Space storage location detection method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a space parking space detection method and device, equipment, a storage medium and a program product, and belongs to the technical field of vehicles. The method comprises the following steps: generating a two-dimensional image according to three-dimensional point cloud data of a to-be-detected area, wherein the three-dimensional point cloud data of the to-be-detected area is obtained through a laser radar; determining vehicle contour data of a plurality of parked vehicles in the two-dimensional image; according to the vehicle contour data of the multiple parked vehicles, candidate parking spaces located between every two adjacent parked vehicles are screened to construct a candidate parking space set in the to-be-detected area, and the geometric size of each candidate parking space is larger than or equal to the geometric size of a preset parking space; and according to the geometric size of the to-be-parked vehicle and the geometric size of each candidate parking space in the candidate parking space set, a target space parking space is determined in the candidate parking space set, and the target space parking space is used for parking the to-be-parked vehicle. According to the embodiment of the invention, stable and accurate space parking space detection can be carried out based on the laser radar.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a spatial storage location detection method, device, equipment, storage medium and program product. Background Art

[0002] With the rapid increase in the number of motor vehicles, the problem of insufficient parking spaces has become increasingly prominent. Therefore, it is particularly necessary to apply efficient and reliable space location detection technology to assist vehicle parking.

[0003] In the related technologies, the spatial storage location detection methods widely used on vehicles are mostly based on the detection of storage locations by sensors such as ultrasonic radar and camera. However, due to the insufficient detection accuracy of ultrasonic radar itself and the fact that the image data collected by the camera is greatly affected by the ambient light conditions, the stability of the vehicle's spatial storage location detection is poor. Therefore, how to improve the stability of the vehicle's spatial storage location detection has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a spatial storage location detection method, device, equipment, storage medium and program product, which aims to perform vehicle spatial storage location detection based on laser radar, thereby improving the stability of spatial storage location detection.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a spatial storage location detection method, the method comprising:

[0006] Generate a two-dimensional image based on three-dimensional point cloud data of the area to be detected, wherein the three-dimensional point cloud data of the area to be detected is obtained by a laser radar;

[0007] determining vehicle profile data of a plurality of parked vehicles in the two-dimensional image;

[0008] According to the vehicle profile data of the plurality of parked vehicles, a candidate storage location located between two adjacent parked vehicles is selected to construct a set of candidate storage locations in the area to be detected, wherein the geometric size of the candidate storage location is greater than or equal to the geometric size of the preset storage location;

[0009] According to the geometric dimensions of the vehicle to be parked and the geometric dimensions of each of the candidate storage locations in the candidate storage location set, a target space storage location is determined in the candidate storage location set, and the target space storage location is used to park the vehicle to be parked.

[0010] In some embodiments, the step of screening a candidate storage location located between two adjacent parked vehicles according to the vehicle profile data of the plurality of parked vehicles includes:

[0011] Determine the maximum values ​​of the vehicle profile data of the plurality of parked vehicles in pixel rows and pixel columns;

[0012] According to the maximum values ​​of the vehicle profile data of the plurality of parked vehicles on the pixel rows and the pixel columns, a plurality of target parked vehicles arranged along the vehicle head direction of the vehicle to be parked are determined from the plurality of parked vehicles, wherein the target parked vehicle is a parked vehicle closest to an extension line of the vehicle head direction;

[0013] According to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles on the pixel row and the pixel column, a candidate storage location located between two adjacent target parked vehicles is screened.

[0014] In some embodiments, determining, from among the plurality of parked vehicles, a plurality of target parked vehicles arranged along the front direction of the vehicle to be parked based on the maximum values ​​of the vehicle profile data of the plurality of parked vehicles on the pixel rows and the pixel columns, comprises:

[0015] Sort the plurality of parked vehicles in the first pixel direction according to the maximum values ​​of the vehicle profile data of the plurality of parked vehicles in the first pixel direction, wherein the first pixel direction is a pixel direction in the pixel row and the pixel column that is perpendicular to the vehicle head direction;

[0016] Determining an overlapping area between a first parked vehicle and a second parked vehicle according to the sorting in the first pixel direction, wherein the first parked vehicle and the second parked vehicle are adjacent to each other in the sorting, and a distance between the first parked vehicle and the extension line is smaller than a distance between the second parked vehicle and the extension line;

[0017] When the overlapping area between the first parked vehicle and the second parked vehicle meets a preset condition, the second parked vehicle is screened out from the plurality of parked vehicles;

[0018] The plurality of target parked vehicles include parked vehicles after the second parked vehicle is screened out.

[0019] In some embodiments, screening a candidate storage location between two adjacent target parked vehicles according to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles on the pixel row and the pixel column includes:

[0020] Sort the plurality of parked vehicles in the second pixel direction according to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles in the second pixel direction, wherein the second pixel direction is another pixel direction in the pixel row and the pixel column except the first pixel direction;

[0021] determining, according to the sorting in the second pixel direction, an overlapping area between a third parked vehicle and a fourth parked vehicle, the third parked vehicle and the fourth parked vehicle being adjacent target parked vehicles in the sorting, and a minimum distance between the third parked vehicle and the extension line being smaller than a minimum distance between the second parked vehicle and the extension line;

[0022] When the overlapping area between the third parked vehicle and the fourth parked vehicle meets a preset condition, screening out the fourth parked vehicle from the plurality of target parked vehicles;

[0023] The candidate storage location is a space between adjacent target parked vehicles among the plurality of target parked vehicles after the fourth parked vehicle is screened out.

[0024] In some embodiments, the preset conditions include:

[0025] The ratio of the overlapping area to the total area is less than a preset threshold, and the total area is a distribution area of ​​two adjacent parked vehicles associated with the overlapping area.

[0026] In some embodiments, before determining the vehicle profile data of the plurality of parked vehicles in the two-dimensional image, the method further comprises:

[0027] According to the front direction of the vehicle to be parked, a first image area and a second image area are determined in the two-dimensional image, wherein the first image area is an image area located on one side of an extension line of the front direction of the vehicle, and the second image area is an image area located on the other side of the extension line;

[0028] The vehicle contour data of the parked vehicles located in the first image area or the second image area are determined as the vehicle contour data of the plurality of parked vehicles.

[0029] In some embodiments, before generating a two-dimensional image based on the three-dimensional point cloud data of the area to be detected, the method further includes:

[0030] Scan the environment where the parked vehicle is located by using a laser radar to obtain three-dimensional point cloud data of the environment;

[0031] According to a preset point cloud data detection range, extracting three-dimensional point cloud data of the area to be detected from the three-dimensional point cloud data of the environment;

[0032] The size information of the point cloud data detection range is consistent with the size information of the area to be detected.

[0033] In some embodiments, after determining the target space storage location in the candidate storage location set according to the geometric size of the vehicle to be parked and the geometric size of each candidate storage location in the candidate storage location set, the method further includes:

[0034] Compare the information of the target spatial storage location with the spatial storage location to be confirmed in the area to be detected, wherein the spatial storage location to be confirmed is a storage location obtained by performing spatial storage location detection on the area to be detected based on an ultrasonic radar, or the spatial storage location to be confirmed is a storage location obtained by performing spatial storage location detection on the area to be detected based on an image acquisition device;

[0035] When the information of the target spatial storage location is consistent with the information of the spatial storage location to be confirmed, the vehicle to be parked is assisted in parking according to the target spatial storage location.

[0036] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a spatial storage location detection device, the device comprising:

[0037] A two-dimensional image generation module, used to generate a two-dimensional image based on three-dimensional point cloud data of the area to be detected, wherein the three-dimensional point cloud data of the area to be detected is obtained by a laser radar;

[0038] a vehicle contour extraction module, for determining vehicle contour data of a plurality of parked vehicles in the two-dimensional image;

[0039] A storage location screening module, used for screening a candidate storage location located between two adjacent parked vehicles according to the vehicle profile data of the plurality of parked vehicles, so as to construct a set of candidate storage locations in the area to be detected, wherein the geometric size of the candidate storage location is greater than or equal to the geometric size of the preset storage location;

[0040] The spatial storage location determination module is used to determine a target spatial storage location in the candidate storage location set according to the geometric dimensions of the vehicle to be parked and the geometric dimensions of each candidate storage location in the candidate storage location set, and the target spatial storage location is used to park the vehicle to be parked.

[0041] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0042] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0043] To achieve the above objectives, the fifth aspect of the embodiments of the present application proposes a computer program product, wherein the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method provided in the first aspect above are implemented.

[0044] The spatial storage location detection method, device, electronic device computer-readable storage medium and computer program product proposed in the present application obtain three-dimensional point cloud data of the area to be detected by laser radar, and generate a two-dimensional image based on the three-dimensional point cloud data, so as to determine the vehicle contour data of each of the multiple vehicles parked in the area to be detected in the two-dimensional image, and screen out candidate storage locations located between two parked vehicles with geometric dimensions greater than or equal to the preset storage location geometric dimensions based on the vehicle contour data of the multiple parked vehicles, so as to mark all the screened candidate storage locations to construct a candidate storage location set in the area to be detected, and for the constructed candidate storage location set, further determine one or more target spatial storage locations in the candidate storage location set for parking the vehicle to be parked based on the geometric dimensions of the current vehicle to be parked and the geometric dimensions of each candidate storage location in the candidate storage location set.

