A control method and device of a vehicle, a controller, a vehicle, and a storage medium

Abstract

Embodiments of the present application provide a vehicle control method and device, a controller, a vehicle and a computer readable storage medium, and are applied to a vehicle. The method comprises: acquiring an image sent by a terminal, identifying the image to obtain current visual positioning information in the image, finding target reference visual positioning information matching the current visual positioning information from pre-stored reference visual positioning information, and controlling the vehicle to travel to a geographic location where the target reference visual positioning information is located. According to the image sent by the terminal, the vehicle can determine the geographic location of the destination area according to the current visual positioning information identified from the image, and then control the vehicle to automatically drive to the destination, so that the efficiency of automatic parking is higher, the terminal does not need to download a parking lot map, data flow of the terminal is saved, and a user only needs to pre-store or shoot an image of the destination to acquire positioning information of the destination, thereby providing convenience for the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a vehicle control method, a vehicle control device, a controller, a vehicle and a computer readable storage medium. BACKGROUND

[0002] In recent years, with the continuous development of automatic driving function, automatic parking function appears, but the existing automatic parking function has some problems. When automatic parking, if the user needs to call the vehicle remotely, the map of the parking place needs to be downloaded in the mobile terminal, then the target geographical position is selected in the downloaded map, and the vehicle is controlled to travel to the target geographical position. However, the screen of the mobile phone is small, and the parking map elements are too many, which leads to the user easily selecting the wrong destination, and the vehicle is easy to travel to the wrong place when calling the vehicle or automatic parking. SUMMARY

[0003] In view of the above problems, the present application embodiment is proposed in order to provide a vehicle control method, device, controller, vehicle and computer readable storage medium which overcomes the above problems or at least partially solves the above problems.

[0004] In order to solve the above problems, the present application embodiment discloses a vehicle control method applied to a vehicle, the method comprising:

[0005] acquiring an image sent by a terminal;

[0006] identifying the image to obtain current visual positioning information in the image;

[0007] from the pre-stored reference visual positioning information, searching for target reference visual positioning information matched with the current visual positioning information;

[0008] controlling the vehicle to travel to a geographical position corresponding to the target reference visual positioning information.

[0009] Optionally, the current visual positioning information includes visual feature points, and the identification of the image to obtain the current visual positioning information in the image comprises:

[0010] screening visual feature points from the pixel points of the image, the visual feature points including at least one of the following: corner points, points with a light-dark contrast greater than a threshold value.

[0011] Optionally, the current visual positioning information further includes parking lot elements, and the identification of the image to obtain the current visual positioning information in the image further comprises:

[0012] According to a preset recognition model, the visual feature points are recognized to obtain the parking lot elements; the parking lot elements at least include one of the following: a column, a speed bump, an anti-collision strip, a parking space number, a lane line, a road identification pattern, a ground identification board, a monitoring camera, a lighting device, and a wall surface indication.

[0013] Optionally, the step of searching, from the pre-stored reference visual positioning information, target reference visual positioning information matching the current visual positioning information comprises:

[0014] The current visual positioning information is compared with the reference visual positioning information to obtain a similarity between the current visual positioning information and the reference visual positioning information.

[0015] Reference visual positioning information with a similarity greater than or equal to a similarity threshold value to the current visual positioning information is determined as target reference visual positioning information.

[0016] Optionally, the current visual positioning information includes multiple, and the method further comprises:

[0017] When at least one of the multiple current visual positioning information matches the reference visual positioning information, the current visual positioning information that does not match the reference visual positioning information among the multiple current visual positioning information is stored as reference visual positioning information corresponding to a geographical position corresponding to target reference visual positioning information matched by the current visual positioning information.

[0018] Optionally, the current visual positioning information includes multiple, and the method further comprises:

[0019] When at least one of the multiple current visual positioning information matches the reference visual positioning information, the current visual positioning information that does not match is stored as reference visual positioning information.

[0020] According to a geographical position corresponding to target reference visual positioning information matched by the current visual positioning information and position information of the current visual positioning information that does not match in the image, a geographical position of the current visual positioning information that does not match is determined.

[0021] The reference visual positioning information corresponding to the current visual positioning information that does not match is stored corresponding to the geographical position of the current visual positioning information that does not match.

[0022] Optionally, before the step of controlling the vehicle to travel to the corresponding geographical position according to the target reference visual positioning information, the method further comprises:

[0023] Send an available signal of a preset function to the terminal, the available signal being used to instruct a user to enable the preset function; the preset function including an automatic parking function or a remote calling function;

[0024] Receive an enabling instruction sent by the terminal, and activate the preset function in response to the enabling instruction.

[0025] The application further discloses a control method of a vehicle, applied to a server, and the method comprises the following steps:

[0026] Obtaining an image sent by a terminal;

[0027] Identifying the image to obtain current visual positioning information in the image;

[0028] Finding target reference visual positioning information matched with the current visual positioning information from pre-stored reference visual positioning information;

[0029] Determining a target geographical position according to the target reference visual positioning information;

[0030] Sending the target geographical position to a vehicle to enable the vehicle to travel to the target geographical position.

[0031] The application further discloses a control device of a vehicle, applied to a vehicle, and the device comprises the following steps:

[0032] An obtaining module is configured to obtain an image sent by a terminal;

[0033] An identifying module is configured to identify the image to obtain current visual positioning information in the image;

[0034] A finding module is configured to find target reference visual positioning information matched with the current visual positioning information from pre-stored reference visual positioning information;

[0035] A control module is configured to control the vehicle to travel to a geographical position corresponding to the target reference visual positioning information.

[0036] Optionally, the current visual positioning information comprises visual feature points, and the identifying module comprises:

[0037] A screening sub-module is configured to screen visual feature points from pixel points of the image, and the visual feature points comprise at least one of the following: corner points, points with a light-dark contrast greater than a threshold.

