A parking assistance method, a parking assistance system, an electronic device, and a vehicle

Abstract

The application provides a parking assistance method, a parking assistance system, an electronic device and a vehicle. The parking assistance method comprises the following steps: collecting an environment parameter of a parking space; extracting feature information of an obstacle in the parking space; identifying a type of the obstacle in the parking space; judging whether the obstacle is movable; calculating a moving time of the obstacle; and outputting different parking strategies under different moving times of the obstacles.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of intelligent auxiliary driving, and particularly relates to a parking auxiliary method, a parking auxiliary system, an electronic device and a vehicle. BACKGROUND

[0002] In the current rapid development of the automobile field, intelligent auxiliary driving systems have been widely applied to various automobile models. As one of the intelligent auxiliary driving systems, the automatic parking auxiliary system has become a high-end configuration or a standard configuration of all models. With the wide application of the automatic parking auxiliary system, the challenges from the complex and diverse parking environment are becoming increasingly severe.

[0003] In the prior art, an environmental perception unit detects obstacles around the vehicle body during parking. If an obstacle is identified during parking, the vehicle stops and searches for a parking space again to plan a parking path. This method is time-consuming and cannot flexibly park according to the type of the obstacle. SUMMARY

[0004] In view of the defects of the prior art, the application provides a parking auxiliary method, a parking auxiliary system, an electronic device and a vehicle. The parking space environment parameters are comprehensively collected, and it is comprehensively judged whether the parking space obstacle is movable. Different parking strategies are selected according to the result of the judgment of the parking space obstacle, the parking space is flexibly released, the operability is strong, and the situation of tight parking space is alleviated.

[0005] To achieve the above-mentioned purpose, the application provides a parking auxiliary method, which comprises:

[0006] acquiring current parking space environment parameters;

[0007] extracting obstacle feature information according to the parking space environment parameters;

[0008] obtaining the type of the obstacle according to the obstacle feature information;

[0009] judging that the obstacle is movable according to the type of the obstacle, and outputting a parking strategy according to the obstacle moving time to assist in completing the current parking.

[0010] In the application, the parking space environment parameters are comprehensively considered during the parking process of the vehicle, the type of the parking space obstacle is judged,

[0011] and the parking space obstacle is analyzed and judged in multiple situations to output different parking strategies, so that the parking is more flexibly and comprehensively assisted.

[0012] The parking space environment parameters include the position, direction and range of the parking space, and the obstacle present in the range of the parking space.

[0013] In the present application, the extraction of the obstacle feature information according to the parking space environment parameters comprises:

[0014] The depth map of the obstacle is obtained by a monocular deep learning method, target detection is performed on the depth map, and more stable and accurate results are obtained through multi-frame tracking to output the obstacle feature information, wherein the obstacle feature information at least includes the obstacle size, weight, quantity and obstacle contour.

[0015] In the present application, the identification of the obstacle type according to the obstacle feature information comprises:

[0016] The obstacle contour of the obstacle feature information is fitted with the trained obstacle database, the target data with the highest fitting degree is selected to determine the obstacle type, and the obstacle type information is sent to the vehicle-mounted display end in real time, wherein the obstacle type is an important influencing factor of the movement of the parking space obstacle, thereby assisting parking.

[0017] In the present application, the judgment of the obstacle as movable according to the parking space obstacle type comprises:

[0018] When the obstacle size, weight and quantity meet the system setting conditions, the obstacle is judged as movable, otherwise the obstacle is judged as immovable; when the obstacle is immovable, the automatic parking system re-searches the parking space.

[0019] The system setting conditions include the obstacle size, weight and quantity, and the parameters thereof can be customized according to the parking habits of the driver;

[0020] Further, in the present application, the movement time of the obstacle is calculated according to the obstacle as movable, and specifically comprises:

[0021] The movement time of the obstacle is calculated according to the obstacle size, weight and quantity,

[0022] Further, the movement time of the obstacle is calculated according to the obstacle size, weight and quantity,

[0023] If yes, the driver is informed to move the obstacle or to re-search the parking space;

[0024] If no, the parking space is directly re-searched.

[0025] In order to solve the above technical problems, the present application further provides a parking assistance system, preferably, the system comprises:

[0026] A data reading module connected with a data acquisition system and reading parking space environment parameters;

[0027] The computing module calculates the parking space obstacle feature information according to the parking space environment parameters, identifies the obstacle type, and calculates the obstacle moving time.