[0045] In this way, the present application generates accurate three-dimensional point cloud data by scanning the surrounding environment based on the high-resolution and high-precision distance measurement capabilities of the laser radar, and identifies and locates the parking space based on the three-dimensional point cloud data of the area to be detected in the three-dimensional point cloud data. It can not only realize spatial storage position detection in situations where ultrasonic radars, cameras and other sensors fail, thereby avoiding the situation where ultrasonic radars or cameras are affected by the environment and cannot perform spatial storage position detection, but also improve the stability of spatial storage position detection in various environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of the steps of the spatial storage location detection method provided in some embodiments of the present application;

[0047] Figure 2 A schematic diagram of the steps of the spatial storage location detection method provided in the embodiment of the present application in other embodiments;

[0048] Figure 3 A schematic diagram of the steps of the spatial storage location detection method provided in the embodiment of the present application in some other embodiments;

[0049] Figure 4 A schematic flow chart of the detailed steps for screening candidate storage locations in an embodiment of a spatial storage location detection method provided in an embodiment of the present application;

[0050] Figure 5 The spatial storage location detection method provided for the embodiment of the present application involves a schematic diagram of a scene for determining a target parked vehicle;

[0051] Figure 6 A schematic diagram of a scenario involving determining candidate storage locations is provided for the spatial storage location detection method provided in the embodiment of the present application;

[0052] Figure 7 A schematic diagram of the steps of the spatial storage location detection method provided in the embodiment of the present application in some other embodiments;

[0053] Figure 8 A schematic diagram of the coordinate correspondence between the two-dimensional image and the three-dimensional point cloud data involved in the spatial storage location detection method provided in the embodiment of the present application;

[0054] Fig. 9 A schematic diagram of a spatial storage location detection algorithm flow chart for a spatial storage location detection method provided in an embodiment of the present application;

[0055] Fig.10 A schematic diagram of the structure of a spatial storage location detection device provided in an embodiment of the present application;

[0056] Fig.11 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0060] First, the overall concept of the spatial storage location detection method provided in the embodiment of the present application is explained.

[0061] With the rapid development of vehicle autonomous driving technology, the application of parking assistance systems in modern intelligent vehicles has become more and more common. The application of parking assistance systems can actively avoid collisions when the vehicle is parking at low speed. Therefore, in the low-speed and complex environment in the city, the application of parking assistance systems by vehicles has greatly improved parking efficiency and safety. However, with the sharp increase in the number of motor vehicles, the problem of insufficient parking spaces has become increasingly prominent. Therefore, it is particularly necessary to apply efficient and reliable space storage detection technology to assist vehicle parking. Efficient and reliable space storage detection technology can not only improve the utilization rate of parking spaces, but also alleviate the problem of limited parking resources and meet the needs of parking lots in terms of efficiency, safety and management.

[0062] Nowadays, the spatial storage location detection methods widely used on vehicles are mostly based on the detection of storage locations using sensors such as ultrasonic radar and cameras. However, although ultrasonic radar is widely used in parallel storage location detection, in the case of vertical storage locations, the detection accuracy is obviously insufficient due to the large incident angle between the ultrasonic radar and the side of the vehicle. The camera detects spatial storage locations based on vision. This method can provide rich image information, but it is very easily affected by ambient lighting conditions, resulting in poor performance in dark environments. In addition, the amount of calculation required for the camera to collect image data for detection is also relatively large, resulting in low overall efficiency. In addition, in the method of spatial storage location detection based on sensors such as short-range radar and laser scanners, although short-range radar and laser scanners can provide higher detection accuracy, these sensors have low angular accuracy and are very sensitive to the shape, direction and reflectivity of objects. They also have poor stability in some specific scenarios.

[0063] As mentioned above, the spatial storage location detection methods currently widely used on vehicles are difficult to provide sufficient reliability in complex environments, and thus there is an urgent need for a detection technology that can work stably in various environments to improve the stability of spatial storage location detection on vehicles.

[0064] Based on this, the embodiment of the present application provides a spatial storage location detection method, device, electronic device and storage medium, which is intended to perform vehicle spatial storage location detection based on laser radar, thereby improving the stability of spatial storage location detection. In the embodiment of the present application, three-dimensional point cloud data of the area to be detected is obtained by laser radar, and a two-dimensional image is generated based on the three-dimensional point cloud data, so that the vehicle contour data of each of the multiple vehicles parked in the area to be detected is determined in the two-dimensional image, and according to the vehicle contour data of the multiple parked vehicles, the candidate storage locations located between the two parked vehicles with geometric dimensions greater than or equal to the preset storage location geometric dimensions are screened out, so that all the screened candidate storage locations are marked to construct a candidate storage location set in the area to be detected, and for the constructed candidate storage location set, one or more target spatial storage locations for parking the vehicle to be parked in the candidate storage location set are further determined according to the geometric dimensions of the current vehicle to be parked and the geometric dimensions of each candidate storage location in the candidate storage location set.

[0065] In this way, since the laser radar itself can work stably under different lighting conditions, it can realize three-dimensional point cloud data collection without being affected by ambient light, and since the laser radar can provide centimeter-level measurement accuracy, it can realize accurate identification of the boundaries and shapes of objects. Therefore, the embodiment of the present application scans the surrounding environment based on the high-resolution and high-precision distance measurement capabilities of the laser radar to generate accurate three-dimensional point cloud data, and identifies and locates the parking space based on the three-dimensional point cloud data of the area to be detected in the three-dimensional point cloud data. It can not only realize spatial storage location detection in situations such as failure of ultrasonic radars, cameras and other sensors, thereby improving the stability of spatial storage location detection in various environments, but also improve the accuracy of the detected spatial storage locations based on high recognition rate and fast processing speed.

[0066] In addition, with the gradual decline in the cost of lidar and the development of multi-functional integration strategies, the way vehicles use lidar to detect spatial storage locations will become more economical and practical. Spatial storage location detection based on lidar will become an important direction of spatial storage location detection technology in future vehicle intelligent parking systems.

[0067] Next, the spatial storage location detection method, device, electronic device and storage medium provided in the embodiments of the present application are specifically described through the following embodiments, and the spatial storage location detection method provided in the embodiments of the present application is first described in detail.

[0068] It should be noted that the spatial storage location detection method provided in the embodiment of the present application relates to the field of vehicle technology. The spatial storage location detection method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be an on-board terminal on a vehicle, or can be a smart phone, tablet computer, laptop computer, desktop computer, etc. associated with the vehicle, and the terminal and the vehicle are associated with each other. The terminal can communicate with the vehicle based on the network to exchange data. The server side can be a backend server terminal device of the vehicle, which can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN) and cloud servers that provide basic cloud computing services such as big data and artificial intelligence platforms. The software can be an application that implements the spatial storage location detection method, a computer program, and a storage medium that carries the computer program. It should be understood that based on different design requirements of actual applications, in different feasible embodiments, the terminal, server, and software that use the spatial storage location detection method provided in the embodiments of the present application may of course also be in other forms not listed here, and the spatial storage location detection method provided in the embodiments of the present application does not specifically limit this.

[0069] In addition, the present application can also be used in many general or special computer system environments or configurations. For example: vehicles, personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, personal computers (PCs), minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0070] For ease of understanding and explanation, the following text will take the spatial storage location detection method provided by the embodiment of the present application as an example to describe in detail the various specific embodiments of the present application. In various specific implementations of the present application, the vehicle to which the spatial storage location detection method provided by the embodiment of the present application is applied is a vehicle to be parked. The implementation of the spatial storage location detection method provided by the embodiment of the present application in any of the above-mentioned forms of subject application can refer to the process of the vehicle application spatial storage location detection method described later.

[0071] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0072] Please refer to Figure 1 , Figure 1 The schematic diagram of the steps of the spatial storage location detection method in some embodiments provided in the present application embodiment. It should be understood that although Figure 1 The subsequent flowcharts of other steps show the execution order of some method steps, but based on the different design requirements of actual applications, the spatial storage location detection method provided in the embodiment of the present application can certainly adopt an execution order different from the method steps shown in the figure. That is, Figure 1 The order of the steps in the method shown does not constitute a limitation on the execution logic order of the spatial storage location detection method provided in the embodiment of the present application. Figure 1 Reasonable changes in the sequence of steps in the method shown should be included in the scope of protection of the spatial storage location detection method provided in the embodiments of the present application.

[0073] like Figure 1 As shown, in some embodiments, the space storage location detection method provided by the embodiment of the present application for the vehicle to be parked may include steps S101 to S104.

[0074] Step S101, generating a two-dimensional image based on three-dimensional point cloud data of the area to be detected, wherein the three-dimensional point cloud data of the area to be detected is obtained by a laser radar.

[0075] It should be noted that the area to be detected can be the parking environment where the vehicle to be parked is located, and the area in front of or around the vehicle to be parked. The vehicle to be parked performs a spatial location detection on the area to be detected to determine whether there is a target spatial location that can be used for parking in the area to be detected. In addition, the parking environment where the vehicle to be parked is located can be an environment without clear parking space markings, or the parking environment can also be an environment with parking space markings but the parked vehicle is not parked according to the markings, etc.

[0076] When the vehicle to be parked performs spatial storage location detection on the area to be detected in order to find the target spatial storage location that meets the parking conditions for parking, after obtaining the three-dimensional point cloud data of the area to be detected through its own configured laser radar, a two-dimensional image is generated based on the three-dimensional point cloud data of the area to be detected.

