A parking space determination method, apparatus, device and storage medium

Abstract

The application discloses a parking space determination method, device and equipment and a storage medium. The method comprises the following steps: acquiring at least one frame of panoramic bird's-eye view corresponding to a current vehicle; acquiring an obstacle area corresponding to each frame of the panoramic bird's-eye view; constructing an obstacle map according to the obstacle area corresponding to each frame of the panoramic bird's-eye view and an inertial navigation value corresponding to the current vehicle; determining a parking area according to the obstacle map; and determining a target parking space according to the parking area. The technical scheme can solve the problems of low space parking space detection rate and poor parking precision, improve the adaptability of a parking system to special scenes, and reasonably construct a space parking space.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a parking space determination method, apparatus, device and storage medium. Background Technology

[0002] With increasingly congested urban roads and a more complex driving and parking environment, "parking difficulties" have become a widespread concern. Therefore, research on automated parking systems has become a hot topic in the field of intelligent transportation. Spatial parking spaces refer to available parking spaces deduced from the parking order of other vehicles and the available space when there are no road markings; these are commonly found on the roadside. Current spatial parking space detection schemes typically utilize ultrasonic sensor signals, employing signal transition edge detection or point filtering methods to detect spatial parking spaces and determine the parking space type based on its length and width. However, these methods generally suffer from poor spatial parking space recognition rates, or even when parking spaces are detected, the accuracy is low, resulting in poor parking performance. Therefore, it is necessary to provide a method for constructing multi-spatial parking spaces. Summary of the Invention

[0003] This invention provides a parking space determination method, apparatus, device, and storage medium to solve the problems of low spatial parking space detection rate and poor parking accuracy, improve the adaptability of the parking system to special scenarios, and rationally construct spatial parking spaces.

[0004] According to one aspect of the present invention, a parking space determination method is provided, comprising:

[0005] Obtain at least one panoramic top-down view corresponding to the current vehicle;

[0006] Obtain the obstacle area corresponding to each frame of the panoramic top-down view;

[0007] An obstacle map is constructed based on the obstacle area corresponding to the panoramic overhead view in each frame and the inertial navigation value corresponding to the current vehicle;

[0008] Parking areas are determined based on the obstacle map;

[0009] The target parking space is determined based on the available parking area.

[0010] In some embodiments, an obstacle map is constructed based on the obstacle region corresponding to each frame of the panoramic overhead view and the inertial navigation value corresponding to the current vehicle, including:

[0011] Establish a coordinate system using the current vehicle location as the origin.

[0012] Based on the preset grid length and preset grid width, a placeholder grid map is established on the coordinate system according to the coordinate origin;

[0013] An obstacle map is constructed based on the occupancy grid map, the obstacle area corresponding to each frame of the panoramic overhead view, and the inertial navigation value corresponding to the current vehicle.

[0014] In some embodiments, an obstacle map is constructed based on the occupancy grid map, the obstacle area corresponding to each frame of the panoramic overhead view, and the inertial navigation value corresponding to the current vehicle, including:

[0015] Obtain the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic top-down view;

[0016] Based on the inertial navigation values, the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic overhead view are projected onto the placeholder grid map;

[0017] Obtain the number of edge pixels within each grid in the placeholder grid map;

[0018] The obstacle map is obtained by filtering out grids in the placeholder grid map where the number of edge pixels within the grid is less than a preset threshold.

[0019] In some embodiments, determining a target parking space based on the available parking area includes:

[0020] Obtain the original length and original width of the current vehicle;

[0021] The target parking space size is determined based on the original length and width of the current vehicle and the preset space margin.

[0022] The target parking space is determined based on the target parking space size and the available parking area.

[0023] In some embodiments, determining a target parking space based on the target parking space size and the available parking area includes:

[0024] The target parking space size is determined based on the target parking space size, the preset grid length, and the preset grid width;

[0025] The target parking space is determined based on the target occupancy grid size and the available parking area.

[0026] In some embodiments, determining a target parking space based on the target occupancy grid size and the available parking area includes:

[0027] The parking space set corresponding to each initial parking space type is determined based on the target occupancy grid size and the parking area, wherein the initial parking space type includes at least one of horizontal parking space, vertical parking space and angled parking space;

[0028] The initial parking space type with the largest number of parking spaces in the parking space set is determined as the target parking space type;

[0029] The target parking space is determined based on the set of parking spaces corresponding to the target parking space type.

