Parking space identification method and device for automatic parking, vehicle and readable storage medium
By using vehicle sensors to identify parking lines and obstacles in parking areas and simulating longitudinal areas, the problem of automatic parking in areas lacking parking line corners is solved, thus expanding the application scope of automatic parking.
Patent Information
- Application Number
- CN202511338311.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-18
- Publication Date
- 2026-01-02
AI Technical Summary
Existing automatic parking systems cannot recognize parking areas with missing or unclear parking space line corners, thus preventing them from achieving automatic parking.
By measuring environmental data of the parking area using target vehicle sensors, the first and second parking space lines are identified. Combined with the starting line of the longitudinal area range simulated by obstacles, the lateral and longitudinal area ranges are determined, and new parking spaces are identified and planned.
It expands the application scenarios of automatic parking, enabling automatic parking in parking areas where parking lines are lacking or corners cannot be identified, thus improving the adaptability of the automatic parking system.
Smart Images
Figure CN121246782A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of automatic parking technology, and in particular to an automatic parking space identification method, device, vehicle, and readable storage medium. Background Technology
[0002] An automatic parking system is a parking assistance control system that enables a car to automatically park in a parking space using the correct driving path. During the parking process, the automatic parking system calculates the parking trajectory and performs automatic control based on environmental measurement data measured in real time by various sensors installed on the vehicle, thereby completing the correct automatic parking.
[0003] When a vehicle uses an automatic parking system to search for a parking space, the parking space must have corner points. These corner points are formed at the intersection of the lines of each pair of parking spaces, and each parking space must have at least two corner points. However, for parking areas defined by only two parking lines, without a dividing line to distinguish between two adjacent parking spaces, the corresponding parking lines do not form corner points. In cases where corner points are missing, or the dividing line is unclear and makes the corner points unrecognizable, automatic parking space identification cannot be achieved and used for automatic parking. Summary of the Invention
[0004] The purpose of this application is to provide an automatic parking space identification method, device, vehicle, and readable storage medium to solve the problem of automatic parking in parking areas where there are no parking space corner points or the parking space corner points cannot be identified.
[0005] To solve the above-mentioned technical problems, this specification is implemented as follows: In a first aspect, a parking space recognition method for automatic parking is provided, applicable to parking areas where there are no parking space line corner points or the parking space line corner points cannot be recognized, the method comprising: Based on environmental measurement data obtained from the parking area measured by the first sensor on the target vehicle, the first parking space line and the second parking space line of the parking area are determined. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area. The lateral area of the target parking space is determined based on the first parking space line and the second parking space line. The lateral area refers to the area of the target parking space that is perpendicular to the lane line. Based on the target obstacles in the parking area measured by the second sensor on the target vehicle, a starting line for the longitudinal area range of the target parking space is simulated, the longitudinal area range referring to the range of the target parking space that intersects with the lane lines; The range of the target parking space is determined by the lateral area and the starting line for automatic parking.
[0006] Optionally, the first sensor includes a camera device and a ranging device, and the environmental measurement data includes acquired images and obstacle distances; Determining the first and second parking space lines of the parking area based on environmental measurement data obtained from the first sensor on the target vehicle includes: Acquire images of the parking area obtained by the camera device on the target vehicle; The parking space line closest to the target vehicle in the parking area identified in the acquired image is determined as the first parking space line; The distance to obstacles in the parking area is obtained by measuring the distance from the ranging device on the target vehicle. Based on the distance to the obstacle, if the corresponding obstacle is identified as a curb or wall near the curb line of the parking area, then the line corresponding to the obstacle is simulated as the second parking space line.
[0007] Optionally, the first sensor includes a camera device, and the environmental measurement data includes acquired images; Determining the first and second parking space lines of the parking area based on environmental measurement data obtained from the first sensor on the target vehicle includes: Acquire images of the parking area obtained by the camera device on the target vehicle; Based on the acquired images, identify parking lines near the target vehicle and obstacles near the curb in the parking area; If the obstacle is identified as a curb or a wall, the line corresponding to the obstacle is simulated as the second parking space line.
[0008] Optionally, based on target obstacles in the parking area measured by a second sensor on the target vehicle, a starting line for the longitudinal area of the target parking space is simulated, including: The distance to or image of the target obstacle in the parking area is obtained by the second sensor on the target vehicle; Based on the distance to the target obstacle or the acquired image, if the target obstacle is identified as being within the horizontal region, then the outer contour line of the target obstacle is simulated; Determine a target outer contour line whose angle with the lane line of the parking area is within a preset angle range; Based on the target outer contour line, a starting line is simulated for the longitudinal area range of the target parking space.
[0009] Optionally, the target obstacle is a vehicle; Determining a target outer contour line whose angle of intersection with the lane line is within a preset angle range includes: If the front of the vehicle is parallel to the lane line, then the target outer contour line is determined to include at least one outer contour line of the vehicle that intersects the lane line at an angle of 90 degrees. If the vehicle's front orientation has a preset angle with the lane line, then the target outer contour line is determined to be at least one of the vehicle's outer contour lines whose angle with the lane line is the preset angle.