[0077] In some embodiments, after acquiring the three-dimensional point cloud data of the area to be detected, the vehicle to be parked can extract the ground point cloud from the three-dimensional point cloud data of the area to be detected, and calculate the average ground elevation value corresponding to the ground point cloud. Then, the vehicle to be parked extracts the non-ground point cloud based on the average ground elevation value corresponding to the ground point cloud, and obtains a two-dimensional image of the non-ground point by gridding and binarizing the non-ground point data within a fixed elevation value range.

[0078] It should be noted that, considering the time delay when acquiring three-dimensional point cloud data by scanning the spatial environment with a laser radar, the vehicle to be parked can specifically use the minimum elevation value to filter out ground points and extract non-ground point clouds from the three-dimensional point cloud data of the detection area. In addition, for the disordered non-ground point cloud data, the vehicle to be parked first sorts the non-ground point cloud so that the non-ground point cloud is distributed in the corresponding grid, and by corresponding the x value of the non-ground point cloud data to the column value of the grid image, and the y value of the non-ground point cloud data to the row value of the grid image, the grid point corresponding to the non-ground point cloud data whose elevation value matches the vehicle height information is set to a preset grayscale value, for example, the preset grayscale value can be 255, thereby generating a two-dimensional image of the three-dimensional point cloud data of the detection area.

[0079] Step S102, determining vehicle contour data of a plurality of parked vehicles in the two-dimensional image.

[0080] After generating a two-dimensional image of the three-dimensional point cloud data of the area to be detected, the vehicle contour data of multiple parked vehicles in the area to be detected are further determined from the two-dimensional image based on the geometric dimensions of the vehicle.

[0081] In some embodiments, the vehicle to be parked can be obtained by smoothing the two-dimensional image, then extracting the contour of the image corresponding to the non-ground point cloud in the two-dimensional image, and then fitting a rectangular frame for each extracted contour area, and filtering out non-vehicle contour data based on the geometric dimensions of the rectangular frame and the geometric dimensions of the vehicle (such as the standard length, bandwidth, height and other information of the vehicle), thereby obtaining the contours and corresponding rectangular frames of multiple vehicles currently parked in the area to be detected, and the contours and corresponding rectangular frames are the vehicle contour data of the parked vehicle.

[0082] It should be noted that since the grid of non-ground point cloud data in the two-dimensional image is discretized, the vehicle to be parked can be obtained by first dilating the two-dimensional image to obtain a two-dimensional image with smooth features, and then further extracting the contour of the smoothed two-dimensional image, and fitting the rectangular frame of the non-ground point cloud in each extracted contour to obtain the contour points and rectangular frames of obstacles (such as pillars and stacked items, etc.) and parked vehicles. After that, the contour points and rectangular frame data of the parked vehicle are screened out as vehicle contour data based on the vehicle's height, length and width and other geometric dimensions and aspect ratio and other geometric information.

[0083] Step S103, based on the vehicle profile data of the plurality of parked vehicles, screening candidate storage locations located between two adjacent parked vehicles to construct a set of candidate storage locations in the area to be detected, wherein the geometric dimensions of the candidate storage locations are greater than or equal to the geometric dimensions of the preset storage locations.

[0084] After the vehicle to be parked determines the vehicle contour data of multiple parked vehicles in the two-dimensional image, further based on the vehicle contour data of the multiple parked vehicles, candidate storage locations whose geometric dimensions are greater than or equal to the geometric dimensions of the preset storage locations are screened out from the space between two adjacent parked vehicles, thereby marking all the screened candidate vehicles to construct a set of candidate storage locations in the area to be detected.

[0085] It should be noted that the geometric dimensions of the preset parking space may be based on the geometric dimensions of a standard parking space, for example, a length of 5 meters and a width of 2.5 meters; or a length of 6 meters and a width of 2.8 meters, and so on.

[0086] In some embodiments, the vehicle to be parked can obtain the geometric dimensions of the space between the two adjacent parked vehicles by traversing the vehicle contour data of any two adjacent parked vehicles. Then, the vehicle to be parked compares the geometric dimensions of the space between the two adjacent parked vehicles with the geometric dimensions of the preset storage location, thereby taking the space between the two adjacent parked vehicles that is greater than or equal to the geometric dimensions of the preset storage location as a candidate storage location, thereby constructing a set of candidate storage locations in the area to be detected.

[0087] Step S104, determining a target space storage location in the candidate storage location set according to the geometric dimensions of the vehicle to be parked and the geometric dimensions of each candidate storage location in the candidate storage location set, wherein the target space storage location is used to park the vehicle to be parked.

[0088] After constructing a set of candidate storage locations in the area to be detected, the geometric dimensions of the vehicle to be parked are compared with the geometric dimensions of each candidate storage location in the candidate storage location set. One or more candidate storage locations in the candidate storage location set that can be used to park the vehicle to be parked are used as the target spatial storage locations obtained by the current spatial storage location detection for the area to be detected.

[0089] For example, it is assumed that the geometric dimensions of the preset storage locations used by the to-be-parked vehicle when constructing the candidate storage location set in the to-be-detected area are 5 meters in length and 2.5 meters in width, so that the space between two adjacent parked vehicles with a length greater than or equal to 5 meters and a width greater than or equal to 2.5 meters is used as a candidate storage location to construct the candidate storage location set in the to-be-detected area. In this way, when the geometric dimensions of the to-be-parked vehicle are 4.9 meters in length and 1.9 meters in width, the to-be-parked vehicle compares its own geometric dimensions with the geometric dimensions of each candidate storage location in the candidate storage location set, and it can be determined that all candidate storage locations in the candidate storage location set can be used to park the to-be-parked vehicle, so that all candidate storage locations in the candidate storage location set are determined as the target spatial storage locations obtained by the current spatial storage location detection for the to-be-detected area. Alternatively, when the geometric dimensions of the vehicle to be parked are 5.2 meters in length and 2 meters in width, the vehicle to be parked will compare its own geometric dimensions with the geometric dimensions of each candidate storage location in the candidate storage location set, so that it can be determined that the candidate storage locations in the candidate storage location set whose length is greater than or equal to 5.2 meters can be used to park the vehicle to be parked, thereby determining the candidate storage locations in the candidate storage location set whose length is greater than or equal to 5.2 meters and whose width is greater than or equal to 2 meters as the target spatial storage locations obtained by the current spatial storage location detection for the area to be detected.

[0090] In an embodiment of the present application, three-dimensional point cloud data of the area to be detected is obtained based on a laser radar using the vehicle to be parked, and a two-dimensional image is generated based on the three-dimensional point cloud data, so as to determine the vehicle contour data of each of the multiple vehicles already parked in the area to be detected in the two-dimensional image, and based on the vehicle contour data of the multiple parked vehicles, a candidate storage location located between two parked vehicles and having a geometric dimension greater than or equal to a preset storage location geometric dimension is screened out, so as to mark all the screened candidate storage locations to construct a candidate storage location set in the area to be detected, and for the constructed candidate storage location set, one or more target space storage locations in the candidate storage location set for parking the vehicle to be parked are further determined based on the geometric dimension of the current vehicle to be parked and the geometric dimension of each candidate storage location in the candidate storage location set.

[0091] In this way, since the laser radar itself can work stably under different lighting conditions, it can realize three-dimensional point cloud data collection without being affected by ambient light, and since the laser radar can provide centimeter-level measurement accuracy, it can realize accurate identification of the boundaries and shapes of objects. Therefore, the embodiment of the present application scans the surrounding environment based on the high-resolution and high-precision distance measurement capabilities of the laser radar to generate accurate three-dimensional point cloud data, and identifies and locates the parking space based on the three-dimensional point cloud data of the area to be detected in the three-dimensional point cloud data. It can not only realize spatial storage location detection in situations such as failure of ultrasonic radars, cameras and other sensors, thereby improving the stability of spatial storage location detection in various environments, but also improve the accuracy of the detected spatial storage locations based on high recognition rate and fast processing speed.

[0092] When a vehicle to be parked is in a parking environment and a spatial location detection is performed on an area to be detected in the environment, the entire environment can be scanned by a laser radar to obtain three-dimensional point cloud data of the area to be detected in the environment.

[0093] Please refer to Figure 2 , Figure 2 A schematic diagram of the step flow of the spatial storage location detection method provided in the embodiment of the present application in other embodiments.

[0094] like Figure 2 As shown, in some embodiments, the spatial storage location detection method provided by the embodiment of the present application for the vehicle to be parked may further include steps S201 to S202 before the above-mentioned step S101 generates a two-dimensional image based on the three-dimensional point cloud data of the area to be detected.

[0095] Step S201, scanning the environment where the parked vehicle is located by laser radar to obtain three-dimensional point cloud data of the environment.

[0096] When the space storage position detection is performed on the area to be detected in the parking environment where the vehicle to be parked is located, the entire environment where the vehicle to be parked is first scanned by a laser radar, thereby obtaining the three-dimensional point cloud data of the environment where the vehicle to be parked is located.