[0038] Optionally, the current visual positioning information further comprises parking lot elements, and the identifying module further comprises:

[0039] The identification sub-module is configured to identify the visual feature points according to a preset identification model to obtain the parking lot element; the parking lot element at least includes one of the following: a column, a speed bump, an anti-collision strip, a parking space number, a lane line, a road identification pattern, a ground signboard, a monitoring camera, a lighting device, and a wall surface indication.

[0040] Optionally, the searching module comprises:

[0041] The comparison sub-module is configured to compare the current visual positioning information with the reference visual positioning information to obtain a similarity between the current visual positioning information and the reference visual positioning information.

[0042] The determination sub-module is configured to determine the reference visual positioning information with a similarity greater than or equal to a similarity threshold value as target reference visual positioning information.

[0043] Optionally, the current visual positioning information comprises a plurality of current visual positioning information, and the apparatus further comprises:

[0044] The first storage module is configured to, when at least one of the plurality of current visual positioning information matches the reference visual positioning information, store the current visual positioning information that does not match the reference visual positioning information as the reference visual positioning information, and store a geographical position corresponding to the target reference visual positioning information matched by the current visual positioning information.

[0045] Optionally, the current visual positioning information comprises a plurality of current visual positioning information, and the apparatus further comprises:

[0046] The matching module is configured to, when at least one of the plurality of current visual positioning information matches the reference visual positioning information, store the current visual positioning information that does not match the reference visual positioning information as the reference visual positioning information.

[0047] The determination module is configured to determine a geographical position of the current visual positioning information that does not match the reference visual positioning information according to a geographical position corresponding to the target reference visual positioning information matched by the current visual positioning information and position information of the current visual positioning information in the image.

[0048] The second storage module is configured to store the reference visual positioning information corresponding to the current visual positioning information that does not match the reference visual positioning information and the geographical position of the current visual positioning information that does not match the reference visual positioning information.

[0049] Optionally, the apparatus further comprises:

[0050] The sending module is configured to send an available signal of a preset function to the terminal, the preset function being a function based on the target reference visual positioning information; the preset function includes an automatic parking function or a remote calling function.

[0051] A response module is configured to receive the enabling instruction sent by the terminal and activate the preset function in response to the enabling instruction.

[0052] The application further discloses a controller, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and when the computer program is executed by the processor, the steps of the control method of the vehicle are implemented.

[0053] The application further discloses a vehicle including the controller.

[0054] The application further discloses a computer readable storage medium, which stores a computer program enabling a processor to execute the steps of the control method of the vehicle.

[0055] The embodiment of the application has the following advantages:

[0056] The application discloses acquiring an image sent by a terminal, identifying the image to obtain current visual positioning information, finding target reference visual positioning information matching the current visual positioning information from pre-stored reference visual positioning information, and controlling a vehicle to travel to a geographic position where the target reference visual positioning information is located according to the target reference visual positioning information. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 is a step flow chart of a control method of a vehicle provided by the embodiment of the application;

[0058] Figure 2 is a schematic diagram of a communication mode of a vehicle and a terminal provided by the embodiment of the application;

[0059] Figure 3 is another schematic diagram of a communication mode of a vehicle and a terminal provided by the embodiment of the application;

[0060] Figure 4 is a step flow chart of another control method of a vehicle provided by the embodiment of the application;

[0061] Figure 5 shows a schematic diagram of an image sent by a terminal provided by the embodiment of the application;

[0062] Figure 6is a step flow chart of a control method of a vehicle provided by an embodiment of the present application;

[0063] Figure 7 is a structural block diagram of a control device of a vehicle provided by an embodiment of the present application;

[0064] Figure 8 is a structural block diagram of a controller provided by an embodiment of the present application;

[0065] Figure 9 is a structural block diagram of a vehicle provided by an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to make the above objectives, characteristics and advantages of the present application more apparent, comprehensible and easily understood, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0067] In the prior art, the whole process of AVP (Automated Valet Parking) includes that a user terminal downloads a parking lot map, after a vehicle enters the parking lot, a destination parking space is selected by the user terminal to activate the valet parking or intelligent calling; however, when the user needs to remotely call the vehicle, a map of a parking lot where the user is located needs to be downloaded in the mobile terminal, and the parking lot map download fails, which may result in that the user cannot use the remote calling function; in the case that the map is successfully downloaded in the mobile terminal, the user needs to select a destination in the downloaded map, and the step of selecting the destination generally includes: clicking a specified parking lot map, zooming in the map, selecting a target parking space, and activating the automatic parking function, the operation is very complex, and the elements displayed in the general parking lot map are limited, and there may be a case that the user fails to select the target parking space, for example, there are thousands of parking spaces in the parking lot map, and the elements displayed on the mobile phone screen are very limited, if the user is not familiar with the parking lot, the error rate of selecting the target parking space is very high, which results in poor user experience.

[0068] Based on this, one of the core ideas of the embodiments of the present application is to provide a control method of a vehicle, by acquiring an image sent by a terminal, the vehicle can recognize the geographical position of a destination area according to the image, and then control the vehicle to automatically drive to the destination, so that the way of selecting the destination area is more convenient, and the terminal does not need to download a parking lot map, which saves data flow for the mobile terminal, and the user only needs to pre-store or shoot an image of the destination to acquire the positioning information of the destination, which provides convenience for the user.

[0069] Reference Figure 1 , a step flow chart of a control method of a vehicle provided by an embodiment of the present application is shown, which is applied to a vehicle, and the method can specifically include the following steps:

[0070] In step 101, an image sent by a terminal is acquired.