[0028] The interaction module sends a moving obstacle prompt to a vehicle-mounted display terminal or sends an interaction instruction to an automatic parking system according to the obstacle moving time.

[0029] Optionally, the interaction module further includes a judging unit configured to generate an interaction instruction according to the obstacle moving time.

[0030] In the present application, the data acquisition system at least includes:

[0031] A plurality of surround-view cameras arranged at any position of the vehicle are configured to acquire the parking space environment parameters.

[0032] To solve the above technical problems, the present application further provides an electronic device, which at least includes:

[0033] an ECU controller, at least one processor, and

[0034] an ECU controller built-in memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the one processor, the instructions are executed by the at least one processor, and the at least one processor can complete the above-mentioned parking assistance method.

[0035] To solve the above technical problems, the present application further provides a vehicle, which includes:

[0036] a vehicle body;

[0037] a plurality of surround-view cameras distributed at any position of the vehicle, the surround-view cameras being configured to acquire the current parking space environment parameters;

[0038] a vehicle-mounted display terminal configured to display the parking space obstacle feature information, the moving obstacle prompt, and the parking strategy;

[0039] an automatic parking system configured to search for a parking space and park the vehicle according to a parking logic;

[0040] and an electronic device in communication connection with the surround-view cameras, the electronic device being configured to complete the above-mentioned parking assistance method.

[0041] Compared with the prior art, the present application has the following beneficial effects:

[0042] This application proposes a parking assistance method, a parking assistance system, an electronic device, and a vehicle. By acquiring parking space environmental parameters, it extracts obstacle feature information, identifies the type of obstacle, determines whether the obstacle is movable, calculates the movement time of the obstacle, and outputs different parking strategies under different obstacle movement times. This enables flexible release of parking spaces, is highly operable, reduces parking time, and avoids situations where parking spaces cannot be released or where parking spaces are scarce. Attached Figure Description

[0043] Figure 1 This is a flowchart of a parking assistance method in one embodiment.

[0044] Figure 2 This is a flowchart of obtaining the current parking space environmental parameters in one embodiment.

[0045] Figure 3 This is a flowchart illustrating the process of extracting obstacle feature information based on the parking space environmental parameters in one embodiment.

[0046] Figure 4 This is a flowchart illustrating the process of identifying the corresponding obstacle type based on the extracted obstacle feature information in one embodiment.

[0047] Figure 5 Here is a flowchart of a parking strategy output based on the obstacle type in one embodiment.

[0048] Figure 6 This is a schematic diagram of a parking assistance system in one embodiment. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions will be clearly and completely described below in conjunction with the embodiments of this application. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0050] Example 1:

[0051] As attached Figure 1 As shown, this embodiment provides a parking assistance method. This method can be used when an automatic parking system detects an obstacle in a parking space. The method is implemented by judging and processing the obstacle in the parking space. Specifically, the method includes:

[0052] S1: Obtain the current parking space environment parameters;

[0053] The current parking space environment parameters include the position, direction and range of the parking space, and obstacles appearing in the range of the parking space. In an embodiment, the visual image around the vehicle body is obtained by a plurality of surround-view cameras arranged at any position of the vehicle, and the current parking space environment parameters are obtained.

[0054] S2: extracting obstacle feature information according to the parking space environment parameters;

[0055] The extraction of the obstacle feature information specifically includes:

[0056] The parking space environment parameters are analyzed by visual image analysis, the obstacles in the range of the parking space are processed by a monocular deep learning method to obtain a depth map of the obstacles, target detection is performed on the depth map, and a 3D frame of the obstacle target and at least the size, weight, number and obstacle contour of the obstacle are output. A more stable and accurate result is obtained by multi-frame tracking to obtain the size, weight, number and obstacle contour of the obstacle and other obstacle feature information.

[0057] S3: identifying the type of the obstacle according to the obstacle feature information;

[0058] The identification of the type of the obstacle specifically includes:

[0059] According to the obstacle feature information, the obstacle contour is analyzed, fitted with a trained obstacle database in a parking obstacle memory storage module built in an ECU controller, the target data with the highest fitting degree is selected to determine the type of the obstacle, and the obstacle type information is sent to a vehicle-mounted display end in real time. When the trained obstacle database in the memory storage module does not have the type of the obstacle and cannot be identified and judged, it is fed back to the vehicle-mounted display end, and the driver judges whether the type of the obstacle is movable. The ECU controller memorizes and deeply learns the judgment result of the driver, and the next time the obstacle is encountered, the obstacle can be automatically identified.

