WO2021259280A1

WO2021259280A1 - Vehicle parking method and apparatus, and vehicle-mounted device and storage medium

Info

Publication number: WO2021259280A1
Application number: PCT/CN2021/101598
Authority: WO
Inventors: 栗海兵; 厉健峰; 杜建宇; 王恒凯; 李超; 马欢; 刘斌; 刘清宇; 吴岗岗
Original assignee: 中国第一汽车股份有限公司
Priority date: 2020-06-24
Filing date: 2021-06-22
Publication date: 2021-12-30
Also published as: CN111783595B; CN111783595A

Abstract

Embodiments of the present application disclose a vehicle parking method and apparatus, and a vehicle-mounted device and a storage medium. The method comprises: obtaining, by means of a photographing apparatus, an external image of an area for parking a vehicle, and extracting at least one continuous area in the external image; obtaining, by means of detection of a radar apparatus, at least one first obstacle area of the area for parking, and fusing all the continuous areas and all the first obstacle areas to determine at least one second obstacle area; and generating a first parking trajectory route according to all the second obstacle areas.

Description

Vehicle parking method, device, vehicle-mounted equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office with an application number of 202010591404.8 on June 24, 2020, and the entire content of the application is incorporated into this application by reference.

Technical field

The embodiments of the present application relate to the field of automobile technology, for example, to a vehicle parking method, device, on-board equipment, and storage medium.

Background technique

With the development of driving assistance and autonomous driving technology, semi-automatic parking or fully automatic parking systems have gradually become an automobile configuration that attracts consumers among automobile products.

In the related art, the parking position of the vehicle is determined by radar detection, but the radar has misjudgment, and there is a situation that the vehicle collides with an obstacle during the parking process or the parking fails. Or, object detection is implemented through images to determine the parking position, but there are also cases of errors in detection, and the detection of objects through images requires high capabilities of the computing chip, resulting in high cost of the computing chip.

Summary of the invention

The embodiments of the present application provide a vehicle parking method, device, on-board equipment, and storage medium, which can improve the accuracy of obstacle detection, reduce the requirements for computing chip capabilities, and save costs.

In the first aspect, an embodiment of the present application provides a method for parking a vehicle, the method including:

Acquiring an external image of the parking area of the vehicle through a camera device, and extracting at least one continuous area in the external image;

At least one first obstacle area in the area to be parked is detected by a radar device, and all the continuous areas are merged with all the first obstacle areas to determine at least one second obstacle area;

According to all the second obstacle areas, a first parking trajectory route is generated.

In the second aspect, an embodiment of the present application also provides a vehicle parking device, which includes:

A continuous region extraction module, configured to acquire an external image of a parking area of the vehicle through a camera device, and extract at least one continuous region in the external image;

The obstacle area determination module is configured to detect at least one first obstacle area in the area to be parked by a radar device, and merge all the continuous areas with all the first obstacle areas to determine at least one second obstacle area Obstacle area

The first parking trajectory route generating module is configured to generate a first parking trajectory route according to all the second obstacle areas.

In a third aspect, an embodiment of the present application also provides an in-vehicle device, the in-vehicle device including:

At least one processor;

The storage device is set to store at least one program,

When the at least one program is executed by the at least one or more processors, the at least one processor implements the method for parking a vehicle according to any embodiment of the present application.

In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and when the computer program is executed by a processor, the implementation of the A method of parking a vehicle.

Description of the drawings

FIG. 1a is a flowchart of a method for parking a vehicle according to Embodiment 1 of the present application;

FIG. 1b is a schematic diagram of continuous regions in an external image provided by Embodiment 1 of the present application;

FIG. 1c is a schematic diagram of a radar image outside a vehicle provided by Embodiment 1 of the present application;

FIG. 1d is a schematic diagram of an obstacle provided in Embodiment 1 of the present application;

Fig. 2a is a flowchart of a method for parking a vehicle provided in the second embodiment of the present application;

FIG. 2b is a schematic diagram of a candidate obstacle area provided in the second embodiment of the present application;

FIG. 3 is a flowchart of a method for parking a vehicle provided in Embodiment 3 of the present application;

FIG. 4 is a schematic structural diagram of a vehicle parking system provided by Embodiment 4 of the present application;

FIG. 5 is a schematic structural diagram of a vehicle parking device provided by Embodiment 5 of the present application;

FIG. 6 is a schematic structural diagram of a vehicle-mounted device according to Embodiment 6 of the present application.

detailed description

The application will be described in detail below with reference to the drawings and embodiments

Example one

Fig. 1a is a flowchart of a method for parking a vehicle provided in the first embodiment of the present application. This embodiment can be applied to the situation of semi-automatic or fully automatic parking of the vehicle in driving assistance or automatic driving. The method can be used by the vehicle parking device. The device can be implemented by software and/or hardware, and the device can be integrated in a vehicle-mounted device. As shown in FIG. 1a, the method includes steps 110 to 130.