[0071] In the embodiment of the present application, the vehicle can acquire the image sent by the terminal in various ways, such as Figure 2 Fig. 2 shows a communication mode between a vehicle and a terminal according to an embodiment of the present application, which comprises that the vehicle end in the vehicle and the terminal transmit data through Bluetooth or WIFI (Wireless Fidelity), that is, the terminal directly transmits the image to the vehicle end through Bluetooth or WIFI. Figure 3 Fig. 3 shows another communication mode between a vehicle and a terminal according to an embodiment of the present application, in which the vehicle end and the terminal transmit data through a cloud, that is, the terminal transmits the image to the cloud through a mobile network, and then the cloud transmits the received image data to the vehicle end through the mobile network, which can be a 4G or 5G network, without limitation here.

[0072] The terminal in the present application can be a mobile terminal or a non-mobile terminal; the mobile terminal can be a mobile phone, a tablet computer, a notebook computer, a palm computer, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc., without specific limitation in the embodiment of the present application.

[0073] In some application scenarios, the user can take a picture or a video of a parking space through the terminal and then send the taken picture or video to the vehicle, which comprises an automatic driving system; when the user takes a video of the parking lot, the automatic driving system can intercept the video, which can be in the way of extracting a picture every certain time according to the video or setting an extraction rule according to the frame rate of the video, and the automatic driving system can eliminate similar pictures in the extracted pictures to obtain multiple pictures; in an example, the video data is 10s, and there are 10-20 pictures per second, so many pictures can be generated, and adjacent pictures are very similar, in order to improve the operation efficiency and avoid extracting invalid pictures, every 3 pictures can be processed, and then the same pictures are removed to obtain multiple pictures.

[0074] In some application scenarios, the user can pre-store a picture or a video of a parking space through the terminal and then send the pre-stored picture or video to the vehicle; when the terminal sends a video, the automatic driving system in the vehicle can intercept the video, and the video interception mode is consistent with the foregoing, without limitation here.

[0075] Step 102, recognizing the image to obtain current visual positioning information in the image.

[0076] In the embodiment of the present application, the current visual positioning information refers to visual information used for representing the current corresponding position of the image, and the current visual positioning information refers to information that can be used for visual positioning in the image to determine the current corresponding position of the image; the vehicle can recognize the image to obtain the current visual positioning information in the image.

[0077] Step 103, searching for target reference visual positioning information matched with the current visual positioning information from the pre-stored reference visual positioning information.

[0078] In the embodiment of the present application, the reference visual positioning information is used for representing visual information of the image of the geographical position in the parking lot map.

[0079] The automobile manufacturer can collect images corresponding to a plurality of geographical positions in the parking lot map before the vehicle is shipped, recognize the collected images to obtain reference visual positioning information corresponding to the plurality of geographical positions, and then mark the plurality of reference visual positioning information in the parking lot map to form reference visual positioning information associated with the parking lot map; or the vehicle can download a required parking lot map in real time from an image download website after the vehicle is shipped, and each geographical position in the parking lot map corresponds to a reference visual positioning information; therefore, the target reference visual positioning information matched with the current visual positioning information can be searched from the pre-stored reference visual positioning information in the vehicle, and the geographical position of the image can be determined according to the target reference visual positioning information since the target reference visual positioning information corresponds to a geographical position in the parking lot map; for example, when the front visual positioning information recognized from the image includes a parking space identifier 512 and a letter H, and the target visual positioning information queried in the vehicle also includes the parking space identifier 512 and the letter H, it is indicated that the current visual positioning information is matched with the target reference visual positioning information, and the geographical position of the target reference visual positioning information can be determined as the geographical position of the image.

[0080] Step 104, controlling the vehicle to travel to the corresponding geographical position.

[0081] In the embodiment of the present application, after the target reference visual positioning information is determined, the automatic parking or remote calling function of the vehicle can be started since the target reference visual positioning information corresponds to a geographical position in the parking lot map, and the vehicle is controlled to travel from the position of the vehicle to the position of the image sent by the terminal to realize automatic parking or automatic calling.

[0082] The application obtains the image sent by the terminal, identifies the image to obtain the current visual positioning information, finds the target reference visual positioning information matching the current visual positioning information in the pre-stored reference visual positioning information, and controls the vehicle to drive to the geographic position where the image is located, because the target reference visual positioning information has the corresponding geographic position. According to the target reference visual positioning information, the vehicle can be controlled to drive to the geographic position of the destination area according to the image, and then the vehicle is automatically driven to the destination, so that the step of automatically parking the vehicle to select the destination is simplified, the way of selecting the destination area is more convenient, the terminal does not need to download the parking lot map, the data flow of the mobile terminal is saved, and the user only needs to pre-store or shoot the image of the destination to obtain the positioning information of the destination, thereby providing convenience for the user.

[0083] As Figure 4 , a step flow chart of another vehicle control method provided by the embodiment of the application is shown, which is applied to a vehicle, and the method can include the following steps:

[0084] Step 201, obtaining the image sent by the terminal.

[0085] In the embodiment of the application, the image can be a picture pre-stored by the terminal or a picture cut from a video, and can also be a picture of a parking lot taken by the terminal or a picture cut from a video, when the user needs to remotely call the vehicle, the picture of the user's location or the picture cut from the video can be sent to the vehicle, and when the user needs to automatically park the vehicle to a specified parking space, the picture of the specified parking space or the picture cut from the video saved in advance can be sent to the vehicle.

[0086] Step 202, identifying the image to obtain the current visual positioning information in the image.

[0087] In the embodiment of the application, when the image is a taken picture, the current visual positioning information in the image can be obtained by identifying the pixel points in the picture, and when the image is a picture cut from a taken video, the current visual positioning information in the image can be obtained by identifying the cut picture.

[0088] In one embodiment of the application, the current visual positioning information can include visual feature points, and the identification of the image to obtain the current visual positioning information in the image can include: screening the visual feature points from the pixel points of the image, and the visual feature points include at least one of the following: a corner point and a point with a brightness contrast greater than a threshold value.