[0097] In some embodiments, a single laser radar installed on the roof or front of the vehicle (such as the upper side of the vehicle's front windshield, the middle area of ​​the vehicle's front grille, etc.) can scan the entire environment in which the vehicle is parked, with a length of about 100 to 200 meters and a width of about 5 to 20 meters in front of the front of the vehicle, thereby obtaining three-dimensional point cloud data of the environment.

[0098] Step S202: extracting three-dimensional point cloud data of the area to be detected from the three-dimensional point cloud data of the environment according to a preset point cloud data detection range.

[0099] It should be noted that the size information of the preset point cloud data detection range is consistent with the size information of the area to be detected. The vehicle to be parked can pre-configure the geometric size of the fixed spatial range of the area to be detected, and use the geometric size as the size information of the point cloud data detection range.

[0100] After the vehicle to be parked scans the environment through the lidar to obtain the three-dimensional point cloud data of the environment, the three-dimensional point cloud data of a fixed spatial range is extracted from the three-dimensional point cloud data of the environment according to the geometric dimensions of the preset point cloud data detection range, and the extracted three-dimensional point cloud data is used as the three-dimensional point cloud data of the area to be detected that requires spatial storage location detection.

[0101] For example, considering that the point cloud density of the three-dimensional point cloud of the environment will decrease as the detection distance increases, the length of the three axes of the point cloud data can be set for the vehicle to be parked as the detection range of the point cloud data, so as to extract the point cloud data of a fixed spatial range based on the length of the three axes as the three-dimensional point cloud data of the area to be detected. For example, the lengths of the three axes of the point cloud data of the vehicle to be parked are: 50 meters for the x-axis, 10 meters for the y-axis, and 3 meters for the z-axis. Therefore, after the laser radar can scan the environment in front of the vehicle with a length of about 100 to 200 meters and a width of about 5 to 20 meters to obtain the three-dimensional point cloud data of the environment, the vehicle to be parked can extract the three-dimensional point cloud data of the fixed spatial range in front of the vehicle to be parked: 50 meters long, 10 meters wide and 3 meters high from the three-dimensional point cloud data of the environment according to the length of 50 meters for the x-axis, 10 meters for the y-axis and 3 meters for the z-axis, and use the three-dimensional point cloud data as the three-dimensional point cloud data of the area to be detected for subsequent spatial storage location detection.

[0102] In this embodiment, a single forward-looking laser radar is used to obtain environmental three-dimensional point cloud data for the vehicle to be parked, and then three-dimensional point cloud data of a fixed spatial range is extracted from the environmental three-dimensional point cloud data for spatial storage location detection. This can ensure the accuracy of spatial storage location detection while saving the hardware cost of the vehicle.

[0103] In the process of spatial storage location detection of the vehicle to be parked based on the three-dimensional point cloud data of the area to be detected, after generating a two-dimensional image based on the three-dimensional point cloud data, the two-dimensional image can be further divided based on the extension line of the direction of the front of the vehicle to be parked, and then the vehicle contour data can be extracted for each divided image area, so as to perform subsequent spatial storage location detection operations.

[0104] Please refer to Figure 3 , Figure 3 A schematic diagram of the step flow of the spatial storage location detection method provided in the embodiment of the present application in some other embodiments.

[0105] like Figure 3 As shown, in some embodiments, the space storage location detection method provided by the embodiment of the present application is applied to the vehicles to be parked. In the above-mentioned step S102, before determining the vehicle contour data of multiple parked vehicles in the two-dimensional image, it can also include steps S301 to S302.

[0106] Step S301, according to the front orientation of the vehicle to be parked, determine a first image area and a second image area in the two-dimensional image, the first image area being the image area located on one side of the extension line of the front orientation, and the second image area being the image area located on the other side of the extension line.

[0107] After generating a two-dimensional image of the vehicle to be parked based on the three-dimensional point cloud data of the area to be detected, the vehicle to be parked is further divided into the two-dimensional image according to the front direction of the vehicle to be parked, with the extension line of the front direction as the dividing line, thereby obtaining a first image area located on one side of the extension line of the front direction and a second image area located on the other side of the extension line of the front direction.

[0108] In some embodiments, when the vehicle to be parked extracts three-dimensional point cloud data within a fixed space in front of the front of the vehicle to be parked to generate a two-dimensional image, the vehicle to be parked can also use the central axis of the pixel row of the two-dimensional image as a dividing line to divide the two-dimensional image into a first image area located on the left side of the central axis and a second image area located on the right side of the central axis.

[0109] Step S302: determining the vehicle outline data of the parked vehicles located in the first image area or the second image area as the vehicle outline data of the plurality of parked vehicles.

[0110] After the two-dimensional image is divided into the first image area and the second image area, the vehicle contour data of the vehicle to be parked can be extracted for the first image area and the second image area respectively, and then the spatial storage location detection is performed based on the extracted vehicle contour data. For example, the vehicle contour data of the vehicle to be parked is obtained for the first image area, so that the vehicle contour data of the parked vehicle in the first image area is used as the vehicle contour data of multiple parked vehicles in the area to be detected, and then the subsequent spatial storage location detection operation is performed based on the vehicle contour data of the multiple parked vehicles. For another example, the vehicle contour data of the vehicle to be parked is obtained for the second image area, so that the vehicle contour data of the parked vehicle in the second image area is used as the vehicle contour data of multiple parked vehicles in the area to be detected, and then the subsequent spatial storage location detection operation is performed based on the vehicle contour data of multiple parked vehicles.

[0111] In this embodiment, the vehicle to be parked can be processed by partitioning the two-dimensional image to extract the vehicle contour data from the first image area and the second image area of ​​the two-dimensional image respectively, so as to perform subsequent spatial storage location detection on the extracted vehicle contour data of multiple parked vehicles. In this way, when there are a large number of vehicles currently parked in the area to be detected, the spatial storage location detection of the vehicle to be parked based on the partition of the area to be parked can achieve faster detection of the target spatial storage location from a part of the area to be detected, thereby improving the efficiency of detecting the spatial storage location.

[0112] After the vehicle contour data of multiple parked vehicles are determined from the two-dimensional image, the vehicle contour data of the multiple parked vehicles can be sorted, and then the vehicle contour data of two adjacent parked vehicles are taken in turn to determine whether the space between the two adjacent parked vehicles is a candidate storage location, thereby constructing a set of candidate storage locations in the area to be detected.

[0113] Please refer to Figure 4 , Figure 4 A schematic flow chart of the detailed steps for screening candidate storage locations in an embodiment of a spatial storage location detection method provided in an embodiment of the present application.

[0114] like Figure 4 As shown, in some embodiments, in the above step S103, screening a candidate storage location between two adjacent parked vehicles according to the vehicle profile data of the plurality of parked vehicles may include steps S401 to S403:

[0115] Step S401, determining the maximum values ​​of the vehicle profile data of the plurality of parked vehicles in pixel rows and pixel columns.

[0116] It should be noted that the maximum values ​​of the vehicle contour data of multiple parked vehicles on pixel rows and pixel columns can be the vehicle contour data of multiple parked vehicles, each with a maximum row value and a minimum row value on pixel rows, and the vehicle contour data of multiple parked vehicles, each with a maximum column value and a minimum column value on pixel columns.

[0117] When the vehicle to be parked can determine the vehicle contour data of the parked vehicle in the two-dimensional image, for each time of vehicle contour data extracted, the maximum value of the vehicle contour data on the pixel row is further extracted, and the maximum value of the vehicle contour data on the pixel column is extracted. In this way, the maximum values ​​of the vehicle contour data of multiple parked vehicles on the pixel row and the pixel column can be determined.

[0118] Step S402, based on the maximum values ​​of the vehicle contour data of the multiple parked vehicles on the pixel rows and the pixel columns, determine a plurality of target parked vehicles arranged along the front direction of the vehicle to be parked among the multiple parked vehicles, wherein the target parked vehicle is a parked vehicle closest to the extension line of the front direction.

[0119] After determining the maximum values ​​of vehicle contour data of multiple parked vehicles on pixel rows and pixel columns, the vehicle to be parked can screen the multiple parked vehicles according to the maximum values ​​of the vehicle contour data on pixel rows and the maximum values ​​of the vehicle contour data on pixel columns, thereby determining multiple target parked vehicles that are arranged along the front direction of the vehicle to be parked and closest to the extension line of the front direction among the multiple parked vehicles.

[0120] In some embodiments, the above step S402, determining, from among the plurality of parked vehicles, a plurality of target parked vehicles arranged along the front direction of the vehicle to be parked, according to the maximum values ​​of the vehicle profile data of the plurality of parked vehicles on the pixel rows and the pixel columns, may include:

[0121] The plurality of parked vehicles are sorted in a first pixel direction according to maximum values ​​of the vehicle contour data of the plurality of parked vehicles in the first pixel direction, wherein the first pixel direction is a pixel direction in the pixel rows and the pixel columns that is perpendicular to the vehicle head direction.

[0122] The maximum values ​​of the vehicle contour data of the multiple parked vehicles on the pixel row and the pixel column of the vehicle to be parked are used. When screening the multiple parked vehicles, when the pixel direction of the pixel row is perpendicular to the front direction of the vehicle to be parked, the vehicle to be parked takes the pixel direction of the pixel row as the first pixel direction, so that the vehicle contour data of the multiple parked vehicles are sorted in the first pixel direction in the order of increasing or decreasing maximum values ​​of the vehicle contour data of the multiple parked vehicles in the first pixel direction.

