Figure-free parking memory method, product, medium, product, equipment and vehicle

Abstract

The invention belongs to the technical field of automatic parking. The invention provides a graph-free parking memory method, a product, a medium, a product, equipment and a vehicle, and the method comprises the steps: obtaining a perception image around the vehicle when the vehicle speed is lower than a set threshold value; when an entrance gate is recognized according to the sensing image, current satellite positioning information of the vehicle is obtained, and whether the current road section is a non-public road section or not is judged according to the positioning information; if the current road section is the public road section, returning to continue to judge the vehicle speed and obtain the sensing image to continue to judge; and if the current road section is a non-public road section, parking memory route learning is started, and when the vehicle is parked at the parking space, a parking memory route is automatically generated. According to the invention, in combination with the perception image around the vehicle and the satellite positioning information, automatic non-graph parking memory in overground and underground scenes is realized, and a user does not need to switch the scenes, so that the user experience is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic parking, and in particular to a non-image parking memory method, product, medium, product, equipment and vehicle. Background Art

[0002] The statements in this section merely provide background art related to the present invention 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 a mobile space that integrates high technology and intelligence. In this trend, the 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 memory parking function (Valet Parking Assist), based on the automatic parking function, through route memory, assisted driving and other functions, to achieve a more comprehensive and automatic parking scene application. However, the current premise of using memory parking requires the user to actively select the scene to use the function, and select a memory starting point and a corresponding route to learn in the scene. After a memory route is generated, the user can actively drive to the route starting point to use the function, and the ability to learn in adaptive scenes is poor. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the present invention provides a method, product, medium, product, device and vehicle for image-free parking memory, which, combined with the perceived images around the vehicle and satellite positioning information, realizes automatic image-free parking memory in above-ground and underground scenes without the need for users to switch scenes, greatly improving the user experience.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for memory parking without a map.

[0008] A non-map parking memory method includes the following processes:

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

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

[0011] If the current road section is a public road section, the system will return to continue to judge the vehicle speed and obtain the perception image to continue the judgment; if the current road section is a non-public road section, the parking route memory learning will be started, and when the vehicle is parked in the parking space, a parking memory route will be automatically generated.

[0012] As a further limitation of the first aspect of the present invention, after the parking route learning is turned on, 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, when the vehicle is parked in the parking space, a parking memory route is automatically generated, and 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 parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

[0014] In a second aspect, the present invention provides a map-free parking memory system.

[0015] A non-image parking memory system, comprising:

[0016] The perception image acquisition unit is configured to: acquire a perception image around the vehicle when the vehicle speed is lower than a set threshold;

[0017] A road section determination unit is configured to: when an entrance gate is identified according to the perception image, obtain the 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;

[0018] The memory route generation unit is configured as follows: if the current road section is a public road section, it returns to continue the vehicle speed judgment and acquires the perception image to continue the judgment; if the current road section is a non-public road section, it starts the memory parking route learning, and when the vehicle is parked in the parking space, a parking memory route is automatically generated.

[0019] As a further limitation of the second aspect of the present invention, in the memory route generation unit, after the parking route learning is turned on, 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, when the vehicle is parked in the parking space, a parking memory route is automatically generated, and 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 parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

[0021] In a third aspect, the present invention provides a non-map parking memory method.

[0022] A non-map parking memory method includes the following processes:

[0023] Acquire the vehicle satellite positioning signal in real time. When the satellite positioning signal is lost, determine whether the current road section is a non-public road section based on the satellite positioning information before the satellite positioning signal is lost. If it is a public road section, return to continue trying to acquire the vehicle satellite positioning signal, and do not learn the parking route at this time; if it is not a public road section, acquire the perception image around the vehicle;

[0024] Determine whether the vehicle has entered the underground parking lot based on the perceived image. If not, return to continue trying to obtain the vehicle satellite positioning signal without learning the parking route. If so, start learning the parking route memory. When the vehicle is parked in the parking space, a parking memory route is automatically generated.