[0089] In the embodiment of the present application, the current visual positioning information can include visual feature points, the visual feature points can include corner points in the image and points with a contrast greater than a threshold, the visual feature points can be obtained by screening the pixel points of the image, that is, some unimportant points are removed, specifically, the point cloud data formed by dynamic obstacles in the pixel points of the image is removed, the point cloud data formed by some static obstacles is removed, and then the corner points and the points with a contrast greater than a threshold are selected.

[0090] In an embodiment of the present application, the current visual positioning information can further include parking lot elements, the image recognition to obtain the current visual positioning information in the image further includes: identifying the visual feature points according to a preset identification model to obtain the parking lot elements; the parking lot elements at least include one of the following: a column, a speed bump, a crash barrier, a parking space number, a lane line, a road identification pattern, a ground identification board, a monitoring camera, a lighting device, and a wall surface instruction.

[0091] In the embodiment of the present application, the current visual positioning information can further include parking lot elements, the parking lot elements refer to elements with fixed positions in the parking lot, and the dynamic obstacles do not have the fixedness, for example, pedestrians and vehicles in motion appear and leave at any time, which can cause certain influence on subsequent image matching, therefore, the elements formed by the dynamic obstacles in the image can be removed; the static obstacles also do not have the fixedness, for example, tricycles and trolleys also appear or leave at any time, therefore, the elements formed by some prohibited obstacles can be removed, and then the remaining pixel points in the image are identified to obtain the parking lot elements, that is, the visual feature points are identified.

[0092] The parking lot elements can include at least one of the following: a column, a speed bump, a crash barrier, a parking space number, a lane line, a road identification pattern, a ground identification board, a monitoring camera, a lighting device, and a wall surface instruction; the visual feature points can be identified by a preset identification model to obtain the parking lot elements, specifically, the preset depth model refers to a pre-trained deep learning model, the points with similar distances in the visual feature points can be aggregated to obtain a feature point set, since different feature point sets in the trained deep learning model correspond to one parking lot element information, the feature point set can be identified by the trained deep learning model to obtain corresponding semantic information, that is, multiple parking lot elements;

[0093] It should be noted that the deep learning model can include one of a convolutional neural network (CNN), a recurrent neural network (RNN), and a recursive neural network (RNN), which is not limited herein.

[0094] Step 203, comparing the current visual positioning information with the reference visual positioning information to obtain the similarity between the current visual positioning information and the reference visual positioning information.

[0095] In the embodiment of the application, the parking lot map corresponds to a reference visual positioning information at each geographical position, the reference visual positioning information also includes the corner points, the points with the contrast greater than the threshold, and the parking lot, the current visual positioning information can be compared with the reference visual positioning information to obtain the similarity between them, and then the target reference visual positioning information matched with the current positioning information can be determined according to the size of the similarity. In an example, the current visual positioning information includes the corner points, the points with the contrast greater than the threshold, and the parking lot element, the parking lot element includes the parking space number H302 and the wall sign: please note the vehicle in front, the reference visual positioning information is extracted, and then the corner points, the points with the contrast greater than the threshold, the parking space number H302, and the wall sign: please note the vehicle in front of the image are compared with the corner points, the points with the contrast greater than the threshold, and the parking lot element in the reference visual positioning information one by one, so as to obtain the similarity between the current visual positioning information and the reference visual positioning information.

[0096] Step 204, determining the reference visual positioning information with the similarity greater than or equal to the similarity threshold to the current visual positioning information as the target reference visual positioning information.

[0097] In the embodiment of the application, the similarity threshold can be set according to the user demand, which is not limited herein, and in an example, the similarity threshold is set to 80%, the corner points, the points with the contrast greater than the threshold, and the parking lot element in the current visual positioning information are compared with the corner points, the points with the contrast greater than the threshold, and the parking lot element in the reference visual positioning information, if the contrast is greater than or equal to 80%, the reference visual positioning information with the similarity greater than or equal to the similarity threshold to the current visual positioning information can be determined as the target reference visual positioning information.

[0098] It should be noted that there will always be some elements same between the current visual positioning information and the reference visual positioning information, for example, both of them include the column, the parking line, and the anti-collision strip, therefore, the reference visual positioning information with the greatest contrast in the multiple contrasts can be taken as the target reference visual positioning information.

[0099] In an embodiment of the present application, when the current visual positioning information includes multiple, at least one of which matches the reference visual positioning information, the reference visual positioning information can be determined as the target reference visual positioning information, and the geographic position of the current visual positioning information is determined. In an example, the current visual positioning information includes a yellow anticollision strip, a parking space number 311, a lane line, and a ground sign MU2596. One of the reference visual positioning information is also the ground sign MU2596. The reference visual positioning information can be determined as the target reference visual positioning information.

[0100] In step 205, a signal indicating availability of the preset function is sent to the terminal, and the signal is used to instruct the user to enable the preset function. The preset function includes an automatic parking function or a remote calling function.

[0101] In the embodiment of the present application, the preset function can be a function based on the target reference visual positioning information, i.e., a function of determining the target reference visual positioning information, which can include an automatic parking function or a remote calling function. When the user needs to park the vehicle in a specified parking space, the preset function is the automatic parking function. When the user needs to call the vehicle from the specified parking space to the user's location, the preset function is the remote calling function. After the target reference visual positioning information is determined, it is indicated that the vehicle has determined the geographic position corresponding to the current reference positioning information. At this time, the vehicle can send a signal indicating availability of the preset function to the terminal. Since the signal can be used to instruct the user to enable the preset function, the terminal can enable the preset function according to the user's demand after receiving the signal indicating availability of the preset function. The present application can send the signal indicating availability of the preset function to the terminal, so that the user can enable the corresponding preset function in the case of knowing the state of the preset function, and avoid starting the preset function in the case of the preset function not being ready. The present application provides convenience for the user.