[0123] In some embodiments, when the multiple parked vehicles are parked vehicles with their front ends facing left, the vehicle to be parked sorts the vehicle contour data of the multiple parked vehicles along the direction of maximum increase of the vehicle contour data of the multiple parked vehicles in the first pixel direction.

[0124] In other embodiments, when the multiple parked vehicles are parked vehicles with their front ends facing to the right of the vehicle to be parked, the vehicle to be parked sorts the vehicle contour data of the multiple parked vehicles along a direction in which the maximum value of the vehicle contour data of the multiple parked vehicles in the first pixel direction decreases.

[0125] An overlapping area between a first parked vehicle and a second parked vehicle is determined according to the sorting in the first pixel direction, the first parked vehicle and the second parked vehicle are adjacent in the sorting, and a distance between the first parked vehicle and the extension line is smaller than a distance between the second parked vehicle and the extension line.

[0126] After sorting the vehicle contour data of the plurality of parked vehicles in the first pixel direction, the vehicle to be parked further sequentially obtains the vehicle contour data of two adjacent first parked vehicles and second parked vehicles according to the sorting, wherein the distance between the first parked vehicle and the extension line of the vehicle head direction of the vehicle to be parked is smaller than the distance between the second parked vehicle and the extension line. Then, the vehicle to be parked determines the overlapping area between the first parked vehicle and the second parked vehicle based on the vehicle contour data of the first parked vehicle and the vehicle contour data of the second parked vehicle.

[0127] It should be noted that the overlapping area between the first parked vehicle and the second parked vehicle is the distribution area of ​​the second parked vehicle corresponding to the overlapping area of ​​the vehicle contour data of the first parked vehicle and the vehicle contour data of the second parked vehicle in the second pixel direction.

[0128] When the overlapping area between the first parked vehicle and the second parked vehicle meets a preset condition, the second parked vehicle is screened out from the plurality of parked vehicles.

[0129] The plurality of target parked vehicles include parked vehicles after the second parked vehicle is screened out.

[0130] It should be noted that the vehicle to be parked performs overlapping area detection on the adjacent first parked vehicle and the second parked vehicle each time for multiple parked vehicles, and after the overlapping area meets the preset conditions and the second parked vehicle is screened out, the vehicle to be parked determines all the remaining parked vehicles among the multiple parked vehicles as target parked vehicles.

[0131] In addition, the preset condition is that the ratio between the overlapping area and the total area is less than a preset threshold, and the total area is the distribution area of ​​two adjacent parked vehicles associated with the overlapping area. That is, the preset condition is that the ratio between the overlapping area between the first parked vehicle and the second parked vehicle and the distribution area of ​​the first parked vehicle and the second parked vehicle is less than the preset threshold. The preset threshold can be any one of 0.5, 0.4, 0.3 and 0.2.

[0132] For the overlapping area between the first parked vehicle and the second parked vehicle, the vehicle to be parked calculates the ratio between the overlapping area and the distribution areas of the first parked vehicle and the second parked vehicle, and detects whether the ratio is less than a preset threshold value. When it is detected that the ratio is less than the preset threshold value, it is determined that the overlapping area between the first parked vehicle and the second parked vehicle meets the preset condition, thereby screening the second parked vehicle from the multiple parked vehicles.

[0133] For example, please refer to Figure 5 , Figure 5 The spatial storage location detection method provided for the embodiment of the present application involves determining a scene schematic diagram of a target parked vehicle.

[0134] like Figure 5 As shown, a two-dimensional image is generated for the vehicle A to be parked based on the three-dimensional point cloud data of the area to be detected, and vehicle contour data of multiple parked vehicles are extracted from the two-dimensional image. The two-dimensional image is divided into a first image area located on the left side of the extension line and a second image area located on the right side of the extension line, with the extension line of the front direction of the vehicle A to be parked as the boundary.

[0135] For the multiple parked vehicles in the first image area on the left side of the extension line, the vehicle to be parked sorts the vehicle contour data of the multiple parked vehicles in the pixel row direction (first pixel direction, the first pixel direction is perpendicular to the front direction of the vehicle A to be parked) along the direction in which the maximum value of the vehicle contour data on the pixel row increases successively. Then, the vehicle to be parked A extracts two adjacent first parked vehicles B and second parked vehicles C (the distance between the first parked vehicle B and the extension line is smaller than the distance between the second parked vehicle C and the extension line) according to the maximum value of the vehicle contour data on the pixel row, and detects the overlapping area ( Figure 5 The distribution area of ​​the second parked vehicle C mapped on the two-dimensional image (the overlapping area shown by the bold dashed line in the figure) is calculated, and the ratio between the distribution area and the distribution areas of the first parked vehicle B and the second parked vehicle C on the two-dimensional image is calculated. Therefore, when it is detected that the ratio is less than the preset threshold value 0.5, the vehicle to be parked A screens out the second parked vehicle C from the multiple parked vehicles in the first image area on the left side of the extension line. In this way, all the remaining parked vehicles except the second parked vehicle C among the multiple parked vehicles in the first image area on the left side of the extension line are the multiple target parked vehicles in the first image area on the left side of the extension line.

[0136] For the multiple parked vehicles in the second image area on the right side of the extension line, the vehicle to be parked sorts the vehicle contour data of the multiple parked vehicles in the direction of pixel rows in a direction in which the maximum value of the vehicle contour data on the pixel row decreases in sequence. Then, the vehicle to be parked A extracts two adjacent first parked vehicles B and second parked vehicles C according to the maximum value of the vehicle contour data on the pixel row, detects the vehicle contour data of the first parked vehicle B and the vehicle contour data of the second parked vehicle C, and their respective overlapping areas in the direction of pixel columns ( Figure 5 The distribution area of ​​the second parked vehicle C mapped on the two-dimensional image (the overlap area shown by the bold dashed line in the figure) is calculated, and the ratio between the distribution area and the distribution area of ​​the first parked vehicle B and the second parked vehicle C on the two-dimensional image is calculated. Therefore, when it is detected that the ratio is less than the preset threshold value 0.5, the vehicle to be parked A screens out the second parked vehicle C from the multiple parked vehicles in the second image area on the right side of the extension line. In this way, all the parked vehicles remaining in the multiple parked vehicles in the second image area on the right side of the extension line except all the second parked vehicles C are the multiple target parked vehicles in the second image area on the right side of the extension line.

[0137] Step S403: screening a candidate storage location between two adjacent target parked vehicles according to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles in the pixel row and the pixel column.

[0138] After determining multiple target parked vehicles that are arranged along the front direction of the vehicle to be parked and closest to the extension line of the front direction among multiple parked vehicles, the vehicle contour data of two adjacent target parked vehicles are taken in sequence according to the maximum values ​​of the vehicle contour data of the multiple target parked vehicles on the pixel rows and the maximum values ​​of the vehicle contour data of the multiple target parked vehicles on the pixel columns, and based on the vehicle contour data of the two adjacent target parked vehicles, the space between the two adjacent target parked vehicles is screened out as a candidate storage location.

[0139] In some embodiments, the above step S403, screening a candidate storage location between two adjacent target parked vehicles according to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles on the pixel row and the pixel column, may include:

[0140] According to the maximum values ​​of the vehicle contour data of the plurality of target parked vehicles in the second pixel direction, the plurality of parked vehicles are sorted in the second pixel direction, wherein the second pixel direction is another pixel direction in the pixel rows and the pixel columns except the first pixel direction.

[0141] For multiple target parked vehicles, when the pixel direction of the pixel row of the vehicle to be parked is perpendicular to the front direction of the vehicle to be parked, the vehicle to be parked uses the pixel direction of the pixel row as the first pixel direction and uses the pixel direction of the pixel column as the second pixel direction, so that the vehicle contour data of the multiple target parked vehicles are sorted in the second pixel direction in the order of increasing or decreasing maximum values ​​of the vehicle contour data of the multiple target parked vehicles in the second pixel direction.

[0142] Determining an overlapping area between a third parked vehicle and a fourth parked vehicle according to the sorting in the second pixel direction, the third parked vehicle and the fourth parked vehicle are target parked vehicles that are adjacent in the sorting, and a minimum distance between the third parked vehicle and the extension line is smaller than a minimum distance between the fourth parked vehicle and the extension line;

[0143] After sorting the vehicle contour data of multiple target parked vehicles in the second pixel direction, the vehicle to be parked sequentially obtains the vehicle contour data of two adjacent third parked vehicles and fourth parked vehicles in order according to the sorting, wherein the minimum distance between the third parked vehicle and the extension line of the vehicle to be parked where the front direction is located is smaller than the minimum distance between the fourth parked vehicle and the extension line. Then, the vehicle to be parked determines the overlapping area between the third parked vehicle and the fourth parked vehicle based on the vehicle contour data of the third parked vehicle and the vehicle contour data of the fourth parked vehicle.

[0144] It should be noted that the overlapping area between the third parked vehicle and the fourth parked vehicle is the distribution area of ​​the fourth parked vehicle corresponding to the overlapping area of ​​the vehicle contour data of the third parked vehicle and the vehicle contour data of the fourth parked vehicle in the first pixel direction.

[0145] When the overlapping area between the third parked vehicle and the fourth parked vehicle meets a preset condition, screening out the fourth parked vehicle from the plurality of target parked vehicles;

[0146] The candidate storage location is a space between adjacent target parked vehicles among the plurality of target parked vehicles after the fourth parked vehicle is screened out.