Step 110: Acquire an external image of the area to be parked of the vehicle through the camera device, and extract at least one continuous area in the external image.

Wherein, the camera device is a device configured to obtain an external image of the vehicle, for example, it may be a camera, a video recorder, or a driving recorder. The camera device can be installed around the vehicle. The number of camera devices may be at least one. For example, there are four camera devices, which are located in the front, rear, left, and right directions of the vehicle, and a complete external image of the vehicle can be acquired through the four camera devices. In order to clearly obtain the external image of the vehicle, the camera device may be located at a relatively high position in the vehicle to obtain the external image at a certain overhead angle.

The parking area may be the location where the vehicle is expected to park and the location near the parking, for example, the parking location and the location that needs to pass during parking.

The external image may be an image of an area to be parked outside the vehicle. The external image may be an image acquired through at least one camera. The external image may be a whole image of the exterior of the vehicle obtained by stitching. The stitching can be achieved by calibrating the vehicle. For example, a mark of each corner of the vehicle may exist in the multiple images of the vehicle acquired by the camera device, and the multiple images can be stitched according to the corresponding marks to generate external image.

Before splicing images to generate external images, you can also perform distortion processing on the images. Distortion is a phenomenon of perspective distortion caused by optical imaging, which is very unfavorable to the imaging quality of the image, and will affect the accuracy of judging objects in the external image of the vehicle. Distortion processing can be image correction by methods in some graphics software in related technologies.

The continuous area refers to the area that represents the same object in the external image. For example, it indicates the area of other vehicles outside the vehicle, the barrier area such as the wall area, and the non-obstacle area such as the straw, speed bump, or manhole cover that is spread on the ground outside the vehicle. The continuous area can be regarded as a suspected obstacle area. The method of extracting the continuous area in the external image can be achieved through edge detection or image binarization.

Exemplarily, FIG. 1b is a schematic diagram of continuous regions in an external image provided in Embodiment 1 of the present application. As shown in FIG. 1b, the external image includes a first continuous region 101 and a second continuous region 102. It is assumed that the first continuous area 101 may be an obstacle area such as a fence, and the second continuous area 102 may be a non-obstacle area such as a speed bump. Only continuous regions are extracted through image processing, and the continuous regions are not detected as obstacles or non-obstacles.

In an implementation of the embodiment of the present application, optionally, extracting at least one continuous area in the external image includes: extracting an area with continuous pixel values in the external image as a continuous area.

Among them, in order to accurately extract the continuous area in the external image, the area with continuous pixel values in the external image can be extracted. The extraction method can be image processing methods such as image binarization and edge detection. The area where the pixel values are continuous can be regarded as the continuous area. The technical solutions in the embodiments of this application only determine the pixel value of the external image. The method used is also a basic image processing method such as binarization or edge detection. It does not involve detecting objects in the image to determine whether the object is obstacle. Therefore, the required calculation amount and calculation capacity are small, and the calculation space occupied is small, which can save the calculation cost and the cost of the calculation chip.

Step 120: Obtain at least one first obstacle area in the area to be parked by a radar device, and merge all continuous areas with all the first obstacle areas to determine at least one second obstacle area.

Wherein, the radar device is a device configured to measure the distance between obstacles around the vehicle and the vehicle, for example, it may be composed of at least one ranging radar. Obstacles outside the vehicle and the spatial location of the obstacles can be found by radar. For example, a radar image of the exterior of the vehicle may be acquired, and the radar image includes the first obstacle area detected by the radar.

Exemplarily, FIG. 1c is a schematic diagram of a radar image outside a vehicle provided in Embodiment 1 of the present application. As shown in FIG. 1c, the radar image includes the first obstacle area 103.