[0030] In some embodiments, obtaining the obstacle region corresponding to each frame of the panoramic top-down view includes:

[0031] Each frame of the panoramic overhead view is input into a deep learning semantic segmentation model to obtain the obstacle region corresponding to each frame of the panoramic overhead view.

[0032] According to another aspect of the present invention, a parking space determination device is provided, the device comprising:

[0033] The first acquisition module is used to acquire at least one panoramic top-down view corresponding to the current vehicle.

[0034] The second acquisition module is used to acquire the obstacle area corresponding to each frame of the panoramic overhead view;

[0035] The construction module is used to construct an obstacle map based on the obstacle area corresponding to each frame of the panoramic overhead view and the inertial navigation value corresponding to the current vehicle;

[0036] The first determining module is used to determine a parking area based on the obstacle map;

[0037] The second determining module is used to determine the target parking space based on the parking area.

[0038] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0039] At least one processor; and

[0040] A memory communicatively connected to the at least one processor; wherein,

[0041] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the parking space determination method according to any embodiment of the present invention.

[0042] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the parking space determination method according to any embodiment of the present invention.

[0043] This invention, through its embodiments, acquires at least one frame of panoramic top-down view corresponding to the current vehicle, obtains the obstacle area corresponding to each frame of panoramic top-down view, constructs an obstacle map based on the obstacle area corresponding to each frame of panoramic top-down view and the inertial navigation value corresponding to the current vehicle, determines a parking area based on the obstacle map, and determines a target parking space based on the parking area. This invention solves the problems of low spatial parking space detection rate and poor parking accuracy, improves the adaptability of the parking system to special scenarios, and rationally constructs spatial parking spaces.

[0044] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0045] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart of a parking space determination method according to an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of a horizontal parking space according to an embodiment of the present invention;

[0048] Figure 3 This is a schematic diagram of a vertical parking space according to an embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram of a slanted train parking space according to an embodiment of the present invention;

[0050] Figure 5 This is a schematic diagram of a panoramic top-down view in an embodiment of the present invention;

[0051] Figure 6 This is a schematic diagram of a semantic segmentation result in an embodiment of the present invention;

[0052] Figure 7 This is a schematic diagram of the structure of a parking space determination device according to an embodiment of the present invention;

[0053] Figure 8 This is a schematic diagram of the structure of an electronic device that implements the parking space determination method of this invention. Detailed Implementation

[0054] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0055] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0056] Example 1

[0057] Figure 1 This is a flowchart of a parking space determination method according to an embodiment of the present invention. This embodiment is applicable to situations involving parking space determination. The method can be executed by the parking space determination device in this embodiment of the present invention, which can be implemented in software and / or hardware, such as... Figure 1 As shown, the method specifically includes the following steps:

[0058] S101. Obtain at least one panoramic top-down view corresponding to the current vehicle.

[0059] In this embodiment, the current vehicle can be the vehicle that will be planned for parking space and parked in the planned parking space.

[0060] The panoramic view can be an overview of a certain area around the current vehicle, with the area centered on the vehicle. The size of this area can be determined by the camera's installation angle and hardware configuration.

[0061] Specifically, four surround-view cameras installed on the current vehicle capture images in real time or periodically (the shooting period can be preset by the user according to the actual situation, and this embodiment does not limit this) the images centered on the current vehicle and including a certain range around the current vehicle. Each frame of the image is transformed by inverse perspective to obtain at least one panoramic overhead view corresponding to the current vehicle.

[0062] S102. Obtain the obstacle area corresponding to each frame of panoramic top-down view.

[0063] The obstacle area can be the region in the panoramic view that is mapped onto obstacles existing around the vehicle. For example, obstacles can be vehicles, pedestrians, buildings, or road equipment.

[0064] Specifically, it obtains the area of ​​obstacles included in each frame of the panoramic overhead view.

[0065] S103. Construct an obstacle map based on the obstacle area corresponding to each frame of the panoramic overhead view and the inertial navigation value corresponding to the current vehicle.

[0066] It is known that the inertial navigation value can be provided by the inertial navigation system on the current vehicle to assist the current driver.

