Cross-parking-stall parking identification method and device, computer equipment and storage medium

Abstract

The invention provides a cross-parking-space parking recognition method and device, computer equipment and a storage medium. The cross-parking-space parking recognition method comprises the steps that a first image collected by a target camera is acquired; adding bounding boxes to the positions of the plurality of vehicles in the first image to obtain a second image; intercepting an area image of each bounding box in the corresponding parking area in the second image according to a preset interception proportion; the preset interception proportion is set according to the angle of the target camera; marking a pixel area of each vehicle in the first image to obtain a third image; segmenting a target pixel region image corresponding to the region image from the third image; and according to the target pixel area image, whether parking space crossing parking exists in each parking area is judged. According to the embodiment of the invention, the judgment accuracy of cross-parking-stall parking can be greatly improved.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to a method, device, computer equipment and storage medium for identifying parking spaces that cross parking spaces. Background Art

[0002] In the process of parking lot management, cameras and computer vision analysis technology are generally used to determine whether there is cross-parking parking. For example, the image taken by the camera is subjected to vehicle key point detection or 3D detection, and the presence of cross-parking parking is determined based on the vehicle key point detection results or 3D detection results.

[0003] The above-mentioned method for judging parking across parking spaces may result in a problem in which the accuracy of judging parking across parking spaces based on the vehicle key point detection results or 3D detection results is also low due to the low detection accuracy of the vehicle key point detection or 3D detection results. Summary of the invention

[0004] In view of this, the present disclosure proposes a method, device, computer equipment and storage medium for identifying cross-parking space parking, so as to solve the problem in the related art that due to the low detection accuracy of vehicle key points or 3D detection, the accuracy of judging cross-parking space parking based on vehicle key point detection results or 3D detection results may also be low.

[0005] The first embodiment of the present disclosure provides a method for identifying parking spaces across parking spaces, the method comprising:

[0006] Acquire a first image captured by a target camera;

[0007] Adding bounding boxes to the positions of multiple vehicles in the first image respectively to obtain a second image;

[0008] intercepting a regional image of each boundary box in the second image within a corresponding parking area according to a preset interception ratio; the preset interception ratio is set according to the angle of the target camera;

[0009] Annotating a pixel region of each vehicle in the first image to obtain a third image;

[0010] Segmenting a target pixel region image corresponding to the region image from the third image;

[0011] It is determined whether there is cross-parking parking in each parking area according to the target pixel area image.

[0012] The disclosed embodiment can avoid the influence of vehicles blocking the parking area on the judgment of straddling parking spaces by intercepting the regional image of each boundary box in the second image within the corresponding parking area according to a preset interception ratio; the disclosed embodiment can also ensure the accuracy of the judgment of straddling parking spaces by segmenting the target pixel regional image corresponding to the regional image from the third image; and judging whether there is straddling parking in each parking area based on the target pixel regional image.

[0013] In an embodiment of the present disclosure, the method further includes:

[0014] Under the condition that a plurality of parking spaces within the field of view of the target camera are in an unparked state, a calibration image is acquired; a parking area of ​​each parking space is calibrated in the calibration image;

[0015] The image of each parking area in the calibration image is intercepted according to the preset interception ratio to obtain a fourth image; the fourth image includes multiple intercepted images of the parking areas.

[0016] In the embodiment of the present disclosure, intercepting the regional image of each boundary box in the second image within the corresponding parking area according to a preset interception ratio includes:

[0017] For any one of the plurality of bounding boxes, determining a first area image of the bounding box in the first image within a corresponding parking area;

[0018] A corresponding second region image is captured from the first region image according to the preset capture ratio.

[0019] In the disclosed embodiment, judging whether there is cross-parking parking in each parking area according to the target pixel area image includes:

[0020] Determining the proportion of pixels of each vehicle in the corresponding intercepted parking area through the target pixel area image and the fourth image;

[0021] It is determined whether there is cross-parking space parking in the parking area according to the proportion.

[0022] In the disclosed embodiment, judging whether there is cross-parking space parking in the parking area according to the proportion includes:

[0023] If the proportion is greater than the first preset proportion, or less than the second preset proportion, it is determined that there is no cross-parking parking in the parking area;

[0024] If the proportion is less than or equal to the first preset proportion, and the proportion is greater than or equal to the second preset proportion, it is determined that there is cross-parking parking in the parking area.

[0025] In the embodiment of the present disclosure, after determining whether there is cross-parking parking in each parking area according to the target pixel area image, the method further includes:

[0026] When it is determined that any parking area is continuously in a cross-parking parking state, an alarm message is sent to the client.