[0010] Optionally, the range of the target parking space is determined by the lateral area and the starting line for automatic parking, including: The target area formed by the intersection of the starting line with the first parking space line and the second parking space line of the horizontal area is defined as the vertical area, and the target area is far away from the target obstacle. Based on the distance between the first parking space line and the second parking space line in the longitudinal area, the parking method of the target vehicle is determined. The parking method includes parking with the front of the vehicle facing parallel to the lane line, or parking with the front of the vehicle facing at an angle to the lane line. Based on the parking method, determine whether the longitudinal area range meets the preset parking space size corresponding to the parking method; If the preset parking space size is met, the range of the target parking space is determined within the longitudinal area for automatic parking.
[0011] Optionally, after determining the range of the target parking space, the method further includes: If the target obstacle is identified as a vehicle, control commands for automatic parking of the target vehicle are transmitted to the vehicle's electronic control unit.
[0012] Secondly, an automatic parking space recognition device is provided, applicable to parking areas where there are no parking space line corner points or the parking space line corner points cannot be recognized, the device comprising: The first determining module determines the first parking space line and the second parking space line of the parking area based on environmental measurement data obtained by the first sensor on the target vehicle measuring the parking area. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area. The second determining module determines the lateral area range of the target parking space based on the first parking space line and the second parking space line. The lateral area range refers to the range of the lane lines perpendicular to the parking area in the target parking space. The simulation module, based on the target obstacles in the parking area measured by the second sensor on the target vehicle, simulates the starting line of the longitudinal area range for the target parking space, wherein the longitudinal area range refers to the range in the target parking space that intersects with the lane lines; The third determining module determines the range of the target parking space by using the horizontal area range and the starting line to perform automatic parking.
[0013] Thirdly, a vehicle is provided, including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.
[0014] Fourthly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.
[0015] For parking areas lacking parking space corner points or where these corner points are unidentifiable, parking space lines are simulated based on target obstacles within the parking area. This, combined with other known parking space lines, yields the range of parking spaces within the parking area suitable for automated parking. Specifically, firstly, based on environmental measurement data obtained from a first sensor on the target vehicle, a first parking space line and a second parking space line are determined within the parking area. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line. Then, based on the first and second parking space lines, the lateral area of the target parking space is determined. This lateral area refers to the portion of the target parking space perpendicular to the lane line. Next, based on target obstacles measured by a second sensor on the target vehicle, a parking space is simulated for the target parking space. The starting line of the longitudinal area of the target parking space is defined, where the longitudinal area refers to the area intersecting the lane lines within the target parking space. Finally, the range of the target parking space is determined by the lateral area and the starting line for automatic parking. This method identifies and plans new parking spaces by integrating three elements: the first parking space line, the second parking space line, and the target obstacle. The identification of new parking spaces does not depend on the corner points of the parking space lines, which solves the problem of not being able to identify parking spaces in parking areas where there are no corner points of the parking space lines or the corner points of the parking space lines cannot be identified, thus expanding the application scenarios and scope of automatic parking. Attached Figure Description
[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of parking spaces that can be identified by existing automatic parking systems.
[0017] Figure 2 This is a diagram illustrating the different types of parking spaces that can be identified by existing automatic parking systems.
[0018] Figure 3 This is a schematic diagram of a parking area where existing automatic parking systems cannot identify parking spaces.
[0019] Figure 4 This is a flowchart illustrating the automatic parking space recognition method according to an embodiment of this application.
[0020] Figure 5 This is a schematic diagram of the vehicle-mounted sensors in the automatic parking space recognition method according to an embodiment of this application.
[0021] Figure 6 This is a schematic diagram illustrating an application scenario of an automatic parking space recognition method according to an embodiment of this application.
[0022] Figure 7 This is a schematic diagram illustrating an application scenario of an automatic parking space recognition method according to another embodiment of this application.
[0023] Figure 8 This is a schematic diagram illustrating an application scenario of the automatic parking space recognition method according to other embodiments of this application.
[0024] Figure 9 This is a structural block diagram of an automatic parking space recognition device according to an embodiment of this application.
[0025] Figure 10 This is a structural block diagram of the vehicle according to an embodiment of this application. Detailed Implementation
[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. The drawing numbers in this application are only used to distinguish the various steps in the solution and are not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.
[0027] An automatic parking system is a parking assistance control system that enables a car to automatically park in a parking space using the correct driving path. During the parking process, the automatic parking system calculates the parking trajectory in real time based on environmental measurement data measured by various sensors installed on the vehicle, and automatically controls the steering system, braking system, engine system, and transmission system to achieve automatic control of steering, speed, and gear selection, thereby completing the correct automatic parking.
[0028] When a vehicle uses an automatic parking system to search for a parking space, the parking space must have parking space corner points. Typically, a single parking space corresponds to a quadrilateral area, and parking spaces are separated by dividing lines. The intersection of two parking space lines forms a parking space corner point, and a single parking space has at least two parking space corner points.