[0067] It should be noted that the obstacle map can be a placeholder grid-style electronic map that shows the obstacles that exist around the current vehicle.

[0068] Specifically, an obstacle map, i.e. a placeholder grid-style electronic map, is constructed based on the obstacle area corresponding to each frame of the panoramic view and the inertial navigation value between every two frames of the panoramic view corresponding to the current vehicle.

[0069] S104. Determine the parking area based on the obstacle map.

[0070] It should be noted that the parking area can be the space around the current vehicle where parking is possible.

[0071] Specifically, based on the obstacle map, the area outside the area where the obstacle is located is designated as a parking zone.

[0072] S105. Determine the target parking space based on the available parking area.

[0073] The target parking space can be the parking space in the available parking area where the current vehicle will park.

[0074] Specifically, at least one parking space is planned in the parking area for the current vehicle to park in. The current vehicle can park in one of the parking spaces, i.e., the target parking space, according to the actual situation.

[0075] This invention, through its embodiments, acquires at least one frame of panoramic top-down view corresponding to the current vehicle, obtains the obstacle area corresponding to each frame of panoramic top-down view, constructs an obstacle map based on the obstacle area corresponding to each frame of panoramic top-down view and the inertial navigation value corresponding to the current vehicle, determines a parking area based on the obstacle map, and determines a target parking space based on the parking area. This invention solves the problems of low spatial parking space detection rate and poor parking accuracy, improves the adaptability of the parking system to special scenarios, and rationally constructs spatial parking spaces.

[0076] Optionally, an obstacle map is constructed based on the obstacle area corresponding to each frame of the panoramic overhead view and the inertial navigation value corresponding to the current vehicle, including:

[0077] Establish a coordinate system with the current location of the vehicle as the origin.

[0078] Specifically, a coordinate system is established starting from the coordinates of the current vehicle's location when the parking space search begins.

[0079] Based on the preset grid length and preset grid width, a placeholder grid map is created on the coordinate system according to the coordinate origin.

[0080] The preset grid length and preset grid width can be pre-set according to actual conditions. This embodiment does not limit the size of the preset grid length and preset grid width. Preferably, the preset grid length and preset grid width can be, for example, 5 cm.

[0081] It should be explained that the parking space grid map can be a grid map built starting from the coordinates of the current vehicle's location when it begins searching for a parking space.

[0082] For example, a coordinate system is established starting from the coordinates when the vehicle begins searching for parking spaces, and a parking space grid map is created with 5 cm * 5 cm as a grid unit.

[0083] An obstacle map is constructed based on the placeholder grid map, the obstacle area corresponding to each frame of the panoramic overhead view, and the inertial navigation value corresponding to the current vehicle.

[0084] Optionally, an obstacle map is constructed based on the placeholder grid map, the obstacle area corresponding to each frame of the panoramic top-down view, and the inertial navigation value corresponding to the current vehicle, including:

[0085] Obtain the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic top-down view.

[0086] It should be noted that edge pixels can be the edge contour pixels of the obstacle area corresponding to each frame of the panoramic top view, and the coordinates of the edge pixels can be the coordinates of the edge contour pixels of the obstacle area corresponding to each frame of the panoramic top view on a coordinate system established with the current vehicle position as the origin.

[0087] Specifically, the coordinates of the edge pixels of the obstacle area corresponding to each frame of the panoramic top-down view are obtained in a coordinate system established with the current vehicle location as the origin.

[0088] Based on the inertial navigation values, the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic top view are projected onto the placeholder grid map.

[0089] Specifically, the coordinates of the edge pixels of the obstacle area corresponding to each frame of the panoramic view are transferred to the vehicle's starting coordinate system based on the vehicle movement value obtained from the inertial navigation record obtained from the vehicle's CAN (Controller Area Network). This is done using a coordinate system established with the current vehicle location as the origin.

[0090] Get the number of edge pixels in each grid of the placeholder grid map.

[0091] Specifically, the number of edge pixels in each grid in the placeholder grid map is obtained by accumulating the pixels where the edge pixels of the obstacle area corresponding to each frame of the panoramic top view fall into each grid.

[0092] The obstacle map is obtained by filtering out grids in the placeholder grid map where the number of edge pixels within the grid is less than a preset threshold.

