Mapless parking memory methods, products, media, equipment, and vehicles

Abstract

This invention belongs to the field of automatic parking technology. It provides a mapless parking memory method, product, medium, device, and vehicle. When the vehicle speed is below a set threshold, it acquires a perception image of the vehicle's surroundings. When an entrance gate is detected based on the perception image, it acquires the vehicle's current satellite positioning information and determines whether the current road segment is a non-public road segment based on this information. If the current road segment is a public road segment, it returns to continue judging vehicle speed and acquiring perception images for further judgment. If the current road segment is a non-public road segment, it initiates parking route learning, automatically generating a parking memory route when the vehicle parks in a parking space. This invention combines perception images of the vehicle's surroundings with satellite positioning information to achieve automatic mapless parking memory in both above-ground and underground scenarios, eliminating the need for user scene switching and greatly improving the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic parking, in particular to a no-map parking memory method, product, medium, product, equipment and vehicle. BACKGROUND

[0002] The statements in this section merely provide background technology related to the present application and do not necessarily constitute prior art.

[0003] With the increasing maturity of intelligent driving technology and the widespread popularity of new energy vehicles, vehicles are no longer just a simple means of transportation, but have evolved into mobile spaces integrating high technology and intelligence. In this trend, automatic parking function, as an important part of intelligent driving technology, is gradually becoming a standard feature of modern cars, greatly improving the convenience and safety of driving.

[0004] Memory parking, full parking lot memory parking function (Valet Parking Assist), is based on automatic parking function, through route memory, auxiliary driving and other functions, to realize more comprehensive and automatic parking scene application. However, the current memory parking requires users to actively choose the scene of function use, and select a memory starting point and the corresponding route for learning after choosing the scene of function use, and the user actively drives to the starting point of the route to use the function, and the adaptive scene learning ability is poor. SUMMARY

[0005] In order to solve the problems of the prior art, the present application provides a no-map parking memory method, product, medium, product, equipment and vehicle, which combines the perception image around the vehicle and the satellite positioning information, realizes automatic no-map parking memory in ground and underground scenes, does not need the user to switch scenes, and greatly improves the user experience.

[0006] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0007] In a first aspect, the present application provides a no-map parking memory method.

[0008] A no-map parking memory method, comprising the following processes:

[0009] When the vehicle speed is lower than a set threshold, the perception image around the vehicle is obtained;

[0010] When the entrance gate is identified according to the perception image, the current satellite positioning information of the vehicle is obtained, and whether the current road section is a non-public road section is judged according to the positioning information;

[0011] If the current road section is a public road section, the vehicle speed judgment and the sensing image acquisition are continued; if the current road section is a non-public road section, the park route learning is started, and a park memory route is automatically generated after the vehicle is parked.

[0012] As a further limitation of the first aspect of the application, after starting the park route learning, a prompt for the park route learning is generated on the vehicle host interface, and a countdown is performed. When the first virtual button is not selected, a park memory route is automatically generated after the vehicle is parked. When the first virtual button is selected, the user is prompted whether to exit the route learning.

[0013] At this time, when the second virtual button is selected, the park route learning is exited, and the vehicle speed judgment and the sensing image acquisition are continued. When the second virtual button is not selected, the judgment process after starting the park route learning is continued.

[0014] In a second aspect, the application provides a no-map park memory system.

[0015] A no-map park memory system comprises:

[0016] A sensing image acquisition unit is configured to acquire a sensing image of the surroundings of the vehicle when the vehicle speed is lower than a set threshold.

[0017] A road section judgment unit is configured to acquire satellite positioning information of the vehicle when an entrance gate is recognized according to the sensing image, and to judge whether the current road section is a non-public road section according to the positioning information.

[0018] A memory route generation unit is configured to return to continue the vehicle speed judgment and the sensing image acquisition if the current road section is a public road section, and to start the park route learning if the current road section is a non-public road section, and to automatically generate a park memory route after the vehicle is parked.

[0019] As a further limitation of the second aspect of the application, in the memory route generation unit, after starting the park route learning, a prompt for the park route learning is generated on the vehicle host interface, and a countdown is performed. When the first virtual button is not selected, a park memory route is automatically generated after the vehicle is parked. When the first virtual button is selected, the user is prompted whether to exit the route learning.

[0020] At this time, when the second virtual button is selected, the park route learning is exited, and the vehicle speed judgment and the sensing image acquisition are continued. When the second virtual button is not selected, the judgment process after starting the park route learning is continued.

