Vehicle searching method, device and equipment and storage medium

Abstract

The invention relates to a vehicle searching method, device and equipment and a storage medium, and the method comprises the steps: obtaining vehicle driving track data and vehicle exterior live-action media data when a vehicle is driven in a parking lot; aligning the vehicle driving track data and the real scene media data outside the vehicle in time; and according to the aligned vehicle driving track data and the outside real scene media data, first real scene vehicle searching navigation data is generated, and the first real scene vehicle searching navigation data is used for guiding a user to search a vehicle. By implementing the vehicle searching method provided by the invention, the problem of low vehicle searching efficiency in the prior art can be improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle search technology, and in particular to a vehicle search method, device, equipment and storage medium. Background Art

[0002] When faced with large parking lots or parking lots with complex terrain, car owners face great challenges in returning to find their cars after parking, and it often takes a long time.

[0003] In this regard, the current position of the car owner and the parking position of the vehicle can be located, and based on these two positioning points, a driving trajectory for guiding the car owner to find his vehicle can be generated.

[0004] However, when the car owner is in a relatively strange or unfamiliar parking environment, the driving trajectory generated based on the above method provides limited information. Searching for the car based on such a driving trajectory alone may cause the car owner to get lost or take too many detours during the search process, resulting in low car search efficiency. Summary of the invention

[0005] Based on this, the present application provides a vehicle finding method, device, equipment and storage medium, which can improve the problem of low vehicle finding efficiency in the prior art.

[0006] In a first aspect, the present application provides a vehicle finding method, which includes: obtaining vehicle driving trajectory data and real-scene media data outside the vehicle when the vehicle is driving in a parking lot; temporally aligning the vehicle driving trajectory data and the real-scene media data outside the vehicle; and generating first real-scene vehicle finding navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, wherein the first real-scene vehicle finding navigation data is used to guide users to find the vehicle.

[0007] In combination with the first aspect, in a first possible implementation of the first aspect, the above-mentioned generation of first real-scene vehicle search and navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle includes: truncating the vehicle driving trajectory data into multiple segments of sub-vehicle driving trajectory data; determining the sub-vehicle real-scene media data outside the vehicle corresponding to each sub-vehicle driving trajectory data according to the alignment result; creating thumbnails of each sub-vehicle real-scene media data outside the vehicle, and fusing the thumbnails of each sub-vehicle driving trajectory data with the corresponding sub-vehicle real-scene media data outside the vehicle to obtain the first real-scene vehicle search and navigation data.

[0008] In combination with the first aspect, in a second possible implementation of the first aspect, the above-mentioned generation of first real-scene vehicle search and navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle includes: in the vehicle driving trajectory data, determining the vehicle position when shooting each frame of the external environment image of the external real-scene media data, and the parking position in the vehicle driving trajectory data according to the alignment result; calculating the distance value between the vehicle position and the parking position corresponding to each frame of the external environment image, and marking the distance value between the vehicle position and the parking position in each frame of the external environment image; fusing the vehicle driving trajectory data with the marked real-scene media data outside the vehicle to generate the first real-scene vehicle search and navigation data.

[0009] In combination with the first aspect, in a third possible implementation of the first aspect, after generating the first real-scene vehicle search and navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, it also includes: if a vehicle search instruction is received, displaying the first real-scene vehicle search and navigation data through a user terminal; monitoring the user's position changes when searching for the vehicle, and calculating the actual walking speed based on the position changes; and adjusting the playback speed of the first real-scene vehicle search and navigation data based on the actual walking speed.

[0010] In combination with the third possible implementation method of the first aspect, in a fourth possible implementation method of the first aspect, the aforementioned adjusting the playback speed of the first real-life vehicle search and navigation data according to the actual walking speed includes: determining a driving trajectory according to the driving trajectory data, and dividing the driving trajectory into multiple sections; playing the first real-life vehicle search and navigation data corresponding to the current section at the expected walking speed; when it is detected that the user is walking into the next section, calculating the average actual walking speed of the previous section, and calibrating the expected walking speed based on the average actual walking speed of the previous section, and playing the first real-life vehicle search and navigation data for the next section at the calibrated expected walking speed.

[0011] In combination with the first aspect, in a fifth possible implementation manner of the first aspect, after generating the first real-scene vehicle search and navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, it also includes: comparing the first real-scene vehicle search and navigation data with the second real-scene vehicle search and navigation data of other vehicles to determine the target vehicle position when the driving trajectory of the vehicle intersects with the other vehicles; determining the first section of the first real-scene vehicle search and navigation data between adjacent target vehicle positions, and the second section of the second real-scene vehicle search and navigation data between adjacent target vehicle positions; determining whether the second section is better than the first section, and if the second section is better than the first section, then in the first real-scene vehicle search and navigation data, replacing the sub-real-scene vehicle search and navigation data corresponding to the first section with the sub-real-scene vehicle search and navigation data corresponding to the second section.

[0012] In combination with the fifth possible implementation method of the first aspect, in the sixth possible implementation method of the first aspect, the above-mentioned determination of whether the second road section is better than the first road section includes: obtaining route information corresponding to the first road section and the second road section respectively; evaluating the difficulty of finding a car corresponding to the first road section and the second road section respectively according to the route information; determining whether the difficulty of finding a car on the second road section is lower than the difficulty of finding a car on the first road section, and if the judgment result is yes, determining whether the second road section is better than the first road section.