[0025] As a further limitation of the third aspect of the present invention, after the parking route learning is turned on, 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, when the vehicle is parked in the parking space, a parking memory route is automatically generated, and when the first virtual button is selected, the user is prompted whether to exit the route learning;

[0026] At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

[0027] In a fourth aspect, the present invention provides a map-free parking memory system.

[0028] A non-image parking memory system, comprising:

[0029] The satellite positioning signal judgment unit is configured to: obtain the vehicle satellite positioning signal in real time, and when the satellite positioning signal is lost, judge whether the current road section is a non-public road section according to the satellite positioning information before the satellite positioning signal is lost, and if it is a public road section, return to continue to try to obtain the vehicle satellite positioning signal, and do not learn the parking route at this time; if it is not a public road section, obtain the perception image around the vehicle;

[0030] 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 satellite positioning signal without learning the parking route; if so, start the parking route memory learning, and automatically generate a parking memory route when the vehicle is parked in the parking space.

[0031] As a further limitation of the fourth aspect of the present invention, in the parking memory route generation unit, after the parking route learning is turned on, 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, when the vehicle is parked in the parking space, a parking memory route is automatically generated, and 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 returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

[0033] In a fifth aspect, the present invention provides a method for memory parking without a map.

[0034] A non-map parking memory method includes the following processes:

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

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

[0037] If the current road section is a public road section, the system returns to continue to judge the vehicle speed and acquire the perception image for further judgment; if the current road section is a non-public road section, the system determines whether the satellite positioning signal is lost. If not, the system determines that the vehicle is in a ground parking lot and directly starts learning the parking route. When the vehicle is parked in the parking space, a parking route memory is automatically generated.

[0038] If the satellite positioning signal is lost and a downhill ramp is detected according to the perception image, it is determined whether the vehicle has entered an underground parking lot according to the downhill ramp. If not, it is determined that the vehicle is in a ground parking lot at this time, and the parking route memory learning is directly started. When the vehicle parks in the parking space, a parking memory route is automatically generated. If so, it is determined that the vehicle has entered an underground parking lot, and the parking route memory learning is started. When the vehicle parks in the parking space, a parking memory route is automatically generated.

[0039] In a sixth aspect, the present invention provides a map-free parking memory system.

[0040] A non-image parking memory system, comprising:

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

[0042] A road section determination unit is configured to: when an entrance gate is recognized according to the perception image, obtain the 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 generation unit is configured to: if the current road section is a public road section, return to continue to judge the vehicle speed and acquire the perception image to continue the judgment; if the current road section is a non-public road section, judge whether the satellite positioning signal is lost, if not lost, judge that it is a ground parking lot at this time, directly start the parking route memory learning, and automatically generate a parking memory route when the vehicle is parked in the parking space;

[0044] The second route generation unit is configured as follows: if the satellite positioning signal is lost and a downhill ramp is detected according to the perception image, it is determined whether to enter the underground parking lot according to the downhill ramp; if not, it is determined that the vehicle is in the ground parking lot at this time, and the parking route memory learning is directly started. When the vehicle is parked in the parking space, a parking memory route is automatically generated; if so, it is determined that the vehicle enters the underground parking lot, and the parking route memory learning is started. When the vehicle is parked in the parking space, a parking memory route is automatically generated.

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

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

[0047] A computer-readable storage medium having a computer program stored therein, wherein when the computer program is executed by the processor, the map-free parking memory method according to the first aspect, the third aspect or the seventh aspect of the present invention is implemented.

[0048] In an eighth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executing the map-free parking memory method as described in the first aspect, the third aspect or the seventh aspect of the present invention.

[0049] In a ninth aspect, the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the map-free parking memory method as described in the first aspect, the third aspect or the seventh aspect of the present invention.