[0021] In a third aspect, the application provides a no-map park memory method

[0022] A no-map parking memory method comprises the following processes:

[0023] Real-time acquisition of a satellite positioning signal of a vehicle, when the satellite positioning signal is lost, judging whether a current road section is a non-public road section according to satellite positioning information before the satellite positioning signal is lost, if the current road section is a public road section, returning to continue attempting to acquire the satellite positioning signal of the vehicle, and at this time, parking route learning is not performed; if the current road section is not a public road section, acquiring a perception image around the vehicle;

[0024] Judging whether an underground parking lot is entered according to the perception image, if not, returning to continue attempting to acquire the satellite positioning signal of the vehicle, and at this time, parking route learning is not performed; if yes, starting to learn a parking route, and automatically generating a parking memory route when the vehicle is parked in a parking space.

[0025] As a further limitation of the third aspect of the present application, after starting to learn the parking route, a prompt of learning the parking route is generated on a host interface of the vehicle, and a countdown is performed, when a first virtual button is not selected, automatically generating the parking memory route when the vehicle is parked in the parking space, and when the first virtual button is selected, prompting a user whether to exit the route learning;

[0026] At this time, when a second virtual button is selected, the parking route learning is exited, and the process of continuing to judge the vehicle speed and acquiring the perception image to continue judging is returned to; when the second virtual button is not selected, the process of judging after starting to learn the parking route is returned to continue to be executed.

[0027] In a fourth aspect, the present application provides a no-map parking memory system.

[0028] A no-map parking memory system comprises:

[0029] A satellite positioning signal judging unit is configured to acquire a satellite positioning signal of a vehicle in real time, when the satellite positioning signal is lost, judging whether a current road section is a non-public road section according to satellite positioning information before the satellite positioning signal is lost, if the current road section is a public road section, returning to continue attempting to acquire the satellite positioning signal of the vehicle, and at this time, parking route learning is not performed; if the current road section is not a public road section, acquiring a perception image around the vehicle;

[0030] A parking memory route generating unit is configured to judge whether an underground parking lot is entered according to the perception image, if not, returning to continue attempting to acquire the satellite positioning signal of the vehicle, and at this time, parking route learning is not performed; if yes, starting to learn a parking route, and automatically generating a parking memory route when the vehicle is parked in a parking space.

[0031] As a further limitation of the fourth aspect of the application, in the parking memory route generation unit, after starting the parking route learning, a prompt for parking route learning is generated on the vehicle host interface and a countdown is performed, when the first virtual button is not selected, after the vehicle is parked in the parking space, a parking memory route is automatically generated, when the first virtual button is selected, the user is prompted whether to exit the route learning;

[0032] At this time, when the second virtual button is selected, the parking route learning is exited and the process of continuing to judge the vehicle speed and acquire the perception image to continue the judgment is returned to continue.

[0033] In the fifth aspect, the application provides a no-map parking memory method.

[0034] A no-map parking memory method, comprising the following processes:

[0035] When the vehicle speed is lower than a set threshold, a perception image around the vehicle is acquired;

[0036] When an entrance gate is identified according to the perception image, current satellite positioning information of the vehicle is acquired, and whether the current road section is a non-public road section is judged according to the positioning information;

[0037] If the current road section is a public road section, the process of continuing to judge the vehicle speed and acquire the perception image to continue the judgment is returned to continue; if the current road section is a non-public road section, whether the satellite positioning signal is lost is judged, if not, it is judged that the vehicle is currently in a ground parking lot, and the parking memory route learning is directly started, and after the vehicle is parked in the parking space, a parking memory route is automatically generated.

[0038] If the satellite positioning signal is lost and a downhill slope is identified according to the perception image, whether the vehicle enters a ground parking lot is judged according to the downhill slope, if not, it is judged that the vehicle is currently in a ground parking lot, and the parking memory route learning is directly started, and after the vehicle is parked in the parking space, a parking memory route is automatically generated; if yes, it is judged that the vehicle enters a ground parking lot, and the parking memory route learning is started, and after the vehicle is parked in the parking space, a parking memory route is automatically generated.

[0039] In the sixth aspect, the application provides a no-map parking memory system.

[0040] A no-map parking memory system, comprising:

[0041] A perception image acquisition unit configured to acquire a perception image around the vehicle when the vehicle speed is lower than a set threshold;

[0042] The road section determining unit is configured to: when an entrance gate is identified according to the perception image, acquire current satellite positioning information of the vehicle, and determine whether the current road section is a non-public road section according to the positioning information;

[0043] The first route generating unit is configured to: if the current road section is a public road section, return to continue vehicle speed determination and perception image acquisition for continuous determination; if the current road section is a non-public road section, determine whether the satellite positioning signal is lost, and if not, determine that the vehicle is currently in a ground parking lot, and directly start memory parking route learning, and automatically generate a memory parking route when the vehicle is parked in a parking space.

