Automated parking method, electronic device, vehicle and readable storage medium
The drone obtains site image data, determines the target parking area and navigation path, and solves the problem of low parking efficiency of the existing automatic parking assist function, and realizes efficient automatic parking of vehicles in different scenarios.
Patent Information
- Application Number
- PCT/CN2024/090057
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-16
- Filing Date
- 2024-04-26
- Publication Date
- 2024-11-21
AI Technical Summary
The existing automatic parking assist function has the problem of low parking efficiency. Users need to drive a car to the parking lot and identify the parking space line through on-board sensors, which is relatively inefficient.
The drone obtains site image data, determines the target parking area and navigation path, and controls the vehicle to automatically drive to and parks into the parking space, realizing the interaction between the drone and the vehicle to improve parking efficiency.
Quickly determine the target parking area and navigation path in any site, improve parking efficiency, expand the vehicle's automatic parking capacity in different scenarios, and realize efficient interactive automatic parking between drones and vehicles.
Smart Images

Figure CN2024090057_21112024_PF_FP_ABST
Abstract
Description
Automatic parking method, electronic device, vehicle and readable storage medium
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This disclosure claims priority to Chinese patent application number 202310553290.1, filed on May 16, 2023, entitled “AN AUTOMATIC PARKING METHOD, ELECTRONIC DEVICE, VEHICLE AND READABLE STORAGE MEDIUM,” the entire contents of which are incorporated herein by reference. Technical Field
[0003] The present disclosure relates to the field of intelligent automobile technology, and in particular to an automatic parking method, electronic equipment, a vehicle, and a readable storage medium. Background Art
[0004] With the continuous increase in the number of cars, parking spaces are becoming increasingly tight, and the problem of difficulty in parking for users is becoming increasingly prominent.
[0005] At present, the fully automatic parking assist function (APA) of automobiles has solved the problem of users' parking difficulties to a certain extent.
[0006] However, the fully automatic parking assistance function requires the user to drive the car to the parking lot and use the vehicle's own sensors to search for parking space lines to identify the parking space, resulting in low parking efficiency.
[0007] Summary of the Invention
[0008] The embodiments of the present disclosure provide an automatic parking method, an electronic device, a vehicle, and a readable storage medium to solve the problem of low parking efficiency of the automatic parking function in the prior art.
[0009] In a first aspect, an embodiment of the present disclosure provides an automatic parking method, applied to a first device, the method comprising:
[0010] Sending a parking processing instruction to the drone; the parking processing instruction is used to control the drone to photograph the site and obtain first image data;
[0011] receiving the first image data sent by the drone;
[0012] determining a target parking area in the site and a target navigation path from the vehicle location to the target parking area based on the first image data;
[0013] The vehicle is controlled to travel along the target navigation path to the target parking area, and the vehicle is controlled to park in the target parking area.
[0014] As a possible implementation manner, the first image data includes: a site image; and determining a target parking area in the site includes:
[0015] determining a selectable parking area in the site based on the first image data;
[0016] When there are at least two parking areas to be selected, a target parking area is determined from the parking areas to be selected.
[0017] As a possible implementation manner, the first image data includes: a site image, a selectable parking area in the site image, and a path element in the site image;
[0018] Determining the target parking area in the site includes:
[0019] When there are at least two parking areas to be selected in the site image, a target parking area is determined from the parking areas to be selected.
[0020] As a possible implementation manner, determining a target parking area from the candidate parking areas includes:
[0021] Obtain the distance from the vehicle's location to each available parking area;
[0022] The to-be-selected parking area corresponding to the minimum distance is determined as the target parking area.
[0023] As a possible implementation manner, determining a target parking area from the candidate parking areas includes:
[0024] Obtain the area of each available parking area;
[0025] The largest candidate parking area is determined as the target parking area.
[0026] As a possible implementation manner, determining a target parking area from the candidate parking areas includes:
[0027] Determine the distance from the vehicle's location to each available parking area and the area of each available parking area;
[0028] The target parking area is determined based on the distance and area of each candidate parking area.
[0029] As a possible implementation manner, when there are at least two parking areas to be selected, before determining a target parking area from the parking areas to be selected, the method further includes:
[0030] Displaying the site image on a display device, and marking the to-be-selected parking area and the to-be-selected navigation path from the vehicle location to the to-be-selected parking area in the site image;
[0031] When there are at least two parking areas to be selected, determining a target parking area from the parking areas to be selected includes:
[0032] Receive the user's selection operation;
[0033] In response to the selection operation, the to-be-selected parking area corresponding to the selection operation is determined as a target parking area.
[0034] As a possible implementation manner, controlling the vehicle to travel along the target navigation path to the target parking area and controlling the vehicle to park in the target parking area includes:
[0035] Obtaining first coordinate information of a target parking area in a first coordinate system and second coordinate information of each point in the target navigation path in the first coordinate system, wherein the first coordinate system is constructed based on the site image;
[0036] According to the flight altitude information of the UAV, a conversion parameter corresponding to the flight altitude is obtained;
[0037] converting the first coordinate information into third coordinate information in the actual scene according to the conversion parameter, and converting the second coordinate information into fourth coordinate information;
[0038] The vehicle is controlled to travel along the target navigation path to the target parking area according to the fourth coordinate information, and the vehicle is controlled to park in the target parking area according to the third coordinate information.
[0039] As a possible implementation, before sending a parking processing instruction to the drone, the following steps are further included:
[0040] Provide flight altitude setting interface;
[0041] Receiving flight altitude information input by a user through the flight altitude setting interface;
[0042] A parking processing instruction including the flight altitude information is generated, and the parking processing instruction is further used to control the UAV to fly to a height corresponding to the flight altitude information.
[0043] As a possible implementation manner, controlling the vehicle to travel along the target navigation path to the target parking area and controlling the vehicle to park in the target parking area includes:
[0044] An activation instruction is sent to an intelligent driving system of the vehicle to notify the intelligent driving system to control the vehicle to travel to the target parking area based on the vehicle sensor data and the target navigation path, and to control the vehicle to park in the target parking area based on the vehicle sensor data and the target parking area.
[0045] As a possible implementation manner, the first image data includes an image whose image quality is greater than a preset quality threshold from among multiple image data taken by the drone.
[0046] As a possible implementation, the first image data includes an image captured by the drone after a lighting device of the drone is turned on, where the lighting device is turned on when the ambient brightness is less than a brightness threshold.
[0047] As a possible implementation manner, the receiving the first image data sent by the drone includes:
[0048] receiving the first image data via a wireless communication connection between the first device and the drone;
[0049] Alternatively, the first image data is received through a communication connection between the first device and a cloud server; the first image data in the cloud server is sent by the drone through a communication connection between the drone and the cloud server.
[0050] In a second aspect, an embodiment of the present disclosure provides an automatic parking device, applied to a first device, comprising:
[0051] An instruction sending module is used to send a parking processing instruction to the drone; the parking processing instruction is used to control the drone to photograph the site and obtain first image data;
[0052] a data receiving module, receiving the first image data sent by the first drone;
[0053] a determination module, configured to determine, based on the first image data, a target parking area in the site and a target navigation path from the vehicle's location to the target parking area;
[0054] A control module controls the vehicle to travel along the target navigation path to the target parking area, and controls the vehicle to park in the target parking area.
[0055] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;
[0056] Memory for storing computer programs;
[0057] The processor is configured to implement the steps of the automatic parking method described in the first aspect when executing the program stored in the memory.
[0058] In a fourth aspect, an embodiment of the present disclosure provides a vehicle, comprising the electronic device as described in the third aspect.
[0059] In a fifth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the automatic parking method described in the first aspect above.