[0050] In a tenth aspect, the present invention provides a vehicle, comprising a control terminal, wherein the control terminal is configured to execute the map-free parking memory method described in the first aspect, the third aspect or the seventh aspect of the present invention.

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

[0052] 1. The present invention innovatively proposes a non-image parking memory method, which is suitable for ground parking lots. When the vehicle speed is lower than a set threshold, a perception image around the vehicle is obtained. When the entrance gate is recognized according to the perception image, the current satellite positioning information of the vehicle is obtained. According to the positioning information, it is determined whether the current road section is a non-public road section. If the current road section is a public road section, the method returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment; if the current road section is a non-public road section, the parking route memory learning is started. When the vehicle is parked in the parking space, a parking memory route is automatically generated. By judging the public road section, invalid learning in the public road section is avoided, and the memory learning accuracy in the ground parking lot scenario is improved.

[0053] 2. The present invention innovatively proposes a non-map parking memory method, which is suitable for underground parking lots. When the satellite positioning signal is lost, it is determined whether the current road section is a non-public road section based on the satellite positioning information before the satellite positioning signal is lost. If it is a public road section, it returns to continue trying to obtain the vehicle satellite positioning signal, and no parking route learning is performed at this time; if it is not a public road section, a perceived image around the vehicle is obtained; based on the perceived image, it is determined whether the vehicle enters the underground parking lot. If not, it returns to continue trying to obtain the vehicle satellite positioning signal, and no parking route learning is performed at this time; if so, parking route learning is started. When the vehicle is parked in the parking space, a parking memory route is automatically generated. Combined with the recognition of the satellite uncertain signal and the perceived image, rapid memory learning in the underground parking lot scenario is achieved.

[0054] 3. The present invention innovatively proposes a non-image parking memory method, which is suitable for the scenario where the ground parking lot is connected to the underground parking lot (that is, one entrance gate corresponds to the ground and underground parking lots). After the vehicle enters the parking lot, it is determined whether the satellite positioning signal is lost. If not, it is determined that the vehicle is in the ground parking lot at this time, and the parking route memory learning is directly started. When the vehicle parks in the parking space, a parking memory route is automatically generated; if the satellite positioning signal is lost and a downhill ramp is found according to the perceived image, it is determined according to the downhill ramp whether the vehicle enters the underground parking lot. If not, it is determined that the vehicle is in the ground parking lot at this time, and the parking route memory learning is directly started. When the vehicle parks in the parking space, a parking memory route is automatically generated; if so, it is determined that the vehicle enters the underground parking lot, and the parking route memory learning is started. When the vehicle parks in the parking space, a parking memory route is automatically generated. The above method realizes the automatic judgment of the vehicle's ground and underground parking, which greatly improves the accuracy of memory learning.

[0055] 4. The present invention uses visual perception and the logic that GPS information will be lost when entering a parking lot to start background route memory when the user enters a common scenario. After parking in the corresponding parking space, a memory route will be automatically generated. When the user comes to the location again, the memory parking function can be used, eliminating the process of active route learning for the user, reducing the user's learning cost, and making the function more practical and concise.

[0056] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0058] Figure 1 A schematic diagram of a flow chart of a non-map parking memory method provided in Embodiment 1 of the present invention;

[0059] Figure 2 A schematic diagram of a non-image parking memory system provided in Embodiment 2 of the present invention;

[0060] Figure 3 A schematic diagram of a flow chart of a method for memory of parking without a map provided in Embodiment 3 of the present invention;

[0061] Figure 4 A schematic diagram of a non-image parking memory system provided in Embodiment 4 of the present invention;

[0062] Figure 5 A schematic diagram of a flow chart of a non-map parking memory method provided in Embodiment 5 of the present invention;

[0063] Figure 6 A schematic diagram of a non-image parking memory system provided in Example 6 of the present invention;

[0064] Figure 7 A schematic diagram of a computer device provided for Example 7 of the present invention. DETAILED DESCRIPTION