[0029] Examples of parking space line corner points are as follows Figure 1 As shown, a single parking space 10 corresponds to a quadrilateral area, including the intersection of adjacent parking lines forming four parking line corner points, namely parking line corner point A, parking line corner point B, parking line corner point C, and parking line corner point D. Adjacent parking spaces are separated by a dividing line 12.
[0030] Examples of other types of parking spaces and corresponding parking space line corners can be found in [reference]. Figure 2 Among them, there are 20 solid-line enclosed parking spaces, 30 T-shaped parking spaces, and 40 straight-line open parking spaces.
[0031] However, for parking areas defined by only two parallel parking lines, such as Figure 3 Parking area 50, defined by parking lines 14 and 16, does not provide a dividing line to distinguish between two adjacent parking spaces, thus the corresponding parking lines do not form parking line corners. Similarly, if the parking area has dividing lines to distinguish between two adjacent parking spaces, but the dividing lines are not clear enough, the parking line corners will also be unrecognizable. Therefore, parking space recognition for automatic parking cannot be achieved and used for automatic vehicle parking.
[0032] To address the problems existing in the prior art, this application provides an automatic parking space recognition scheme. For parking areas without parking space line corners or where parking space line corners cannot be identified, parking space lines are simulated based on target obstacles in the parking area. This is combined with other known parking space lines to obtain the range of parking spaces within the parking area suitable for automatic parking. Specifically, firstly, based on environmental measurement data obtained from a first sensor on the target vehicle, a first parking space line and a second parking space line are determined in the parking area. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area. Then, based on the first and second parking space lines, the lateral area range of the target parking space is determined. The lateral area range refers to the area of the target parking space perpendicular to the lane line. Next, based on target obstacles in the parking area measured by a second sensor on the target vehicle, a parking space is simulated for automatic parking. The starting line of the longitudinal area of the target parking space is defined, where the longitudinal area refers to the area intersecting the lane lines within the target parking space. Finally, the range of the target parking space is determined by the lateral area and the starting line for automatic parking. This method identifies and plans new parking spaces by integrating three elements: the first parking space line, the second parking space line, and the target obstacle. The identification of new parking spaces does not depend on the corner points of the parking space lines, which solves the problem of not being able to identify parking spaces in parking areas where there are no corner points of the parking space lines or the corner points of the parking space lines cannot be identified, thus expanding the application scenarios and scope of automatic parking.
[0033] Specifically, embodiments of the present application include an automatic parking space recognition method, device, vehicle, and readable storage medium. The embodiments are described in detail below.
[0034] One embodiment of this application provides a parking space recognition method for automatic parking, applicable to parking areas where there are no parking space line corner points or the parking space line corner points cannot be recognized. The automatic parking space recognition method can be executed by an automatic parking system, specifically by the electronic control unit (ECU) of the automatic parking system.
[0035] Figure 4 This is a flowchart illustrating the vehicle driving road condition recognition method of this embodiment, as shown below. Figure 4 As shown, it includes the following steps 102 to 108.
[0036] Step 102: Based on the environmental measurement data obtained by the first sensor on the target vehicle measuring the parking area, determine the first parking space line and the second parking space line of the parking area. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area.
[0037] In this embodiment of the application, the parking area refers to a parking area without parking space line corner points or where the parking space line corner points cannot be identified, for example... Figure 3 The parking area shown is 50. The target vehicle is a vehicle that passes through the parking area and needs to perform automatic parking within that area using the automatic parking system, for example... Figure 3 The target vehicle is 100.
[0038] The target vehicle is equipped with various types of sensors to measure various data during the driving process. For example, if the user confirms that the automatic parking function is activated when the target vehicle passes through the target parking area, it means that the user needs to perform automatic parking on the target vehicle in that parking area.
[0039] In step 102, the first sensor on the target vehicle begins to measure the parking area, obtains the corresponding environmental measurement data, and uses it to determine the first parking space line and the second parking space line of the parking area.
[0040] Here, the first parking space line is closer to the lane line of the parking area, i.e., closer to the target vehicle; the second parking space line is closer to the curb line of the parking area, i.e., farther from the target vehicle. In other words, the parking area is located on one side of the target vehicle. For example, as... Figure 3 As shown, the target vehicle 100 is located on one side of the parking area 50.
[0041] The curb line refers to the line formed by the curb. When the curb line is a wall relative to the lane line, the curb line refers to the wall. The first parking space line is close to the lane line of the parking area. This can indicate that there is a certain distance between the first parking space line and the lane line, or it can indicate that the first parking space line and the lane line coincide.
[0042] Similarly, the second parking space line being close to the curb line of the parking area can indicate that there is a certain distance between the second parking space line and the curb line, or it can indicate that the second parking space line coincides with the curb line. For example, only one first parking space line is drawn in the parking area, and the second parking space line coincides with the curb or wall and is used as the second parking space line of the parking area. The first parking space line and the corresponding curb or wall constitute the parking area.
[0043] For the parking area in the above application scenario, it is first necessary to use the sensors on the target vehicle to measure the corresponding environmental measurement data, and use it to determine the first parking space line and the second parking space line of the parking area.