[0013] In the second aspect, the present application also provides a vehicle finding device, which includes: an acquisition module, used to obtain vehicle driving trajectory data and real-scene media data outside the vehicle when the vehicle is driving in a parking lot; a first processing module, used to temporally align the vehicle driving trajectory data and the real-scene media data outside the vehicle; a second processing module, used to generate first real-scene vehicle finding navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, wherein the first real-scene vehicle finding navigation data is used to guide users to find the vehicle.

[0014] In combination with the second aspect, in a first possible implementation of the second aspect, the aforementioned second processing module is specifically used to: truncate the vehicle driving trajectory data into multiple segments of sub-vehicle driving trajectory data; determine the sub-vehicle external real-scene media data corresponding to each sub-vehicle driving trajectory data based on the alignment results; create thumbnails of each sub-vehicle external real-scene media data, and merge each sub-vehicle driving trajectory data with the thumbnails of the corresponding sub-vehicle external real-scene media data to obtain first real-scene vehicle search navigation data.

[0015] In combination with the second aspect, in a second possible implementation manner of the second aspect, the aforementioned second processing module is specifically used to: determine, in the vehicle driving trajectory data, the vehicle position when shooting each frame of the external environment image of the external real scene media data, and the parking position in the vehicle driving trajectory data according to the alignment result; calculate the distance value between the vehicle position and the parking position corresponding to each frame of the external environment image, and mark the distance value between the vehicle position and the parking position in each frame of the external environment image; merge the vehicle driving trajectory data with the marked external real scene media data to generate first real scene vehicle search navigation data.

[0016] In combination with the second aspect, in a third possible implementation manner of the second aspect, the car finding device also includes a third processing module, and the third processing module is used to: if a car finding instruction is received, display the first real-scene car finding navigation data through the user terminal; monitor the user's position changes when finding the car, and calculate the actual walking speed based on the position changes; adjust the playback speed of the first real-scene car finding navigation data according to the actual walking speed.

[0017] In combination with the third possible implementation method of the second aspect, in the fourth possible implementation method of the second aspect, the aforementioned third processing module is specifically used to: determine the driving trajectory based on the driving trajectory data, and divide the driving trajectory into multiple sections; play the first real-life vehicle search and navigation data corresponding to the current section at the expected walking speed; when it is detected that the user is walking into the next section, calculate the average actual walking speed of the previous section, and calibrate the expected walking speed based on the average actual walking speed of the previous section, and play the first real-life vehicle search and navigation data of the next section at the calibrated expected walking speed.

[0018] In combination with the second aspect, in a fifth possible implementation manner of the second aspect, the vehicle finding device also includes a fourth processing module, and the fourth processing module is used to: compare the first real-scene vehicle finding navigation data with the second real-scene vehicle finding navigation data of other vehicles to determine the target vehicle position when the vehicle and the other vehicles' driving trajectories intersect; determine the first section of the first real-scene vehicle finding navigation data between adjacent target vehicle positions, and the second section of the second real-scene vehicle finding navigation data between adjacent target vehicle positions; determine whether the second section is better than the first section, and if the second section is better than the first section, then in the first real-scene vehicle finding navigation data, replace the sub-real-scene vehicle finding navigation data corresponding to the first section with the sub-real-scene vehicle finding navigation data corresponding to the second section.

[0019] In combination with the fifth possible implementation mode of the second aspect, in the sixth possible implementation mode of the second aspect, the aforementioned fourth processing module is specifically used to: obtain route information corresponding to the first section and the second section respectively; evaluate the difficulty of finding a car corresponding to the first section and the second section respectively according to the route information; determine whether the difficulty of finding a car on the second section is lower than that on the first section, and if the judgment result is yes, determine whether the second section is better than the first section.

[0020] In a third aspect, the present application also provides a vehicle finding device, which includes a processor and a memory, wherein the processor and the memory are connected via a bus; the processor is used to execute multiple instructions; the memory is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executed by a vehicle finding method such as the first aspect or any one of the embodiments of the first aspect.

[0021] In a fourth aspect, the present application further provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor and executed by a vehicle-finding method such as the first aspect or any one of the embodiments of the first aspect.

[0022] In summary, the present application provides a vehicle finding method, device, equipment and storage medium, wherein the present application generates first real-scene vehicle finding navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, so that the user can see both the driving trajectory and the real-time scene on the driving trajectory by displaying the first real-scene vehicle finding navigation data. Combining the trajectory and the real-time scene can achieve quick vehicle finding, increase the intuitiveness of vehicle finding, reduce the difficulty of vehicle finding, and thus improve the problem of low vehicle finding efficiency in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the architecture of a vehicle search system in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of a process flow of a vehicle search method in an embodiment of the present application;

[0025] Figure 3 is a schematic block diagram of a vehicle finding device in an embodiment of the present application;

[0026] Figure 4 This is a structural block diagram of a vehicle-finding device in one embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] The present application provides a method for finding a car. The method can be used in a scenario where a user is looking for a parked car in a parking lot, so that the user can provide first real-scene car-finding navigation data that combines a driving trajectory and a real-time scene to help the car owner to perform real-scene car-finding navigation, thereby achieving rapid car-finding, increasing the intuitiveness of car-finding, and reducing the difficulty of car-finding, thereby improving the problem of low car-finding efficiency in the prior art.

[0029] The vehicle search method provided in the present application can be applied to a vehicle search device and a vehicle search equipment. The vehicle search device and the vehicle search equipment can be a user terminal, a vehicle (or a vehicle-mounted terminal) or a server. The user terminal can include a mobile phone, a tablet computer, a smart watch, etc. The server can be a single server or a server cluster. Figure 1 , is a schematic diagram of the architecture of a car-finding system provided in this application. Figure 1 The vehicle search system shown includes a vehicle 10, a user terminal 20, and a server 30. Depending on the application scenario, Figure 1The communication mode established between the various devices in the vehicle search system shown can be between the vehicle 10 and the user terminal 20, or between the vehicle 10 and the server 30, and between the server 30 and the user terminal 20. It should be noted that the vehicle search system referred to in this application is not limited to Figure 1 The vehicle finding system shown, the vehicle finding system referred to in this application may include more or fewer devices on this basis.