[0093] The preset threshold can be a threshold set in advance according to the actual situation. In this embodiment, the size of the preset threshold is not limited.

[0094] Specifically, after obtaining the number of edge pixels in each grid of the placeholder grid map, it is determined whether the number of edge pixels in each grid meets the preset threshold. If not, the grid is deleted; if so, the grid is retained to form an obstacle map.

[0095] Optionally, the target parking space can be determined based on the available parking area, including:

[0096] Get the original length and original width of the current vehicle.

[0097] The original length and original width can be the actual length and width of the current vehicle body.

[0098] Specifically, obtain the actual length and width corresponding to the current vehicle model.

[0099] The target parking space size is determined based on the vehicle's original length, original width, and preset space allowance.

[0100] It should be explained that the preset space allowance can be the length and width that must be available when the vehicle is parked. The preset space allowance can be set by the user according to the actual vehicle model. This embodiment does not limit this. For example, the preset space allowance can be: 1 meter in width and 0.5 meters in length.

[0101] The target parking space size can be the actual size of the parking space required to park the current vehicle.

[0102] Specifically, the calculation method for the target parking space size can be, for example, the original length plus the length in the preset space allowance, or the original width plus the width in the preset space allowance.

[0103] The target parking space is determined based on the size of the target parking space and the available parking area.

[0104] Optionally, the target parking space can be determined based on the target parking space size and the available parking area, including:

[0105] The target parking space size is determined based on the target parking space size, the preset grid length, and the preset grid width.

[0106] It should be explained that the target occupancy grid size can be the grid size that the parking space required to park the current vehicle needs to occupy in the obstacle map.

[0107] Specifically, the length and width of the target parking space are divided by the preset grid length and preset grid width, respectively, to obtain the grid size that the parking space required to park the current vehicle needs to occupy in the obstacle map.

[0108] The target parking space is determined based on the target occupancy grid size and the available parking area.

[0109] In practice, the unoccupied parking grid space on the obstacle map may be quite large, potentially containing multiple parking spaces. Therefore, it is necessary to construct multiple parking spaces simultaneously, which is beneficial for subsequent parking planning.

[0110] Optionally, the target parking space can be determined based on the target occupancy grid size and the available parking area, including:

[0111] The set of parking spaces corresponding to each initial parking space type is determined based on the target occupancy grid size and the available parking area.

[0112] The initial parking space type includes at least one of the following: horizontal parking space, vertical parking space, and angled parking space.

[0113] Figure 2This is a schematic diagram of a horizontal parking space according to an embodiment of the present invention. Figure 2 As shown, a horizontal parking space is one whose overall orientation is horizontal to the current driving direction of the vehicle. Specifically, a greedy algorithm can be used to determine the set of parking spaces corresponding to horizontal parking spaces based on the target occupancy grid size and the available parking area. That is, the optimal two-dimensional spatial arrangement of parking spaces in the unoccupied grid is calculated according to the parking space type of the horizontal parking space.

[0114] Figure 3 This is a schematic diagram of a vertical parking space according to an embodiment of the present invention. Figure 3 As shown, a perpendicular parking space is one whose overall direction is perpendicular to the current driving direction of the vehicle. Specifically, a greedy algorithm can be used to determine the set of parking spaces corresponding to perpendicular parking spaces based on the target occupancy grid size and the available parking area. That is, the optimal two-dimensional spatial arrangement of parking spaces in the unoccupied grid is calculated according to the parking space type of the perpendicular parking space.

[0115] Figure 4 This is a schematic diagram of a slanted train parking space according to an embodiment of the present invention. For example... Figure 4 As shown, an angled parking space is one whose overall direction is at an angle to the current vehicle's direction of travel; the size of the angle is not limited. Specifically, a greedy algorithm can be used to determine the set of parking spaces corresponding to the angled parking spaces based on the target grid size and the available parking area. This involves calculating the optimal two-dimensional spatial arrangement of parking spaces in the unoccupied grid according to the parking space type. During this process, parking spaces can be divided into 5° intervals between 20° and 70°, retaining the angled parking spaces that can accommodate more vehicles within the available parking space; this angle is then determined as the optimal angle.