The fusion of the continuous area and the first obstacle area may be a process of calibrating the first obstacle area in the continuous area of the external image to determine the second obstacle area. The accuracy of the obstacle determination can be improved, the parking safety can be improved, and the required cost is low.

In an implementation of the embodiment of the present application, optionally, fusing all continuous areas with all first obstacle areas to determine at least one second obstacle area includes: combining all continuous areas with the first obstacle area The continuous areas corresponding to the areas are determined as the second obstacle area.

Exemplarily, as shown in FIGS. 1b and 1c, assuming that the spatial position of the first obstacle area 103 in FIG. 1c corresponds to the first continuous area 101 in FIG. 1b, it can be determined that the first continuous area 101 is the second Obstacle area. It should be noted that when the radar is detecting, for example, when detecting the object represented by the first continuous area 101, due to the limitation of radar technology, it may only be able to detect the part of the first continuous area 101 as shown in Figure 1c. An obstacle area 103, and the entire first continuous area 101 cannot be detected. Through the fusion of Fig. 1b and Fig. 1c, it can be determined that the first continuous area 101 is the second obstacle area, and there is no area corresponding to the second continuous area 102 in Fig. 1b in Fig. 1c, and the second continuous area can be determined 102 is a non-obstacle area. It can solve the problem of inaccurate radar detection of obstacles, improve the accuracy of obstacle determination, and ensure parking safety.

Fig. 1d is a schematic diagram of an obstacle provided by Embodiment 1 of the present application. As shown in Fig. 1d, the second obstacle area 104 is a second obstacle area obtained by fusion of Figs. 1b and 1c. The second obstacle area 104 may be a corresponding closed area formed by the first continuous area 101.

Step 130: Generate a first parking trajectory route according to all the second obstacle areas.

Wherein, the first parking trajectory route may be a trajectory route taken by the vehicle from the current position to the predicted parking position. Among them, the first parking trajectory route will not cross the second obstacle area. That is, the generated first parking trajectory route is a trajectory route for the vehicle to park from the current position to the predicted parking position, avoiding the second obstacle area. There may be at least one first parking trajectory route, and the driver can select a desired parking route to park the vehicle.

In the technical solution of this embodiment, an external image of the area to be parked of the vehicle is acquired through a camera device, and at least one continuous area in the external image is extracted; at least one first obstacle area of the area to be parked is detected by a radar device, It merges all continuous areas with all first obstacle areas to determine at least one second obstacle area; according to all second obstacle areas, the first parking trajectory is generated, which solves the problem of vehicle parking and realizes Improve the accuracy of obstacle detection while reducing the computing power requirements of the computing chip, saving costs, and ensuring the effect of safe parking.

Example two

Fig. 2a is a flowchart of a method for parking a vehicle provided in the second embodiment of the present application. This embodiment is a refinement of the above technical solution, and the technical solution in this embodiment can be combined with each optional solution in at least one of the above embodiments. As shown in Figure 2a, the method includes steps 210 to 290.

Step 210: Acquire an external image of the area to be parked of the vehicle through the camera device, and extract an area with continuous pixel values in the external image as a continuous area.

Step 220: Obtain at least one first obstacle area in the area to be parked by the radar device, and determine the continuous areas corresponding to the first obstacle area in all the continuous areas as the second obstacle area.

Step 230: Generate a first parking trajectory route according to all the second obstacle areas.

Step 240: Obtain at least one candidate obstacle area obtained after removing the second obstacle area from all the continuous areas.

Exemplarily, FIG. 2b is a schematic diagram of a candidate obstacle area provided in the second embodiment of the present application. As shown in FIG. 2b, it is assumed that the candidate obstacle area 201 is an obstacle area such as a fence. By extracting the continuous area of the external image, the area can be extracted. However, due to the shortcomings of radar detection technology, barriers like fences cannot be detected. Therefore, the candidate obstacle area 201 will not be determined as the second obstacle area after the continuous area is merged with the first obstacle area, but may be determined as the candidate obstacle area first.

Exemplarily, as shown in FIG. 1b, according to the fusion of FIG. 1b and FIG. 1c, it can be determined that the first continuous area 101 in FIG. 1b is the second obstacle area, and the second continuous area 102 is not the second obstacle area. Can be determined as a candidate obstacle area.

Step 250: Generate and display a first electronic map matching the area to be parked.