[0030] Combined in an implementable way Figure 1 The vehicle search system and method shown can be executed by the vehicle 10. Specifically, the vehicle 10 can record the vehicle driving trajectory data and the images or videos taken along the driving trajectory (i.e., the real-scene media data outside the vehicle), and then process these data to obtain the first real-scene vehicle search navigation data, and then send the first real-scene navigation data to the user terminal 20 for display. Specifically, the vehicle 10 sends the first real-scene navigation data to the user terminal 20 for display in the manner that the vehicle 10 directly sends the first real-scene navigation data to the user terminal 20 for display, or the vehicle 10 uploads the first real-scene vehicle search navigation data to the server 30, and the server 30 sends the first real-scene vehicle search navigation data to the user terminal 20 for display.

[0031] In another practicable manner, combining Figure 1 In the vehicle search system shown, the vehicle search method can be executed by the user terminal 20. Specifically, the vehicle 10 can record the vehicle driving trajectory data and the images or videos taken along the driving trajectory, and then send these data to the user terminal 20. After receiving these data, the user terminal 20 will process these data to obtain the first real-life vehicle search navigation data, and then display it. Figure 1 From the vehicle search system shown in the figure, the vehicle search method can be executed by the server 30. The vehicle 10 can record the driving trajectory data and the images or videos taken along the driving trajectory, and then upload these data to the server 30. After receiving these data, the server 30 processes these data to obtain the first real-scene vehicle search navigation data, and then sends the first real-scene navigation vehicle search data to the user terminal 20 for display.

[0032] The vehicle 10 can start the car search function after detecting an event that triggers the start of the car search function. Specifically, the vehicle 10 can start the car search function after detecting a touch operation such as a click operation on a button displayed on the vehicle display screen for starting the car search function, thereby realizing that the car search function is actively triggered by the car owner. Among them, the button displayed on the vehicle display screen for starting the car search function includes but is not limited to a car search function button in a car search application installed for the vehicle 10. Alternatively, the vehicle 10 can start the car search function after using the vehicle camera to capture a special scene (such as capturing a vehicle entering a garage ramp or detecting a railing lift at the entrance of a parking lot), thereby realizing that the vehicle automatically triggers the car search function. The vehicle 10 can also confirm with the owner whether to start the car search function through the vehicle display screen after detecting an event that triggers the start of the car search function, and start the car search function after detecting that the owner confirms the instruction to start the car search function.

[0033] The vehicle 20 can send the car navigation route map to the user terminal 20 or the server 30 after the driver gets off the vehicle, the door is opened, the door is opened and then closed, the vehicle is powered off, etc. In addition, the vehicle 10 can select the target device (such as the user terminal or server to which the car navigation route map is to be sent) based on the current communication conditions (such as the signal quality of the parking lot). The vehicle 10 can also select the transmission path (Bluetooth, 5G, etc.) for the target device based on the current communication conditions.

[0034] In order to better understand the vehicle search method proposed in this application, this application also provides an embodiment of the vehicle search method, such as Figure 2 As shown, next, this application takes the vehicle search device as the execution subject and describes the method in detail:

[0035] 100: Acquire vehicle driving trajectory data and real-scene media data outside the vehicle when the vehicle is driving in the parking lot;

[0036] 200: Temporally aligning the vehicle driving trajectory data and the real scene media data outside the vehicle;

[0037] 300: Generate first real-scene vehicle search navigation data according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle.

[0038] For step 100, when the vehicle finding device is a user terminal, the vehicle finding device receives the vehicle driving trajectory data and the real-scene media data outside the vehicle sent by the vehicle to obtain the vehicle driving trajectory data and the real-scene media data outside the vehicle; when the vehicle finding device is a vehicle, the vehicle finding device directly obtains the vehicle driving trajectory data and the real-scene media data outside the vehicle from local storage.

[0039] In an embodiment of the present application, the vehicle driving trajectory data includes a vehicle position sequence of multiple consecutive vehicle positions of the vehicle, and a timestamp corresponding to each vehicle position.

[0040] In an optional implementation, the vehicle driving trajectory data may be obtained by collecting the actual position coordinates of the vehicle during driving through the vehicle's onboard positioning system. The onboard positioning system may be a GPS positioning system or a satellite positioning system, and the like.

[0041] In another optional embodiment, the above-mentioned vehicle driving trajectory data can be generated by collecting the actual driving route data of the vehicle, and the actual driving route data includes the steering wheel rotation angle of the vehicle during driving and the actual driving distance of the vehicle, wherein the actual driving distance of the vehicle can be calculated by collecting the number of circles of wheel rotation during driving. It can be understood that in the vehicle driving trajectory data obtained in this way, the vehicle position is not the actual position of the vehicle, but a virtual position based on the virtual coordinates established during data collection. The collection of this type of vehicle driving trajectory data does not need to rely on the vehicle positioning system and is suitable for use in underground parking lots without positioning signals.