[0044] Optionally, in step 102, the first sensor includes a camera device and a ranging device, and the environmental measurement data includes acquired images and obstacle distances. Determining the first and second parking space lines of the parking area based on the environmental measurement data obtained by the first sensor on the target vehicle includes: acquiring an image of the parking area obtained by the camera device on the target vehicle; identifying the parking space line in the parking area near the target vehicle identified in the acquired image as the first parking space line; acquiring the obstacle distances obtained by the ranging device on the target vehicle from the parking area; and, based on the obstacle distances, if the identified obstacle is a curb or wall near the curb line of the parking area, simulating the line corresponding to the obstacle as the second parking space line.
[0045] Examples of sensor setups on the target vehicle include Figure 5 As shown, in Figure 5 In the example, when the automatic parking function is turned on or enabled, the environment of the parking area can be measured by multiple camera devices 120 (e.g., fisheye cameras) and multiple ranging devices 140 (e.g., ultrasonic radar, millimeter-wave radar or other devices that can identify obstacles based on distance) installed on the vehicle, so as to identify the first parking space line and the second parking space line of the parking area.
[0046] In this embodiment, the first sensor used to identify the first and second parking space lines in the parking area includes a camera device and a ranging device. The camera device measures the parking area to obtain a captured image. Based on the captured image, visual judgment can be performed to identify the parking space line closest to the target vehicle in the captured image, i.e., the first parking space line. Here, the parking space line closest to the target vehicle can be a lane line in a roadside parking area or a parking space line marked in a regular parking lot. The ranging device measures the distance to obstacles in the parking area to obtain the distance. Based on the obstacle distance detected by ultrasonic waves, it can be identified whether the corresponding obstacle is a wall or curb corresponding to the curb line close to the parking area, and then the line corresponding to the obstacle is simulated as the second parking space line.
[0047] Based on another solution provided by the above embodiments, optionally, in step 102 above, the first sensor includes a camera device, and the environmental measurement data includes acquired images; determining the first parking space line and the second parking space line of the parking area based on the environmental measurement data obtained by the first sensor on the target vehicle measuring the parking area includes: acquiring the acquired image obtained by the camera device on the target vehicle measuring the parking area; based on the acquired image, identifying the parking space line near the target vehicle and the obstacle near the curb line of the parking area; if the obstacle is identified as a curb or a wall, then the line corresponding to the obstacle is simulated as the second parking space line.
[0048] In this embodiment, the first sensor used to identify the first and second parking space lines in the parking area includes a camera device. The camera device measures the parking area to obtain a captured image. Based on the captured image, visual judgment can be performed to identify the parking space lines near the target vehicle and obstacles near the parking area. The parking space line near the target vehicle is determined as the first parking space line. This parking space line can be a lane line in a roadside parking area or a parking space line marked in a regular parking lot. If the obstacle near the parking area is a wall or curb, the line corresponding to the obstacle is simulated as the second parking space line.
[0049] Step 104: Determine the lateral area of the target parking space based on the first parking space line and the second parking space line. The lateral area refers to the area of the target parking space that is perpendicular to the lane line.
[0050] As mentioned above, the first parking space line is either the lane line or the parking space line within the parking area, while the second parking space line is located near the curb of the parking area. Therefore, it can be seen that the first and second parking space lines tend to be parallel, and the area defined between the two lines is the lateral area of the target parking space. Here, the target parking space refers to the parking space to be identified for automatic parking of the target vehicle, and the lateral area refers to the area within the target parking space perpendicular to the lane line. Combined with... Figure 6 (a) to (b) show the lateral area, which corresponds to parking area 50. Within the lateral area, there are no dividing lines between adjacent parking spaces.
[0051] Step 106: Based on the target obstacles in the parking area measured by the second sensor on the target vehicle, simulate the starting line of the longitudinal area range for the target parking space, wherein the longitudinal area range refers to the range in the target parking space that intersects with the lane line.
[0052] After determining the lateral area in step 104, it is necessary to further determine the starting line of the longitudinal area. The longitudinal area refers to the portion of the target parking space that intersects with the lane lines, as mentioned above. The lateral area refers to the portion of the target parking space that is perpendicular to the lane lines. Lateral and longitudinal define different directions for parking the vehicle; for example, the vehicle's direction is lateral, and the length direction is longitudinal, or vice versa. The lateral and longitudinal areas define the target parking space to accommodate the target vehicle.
[0053] For parking area 50, the longitudinal range of a single parking space is unknown. In this embodiment, the starting line of the longitudinal range is first simulated by combining the target obstacles in the parking area.
[0054] Based on another solution provided by the above embodiments, optionally, in step 106 above, simulating the starting line of the longitudinal area range for the target parking space based on the target obstacle in the parking area measured by the second sensor on the target vehicle includes: acquiring the distance or acquiring an image of the target obstacle obtained by the second sensor on the target vehicle measuring the parking area; simulating the outer contour line of the target obstacle if the target obstacle is identified as being located within the lateral area based on the distance or acquiring image of the target obstacle; determining the target outer contour line whose angle with the lane line of the parking area is within a preset angle range; and simulating the starting line of the longitudinal area range for the target parking space based on the target outer contour line.