[0147] It should be noted that, for the vehicle to be parked, the adjacent third parked vehicle and the fourth parked vehicle are taken for overlapping area detection each time for multiple target parked vehicles, and after the fourth parked vehicle is screened out when the overlapping area meets the preset conditions, the space between two adjacent target parked vehicles among all the remaining target parked vehicles among the multiple target parked vehicles is used as a candidate storage location.

[0148] In addition, the preset condition is that the ratio between the overlapping area and the total area is less than a preset threshold, and the total area is the distribution area of ​​two adjacent parked vehicles associated with the overlapping area. That is, the preset condition is that the ratio between the overlapping area between the third parked vehicle and the fourth parked vehicle and the distribution area of ​​the third parked vehicle and the fourth parked vehicle is less than the preset threshold.

[0149] For the overlapping area between the third parked vehicle and the fourth parked vehicle, the vehicle to be parked calculates the ratio between the overlapping area and the distribution area of ​​the third parked vehicle and the fourth parked vehicle, and detects whether the ratio is less than a preset threshold value. If the ratio is detected to be less than the preset threshold value, it is determined that the overlapping area between the third parked vehicle and the fourth parked vehicle meets the preset condition, thereby filtering the fourth parked vehicle from the plurality of parked vehicles. Afterwards, the vehicle to be parked determines the space between two adjacent target parked vehicles as a candidate storage location among all the remaining target parked vehicles among the plurality of target parked vehicles.

[0150] It should be noted that the overlapping area between the first parked vehicle and the second parked vehicle is the distribution area of ​​the second parked vehicle corresponding to the overlapping area of ​​the vehicle contour data of the first parked vehicle and the vehicle contour data of the second parked vehicle in the second pixel direction.

[0151] For example, please refer to Figure 6 , Figure 6 The spatial storage location detection method provided for the embodiment of the present application involves a scenario schematic diagram for determining candidate storage locations.

[0152] like Figure 6 As shown, for multiple target parked vehicles in the image area on either side of the extension line, the vehicle A to be parked sorts the vehicle contour data of the multiple target parked vehicles in the pixel row direction (second pixel direction) along the direction in which the maximum value of the vehicle contour data on the pixel column increases in sequence. Then, the vehicle A to be parked extracts two adjacent third parked vehicles D and fourth parked vehicles E (the minimum spacing between the third parked vehicle D and the extension line is smaller than the minimum spacing between the fourth parked vehicle E and the extension line) according to the maximum value of the vehicle contour data on the pixel row, and detects the overlapping area ( Figure 6 The distribution area of ​​the fourth parked vehicle E mapped on the two-dimensional image (the overlapping area shown by the bold dashed line in the figure) is calculated, and the ratio between the distribution area and the distribution areas of the third parked vehicle D and the fourth parked vehicle E on the two-dimensional image is calculated. Therefore, when it is detected that the ratio is less than the preset threshold value 0.5, the vehicle A to be parked screens out the fourth parked vehicle E from the multiple target parked vehicles in the first image area on the left side of the extension line. Afterwards, for the multiple target parked vehicles remaining after the fourth parked vehicle E is removed, the vehicle to be parked selects two adjacent target parked vehicles in turn, and uses the space between the two adjacent target parked vehicles as the candidate storage location ( Figure 6 The spatial area shown by the bold solid line in the figure is constructed to obtain a set of candidate storage locations in the entire area to be detected.

[0153] In this embodiment, the maximum values ​​of the vehicle contour data of multiple parked vehicles in the area to be detected on the pixel rows and pixel columns are determined by the vehicle to be parked. First, according to the maximum values ​​of the vehicle contour data of multiple parked vehicles on the pixel rows and pixel columns, multiple target parked vehicles arranged along the front direction of the vehicle to be parked and closest to the extension line of the front direction are determined from the multiple parked vehicles. Then, according to the maximum values ​​of the vehicle contour data of multiple target parked vehicles on the pixel rows and pixel columns, the candidate storage locations located between two adjacent target parked vehicles are screened out, thereby constructing a candidate storage location set for the area to be detected. In this way, after scanning the surrounding environment based on the high-resolution and high-precision distance measurement capabilities of the laser radar to generate accurate three-dimensional point cloud data, the two-dimensional image corresponding to the three-dimensional point cloud data is processed to identify the parking space in the area to be detected, thereby improving the accuracy of spatial storage location detection for the area to be detected.

[0154] After constructing a set of candidate storage locations in the area to be detected, and further determining one or more target spatial storage locations in the candidate storage location set based on the geometric dimensions of the current vehicle to be parked and the geometric dimensions of the candidate storage locations, the vehicle to be parked can also be combined with ultrasonic radar and / or image acquisition device to further compare the storage location information of the target spatial storage locations detected, thereby further improving the accuracy of spatial storage location detection.

[0155] Please refer to Figure 7 , Figure 7 A schematic diagram of the step flow of the spatial storage location detection method provided in the embodiment of the present application in some other embodiments.

[0156] like Figure 7 As shown, in some embodiments, when the vehicle to be parked executes the spatial storage location detection method provided in the embodiments of the present application, in the above-mentioned step S104, after the target spatial storage location is determined in the candidate storage location set based on the geometric dimensions of the vehicle to be parked and the geometric dimensions of each candidate storage location in the candidate storage location set, steps S701 to S702 may also be included.

[0157] Step S701, comparing the target spatial storage location with the spatial storage location to be confirmed in the area to be detected, wherein the spatial storage location to be confirmed is a storage location obtained by performing spatial storage location detection on the area to be detected based on an ultrasonic radar, or the spatial storage location to be confirmed is a storage location obtained by performing spatial storage location detection on the area to be detected based on an image acquisition device;

[0158] In addition to the spatial storage location detection of the area to be detected based on the laser radar, the vehicle to be parked can also perform spatial storage location detection of the area to be detected by ultrasonic radar and / or image acquisition device (such as camera). In this way, when the vehicle to be parked obtains one or more spatial storage locations to be confirmed by performing spatial storage location detection of the area to be detected based on the ultrasonic radar, the vehicle to be parked can determine one or more target spatial storage locations that can be used to park the vehicle to be parked in the candidate storage location set, and then compare the information of the target spatial storage locations with the spatial storage locations to be confirmed in turn.

[0159] Step S702: When the information of the target space storage location is consistent with the information of the space storage location to be confirmed, assisting the vehicle to be parked in parking according to the target space storage location.

[0160] After the vehicle to be parked compares information of one or more target spatial storage locations in the candidate storage location set with the spatial storage locations to be confirmed obtained by spatial storage location detection based on ultrasonic radar and / or image acquisition device, if the geometric dimensions of one or more target spatial storage locations obtained by the comparison of the vehicle to be parked are consistent with the geometric dimensions of the spatial storage locations to be confirmed (or the error is less than a threshold), the vehicle to be parked can use the one or more target spatial storage locations as priority parking locations for the vehicle to be parked, and upon receiving permission from the user of the vehicle to be parked, select the target spatial storage location closest to the vehicle to be parked or the target spatial storage location with the largest geometric dimensions to assist the vehicle to be parked in dialing into the target spatial storage location.

[0161] In this embodiment, the vehicle to be parked further uses ultrasonic radar and / or image acquisition device to perform spatial storage location detection on the detection area, so that after the target spatial storage location is determined in the candidate storage location set, the target spatial storage location is further compared with the spatial storage location detected by the ultrasonic radar and / or image acquisition device for location information, so that the accuracy of spatial storage location detection in the detection area can be further improved. In addition, when the geometric dimensions of the vehicle to be parked in the target spatial storage location are consistent with the geometric dimensions of the spatial storage location detected by the ultrasonic radar and / or image acquisition device, the vehicle to be parked is assisted to be dialed into the target spatial storage location, and the vehicle loss caused by parking when a single radar detects an error in the spatial storage location can also be avoided.

[0162] Please refer to Figure 8 and Fig. 9 , Figure 8 A schematic diagram of the coordinate correspondence between the two-dimensional image and the three-dimensional point cloud data involved in the spatial storage location detection method provided in the embodiment of the present application, Fig. 9 This is a schematic diagram of a spatial storage location detection algorithm flow chart of the spatial storage location detection method provided in the embodiment of the present application. Figure 8 and Fig. 9 A preferred embodiment of the spatial storage location detection method provided in the embodiment of the present application is proposed for a vehicle to be parked.

[0163] First, after the vehicle to be parked obtains the three-dimensional point cloud data of the current environment through any type of laser radar (such as mechanical or solid-state laser radar), it traverses the three-dimensional point cloud data of the environment to determine whether the x, y, and z values ​​of each point are within the fixed spatial range of the set to be detected, and retains the point cloud within the fixed spatial range to obtain the three-dimensional point cloud data rangPoints of the area to be detected. After that, the vehicle to be parked discretizes the three-dimensional point cloud data rangPoints to obtain the corresponding grid, and counts the maximum and minimum elevation values ​​of the point set in each grid, and selects the points in the grid that meet the maximum and minimum elevation value difference conditions as the ground points groundPoints, and the remaining points as non-ground points nongroundPoints, and calculates the average elevation value ground_z of the ground point set. Then, the vehicle to be parked is as follows Figure 8 The coordinate correspondence shown in the figure is based on the fixed spatial range and grid size to construct a two-dimensional image mask, and by traversing the non-ground points nongroundPoints, the x value corresponds to the column col and the y value corresponds to the row row. When the elevation value of the traversed point cloud meets the height information of the vehicle, the (row, col) image grid point is set to 255, and then the two-dimensional image mask of the three-dimensional point cloud data rangPoints is obtained.