[0060] S4: if the obstacle is movable according to the type of the obstacle, a parking strategy is output according to the moving time of the obstacle to assist in completing the current parking.

[0061] When the size, weight and number of the obstacle meet the system setting conditions, the obstacle is determined to be movable, otherwise the obstacle is determined to be immovable. When the obstacle is immovable, the automatic parking system searches for a parking space again.

[0062] The obstacle size, weight, and quantity are compared with system setting conditions, for example, the obstacle size with a height of no more than 2 meters (definable) or a width of no more than 2 meters (definable) is considered movable, the obstacle weight of no more than 80 kg (definable) is considered movable, and the obstacle quantity of no more than 5 pieces (definable) is considered movable;

[0063] According to the output parking strategy according to the obstacle moving time, specifically comprising:

[0064] According to the obstacle being movable, the obstacle moving time is calculated;

[0065] The obstacle moving time is calculated according to the obstacle size, weight, and quantity, for example, the system records the obstacle weight of a single quantity standard size through the parking obstacle memory storage module built in the ECU controller, and preliminarily sets the time required by a 60 kg adult driver to move the obstacle, and the obstacle moving time is calculated according to the obstacle size, weight, and quantity;

[0066] Further, it is judged whether the obstacle moving time is within a threshold value;

[0067] If yes, the driver is informed to move the obstacle or to select to search for a parking space again;

[0068] If no, the parking space is directly searched again.

[0069] The embodiment collects parking space environment parameters through the surround view camera of the data acquisition system, comprehensively considers various factors of the parking space searched by the automatic parking system, and outputs different parking strategies, so that a parking scheme more in line with the actual situation is obtained, and the parking space is more flexibly released to avoid long-time search for a parking space.

[0070] In some embodiments, whether the obstacle is movable and the moving time can be set according to a plurality of parameters actually affecting the parking space, or different parameters can be set according to different drivers, and both are not limited thereto.

[0071] In some embodiments, according to the parking space obstacle type, it is judged that the obstacle is movable, the obstacle moving time is calculated, and is sent to the interaction module in real time: according to the obstacle moving time, a moving obstacle prompt is sent to the vehicle-mounted display end or an interaction instruction is sent to the automatic parking system, so that the parking space is flexibly released.

[0072] As shown in the accompanying Figure 2 In some embodiments, the step S1 of acquiring the current parking space environment parameters from each surround view camera can include:

[0073] S101: Start the surround view camera to acquire information around the vehicle;

[0074] S102: The automatic parking system automatically searches for a parking space according to the vehicle body surrounding information;

[0075] S103: Obtain the current parking space environment parameters.

[0076] Among them: automatically search for a parking space, obtain the parking space environment parameters can be obtained through real-time updating of the cloud, the cloud supports communication connection with all vehicle ends, and can also obtain real-time parking space environment parameters collected by each vehicle end, when any vehicle passes through the target parking space or is about to pass through the target parking space, the target parking space environment parameters are downloaded from the cloud to supplement or correct the parking space environment parameters collected by the vehicle.

[0077] As shown in the accompanying Figure 3 In some embodiments, the extracting obstacle feature information according to the parking space environment parameters specifically includes:

[0078] S111: Input the parking space environment parameters;

[0079] S112: Monocular depth learning method obtains obstacle depth map;

[0080] S113: Target detection is performed on the obstacle depth map, and the feature information of the target is output.

[0081] Among them, the monocular depth learning method is used to process the visual image of the input parking space environment parameters, obtain the depth map of the parking space obstacle, perform target detection on the obtained depth map, use multi-frame tracking to obtain more stable and accurate results, and obtain the feature information of the obstacle, including at least obstacle size, weight, number and obstacle contour.

[0082] When processing the visual image, methods including but not limited to monocular depth learning, binocular depth learning, laser radar or structured light are used.

[0083] As shown in the accompanying Figure 4 In some embodiments, the identifying corresponding obstacle type according to the extracted obstacle feature information specifically includes:

[0084] S121: Input the obstacle contour of the obstacle feature information;

[0085] S122: Fit with the trained obstacle database;

[0086] S123: Select the data with the highest fitting degree to determine the obstacle type.