[0027] In an embodiment of the present disclosure, the method further includes:

[0028] For any one of the plurality of parking areas, when it is detected that the parking area is in a cross-parking space parking state, the number of cross-parking space parking times of the parking area is accumulated;

[0029] When the number of times of parking across parking spaces in the parking area reaches a preset number, it is determined that the parking area is continuously in a state of parking across parking spaces;

[0030] When the parking area is in an idle state or an occupied state, the number of times of parking across parking spaces in the parking area is cleared.

[0031] An embodiment of a second aspect of the present disclosure provides a device for identifying parking spaces across parking spaces, comprising:

[0032] An image acquisition module, used to acquire a first image captured by a target camera;

[0033] A bounding box adding module, used to add bounding boxes to the positions of multiple vehicles in the first image respectively to obtain a second image;

[0034] A regional image capture module, used to capture a regional image of each boundary box in the second image within a corresponding parking area according to a preset capture ratio; the preset capture ratio is set according to the angle of the target camera;

[0035] A pixel region labeling module, used for labeling the pixel region of each vehicle in the first image to obtain a third image;

[0036] An image segmentation module, used for segmenting a target pixel region image corresponding to the region image from the third image;

[0037] The cross-parking space parking judgment module is used to judge whether there is cross-parking space parking in each parking area according to the target pixel area image to obtain the camera image.

[0038] An embodiment of the third aspect of the present disclosure provides an electronic device, which includes a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the cross-parking space parking identification method described in the first aspect above by executing the computer instructions.

[0039] An embodiment of the fourth aspect of the present disclosure provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the method for identifying cross-parking space parking described in the first aspect.

[0040] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will become apparent from the following description or be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present disclosure. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.

[0042] In the attached picture:

[0043] Figure 1 A schematic diagram showing a flow chart of a method for identifying parking spaces across parking spaces provided by an embodiment of the present disclosure is shown;

[0044] Figure 2 A schematic diagram of adding a bounding box to a vehicle position provided by an embodiment of the present disclosure is shown;

[0045] Figure 3 A schematic diagram showing a method of obtaining a corresponding second region image from a first region image according to a preset capture ratio provided by an embodiment of the present disclosure;

[0046] Figure 4 A schematic diagram showing a parking area blocked by a vehicle provided by an embodiment of the present disclosure is shown;

[0047] Figure 5 A schematic diagram of marking a pixel area of ​​each vehicle in a first image provided by an embodiment of the present disclosure is shown;

[0048] Figure 6 A schematic diagram of a process of performing intersection processing on a regional image and a third image provided by an embodiment of the present disclosure is shown;

[0049] Figure 7 A schematic diagram showing a fourth image obtained by intercepting an image of each parking area in a calibration image according to a preset interception ratio provided by an embodiment of the present disclosure;

[0050] Figure 8 A schematic diagram showing intercepting a pre-captured image according to a preset interception ratio provided by an embodiment of the present disclosure is shown;

[0051] Fig. 9 A flowchart of a specific implementation method of determining whether there is cross-parking space parking provided by an embodiment of the present disclosure is shown;

[0052] Fig.10 A schematic diagram of the structure of a device for identifying parking spaces across parking spaces provided by an embodiment of the present disclosure is shown;

[0053] Fig.11 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown;

[0054] Fig.12 A schematic diagram of a storage medium provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0055] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0056] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in the present disclosure should have the common meanings understood by those skilled in the art to which the present disclosure belongs.

[0057] According to an embodiment of the present disclosure, an embodiment of a method for identifying cross-parking spaces is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0058] In this embodiment, a method for identifying parking spaces across parking spaces is provided, which can be used in a parking space management control unit of a parking lot. Figure 1 is a flow chart of a method for identifying parking spaces across parking spaces according to an embodiment of the present disclosure. Figure 1 As shown, the process includes the following steps:

[0059] Step S101, obtaining a first image captured by a target camera.

[0060] Specifically, the first image refers to an image containing one or more parking spaces captured by a target camera, for example Figure 2 The field of view of the target camera includes the complete parking area of ​​interest, such as Figure 2 The parking area is formed by the four coordinates a1, a2, a3 and a4.

[0061] Step S102: adding bounding boxes to the positions of multiple vehicles in the first image respectively to obtain a second image.

[0062] Specifically, a bounding box can be added to the position of each vehicle in the first image by using 2D detection technology, for example Figure 2 shown.

[0063] Step S102: capturing a region image of each boundary box in the second image within a corresponding parking area according to a preset capture ratio.