[0055] In this embodiment, a target obstacle exists in the parking area. At least one obstacle can be identified by measuring the parking area using a second sensor on the target vehicle. Obstacle identification can be achieved using a camera device or a ranging device.
[0056] When a camera is used to measure the parking area, images are captured. Based on these images, visual judgment can be made to identify obstacles within the parking area. Alternatively, when a distance measuring device is used to measure the parking area, the distance to obstacles can be obtained. Based on this distance, obstacles within the parking area can be identified.
[0057] Furthermore, it is necessary to select a target obstacle located within the lateral area, i.e., an obstacle already parked within the parking area, and use this obstacle as a reference point. The starting line of the longitudinal area is then simulated based on the outer contour of this obstacle. Obstacles located outside the lateral area cannot be used as reference points for determining the starting line of the longitudinal area.
[0058] Regardless of whether it's based on the acquired images or the obstacle distance, the external contour and type of the target obstacle can be identified. The external contour of the target obstacle is simulated as an outer contour line, which outlines the overall shape of the obstacle. The outer contour line is selected based on the angle between its intersection with the lane lines and serves as the starting line for simulating the longitudinal area of the target parking space. The target obstacle can be a vehicle parked in the parking area, including cars, trucks, motorcycles, and / or bicycles. It can also be other non-vehicle objects, such as fixed crash barriers or bollards.
[0059] In an optional embodiment, the target obstacle is a vehicle; determining the target outer contour line whose angle of intersection with the lane line is within a preset angle range includes: if the vehicle's front is parallel to the lane line, then determining the target outer contour line includes at least one outer contour line of the vehicle whose angle of intersection with the lane line is 90 degrees; if the vehicle's front has a preset angle with the lane line, then determining the target outer contour line includes at least one outer contour line of the vehicle whose angle of intersection with the lane line is the preset angle.
[0060] For example, if the target obstacle in a parking area is a parked vehicle, the target outer contour line can be determined by considering the parking method of the vehicle to establish the starting line for simulating the longitudinal area. The starting line of the longitudinal area serves as a dividing line to define parking spaces within the lateral area; therefore, the corresponding target outer contour line needs to be determined by considering the parking method of the parked vehicles.
[0061] Specifically, if the front of a parked vehicle is parallel to the lane lines, for example, referring to... Figure 6 In (b), the target obstacle 200 is a parked vehicle with its front facing parallel to the lane line (corresponding to the first parking space line 14). Then, the target outer contour line is the outer contour line 18 of the parked vehicle that intersects the lane line at an angle of 90 degrees, as shown in the figure. The front and rear of the vehicle each correspond to an outer contour line 18. The target outer contour line may include at least one outer contour line 18 to simulate the starting line of the longitudinal region.
[0062] Specifically, if the front of a parked vehicle has a preset angle with the lane line, for example, referring to... Figure 7 In (a) and (b), the target obstacle 200 is a parked vehicle, and the vehicle's front orientation has a preset angle θ with the lane line (corresponding to the first parking space line 14). Figure 7 In (a), the preset included angle θ is greater than 90 degrees, indicating that the parked vehicle is parked at an angle in the angled parking space. Figure 7 In (b), the preset angle θ is 90 degrees, indicating that the parked vehicle is parked perpendicular to the lane line in a rectangular parking space. In both scenarios above, the target outer contour line is the outer contour line of the parked vehicle whose angle with the lane line is the preset angle θ, i.e., the outer contour line of the parked vehicle parallel to the vehicle body direction.
[0063] like Figure 7 As shown, each side of the vehicle body corresponds to an outer contour line 18. The target outer contour line may include at least one outer contour line 18 to simulate the starting line of the longitudinal region.
[0064] Step 108: Determine the range of the target parking space by using the lateral area range and the starting line to perform automatic parking.
[0065] After obtaining the starting line of the longitudinal area range based on the obstacle simulation of the parking area, the target parking space for parking the target vehicle can be determined by combining it with the lateral area range determined in step 104.
[0066] Specifically, based on the solution provided in the above embodiments, optionally, in step 108, determining the range of the target parking space for automatic parking by means of the lateral area range and the starting line includes: determining the target area range formed by the intersection of the starting line with the first parking space line and the second parking space line of the lateral area range as the longitudinal area range, wherein the target area range is far away from the target obstacle; determining the parking method of the target vehicle based on the distance between the first parking space line and the second parking space line in the longitudinal area range, wherein the parking method includes parking with the front of the vehicle facing parallel to the lane line or parking with the front of the vehicle facing at an angle to the lane line; determining whether the longitudinal area range meets the preset parking space size corresponding to the parking method based on the parking method; if the preset parking space size is met, then determining the range of the target parking space in the longitudinal area range for automatic parking.
[0067] Combination Figure 6 In (b), the starting line (corresponding to the outer contour line 18) intersects with the first parking space line 14 and the second parking space line 16 of the transverse area, respectively, resulting in two parking space line corner points. The three lines enclose the target area, which is far away from the target obstacle 200. That is, the target area is the area excluding the area where the target obstacle 200 is located. For example, if there are two starting lines, the target area is the area located to the right of the front of the target obstacle 200 and the area located to the left of the rear of the target obstacle 200.