[0087] The trained obstacle database is stored in a parking obstacle memory storage module in a vehicle ECU controller, and when the trained obstacle database in the memory storage module does not have the obstacle type and cannot be identified and judged, it is fed back to a vehicle-mounted display end, and the driver judges whether the obstacle type is movable, and the ECU controller memorizes and deeply learns the driver's judgment result, and the next time the obstacle is encountered, it can be automatically identified.

[0088] As shown in the accompanying Figure 5 In some embodiments, if it is determined that the obstacle is movable according to the type of the obstacle, a parking strategy is output according to the moving time of the obstacle to assist in completing the current parking, and the method specifically comprises the following steps.

[0089] S131: inputting the type of the parking space obstacle;

[0090] S132: judging whether the parking space obstacle is movable;

[0091] S133: judging whether the obstacle is within a threshold value;

[0092] If the parking space obstacle is not movable, the parking space is searched again.

[0093] If the parking space obstacle is movable and the obstacle is not within the threshold value, the parking space is searched again.

[0094] If the obstacle is within the threshold value, the driver selects to move the obstacle or to search for a parking space again.

[0095] The threshold value is the set moving time of the obstacle.

[0096] The system setting time in the embodiment can be customized and modified by comprehensively considering the daily parking behavior and habits of the driver, is suitable for the judgment and analysis of obstacle movement in various parking situations, can meet the parking needs of different drivers, and more flexibly and comprehensively assists parking.

[0097] Embodiment two:

[0098] To solve the above technical problems, the application further provides a parking assistance system in another embodiment.

[0099] As shown in the accompanying Figure 6 The parking assistance system in the embodiment specifically comprises the following:

[0100] The data reading module is in communication connection with any surround-view camera and collects visual images around the vehicle body and reads parking space environment parameters; in the embodiment, the any surround-view sensor is arranged at any position of the vehicle end and is used to collect parking space environment parameters.

[0101] The computing module calculates the parking space obstacle feature information according to the parking space environment parameters, identifies the obstacle type, and calculates the obstacle moving time.

[0102] The interaction module sends a moving obstacle prompt to the vehicle display terminal or sends an interaction instruction to the automatic parking system according to the obstacle moving time; wherein the interaction instruction can be selected as starting the obstacle identification module, performing automatic parking, or re-searching the parking space.

[0103] The interaction module further includes a judgment unit, which can be used to generate an interaction instruction according to the obstacle moving time.

[0104] When the car is ready to park, the automatic parking system is started, and the look-around camera starts to collect the parking space environment parameters in real time, and sends the obtained parking space environment visual image to the data reading module; after the data reading module receives the visual image information, it is transmitted to the computing module, and the computing module processes the visual image information through deep learning method, and detects the target of the obtained depth map to obtain the parking space obstacle feature information, judges the obstacle type and whether it is movable through the judgment module, and sends the judgment result to the vehicle display terminal and the interaction module.

[0105] The vehicle interaction module sends an interaction instruction according to the obstacle moving time result output by the judgment unit.

[0106] Preferably, when the parking space obstacle is not movable, the automatic parking system re-searches the parking space;

[0107] Preferably, when the parking space obstacle is movable, it is further judged whether the obstacle moving time is within the threshold value;

[0108] The obstacle moving time is calculated according to the obstacle size, weight and quantity,

[0109] Preferably, if the obstacle moving time is within the threshold value, the driver is notified to move the obstacle or re-search the parking space;

[0110] Preferably, if the obstacle moving time is not within the threshold value, the parking space is directly re-searched;

[0111] Further, the driver sees the parking space obstacle feature information, the moving obstacle prompt and the parking strategy through the vehicle display terminal.

[0112] It should be noted that the above embodiments are only for ease of understanding and cannot be regarded as a limitation on the content of the present application. For example, the visual acquisition module, the above embodiment is preferably 4 surround cameras, other preferred schemes such as adding 2 surround cameras or cameras, radar, expanding the detection range of the environment around the vehicle body, are all feasible schemes and belong to the content of the present application.

[0113] Embodiment three:

[0114] In order to solve the above technical problems, the present application further provides an electronic device in another embodiment.

[0115] In the embodiment, the electronic device at least includes the following;

[0116] An ECU controller, at least one processor, and

[0117] The ECU controller is in communication connection with the at least one processor built-in memory, wherein the memory stores instructions executable by the one processor, the instructions are executed by the at least one processor, and the at least one processor can complete an auxiliary parking method as described above.