[0044] The second route generating unit is configured to: if the satellite positioning signal is lost and a downhill slope is identified according to the perception image, determine whether to enter a ground parking lot according to the downhill slope, and if not, determine that the vehicle is currently in a ground parking lot, and directly start memory parking route learning, and automatically generate a memory parking route when the vehicle is parked in a parking space; if yes, determine that the vehicle enters a ground parking lot, and start memory parking route learning, and automatically generate a memory parking route when the vehicle is parked in a parking space.

[0045] In a seventh aspect, the present application provides a computer device, comprising: a processor and a computer readable storage medium;

[0046] The processor is adapted to execute a computer program;

[0047] The computer readable storage medium has a computer program stored therein, and the computer program is executed by the processor to implement the no-map parking memory method according to the first aspect, the third aspect or the seventh aspect of the present application.

[0048] In an eighth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is adapted to be loaded and executed by a processor to implement the no-map parking memory method according to the first aspect, the third aspect or the seventh aspect of the present application.

[0049] In a ninth aspect, the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the no-map parking memory method according to the first aspect, the third aspect or the seventh aspect of the present application.

[0050] In a tenth aspect, the present application provides a vehicle, comprising a control terminal configured to execute the no-map parking memory method according to the first aspect, the third aspect or the seventh aspect of the present application.

[0051] Compared with the prior art, the present application has the following beneficial effects:

[0052] 1. The application innovatively proposes a no-map parking memory method, which is suitable for the case of ground parking lot. When the vehicle speed is lower than the set threshold, the perception image around the vehicle is obtained. When the entrance gate is identified according to the perception image, the current satellite positioning information of the vehicle is obtained. Whether the current section is a non-public section is judged according to the positioning information. If the current section is a public section, the vehicle speed judgment and perception image acquisition are continued to judge. If the current section is a non-public section, the park route learning is started. When the vehicle stops at the parking space, a parking memory route is automatically generated. Through the judgment of the public section, invalid learning under the public section is avoided, and the memory learning accuracy in the ground parking lot scene is improved.

[0053] 2. The application innovatively proposes a no-map parking memory method, which is suitable for the case of underground parking lot. When the satellite positioning signal is lost, whether the current section is a non-public section is judged according to the satellite positioning information before the satellite positioning signal is lost. If it is a public section, the satellite positioning signal of the vehicle is continuously tried to be obtained, and the parking route learning is not performed at this time. If it is not a public section, the perception image around the vehicle is obtained. Whether it enters the underground parking lot is judged according to the perception image. If not, the satellite positioning signal of the vehicle is continuously tried to be obtained, and the parking route learning is not performed at this time. If yes, the park route learning is started. When the vehicle stops at the parking space, a parking memory route is automatically generated. Combined with the identification of the satellite positioning signal and the perception image, rapid memory learning in the underground parking lot scene is realized.

[0054] 3. The application innovatively proposes a no-map parking memory method, which is suitable for the case of ground parking lot connected to underground parking lot (i.e. one entrance gate corresponds to ground and underground parking lot). After the vehicle enters, whether the satellite positioning signal is lost is judged. If not, it is judged that the vehicle is in the ground parking lot, and the park route learning is started. When the vehicle stops at the parking space, a parking memory route is automatically generated. If the satellite positioning signal is lost and the downhill slope is identified according to the perception image, whether it enters the underground parking lot is judged according to the downhill slope. If not, it is judged that the vehicle is in the ground parking lot, and the park route learning is started. When the vehicle stops at the parking space, a parking memory route is automatically generated. If yes, it is judged that the vehicle enters the underground parking lot, and the park route learning is started. When the vehicle stops at the parking space, a parking memory route is automatically generated. Through the above method, the automatic judgment of the vehicle on the ground and underground parking is realized, and the memory learning accuracy is greatly improved.

[0055] 4、The present application can generate a memory route automatically after parking in the corresponding parking space after the user enters the common scene and the background memory route is started by visual perception and logical judgment of GPS information loss, and the user can use the memory parking function when coming to the place again, which avoids the process of user active route learning, reduces the user learning cost, and makes the function more practical and simple.

[0056] Advantages of the additional aspects of the present application will become apparent in the following description, which is given by way of example only, from the following description with reference to the drawings, or will be learned by the practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0057] The accompanying drawings, which form a part of the specification, are included to provide a further understanding of the application and are incorporated herein by reference. The illustrations are shown by way of example and are not intended to limit the application, unless specified.