[0068] The target area formed above is the longitudinal area, which provides the corner points of the parking space lines and can be used for parking space planning. Based on the distance between the first parking space line 14 and the second parking space line 16 in the longitudinal area, the parking method of the target vehicle is determined. The parking method includes parking with the front of the vehicle parallel to the lane line (including horizontal parking) and parking with the front of the vehicle at an angle to the lane line (including angled parking and perpendicular parking).
[0069] Different parking methods require different parking space sizes or layout standards. Therefore, it's necessary to determine whether the longitudinal area meets the preset parking space size corresponding to the target vehicle's parking method. For example, for... Figure 6For parking where the front of the vehicle is parallel to the lane line, it is necessary to determine whether the difference between the length of the longitudinal area along the vehicle length direction and the length of the target vehicle is greater than a preset length threshold. The preset length threshold is related to the standard division length of the parking space.
[0070] If it is greater than, it means that there is a target parking area within the longitudinal region that satisfies the requirement of parking 100 of the target vehicle. For example, Figure 6 (c) refers to two parking areas 22 located before and after the target obstacle 200. Further, the target vehicle 100 can be automatically parked based on the determined range of the target parking space. If the range is not greater than a certain value, it indicates that there is no suitable target parking area within the longitudinal region for the target vehicle 100 to park. In this case, the target vehicle 100 can continue to move forward, scanning the roadside parking areas as it goes, until a suitable target parking area is found and automatic parking is performed, or if no suitable target parking area is found, it leaves the parking area.
[0071] In the above embodiment, after the range of the target parking space is identified in step 108, automatic parking can be performed. In another embodiment, to avoid the identified parking area being an actual parking area, for example, if the target obstacle in the parking area is a bollard or a barrier, the target parking space determined based on the simulated starting line corresponding to the target obstacle may not be a reasonable parking space, causing misjudgment. Directly performing automatic parking would pose certain risks.
[0072] Optionally, after determining the range of the target parking space, the method further includes: if the type of the target obstacle is identified as a vehicle, then transmitting control commands for automatic parking of the target vehicle to the vehicle's electronic control unit.
[0073] To avoid identifying parking spaces as unsuitable or unparkable in specific scenarios, this can be achieved by restricting the types of target obstacles. When identifying the starting line of the longitudinal area, the target vehicle's camera can be used to determine the type of target obstacle, such as whether it is a vehicle, and further, whether it is a passenger car. Only if the conditions are met can automatic parking be performed in the target parking space.
[0074] Alternatively, the strategy can restrict the use of parking spaces for automatic parking to be determined based on conditions such as parking lines close to the target vehicle, curbs far from the target vehicle, and target obstacles within the parking area. Such conditional restrictions can help avoid potential parking space misjudgments and inappropriate use.
[0075] After determining that the target parking space is suitable for automatic parking, control commands for automatic parking of the target vehicle are transmitted to the target vehicle's Central Electronic Module (CEM).
[0076] In the above embodiments, a target parking space can be identified by a combination of three elements: parking space line (i.e., first parking space line), curb or wall (i.e., second parking space line), and vehicle (i.e., target obstacle).
[0077] Figure 8 Different application scenarios of the automatic parking space recognition method according to embodiments of this application are given, wherein Figure 8 (a) shows a combination of elements including parking lines, curbs, and vehicles (e.g., passenger car 202). Figure 8 (b) shows a combination of elements including parking lines, walls, and vehicles (e.g., motorcycle 204 or bicycle 206).
[0078] Furthermore, for scenarios where the dividing line 12 (i.e., the parking space line) between two adjacent parking spaces is severely worn, making the corner points of the parking space line unrecognizable, for example... Figure 8 As shown in (c), the above method can also be used to identify target parking spaces.
[0079] Therefore, the automatic parking system can support more parking scenarios, thus significantly improving the adaptability of the automatic parking system.
[0080] In this embodiment, for parking areas without parking space line corners or where parking space line corners cannot be identified, parking space lines are simulated based on target obstacles in the parking area, and combined with other known parking space lines to obtain the range of parking spaces within the parking area that can be used for automatic parking. Specifically, firstly, based on environmental measurement data obtained from the parking area measured by the first sensor on the target vehicle, the first parking space line and the second parking space line of the parking area are determined. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area. Then, based on the first parking space line and the second parking space line, the lateral area range of the target parking space is determined. The lateral area range refers to the range of the target parking space perpendicular to the lane line. Next, based on the target obstacles in the parking area measured by the second sensor on the target vehicle, a parking space is simulated for the target parking space. The starting line of the longitudinal area of the target parking space is defined, where the longitudinal area refers to the area intersecting the lane lines within the target parking space. Finally, the range of the target parking space is determined by the lateral area and the starting line for automatic parking. This method identifies and plans new parking spaces by integrating three elements: the first parking space line, the second parking space line, and the target obstacle. The identification of new parking spaces does not depend on the corner points of the parking space lines, which solves the problem of not being able to identify parking spaces in parking areas where there are no corner points of the parking space lines or the corner points of the parking space lines cannot be identified, thus expanding the application scenarios and scope of automatic parking.