[0118] In order to have a better operation experience, a specific embodiment of the electronic device in the embodiment is provided, wherein when the obstacle profile of the input obstacle feature information is not found in the fitting process of the obstacle database trained in the memory storage module of the ECU controller, the corresponding data of the obstacle type cannot be identified and judged, the obstacle data is fed back to the vehicle display end, whether the driver judges the obstacle type is movable, the ECU controller stores and learns the driver's judgment result, and the next time the obstacle is encountered, it can be automatically identified.

[0119] Embodiment four:

[0120] In order to solve the above technical problems, the present application further provides a vehicle in another embodiment.

[0121] In the embodiment, the vehicle at least includes the following:

[0122] Vehicle body;

[0123] A plurality of surround cameras distributed at any position of the vehicle end, the surround cameras are used to acquire the current parking space environment parameters;

[0124] Vehicle display end for displaying the parking space obstacle feature information, moving obstacle prompt and parking strategy;

[0125] Automatic parking system for searching parking space and parking vehicle according to parking logic;

[0126] And an electronic device in communication connection with the surround view camera, the electronic device being configured to perform the parking assistance method.

[0127] The various function units in the embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of hardware plus software function unit.

[0128] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0129] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and in actual application, another division mode can be used, for example, a plurality of units or page components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0130] The integrated unit realized in the form of software function unit can be stored in a computer readable storage medium. The software function unit is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute part of the steps of the method described in the embodiments of the present application. The storage medium described above includes a U disk, a mobile hard disk, a read-only first memory (ROM), a random access first memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0131] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A parking assistance method characterized by, The method comprises the following steps: acquiring current parking space environment parameters; extracting obstacle feature information according to the parking space environment parameters; identifying the type of the obstacle according to the obstacle feature information; judging whether the obstacle is movable according to the type of the obstacle, and outputting a parking strategy according to the obstacle moving time to assist in completing the current parking; wherein the identification of the type of the obstacle according to the extracted obstacle feature information comprises: fitting the obstacle contour of the obstacle feature information with a trained obstacle database, and selecting the target data with the highest fitting degree to determine the type of the obstacle; the judgment of whether the obstacle is movable according to the type of the obstacle comprises: when the size, weight and quantity of the obstacle meet the system setting conditions, judging that the obstacle is movable, otherwise, judging that the obstacle is immovable; when the obstacle is immovable, the automatic parking system re-searches for a parking space; the parking strategy comprises: calculating the obstacle moving time according to the size, weight and quantity of the obstacle, judging whether the obstacle moving time is within a threshold, if yes, notifying the driver to move the obstacle or to re-search for a parking space, otherwise, directly re-searching for a parking space.

2. The parking assistance method according to claim 1, characterized by, The current parking space environment parameters at least include: the position, direction and range of the parking space, and the obstacle appearing in the range of the parking space.

3. The parking assistance method according to claim 2, characterized by, The extraction of the obstacle feature information comprises: obtaining the depth map of the obstacle through a monocular deep learning method, performing target detection on the depth map, and outputting the obstacle feature information, which at least includes the size, weight, quantity and contour of the obstacle.

4. A parking assistance system employing a parking assistance method according to any one of claims 1 to 3, characterized by The parking assistance system comprises: a data reading module connected with a data acquisition system and reading the parking space environment parameters; a calculation module calculating the parking space obstacle feature information, identifying the type of the obstacle, and calculating the obstacle moving time according to the parking space environment parameters; an interaction module issuing a moving obstacle prompt to a vehicle display terminal or issuing an interaction instruction to an automatic parking system according to the obstacle moving time.

5. The parking assistance system according to claim 4, wherein the data acquisition system at least comprises: a plurality of surround-view cameras arranged at any position of the vehicle and used for acquiring the parking space environment parameters.

6. An electronic device, comprising: The electronic device comprises: an ECU controller, at least one processor, and an ECU controller built-in memory in communication connection with the at least one processor, wherein the memory stores instructions executable by the one processor, and the instructions are executed by the at least one processor to enable the at least one processor to complete the parking assistance method according to any one of claims 1-3.

7. A vehicle characterized by comprising: It comprises: a vehicle body; a plurality of surround-view cameras distributed at any position of the vehicle, the surround-view cameras being used for acquiring the current parking space environment parameters; a vehicle display terminal used for displaying the parking space obstacle feature information, the moving obstacle prompt and the parking strategy; an automatic parking system used for searching for a parking space and parking the vehicle according to the parking logic; And an electronic device in communication connection with the surround view camera, the electronic device is used for completing the parking assistance method as any one of claims 1-3.

Images