[0060] Compared with the prior art, the present disclosure has the following advantages:
[0061] In the disclosed embodiments, a first device uses a drone to acquire first image data corresponding to a site. The device then determines a target parking area within the site and a target navigation path from the vehicle's location to the target parking area based on the first image data. The first device can determine the target parking area and target navigation path at any site based on the first image data transmitted by the drone, thereby controlling the vehicle to automatically park according to the target parking area and target navigation path. In the automated parking method provided by the disclosed embodiments, the first device uses a drone to acquire first image data corresponding to a large field of view of the site, quickly determining the target navigation path and target parking area, and controlling the vehicle to drive along the target navigation path to the target parking area and then control the vehicle to park in the target parking area. This entire process is automatically accomplished through interaction between the drone and the first device, improving parking efficiency while being unrestricted by application scenarios. Furthermore, acquiring the first image data corresponding to the site through the drone allows the target parking area to be determined within a larger area around the vehicle, expanding the range of target parking areas and target navigation paths available for selection, making it easier for the vehicle to automatically park in various scenarios.
[0062] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments.
[0064] FIG1 is a schematic diagram of an automatic parking method provided by an embodiment of the present disclosure;
[0065] FIG2 is a schematic diagram of a communication link between a drone and a vehicle-mounted terminal according to an embodiment of the present disclosure;
[0066] FIG3 is a schematic diagram of an installation position of a drone provided by an embodiment of the present disclosure;
[0067] FIG4 is a schematic diagram of a method for determining conversion parameters according to an embodiment of the present disclosure;
[0068] FIG5 is a schematic diagram of another automatic parking method provided by an embodiment of the present disclosure;
[0069] FIG6 is a schematic diagram of a site image provided by an embodiment of the present disclosure;
[0070] FIG7 is a schematic diagram of an automatic parking device provided by an embodiment of the present disclosure;
[0071] FIG8 is a block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0072] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.
[0073] FIG1 is an automatic parking method provided by an embodiment of the present disclosure, which is applied to a first device. The method includes steps 110 to 150:
[0074] The automatic parking method provided in the embodiments of the present disclosure is applied to a first device, which includes but is not limited to an on-board terminal in a vehicle and a mobile terminal of a user. The on-board terminal may be a vehicle-mounted head unit (HUT); the mobile terminal may be a mobile phone terminal, a mobile phone, a laptop computer, a digital broadcast receiver, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a wearable device, etc. The on-board terminal and / or the mobile terminal may establish a communication connection with a drone to implement the automatic parking method provided in steps 110 to 140. The first device may establish a communication connection with the drone via a Bluetooth connection, a wireless connection (wifi, wireless fidelity), a data connection (e.g., a 4G data connection, a 5G data connection, etc.), and the embodiments of the present disclosure do not specifically limit this.
[0075] FIG2 is a schematic diagram of a communication link between a drone and an on-board terminal provided by an embodiment of the present disclosure. As shown in FIG2 , the communication link between the drone 100 and the on-board terminal in the vehicle 200 includes a communication link 1 and a communication link 2. Communication link 1 is a data connection link, including but not limited to a 4G data connection and a 5G data connection. Specifically, the drone 100 sends the first image data to the cloud server 300 via communication link 1, and the cloud server 300 forwards the first image data to the on-board terminal in the vehicle 200 via communication link 1. Communication link 2 is a Bluetooth connection or a wireless connection. Specifically, the drone 100 can directly send the first image data to the on-board terminal in the vehicle 200 via communication link 2.
[0076] It should be noted that the first image data sent by the drone to the first device can be in a photo format, or of course, in a video format, and this embodiment of the present disclosure does not specifically limit this.
[0077] In the disclosed embodiments, the drone may include, but is not limited to, an image acquisition device, an image processing device, and a communication device. The image acquisition device is configured to capture a site image corresponding to the site and transmit the site image to the image processing device, which processes the site image to obtain first image data, and transmits the first image data to the first device via the communication device.
[0078] Figure 3 is a schematic diagram of a drone installation location provided by an embodiment of the present disclosure. As shown in Figure 3, a parking platform is provided on the top of the vehicle 200 to provide a parking location for the drone 100 when the drone 100 is not in operation.
[0079] In the embodiment of the present disclosure, a parking platform can also be set in the trunk of the vehicle 200. After the drone 100 sends the first image data to the first device, the vehicle 200 can automatically open the trunk to allow the drone 100 to land on the parking platform set in the trunk.
[0080] Step 110: Send a parking processing instruction to the drone.
[0081] The parking processing instruction is used to control the drone to photograph the site and obtain first image data.
[0082] In the disclosed embodiment, when a user needs to park their vehicle, they can send a parking instruction to the drone via a first device. The first device, in response to the parking instruction, controls the drone to photograph a location and acquire first image data corresponding to the location. It should be noted that the parking instruction may include execution parameter information for the drone, instructing the drone to photograph the location and acquire first image data corresponding to the location in accordance with the execution parameter information. The execution parameter information includes, but is not limited to, image acquisition angle, range of motion, and flight altitude.
[0083] The image acquisition angle is the downward angle parameter at which the drone's image acquisition device captures the image corresponding to the site during the drone's first image acquisition. By setting the image acquisition angle, the site image captured by the drone corresponds to the target perspective, facilitating processing of the site image by the drone or the first device. For example, when the drone acquires the first image data, the plane of the camera in the drone's image acquisition device remains level with the horizontal plane. The flight altitude is the altitude of the drone when acquiring the site image, and the range of movement is the range of movement of the drone when acquiring the site image. The drone's flight altitude and range of movement can be set based on the drone's hardware characteristics. For example, the upper limit of the flight altitude can be determined based on the pixels of the drone's image acquisition device to ensure the discernibility of necessary element information in the site image captured by the drone's image acquisition device. Furthermore, the upper limit of the unmanned range of movement can be determined based on the range limit of the communication connection between the drone and the first device to ensure that the communication connection between the drone and the first device is not interrupted due to excessive distance. The drone's execution parameters can be set based on actual image acquisition needs and are not specifically limited in this embodiment of the present disclosure. In the embodiment of the present disclosure, when the drone receives the parking processing instruction sent by the first device, it can first capture a site image corresponding to the site, and then obtain first image data corresponding to the site based on the site image.
[0084] It should be noted that after the drone photographs the site and obtains the site image corresponding to the site, it may not process the site image and directly send the site image as the first image data to the first device; after the drone photographs the site and obtains the site image corresponding to the site, it may also process the site image through an image processing device and send the site image and the processed image data as the first image data to the first device. The processed image data includes but is not limited to the selectable parking area in the site image and the path elements in the site image.
[0085] Step 120: Receive the first image data sent by the drone.
[0086] In the disclosed embodiment, if there are multiple first devices that establish communication connections with the drone, the drone can simultaneously send first image data to multiple first devices via a communication device. Of course, multiple first devices can also establish communication connections between each other, allowing the drone to send first image data to any one of the multiple first devices, which can then forward the first image data sent by the drone to the other first devices. Therefore, a first device can receive the first image data sent by the drone via a communication connection with the drone, and can also indirectly receive the first image data sent by the drone via a communication connection with other first devices. This is not specifically limited in the disclosed embodiment.
[0087] Step 130: Determine a target parking area in the site and a target navigation path from the vehicle location to the target parking area based on the first image data.
[0088] In the disclosed embodiment, the target navigation path is a path corresponding to a target parking area, and the vehicle can travel from the vehicle's current location to the target parking area along the target navigation path. The number of target parking areas is 1, and the number of target navigation paths is also 1, with a one-to-one correspondence between the target parking areas and the target navigation paths.
[0089] In actual applications, the target parking area includes specific area range coordinates. During automatic parking, parking can be performed more safely and accurately based on the specific area range coordinates.
[0090] Specifically, if the drone has not processed the site image, the first image data only includes the site image. In this case, after the first device receives the first image data through step 120, it is necessary to first identify road signs, parking spaces, obstacles, drivable areas, etc. in the site image in the first image data based on a deep learning target detection algorithm, and perform other processing operations such as marking the obstacle information, drivable area information, and parking area information in the site image. Then, based on the processed image data and the site image, the target parking area in the site and the target navigation path from the vehicle's location to the target parking area are determined. Alternatively, if the drone has already processed the site image, the first image data includes the site image and image data corresponding to the site image. In this case, after the first device receives the first image data through step 120, it can directly determine the target parking area in the site and the target navigation path from the vehicle's location to the target parking area based on the site image in the first image data and the image data corresponding to the site image.