Among them, the second obstacle area, the first parking track route, and the candidate obstacle area are displayed on the first electronic map. In the first electronic map, the representation of the second obstacle area and the candidate obstacle area may be different, for example, the second obstacle area may be represented in red, and the candidate obstacle area may be represented in yellow; or, The second obstacle area may be represented by a solid line, and the candidate obstacle area may be represented by a dashed line; or, a combination of the two methods may be used. The first parking trajectory route can be indicated in gray or green; or, the first parking trajectory route can be indicated by a dashed or solid line with arrows; or, a combination of the two methods is used.

In an implementation manner of the embodiment of the present application, optionally, after generating and displaying the first electronic map matching the area to be parked, the method further includes: obtaining a first parking determination instruction according to the displayed first electronic map , And park according to the first determined parking instruction and the first parking trajectory route.

The first parking determination instruction may be an instruction for the driver to determine to use one of the first parking trajectory routes for parking. For example, when the first electronic map is displayed, a selection button or a selection touch key for at least one parking track route in the first electronic map may be provided. When it is obtained that the driver selects one of the parking trajectory routes, it can be determined as the first definite parking instruction, and parking is performed according to the parking trajectory route corresponding to the first definite parking instruction.

In addition, when displaying the first electronic map, you can also provide a cancel button or cancel touch button, so that when the driver discovers a special situation, he can cancel the currently selected parking track in time, cancel the parking, avoid accidents, and ensure safe parking .

Step 260: In response to the selection of the target candidate obstacle area in the first electronic map, a third obstacle area is determined in the area to be parked.

Among them, the first electronic map also provides a selection key or a selection touch key for the candidate obstacle area. The driver can select the candidate obstacle area in the first electronic map as the target candidate obstacle area. The target candidate obstacle selected by the driver can be determined as the third obstacle area. For example, the driver may determine that the candidate obstacle area 201 in FIG. 2b is a fence, and may be selected as the target candidate obstacle area. The driver may determine that the second continuous area 102 in FIG. 1b is a speed bump, and may not be selected as the target candidate obstacle area. Therefore, the candidate obstacle area 201 in FIG. 2b can be determined as the third obstacle area; the second continuous area 102 in FIG. 1b is not the third obstacle area. It can avoid the problem of radar missed detection, improve the accuracy and comprehensiveness of obstacle determination, and ensure parking safety.

Step 270: Generate a second parking trajectory route according to the second obstacle area and the third obstacle area.

Wherein, the second parking trajectory route may be a trajectory route taken by the vehicle from the current position to the predicted parking position. Among them, the second parking trajectory route will not cross the second obstacle area and the third obstacle area. That is, the generated second parking trajectory route is a trajectory route for the vehicle to park from the current position to the predicted parking position, avoiding the second obstacle area and the third obstacle area. There may be at least one second parking trajectory route, and the driver can select a desired parking route to park the vehicle.

Step 280: Generate and display a second electronic map matching the area to be parked, and display the second obstacle area, the third obstacle area, and the second parking track route on the second electronic map.

Wherein, the display modes of the second obstacle area and the third obstacle area may be the same, for example, both are represented by red, or both are represented by solid lines, or the two methods are combined for representation. The second parking trajectory route can be represented in green, or represented by a solid line with an arrow or a dashed line, or represented by a combination of the two methods, and so on.

In an implementation of the embodiment of the present application, optionally, after generating and displaying a second electronic map matching the area to be parked, the method further includes: obtaining a second parking determination instruction according to the displayed second electronic map , And park according to the second determined parking instruction and the second parking trajectory route.

Wherein, the second parking determination instruction may be an instruction for the driver to determine to use one of the second parking trajectory routes for parking. For example, when the second electronic map is displayed, a selection button or a selection touch key for at least one parking track route in the second electronic map may be provided. When it is acquired that the driver selects one of the parking trajectory routes, it can be determined as the second definite parking instruction, and parking is performed according to the parking trajectory route corresponding to the second definite parking instruction.

Step 290: Store the second electronic map according to the real-time positioning result of the vehicle.

Among them, the second electronic map and the positioning result of the vehicle can be stored. When the vehicle is at the same or similar positioning position next time, the second electronic map can be directly displayed to increase the parking speed. In addition, if the driver does not select the target candidate obstacle area in the first electronic map, the first electronic map and the positioning result of the vehicle can also be stored. When the vehicle is located at the same or similar positioning position next time, the first electronic map can be directly displayed. An electronic map to increase the speed of parking.