[0081] In addition, corresponding to Figure 1 In addition to the method shown, another embodiment of this application also provides a parking space recognition device for automatic parking. Figure 9 This is a structural diagram of the automatic parking space recognition device 1000, which is applied to parking areas where there are no parking space line corner points or the parking space line corner points cannot be recognized. The device includes: The first determining module 1200 determines the first parking space line and the second parking space line of the parking area based on environmental measurement data obtained by the first sensor on the target vehicle measuring the parking area. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area. The second determining module 1400 determines the lateral area range of the target parking space based on the first parking space line and the second parking space line. The lateral area range refers to the range of the lane lines perpendicular to the parking area in the target parking space. The simulation module 1600, based on the target obstacles in the parking area measured by the second sensor on the target vehicle, simulates the starting line of the longitudinal area range for the target parking space, wherein the longitudinal area range refers to the range in the target parking space that intersects with the lane lines. The third determining module 1800 determines the range of the target parking space by using the horizontal area range and the starting line to perform automatic parking.
[0082] Optionally, the first determining module 1200 acquires an image of the parking area measured by a camera device on the target vehicle; identifies a parking line in the parking area near the target vehicle in the acquired image as the first parking line; acquires the distance to an obstacle in the parking area measured by a distance measuring device on the target vehicle; and, based on the obstacle distance, if the corresponding obstacle is identified as a curb or wall near the curb line of the parking area, simulates the line corresponding to the obstacle as the second parking line.
[0083] Optionally, the first determining module 1200 acquires images of the parking area measured by the camera device on the target vehicle; based on the acquired images, it identifies parking space lines near the target vehicle and obstacles near the curb line of the parking area; if the obstacle is identified as a curb or a wall, the line corresponding to the obstacle is simulated as the second parking space line.
[0084] Optionally, the simulation module 1600 acquires the distance to or image of the target obstacle obtained by the second sensor on the target vehicle measuring the parking area; based on the distance to or image of the target obstacle, if the target obstacle is identified as being located within the lateral area, the module simulates the outer contour line of the target obstacle; determines the target outer contour line whose angle with the lane line of the parking area is within a preset angle range; and simulates the starting line of the longitudinal area range for the target parking space based on the target outer contour line.
[0085] Optionally, the third determining module 1800 determines the target area formed by the intersection of the starting line with the first parking space line and the second parking space line of the horizontal area as the vertical area, and the target area is far away from the target obstacle; based on the distance between the first parking space line and the second parking space line in the vertical area, it determines the parking method of the target vehicle, the parking method including parking with the front of the vehicle parallel to the lane line or parking with the front of the vehicle at an angle to the lane line; based on the parking method, it determines whether the vertical area meets the preset parking space size corresponding to the parking method; if it meets the preset parking space size, it determines the range of the target parking space in the vertical area for automatic parking.
[0086] Optionally, the system also includes a transmission module that, after determining the range of the target parking space, transmits control commands for automatic parking of the target vehicle to the vehicle's electronic control unit if the target obstacle is identified as a vehicle.
[0087] The automatic parking space recognition device in this embodiment targets parking areas without parking space line corners or where parking space line corners cannot be recognized. It simulates parking space lines based on target obstacles in the parking area and combines this with other known parking space lines to obtain the range of parking spaces within the parking area suitable for automatic parking. Specifically, firstly, based on environmental measurement data obtained from a first sensor on the target vehicle, a first parking space line and a second parking space line are determined in the parking area. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area. Then, based on the first and second parking space lines, the lateral area range of the target parking space is determined. The lateral area range refers to the area of the target parking space perpendicular to the lane line. Next, based on the target obstacles in the parking area measured by a second sensor on the target vehicle, a parking space is simulated for the target parking space. The starting line of the longitudinal area of the target parking space is defined, where the longitudinal area refers to the area intersecting the lane lines within the target parking space. Finally, the range of the target parking space is determined by the lateral area and the starting line for automatic parking. This method identifies and plans new parking spaces by integrating three elements: the first parking space line, the second parking space line, and the target obstacle. The identification of new parking spaces does not depend on the corner points of the parking space lines, which solves the problem of not being able to identify parking spaces in parking areas where there are no corner points of the parking space lines or the corner points of the parking space lines cannot be identified, thus expanding the application scenarios and scope of automatic parking.
[0088] It should be noted that the specific methods by which each model performs operations in the automatic parking space recognition device in the above embodiments have been described in detail in the embodiments of the method, and will not be elaborated here.
[0089] In addition, another embodiment of this application provides a vehicle. Figure 10 This is a schematic diagram of the vehicle structure. The vehicle 2000 includes a processor 2400 and a memory 2200. The memory 2200 stores programs or instructions that can run on the processor 2400. When the program or instructions are executed by the processor 2400, they implement the various steps of the above-described automatic parking space recognition method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.
[0090] This application also provides a readable storage medium storing a program or instructions. When executed by a processor, the program or instructions implement the various processes of any of the above-described embodiments of the automatic parking space recognition method, achieving the same technical effect. To avoid repetition, these will not be described again here. The readable storage medium includes computer-readable storage media, such as read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0091] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to enable a computer to execute various processes of any of the above-described automatic parking space recognition method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.