[0102] In step 206, an enabling instruction sent by the terminal is received, and the preset function is activated in response to the enabling instruction.

[0103] In the embodiment of the present application, after the terminal receives the signal indicating availability of the preset function, the terminal can send an enabling instruction to the vehicle. After the vehicle receives the enabling instruction, the corresponding preset function can be activated. In an example, when the preset function of the vehicle includes a remote calling function, and the remote calling function is available, the user clicks an enabling remote calling button of the terminal. The terminal sends an enabling remote calling instruction to the vehicle based on the user's command. After the vehicle receives the enabling remote calling instruction sent by the terminal, the remote calling function is activated.

[0104] In step 207, the vehicle is controlled to travel to the geographic position corresponding to the target reference visual positioning information.

[0105] In the embodiment of the present application, after the target reference visual positioning information is determined, since the target reference visual positioning information in the parking lot map corresponds to a geographic location, the automatic driving system in the vehicle can plan a driving path between the vehicle and the geographic location of the target reference visual positioning information, and then drive to the corresponding position according to the driving path. In an example, the user is at the 301 parking space of the parking lot, the vehicle is parked at the 603 parking space of the parking lot, the user sends the picture of the 301 parking space to the vehicle, the vehicle identifies the geographic location of the 301 parking space according to the picture, and then sends the state that the automatic calling function is available to the user terminal. After the user terminal receives the state that the automatic calling function is available, a driving path between the 301 parking space and the 603 parking space is planned, and then the vehicle is controlled to drive from the 603 parking space to the 301 parking space, i.e. the user's location. In the present application, the user does not need to walk to the parking position, but only needs to send the picture or video of the user's location, so as to realize remote calling of the vehicle and improve the convenience for the user.

[0106] In another example, when the user drives the vehicle to the entrance of the parking lot of a certain shopping mall, and wants to park the vehicle in the H area 622 parking space of the first floor underground of the shopping mall by using the automatic parking function, the user can send the picture or video of the H area 622 parking space pre-stored in the mobile phone to the vehicle. The vehicle can identify the geographic location of the H area 622 parking space according to the picture or video, and then send the state that the automatic parking function is available to the user terminal. After the user terminal receives the state that the automatic parking function is available, the automatic parking function is enabled. Then, after the vehicle receives the enabling instruction, a driving path between the geographic location of the H area 622 parking space and the vehicle is planned, and then the vehicle is controlled to drive to the geographic location of the H area 622 parking space, so as to realize automatic parking.

[0107] In an embodiment of the present application, the current visual positioning information includes a plurality of, and the method further comprises:

[0108] When at least one of the plurality of current visual positioning information matches the reference visual positioning information, the current visual positioning information in the plurality of current visual positioning information which does not match the reference visual positioning information is stored as the reference visual positioning information, and the geographic location corresponding to the target reference visual positioning information matched by the current visual positioning information is stored.

[0109] In the embodiment of the present application, the current visual positioning information can include multiple, for example, a picture sent by the terminal, the current visual positioning information identified from the picture is the wall marking H area, two yellow lane lines on the ground, and the ground digital marking 1602, and in the vehicle-mounted map, it can be found that only the ground marking 1602 in the current visual positioning information matches the reference visual positioning information, which indicates that the current visual positioning information matches the reference visual positioning information, at this time, the geographic position corresponding to the current visual positioning information which does not match the reference visual positioning information can be determined according to the geographic position of the target reference visual positioning information, the geographic position corresponding to the current visual positioning information which does not match the reference visual positioning information is marked in the current visual positioning information which does not match the reference visual positioning information, that is, the geographic position corresponding to the target reference visual positioning information is matched with the H area and the two yellow lane lines on the ground one by one, then the H area and the two yellow lane lines on the ground are added as the reference visual positioning information, at this time, the target reference visual positioning information is changed from only the ground marking 1602 to the wall marking H area, the two yellow lane lines on the ground, and the ground digital marking 1602, when the wall marking H area and the two yellow lane lines on the ground are identified, the corresponding geographic position can also be determined; when at least one of the multiple current visual positioning information matches the reference visual positioning information, the present application can continuously extract new information elements and add them to the reference visual positioning information, so that the data for the current visual positioning information to match is more and more rich.

[0110] In an embodiment of the present application, the current visual positioning information includes multiple, and the method further comprises:

[0111] When at least one of the multiple current visual positioning information matches the reference visual positioning information, the current visual positioning information which does not match is taken as the reference visual positioning information; the geographic position of the current visual positioning information which does not match is determined according to the geographic position corresponding to the target reference visual positioning information which matches the current visual positioning information, and the position information of the current visual positioning information which does not match in the image; the reference visual positioning information corresponding to the current visual positioning information which does not match is stored in correspondence with the geographic position of the current visual positioning information which does not match.

[0112] In the embodiment of the present application, the multiple current visual positioning information in the image has a certain positional relationship, after the geographic position of one of the current visual positioning information is determined, the geographic positions of other current visual positioning information can be determined according to the positional relationship.

[0113] In an example, as Figure 5, the schematic diagram of the image sent by the terminal is shown, the current visual positioning information identified in the image is A, B and C, the relative distance between A and B identified from the image is d1, the relative distance between A and C is d2, and only A in the current visual positioning information matches the reference visual positioning information, that is, the geographic position of A can be determined according to the target reference visual positioning information matched with A, then the geographic position information of B can be determined according to the geographic position of A and d1, and the geographic position information of C can be determined according to the geographic position of A and d2, then B and C can be added as reference visual positioning information respectively, wherein the reference visual positioning information B is stored in correspondence with the geographic position of B, and the reference visual positioning information C is stored in correspondence with the geographic position of C, in this way, when at least one of the current visual positioning information in the current multiple current visual positioning information matches the reference visual positioning information, the current visual positioning information which does not match the target reference reference visual positioning information can be added as the reference visual positioning information, so that when the current positioning reference information of the parking lot changes, for example, the previous ground landmark, new semantic information and new corner point, the newly added current positioning reference information can be updated to the reference visual positioning information, the matching elements in the identification library are continuously improved, and the efficiency of the automatic driving system to identify the destination is improved.