[0042] The real-scene media data outside the vehicle is obtained by capturing the vehicle camera. The number of the vehicle camera can be one or more, and the vehicle camera can be set on the roof or other positions of the vehicle. The real-scene media data outside the vehicle includes a sequence of vehicle environment images of a plurality of continuous vehicle environment images outside the vehicle, and the timestamp corresponding to each vehicle environment image. The sequence of vehicle environment images can be obtained in the following ways: the vehicle captures a group or a picture of the vehicle environment image every time it travels a certain distance, such as capturing a group or a picture of the vehicle environment image every time the vehicle travels 1 meter; or, the vehicle captures a group or a picture of the vehicle environment image every time a certain period of time passes, such as capturing a group or a picture of the vehicle environment image every 1 second; or, the vehicle captures a group or a picture of the vehicle environment image every time it arrives at a special location, and the special location includes a corner, an intersection, or a ramp on the upper and lower floors of a garage, etc.

[0043] Before the vehicle search device obtains the vehicle driving trajectory data and the real-scene media data outside the vehicle in step 100, the vehicle 10 records the driving data, and the driving data includes the vehicle driving trajectory data and the real-scene media data outside the vehicle when the vehicle is driving in the parking lot. The driving data may be recorded by the vehicle 10 after detecting the first event. The first event may be the vehicle starting the vehicle search function. Optionally, the first event may also be special scenes such as the vehicle entering the garage ramp, the lifting of the railing at the entrance of the parking lot, the instruction to start the vehicle search function or the instruction to confirm the start of the vehicle search function, etc. The driving data may be recorded after the vehicle detects the second event. The second event may be the vehicle parking in the parking space. Optionally, the second event may also be the driver getting off the vehicle, the door opening, the door opening and closing, the vehicle powering off, and so on.

[0044] For step 200, in order to achieve time alignment, the vehicle search device reads the timestamps corresponding to each vehicle position in the vehicle driving trajectory data, and the timestamps corresponding to each vehicle exterior environment image in the vehicle exterior real-scene media data, and then aligns the vehicle positions and vehicle exterior environment images with the same or similar timestamps, that is, matches and associates the vehicle positions and vehicle exterior environment images with the same or similar timestamps, so that each vehicle position corresponds to an vehicle exterior environment image.

[0045] If there are multiple images of the exterior environment with the same or similar timestamps as a certain vehicle position, the image with the best quality in terms of pixels, clarity, brightness and road integrity is selected from the multiple images as the image matching and associated with the certain vehicle position, and the other images of the multiple images of the exterior environment are deleted; or the images of the exterior environment are fused to obtain a high-quality image, and the high-quality image is used as the image matching and associated with the certain vehicle position.

[0046] When the acquisition frequencies of vehicle driving trajectory data and external real-scene media data are different, the timestamps of the vehicle position and the external environment image may not be exactly the same and one-to-one corresponding. Therefore, when the timestamps are the same, the vehicle position and the external environment image with the same timestamp are preferentially associated; when the timestamps are different, the proximity principle is adopted to associate the vehicle position and the external environment image with the closest timestamp; if there is a vehicle position without a corresponding image, the interpolation method is used to generate the external environment image corresponding to the vehicle position; if there is an external environment image without a corresponding position, the interpolation method is used to estimate the vehicle position corresponding to the external environment image, so that the vehicle position in the vehicle driving trajectory data and the external environment image in the external real-scene media data are associated one-to-one, thereby realizing the temporal alignment of the vehicle driving trajectory data and the external real-scene media data, and then the vehicle search device can subsequently determine the vehicle position when each frame of the external environment image of the external real-scene media data is captured according to the alignment result.

[0047] For step 300, the first real-scene car search navigation data includes a driving trajectory in the parking lot, and a real scene of the parking lot associated with different vehicle positions on the driving trajectory. The first real-scene car search navigation data is used to guide the user to find the car. The car search device can directly fuse the aligned vehicle driving trajectory data with the real-scene media data outside the vehicle, or fuse the vehicle driving trajectory data with a thumbnail of the real-scene media data outside the vehicle, or fuse the vehicle driving trajectory data with the real-scene media data outside the vehicle marked with a distance value from the parking position, to generate the first real-scene car search navigation data. In this regard, the present application provides some implementable methods, such as:

[0048] In an implementable manner, the above-mentioned generation of first real-scene vehicle search and navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle includes: truncating the vehicle driving trajectory data into multiple segments of sub-vehicle driving trajectory data; determining the sub-vehicle real-scene media data outside the vehicle corresponding to each sub-vehicle driving trajectory data according to the alignment result; creating thumbnails of each sub-vehicle real-scene media data outside the vehicle, and fusing the thumbnails of each sub-vehicle driving trajectory data with the corresponding sub-vehicle real-scene media data outside the vehicle to obtain the first real-scene vehicle search and navigation data.

[0049] Among them, the vehicle search device can truncate the vehicle driving trajectory data into multiple segments of vehicle driving trajectory data equally divided by driving time or driving distance according to the principle of equally dividing the driving time or driving distance; or, take the sudden change position point in the vehicle position as the interception point, and truncate the vehicle driving trajectory data into multiple segments of vehicle driving trajectory data. For example, the sudden change position point in the vehicle position can refer to a position point where the horizontal axis or the vertical axis suddenly changes after remaining unchanged for a period of time, and this position point is usually a turning point; or take the position point at a special location as the interception point, and truncate the vehicle driving trajectory data into multiple segments of vehicle driving trajectory data. The special location includes a corner, an intersection, or a ramp on the upper and lower floors of a garage.