[0058] Figure 1 A flowchart of the no-map parking memory method provided for the embodiment 1 of the present application is shown in the figure;

[0059] Figure 2 A schematic diagram of the no-map parking memory system provided for the embodiment 2 of the present application is shown in the figure;

[0060] Figure 3 A flowchart of the no-map parking memory method provided for the embodiment 3 of the present application is shown in the figure;

[0061] Figure 4 A schematic diagram of the no-map parking memory system provided for the embodiment 4 of the present application is shown in the figure;

[0062] Figure 5 A flowchart of the no-map parking memory method provided for the embodiment 5 of the present application is shown in the figure;

[0063] Figure 6 A schematic diagram of the no-map parking memory system provided for the embodiment 6 of the present application is shown in the figure;

[0064] Figure 7 A schematic diagram of the computer device provided for the embodiment 7 of the present application is shown in the figure. DETAILED DESCRIPTION

[0065] The present application will be further described below with reference to the accompanying drawings and embodiments.

[0066] It should be noted that the following detailed description is exemplary in nature and is intended to provide further description of the present application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0067] The embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0068] Embodiment 1:

[0069] The present implementation proposes a no-map parking memory method, as shown in the following figure, including the following processes: Figure 1

[0070] The four surround view cameras of the automatic parking assistance system perform real-time visual perception when the vehicle speed is less than 50 km / h, and the perception image is obtained. Understandably, the vehicle speed threshold here can also be selected according to the specific working conditions, such as 10 km / h or 20 km / h, etc., which will not be repeated here.

[0071] When the entrance gate is identified according to the perception image, the current satellite positioning information (such as GPS satellite positioning information or Beidou satellite positioning information) of the vehicle is obtained, and it is judged whether the current section is a non-public section according to the positioning information; if the current section is a public section, return to continue the vehicle speed judgment and perception image acquisition to continue the judgment; if the current section is a non-public section, start the parking route learning, and automatically generate a parking memory route when the vehicle stops at the parking space.

[0072] More specifically, after starting the parking route learning, a prompt "Start background route learning" for parking route learning is generated on the vehicle host interface and a countdown (for example, 5 seconds) is performed. When the first virtual button (i.e. the virtual button corresponding to the prompt) is not selected (which can be selected by touching at the same time or by voice), when the vehicle stops at the parking space, a parking memory route is automatically generated. When the first virtual button is selected, the user is prompted whether to exit the route learning;

[0073] At this time, when the second virtual button (i.e. the virtual button prompting the user whether to exit the route learning) is selected, the parking route learning is exited and the vehicle speed judgment and perception image acquisition are continued to continue the judgment. When the second virtual button is not selected, the judgment process after starting the parking route learning is continued.

[0074] In the present implementation, preferably, the entrance gate identified according to the perception image can use an algorithm based on convolutional neural network (CNN) and target detection algorithm (such as YOLO or Faster R-CNN). The present implementation provides the following schematic:

[0075] First, image preprocessing is performed: the input image is adjusted to a size suitable for neural network input, the image data is standardized, and the pixel value is usually scaled to the range of [0, 1] or [-1, 1].

[0076] ​Second, feature extraction is performed, and pre-trained convolutional neural networks (such as VGG16, ResNet, MobileNet, etc.) are used to extract image features. These features are usually extracted through convolutional layers, pooling layers, and activation functions, etc.

[0077] Finally, target detection is performed, and target detection algorithms (such as YOLO, Faster R-CNN, etc.) are used to detect entrance gates in images. These algorithms usually slide windows over feature maps and perform classification and bounding box regression for each window.

[0078] In target detection algorithms, bounding box regression is a key step that adjusts the predicted bounding box to more accurately match the actual target. The formula for bounding box regression is usually as follows:

[0079] Let the predicted bounding box be (P x , P y , P w , P h ), and the real bounding box be (G x , G y , G w , G h ), where (x, y) is the coordinate of the center of the bounding box, and (w, h) is the width and height of the bounding box. The goal of bounding box regression is to find a mapping function f such that f(P) = G. This function is usually implemented through linear regression, and its formula is as follows:

[0080]

[0081] where (δ x , δ y , δ w , δ h ) is the offset between the predicted bounding box and the real bounding box, and the target detection algorithm learns these offsets to adjust the bounding box when predicting.