[0065] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0066] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0067] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0068] Embodiment 1:

[0069] This implementation proposes a non-map parking memory method, such as Figure 1 As shown, the following process is included:

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

[0071] When the entrance gate is recognized according to the perception image, the current satellite positioning information of the vehicle (such as GPS satellite positioning information or Beidou satellite positioning information) is obtained, and whether the current road section is a non-public road section is determined according to the positioning information; if the current road section is a public road section, the system returns to continue to judge the vehicle speed and obtain the perception image to continue the judgment; if the current road section is a non-public road section, the parking route memory learning is started, and when the vehicle is parked in the parking space, a parking memory route is automatically generated.

[0072] More specifically, after the parking route learning is turned on, a parking route learning prompt "Start background route learning" is generated on the vehicle host interface and a countdown (e.g., 5 seconds) is started. When the first virtual button (i.e., the virtual button corresponding to the prompt) is not selected (it can be selected by touch or by voice at the same time), when 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.

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

[0074] In this implementation, preferably, an algorithm based on a convolutional neural network (CNN) and a target detection algorithm (such as YOLO or Faster R-CNN) can be used to identify the entrance gate according to the perceived image. This implementation provides the following schematic diagram:

[0075] First, image preprocessing is performed: the input image is resized to a size suitable for the neural network input and the image data is standardized, usually scaling the pixel values ​​to the [0, 1] range or the [-1, 1] range.

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

[0077] Finally, object detection is performed to detect the entrance gate in the image using an object detection algorithm (such as YOLO, Faster R-CNN, etc.). These algorithms usually slide windows on the feature map and perform classification and bounding box regression for each window.

[0078] In the object detection algorithm, bounding box regression is a key step, which is used to adjust 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 ), the actual bounding box is (G x , G y , G w , G h ), where (x, y) is the coordinate of the center of the bounding box, (w, h) is the width and height of the bounding box, and 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] Among them, (δ x , δ y , δ w , δ h ) is the offset between the predicted bounding box and the true bounding box. The object detection algorithm learns these offsets to adjust the bounding box when predicting.

[0082] Embodiment 2:

[0083] like Figure 2 As shown, this implementation provides a non-map parking memory system, including:

[0084] The perception image acquisition unit is configured to: acquire a perception image around the vehicle when the vehicle speed is lower than a set threshold;

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

[0086] The memory route generation unit is configured as follows: if the current road section is a public road section, it returns to continue the vehicle speed judgment and acquires the perception image to continue the judgment; if the current road section is a non-public road section, it starts the memory parking route learning, and when the vehicle is parked in the parking space, a parking memory route is automatically generated.

[0087] In the memory route generation unit, after the parking route learning is turned on, 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 the route learning;

[0088] At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

[0089] It is understandable that the above-mentioned various units can be separately or all combined into one or several other units to constitute, or some (some) units therein can also be split into multiple smaller units in function to constitute, which can achieve 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. In practical applications, the function of a unit can also be realized by multiple units, or the function of multiple units can be realized by one unit. In other embodiments of the present application, the system can also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0090] According to another embodiment of the present application, the system described in this embodiment can be constructed, and the method of Example 1 of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 1 on a general computing device such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, 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] This implementation proposes a non-map parking memory method, such as Figure 3 As shown, the following process is included:

[0093] Acquire the vehicle satellite positioning signal (such as GPS satellite positioning information or Beidou satellite positioning information) in real time. When the satellite positioning signal is lost, determine whether the current road section is a non-public road section based on the satellite positioning information before the satellite positioning signal is lost. If it is a public road section, return to continue trying to acquire the vehicle satellite positioning signal, and do not learn the parking route at this time; if it is not a public road section, acquire the perception image around the vehicle;

[0094] Determine whether to enter an underground parking lot based on the perceived image (for example, by identifying a downhill slope or identifying a dark environment or surrounding walls, etc.); if not, return to continue trying to obtain the vehicle satellite positioning signal without learning the parking route; if so, start learning the parking route memory, and automatically generate a parking memory route when the vehicle is parked in the parking space.