[0091] Step 140: Control the vehicle to travel along the target navigation path to the target parking area, and control the vehicle to park in the target parking area.
[0092] In the embodiment of the present disclosure, after the first device determines the target parking area and the target navigation path through steps 110 to 130, the empty vehicle can be driven along the target navigation path to the target parking area according to the target parking area and the target navigation path, and the vehicle can be controlled to park in the target parking area.
[0093] It should be noted that in the embodiment of the present disclosure, if the information processing capability of the drone chip is capable of determining the target parking area and the target navigation path based on the first image data, some or all of the operations corresponding to steps 120 to 140 can also be implemented in the drone, and the embodiment of the present disclosure does not specifically limit this. Specifically, after obtaining the first image data corresponding to the site, the drone can determine the target parking area in the site and the target navigation path from the vehicle's location to the target parking area based on the first image data; thereafter, the drone sends the determined target parking area and target navigation path to the first device via a communication connection, and the first device controls the vehicle to travel along the target navigation path to the target parking area and controls the vehicle to park in the target parking area. Alternatively, the drone directly controls the vehicle to travel along the target navigation path to the target parking area and controls the vehicle to park in the target parking area based on the target parking area and the target navigation path via a communication connection.
[0094] It should be noted that, when the first device is a vehicle-mounted terminal, the vehicle performs automatic driving and parking based on the target navigation path, target parking area and the vehicle's own sensor data.
[0095] It should be noted that when the first device is a mobile terminal of a vehicle, the mobile terminal sends the target navigation path and target parking area to the vehicle and starts the vehicle's automatic driving system. Then the vehicle's automatic driving system performs the above-mentioned automatic driving and parking process based on the above-mentioned target navigation path and target parking area and the vehicle's own sensor data.
[0096] In the above implementation process, the first device can determine the target parking area and target navigation path based on the first image data transmitted by the drone in a site without parking space lines, and then control the vehicle to automatically park according to the target parking area and target navigation path. The automatic parking method provided by the disclosed embodiment is not limited by the application scenario and can realize the automatic parking function in any scenario. Moreover, the first device can obtain first image data corresponding to a large field of view of the site through the drone, quickly determine the target navigation path and target parking area, control the vehicle to drive along the target navigation path to the target parking area, and control the vehicle to park in the target parking area. This entire process can be automatically achieved through the interactive cooperation between the drone and the first device, thereby improving parking efficiency. In addition, by obtaining the first image data corresponding to the venue through the drone, it is not limited by the size of the large vehicle screen and can determine the target parking area within a larger range around the vehicle, expanding the range of selection of the target parking area and the target navigation path. The drone's own camera can be used to expand the area that the vehicle cannot perceive through its own sensors, thereby improving the unmanned driving function by processing the pictures taken by the drone, and extending the perception range of the vehicle's automatic parking system, so that the vehicle can more easily complete automatic parking in different scenarios, and the operation is more convenient and efficient.
[0097] In one embodiment of the present disclosure, determining the target parking area in the site in step 130 may include steps 131 and 132:
[0098] Step 131: Determine a parking area to be selected in the site based on the first image data.
[0099] Step 132: When there are at least two parking areas to be selected, determine a target parking area from the parking areas to be selected.
[0100] In the disclosed embodiments, the first image data includes a site image. Specifically, the disclosed embodiments correspond to a scenario where a drone captures a site image, obtains a site image, and then transmits the site image as the first image data to a first device without processing the site image. In this case, the first image data received by the first device includes the site image but does not include processed image data obtained by processing the site image.
[0101] Specifically, after the first device receives the first image data sent by the drone through step 120, it first determines the available parking areas in the venue based on the venue image in the first image data; then, if there are at least two available parking areas, it determines the target parking area from among the available parking areas; if there is only one available parking area, it can determine the target parking area.
[0102] The first device determines the candidate parking areas in the venue based on the first image data. Specifically, the first device identifies road signs, parking spaces, obstacles, drivable areas, etc. in the venue image based on a deep learning target detection algorithm, and performs processing operations such as marking obstacles, drivable areas, and candidate parking areas in the venue image to determine the candidate parking areas in the venue image and path elements in the venue image. The candidate parking areas are all areas in the venue image that meet the vehicle parking conditions, including but not limited to parking spaces in a parking lot, roadside parking spaces, and parking areas in open areas. The present disclosed embodiment is not limited to the deep learning-based target detection algorithm.
[0103] When the first device determines the available parking areas in the venue through step 131, and there are at least two available parking areas, the target parking area can be further determined from the available parking areas based on the available parking areas in the venue image and the path elements in the venue image.
[0104] The above implementation process allows the site to be photographed solely by a drone, acquiring first image data including an image of the site. After the first device receives the first image data, the first device determines the candidate parking areas within the site based on the first image data, thereby determining the target parking area. This requires relatively low processing power from the drone's chip; any drone with photography and communication capabilities can implement the automatic parking method provided by the disclosed embodiments. This increases the application scenarios of the automatic parking method while also reducing the configuration requirements for the drone.
[0105] In one embodiment of the present disclosure, determining the target parking area in the site in step 130 may include step 133:
[0106] Step 133: When there are at least two parking areas to be selected in the site image, determine a target parking area from the parking areas to be selected.
[0107] In the disclosed embodiment, the first image data includes a site image, selectable parking areas within the site image, and path elements within the site image. Path elements within the site image may include, but are not limited to, obstacles, road signs, and drivable areas. The disclosed embodiment is applicable in scenarios where a drone processes a scene map and then transmits the first image data, including the site image, selectable parking areas within the site image, and path elements within the site image, to a first device.
[0108] Specifically, the scenario corresponding to the embodiment of the present disclosure is that after a drone photographs a site and obtains a site image, it first uses a deep learning-based target detection algorithm to identify road signs, parking spaces, obstacles, drivable areas, etc. in the site image, and performs marking and other processing operations on the obstacles, drivable areas, and areas to be selected for parking in the site image to obtain first image data including the site image, the areas to be selected for parking in the site image, and the path elements in the site image; then, the drone sends the first image data to the first device.
[0109] In the embodiment of the present disclosure, after the first device receives the first image data sent by the drone in step 120, the site image, the candidate parking areas in the site image, and the path elements in the site image can be directly obtained from the first image data. Thereafter, the first device determines a target parking area from among the candidate parking areas based on the path elements in the site image, if there are at least two candidate parking areas in the site image. If there is only one candidate parking area in the site image, the first device determines the candidate parking area as the target parking area. For details, please refer to the relevant description of step 132, which will not be repeated here.
[0110] In the above implementation process, when the drone chip has strong processing capabilities, the drone can share part or all of the image processing work of the first device, thereby improving the efficiency of the first device in executing step 133 and the subsequent step 140. When the user needs to park, the first device can quickly respond to the user's parking request through interaction with the drone to achieve automatic parking.
[0111] In one embodiment of the present disclosure, determining the target parking area from the candidate parking areas in step 132 or step 133 may include steps A11 and A12:
[0112] Step A11: Obtain the distance from the vehicle's location to each available parking area.
[0113] Step A12: Determine the candidate parking area corresponding to the minimum distance as the target parking area.
[0114] In an embodiment of the present disclosure, when there are at least two selectable parking areas in the site image, the first device may determine the distance from the vehicle's location to each selectable parking area based on path elements in the site image; then, based on the principle of from near to far, the selectable parking area corresponding to the shortest distance is determined as the target parking area.
[0115] It should be noted that the path elements in the site image may include all obstacles in the site and the drivable areas (Freespace) between each obstacle. The first device can obtain the distance from the vehicle position to each of the available parking areas based on the drivable area, the vehicle position, and the position of each of the available parking areas.
