box. In response to the first instruction 21 and the surrounding environment image 22, the AI ​​can call a large model to perform the first parking space recognition operation, and then input the first parking space recognition result 23 in the dialog box.

[0101] like Figure 3 As shown, in response to detecting that the vehicle's gear has been adjusted to park, the parking memory agent can input a second instruction 31, "Perform a second parking space recognition operation based on the following transparent chassis image of the vehicle," and a transparent chassis image 32 in the dialog box. In response to the second instruction 31 and the transparent chassis image 32, the AI ​​can invoke a large model to perform the second parking space recognition operation, and then input the second parking space recognition result 33 in the dialog box.

[0102] like Figure 4 As shown, in response to detecting a parking intention for a vehicle, the parking memory agent can enter a third instruction 41, "Perform parking area recognition operation based on the vehicle's location information and the following front view image," and a front view image 42 in the dialog box. In response to the third instruction 41 and the front view image 42, the AI ​​can invoke a large model to perform the parking area recognition operation, and then enter the parking area recognition result 43 in the dialog box.

[0103] Furthermore, in some embodiments, after the first intelligent agent obtains the parking location information (parking floor, parking zone, and / or parking space), such as... Figure 5 As shown, the control 51 corresponding to the first intelligent agent can be displayed on the vehicle's display screen, and the parking location information can be displayed in the control 51. Furthermore, the parking path of the vehicle can also be displayed.

[0104] In this way, users can obtain the vehicle's parking location information in real time through the above dialog box and monitor whether the parking location information is correct, thereby improving the accuracy of obtaining parking location information.

[0105] It should be noted that the various embodiments described in this application can be combined with each other or implemented individually without conflict, and this application does not limit this.

[0106] For ease of understanding, a specific embodiment will be used as an example: In this specific embodiment, the above-described method for obtaining parking location information can be executed by the vehicle's parking memory agent, and may include the following steps: a) When the vehicle speed is greater than 0 and less than 5 km / h, AgentManager will activate the parking memory agent (hereinafter referred to as Agent) service; b) The agent acquires continuous video frames through the intelligent driving front-facing camera and sends them to the large model, which then determines whether the vehicle is entering a parking lot. c) If no entry into the parking lot is detected for 5 consecutive minutes, the Agent exits; d) If entry into the parking lot is detected, parking floor and area recognition begins, and the small model is triggered to recognize the parking space border; e) The Agent sends frames to the large model via the intelligent driving front camera. The large model analyzes the floor and area information in the image and returns it to the Agent. f) The small model is integrated into the DHU. The Agent sends frames to the small model through the AVM camera. The small model identifies whether there is a parking space border. The Agent listens to the recognition result of the small model. g) If the small model recognizes the parking space border, send the AVM camera image frame to the large model to recognize the parking space number; h) The user engages Parking (P) and parking is complete. The identified parking floor, zone, and parking space number are sent to the vehicle's display screen and the user's mobile phone.

[0107] Based on the parking location information acquisition method provided in the above embodiments, this application also provides specific implementation methods of the parking location information acquisition device. Please refer to the following embodiments.

[0108] See Figure 6 The parking location information acquisition device provided in this application embodiment may include: The first execution module 601 is used to respond to the detection of a parking intention for a vehicle, perform a first parking space recognition operation based on the vehicle's location information and surrounding environment images, and obtain a first parking space recognition result. The second execution module 602 is used to respond to the detection that the vehicle's gear has been adjusted to parking gear, and to perform a second parking space recognition operation based on the transparent chassis image of the vehicle to obtain a second parking space recognition result; The sending module 603 is used to send the target parking space identification result of the vehicle to the user equipment associated with the vehicle; wherein the target parking space identification result is determined based on the first parking space identification result and the second parking space identification result.

[0109] The parking location information acquisition device provided in this application embodiment can realize the various processes in the method embodiment, and will not be described again here to avoid repetition.

[0110] Figure 7 A schematic diagram of the hardware structure of the parking location information acquisition device provided in an embodiment of this application is shown.

[0111] The parking location information acquisition device may include a processor 701 and a memory 702 storing computer program instructions.

[0112] Specifically, the processor 701 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0113] Memory 702 may include mass storage for data or instructions. For example, and not limitingly, memory 702 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 702 may include removable or non-removable (or fixed) media. Where appropriate, memory 702 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 702 is non-volatile solid-state memory.

[0114] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0115] The processor 701 reads and executes computer program instructions stored in the memory 702 to implement any of the parking location information acquisition methods in the above embodiments.

[0116] In one example, the parking location information acquisition device may further include a communication interface 707 and a bus 710. For example, Figure 7 As shown, the processor 701, memory 702, and communication interface 707 are connected through bus 710 and complete communication with each other.