[0082] Embodiment 2:

[0083] As shown in Figure 2 , the present implementation provides a no-map parking memory system, which includes:

[0084] A perception image acquisition unit configured to acquire a perception image around the vehicle when the vehicle speed is below a set threshold;

[0085] A road segment judgment unit configured to, when an entrance gate is identified according to the perception image, acquire the current satellite positioning information (such as GPS satellite positioning information or Beidou satellite positioning information) of the vehicle, and determine whether the current road segment is a non-public road segment according to the positioning information;

[0086] The memory route generating unit is configured to: if the current route section is a public route section, return to continue vehicle speed judgment and sensing image acquisition to continue judgment; and if the current route section is a non-public route section, start a park route learning, and automatically generate a park memory route after the vehicle stops at a parking space.

[0087] In the memory route generating unit, after starting the park route learning, a prompt of the park route learning is generated on a vehicle host interface and a countdown is performed, and when the first virtual button is not selected, a park memory route is automatically generated after the vehicle stops at a parking space, and when the first virtual button is selected, a user is prompted whether to exit the route learning.

[0088] At this time, when the second virtual button is selected, the park route learning is exited and a return is made to continue vehicle speed judgment and sensing image acquisition to continue judgment, and when the second virtual button is not selected, a return is made to continue the judgment process after starting the park route learning.

[0089] It can be understood that the above-mentioned units can be combined into one or several other units respectively or totally, or some of the units can be further split into multiple units with smaller functions to constitute, which can realize the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions, and in actual application, the functions of one unit can also be realized by multiple units, or the functions of multiple units can be realized by one unit. In other embodiments of the present application, the system can also include other units, and in actual application, these functions can also be realized by other units and can be realized by multiple units in cooperation.

[0090] According to another embodiment of the present application, the system described in the embodiment can be constructed and the method of the embodiment 1 can be realized by running a computer program (including program codes) capable of executing each step involved in the corresponding method described in the embodiment 1 on a general computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU), a random access memory (RAM), a read only memory (ROM), etc., the computer program can be recorded on a computer readable recording medium, and loaded into the above-mentioned computing device through the computer readable recording medium and run therein.

[0091] Embodiment 3:

[0092] The present implementation proposes a no-map park memory method, as shown in Figure 3 including the following processes:

[0093] Real-time acquisition of vehicle satellite positioning signal (for example, GPS satellite positioning information or Beidou satellite positioning information), when the satellite positioning signal is lost, according to the satellite positioning information before the satellite positioning signal is lost, it is judged whether the current section is a non-public section, if it is a public section, return to continue to try to acquire the vehicle satellite positioning signal, at this time, no parking route learning is performed; if it is not a public section, acquire the perception image around the vehicle;

[0094] According to the perception image, it is judged whether to enter an underground parking lot (for example, by identifying a downhill or identifying a dark environment or a wall around, etc.), if not, return to continue to try to acquire the vehicle satellite positioning signal, at this time, no parking route learning is performed; if yes, start the parking route learning, and when the vehicle stops in the parking space, a parking memory route is automatically generated.

[0095] In the present implementation, preferably, after starting the parking route learning, a prompt "start background route learning" of the parking route learning is generated on the vehicle host interface and a countdown (for example, 5s) is performed, when the first virtual button (i.e. the virtual button corresponding to the prompt) is not selected (which can be selected by touching at the same time, or by voice), when the vehicle stops in the parking space, a parking memory route is automatically generated, when the first virtual button is selected, the user is prompted whether to exit the route learning;

[0096] At this time, when the second virtual button (i.e. the virtual button prompting the user whether to exit the route learning) is selected, the parking route learning is exited, and the vehicle speed judgment and the perception image acquisition are continued to judge;

[0097] Embodiment 4:

[0098] As shown in Figure 4 The present implementation provides a no-map parking memory system, comprising:

[0099] A no-map parking memory system, comprising:

[0100] A satellite positioning signal judgment unit is configured to: acquire a vehicle satellite positioning signal in real time, when the satellite positioning signal is lost, according to the satellite positioning information before the satellite positioning signal is lost, it is judged whether the current section is a non-public section, if it is a public section, return to continue to try to acquire the vehicle satellite positioning signal, at this time, no parking route learning is performed; if it is not a public section, acquire the perception image around the vehicle;

[0101] The parking memory route generation unit is configured to: determine whether to enter the underground parking lot based on the perceived image; if not, return to continue trying to obtain the vehicle's satellite positioning signal, and do not perform parking route learning at this time; if yes, start parking route learning, and automatically generate a parking memory route when the vehicle is parked in the parking space.

[0102] In this preferred implementation, after parking route learning is enabled in the parking route generation unit, a parking route learning prompt is generated on the vehicle host interface and a countdown is started. When the first virtual button is not selected, a parking route is automatically generated after the vehicle is parked in the parking space. When the first virtual button is selected, the user is prompted whether to exit route learning.