[0050] According to the alignment results obtained previously, the sub-vehicle external real-scene media data corresponding to the driving trajectory data of each sub-vehicle is determined, and a thumbnail is generated in at least one external environment image in each sub-vehicle external real-scene media data, for example, part or all of the images in the at least one external environment image are synthesized into a video thumbnail, or the at least one external environment image is fused to obtain a thumbnail, or an external environment image with the best quality is selected from the at least one external environment image as a thumbnail. After the thumbnails of the external real-scene media data of each sub-vehicle are obtained, the driving trajectory data of each sub-vehicle is fused with the thumbnail of the corresponding external real-scene media data of the sub-vehicle to obtain the first real-scene car search navigation data. The fusion method includes but is not limited to superposition, splicing, etc., so that the first real-scene car search navigation data after fusion can display both the driving trajectory and the thumbnail of the real scene, so as to help users to intuitively find the car, thereby improving the car search efficiency.

[0051] In one embodiment, when the car search device is a user terminal, when the car search device receives a click instruction for a thumbnail, in response to the click instruction, the thumbnail is displayed in a pop-up window or the like, and the pop-up window also includes a close button for closing the thumbnail. In addition, when the car search device receives a zoom instruction for a thumbnail, in response to the zoom instruction, the thumbnail is zoomed in and out, and the zoom instruction includes a zoom-in instruction and a zoom-out instruction.

[0052] In another feasible manner, the aforementioned method generates the first real-scene vehicle search and navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, including: determining the vehicle position when shooting each frame of the external environment image of the external vehicle real-scene media data and the parking position in the vehicle driving trajectory data according to the alignment result in the vehicle driving trajectory data; calculating the distance value between the vehicle position and the parking position corresponding to each frame of the external environment image, and marking the distance value between the vehicle position and the parking position in each frame of the external environment image; fusing the vehicle driving trajectory data with the marked real-scene media data outside the vehicle to generate the first real-scene vehicle search and navigation data.

[0053] Among them, the present application associates the vehicle position in the vehicle driving trajectory data and the external environment image in the external real-scene media data through the aforementioned alignment operation, so that the vehicle search device can determine the vehicle position when each frame of the external environment image of the external real-scene media data is shot according to the alignment result, and obtain the vehicle position last recorded in the vehicle driving trajectory data as the parking position, and then calculate the distance value between the vehicle position corresponding to each frame of the external environment image and the parking position on the driving trajectory, and obtain the distance value corresponding to each frame of the external environment image.

[0054] The car finding device marks the distance value corresponding to each frame of the external environment image on each external environment image. The marking method includes but is not limited to at least one of text marking, image marking, gesture marking and voice marking. Then the car finding device merges the vehicle driving trajectory data with the marked external real-scene media data, so that the generated first real-scene car finding navigation data can not only display the driving trajectory, but also prompt the position of each vehicle position on the driving trajectory and the parking position, so as to help users find the car intuitively, thereby improving the car finding efficiency.

[0055] After the first real-life car search navigation data is generated in step 300, the first real-life car search navigation data can be displayed through the user terminal to help the user find the car. In order to improve the car search effect, the first real-life car search navigation data can be automatically played without manual adjustment by the user. In this regard, the present application provides some possible implementation methods, such as:

[0056] In an practicable manner, the playback speed of the first real-life car navigation data is a default speed, which is the mean, median or mode of the walking speeds of all users, and the default speeds corresponding to all users are consistent;

[0057] In another feasible manner, the playback speed of the first real-scene car search and navigation data is adjusted according to the actual walking speed of the user, so that the first real-scene car search and navigation data is linked with the actual behavior of the user, which greatly improves the car search effect. Specifically, after the first real-scene car search and navigation data is generated according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, it also includes: if a car search instruction is received, the first real-scene car search and navigation data is displayed through the user terminal; the position change of the user when searching for the car is monitored, and the actual walking speed is calculated according to the position change; the playback speed of the first real-scene car search and navigation data is adjusted according to the actual walking speed.

[0058] Among them, if the car finding device is a user terminal, then when the car finding device receives the car finding instruction sent by the user through the touch screen or button, the car finding device directly obtains the first real-scene car finding navigation data in the local storage and displays the first real-scene car finding navigation data; if the car finding device is a vehicle, then when the car finding device receives the vehicle finding instruction sent by the user terminal, the car finding device sends the first real-scene car finding navigation data to the user terminal, so that the user terminal displays the first real-scene car finding navigation data.

[0059] In addition, when monitoring the actual walking speed of the user when looking for a car, considering the poor signal of the parking lot, if the speed is detected by using GPS in real time, there may be a delay, resulting in the playback speed not matching the actual walking speed of the user. In this regard, the present application provides some possible implementation methods, such as:

[0060] In one practicable manner, the vehicle search device may detect the actual walking speed of the user in real time through an acceleration sensor and a speed sensor on the user terminal, without detecting the actual walking speed or actual location of the user through GPS;

[0061] In another feasible manner, the car finding device divides the driving trajectory into multiple sections to reduce the reliance on GPS while saving computing resources and avoiding frequent adjustments. Each time the next section is entered, the playback speed of the first real-life car finding navigation data is adjusted according to the actual walking speed of the user in the previous section. Specifically, the aforementioned adjustment of the playback speed of the first real-life car finding navigation data according to the actual walking speed includes: determining the driving trajectory according to the driving trajectory data, and dividing the driving trajectory into multiple sections; playing the first real-life car finding navigation data corresponding to the current section at the expected walking speed; when it is detected that the user enters the next section on foot, calculating the average actual walking speed of the previous section, calibrating the expected walking speed according to the average actual walking speed of the previous section, and playing the first real-life car finding navigation data of the next section at the calibrated expected walking speed.