[0116] The initial parking space type with the most parking spaces in the parking space set is determined as the target parking space type.

[0117] The target parking space type can be the type of parking space with the most parking spaces in the parking space set, that is, the type of parking space that can divide the parking area into the most parking spaces.

[0118] Specifically, by counting the number of parking spaces in the set corresponding to horizontal parking spaces, the number of parking spaces in the set corresponding to perpendicular parking spaces, and the number of parking spaces in the set corresponding to inclined parking spaces under the optimal angle, the initial parking space type with the largest number of parking spaces in the set is determined as the target parking space type, which can better utilize available parking space.

[0119] The target parking space is determined based on the set of parking spaces corresponding to the target parking space type.

[0120] Specifically, after determining the target parking space type, a parking space can be selected from the set of parking spaces corresponding to the target parking space type as the target parking space. The criteria for selection are not limited in this embodiment. For example, it can be any parking space in the set, the parking space in the set that is closest to the current vehicle position, or a parking space in the set selected by the user.

[0121] Optionally, obtain the obstacle region corresponding to each frame of the panoramic top-down view, including:

[0122] Each frame of the panoramic overhead view is input into a deep learning semantic segmentation model to obtain the obstacle region corresponding to each frame of the panoramic overhead view.

[0123] For example, Figure 5 This is a schematic diagram of a panoramic top-down view in an embodiment of the present invention, such as... Figure 5 As shown, the black rectangle in the center of the image represents the current vehicle, surrounded by other vehicles and obstacles. By inputting this panoramic overhead view into a deep learning semantic segmentation model, the obstacle region corresponding to this panoramic overhead view is obtained. Figure 6 This is a schematic diagram of a semantic segmentation result in an embodiment of the present invention, such as... Figure 6 As shown, the black rectangle in the middle of the image represents the current vehicle, and the surrounding shaded area represents the obstacle area.

[0124] During the implementation process, due to the distortion effect of visual inverse perspective transformation, the edges of reflective or three-dimensional objects will be stretched, and the distorted stretched edges are radial, roughly passing through the focal point of each camera. These edges do not actually exist. Therefore, this property is used to filter out the image edges in the radial direction with the installation position of each single camera as the origin during the scanning process, leaving the image contour points on the real ground. Then, these contour points are transformed from the image coordinates centered on the vehicle to the world coordinate system centered on the vehicle. Finally, an obstacle map is constructed based on the processed panoramic overhead view of each frame.

[0125] The technical solution of this invention involves obtaining a panoramic overhead view of the vehicle by performing inverse perspective transformation on images from four surround-view cameras installed on the vehicle body. An obstacle area on the panoramic overhead view is obtained based on a deep learning-based semantic segmentation model. Radial edge filtering is performed on the image using the distortion characteristics of inverse perspective transformation. Then, the obstacle edge pixels of each frame are projected onto a vacant grid map using inertial navigation values ​​obtained from the vehicle's CAN bus. Vertical, horizontal, and diagonal parking spaces are then constructed using parking space types and the length and width of standard parking spaces. This process is traversed in the unoccupied grid space, and multiple parking spaces are arranged within the space using a greedy algorithm. Finally, the target parking space is determined so that the current vehicle can park. This invention's technical solution designs a method for constructing multiple unmarked parking spaces using surround-view camera images and electronic map technology. This solves the problems of simultaneously constructing multiple parking spaces in unmarked parking areas and determining parking space types, improving the detection accuracy of parking spaces, enhancing the adaptability of the parking system to special scenarios, and further improving the detection robustness of the automatic parking system.

[0126] Example 2

[0127] Figure 7 This is a schematic diagram of a parking space determination device according to an embodiment of the present invention. This embodiment is applicable to situations requiring parking space determination. The device can be implemented using software and / or hardware methods, and can be integrated into any device that provides parking space determination functionality, such as... Figure 7 As shown, the parking space determination device specifically includes: a first acquisition module 201, a second acquisition module 202, a construction module 203, a first determination module 204, and a second determination module 205.

[0128] The first acquisition module 201 is used to acquire at least one panoramic top-down view corresponding to the current vehicle.