[0103] When the second virtual button is selected, the system exits parking route learning and returns to continue judging vehicle speed and acquiring perception images for further judgment. When the second virtual button is not selected, the system returns to continue the judgment process after parking route learning is enabled.

[0104] Example 5:

[0105] like Figure 5 As shown, this implementation provides a mapless parking memory method, applicable to scenarios where a surface parking lot connects to an underground parking lot (i.e., one entrance gate corresponds to both the surface and underground parking lots), and includes the following process:

[0106] When the vehicle speed is below a set threshold, acquire perception images of the area around the vehicle;

[0107] When the entrance gate is identified based on the perceived image, the vehicle's current satellite positioning information is obtained, and the location information is used to determine whether the current road segment is a non-public road segment.

[0108] If the current road segment is a public road segment, return to continue to determine the vehicle speed and acquire perception images for further judgment; if the current road segment is a non-public road segment, determine whether the satellite positioning signal is lost. If it is not lost, determine that it is currently a parking lot on the ground and directly start the memory parking route learning. When the vehicle is parked in the parking space, a parking memory route is automatically generated.

[0109] If the satellite positioning signal is lost and the vehicle is identified as being on a downhill slope based on the perceived image, the system determines whether the vehicle has entered an underground parking lot. If not, the system determines that the vehicle is currently in an above-ground parking lot and initiates parking route learning. Once the vehicle is parked in a parking space, a parking route memory is automatically generated. If the vehicle is parked in an underground parking lot, the system initiates parking route learning and automatically generates a parking route memory once the vehicle is parked in a parking space.

[0110] After starting the parking route learning, a parking route learning prompt is generated on the vehicle's main unit interface and a countdown begins. When the first virtual button is not selected, a parking memory route is automatically generated after the vehicle parks in the parking space. When the first virtual button is selected, the user is prompted whether to exit the route learning.

[0111] When the second virtual button is selected, the system exits parking route learning and returns to continue judging vehicle speed and acquiring perception images for further judgment. When the second virtual button is not selected, the system returns to continue the judgment process after parking route learning is enabled.

[0112] Example 6:

[0113] like Figure 6 As shown, this implementation provides a mapless parking memory system, including:

[0114] The perception image acquisition unit is configured to acquire perception images of the vehicle's surroundings when the vehicle speed is below a set threshold.

[0115] The road segment determination unit is configured to: when an entrance gate is identified based on the perceived image, obtain the vehicle's current satellite positioning information, and determine whether the current road segment is a non-public road segment based on the positioning information;

[0116] The first route generation unit is configured to: if the current road segment is a public road segment, return to continue to judge the vehicle speed and acquire perception images to continue the judgment; if the current road segment is a non-public road segment, judge whether the satellite positioning signal is lost; if it is not lost, judge that it is a parking lot on the ground, directly start the memory parking route learning, and automatically generate a parking memory route when the vehicle is parked in the parking space.

[0117] The second route generation unit is configured to: if the satellite positioning signal is lost and a downhill ramp is identified based on the perceived image, determine whether to enter the underground parking lot based on the downhill ramp; if not, determine that it is currently in the above-ground parking lot and directly activate the parking route learning; when the vehicle is parked in the parking space, automatically generate a parking route memory; if so, determine that it is in the underground parking lot and activate the parking route learning; when the vehicle is parked in the parking space, automatically generate a parking route memory.

[0118] In the second route generation unit, after the parking route learning is enabled, a parking route learning prompt is generated on the vehicle host interface and a countdown is started. When the first virtual button is not selected, a parking memory route is automatically generated after the vehicle is parked in the parking space. When the first virtual button is selected, the user is prompted whether to exit route learning.

[0119] At this time, when the second virtual button is selected, the parking route learning is exited, and the vehicle speed judgment and the sensing image acquisition are continued to judge, and when the second virtual button is not selected, the judgment process after the parking route learning is started is continued.

[0120] Embodiment 7:

[0121] As shown in Figure 7 The electronic device includes a processor 1001, a communication interface 1002, and a computer readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer readable storage medium 1003 can be connected by a bus or other means.

[0122] The communication interface 1002 is configured to receive and send data, the computer readable storage medium 1003 can be stored in the memory of the electronic device, the computer readable storage medium 1003 is configured to store a computer program, the computer program includes program instructions, and the processor 1001 is configured to execute the program instructions stored in the computer readable storage medium 1003.

[0123] The processor 1001 (also referred to as CPU (Central Processing Unit, Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, and is particularly suitable for loading and executing one or more instructions to implement a corresponding method flow or a corresponding function.