[0062] After the first real-scene car search navigation data is generated in step 300, the car search device can also use the second real-scene car search navigation data of other vehicles to optimize the first real-scene car search navigation data of the vehicle to further improve the car search efficiency. Because the user may not be familiar with the parking lot or need to look for a parking space everywhere, the driving trajectory of the user's vehicle may not be optimal. If the user searches for the vehicle completely according to the driving trajectory when looking for a parking space, the car search efficiency may still be very low. In this regard, the present application also provides an implementable method. Specifically, according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, After generating the first real-scene vehicle search and navigation data, the first real-scene vehicle search and navigation data is compared with the second real-scene vehicle search and navigation data of other vehicles to determine the target vehicle position when the vehicle and the other vehicles' driving trajectories intersect; determine the first road section between adjacent target vehicle positions of the first real-scene vehicle search and navigation data, and the second road section between adjacent target vehicle positions of the second real-scene vehicle search and navigation data; determine whether the second road section is better than the first road section, and if the second road section is better than the first road section, then in the first real-scene vehicle search and navigation data, replace the sub-real-scene vehicle search and navigation data corresponding to the first road section with the sub-real-scene vehicle search and navigation data corresponding to the second road section.

[0063] Among them, the car finding device compares the driving trajectory indicated by the first real-scene car finding navigation data with the driving trajectory indicated by the second real-scene car finding navigation data of other vehicles, so as to compare the target vehicle position when the two driving trajectories of the local vehicle and the other vehicles intersect. There may be multiple target vehicle positions. The car finding device confirms in turn whether the road sections between adjacent target vehicle positions overlap. If not, it determines whether the second road section between adjacent vehicle positions of other vehicles is better than the second road section between the adjacent vehicle positions of the local vehicle. If the judgment result is yes, data replacement is performed, so that the replaced first real-scene car finding navigation data can help users find cars more efficiently.

[0064] In order to determine whether the second road section is better than the first road section, the car-finding device can evaluate at least one item of the distance length, car-finding difficulty and travel time of each road section. Taking the car-finding difficulty as an example, the present application provides a specific and implementable method. Specifically, the aforementioned determination of whether the second road section is better than the first road section includes: obtaining route information corresponding to the first road section and the second road section respectively; evaluating the car-finding difficulty corresponding to the first road section and the second road section respectively according to the route information; determining whether the car-finding difficulty of the second road section is lower than that of the first road section. If the judgment result is yes, determining whether the second road section is better than the first road section.

[0065] Among them, the route information includes at least one of the following: the distance of the parking route, the attribute information of the obstacles on the parking route, the attribute information of the environmental prompts distributed around the parking route, and the evaluation data of the difficulty of finding a car for the parking route. The attribute information of the obstacle may include the type of obstacle, the size of the obstacle, the number of obstacles, etc. The attribute information of the environmental prompt may include the type of environmental prompt, the size of the environmental prompt, the number of environmental prompts, etc. The evaluation data of the difficulty of finding a car may be collected after determining that the vehicle has been found. The evaluation data of the difficulty of finding a car may be, for example, the difficulty of level 1, level 2, etc., and the higher the level, the greater the difficulty. In addition to being expressed in the form of level, the evaluation data of the difficulty of finding a car may also be expressed in the form of difficulty of 1 star, 2 stars, etc., and the higher the star rating, the greater the difficulty. The evaluation data of the difficulty of finding a car may also be expressed in the form of a specific score, which is not limited here. In addition, the evaluation data of the difficulty of finding a car may be the evaluation data of the difficulty of finding a car within the target time range, for example, the evaluation data of the difficulty of finding a car in the past month or the past six months.

[0066] In some embodiments, the vehicle search device determines whether the vehicle repeatedly passes through the same road section based on the first real-scene vehicle search navigation data. If the vehicle repeatedly passes through the same road section, the first real-scene vehicle search navigation data is optimized using the repeatedly passed road section. Whether the vehicle repeatedly passes through the same road section can be determined in the following manner: the number of times the same environmental prompt object is identified is determined based on the real-scene media data outside the vehicle. If the number is greater than 2, it means that the vehicle repeatedly passes through the same road section. Or, the number of times the same license plate is identified is determined based on the real-scene media data outside the vehicle. If the number is greater than 2, it means that the vehicle repeatedly passes through the same road section. The method of optimizing the driving trajectory using the repeatedly passed road section can be: deleting the data of the repeated driving trajectory in the first real-scene vehicle search navigation data to obtain the deleted first real-scene vehicle search navigation data. By displaying the deleted first real-scene vehicle search navigation data, the user can be helped to find the car faster, thereby improving the efficiency of finding the car.

[0067] The present application also provides a vehicle finding device. The embodiment of the present application can divide the functional modules of the device according to the above method example. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. Specifically, the vehicle finding device includes: an acquisition module 310, which is used to obtain vehicle driving trajectory data and real-scene media data outside the vehicle when the vehicle is driving in the parking lot; a first processing module 320, which is used to align the vehicle driving trajectory data and the real-scene media data outside the vehicle in time; a second processing module 330, which is used to generate first real-scene vehicle finding navigation data according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, wherein the first real-scene vehicle finding navigation data is used to guide the user to find the vehicle.

[0068] In one possible implementation, the aforementioned second processing module 330 is specifically used to: truncate the vehicle driving trajectory data into multiple segments of sub-vehicle driving trajectory data; determine the sub-vehicle external real-scene media data corresponding to each sub-vehicle driving trajectory data based on the alignment result; create thumbnails of each sub-vehicle external real-scene media data, and merge each sub-vehicle driving trajectory data with the thumbnails of the corresponding sub-vehicle external real-scene media data to obtain the first real-scene vehicle navigation data.