In the technical solution of this embodiment, an external image of the area to be parked of the vehicle is acquired through a camera device, and an area with continuous pixel values in the external image is extracted as a continuous area; at least one first obstacle in the area to be parked is detected by a radar device In all the continuous areas, the continuous area corresponding to the first obstacle area is determined as the second obstacle area; according to all the second obstacle areas, the first parking trajectory route is generated; in all the continuous areas, Obtain at least one candidate obstacle area obtained after removing the second obstacle area; generate and display a first electronic map matching the area to be parked; in response to the selection of the target candidate obstacle area in the first electronic map, Determine the third obstacle area in the area to be parked; generate the second parking trajectory route according to the second obstacle area and the third obstacle area; generate and display a second electronic map matching the area to be parked, in The second electronic map displays the second obstacle area, the third obstacle area and the second parking track route; according to the real-time positioning results of the vehicle, the second electronic map is stored, which solves the problem of vehicle parking and realizes Improve the accuracy of obstacle detection while reducing the computing power requirements of the computing chip, saving costs, avoiding radar detection errors or missing detection, ensuring safe parking, and improving parking speed.

Example three

Fig. 3 is a flowchart of a method for parking a vehicle provided in the third embodiment of the present application. This embodiment is a refinement of the above technical solution, and the technical solution in this embodiment can be combined with each optional solution in at least one of the above embodiments. As shown in FIG. 3, the method includes steps 310 to 470.

Step 310: Obtain the real-time positioning result of the vehicle, and determine whether the target electronic map matching the current parking area is stored according to the real-time positioning result; respond to the judgment that the target electronic map matching the current parking area is stored As a result, step 320 is executed; in response to the judgment result that the target electronic map matching the current parking area is not stored, step 340 is executed.

Wherein, the target electronic map may be an electronic map corresponding to the positioning result of the vehicle, for example, it may be a pre-stored first electronic map or a second electronic map. The target electronic map can include obstacle areas and parking trajectory routes. There may be at least one parking track route. Optionally, the parking trajectory route may be the parking trajectory route adopted last time when the vehicle was at the current positioning position, which can increase the parking speed. Optionally, the target electronic map may provide buttons or touch buttons for displaying all the parking trajectory routes, so that the driver can understand all the optional parking methods.

Step 320: Display the target electronic map, and the target electronic map includes the target parking track route.

The target parking trajectory route may be one selected by the driver according to multiple parking trajectory routes, or the parking trajectory route adopted last time when the vehicle was at the current positioning position. The target electronic map can be displayed through the human-computer interaction interface in the vehicle.

Step 330: Obtain a third determined parking instruction according to the displayed target electronic map, and perform parking according to the third determined parking instruction and the target parking trajectory route, and the end.

Wherein, the third parking determination instruction may be an instruction for the driver to determine to use one of the target parking trajectory routes for parking. For example, when displaying the target electronic map, a selection button or a selection touch key for at least one parking track route in the target electronic map may be provided. When it is acquired that the driver selects one of the parking trajectory routes, it can be determined as the third definite parking instruction, and parking is performed according to the parking trajectory route corresponding to the third definite parking instruction.

Step 340: Acquire an external image of the area to be parked of the vehicle through the camera device, and extract at least one continuous area in the external image.

Step 350: Obtain at least one first obstacle area in the area to be parked by a radar device, and merge all continuous areas with all first obstacle areas to determine at least one second obstacle area.

Step 360: Generate a first parking trajectory route according to all the second obstacle areas.

Step 370: Obtain at least one candidate obstacle area obtained after removing the second obstacle area from all the continuous areas.

Step 380: Generate and display a first electronic map matching the area to be parked, where the first electronic map displays the second obstacle area, the first parking track route, and the candidate obstacle area.

Step 390: Obtain a first definite parking instruction or a selection instruction of the target candidate obstacle area for the first electronic map; if the first definite parking instruction is acquired, go to step 410; if the target candidate obstacle area is acquired Select the instruction and go to step 430.

Step 410: Carry out parking according to the first determined parking instruction and the first parking trajectory route.

Step 420: Store the first electronic map according to the real-time positioning result of the vehicle, and end.