[0117] The communication interface 707 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0118] Bus 710 includes hardware, software, or both, that couples components of a parking location information acquisition device together. For example, and not as a limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 710 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0119] Furthermore, in conjunction with the parking location information acquisition method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the parking location information acquisition methods in the above embodiments.

[0120] This application embodiment may also provide a computer program product, wherein when the instructions in the computer program product are executed by the processor of the parking location information acquisition device, the parking location information acquisition device performs any of the parking location information acquisition methods in the above embodiments.

[0121] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0122] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM, floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0123] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0124] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0125] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A parking position information acquisition method characterized by comprising: The method comprises: in response to monitoring a parking intention of a vehicle, performing a first parking space identification operation according to positioning information of the vehicle and a surrounding environment image of the vehicle, to obtain a first parking space identification result; in response to monitoring that a gear of the vehicle is adjusted to a parking gear, performing a second parking space identification operation according to a transparent ground image of the vehicle, to obtain a second parking space identification result; sending a target parking space identification result of the vehicle to a user equipment associated with the vehicle; wherein the target parking space identification result is determined based on the first parking space identification result and the second parking space identification result.

2. The method of claim 1, wherein, The first parking space identification result comprises at least one of the following: a parking space number, a parking space feature; and / or, the second parking space identification result comprises at least one of the following: a parking space number, a parking space feature.

3. The method of claim 1, wherein, The first parking space identification operation performed according to the positioning information of the vehicle and the surrounding environment image of the vehicle comprises: determining a candidate parking space number list according to the positioning information of the vehicle; matching the parking space features associated with each parking space number in the candidate parking space number list with target parking space features in the surrounding environment image of the vehicle respectively, to obtain a matching degree corresponding to each parking space number; determining a parking space number corresponding to the maximum matching degree as the first parking space identification result.

4. The method of claim 3, wherein, The candidate parking space number list is determined according to the positioning information of the vehicle, comprising: determining a target parking subzone where the vehicle is located and a target driving track of the vehicle in the target parking subzone according to the positioning information of the vehicle; determining a candidate parking space number list according to a historical parking space identification result associated with the target driving track.

5. The method of claim 1, wherein, Before the target parking space identification result of the vehicle is sent to the user equipment associated with the vehicle, the method further comprises: in response to the parking space numbers of the first parking space identification result and the second parking space identification result being different, determining the second parking space identification result as the target parking space identification result.

6. The method of claim 5, wherein, The first parking space identification result is obtained by a machine learning model; after the second parking space identification result is determined as the target parking space identification result, the method further comprises: post-training the machine learning model according to the positioning information, the surrounding environment image and the target parking space identification result.

7. The method of claim 1, wherein, The method further comprises any one of the following: in response to identifying that the vehicle enters a parking lot and a vehicle speed of the vehicle is less than a preset value, determining that the parking intention is monitored; in response to identifying that the vehicle speed of the vehicle is less than a preset value, identifying a parking space frame from a surrounding environment image of the vehicle, and detecting a steering signal, to determine that the parking intention is monitored.

8. The method of claim 1, wherein, When the target parking space identification result of the vehicle is sent to the user equipment associated with the vehicle, the method further comprises: sending a target parking area identification result of the vehicle to a user terminal associated with the vehicle; the target parking area identification result is obtained by performing a parking area identification operation according to the positioning information of the vehicle and a front view image after the parking intention is monitored. The target parking area identification result includes at least one of a parking floor identification result and a parking subarea identification result.

9. The method of claim 8, wherein, The parking area identification operation includes: performing optical character recognition on the front view image of the vehicle to obtain an initial parking area identification result; in response to the parking subarea identification result in the initial parking area identification result being empty, filling the parking subarea identification result according to the positioning information of the vehicle to obtain the target parking area identification result.

10. The method of claim 1, wherein, The method further includes: in response to monitoring the parking intention, displaying a dialog box of a first intelligent agent and a second intelligent agent through a display screen of the vehicle; The first intelligent agent is configured to input an instruction indicating the second intelligent agent to perform a target identification operation in the dialog box, and the target identification operation includes the parking space identification operation. The second intelligent agent is configured to call a machine learning model to perform the target identification operation, and input an identification result of the target identification operation in the dialog box.

11. A parking position information acquisition apparatus characterized by comprising: The device includes a processor and a memory storing computer program instructions; the processor executes the computer program instructions to implement the parking position information acquisition method in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer program instructions, and the computer program instructions are executed by the processor to implement the parking position information acquisition method in any one of claims 1 to 10.

13. A computer program product, characterised in that, The instructions in the computer program product are executed by the processor of the parking position information acquisition device, so that the parking position information acquisition device executes the parking position information acquisition method in any one of claims 1 to 10.

Images