[0095] In this implementation, preferably, after the parking route learning is turned on, a prompt "Start background route learning" for parking route learning is generated on the vehicle host interface and a countdown (e.g., 5 seconds) is started. When the first virtual button (i.e., the virtual button corresponding to the prompt) is not selected (it can be selected by touching or by voice at the same time), when 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 route learning.

[0096] At this time, when the second virtual button (i.e., the virtual button that prompts the user whether to exit route learning) is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is started.

[0097] Embodiment 4:

[0098] like Figure 4 As shown, this implementation provides a non-map parking memory system, including:

[0099] A non-image parking memory system, comprising:

[0100] The satellite positioning signal judgment unit is configured to: obtain the vehicle satellite positioning signal in real time, and when the satellite positioning signal is lost, judge whether the current road section is a non-public road section according to the satellite positioning information before the satellite positioning signal is lost, and if it is a public road section, return to continue to try to obtain the vehicle satellite positioning signal, and do not learn the parking route at this time; if it is not a public road section, obtain 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 satellite positioning signal without learning the parking route; if so, start the parking route memory learning, and automatically generate a parking memory route when the vehicle is parked in the parking space.

[0102] Preferably, in the parking memory route generation unit, after the parking route learning is turned on, 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 the route learning.

[0103] At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

[0104] Embodiment 5:

[0105] like Figure 5 As shown, this implementation provides a non-map parking memory method, which is applicable to the scenario where a ground parking lot is connected to an underground parking lot (i.e., one entrance gate corresponds to the ground and underground parking lots), and includes the following processes:

[0106] When the vehicle speed is lower than a set threshold, a perception image around the vehicle is obtained;

[0107] When an entrance gate is identified according to the perception image, current satellite positioning information of the vehicle is obtained, and whether the current road section is a non-public road section is determined according to the positioning information;

[0108] If the current road section is a public road section, the system returns to continue to judge the vehicle speed and acquire the perception image for further judgment; if the current road section is a non-public road section, the system determines whether the satellite positioning signal is lost. If not, the system determines that the vehicle is in a ground parking lot and directly starts learning the parking route. When the vehicle is parked in the parking space, a parking route memory is automatically generated.

[0109] If the satellite positioning signal is lost and a downhill ramp is detected according to the perception image, it is determined whether the vehicle has entered an underground parking lot according to the downhill ramp. If not, it is determined that the vehicle is in a ground parking lot at this time, and the parking route memory learning is directly started. When the vehicle parks in the parking space, a parking memory route is automatically generated. If so, it is determined that the vehicle has entered an underground parking lot, and the parking route memory learning is started. When the vehicle parks in the parking space, a parking memory route is automatically generated.

[0110] After starting the parking route learning, a parking route learning prompt and countdown are generated on the vehicle host interface. When the first virtual button is not selected, a parking route memory 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.

[0111] At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

[0112] Embodiment 6:

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

[0114] The perception image acquisition unit is configured to: acquire a perception image around the vehicle when the vehicle speed is lower than a set threshold;

[0115] A road section determination unit is configured to: when an entrance gate is recognized according to the perception image, obtain the 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;

[0116] The first route generation unit is configured to: if the current road section is a public road section, return to continue to judge the vehicle speed and acquire the perception image to continue the judgment; if the current road section is a non-public road section, judge whether the satellite positioning signal is lost, if not lost, judge that it is a ground parking lot at this time, directly start the parking route memory 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 as follows: if the satellite positioning signal is lost and a downhill ramp is detected according to the perception image, it is determined whether to enter the underground parking lot according to the downhill ramp; if not, it is determined that the vehicle is in the ground parking lot at this time, and the parking route memory learning is directly started. When the vehicle is parked in the parking space, a parking memory route is automatically generated; if so, it is determined that the vehicle enters the underground parking lot, and the parking route memory learning is started. When the vehicle is parked in the parking space, a parking memory route is automatically generated.