[0069] In one possible implementation, the aforementioned second processing module 330 is specifically used to: determine, in the vehicle driving trajectory data, the vehicle position when shooting each frame of the external environment image of the external real scene media data, and the parking position in the vehicle driving trajectory data according to the alignment result; calculate the distance value between the vehicle position and the parking position corresponding to each frame of the external environment image, and mark the distance value between the vehicle position and the parking position in each frame of the external environment image; merge the vehicle driving trajectory data with the marked external real scene media data to generate the first real scene vehicle search navigation data.

[0070] In one possible implementation, the car-finding device also includes a third processing module 340, which is used to: if a car-finding instruction is received, display the first real-scene car-finding navigation data through the user terminal; monitor the user's position changes when searching for the car, and calculate the actual walking speed based on the position changes; and adjust the playback speed of the first real-scene car-finding navigation data based on the actual walking speed.

[0071] In one possible implementation, the aforementioned third processing module 340 is specifically used to: determine the driving trajectory based on the driving trajectory data, and divide the driving trajectory into multiple sections; play the first real-life vehicle search and navigation data corresponding to the current section at the expected walking speed; when it is detected that the user is walking into the next section, calculate the average actual walking speed of the previous section, and calibrate the expected walking speed based on the average actual walking speed of the previous section, and play the first real-life vehicle search and navigation data of the next section at the calibrated expected walking speed.

[0072] In one embodiment, the vehicle finding device also includes a fourth processing module 350, which is used to: compare the first real-scene vehicle finding navigation data with the second real-scene vehicle finding navigation data of other vehicles to determine the target vehicle position when the vehicle intersects with the driving trajectories of other vehicles; determine the first section of the first real-scene vehicle finding navigation data between adjacent target vehicle positions, and the second section of the second real-scene vehicle finding navigation data between adjacent target vehicle positions; determine whether the second section is better than the first section, and if the second section is better than the first section, then in the first real-scene vehicle finding navigation data, replace the sub-real-scene vehicle finding navigation data corresponding to the first section with the sub-real-scene vehicle finding navigation data corresponding to the second section.

[0073] In one possible implementation, the aforementioned fourth processing module 350 is specifically used to: obtain route information corresponding to the first section and the second section respectively; evaluate the difficulty of finding a car corresponding to the first section and the second section respectively according to the route information; determine whether the difficulty of finding a car on the second section is lower than the difficulty of finding a car on the first section, and if the judgment result is yes, determine whether the second section is better than the first section.

[0074] The present application also provides a vehicle-finding device, which may include: a processor 410 and a memory 420. The processor 410 and the memory 420 are connected via a bus 430. The processor 410 is used to execute multiple instructions; the memory is used to store multiple instructions, which are suitable for being loaded by the processor and executed as in the vehicle-finding method in the above embodiment. Among them, the processor may be an electronic control unit (ECU), a central processing unit (CPU), a general-purpose processor, a coprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of 5SP and a microprocessor, and the like. In this embodiment, the processor may be a single-chip microcomputer, and various control functions may be implemented by programming the single-chip microcomputer. The processor has the advantages of powerful computing power and fast processing. Specifically, the processor 410 is used to execute the function of the acquisition module 310, which is used to obtain the vehicle driving trajectory data and the real-scene media data outside the vehicle when the vehicle is driving in the parking lot; it is also used to execute the function of the first processing module 320, which is used to temporally align the vehicle driving trajectory data and the real-scene media data outside the vehicle; it is also used to execute the function of the second processing module 330, which is used to generate the first real-scene vehicle search navigation data based on the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, wherein the first real-scene vehicle search navigation data is used to guide the user to find the vehicle.

[0075] In one possible implementation, the aforementioned processor 410 is specifically used to: truncate the vehicle driving trajectory data into multiple segments of sub-vehicle driving trajectory data; determine the sub-vehicle external real-scene media data corresponding to each sub-vehicle driving trajectory data based on the alignment result; create thumbnails of each sub-vehicle external real-scene media data, and merge each sub-vehicle driving trajectory data with the thumbnails of the corresponding sub-vehicle external real-scene media data to obtain the first real-scene vehicle search navigation data.

[0076] In one possible implementation, the aforementioned processor 410 is specifically used to: determine, in the vehicle driving trajectory data, the vehicle position when shooting each frame of the external environment image of the external real scene media data, and the parking position in the vehicle driving trajectory data according to the alignment result; calculate the distance value between the vehicle position and the parking position corresponding to each frame of the external environment image, and mark the distance value between the vehicle position and the parking position in each frame of the external environment image; merge the vehicle driving trajectory data with the marked external real scene media data to generate the first real scene vehicle search navigation data.

[0077] In one possible implementation, the processor 410 is also used to execute the functions of the third processing module 340, which is used to: if a vehicle search instruction is received, display the first real-life vehicle search navigation data through the user terminal; monitor the user's position changes when searching for a vehicle, and calculate the actual walking speed based on the position changes; and adjust the playback speed of the first real-life vehicle search navigation data based on the actual walking speed.

[0078] In one possible implementation, the processor 410 is specifically used to: determine a driving trajectory based on driving trajectory data, and divide the driving trajectory into multiple sections; play the first real-life vehicle search and navigation data corresponding to the current section at an expected walking speed; when it is detected that the user is walking into the next section, calculate the average actual walking speed of the previous section, calibrate the expected walking speed based on the average actual walking speed of the previous section, and play the first real-life vehicle search and navigation data for the next section at the calibrated expected walking speed.