[0064] Specifically, the preset interception ratio is set according to the angle of the target camera. When the target camera is at different positions and / or different angles, the preset interception ratio is different. For example, when the target camera is directly in front of or behind the parking area, the preset interception ratio can be set to 1 / 3.

[0065] In some specific embodiments, the above step S102 includes steps S1021 and S1022:

[0066] Step S1021, for any one of the plurality of bounding boxes, determining a first area image of the bounding box in the first image within a corresponding parking area;

[0067] Step S1022: cropping the first region image to obtain a corresponding second region image according to the preset cropping ratio.

[0068] In the above steps S1021 and S1022, it is necessary to first determine the first area image of the boundary box in the parking area, for example Figure 3 Then the first region image is intercepted according to a preset interception ratio (eg, 1 / 3), thereby retaining 1 / 3 of the region in the first region image facing the camera as the second region image, for example Figure 3 The blue area in the

[0069] In the disclosed embodiment, the partial image of the vehicle boundary frame in the parking area is captured according to a preset capture ratio, which can avoid interference from the parking area being blocked by the vehicle, thereby affecting the determination of whether there is cross-parking parking in the parking area. Figure 4As shown, the parking area (white frame) at the front position of each vehicle is not blocked by the vehicle, while the parking area at the rear position is blocked by the vehicle. Therefore, it is necessary to intercept the image information of the unblocked parking area as a basis for judging whether there is cross-parking parking in the parking area; and the interception ratio needs to be set according to the target camera in different positions and / or different angles. For example: when the camera is at a higher position, the unblocked parking area captured by the camera is larger, and the interception ratio is also larger, for example, greater than 1 / 3; similarly, when the camera is at a lower position, the unblocked parking area captured by the camera is smaller, and the interception ratio is also smaller, for example, less than 1 / 3.

[0070] Step S103: annotate the pixel area of ​​each vehicle in the first image to obtain a third image.

[0071] Specifically, the pixel area of ​​each vehicle in the first image can be labeled by using instance segmentation technology, such as Figure 5 The yellow area, green area, blue area and purple area in the image.

[0072] Step S104: segmenting a target pixel region image corresponding to the region image from the third image.

[0073] Specifically, the target pixel region image can be obtained by performing intersection processing on the region image obtained in step S102 and the third image obtained in step S103. The specific intersection processing process is as follows: Figure 6 As shown: the area image b1 is intersected with the third image b2 in which the pixel areas of each vehicle are marked, so as to obtain the target pixel area image b3.

[0074] In some specific embodiments, the present invention needs to perform the following pre-operations before determining whether there is cross-parking parking in the parking area, namely:

[0075] Step c1, acquiring a calibration image under the condition that a plurality of parking spaces within the field of view of the target camera are in an unparked state.

[0076] Specifically, the parking area of ​​each parking space is marked in the calibration image, for example Figure 7 shown.

[0077] Step c2, intercepting the image of each parking area in the calibration image according to the preset interception ratio to obtain a fourth image; the fourth image includes multiple intercepted images of the parking area, such as Figure 7 shown.

[0078] Step S105 , judging whether there is cross-parking space parking in each parking area according to the target pixel area image.

[0079] In some specific embodiments, the above step S105 includes step S1051-step S1052:

[0080] Step S1051, determining the proportion of pixels of each vehicle in the corresponding intercepted parking area through the target pixel area image and the fourth image.

[0081] In some specific embodiments, the fourth image can be understood as being obtained by intercepting the pre-captured image according to a preset interception ratio, for example Figure 8 The pre-collected image refers to the image captured by the camera when the vehicle is parked correctly in the parking area, for example Figure 8 The "802" in the

[0082] In some specific embodiments, the percentage of each vehicle's pixels in the corresponding intercepted parking area can be understood as: what percentage of the vehicle's pixels are located in the area marked as the parking space. For example, there are 500 vehicle pixels in the vehicle image, and 600 parking area pixels in the parking space image. After data processing, it can be determined that 300 vehicle pixels fall in the parking area, and the percentage of vehicle pixels in the parking area is 300 / 500=60%.

[0083] Similarly, the target pixel area image in the embodiment of the present disclosure is equivalent to the pixel points falling in the parking area in the above example, and the fourth image in the embodiment of the present disclosure is equivalent to the pixels of the vehicle in the vehicle image in the above example. Therefore, the proportion can be calculated by the target pixel area image, the fourth image, and the following formula:

[0084] a=s1 / s2

[0085] Wherein, a represents a proportion, s1 represents the number of pixels in the above-mentioned target pixel area image, and s2 represents the number of pixels in the fourth image.