[0116] Specifically, because the size of the site image captured by the drone differs from the actual size of the site, it is necessary to determine the proportional relationship between the site image size and the actual size of the site, namely the conversion parameter. The conversion parameter between the site image size and the actual size of the site can be calibrated based on the relationship between the actual size of a reference site of known size and the size of a reference image corresponding to the site captured by the drone at a specified flight altitude. The conversion parameter calibration method includes steps B11 to B14, and this method can be applied to the drone or the first device:
[0117] Step B11: Obtain a first size of the reference site.
[0118] The reference site is a site with known actual dimensions. The first dimension is the actual dimension of the reference site, and the first dimension may be a first area S1 of the reference site or a first side length L1 of the reference site.
[0119] Step B12: Determine a second size of the reference image corresponding to the reference site acquired by the UAV.
[0120] Among them, the reference image is an image corresponding to the reference site taken by the drone at a specified flight altitude; the second size is the size of the reference image, and the second size can be the second area S2 of the reference image, or the second side length L2 of the reference image.
[0121] Step B13: Obtain the flight altitude H1 corresponding to when the UAV takes the reference image.
[0122] Step B14: Determine a conversion parameter corresponding to the flight altitude H1 according to the first size of the reference site and the second size of the reference image.
[0123] Specifically, when the first size is the first area S1 of the reference region and the second size is the second area S2 of the reference image, the first conversion parameter can be determined by the following formula: a=S1 / S2 (Formula 1)
[0124] Wherein, a represents the first conversion parameter corresponding to the flight altitude H1; S1 represents the first area of the reference site; and S2 represents the second area of the reference image.
[0125] In addition, when the first size is the first side length L1 of the reference field and the second size is the second side length L2 of the reference image, the second conversion parameter can be determined by the following formula: b=L1 / L2 (Formula 2)
[0126] Wherein, b represents the second conversion parameter corresponding to the flight height H1; L1 represents the first side length of the reference site; L2 represents the second side length of the reference image, and
[0127] In the disclosed embodiment, the first conversion parameter and the second conversion parameter correspond to different flight altitudes of different drones. Steps B11 to B14 can be repeatedly performed at different flight altitudes to determine the corresponding relationship between different flight altitudes and the first conversion parameter and the second conversion parameter. Correspondingly, steps B12 and B14 can also be repeatedly performed at the same flight altitude, and the average value of the first conversion parameter repeatedly determined at the same flight altitude is determined as the final first conversion parameter, and the average value of the second conversion parameter repeatedly determined at the same takeoff altitude is determined as the final second conversion parameter, thereby improving the reliability of the first conversion parameter and the second conversion parameter.
[0128] For example, FIG4 is a schematic diagram of a conversion parameter determination method provided by an embodiment of the present disclosure. As shown in FIG4 , based on the principle of proportional magnification of similar triangles, a reference site 410 of known actual size and a reference image 420 corresponding to the reference site 410 acquired by a drone can be used to determine a first proportional relationship between the reference site 410 and the reference image 420 when the liftoff height is H1 according to Formula 1, and a second proportional relationship between the reference site 410 and the reference image 420 can also be determined according to Formula 2. It should be noted that determining either the first proportional relationship or the second proportional relationship can implement the automatic parking method provided by an embodiment of the present disclosure.
[0129] In the embodiment of the present disclosure, the distance from the vehicle's location to each available parking area may be determined based on the coordinates of each point in the site.
[0130] Specifically, in the site image, a first coordinate system can be constructed with the own vehicle, that is, the vehicle controlled by the first device, as the origin of the coordinate system and the vehicle's driving direction as the longitudinal axis of the coordinate system. By measuring the distance between each point in the site image and the first longitudinal axis and the first transverse axis of the first coordinate system, the image coordinates of each point in the site image in the first coordinate system can be determined. Corresponding to the first coordinate system, in the actual site, a coordinate system constructed with the own vehicle as the origin of the coordinate system and the vehicle's driving direction as the longitudinal axis of the coordinate system is a second coordinate system. The site coordinates in the actual site corresponding to each point in the site image can be determined based on the image coordinates and the first conversion parameters and the second conversion parameters.
[0131] Exemplarily, the site coordinates (X1, Y1) of any point F in the actual site are determined as follows: first, the image coordinates (x1, y1) of the point f corresponding to point F in the site image are determined. Specifically, x1 and y1 can be determined by measuring the distance between point f in the site image and the coordinate origin (i.e., the vehicle).
[0132] Then, the second horizontal coordinate X1 of the midpoint F in the target area is determined according to the following formula: X1 = x1*b (Formula 3)
[0133] or
[0134] Or X1=x1*a / b (Formula 5)
[0135] Wherein, X1 represents the second horizontal coordinate of the actual site midpoint F; x1 represents the first horizontal coordinate of the site image midpoint f; a represents the first scaling factor; and b represents the second scaling factor.
[0136] Then, the first vertical coordinate Y1 of the midpoint F in the target area is determined according to the following formula: Y1 = y1 * b (Formula 6)
[0137] or
[0138] Or Y1=y1*a / b (Formula 8)
[0139] Wherein, Y1 represents the second ordinate of the midpoint F of the actual site; y1 represents the first ordinate of the midpoint f of the site image; a represents the first scaling factor; and b represents the second scaling factor.
[0140] Finally, determine the site coordinates (X1, Y1) of any point F in the actual site as (x1*b, y1*b) or Or (x1*a / b, y1*a / b).
[0141] It should be noted that the distance from the vehicle's position to each available parking area can be the distance from the vehicle's position to each available parking area in the site image, or the distance from the vehicle's position to each available parking area in the actual site. The distance from the vehicle's position to each available parking area in the site image and the distance from the vehicle's position to each available parking area in the actual site can be converted using a second conversion parameter, which is not specifically limited in the embodiments of the present disclosure.
[0142] During the above implementation process, when there are at least two parking areas to be selected in the site image, the first device can determine the parking area corresponding to the smallest distance as the target parking area based on the distance from the vehicle's location to each parking area, in order of near to far, to save time in reaching the target parking area from the vehicle's location.
[0143] Optionally, in an embodiment of the present disclosure, determining the target parking area from the candidate parking areas in step 132 or step 133 may include steps A21 and A22:
[0144] Step A21: Obtain the area of each available parking area.
[0145] Step A22: Determine the largest available parking area as the target parking area.
[0146] In an embodiment of the present disclosure, when there are at least two selectable parking areas in a site image, taking into account the difficulty of parking in actual scenarios, the first device may determine the areas of each selectable parking area based on path elements in the site image; then, the selectable parking area with the largest area is determined as the target parking area, thereby reducing the difficulty of automatic parking and providing the user with a better riding experience.
[0147] The first device may determine the side lengths of the candidate parking areas based on the image coordinates corresponding to the candidate parking areas in the site image in the first image data and the image coordinates of each vertex in the candidate parking areas, and further calculate the areas of each candidate parking area based on the side lengths; then, the target parking area is determined through step A22.
[0148] It should be noted that the area of each available parking area can be the area of each available parking area in the venue image, or the area of each available parking area in the actual venue. The area of each available parking area in the venue image and the area of each available parking area in the actual venue can be converted using the first conversion parameter, which is not specifically limited in the embodiments of the present disclosure.
[0149] During the above implementation process, when there are at least two selectable parking areas in the venue image, the first device can determine the largest selectable parking area as the target parking area based on the area of each selectable parking area and the parking difficulty level, thereby reducing the difficulty of automatic parking and providing the user with a better riding experience.
[0150] In one embodiment of the present disclosure, determining the target parking area from the candidate parking areas in step 132 or step 133 may include steps A31 and A32:
[0151] Step A31: Determine the distance from the vehicle's location to each available parking area and the area of each available parking area.
[0152] Step A32: Determine a target parking area based on the distances and areas of the candidate parking areas.