[0164] Afterwards, the two-dimensional image mask of the vehicle to be parked is first expanded using the dilate function in the open source computer vision library (OpenCV), and then the findContours function is used to extract the contours corresponding to all objects (including obstacles and vehicles) in the two-dimensional image mask and the data points contours within the contours. Then, the minAreaRect function is further used to fit the obstacle contours contours to obtain the corresponding rects data; the length and area of ​​the minimum circumscribed rectangle of the object are obtained based on the rects data of the object, and the vehicle data consistent with the vehicle geometric features are screened out based on the length and width, the aspect ratio, and the ratio of the contour area to the circumscribed rectangle area, so as to obtain the vehicle contour data {contours, rects} of the parked vehicle in the area to be detected.

[0165] Then, the vehicle to be parked first takes the column corresponding to half of the maximum row value of the two-dimensional image mask as the dividing line, and divides the vehicle contour data {contours, rects} of the parked vehicle into the vehicle contour data on the left side of the left dividing line and the vehicle contour data on the right side of the dividing line, and then traverses the contour information contours of the vehicle contour data on both sides to obtain the maximum row value, minimum row value, maximum column value and minimum column value {min_c, max_c, min_r, max_r} covered by the point set, forming minmaxRC, and finally obtaining the vehicle contour data on the left and right sides as {contours, rects, minmaxRC}. Based on this, the vehicle to be parked will sort the vehicle contour data on the left side along the direction of increasing row values, and take the adjacent vehicle contour data minmaxRC after sorting in sequence. When the ratio of the overlapping area of ​​the adjacent vehicle contour data minmaxRC in the column value direction to the total area (the distribution of the adjacent vehicle contour data on the two-dimensional image mask) is less than the threshold value (0.5), the vehicle data with a larger row value will be screened out, and then the minmaxRC_col (the vehicle contour data of the target parked vehicle) will be screened out through a loop. Then sort the minmaxRC_col data along the direction of increasing column values, and take the adjacent data minmaxRC_col in sequence. When the ratio of the overlapping area of ​​the adjacent data minmaxRC_col in the row value direction to the total area is less than the threshold value, the vehicle contour data with a larger row value will be screened out, and then the minmaxRC_col_row (the vehicle contour data of the target parked vehicle remaining after the fourth parked vehicle is screened out) will be screened out through a loop. Finally, the adjacent vehicle data minmaxRC_col_row is taken out in turn, and the minimum row value and respective column value of the two vehicles are obtained to form the two starting points of the storage location. The data whose width of the storage location starting point meets the conditions (candidate storage location) is retained. Then, the nearest point sampling of the two-dimensional image mask is performed along the two starting points to obtain the storage location end point set, and the storage location end point set is sorted so that the storage location end point closest to the storage location starting point is ranked first. The vehicle to be parked then performs a nearest neighbor search for each storage location end point, thereby eliminating isolated storage location end points, and obtains the shallowest storage location depth corresponding to all storage location end point sets, retains the data whose storage location depth meets the conditions, and obtains the spatial storage location information on the left (target spatial storage location). For the vehicle contour data on the right, the vehicle to be parked adopts the same processing process as the above processing of the vehicle contour data on the left to obtain the spatial storage location information on the right, and finally obtains all the target spatial storage locations in the area to be detected that can be used to park the vehicle to be parked.

[0166] See also Fig.10The present application also provides a spatial storage location detection device that can implement the above-mentioned spatial storage location detection method. The device includes a two-dimensional image generation module 1001, a vehicle contour extraction module 1002, a storage location screening module 1003, and a spatial storage location determination module 1004. Among them,

[0167] A two-dimensional image generation module 1001 is used to generate a two-dimensional image according to three-dimensional point cloud data of the area to be detected, wherein the three-dimensional point cloud data of the area to be detected is obtained by a laser radar;

[0168] A vehicle contour extraction module 1002, for determining vehicle contour data of a plurality of parked vehicles in the two-dimensional image;

[0169] The storage location screening module 1003 is used to screen a candidate storage location located between two adjacent parked vehicles according to the vehicle profile data of the plurality of parked vehicles, so as to construct a set of candidate storage locations in the area to be detected, wherein the geometric size of the candidate storage location is greater than or equal to the geometric size of the preset storage location;

[0170] The spatial storage location determination module 1004 is used to determine a target spatial storage location in the candidate storage location set according to the geometric dimensions of the vehicle to be parked and the geometric dimensions of each candidate storage location in the candidate storage location set, and the target spatial storage location is used to park the vehicle to be parked.

[0171] In some embodiments, the storage location screening module 1003 includes:

[0172] A maximum value determining unit, used to determine the maximum values ​​of the vehicle profile data of the plurality of parked vehicles in pixel rows and pixel columns;

[0173] a vehicle screening unit, configured to determine, from among the plurality of parked vehicles, a plurality of target parked vehicles arranged along the vehicle head direction of the vehicle to be parked, according to the maximum values ​​of the vehicle profile data of the plurality of parked vehicles on the pixel rows and the pixel columns, wherein the target parked vehicle is a parked vehicle closest to an extension line of the vehicle head direction;

[0174] The storage location screening unit is used to screen a candidate storage location located between two adjacent target parked vehicles according to the maximum values ​​of the vehicle profile data of the multiple target parked vehicles on the pixel rows and the pixel columns.

[0175] In some embodiments, the vehicle screening unit is further configured to:

[0176] Sort the plurality of parked vehicles in the first pixel direction according to the maximum values ​​of the vehicle profile data of the plurality of parked vehicles in the first pixel direction, wherein the first pixel direction is a pixel direction in the pixel row and the pixel column that is perpendicular to the vehicle head direction;

[0177] Determining an overlapping area between a first parked vehicle and a second parked vehicle according to the sorting in the first pixel direction, wherein the first parked vehicle and the second parked vehicle are adjacent to each other in the sorting, and a distance between the first parked vehicle and the extension line is smaller than a distance between the second parked vehicle and the extension line;

[0178] When the overlapping area between the first parked vehicle and the second parked vehicle meets a preset condition, the second parked vehicle is screened out from the plurality of parked vehicles;

[0179] The plurality of target parked vehicles include parked vehicles after the second parked vehicle is screened out.

[0180] In some embodiments, the storage location screening unit is further used to:

[0181] Sort the plurality of parked vehicles in the second pixel direction according to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles in the second pixel direction, wherein the second pixel direction is another pixel direction in the pixel row and the pixel column except the first pixel direction;

[0182] determining, according to the sorting in the second pixel direction, an overlapping area between a third parked vehicle and a fourth parked vehicle, the third parked vehicle and the fourth parked vehicle being adjacent target parked vehicles in the sorting, and a minimum distance between the third parked vehicle and the extension line being smaller than a minimum distance between the second parked vehicle and the extension line;

[0183] When the overlapping area between the third parked vehicle and the fourth parked vehicle meets a preset condition, screening out the fourth parked vehicle from the plurality of target parked vehicles;

[0184] The candidate storage location is a space between adjacent target parked vehicles among the plurality of target parked vehicles after the fourth parked vehicle is screened out.

[0185] In some embodiments, the preset condition includes: a ratio between the overlapping area and the total area is less than a preset threshold, and the total area is a distribution area of ​​two adjacent parked vehicles associated with the overlapping area.

[0186] In some embodiments, the spatial storage location detection device further includes:

[0187] An image segmentation module is used to determine a first image area and a second image area in the two-dimensional image according to the front orientation of the vehicle to be parked, the first image area being an image area located on one side of an extension line of the front orientation, and the second image area being an image area located on the other side of the extension line; and determining vehicle contour data of a parked vehicle located in the first image area or the second image area as the vehicle contour data of the multiple parked vehicles.

[0188] In some embodiments, the spatial storage location detection device further includes:

[0189] The point cloud acquisition module is used to scan the environment where the parked vehicle is located through a laser radar to obtain three-dimensional point cloud data of the environment;

[0190] A point cloud extraction module, used to extract the three-dimensional point cloud data of the area to be detected from the three-dimensional point cloud data of the environment according to a preset point cloud data detection range;

[0191] The size information of the point cloud data detection range is consistent with the size information of the area to be detected.

[0192] In some embodiments, the spatial storage location detection device further includes:

[0193] A parking assistance module is used to compare information between the target spatial storage location and the spatial storage location to be confirmed in the area to be detected, wherein the spatial storage location to be confirmed is a storage location obtained by spatial storage location detection of the area to be detected based on an ultrasonic radar, or the spatial storage location to be confirmed is a storage location obtained by spatial storage location detection of the area to be detected based on an image acquisition device; and, when the information of the target spatial storage location is consistent with the information of the spatial storage location to be confirmed, assisting the vehicle to be parked in parking according to the target spatial storage location.

[0194] The specific implementation of the spatial storage location detection device provided in the embodiment of the present application is basically the same as the specific implementation of the above-mentioned spatial storage location detection method, and will not be repeated here.