[0086] Step S1052, determining whether there is cross-parking space parking in the parking area according to the proportion.

[0087] In some specific embodiments, the above step S1052 includes step d1-step d2:

[0088] Step d1: If the proportion is greater than a first preset proportion, or less than a second preset proportion, it is determined that there is no cross-parking parking in the parking area.

[0089] Specifically, if the proportion is greater than the first preset proportion, it means that the parking area is occupied; if the proportion is less than the second preset proportion, it means that the parking area is vacant. The first preset proportion and the second preset proportion can be set according to actual conditions and are not specifically limited here. For example, the first preset proportion is 0.9 and the second preset proportion is 0.1.

[0090] Step d2: If the proportion is less than or equal to the first preset proportion, and the proportion is greater than or equal to the second preset proportion, it is determined that there is cross-parking space parking in the parking area.

[0091] In some specific embodiments, after determining whether there is cross-parking parking in each parking area according to the target pixel area image, the method further includes:

[0092] When it is determined that any parking area is continuously in a cross-parking parking state, an alarm message is sent to the client.

[0093] In some specific embodiments, the method further comprises:

[0094] For any one of the plurality of parking areas, when it is detected that the parking area is in a cross-parking space parking state, the number of cross-parking space parking times of the parking area is accumulated;

[0095] When the number of times of parking across parking spaces in the parking area reaches a preset number, it is determined that the parking area is continuously in a state of parking across parking spaces;

[0096] When the parking area is in an idle state or an occupied state, the number of times of parking across parking spaces in the parking area is cleared.

[0097] The disclosed embodiment also provides a specific implementation method for determining whether there is cross-parking parking, for example Fig. 9 As shown:

[0098] Pre-operation: The operation of this system requires some parameters to be set and calibrated. This system collects camera data. First, according to the camera angle, set the appropriate vehicle detection interception ratio. The camera field of view should include the complete parking space of interest, and the parking space of interest should be calibrated. Each parking space of interest is represented by four-point coordinates, and the four-point coordinates form a quadrilateral.

[0099] After parsing the camera data, AI visual analysis is performed on the image, including two parts, 2D detection and instance segmentation. A certain proportion of the 2D detection data is intercepted, and the part of the vehicle detection frame within the parking space quadrilateral is intercepted. The purpose of interception is to avoid interference from the parking space being blocked by the vehicle. After obtaining the data intercepted by the detection frame, it is intersected with the mask obtained by vehicle segmentation to obtain a partial segmentation mask of the vehicle. This mask is intersected with the parking space data calibrated in the pre-operation, and the percentage α of the vehicle pixels falling within the parking space is calculated. Based on this percentage, the three states of the parking space can be judged, such as Fig. 9 As shown: if α>0.9, the parking space is occupied, if α<0.1, the parking space is vacant, and if 0.1<α<0.9, it is a cross-parking space.

[0100] To avoid interference from vehicles entering and leaving the garage, the system will only issue an alarm when it detects that the parking space is continuously in a state of crossing parking spaces. Initialize a count. When the system detects that the parking space is in a state of crossing parking spaces, the count is +1. When the system detects that the parking space is in an idle or occupied state, the count is cleared. When the count reaches a certain value, it means that the parking space has been in a state of crossing parking spaces for a certain period of time. If this condition is met, the system will generate an alarm.

[0101] This system determines the parking space status through AI visual analysis, and identifies the parking space status through post-processing calculation based on the fused data by fusing 2D detection and segmentation results, cleverly avoiding the difficulty of parking spaces being blocked by vehicles. Compared with key point detection and monocular 3D detection, the 2D detection and segmentation results of vehicles are greatly improved, ensuring the accuracy of cross-parking space recognition.

[0102] Corresponding to the implementation of the above-mentioned method for identifying parking across parking spaces, the present disclosure also provides a device for identifying parking across parking spaces, which is used to implement the above-mentioned method. Figures 1 to 9 The method for identifying parking spaces across parking spaces described in any of the embodiments shown in the figure. Fig.10 As shown, the cross-parking space parking recognition device includes:

[0103] An image acquisition module, used to acquire a first image captured by a target camera;

[0104] A bounding box adding module, used to add bounding boxes to the positions of multiple vehicles in the first image respectively to obtain a second image;

[0105] A regional image capture module, used to capture a regional image of each boundary box in the second image within a corresponding parking area according to a preset capture ratio; the preset capture ratio is set according to the angle of the target camera;

[0106] A pixel region labeling module, used for labeling the pixel region of each vehicle in the first image to obtain a third image;

[0107] An image segmentation module, used for segmenting a target pixel region image corresponding to the region image from the third image;

[0108] The cross-parking space parking judgment module is used to judge whether there is cross-parking space parking in each parking area according to the target pixel area image to obtain the camera image.