[0153] In the embodiment of the present disclosure, when there are at least two parking areas to be selected in the site image, two factors, namely the distance from the vehicle's location to each parking area to be selected and the area of each parking area to be selected, can also be comprehensively considered, and weight values can be set for the two factors according to user preferences. Specifically, the weight value corresponding to the distance from the vehicle's location to the parking area to be selected is a first weight value, and the weight value corresponding to the area of the parking area to be selected is a second weight value. Then, the reference value of each parking area to be selected can be determined by the distance, area, first weight value, and second weight value, and the reference values are sorted, and the parking area to be selected corresponding to the reference value ranked first is determined as the target parking area. The reference value corresponding to each parking area to be selected can be determined by the following formula: Reference value = distance from the vehicle's location to the parking area to be selected × first weight value + area of the parking area to be selected × second weight value (Formula 9)
[0154] For example, if the user prefers to reach the target parking area through a shorter target navigation path, a higher first weight value can be set for the distance from the vehicle's location to the to-be-selected parking area, and a lower second weight value can be set for the area of the to-be-selected parking area; if the user prefers to park in the parking area with fewer attempts, a lower first weight value can be set for the distance from the vehicle's location to the to-be-selected parking area, and a higher second weight value can be set for the area of the to-be-selected parking area.
[0155] Of course, the target parking area can also be determined from the candidate parking areas by taking the distance from the vehicle location to each candidate parking area as the first priority and the area of each candidate parking area as the second priority.
[0156] During the above implementation process, when there are at least two parking areas to be selected in the site image, in the process of determining the target parking area from the parking areas to be selected, the distance from the vehicle's location to each parking area to be selected and the area of each parking area to be selected are comprehensively considered. This allows the vehicle to reach the target parking area in a relatively short distance and complete automatic parking with a relatively small number of vehicle movements, providing users with a more reasonable and comfortable automatic parking experience.
[0157] FIG5 is a schematic diagram of another automatic parking method provided by an embodiment of the present disclosure, which is applied to a first device. The method includes steps 210 to 270:
[0158] Step 210: Send a parking processing instruction to the drone.
[0159] This step can be referred to the detailed description of step 110 and will not be repeated here.
[0160] Step 220: Receive the first image data sent by the drone.
[0161] This step can be referred to the detailed description of step 120 and will not be repeated here.
[0162] Step 230: Display the site image on a display device, and mark the candidate parking area and the candidate navigation path from the vehicle location to the candidate parking area in the site image.
[0163] In an embodiment of the present disclosure, the first device includes a display device for displaying the site image, the candidate parking areas marked in the site image, and the candidate navigation paths from the vehicle location to the candidate parking areas.
[0164] It should be noted that a candidate navigation path is a path corresponding to a candidate parking area, and a vehicle can travel to the corresponding candidate parking area via the candidate navigation path. There can be one or more candidate parking areas. If there is only one candidate parking area, at least one candidate navigation path can be marked based on the candidate parking area, so that the vehicle can travel to the candidate parking area via the at least one candidate navigation path. If there are multiple candidate parking areas, the multiple different candidate parking areas can be arranged in descending order of priority, and at least one candidate navigation path corresponding to each different candidate parking area is marked.
[0165] Specifically, when the number of available parking areas to be selected is 1 and the number of available navigation paths to be selected corresponding to the available parking area is also 1, the first device may display the available parking area to be selected and the available navigation path to be selected through the display device; when the number of available parking areas to be selected is 1 and the number of available navigation paths to be selected corresponding to the available parking area is multiple, the first device may display the available parking area to be selected and the multiple available navigation paths to be selected corresponding to the available parking area through the display device.
[0166] Furthermore, if there are multiple available parking areas, the different available parking areas can be numbered in descending order of priority, and the first device can display the multiple available parking areas and their corresponding numbers to the user via the display device. Furthermore, while the first device displays the multiple available parking areas and their corresponding numbers to the user via the display device, the available navigation path corresponding to the highest-priority available parking area can be displayed by default. Based on the user's selection, the available navigation path corresponding to the user-selected available parking area can be displayed via the display device. The disclosed embodiments do not specifically limit the manner in which the available parking areas and navigation paths are displayed.
[0167] It should be noted that the parking areas to be selected and the navigation paths to be selected displayed to the user by the first device through the display device are displayed with the venue image as the background, so that the user can view and select the parking areas to be selected and the navigation paths to be selected more intuitively.
[0168] Step 240: Receive the user's selection operation.
[0169] Step 250: In response to the selection operation, determine the to-be-selected parking area corresponding to the selection operation as a target parking area.
[0170] In the embodiment of the present disclosure, after the first device displays the venue image in step 230 and marks the candidate parking area and the candidate navigation path from the vehicle's location to the candidate parking area in the venue image, the user can select a candidate parking area and the candidate navigation path corresponding to the candidate parking area based on the candidate parking area and the candidate navigation path marked in the venue image displayed by the display device of the first device; after receiving the user's selection operation for the candidate parking area and the candidate navigation path corresponding to the candidate parking area, the first device executes step 250 to determine, in response to the selection operation, the candidate parking area corresponding to the selection operation as the target parking area, and the candidate navigation path corresponding to the selection operation as the target navigation path from the vehicle's location to the target parking area.
[0171] It should be noted that when there are multiple first devices, for example, when the first devices include an in-vehicle terminal and a mobile terminal, the user can independently select a parking area and a navigation route corresponding to the parking area based on the site image displayed on the display device of any of the first devices, the candidate parking areas marked in the site image, and the candidate navigation route from the vehicle's location to the candidate parking area. After receiving a selection operation input by the user, the first device, in response to the user's selection operation, determines the candidate parking area corresponding to the selection operation as the target parking area and the candidate navigation route corresponding to the selection operation as the target navigation route. Simultaneously, the first device can synchronize the determined target parking area and target navigation route with other first devices through communication connections with the other first devices, enabling real-time information sharing between different first devices. This allows the user to observe the vehicle's automatic parking process through any of the first devices, improving the operability of the user in selecting parking routes and parking areas, as well as the convenience of the user in selecting parking areas and navigation routes.
[0172] Step 260: Determine a target navigation path from the vehicle location to the target parking area based on the first image data and the target parking area.
[0173] In the embodiment of the present disclosure, after determining the target parking area in step 250 , the first device may determine a target navigation path from the vehicle location to the target parking area based on the first image data and the target parking area.
[0174] Step 270: Control the vehicle to travel along the target navigation path to the target parking area, and control the vehicle to park in the target parking area.
[0175] This step can refer to the detailed description of step 140 and will not be repeated here.
[0176] During the above implementation, the user can select a target parking area and a target navigation path from the vehicle's location to the target parking area through any first device, enabling the user to independently select the parking area and target navigation path through the first device. The automatic parking method provided by the disclosed embodiments is not limited by application scenarios and also improves user operability and enhances the user experience.
[0177] In one embodiment of the present disclosure, controlling the vehicle to travel along the target navigation path to the target parking area and parking the vehicle in the target parking area in step 140 may include steps 141 to 144:
[0178] Step 141: Obtain first coordinate information of a target parking area in a first coordinate system, and second coordinate information of each point in the target navigation path in the first coordinate system.
[0179] The first coordinate system is constructed based on the site image.
[0180] In the disclosed embodiments, the first coordinate system is constructed within the scene image, with the ego vehicle (i.e., the vehicle controlled by the first device) as the origin of the coordinate system and the ego vehicle's travel direction as the vertical axis of the coordinate system. It should be noted that the horizontal axis of the first coordinate system is perpendicular to the ego vehicle's travel direction.
[0181] The first coordinate information includes the first coordinate of each point in the target parking area in the first coordinate system; the second coordinate information includes the second coordinate of each point in the target navigation path in the first coordinate system. It should be noted that the aforementioned image coordinates include the first coordinates and the second coordinates.
[0182] Step 142: According to the flight altitude information of the UAV, a conversion parameter corresponding to the flight altitude is obtained.
[0183] The flight altitude information includes the altitude at which the UAV flies when executing the parking processing instruction, photographing the site, and acquiring the first image data.