[0129] The second acquisition module 202 is used to acquire the obstacle area corresponding to each frame of the panoramic overhead view;

[0130] Construction module 203 is used to construct an obstacle map based on the obstacle area corresponding to each frame of the panoramic overhead view and the inertial navigation value corresponding to the current vehicle;

[0131] The first determining module 204 is used to determine a parking area based on the obstacle map;

[0132] The second determining module 205 is used to determine the target parking space based on the parking area.

[0133] Optionally, the building module 203 includes:

[0134] The first establishment unit is used to establish a coordinate system with the current location of the vehicle as the origin.

[0135] The second establishment unit is used to establish a placeholder grid map on the coordinate system based on the preset grid length and preset grid width and the coordinate origin;

[0136] The construction unit is used to construct an obstacle map based on the placeholder grid map, the obstacle area corresponding to each frame of the panoramic overhead view, and the inertial navigation value corresponding to the current vehicle.

[0137] Optionally, the building unit is specifically used for:

[0138] Obtain the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic top-down view;

[0139] Based on the inertial navigation values, the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic overhead view are projected onto the placeholder grid map;

[0140] Obtain the number of edge pixels within each grid in the placeholder grid map;

[0141] The obstacle map is obtained by filtering out grids in the placeholder grid map where the number of edge pixels within the grid is less than a preset threshold.

[0142] Optionally, the second determining module 205 includes:

[0143] The acquisition unit is used to acquire the original length and original width of the current vehicle;

[0144] The first determining unit is used to determine the target parking space size based on the original length, original width and preset space margin of the current vehicle.

[0145] The second determining unit is used to determine the target parking space based on the target parking space size and the available parking area.

[0146] Optionally, the second determining unit includes:

[0147] The first determining subunit is used to determine the target occupancy grid size based on the target parking space size, the preset grid length, and the preset grid width;

[0148] The second determining subunit is used to determine the target parking space based on the target occupancy grid size and the parking area.

[0149] Optionally, the second determining subunit is specifically used for:

[0150] The parking space set corresponding to each initial parking space type is determined based on the target occupancy grid size and the parking area, wherein the initial parking space type includes at least one of horizontal parking space, vertical parking space and angled parking space;

[0151] The initial parking space type with the largest number of parking spaces in the parking space set is determined as the target parking space type;

[0152] The target parking space is determined based on the set of parking spaces corresponding to the target parking space type.

[0153] Optionally, the second acquisition module 202 is specifically used for:

[0154] Each frame of the panoramic overhead view is input into a deep learning semantic segmentation model to obtain the obstacle region corresponding to each frame of the panoramic overhead view.

[0155] The above-mentioned product can execute the parking space determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the parking space determination method.

[0156] Example 3

[0157] Figure 8 A schematic diagram of an electronic device 30 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0158] like Figure 8 As shown, the electronic device 30 includes at least one processor 31 and a memory, such as a read-only memory (ROM) 32 or a random access memory (RAM) 33, communicatively connected to the at least one processor 31. The memory stores computer programs executable by the at least one processor. The processor 31 can perform various appropriate actions and processes based on the computer program stored in the ROM 32 or loaded from storage unit 38 into the RAM 33. The RAM 33 can also store various programs and data required for the operation of the electronic device 30. The processor 31, ROM 32, and RAM 33 are interconnected via a bus 34. An input / output (I / O) interface 35 is also connected to the bus 34.

[0159] Multiple components in electronic device 30 are connected to I / O interface 35, including: input unit 36, such as keyboard, mouse, etc.; output unit 37, such as various types of monitors, speakers, etc.; storage unit 38, such as disk, optical disk, etc.; and communication unit 39, such as network card, modem, wireless transceiver, etc. Communication unit 39 allows electronic device 30 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0160] Processor 31 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 31 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 31 performs the various methods and processes described above, such as the parking space determination method:

[0161] Obtain at least one panoramic top-down view corresponding to the current vehicle;

[0162] Obtain the obstacle area corresponding to each frame of the panoramic top-down view;

[0163] An obstacle map is constructed based on the obstacle area corresponding to the panoramic overhead view in each frame and the inertial navigation value corresponding to the current vehicle;

[0164] Parking areas are determined based on the obstacle map;

[0165] The target parking space is determined based on the available parking area.