[0195] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned spatial storage location detection method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0196] See also Fig.11 , Fig.11 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0197] The processor 1101 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0198] The memory 1102 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1102 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1102, and the processor 1101 calls and executes the spatial storage location detection method of the embodiment of this application;

[0199] Input / output interface 1103, used to implement information input and output;

[0200] The communication interface 1104 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0201] A bus 1105 that transmits information between various components of the device (e.g., the processor 1101, the memory 1102, the input / output interface 1103, and the communication interface 1104);

[0202] The processor 1101 , the memory 1102 , the input / output interface 1103 and the communication interface 1104 are connected to each other in communication within the device via the bus 1105 .

[0203] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned spatial storage location detection method is implemented.

[0204] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0205] The embodiment of the present application also provides a computer program product, including a computer program. The steps implemented when the computer program is executed by a processor are basically the same as the specific embodiment of the above-mentioned spatial storage location detection method, and will not be repeated here.

[0206] The spatial storage location detection method, spatial storage location detection device, electronic device, computer-readable storage medium and computer program product provided in the embodiments of the present application obtain three-dimensional point cloud data of the area to be detected based on a laser radar through a vehicle to be parked, and generate a two-dimensional image based on the three-dimensional point cloud data, so as to determine the vehicle contour data of each of the multiple vehicles parked in the area to be detected in the two-dimensional image, and screen out candidate storage locations located between two parked vehicles with geometric dimensions greater than or equal to the preset storage location geometric dimensions based on the vehicle contour data of the multiple parked vehicles, so as to mark all the screened candidate storage locations to construct a candidate storage location set in the area to be detected, and for the constructed candidate storage location set, further determine one or more target spatial storage locations in the candidate storage location set for parking the vehicle to be parked based on the geometric dimensions of the current vehicle to be parked and the geometric dimensions of each candidate storage location in the candidate storage location set.

[0207] In this way, since the laser radar itself can work stably under different lighting conditions, it can realize three-dimensional point cloud data collection without being affected by ambient light, and since the laser radar can provide centimeter-level measurement accuracy, it can realize accurate identification of the boundaries and shapes of objects. Therefore, the embodiment of the present application scans the surrounding environment based on the high-resolution and high-precision distance measurement capabilities of the laser radar to generate accurate three-dimensional point cloud data, and identifies and locates the parking space based on the three-dimensional point cloud data of the area to be detected in the three-dimensional point cloud data. It can not only realize spatial storage location detection in situations such as failure of ultrasonic radars, cameras and other sensors, thereby improving the stability of spatial storage location detection in various environments, but also improve the accuracy of the detected spatial storage locations based on high recognition rate and fast processing speed.

[0208] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0209] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0210] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0211] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0212] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0213] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0214] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0215] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0216] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0217] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0218] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A spatial storage location detection method, characterized in that: The method comprises: Generate a two-dimensional image based on three-dimensional point cloud data of the area to be detected, wherein the three-dimensional point cloud data of the area to be detected is obtained by a laser radar; determining vehicle profile data of a plurality of parked vehicles in the two-dimensional image; According to the vehicle profile data of the plurality of parked vehicles, a candidate storage location located between two adjacent parked vehicles is selected to construct a set of candidate storage locations in the area to be detected, wherein the geometric size of the candidate storage location is greater than or equal to the geometric size of the preset storage location; According to the geometric dimensions of the vehicle to be parked and the geometric dimensions of each of the candidate storage locations in the candidate storage location set, a target space storage location is determined in the candidate storage location set, and the target space storage location is used to park the vehicle to be parked.

2. The method according to claim 1, characterized in that The step of selecting a candidate storage location between two adjacent parked vehicles according to the vehicle profile data of the plurality of parked vehicles comprises: Determine the maximum values ​​of the vehicle profile data of the plurality of parked vehicles in pixel rows and pixel columns; According to the maximum values ​​of the vehicle profile data of the plurality of parked vehicles on the pixel rows and the pixel columns, a plurality of target parked vehicles arranged along the vehicle head direction of the vehicle to be parked are determined from the plurality of parked vehicles, wherein the target parked vehicle is a parked vehicle closest to an extension line of the vehicle head direction; According to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles on the pixel row and the pixel column, a candidate storage location located between two adjacent target parked vehicles is screened.

3. The method according to claim 2, characterized in that The method of determining, according to the maximum values ​​of the vehicle profile data of the plurality of parked vehicles on the pixel rows and the pixel columns, a plurality of target parked vehicles arranged along the front direction of the vehicle to be parked from among the plurality of parked vehicles comprises: Sort the plurality of parked vehicles in the first pixel direction according to the maximum values ​​of the vehicle profile data of the plurality of parked vehicles in the first pixel direction, wherein the first pixel direction is a pixel direction in the pixel row and the pixel column that is perpendicular to the vehicle head direction; Determining an overlapping area between a first parked vehicle and a second parked vehicle according to the sorting in the first pixel direction, wherein the first parked vehicle and the second parked vehicle are adjacent to each other in the sorting, and a distance between the first parked vehicle and the extension line is smaller than a distance between the second parked vehicle and the extension line; When the overlapping area between the first parked vehicle and the second parked vehicle meets a preset condition, the second parked vehicle is screened out from the plurality of parked vehicles; The plurality of target parked vehicles include parked vehicles after the second parked vehicle is screened out.

4. The method according to claim 2, characterized in that: The step of screening a candidate storage location between two adjacent target parked vehicles according to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles on the pixel row and the pixel column comprises: Sort the plurality of parked vehicles in the second pixel direction according to the maximum values ​​of the vehicle profile data of the plurality of target parked vehicles in the second pixel direction, wherein the second pixel direction is another pixel direction in the pixel row and the pixel column except the first pixel direction; Determining an overlapping area between a third parked vehicle and a fourth parked vehicle according to the sorting in the second pixel direction, the third parked vehicle and the fourth parked vehicle are target parked vehicles that are adjacent in the sorting, and a minimum distance between the third parked vehicle and the extension line is smaller than a minimum distance between the fourth parked vehicle and the extension line; When the overlapping area between the third parked vehicle and the fourth parked vehicle meets a preset condition, screening out the fourth parked vehicle from the plurality of target parked vehicles; The candidate storage location is a space between adjacent target parked vehicles among the plurality of target parked vehicles after the fourth parked vehicle is screened out.

5. The method according to claim 3 or 4, characterized in that: The preset conditions include: The ratio of the overlapping area to the total area is less than a preset threshold, and the total area is a distribution area of ​​two adjacent parked vehicles associated with the overlapping area.

6. The method according to claim 1, characterized in that Before determining the vehicle profile data of a plurality of parked vehicles in the two-dimensional image, the method further comprises: According to the front direction of the vehicle to be parked, a first image area and a second image area are determined in the two-dimensional image, wherein the first image area is an image area located on one side of an extension line of the front direction of the vehicle, and the second image area is an image area located on the other side of the extension line; The vehicle contour data of the parked vehicles located in the first image area or the second image area are determined as the vehicle contour data of the plurality of parked vehicles.

7. The method according to claim 1, characterized in that Before generating a two-dimensional image based on the three-dimensional point cloud data of the area to be detected, the method further includes: Scan the environment where the parked vehicle is located by using a laser radar to obtain three-dimensional point cloud data of the environment; According to a preset point cloud data detection range, extracting three-dimensional point cloud data of the area to be detected from the three-dimensional point cloud data of the environment; The size information of the point cloud data detection range is consistent with the size information of the area to be detected.

8. The method according to claim 1, characterized in that After determining the target space storage location in the candidate storage location set according to the geometric size of the vehicle to be parked and the geometric size of each candidate storage location in the candidate storage location set, the method further includes: Compare the information of the target spatial storage location with the spatial storage location to be confirmed in the area to be detected, wherein the spatial storage location to be confirmed is a storage location obtained by performing spatial storage location detection on the area to be detected based on an ultrasonic radar, or the spatial storage location to be confirmed is a storage location obtained by performing spatial storage location detection on the area to be detected based on an image acquisition device; When the information of the target spatial storage location is consistent with the information of the spatial storage location to be confirmed, the vehicle to be parked is assisted in parking according to the target spatial storage location.

9. A spatial storage location detection device, characterized in that: The device comprises: A two-dimensional image generation module, used to generate a two-dimensional image based on three-dimensional point cloud data of the area to be detected, wherein the three-dimensional point cloud data of the area to be detected is obtained by a laser radar; a vehicle contour extraction module, for determining vehicle contour data of a plurality of parked vehicles in the two-dimensional image; A storage location screening module, used for screening a candidate storage location located between two adjacent parked vehicles according to the vehicle profile data of the plurality of parked vehicles, so as to construct a set of candidate storage locations in the area to be detected, wherein the geometric size of the candidate storage location is greater than or equal to the geometric size of the preset storage location; The spatial storage location determination module is used to determine a target spatial storage location in the candidate storage location set according to the geometric dimensions of the vehicle to be parked and the geometric dimensions of each candidate storage location in the candidate storage location set, and the target spatial storage location is used to park the vehicle to be parked.

10. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the spatial storage location detection method according to any one of claims 1 to 8 when executing the computer program.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the spatial storage location detection method described in any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the spatial storage location detection method described in any one of claims 1 to 8 are implemented.

Images