Step 430: In response to the selection of the target candidate obstacle area in the first electronic map, a third obstacle area is determined in the parking area.

Step 440: Generate a second parking trajectory route according to the second obstacle area and the third obstacle area.

Step 450: Generate and display a second electronic map matching the area to be parked, and display the second obstacle area, the third obstacle area, and the second parking track route on the second electronic map.

Step 460: Obtain a second determined parking instruction according to the displayed second electronic map, and perform parking according to the second determined parking instruction and the second parking trajectory route.

Step 470: Store the second electronic map according to the real-time positioning result of the vehicle.

The technical solution of this embodiment first obtains the real-time positioning result of the vehicle before parking, and judges whether the target electronic map matching the current parking area is stored according to the real-time positioning result; According to the judgment result of the target electronic map matching the parking area, the target electronic map is displayed, and the target electronic map includes the target parking track route; according to the displayed target electronic map, the third confirmation parking instruction is obtained, and according to the third confirmation The parking instruction and the target parking trajectory route are used for parking, which solves the problem of vehicle parking, and realizes the effect of reducing the generation process of the parking trajectory route and increasing the parking speed when the same or similar positioning results are achieved.

Embodiment four

FIG. 4 is a schematic structural diagram of a vehicle parking system provided by Embodiment 4 of the present application. As shown in FIG. 4, the system includes: a camera device 510, an image processing device 520, a radar detection device 530, a display and operation device 540, The map generation device 550, the parking control device 560, and the vehicle chassis device 570.

Among them, the camera device 510 is connected to the image processing device 520; the image processing device 520 and the radar detection device 530 are both connected to the map generating device 550; the image processing device 520 and the radar detection device 530 are both connected to the display and operation device 540; display and operation The device 540 is connected to the map generating device 550; the map generating device 550 is connected to the parking control device 560; the parking control device 560 is connected to the vehicle chassis device 570.

The camera device 510 is composed of a number of cameras, arranged around the vehicle, and configured to capture images around the vehicle in real time. The image processing device 520 is configured to perform distortion processing and splicing on the image, and extract continuous regions in the spliced image. The image processing device 520 is further configured to send an image including a continuous area to the display and operation device 540 and the map generation device 550. The radar detection device 530 is composed of several ranging radars, and is configured to measure the distance between obstacles around the vehicle and the vehicle, and send the radar ranging information to the display and operation device 540 and the map generation device 550. The map generating device 550 is configured to perform fusion judgment based on the image including the continuous area and the radar ranging information, generate the first version of the electronic map, and send it to the display and operation device 540. Among them, the first version of the electronic map includes obstacles and parking track routes. The parking trajectory route is planned according to the obstacle area. The display and operation device 540 is configured to display the image of the continuous area, the radar ranging information and the first version of the electronic map, obtain the operation instructions of the driver, and send the operation instructions to the map generating device 550.

The map generating device 550 is further configured to generate a final electronic map according to the driver's operation instruction, and send the final electronic map to the parking control device 560. For example, based on the driver's marking of impassable areas (obstacle areas) in the first version of the electronic map and obstacles in the first version of the electronic map, the final version of the electronic map is generated. Among them, the final electronic map includes obstacle areas, impassable areas, and parking track routes. The parking track route is planned according to the obstacle area and the impassable area. The map generating device 550 is also configured to store the final electronic map. The parking control device 560 is configured to control the vehicle chassis device 570 to park according to the final electronic map.

The technical solution of this embodiment, through the camera device, the image processing device, the radar detection device, the display and operation device, the map generation device, the parking control device, and the vehicle chassis device, can be based on the continuous area in the image and the radar ranging information Generate the first version of the electronic map to avoid limited radar detection; generate the final version of the electronic map according to the first version of the electronic map and the impassable areas marked by the driver to avoid the situation of radar detection missed; realize the parking of the vehicle according to the final version of the electronic map , Which can improve the accuracy of obstacle detection while reducing the computing power requirements of the computing chip, saving costs, and ensuring safe parking.

Embodiment five

FIG. 5 is a schematic structural diagram of a vehicle parking device provided in Embodiment 5 of the present application. With reference to Fig. 5, the device includes: a continuous area extraction module 610, an obstacle area determination module 620, and a first parking trajectory route generation module 630.