[0114] The application discloses acquiring an image sent by a terminal, identifying the image to obtain current visual positioning information, finding target reference visual positioning information matched with the current visual positioning information in prestored reference visual positioning information, and the target reference visual positioning information has corresponding geographic position; and controlling a vehicle to travel to the geographic position where the image is located according to the target reference visual positioning information. The vehicle can identify the geographic position of a destination region according to the image, and then automatically drive to the destination, so that the step of selecting the destination by the automatic parking is simplified, the way of selecting the destination region is more convenient, the terminal does not need to download the parking lot map, data flow of the mobile terminal is saved, and the user only needs to prestore or shoot the image of the destination to acquire the positioning information of the destination, so that convenience is provided for the user. The reference visual positioning information of the vehicle terminal can be updated and expanded in real time, abnormality of the automatic parking function caused by changes of the parking lot is avoided, robustness of the automatic driving system of the vehicle is continuously increased, reliability of the function is continuously improved, and experience of the user is continuously optimized.

[0115] Reference Figure 6 , a step flow chart of a control method of a vehicle is shown, applied to a server, and the method can include the following steps:

[0116] Step 301, acquiring an image sent by a terminal;

[0117] In the embodiment of the present application, the image can be a picture pre-stored by the terminal or a picture cut from a video, and can also be a picture of a parking lot captured by the terminal in real time or a picture cut from a video, when the user needs to remotely call the vehicle, the picture of the user's location or the picture cut from the video can be sent to the server, and when the user needs to automatically park the vehicle to the specified parking space, the picture of the specified parking space cut from the video saved in advance can be sent to the server.

[0118] In step 302, the image is recognized to obtain current visual positioning information in the image.

[0119] In the embodiment of the present application, the current visual positioning information refers to visual information used to represent the current corresponding position of the image, which can be used for visual positioning to determine the information of the current corresponding position of the image; the server can recognize the obtained image to obtain the current visual positioning information in the image.

[0120] In step 303, target reference visual positioning information matched with the current visual positioning information is searched from the pre-stored reference visual positioning information.

[0121] In the embodiment of the present application, the server can pre-collect images corresponding to a plurality of geographic positions in the parking lot map, recognize the collected images to obtain reference visual positioning information corresponding to a plurality of geographic positions, and then mark the plurality of reference visual positioning information on the parking lot map downloaded by the server to form reference visual positioning information associated with the parking lot map, based on which, the server can search target reference visual positioning information matched with the current visual positioning information from the pre-stored reference visual positioning information, and since the target reference visual positioning information corresponds to a geographic position in the parking lot map, the geographic position of the image can be determined according to the target reference visual positioning information.

[0122] In step 304, the target geographic position is determined according to the target reference visual positioning information.

[0123] In the embodiment of the present application, the target geographic position refers to the current corresponding geographic position of the image, since the target reference visual positioning information corresponds to a geographic position in the parking lot map, the target geographic position of the image can be determined according to the target reference visual positioning information.

[0124] In step 305, the target geographic position is sent to the vehicle to make the vehicle travel to the target geographic position.

[0125] In the embodiment of the present application, after the server determines the geographic position, the target geographic position can be sent to the vehicle, since the vehicle is configured with an automatic driving function, the path of the vehicle from the position to the destination geographic position can be planned according to the geographic position of the destination, and then the vehicle travels to the target geographic position according to the planned path.

[0126] The application can acquire the image sent by the terminal through the server, recognize the geographic position of the destination area according to the image, and send the geographic position of the destination area to the vehicle, so that the vehicle is automatically driven to the destination area, the step of automatically parking and selecting the destination is simplified, the way of selecting the destination area is more convenient, the terminal does not need to download the parking lot map, the data flow of the mobile terminal is saved, the user only needs to prestore or shoot the image of the destination and send it to the server, and the vehicle can acquire the geographic position information of the destination, thereby providing convenience for automatic calling of the vehicle or automatic parking.

[0127] It should be noted that, for the method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the application are not limited to the action sequence described, because according to the embodiments of the application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions involved are not necessarily necessary for the embodiments of the application.

[0128] Referring to Figure 7 , a structural block diagram of a control device of a vehicle is shown, which is applied to a vehicle, and the device can specifically include the following modules:

[0129] The acquisition module 401 is configured to acquire an image sent by a terminal.

[0130] The identification module 402 is configured to identify the image to obtain current visual positioning information in the image.

[0131] The search module 403 is configured to search, from pre-stored reference visual positioning information, target reference visual positioning information matched with the current visual positioning information.

[0132] The control module 404 is configured to control the vehicle to travel to a geographic position corresponding to the target reference visual positioning information.

[0133] The application discloses a control device of a vehicle, which comprises an acquisition module, an identification module, a search module and a control module. The control device can acquire an image sent by a terminal, recognize a geographic position of a destination area according to the image, control a vehicle to automatically drive to the destination, improve the efficiency of automatic parking, save data flow of the terminal, and provide convenience for users by pre-storing or shooting an image of the destination to acquire positioning information of the destination.

[0134] In an embodiment of the application, the current visual positioning information comprises a visual feature point, and the identification module 402 can comprise:

[0135] The screening sub-module is configured to screen visual feature points from the pixels of the image, the visual feature points including at least one of the following: a corner point, and a point with a light-dark contrast greater than a threshold value.