[0092] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0093] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0094] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.
Claims
1. A parking space recognition method for automatic parking, characterized in that, The method, applicable to parking areas without parking space line corner points or where parking space line corner points cannot be identified, includes: Based on environmental measurement data obtained from the parking area measured by the first sensor on the target vehicle, the first parking space line and the second parking space line of the parking area are determined. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area. The lateral area of the target parking space is determined based on the first parking space line and the second parking space line. The lateral area refers to the area of the target parking space that is perpendicular to the lane line. Based on the target obstacles in the parking area measured by the second sensor on the target vehicle, a starting line for the longitudinal area range of the target parking space is simulated, the longitudinal area range referring to the range of the target parking space that intersects with the lane lines; The range of the target parking space is determined by the lateral area and the starting line for automatic parking.
2. The method according to claim 1, characterized in that, The first sensor includes a camera device and a ranging device, and the environmental measurement data includes acquired images and obstacle distances; Determining the first and second parking space lines of the parking area based on environmental measurement data obtained from the first sensor on the target vehicle includes: Acquire images of the parking area obtained by the camera device on the target vehicle; The parking space line closest to the target vehicle in the parking area identified in the acquired image is determined as the first parking space line; The distance to obstacles in the parking area is obtained by measuring the distance from the ranging device on the target vehicle. Based on the distance to the obstacle, if the corresponding obstacle is identified as a curb or wall near the curb line of the parking area, then the line corresponding to the obstacle is simulated as the second parking space line.
3. The method according to claim 1, characterized in that, The first sensor includes a camera device, and the environmental measurement data includes acquired images; Determining the first and second parking space lines of the parking area based on environmental measurement data obtained from the first sensor on the target vehicle includes: Acquire images of the parking area obtained by the camera device on the target vehicle; Based on the acquired images, identify parking lines near the target vehicle and obstacles near the curb in the parking area; If the obstacle is identified as a curb or a wall, the line corresponding to the obstacle is simulated as the second parking space line.
4. The method according to claim 1, characterized in that, Based on target obstacles in the parking area measured by a second sensor on the target vehicle, a starting line is simulated for the longitudinal area of the target parking space, including: The distance to or image of the target obstacle in the parking area is obtained by the second sensor on the target vehicle; Based on the distance to the target obstacle or the acquired image, if the target obstacle is identified as being within the horizontal region, then the outer contour line of the target obstacle is simulated; Determine a target outer contour line whose angle with the lane line of the parking area is within a preset angle range; Based on the target outer contour line, a starting line is simulated for the longitudinal area range of the target parking space.
5. The method according to claim 4, characterized in that, The target obstacle is a vehicle; Determining a target outer contour line whose angle of intersection with the lane line is within a preset angle range includes: If the front of the vehicle is parallel to the lane line, then the target outer contour line is determined to include at least one outer contour line of the vehicle that intersects the lane line at an angle of 90 degrees. If the vehicle's front orientation has a preset angle with the lane line, then the target outer contour line is determined to be at least one of the vehicle's outer contour lines whose angle with the lane line is the preset angle.
6. The method according to claim 1, characterized in that, The range of the target parking space is determined by the lateral area and the starting line for automatic parking, including: The target area formed by the intersection of the starting line with the first parking space line and the second parking space line of the horizontal area is defined as the vertical area, and the target area is far away from the target obstacle. Based on the distance between the first parking space line and the second parking space line in the longitudinal area, the parking method of the target vehicle is determined. The parking method includes parking with the front of the vehicle facing parallel to the lane line, or parking with the front of the vehicle facing at an angle to the lane line. Based on the parking method, determine whether the longitudinal area range meets the preset parking space size corresponding to the parking method; If the preset parking space size is met, the range of the target parking space is determined within the longitudinal area for automatic parking.
7. The method according to claim 1, characterized in that, After determining the range of the target parking space, the process also includes: If the target obstacle is identified as a vehicle, control commands for automatic parking of the target vehicle are transmitted to the vehicle's electronic control unit.
8. A parking space recognition device for automatic parking, characterized in that, The device, applicable to parking areas where parking space line corners are absent or cannot be identified, comprises: The first determining module determines the first parking space line and the second parking space line of the parking area based on environmental measurement data obtained by the first sensor on the target vehicle measuring the parking area. The first parking space line is close to the lane line of the parking area, and the second parking space line is close to the curb line of the parking area. The second determining module determines the lateral area range of the target parking space based on the first parking space line and the second parking space line. The lateral area range refers to the range of the lane lines perpendicular to the parking area in the target parking space. The simulation module, based on the target obstacles in the parking area measured by the second sensor on the target vehicle, simulates the starting line of the longitudinal area range for the target parking space, wherein the longitudinal area range refers to the range in the target parking space that intersects with the lane lines; The third determining module determines the range of the target parking space by using the horizontal area range and the starting line to perform automatic parking.
9. A vehicle, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the method as described in any one of claims 1-7.
10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1-7.