The continuous region extraction module 610 is configured to acquire an external image of the area to be parked of the vehicle through the camera device, and extract at least one continuous region in the external image;

The obstacle area determination module 620 is configured to detect at least one first obstacle area in the area to be parked by a radar device, and merge all continuous areas with all the first obstacle areas to determine at least one second obstacle area ；

The first parking trajectory route generating module 630 is configured to generate the first parking trajectory route according to all the second obstacle areas.

Optionally, the continuous region extraction module 610 includes:

The continuous area extracting unit is configured to extract the area with continuous pixel values in the external image as the continuous area.

Optionally, the obstacle area determination module 620 includes:

The obstacle area determining unit is configured to determine the continuous areas respectively corresponding to the first obstacle area in all the continuous areas as the second obstacle area.

Optionally, the device further includes:

The candidate obstacle area acquisition module is set to obtain at least one candidate obstacle obtained after removing the second obstacle area in all continuous areas after generating the first parking trajectory route based on all the second obstacle areas area;

The first electronic map generation module is configured to generate and display a first electronic map matching the area to be parked, wherein the first electronic map displays the second obstacle area, the first parking track route, and the candidate obstacle area ；

The third obstacle area determination module is configured to determine the third obstacle area in the parking area in response to the selection of the target candidate obstacle area in the first electronic map;

The second parking trajectory route generation module is configured to generate a second parking trajectory route according to the second obstacle area and the third obstacle area.

Optionally, the device further includes:

The second electronic map generation module is configured to generate and display a second electronic map matching the area to be parked after generating a second parking trajectory route according to the second obstacle area and the third obstacle area. The second obstacle area, the third obstacle area and the second parking track route are displayed on the electronic map;

The second electronic map storage module is configured to store the second electronic map according to the real-time positioning result of the vehicle.

Optionally, the device further includes:

The parking module is configured to, after generating and displaying a first electronic map matching the area to be parked, obtain a first parking instruction according to the displayed first electronic map, and obtain a first parking instruction according to the first parking instruction and the first parking instruction. Parking on the parking track route; or,

The parking module is configured to, after generating and displaying a second electronic map matching the area to be parked, obtain a second parking instruction according to the displayed second electronic map, and obtain a second parking instruction according to the second parking instruction and the second parking instruction. The parking track route is used for parking.

Optionally, the device further includes:

The target electronic map acquisition module is configured to acquire the real-time positioning result of the vehicle before acquiring the external image of the parking area of the vehicle through the camera device, and determine whether to store the target electronic matching the current parking area according to the real-time positioning result map;

The target electronic map display module is configured to display the target electronic map in response to the stored judgment result of the target electronic map matching the current parking area, and the target electronic map includes the target parking track route;

The parking module is further configured to obtain a third determined parking instruction according to the displayed target electronic map, and perform parking according to the third determined parking instruction and the target parking trajectory route.

The vehicle parking device provided by the embodiment of the present application can execute the vehicle parking method provided by any embodiment of the present application, and is equipped with functional modules corresponding to the execution method.

Example Six

FIG. 6 is a schematic structural diagram of a vehicle-mounted device provided in Embodiment 6 of the present application. As shown in FIG. 6, the device includes:

At least one processor 710, and one processor 710 is taken as an example in FIG. 6;

Memory 720;

The device may further include: an input device 730 and an output device 740.

The processor 710, the memory 720, the input device 730, and the output device 740 in the device may be connected by a bus or other methods. In FIG. 6, the connection by a bus is taken as an example.

The memory 720, as a non-transitory computer-readable storage medium, can be configured to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to a vehicle parking method in the embodiment of the present application (for example, The continuous area extraction module 610 shown in FIG. 5, the obstacle area determination module 620 and the first parking trajectory route generation module 630). The processor 710 executes various functional applications and data processing of the computer equipment by running the software programs, instructions, and modules stored in the memory 720, that is, to implement a vehicle parking method in the foregoing method embodiment, namely:

The memory 720 may include a program storage area and a data storage area. The program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of a computer device, and the like. In addition, the memory 720 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 720 may optionally include memories remotely provided with respect to the processor 710, and these remote memories may be connected to the terminal device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 730 may be configured to receive input numeric or character information, and generate key signal input related to user settings and function control of the computer equipment. The output device 740 may include a display device such as a display screen.