[0118] In the second route generation unit, after the parking route learning is turned on, 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 memory 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.

[0119] At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

[0120] Embodiment 7:

[0121] like Figure 7 As shown, this implementation provides an electronic device, which 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 may be connected via a bus or other means.

[0122] Among them, the communication interface 1002 is used 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 used to store a computer program, the computer program includes program instructions, and the processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0123] Processor 1001 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions.

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

[0125] Embodiment 8:

[0126] This implementation provides a computer-readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the electronic device and, of course, extended storage media supported by the electronic device. The computer-readable storage medium provides a storage space that stores the processing system of the electronic device.

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

[0128] In one embodiment, one or more instructions are stored in the computer-readable storage medium; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the method of Example 1, Example 3 or Example 5.

[0129] Embodiment 9:

[0130] This implementation provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of an electronic device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the electronic device executes the method of Embodiment 1, Embodiment 3, or Embodiment 5.

[0131] Embodiment 10:

[0132] The present implementation provides a vehicle, including a control terminal, wherein the control terminal is configured to execute the map-free parking memory method described in Embodiment 1, Embodiment 3, or Embodiment 5 of the present invention.

[0133] In summary, the present invention provides a new way to learn memory parking routes. Background route learning makes the human-computer interaction of the memory parking function simpler and reduces the user's learning cost. There are corresponding solutions for both ground parking lots and underground parking lots, which can cover conventional memory parking route learning scenarios.

[0134] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A parking memory method without a map, characterized in that: The process includes: When the vehicle speed is lower than a set threshold, a perception image around the vehicle is obtained; When an entrance gate is identified according to the perception image, current satellite positioning information of the vehicle is obtained, and whether the current road section is a non-public road section is determined according to the positioning information; If the current road section is a public road section, the system will return to continue to judge the vehicle speed and obtain the perception image to continue the judgment; if the current road section is a non-public road section, the parking route memory learning will be started, and when the vehicle is parked in the parking space, a parking memory route will be automatically generated.

2. The method for memory parking without a map as claimed in claim 1, characterized in that: After turning on parking route learning, a parking route learning prompt and countdown are generated on the vehicle host interface. 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; At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

3. A non-map parking memory system, characterized in that: include: The perception image acquisition unit is configured to: acquire a perception image around the vehicle when the vehicle speed is lower than a set threshold; A road section determination unit is configured to: when an entrance gate is identified according to the perception image, obtain the 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; The memory route generation unit is configured as follows: if the current road section is a public road section, it returns to continue the vehicle speed judgment and acquires the perception image to continue the judgment; if the current road section is a non-public road section, it starts the memory parking route learning, and when the vehicle is parked in the parking space, a parking memory route is automatically generated.

4. The image-free parking memory system according to claim 3, characterized in that: In the memory route generation unit, after the parking route learning is turned on, 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 the route learning; At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

5. A parking memory method without a map, characterized in that: The process includes: Acquire the vehicle satellite positioning signal in real time. When the satellite positioning signal is lost, determine whether the current road section is a non-public road section based on the satellite positioning information before the satellite positioning signal is lost. If it is a public road section, return to continue trying to acquire the vehicle satellite positioning signal. At this time, do not learn the parking route; If it is not a public road, obtain the perception image around the vehicle; Determine whether to enter the underground parking lot according to the sensed image, if not, return to continue trying to obtain the vehicle satellite positioning signal, and do not learn the parking route at this time; If so, the parking route learning will be turned on, and when the vehicle is parked in the parking space, a parking memory route will be automatically generated.