[0184] In the embodiment of the present disclosure, the conversion parameters include a first conversion parameter and a second conversion parameter. When the flight altitude in the flight altitude information is determined, the first conversion parameter or the second conversion parameter corresponding to the flight altitude can be determined according to steps B11 to B14, which will not be repeated here.
[0185] Step 143: Convert the first coordinate information into third coordinate information in the actual scene according to the conversion parameters, and convert the second coordinate information into fourth coordinate information.
[0186] The third and fourth coordinates are both coordinate information in a second coordinate system corresponding to the actual scene. The aforementioned scene coordinates include the third and fourth coordinates. Specifically, the second coordinate system is a coordinate system constructed in the actual scene corresponding to the first coordinate system, with the vehicle as the origin and the vehicle's travel direction as the longitudinal axis.
[0187] The third coordinate information includes the third coordinate of each point in the target parking area in the actual scene in the second coordinate system; the fourth coordinate information includes the fourth coordinate of each point in the target navigation path in the actual scene in the second coordinate system. Specifically, based on the conversion parameters obtained in step 142, the first coordinate information can be converted to the third coordinate information in the actual scene, and the second coordinate information can be converted to the fourth coordinate information using Formula 3 and Formula 6, Formula 4 and Formula 7, or Formula 5 and Formula 8.
[0188] Step 144: Control the vehicle to travel along the target navigation path to the target parking area according to the fourth coordinate information, and control the vehicle to park in the target parking area according to the third coordinate information.
[0189] In an embodiment of the present disclosure, the first device can control the vehicle to travel along the fourth coordinate to the target parking area based on the fourth coordinate of each point in the target navigation path in the fourth coordinate information in the actual scenario; similarly, after the first device controls the vehicle to travel to the target parking area, the first device will control the vehicle to park in the target parking area based on the third coordinate of each point in the target parking area in the third coordinate information in the actual scenario.
[0190] Figure 6 is a schematic diagram of a site image provided by an embodiment of the present disclosure. Figure 6 illustrates a target parking area 601 determined by a first device from among candidate parking areas 604 in site image 600 based on first image data, and a target navigation path 602 determined from a vehicle location 603 to the target parking area 601. Specifically, the first device can control a vehicle to travel from the vehicle location 603 along the target navigation path 602 to the target parking area 601, and then control the vehicle to park in the target parking area 601, by following the method described in steps 141 to 144.
[0191] During the above implementation process, the first device controls the vehicle to travel along the target navigation path to the target parking area based on the fourth coordinate information of the target navigation path in the actual scenario; then, based on the third coordinate information of the target parking area in the actual scenario, the vehicle is controlled to park in the target parking area. This achieves precise control of the vehicle's driving and parking processes through the coordinates of the target navigation route and the target parking area in the actual scenario, thereby improving the reliability and accuracy of automatic parking of the vehicle controlled by the first device.
[0192] In one embodiment of the present disclosure, before sending the parking processing instruction to the drone in step 110, steps 101 to 103 may also be included:
[0193] Step 101: Provide a flight altitude setting interface.
[0194] Specifically, the flight altitude setting interface may include a flight altitude value input area, a flight altitude unit input area, and a confirmation button. The first device displays the flight altitude setting interface to the user, and the user can enter the flight altitude value and the unit corresponding to the flight altitude value in the flight altitude value input area, such as millimeters, centimeters, meters, kilometers, etc. Finally, after confirming that the entered flight altitude value and flight altitude unit are correct, the user can click the confirmation button in the flight altitude setting interface to send the flight altitude information to the first device.
[0195] Step 102: Receive flight altitude information input by the user through the flight altitude setting interface.
[0196] The flight altitude information may include but is not limited to a flight altitude value and a flight altitude unit.
[0197] Step 103: Generate a parking processing instruction including the flight altitude information, wherein the parking processing instruction is further used to control the UAV to fly to a height corresponding to the flight altitude information.
[0198] In an embodiment of the present disclosure, the parking processing instruction may also include flight altitude information. The first device may generate a parking processing instruction including the flight altitude information, and control the drone to fly to the altitude corresponding to the flight altitude information by sending the parking processing instruction including the flight altitude information to the drone.
[0199] The parking processing instruction may also include an image acquisition angle and an activity range. Accordingly, step 101 may also provide an image acquisition angle setting interface and an activity range setting interface. The first device may also receive image acquisition angle information input by the user through the image acquisition angle setting interface through step 102, and receive activity range information input by the user through the activity range setting interface. Finally, the first device may generate a parking processing instruction including flight altitude information, image acquisition angle information and activity range information through step 103, and send a parking processing instruction including flight altitude information, image acquisition angle information and activity range information to the drone. The parking processing instruction may be used to control the drone to fly to the height corresponding to the flight altitude information, and the site may be photographed within the activity range according to the image acquisition angle to obtain first image data.
[0200] During the above implementation process, the setting of the flight altitude corresponding to the drone and the control of the flight altitude of the drone are realized through the first device, so that the site image and the first image data corresponding to the site are both taken by the drone at the flight altitude set by the user, providing a basis for subsequently determining the conversion parameters according to the altitude information.
[0201] In one embodiment of the present disclosure, the step 140 of controlling the vehicle to travel along the target navigation path to the target parking area and controlling the vehicle to park in the target parking area may include step 145:
[0202] Step 145: Send an activation instruction to the intelligent driving system of the vehicle to notify the intelligent driving system to control the vehicle to travel to the target parking area based on the vehicle sensor data and the target navigation path, and to control the vehicle to park in the target parking area based on the vehicle sensor data and the target parking area.
[0203] In an embodiment of the present disclosure, the vehicle may include an intelligent driving system. The first device may send an activation instruction to the intelligent driving system, instructing the intelligent driving system to control the vehicle to travel to the target parking area based on the vehicle's sensor data and a target navigation path, and to control the vehicle to park in the target parking area based on the vehicle's sensor data and the target parking area. The activation instruction may include the target parking area in the venue determined by the first device in step 130 and the target navigation path determined from the vehicle's location to the target parking area.
[0204] The intelligent driving system is a vehicle's system for implementing automatic cruise control and automatic parking functions. The vehicle's intelligent driving system includes, but is not limited to, a perception component, a path planning component, and a control component. The perception component is used to obtain sensor data from the vehicle, including vehicle status data and vehicle environment data. Specifically, the perception component may include a body state sensor for acquiring vehicle body state data. The body state data may include at least one of IMU (Inertial Measurement Unit) data, steering wheel angle information, wheel speed pulses and wheel speed information, and body posture information. The intelligent driving system may perform dead reckoning based on the body state data to avoid collisions with other vehicles or obstacles that appear temporarily on the road while the vehicle is traveling along the target navigation path. The perception component may also include a surround-view camera for acquiring body environment data. The body environment data may include image data corresponding to the driving environment along the vehicle's route. The intelligent driving system may identify objects along the vehicle's route based on the body environment data and extract feature points and semantic information, such as road signs and obstacles. The identified objects are then compared one by one with the information in the first image data, and the information is used in conjunction with the target navigation route and target parking area for reference to assist in positioning the vehicle during driving. In actual scenarios, the information contained in the first image data acquired by the drone may not fully enable the vehicle's intelligent driving system to accurately locate the vehicle. The sensor data acquired by the perception component can assist the vehicle's intelligent driving system in completing the automatic parking function.
[0205] The path planning component is used to plan the vehicle's actual driving path based on the sensor data obtained by the perception component, as well as the target parking area and the target navigation path, to ensure that the vehicle can accurately and safely drive to the target parking area and complete automatic parking in the target parking area.
[0206] The control component is used to control the vehicle to travel and park according to the actual driving path of the vehicle planned by the path planning component.