[0079] In one embodiment, the processor 410 is also used to execute the fourth processing module 350, which is used to: compare the first real-scene vehicle search navigation data with the second real-scene vehicle search navigation data of other vehicles to determine the target vehicle position when the vehicle intersects with the driving trajectories of other vehicles; determine the first section of the first real-scene vehicle search navigation data between adjacent target vehicle positions, and the second section of the second real-scene vehicle search navigation data between adjacent target vehicle positions; determine whether the second section is better than the first section, and if the second section is better than the first section, then in the first real-scene vehicle search navigation data, replace the sub-real-scene vehicle search navigation data corresponding to the first section with the sub-real-scene vehicle search navigation data corresponding to the second section.

[0080] In one possible implementation, the processor 410 is specifically used to: obtain route information corresponding to the first section and the second section respectively; evaluate the difficulty of finding a car corresponding to the first section and the second section respectively according to the route information; determine whether the difficulty of finding a car on the second section is lower than the difficulty of finding a car on the first section, and if the judgment result is yes, determine whether the second section is better than the first section.

[0081] In one embodiment, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method in any of the above embodiments. The processor is used to execute the plurality of instructions; the memory is used to store the plurality of instructions, which are loaded by the processor and executed as the method for finding a vehicle in the above embodiments.

[0082] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0083] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for finding a vehicle, characterized in that: The method comprises: Acquire vehicle driving trajectory data and real-scene media data outside the vehicle when the vehicle is driving in the parking lot; Temporally aligning the vehicle driving trajectory data and the real-scene media data outside the vehicle; First real-scene vehicle-finding navigation data is generated according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, wherein the first real-scene vehicle-finding navigation data is used to guide the user to find the vehicle.

2. The method according to claim 1, characterized in that The step of generating first real-scene vehicle search navigation data according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle includes: Truncating the vehicle driving trajectory data into multiple segments of sub-vehicle driving trajectory data; Determine the sub-vehicle external real scene media data corresponding to the driving trajectory data of each sub-vehicle according to the alignment result; Thumbnails of real-scene media data outside each sub-vehicle are created, and the driving trajectory data of each sub-vehicle is integrated with the thumbnails of the corresponding real-scene media data outside the sub-vehicle to obtain first real-scene vehicle search navigation data.

3. The method according to claim 1, characterized in that The step of generating first real-scene vehicle search navigation data according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle includes: In the vehicle driving trajectory data, the vehicle position when each frame of the vehicle exterior environment image of the vehicle exterior real scene media data is captured and the parking position in the vehicle driving trajectory data are determined according to the alignment result; Calculate the distance between the vehicle position and the parking position corresponding to each frame of the vehicle external environment image, and mark the distance between the vehicle position and the parking position in each frame of the vehicle external environment image; The vehicle driving trajectory data is integrated with the marked real-scene media data outside the vehicle to generate first real-scene vehicle search navigation data.

4. The method according to claim 1, characterized in that: After generating the first real-scene vehicle search navigation data according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, the method further includes: If a vehicle search instruction is received, the first real-scene vehicle search navigation data is displayed through the user terminal; Monitoring the user's position change when searching for a car, and calculating the actual walking speed based on the position change; The playing speed of the first real-scene vehicle-finding navigation data is adjusted according to the actual walking speed.

5. The method according to claim 4, characterized in that The adjusting the playback speed of the first real-scene car-finding navigation data according to the actual walking speed includes: Determine a driving trajectory according to the driving trajectory data, and divide the driving trajectory into a plurality of sections; Play the first real-life car-finding navigation data corresponding to the current road section according to the expected walking speed; When it is detected that the user is walking into the next road segment, the average actual walking speed of the previous road segment is calculated, and the expected walking speed is calibrated according to the average actual walking speed of the previous road segment, and the first real-life car navigation data of the next road segment is played according to the calibrated expected walking speed.

6. The method according to claim 1, characterized in that After generating the first real-scene vehicle search navigation data according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, the method further includes: Comparing the first real-scene vehicle-finding navigation data with the second real-scene vehicle-finding navigation data of other vehicles to determine the position of the target vehicle when the driving tracks of the vehicle intersect with the driving tracks of other vehicles; Determine a first road section between adjacent target vehicle positions of the first real-scene vehicle search navigation data, and a second road section between the adjacent target vehicle positions of the second real-scene vehicle search navigation data; Determine whether the second road section is better than the first road section. If the second road section is better than the first road section, replace the sub-real scene car search navigation data corresponding to the first road section with the sub-real scene car search navigation data corresponding to the second road section in the first real scene car search navigation data.

7. The method according to claim 6, characterized in that The determining whether the second road section is better than the first road section includes: Obtaining route information corresponding to the first road section and the second road section respectively; evaluating the difficulty of finding a vehicle corresponding to the first road section and the second road section respectively according to the route information; It is determined whether the difficulty of finding a car on the second road section is lower than that of finding a car on the first road section. If the determination result is yes, it is determined whether the second road section is better than the first road section.

8. A vehicle finding device, characterized in that: The device comprises: An acquisition module, used to acquire vehicle driving trajectory data and real-scene media data outside the vehicle when the vehicle is driving in the parking lot; A first processing module, used for temporally aligning the vehicle driving trajectory data and the real scene media data outside the vehicle; The second processing module is used to generate first real-scene vehicle search navigation data according to the aligned vehicle driving trajectory data and the real-scene media data outside the vehicle, wherein the first real-scene vehicle search navigation data is used to guide the user to find the vehicle.

9. A vehicle finding device, characterized in that: The vehicle-finding device comprises a processor and a memory, wherein the memory stores a program or an instruction, and when the program or the instruction is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes the program or the instructions, and when the program or the instructions are executed on a device, the device is caused to perform the method according to any one of claims 1 to 7.

Images