6. The method for memory parking without a map as claimed in claim 5, characterized in that: After turning on parking route learning, a parking route learning prompt and countdown are generated on the vehicle host interface. 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; At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

7. A non-map parking memory system, characterized in that: include: The satellite positioning signal judgment unit is configured to: obtain the vehicle satellite positioning signal in real time, and when the satellite positioning signal is lost, judge whether the current road section is a non-public road section according to the satellite positioning information before the satellite positioning signal is lost, and if it is a public road section, return to continue to try to obtain the vehicle satellite positioning signal, and do not perform parking route learning at this time; If it is not a public road, obtain the perception image around the vehicle; The parking memory route generation unit is configured to: determine whether to enter the underground parking lot according to the sensed image, and if not, return to continue trying to obtain the vehicle satellite positioning signal without performing parking route learning at this time; If so, the parking route learning will be turned on, and when the vehicle is parked in the parking space, a parking memory route will be automatically generated.

8. The image-free parking memory system according to claim 7, wherein: In the parking memory route generation unit, after the parking route learning is turned on, 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 the route learning; At this time, when the second virtual button is selected, the parking route learning is exited, and the process returns to continue the vehicle speed judgment and the perception image acquisition to continue the judgment. When the second virtual button is not selected, the process returns to continue the judgment process after the parking route learning is turned on.

9. A parking memory method without a map, characterized in that: The process includes: When the vehicle speed is lower than a set threshold, a perception image around the vehicle is obtained; When an entrance gate is identified according to the perception image, current satellite positioning information of the vehicle is obtained, and whether the current road section is a non-public road section is determined according to the positioning information; If the current road section is a public road section, the process returns to continue to judge the vehicle speed and acquire the perception image to continue the judgment; If the current road section is a non-public road section, it is determined whether the satellite positioning signal is lost. If not, it is determined that the vehicle is in a ground parking lot and the parking route memory learning is directly started. When the vehicle is parked in the parking space, a parking memory route is automatically generated. If the satellite positioning signal is lost and the vehicle finds a downhill ramp according to the perception image, it is determined whether the vehicle enters an underground parking lot according to the downhill ramp. If not, it is determined that the vehicle is in a ground parking lot and the parking route memory learning is directly started. When the vehicle parks in the parking space, a parking route memory is automatically generated. If so, it is judged that the vehicle has entered an underground parking lot and the parking route memory learning is started. When the vehicle parks in the parking space, a parking memory route is automatically generated.

10. A non-map parking memory system, characterized in that: include: The perception image acquisition unit is configured to: acquire a perception image around the vehicle when the vehicle speed is lower than a set threshold; A road section determination unit is configured to: when an entrance gate is recognized according to the perception image, obtain the 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; The first route generating unit is configured to: if the current road section is a public road section, return to continue to judge the vehicle speed and acquire the perception image to continue the judgment; If the current road section is a non-public road section, it is determined whether the satellite positioning signal is lost. If not, it is determined that the vehicle is in a ground parking lot and the parking route memory learning is directly started. When the vehicle is parked in the parking space, a parking memory route is automatically generated. The second route generating unit is configured to: if the satellite positioning signal is lost and a downhill ramp is detected according to the sensed image, determine whether the vehicle enters an underground parking lot according to the downhill ramp, and if not, determine that the vehicle is in a ground parking lot at this time, directly start memory parking route learning, and automatically generate a parking memory route when the vehicle is parked in the parking space; If so, it is judged that the vehicle has entered an underground parking lot and the parking route memory learning is started. When the vehicle parks in the parking space, a parking memory route is automatically generated.

11. A computer device, characterized in that: include: A processor and a computer readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the map-free parking memory method as described in any one of claims 1-2, 5-6, and 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the map-free parking memory method as described in any one of claims 1-2, 5-6.

13. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the method for memory for parking without a map as described in any one of claims 1-2, 5-6 is implemented.

14. A vehicle, characterized in that: It comprises a control terminal, which is configured to execute the map-free parking memory method as described in any one of claims 1-2, 5-6.

Images