[0124] The processor 1001 is configured to execute the method of embodiment 1, embodiment 3, or embodiment 5.

[0125] Embodiment 8:

[0126] The computer readable storage medium provided by the present embodiment is a memory device in the electronic device, which is used to store programs and data. It can be understood that the computer readable storage medium herein can include a built-in storage medium in the electronic device, and of course can also include an expansion storage medium supported by the electronic device. The computer readable storage medium provides a storage space, and the storage space stores a processing system of the electronic device.

[0127] In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory; optionally, it can also be at least one computer readable storage medium located away from the aforementioned processor.

[0128] In one embodiment, the computer readable storage medium stores one or more instructions; the one or more instructions stored in the computer readable storage medium are loaded and executed by the processor to implement the method of embodiment 1, embodiment 3 or embodiment 5.

[0129] Embodiment 9:

[0130] The present implementation provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the electronic device to perform the method of embodiment 1, embodiment 3 or embodiment 5.

[0131] Embodiment 10:

[0132] The present implementation provides a vehicle comprising a control terminal configured to perform the no-map parking memory method of embodiment 1, embodiment 3 or embodiment 5 of the present application.

[0133] In summary, the present application provides a new memory parking route learning method. The background route learning makes the human-computer interaction of the memory parking function simpler and reduces the learning cost of the user. The corresponding solutions are provided for the ground parking lot and the underground parking lot, and the solutions can cover the conventional memory parking route learning scenarios.

[0134] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for parking memory without map, characterized in that, The method comprises the following processes: acquiring a perception image around the vehicle when the vehicle speed is lower than a set threshold value; when an entrance gate is identified according to the perception image, acquiring satellite positioning information of the vehicle at present, and determining whether the current road section is a non-public road section according to the positioning information; if the current road section is a public road section, returning to continue the vehicle speed determination and the perception image acquisition to continue the determination; if the current road section is a non-public road section, starting the park route learning, and automatically generating a park memory route when the vehicle stops at a parking space; after starting the park route learning, generating a prompt of the park route learning on a vehicle host interface and counting down, automatically generating a park memory route when the vehicle stops at a parking space if a first virtual button is not selected, and prompting a user whether to exit the route learning if the first virtual button is selected; at this time, exiting the park route learning if a second virtual button is selected, returning to continue the vehicle speed determination and the perception image acquisition to continue the determination, and returning to continue the determination process after starting the park route learning if the second virtual button is not selected.

2. A no-map parking memory system characterized by, The method comprises: a perception image acquisition unit configured to acquire a perception image around the vehicle when the vehicle speed is lower than a set threshold value; a road section determination unit configured to acquire satellite positioning information of the vehicle at present when an entrance gate is identified according to the perception image, and determine whether the current road section is a non-public road section according to the positioning information; a memory route generation unit configured to return to continue the vehicle speed determination and the perception image acquisition to continue the determination if the current road section is a public road section, and start the park route learning and automatically generate a park memory route when the vehicle stops at a parking space if the current road section is a non-public road section; in the memory route generation unit, after starting the park route learning, generating a prompt of the park route learning on a vehicle host interface and counting down, automatically generating a park memory route when the vehicle stops at a parking space if a first virtual button is not selected, and prompting a user whether to exit the route learning if the first virtual button is selected; at this time, exiting the park route learning if a second virtual button is selected, returning to continue the vehicle speed determination and the perception image acquisition to continue the determination, and returning to continue the determination process after starting the park route learning if the second virtual button is not selected.

3. A method for a mapless parking memory, applied to the mapless parking memory system according to claim 2, characterized in that, The method comprises the following processes: acquiring a satellite positioning signal of the vehicle in real time, determining whether the current road section is a non-public road section according to satellite positioning information before the satellite positioning signal is lost if the satellite positioning signal is lost, returning to continue the attempt to acquire the satellite positioning signal of the vehicle if the current road section is a public road section, and not performing the park route learning at this time; acquiring a perception image around the vehicle if the current road section is not a public road section; determining whether to enter an underground parking lot according to the perception image, returning to continue the attempt to acquire the satellite positioning signal of the vehicle if not, and not performing the park route learning at this time; starting the park route learning and automatically generating a park memory route when the vehicle stops at a parking space if yes.

4. The no-map park memory method of claim 3, wherein When the parking route learning is started, a prompt of the parking route learning is generated on the host interface of the vehicle and a countdown is performed. When the first virtual button is not selected, a parking memory route is automatically generated after the vehicle is parked in the parking space. When the first virtual button is selected, the user is prompted whether to exit the route learning. At this time, when the second virtual button is selected, the parking route learning is exited and the process of judging the vehicle speed and acquiring the perception image is continued. When the second virtual button is not selected, the process after the parking route learning is started is continued.