Example Seven

The seventh embodiment of the present application provides a computer-readable storage medium having a computer program stored on the computer-readable storage medium, and when the program is executed by a processor, a method for parking a vehicle as provided in the embodiment of the present application is implemented:

Any combination of at least one computer-readable medium can be used. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media (non-exhaustive list) include: electrical connections with at least one wire, portable computer disks, hard disks, random access memory (RAM), read-only memory (Read Only Memory, ROM), Erasable Programmable Read Only Memory (EPROM or flash memory), optical fiber, Compact Disc-Read Only Memory (CD-ROM), optical Storage device, magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and computer-readable program code is carried therein. This propagated data signal can take many forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable medium may send, propagate or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .

The program code contained on the computer-readable medium can be transmitted by any suitable medium, including, but not limited to, wireless, wire, optical cable, radio frequency (RF), etc., or any suitable combination of the foregoing.

The computer program code used to perform the operations of this application can be written in at least one programming language or a combination thereof. The programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages. Programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network-including Local Area Network (LAN) or Wide Area Network (WAN)-or it can be connected to an external computer ( For example, use an Internet service provider to connect via the Internet).

Claims

A method for parking a vehicle, including:

Acquiring an external image of the parking area of the vehicle through a camera device, and extracting at least one continuous area in the external image;

At least one first obstacle area in the area to be parked is detected by a radar device, and all the continuous areas are merged with all the first obstacle areas to determine at least one second obstacle area;

According to all the second obstacle areas, a first parking trajectory route is generated.
The method according to claim 1, wherein extracting at least one continuous region in the external image comprises:

Extracting an area with continuous pixel values in the external image as the continuous area.
The method according to claim 1, wherein fusing all the continuous areas with all the first obstacle areas to determine at least one second obstacle area comprises:

The continuous areas corresponding to the first obstacle area in all the continuous areas are determined as the second obstacle area.
The method according to claim 1, after generating a first parking trajectory route based on all the second obstacle areas, further comprising:

Obtaining at least one candidate obstacle area obtained after removing the second obstacle area in all the continuous areas;

Generate and display a first electronic map matching the parking area, wherein the second obstacle area, the first parking track route, and the candidate obstacle are displayed in the first electronic map area;

In response to the selection of the target candidate obstacle area in the first electronic map, determining a third obstacle area in the parking area;

According to the second obstacle area and the third obstacle area, a second parking trajectory route is generated.
The method according to claim 4, after generating a second parking trajectory route according to the second obstacle area and the third obstacle area, further comprising:

Generate and display a second electronic map matching the parking area, and display the second obstacle area, the third obstacle area, and the second parking track route on the second electronic map ；

According to the real-time positioning result of the vehicle, the second electronic map is stored.
According to the method of claim 5,

After generating and displaying the first electronic map matching the parking area, the method further includes:

Acquire a first definite parking instruction according to the displayed first electronic map, and perform parking according to the first definite parking instruction and the first parking trajectory route; or,

After generating and displaying the second electronic map matching the parking area, the method further includes:

Acquire a second definite parking instruction according to the displayed second electronic map, and perform parking according to the second definite parking instruction and the second parking trajectory route.
The method according to claim 1, before acquiring the external image of the parking area of the vehicle through the camera device, further comprising:

Acquiring a real-time positioning result of the vehicle, and judging whether a target electronic map matching the current parking area is stored according to the real-time positioning result;

In response to storing the judgment result of the target electronic map matching the current parking area, displaying the target electronic map, the target electronic map including the target parking track route;

Obtain a third determined parking instruction according to the displayed target electronic map, and perform parking according to the third determined parking instruction and the target parking trajectory route.
A vehicle parking device, including:

A continuous region extraction module, configured to acquire an external image of a parking area of the vehicle through a camera device, and extract at least one continuous region in the external image;

The obstacle area determination module is configured to detect at least one first obstacle area in the area to be parked by a radar device, and merge all the continuous areas with all the first obstacle areas to determine at least one second obstacle area Obstacle area

The first parking trajectory route generating module is configured to generate a first parking trajectory route according to all the second obstacle areas.
An in-vehicle device, including:

At least one processor;

The storage device is set to store at least one program,

When the at least one program is executed by the at least one processor, the at least one processor implements the method for parking a vehicle according to any one of claims 1-7.
A computer-readable storage medium having a computer program stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method for parking a vehicle according to any one of claims 1-7 is realized.