[0207] For example, while the intelligent driving system is controlling a vehicle to follow a target navigation path, another vehicle suddenly appears on the road ahead and stops due to a sudden malfunction. The first image data transmitted by the drone does not include information about the vehicle. In this case, the path planning component in the vehicle's intelligent driving system can, based on the sensor data acquired by the perception component, plan a path that allows the vehicle to avoid the malfunctioning vehicle ahead. The control component then controls the vehicle according to this path, avoiding a collision with the malfunctioning vehicle ahead and ensuring that the vehicle accurately and safely reaches the target parking area and completes automatic parking there.
[0208] During the above implementation process, through the interaction and cooperation between the first device and the vehicle's intelligent driving system, the intelligent driving system controls the vehicle to complete automatic parking in a more accurate and safe manner based on the target navigation path, target parking area and vehicle sensor data determined by the first device.
[0209] In one embodiment of the present disclosure, the first image data includes an image whose image quality is greater than a preset quality threshold among the multiple image data taken by the drone.
[0210] The preset quality threshold is a threshold corresponding to the image instruction, and specifically may be at least one of a pixel threshold and a resolution threshold.
[0211] In the embodiment of the present disclosure, when photographing a site, the drone may capture multiple site images corresponding to the same site, and determine an image having an image instruction greater than a preset quality threshold from the multiple site images, process the image to obtain first image data of the image, or directly send the image as the first image data to the first device, so that the first device can execute steps 120 and 140 based on the first image data including higher image quality, thereby improving the accuracy and reliability of controlling the vehicle according to the target parking area and the target navigation path.
[0212] In one embodiment of the present disclosure, the first image data includes an image captured by the drone after a lighting device of the drone is turned on, and the lighting device is turned on when the ambient brightness is less than a brightness threshold.
[0213] In the disclosed embodiments, the drone may further include a lighting device and a light sensor. The light sensor is used to detect light intensity information and transmit the light intensity information to the drone. The drone controls the lighting device to turn on the lighting device based on the light intensity information when the light intensity information falls below a preset light threshold.
[0214] The preset illumination threshold can be set according to the resolution effect of the site image captured by the drone, so as to ensure that the drone can capture clear site images even in dark scenes (for example, at night).
[0215] The above implementation process can use the lighting device in the drone to illuminate in a dimly lit scene, assisting the drone to complete the operation of photographing the site and obtaining the first image data. This ensures that the drone is not affected by external lighting and can normally photograph the site according to the parking processing instruction and obtain the first image data, thereby ensuring the normal progress of the vehicle's automatic parking process and further expanding the application scenarios of the automatic parking method provided by the embodiment of the present disclosure.
[0216] In one embodiment of the present disclosure, the receiving of the first image data sent by the drone in step 120 may include step 121 or step 122:
[0217] Step 121: Receive the first image data through a wireless communication connection between the first device and the drone.
[0218] Among them, the wireless communication connection method may include but is not limited to Bluetooth connection and Wi-Fi connection.
[0219] Step 122: Receive the first image data through the communication connection between the first device and the cloud server; the first image data in the cloud server is sent by the drone through the communication connection between the drone and the cloud server.
[0220] Specifically, the first device and the cloud server can be connected via a data connection, such as a 4G data connection, a 5G data connection, etc.; similarly, the drone and the cloud server can also be connected via a data connection.
[0221] The embodiments of the present disclosure provide multiple ways to achieve a communication connection between the first device and the drone, thereby improving the reliability of the communication connection between the first device and the drone and providing a strong guarantee for the first device to more easily execute steps 110 to 140.
[0222] FIG7 is a schematic diagram of an automatic parking device provided by an embodiment of the present disclosure, which is applied to a first device. The device includes:
[0223] The instruction sending module 710 is used to send a parking processing instruction to the drone; the parking processing instruction is used to control the drone to photograph the site and obtain first image data;
[0224] A data receiving module 720 receives the first image data sent by the first drone;
[0225] a determination module 730 that determines, based on the first image data, a target parking area in the site and a target navigation path from the vehicle's location to the target parking area;
[0226] The control module 740 controls the vehicle to travel along the target navigation path to the target parking area, and controls the vehicle to park in the target parking area.
[0227] As a possible implementation manner, the first image data includes: a site image; the determination module includes:
[0228] a first determining submodule, configured to determine a selectable parking area in the site based on the first image data;
[0229] The second determining submodule is configured to determine a target parking area from the candidate parking areas when there are at least two candidate parking areas.
[0230] As a possible implementation, the first image data includes: a site image, a selectable parking area in the site image, and path elements in the site image; and the determination module includes:
[0231] The third determining submodule is configured to determine a target parking area from among the candidate parking areas when there are at least two candidate parking areas in the site image.
[0232] As a possible implementation, the determining module includes:
[0233] The first acquisition submodule is used to obtain the distance from the vehicle's location to each parking area to be selected;
[0234] The fourth determining submodule is configured to determine the candidate parking area corresponding to the minimum distance as the target parking area.
[0235] As a possible implementation, the determining module includes:
[0236] The second acquisition submodule is used to obtain the area of each parking area to be selected;
[0237] The fifth determining submodule is configured to determine the largest candidate parking area as the target parking area.
[0238] As a possible implementation, the determining module includes:
[0239] a sixth determining submodule, configured to determine the distance from the vehicle's location to each of the available parking areas, and the area of each of the available parking areas;
[0240] The seventh determination submodule is configured to determine a target parking area based on the distances and areas of the candidate parking areas.
[0241] As a possible implementation, the determining module includes:
[0242] a marking submodule, configured to display the site image on a display device and mark the to-be-selected parking area and a to-be-selected navigation path from the vehicle's location to the to-be-selected parking area in the site image;
[0243] The second determining submodule or the third determining submodule includes
[0244] A receiving unit, configured to receive a user's selection operation;
[0245] A determining unit is configured to, in response to the selection operation, determine the to-be-selected parking area corresponding to the selection operation as a target parking area.
[0246] As a possible implementation, the control module includes:
[0247] a third acquisition submodule, configured to acquire first coordinate information of a target parking area in a first coordinate system, and second coordinate information of each point in the target navigation path in the first coordinate system; the first coordinate system being constructed based on the site image;
[0248] A fourth acquisition submodule is configured to acquire, based on the flight altitude information of the UAV, a conversion parameter corresponding to the flight altitude;
[0249] a coordinate conversion submodule, configured to convert the first coordinate information into third coordinate information in an actual scene, and convert the second coordinate information into fourth coordinate information, according to the conversion parameters;
[0250] The control submodule is configured to control the vehicle to travel along the target navigation path to the target parking area according to the fourth coordinate information, and to control the vehicle to park in the target parking area according to the third coordinate information.
[0251] As a possible implementation manner, the device further includes:
[0252] The interface providing module is used to provide a flight altitude setting interface;
[0253] An information receiving module, configured to receive flight altitude information input by a user through the flight altitude setting interface;
[0254] The instruction generation module is used to generate a parking processing instruction including the flight altitude information, and the parking processing instruction is also used to control the UAV to fly to the altitude corresponding to the flight altitude information.
[0255] As a possible implementation, the control module includes:
[0256] and a command sending submodule, configured to send an activation command to the intelligent driving system of the vehicle, so as to notify the intelligent driving system to control the vehicle to travel to the target parking area based on the vehicle sensor data and the target navigation path, and to control the vehicle to park in the target parking area based on the vehicle sensor data and the target parking area.
[0257] As a possible implementation manner, the first image data includes an image whose image quality is greater than a preset quality threshold from among multiple image data taken by the drone.
[0258] As a possible implementation, the first image data includes an image captured by the drone after a lighting device of the drone is turned on, where the lighting device is turned on when the ambient brightness is less than a brightness threshold.
[0259] As a possible implementation, the data receiving module includes:
[0260] a receiving submodule, configured to receive the first image data via a wireless communication connection between the first device and the drone;
[0261] The receiving submodule is further configured to receive the first image data through the communication connection between the first device and the cloud server; the first image data in the cloud server is sent by the drone through the communication connection between the drone and the cloud server.
[0262] For the above-mentioned device embodiment, since it is basically similar to the automatic parking method embodiment, the relevant parts can be referred to the partial description of the method embodiment.