5. A parking memory system without map, using the parking memory method without map according to any one of claims 1, 3-4, characterized in that, The process includes: The satellite positioning signal judging unit is configured to acquire the satellite positioning signal of the vehicle in real time. When the satellite positioning signal is lost, whether the current section is a non-public section is judged according to the satellite positioning information before the satellite positioning signal is lost. If it is a public section, the process of acquiring the satellite positioning signal of the vehicle is continued. At this time, the parking route learning is not performed. If it is not a public section, the perception image around the vehicle is acquired. The parking memory route generating unit is configured to judge whether the underground parking lot is entered according to the perception image. If not, the process of acquiring the satellite positioning signal of the vehicle is continued. At this time, the parking route learning is not performed. If yes, the parking route learning is started. After the vehicle is parked in the parking space, a parking memory route is automatically generated.

6. The no-map parking memory system of claim 5, wherein When the parking route learning is started, a prompt of the parking route learning is generated on the host interface of the vehicle and a countdown is performed. When the first virtual button is not selected, a parking memory route is automatically generated after the vehicle is parked in the parking space. When the first virtual button is selected, the user is prompted whether to exit the route learning. At this time, when the second virtual button is selected, the parking route learning is exited and the process of judging the vehicle speed and acquiring the perception image is continued. When the second virtual button is not selected, the process after the parking route learning is started is continued.

7. A method for a no-map parking memory system as claimed in any one of claims 2, 5-6, characterized in that, The process includes: When the vehicle speed is lower than a set threshold, the perception image around the vehicle is acquired. When an entrance gate is recognized according to the perception image, the current satellite positioning information of the vehicle is acquired. Whether the current section is a non-public section is judged according to the positioning information. If the current section is a public section, the process of judging the vehicle speed and acquiring the perception image is continued. If the current section is a non-public section, whether the satellite positioning signal is lost is judged. If not, it is judged that the vehicle is in an aboveground parking lot. The parking route learning is directly started. After the vehicle is parked in the parking space, a parking memory route is automatically generated. If the satellite positioning signal is lost and a downhill slope is recognized according to the perception image, whether the underground parking lot is entered is judged according to the downhill slope. If not, it is judged that the vehicle is in an aboveground parking lot. The parking route learning is directly started. After the vehicle is parked in the parking space, a parking memory route is automatically generated. If yes, it is judged that the underground parking lot is entered. The parking route learning is started. After the vehicle is parked in the parking space, a parking memory route is automatically generated.

8. A parking memory system without map, characterized by the parking memory system without map according to any one of claims 1, 3-4, 7, wherein The process includes: An awareness image acquisition unit is configured to acquire an awareness image of the surroundings of the vehicle when the vehicle speed is lower than a set threshold value; A road section determination unit is configured to acquire satellite positioning information of the vehicle when an entrance gate is identified according to the awareness image, and determine whether the current road section is a non-public road section according to the positioning information; If the current road section is a public road section, the first route generation unit is configured to return to continue vehicle speed determination and awareness image acquisition for continuous determination; If the current road section is a non-public road section, the first route generation unit is configured to determine whether the satellite positioning signal is lost, and if not, determine that the vehicle is currently in a ground parking lot, and directly start a memory parking route learning, and automatically generate a memory parking route when the vehicle is parked in a parking space; If the satellite positioning signal is lost and a downhill slope is identified according to the awareness image, the second route generation unit is configured to determine whether the vehicle enters a ground parking lot according to the downhill slope, and if not, determine that the vehicle is currently in a ground parking lot, and directly start a memory parking route learning, and automatically generate a memory parking route when the vehicle is parked in a parking space; If yes, determine that the vehicle enters a ground parking lot, and start a memory parking route learning, and automatically generate a memory parking route when the vehicle is parked in a parking space.

9. A computer device, comprising: It comprises: a processor and a computer readable storage medium; a processor adapted to execute a computer program; a computer readable storage medium having a computer program stored therein, wherein the computer program is executed by the processor to implement the map-free parking memory method of any one of claims 1, 3-4, and 7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is adapted to be loaded and executed by the processor to implement the map-free parking memory method of any one of claims 1, 3-4.

11. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program is executed by the processor to implement the map-free parking memory method of any one of claims 1, 3-4.

12. A vehicle characterized by comprising: It comprises a control terminal configured to execute the map-free parking memory method of any one of claims 1, 3-4.

Images