[0136] In an embodiment of the present application, the current visual positioning information further includes parking lot elements, and the identification module 402 further includes:

[0137] The identification sub-module is configured to identify the visual feature points according to a preset identification model to obtain the parking lot elements, the parking lot elements including at least one of the following: a column, a speed bump, an anti-collision strip, a parking space number, a lane line, a road identification pattern, a ground identification board, a monitoring camera, an illumination device, and a wall surface indication.

[0138] In an embodiment of the present application, the searching module 403 includes:

[0139] The comparison sub-module is configured to compare the current visual positioning information with the reference visual positioning information to obtain a similarity between the current visual positioning information and the reference visual positioning information.

[0140] The determination sub-module is configured to determine the reference visual positioning information with a similarity greater than or equal to a similarity threshold value to the current visual positioning information as target reference visual positioning information.

[0141] In an embodiment of the present application, the current visual positioning information includes a plurality of, and the device further includes:

[0142] The first storage module is configured to, when at least one of the plurality of current visual positioning information matches the reference visual positioning information, store the current visual positioning information that does not match the reference visual positioning information as the reference visual positioning information, and store a geographical position corresponding to the target reference visual positioning information matched by the current visual positioning information.

[0143] Optionally, the current visual positioning information includes a plurality of, and the device further includes:

[0144] The matching module is configured to, when at least one of the plurality of current visual positioning information matches the reference visual positioning information, store the current visual positioning information that does not match the reference visual positioning information as the reference visual positioning information.

[0145] The determination module is configured to determine a geographical position of the current visual positioning information that does not match the reference visual positioning information according to a geographical position corresponding to the target reference visual positioning information matched by the current visual positioning information and position information of the current visual positioning information in the image.

[0146] The second storage module is configured to store the reference visual positioning information corresponding to the unmatched current visual positioning information in the geographic position corresponding to the unmatched current visual positioning information.

[0147] In an embodiment of the present application, the device further comprises:

[0148] The sending module is configured to send an available signal of a preset function to the terminal, the preset function being a function based on the target reference visual positioning information; the preset function including an automatic parking function or a remote calling function.

[0149] The response module is configured to receive an enabling instruction sent by the terminal and activate the preset function in response to the enabling instruction.

[0150] The application discloses a control device of a vehicle, comprising an acquisition module, an identification module, a search module and a control module; the vehicle can identify the geographic position of a destination area according to an image sent by a terminal, and then automatically drive to the destination, so that the efficiency of automatic parking is higher, the terminal is free from downloading a parking lot map, data flow of the terminal is saved, a user only needs to prestore or shoot an image of the destination to acquire positioning information of the destination, and convenience is provided for the user; the application can update and expand reference visual positioning information of the terminal in real time, avoids abnormality of an automatic parking function caused by changes in a parking lot, continuously increases robustness of an automatic driving system, continuously improves reliability of a function, and continuously optimizes experience of the user.

[0151] For the device embodiment, the description is relatively simple because the device embodiment is basically similar to the method embodiment, and the related parts refer to the part of the method embodiment.

[0152] As Figure 8 As shown in the figure, the controller 50 provided by the embodiment of the application comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, the computer program realizes each process of the control method of the vehicle and achieves the same technical effect when executed by the processor, and details are not repeated here to avoid repetition.

[0153] As Figure 9 As shown in the figure, the vehicle 60 provided by the embodiment of the application comprises the controller as described above.

[0154] It should be noted that the vehicle can also include other components, such as a vehicle generally including a chassis, a vehicle body, an engine, and electrical equipment. The engine is a power device of the vehicle, used to generate power; the chassis is used to support the transmitter and the vehicle body, and the chassis can drive the vehicle to move according to the power generated by the engine; the vehicle body is mounted on the frame of the chassis, used for the driver, the passenger to ride or load the goods; the electrical equipment includes a power supply and an electrical equipment, for example, the power supply includes a storage battery and a generator, and the electrical equipment includes a starting system of the engine or other electrical devices. The vehicle also includes a vehicle sensor (such as a camera, a laser radar, a millimeter wave radar, an RGBD camera, etc.), which is used to perceive the environmental information of the surrounding environment of the vehicle. The vehicle also includes an automatic driving system, which is used to assist the driver to drive, realize automatic parking and remote calling of the vehicle.

[0155] The embodiments of the present application also provide a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to realize each process of the control method of the vehicle, and the same technical effects can be achieved. To avoid repetition, details are not described here.

[0156] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The same or similar parts between each embodiment are referred to each other.

[0157] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, device, or computer program product. Therefore, the embodiments of the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0158] The embodiments of the present application are described with reference to flowcharts and / or block diagrams according to the method, terminal device (system), and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of the flows and / or blocks in the flowchart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the computer or other programmable data processing terminal device produce a machine that implements the function specified in the flowchart and / or block diagram. Figure 1 The device for realizing the function specified in one flow or multiple flows and / or blocks Figure 1 The device for realizing the function specified in one flow or multiple flows and / or blocks

[0159] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks or steps.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks or steps.

[0161] Although preferred embodiments of the present application have been described, those skilled in the art will be able to make additional changes and modifications thereto without departing from the scope of the present application. Accordingly, it is intended to embrace all such changes and modifications as fall within the scope of the present application.

[0162] Finally, it is also important to note that the use of relational terms such as first and second, and the like, are used solely to distinguish one from another entity or action without necessarily requiring or implying any actual such relationship or order between or among the entities or actions. Also, the use of terms such as including, comprising, or having are used herein to be open ended terms that specify the presence of stated elements or features, but do not preclude the presence or addition of one or more other elements or features. As used herein, the phrase "at least one of A and B" means that "A or B or both A and B." As used herein, the phrase "at least one of A, B, and C" means "A or B or C or any combination of these." As used herein, the phrase "at least one of A, B, and C, and possibly others" means "A or B or C or any combination of these or any number of other elements."