[0166] In some embodiments, the parking space determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 38. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 30 via ROM 32 and / or communication unit 39. When the computer program is loaded into RAM 33 and executed by processor 31, one or more steps of the parking space determination method described above may be performed. Alternatively, in other embodiments, processor 31 may be configured to perform the parking space determination method by any other suitable means (e.g., by means of firmware).

[0167] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0168] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0169] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0170] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0171] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0172] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0173] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0174] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining parking spaces, characterized in that, include: Obtain at least one panoramic top-down view corresponding to the current vehicle; Obtain the obstacle area corresponding to each frame of the panoramic top-down view; Radial edge filtering is performed on each frame of the panoramic overhead view to filter out the image edges in the radial direction with each camera installation position as the origin, and retain the image contour points on the real ground as the edge pixels of the obstacle area; An obstacle map is constructed based on the obstacle area corresponding to each frame of the panoramic overhead view and the inertial navigation value corresponding to the current vehicle, including: Establish a coordinate system using the current vehicle location as the origin. Based on the preset grid length and preset grid width, a placeholder grid map is established on the coordinate system according to the coordinate origin; Obtain the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic top-down view; Based on the inertial navigation values, the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic overhead view are projected onto the placeholder grid map; Obtain the number of edge pixels within each grid in the placeholder grid map; Filter out grids in the placeholder grid map where the number of edge pixels is less than a preset threshold to obtain an obstacle map; Parking areas are determined based on the obstacle map; The target parking space is determined based on the available parking area.

2. The method according to claim 1, characterized in that, Determining the target parking space based on the available parking area includes: Obtain the original length and original width of the current vehicle; The target parking space size is determined based on the original length and width of the current vehicle and the preset space margin. The target parking space is determined based on the target parking space size and the available parking area.

3. The method according to claim 2, characterized in that, Determining the target parking space based on the target parking space size and the available parking area includes: The target parking space size is determined based on the target parking space size, the preset grid length, and the preset grid width; The target parking space is determined based on the target occupancy grid size and the available parking area.

4. The method according to claim 3, characterized in that, Determining the target parking space based on the target occupancy grid size and the available parking area includes: The parking space set corresponding to each initial parking space type is determined based on the target occupancy grid size and the parking area, wherein the initial parking space type includes at least one of horizontal parking space, vertical parking space and angled parking space; The initial parking space type with the largest number of parking spaces in the parking space set is determined as the target parking space type; The target parking space is determined based on the set of parking spaces corresponding to the target parking space type.

5. The method according to claim 1, characterized in that, Obtain the obstacle region corresponding to each frame of the panoramic top-down view, including: Each frame of the panoramic overhead view is input into a deep learning semantic segmentation model to obtain the obstacle region corresponding to each frame of the panoramic overhead view.

6. A parking space determination device, characterized in that, include: The first acquisition module is used to acquire at least one panoramic top-down view corresponding to the current vehicle. The second acquisition module is used to acquire the obstacle area corresponding to each frame of the panoramic overhead view; The construction module is used to construct an obstacle map based on the obstacle area corresponding to each frame of the panoramic overhead view and the inertial navigation value corresponding to the current vehicle; The first determining module is used to determine a parking area based on the obstacle map; The second determining module is used to determine the target parking space based on the parking area; The device is also used for: Radial edge filtering is performed on each frame of the panoramic overhead view to filter out the image edges in the radial direction with each camera installation position as the origin, and retain the image contour points on the real ground as the edge pixels of the obstacle area; The building module includes: The first establishment unit is used to establish a coordinate system with the current location of the vehicle as the origin. The second establishment unit is used to establish a placeholder grid map on the coordinate system based on the preset grid length and preset grid width and the coordinate origin; The construction unit is used to construct an obstacle map based on the occupancy grid map, the obstacle area corresponding to each frame of the panoramic overhead view, and the inertial navigation value corresponding to the current vehicle. The building unit is specifically used for: Obtain the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic top-down view; project the edge pixel coordinates of the obstacle area corresponding to each frame of the panoramic top-down view onto the placeholder grid map according to the inertial navigation value; obtain the number of edge pixels in each grid in the placeholder grid map; filter out grids in the placeholder grid map whose number of edge pixels is less than a preset threshold to obtain the obstacle map.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the parking space determination method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the parking space determination method according to any one of claims 1-5.

Images