[0263] In the automatic parking apparatus provided by the disclosed embodiments, a first device uses a drone to acquire first image data corresponding to a site. The device then determines a target parking area within the site and a target navigation path from the vehicle's location to the target parking area based on the first image data. The first device can determine the target parking area and target navigation path at any site based on the first image data transmitted by the drone, thereby controlling the vehicle to automatically park according to the target parking area and target navigation path. In the automatic parking method provided by the disclosed embodiments, the first device uses a drone to acquire first image data corresponding to a large field of view of the site, quickly determining the target navigation path and target parking area, and controlling the vehicle to drive along the target navigation path to the target parking area and then control the vehicle to park in the target parking area. This entire process is automatically accomplished through interaction between the drone and the first device, improving parking efficiency while being unrestricted by application scenarios. Furthermore, by acquiring the first image data corresponding to the site through the drone, the target parking area can be determined within a larger area around the vehicle, expanding the range of target parking areas and target navigation paths available for selection, making it easier for the vehicle to automatically park in different scenarios.
[0264] An embodiment of the present disclosure further provides an electronic device, as shown in FIG8 , including a processor 801 , a communication interface 802 , a memory 803 and a communication bus 804 , wherein the processor 801 , the communication interface 802 , and the memory 803 communicate with each other via the communication bus 804 .
[0265] The memory 803 is used to store computer programs.
[0266] When the processor 801 is used to execute the program stored in the memory 803, the following steps are implemented: sending a parking processing instruction to the drone; the parking processing instruction is used to control the drone to photograph the site and obtain first image data; receiving the first image data sent by the drone; determining a target parking area in the site and a target navigation path from the vehicle's location to the target parking area based on the first image data; controlling the vehicle to travel along the target navigation path to the target parking area, and controlling the vehicle to park in the target parking area.
[0267] The processor 801 may also implement other steps in the above-mentioned automatic parking method, which will not be described in detail here.
[0268] The communication bus mentioned in the electronic device mentioned above may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.
[0269] The communication interface is used for communication between the above electronic device and other devices.
[0270] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.
[0271] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.
[0272] In yet another embodiment provided by the present disclosure, a vehicle is further provided. The vehicle includes the electronic device described in the above embodiment.
[0273] In another embodiment provided by the present disclosure, a computer-readable storage medium is further provided. The computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the automatic parking method described in the above embodiment.
[0274] In another embodiment provided by the present disclosure, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the automatic parking method described in the above embodiment.
[0275] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).
[0276] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.
[0277] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments. The embodiments of the apparatus, electronic device, computer-readable storage medium, and computer program product containing instructions thereof are generally similar to the method embodiments, so their description is relatively simple. For related portions, reference can be made to the description of the method embodiments.
[0278] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the scope of protection of the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present disclosure are included in the scope of protection of the present disclosure.
Claims
1. An automatic parking method, characterized in that: Applied to a first device, the method includes: Sending a parking processing instruction to the drone; the parking processing instruction is used to control the drone to photograph the site and obtain first image data; receiving the first image data sent by the drone; Determine, based on the first image data, a target parking area in the venue and a target navigation path from the vehicle location to the target parking area; The vehicle is controlled to travel along the target navigation path to the target parking area, and the vehicle is controlled to park in the target parking area.
2. The method according to claim 1, characterized in that The first image data includes: a site image; the determining of a target parking area in the site includes: Determine, according to the first image data, a parking area to be selected in the venue; When there are at least two parking areas to be selected, a target parking area is determined from the parking areas to be selected.
3. The method according to claim 1, characterized in that The first image data includes: a site image, a selectable parking area in the site image, and a path element in the site image; The determining of the target parking area in the venue includes: When there are at least two parking areas to be selected in the site image, a target parking area is determined from the parking areas to be selected.
4. The method according to claim 2 or 3, characterized in that: The step of determining a target parking area from the to-be-selected parking areas comprises: Obtain the distance from the vehicle's location to each available parking area; The to-be-selected parking area corresponding to the minimum distance is determined as the target parking area.
5. The method according to claim 2 or 3, characterized in that: The step of determining a target parking area from the to-be-selected parking areas comprises: Obtain the area of each parking area to be selected; The largest candidate parking area is determined as the target parking area.
6. The method according to claim 2 or 3, characterized in that: The step of determining a target parking area from the to-be-selected parking areas comprises: Determine the distance from the vehicle location to each of the available parking areas, and the area of each of the available parking areas; The target parking area is determined based on the distance and area of each candidate parking area.
7. The method according to claim 2 or 3, characterized in that: When there are at least two parking areas to be selected, before determining a target parking area from the parking areas to be selected, the method further includes: Displaying the site image on a display device, and marking the to-be-selected parking area and a to-be-selected navigation path from the vehicle location to the to-be-selected parking area in the site image; When there are at least two parking areas to be selected, determining a target parking area from the parking areas to be selected includes: Receive the user's selection operation; In response to the selection operation, the to-be-selected parking area corresponding to the selection operation is determined as a target parking area.
8. The method according to claim 2 or 3, characterized in that: The controlling the vehicle to travel along the target navigation path to the target parking area, and controlling the vehicle to park in the target parking area, comprises: Acquire first coordinate information of a target parking area in a first coordinate system, and second coordinate information of each point in the target navigation path in the first coordinate system; the first coordinate system is constructed based on the site image; According to the flight altitude information of the UAV, obtaining a conversion parameter corresponding to the flight altitude; According to the conversion parameter, the first coordinate information is converted into the third coordinate information in the actual scene, and the second coordinate information is converted into the third coordinate information in the actual scene. The information is converted into fourth coordinate information; According to the fourth coordinate information, the vehicle is controlled to travel along the target navigation path to the target parking area, and according to the third coordinate information, the vehicle is controlled to park in the target parking area.
9. The method according to claim 8, characterized in that Before sending the parking processing instruction to the drone, it also includes: Provide flight altitude setting interface; Receiving flight altitude information input by a user through the flight altitude setting interface; A parking processing instruction including the flight altitude information is generated, and the parking processing instruction is also used to control the UAV to fly to a height corresponding to the flight altitude information.
10. The method according to claim 1, characterized in that The controlling the vehicle to travel along the target navigation path to the target parking area, and controlling the vehicle to park in the target parking area, comprises: An activation instruction is sent to the intelligent driving system of the vehicle to notify the intelligent driving system to control the vehicle to travel to the target parking area according to the vehicle sensor data and the target navigation path, and to control the vehicle to park in the target parking area according to the vehicle sensor data and the target parking area.
11. The method according to claim 1, characterized in that: The first image data includes an image whose image quality is greater than a preset quality threshold from among multiple image data taken by the drone.
12. The method according to claim 1, characterized in that The first image data includes an image taken by the drone after a lighting device of the drone is turned on, and the lighting device is turned on when the ambient brightness is less than a brightness threshold.
13. The method according to claim 1, characterized in that The receiving the first image data sent by the drone includes: Receiving the first image data through a wireless communication connection between the first device and the drone; And / or, the first image data is received through a communication connection between the first device and a cloud server; the first image data in the cloud server is sent by the drone through a communication connection between the drone and the cloud server.
14. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is configured to implement the steps of the assisted parking method according to any one of claims 1 to 13 when executing the program stored in the memory.
15. A vehicle, characterized in that: The vehicle includes the electronic device as claimed in claim 14.
16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the assisted parking method according to any one of claims 1 to 13 are implemented.
Citation Information
Patent Citations
Method for searching parking stall based on UAV, and UAV
CN107025802A
Unmanned-aerial-vehicle-based parking space monitoring system and monitoring method thereof
CN107644545A
Method and device for finding a parking space by drone
CN109215375A
Unmanned aerial vehicle-based automatic parking system and automatic parking method
CN110562248A
Vehicle parking method and device, vehicle and storage medium
CN110606071A
Cited By
Environment sensing method and device, vehicle, storage medium and program product
CN120080860A