[0163] The above provides a kind of vehicle control method, device, controller, vehicle, computer readable storage medium provided by the present application, detailed introduction is carried out in this paper, the principle and implementation mode of the present application are described by specific example, the above example is only for helping understanding the method of the present application and its core idea;For the general technical personnel in the art, according to the idea of the present application, there will be changes in specific implementation mode and application range, the above description should not be understood as the limitation of the present application.

Claims

1. A control method of a vehicle, characterized by, The method is applied to a vehicle and comprises the following steps: acquiring an image sent by a mobile terminal; identifying the image to obtain current visual positioning information in the image; searching for target reference visual positioning information matching the current visual positioning information from pre-stored reference visual positioning information; controlling the vehicle to travel to a geographical position corresponding to the target reference visual positioning information; the current visual positioning information comprises a plurality of current visual positioning information, and the method further comprises the following steps: when at least one of the plurality of current visual positioning information matches the reference visual positioning information, taking current visual positioning information in the plurality of current visual positioning information which does not match the reference visual positioning information as reference visual positioning information, and storing the reference visual positioning information corresponding to the geographical position corresponding to the target reference visual positioning information matched by the current visual positioning information; or, when at least one of the plurality of current visual positioning information matches the reference visual positioning information, taking the current visual positioning information which does not match as reference visual positioning information; determining a geographical position of the current visual positioning information which does not match according to the geographical position corresponding to the target reference visual positioning information matched by the current visual positioning information and position information of the current visual positioning information which does not match in the image; storing the reference visual positioning information corresponding to the current visual positioning information which does not match and the geographical position of the current visual positioning information which does not match.

2. The method of claim 1, wherein, The current visual positioning information comprises visual feature points, and the step of identifying the image to obtain current visual positioning information in the image comprises the following steps: screening visual feature points from pixel points of the image, wherein the visual feature points comprise at least one of the following: corner points, points with a contrast greater than a threshold.

3. The method of claim 2, wherein, The current visual positioning information further comprises parking lot elements, and the step of identifying the image to obtain current visual positioning information in the image further comprises the following step: identifying the visual feature points according to a preset identification model to obtain the parking lot elements; the parking lot elements comprise at least one of the following: a column, a speed bump, a crash barrier, a parking space number, a lane line, a road identification pattern, a ground signboard, a monitoring camera, a lighting device, and a wall surface instruction.

4. The method of claim 1, wherein, The step of searching for target reference visual positioning information matching the current visual positioning information from pre-stored reference visual positioning information comprises the following steps: comparing the current visual positioning information with the reference visual positioning information to obtain a similarity of the current visual positioning information and the reference visual positioning information; determining reference visual positioning information with a similarity greater than or equal to a similarity threshold as target reference visual positioning information.

5. The method of claim 1, wherein, Before the step of controlling the vehicle to travel to a geographical position corresponding to the target reference visual positioning information according to the target reference visual positioning information, the method further comprises the following steps: sending an available signal of a preset function to the terminal, wherein the available signal is used to instruct a user to enable the preset function; the preset function comprises an automatic parking function or a remote calling function; receiving an enabling instruction sent by the terminal, and activating the preset function in response to the enabling instruction.

6. A control method of a vehicle characterized by comprising: The method is applied to a server and comprises the following steps: acquiring an image sent by a mobile terminal; identifying the image to obtain current visual positioning information in the image; finding target reference visual positioning information matching the current visual positioning information from pre-stored reference visual positioning information; determining a target geographic location according to the target reference visual positioning information; sending the target geographic location to a vehicle to make the vehicle travel to the target geographic location; the current visual positioning information includes multiple, and the method further includes: when at least one of the multiple current visual positioning information matches the reference visual positioning information, storing current visual positioning information in the multiple current visual positioning information which does not match the reference visual positioning information as reference visual positioning information, and storing a geographic location corresponding to target reference visual positioning information matched by the current visual positioning information; or, when at least one of the multiple current visual positioning information matches the reference visual positioning information, storing the unmatched current visual positioning information as reference visual positioning information; determining a geographic location of the unmatched current visual positioning information according to a geographic location corresponding to target reference visual positioning information matched by the current visual positioning information and position information of the unmatched current visual positioning information in the image; storing reference visual positioning information corresponding to the unmatched current visual positioning information and the geographic location of the unmatched current visual positioning information.

7. A control device of a vehicle characterized by comprising: application to a vehicle, the device includes: an acquisition module for acquiring an image sent by a terminal; an identification module for identifying the image to obtain current visual positioning information in the image; a finding module for finding target reference visual positioning information matching the current visual positioning information from pre-stored reference visual positioning information; a control module for controlling the vehicle to travel to a geographic location corresponding to the target reference visual positioning information; the current visual positioning information includes multiple, and the device further includes: a first storage module for storing current visual positioning information in the multiple current visual positioning information which does not match the reference visual positioning information as reference visual positioning information when at least one of the multiple current visual positioning information matches the reference visual positioning information, and storing a geographic location corresponding to target reference visual positioning information matched by the current visual positioning information; a matching module for storing the unmatched current visual positioning information as reference visual positioning information when at least one of the multiple current visual positioning information matches the reference visual positioning information; a determination module for determining a geographic location of the unmatched current visual positioning information according to a geographic location corresponding to target reference visual positioning information matched by the current visual positioning information and position information of the unmatched current visual positioning information in the image; a second storage module for storing reference visual positioning information corresponding to the unmatched current visual positioning information and the geographic location of the unmatched current visual positioning information.

8. A controller characterized by, includes: A processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program, when executed by the processor, implementing the steps of the control method of the vehicle according to any one of claims 1 to 6.

9. A vehicle characterized by comprising: The vehicle comprises a controller according to claim 8.

10. A computer-readable storage medium, characterized in that, The computer program stored on the memory causes the processor to execute the steps of the control method of the vehicle according to any one of claims 1 to 6.

Images