[0109] Optionally, the device further comprises:

[0110] The fourth image acquisition module is used to acquire a calibration image under the condition that multiple parking spaces within the field of view of the target camera are in an unparked state; calibrate the parking area of ​​each parking space in the calibration image; intercept the image of each parking area in the calibration image according to the preset interception ratio to obtain a fourth image; the fourth image includes multiple intercepted images of the parking areas.

[0111] Optionally, the regional image capture module is further used to: determine, for any one of the multiple boundary boxes, a first regional image of the boundary box in the first image within the corresponding parking area; and capture a corresponding second regional image from the first regional image according to the preset capture ratio.

[0112] Optionally, the straddling parking space judgment module is further used to: determine the proportion of pixels of each vehicle in the corresponding intercepted parking area through the target pixel area image and the fourth image; and determine whether there is straddling parking space in the parking area based on the proportion.

[0113] Optionally, the straddling parking space judgment module is also used to: if the proportion is greater than a first preset proportion, or less than a second preset proportion, determine that there is no straddling parking in the parking area; if the proportion is less than or equal to the first preset proportion, and the proportion is greater than or equal to the second preset proportion, determine that there is straddling parking in the parking area.

[0114] Optionally, the device further includes: an alarm module, configured to send an alarm message to the client when it is determined that any parking area is continuously in a cross-parking space parking state.

[0115] Optionally, the device also includes: a data recording module, which is used for accumulating the number of cross-parking parking times in any one of the multiple parking areas when it is detected that the parking area is in a cross-parking parking state; when the number of cross-parking parking times in the parking area reaches a preset number, it is determined that the parking area is continuously in a cross-parking parking state; when the parking area is in an idle state or an occupied state, the number of cross-parking parking times in the parking area is cleared.

[0116] The apparatus for identifying cross-parking spaces provided in the above-mentioned embodiments of the present disclosure and the method for identifying cross-parking spaces provided in the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0117] The disclosed embodiment also provides an electronic device to execute the above-mentioned cross-parking space parking recognition method. Fig.11 , which shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. Fig.11 As shown, the electronic device 11 includes: a processor 1100, a memory 1101, a bus 1102 and a communication interface 1103, wherein the processor 1100, the communication interface 1103 and the memory 1101 are connected via the bus 1102; the memory 1101 stores a computer program that can be run on the processor 1100, and the processor 1100 executes the aforementioned Figures 1 to 9 A method for identifying cross-parking spaces provided by any of the illustrated embodiments.

[0118] The memory 1101 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 1103 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0119] The bus 1102 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 1101 is used to store programs. After receiving the execution instruction, the processor 1100 executes the program. Figures 1 to 9 The method for identifying cross-parking spaces disclosed in any of the illustrated embodiments may be applied to the processor 1100 or implemented by the processor 1100 .

[0120] The processor 1100 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 1100 or the instruction in the form of software. The above processor 1100 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or a combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 1101, and the processor 1100 reads the information in the memory 1101 and completes the steps of the above method in combination with its hardware.

[0121] The electronic device provided by the embodiment of the present disclosure and the method for identifying cross-parking spaces provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.

[0122] The present disclosure also provides a computer-readable storage medium corresponding to the method for identifying parking spaces across parking spaces provided in the above embodiments. Fig.12 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the method for identifying cross-parking spaces provided in any of the aforementioned embodiments will be executed.

[0123] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0124] The computer-readable storage medium provided in the above-mentioned embodiments of the present disclosure and the cross-parking space parking recognition method provided in the embodiments of the present disclosure are based on the same inventive concept, and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0125] It should be noted that:

[0126] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present disclosure can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.

[0127] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present disclosure, the various features of the present disclosure are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following schematic diagram: the claimed disclosure requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present disclosure.

[0128] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of this disclosure and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0129] The above is only a preferred specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for identifying parking spaces across parking spaces, characterized in that: The method comprises: Acquire a first image captured by a target camera; Adding bounding boxes to the positions of multiple vehicles in the first image respectively to obtain a second image; intercepting a regional image of each boundary box in the second image within a corresponding parking area according to a preset interception ratio; the preset interception ratio is set according to the angle of the target camera; Annotating a pixel region of each vehicle in the first image to obtain a third image; Segmenting a target pixel region image corresponding to the region image from the third image; It is determined whether there is cross-parking parking in each parking area according to the target pixel area image.

2. The method according to claim 1, characterized in that The method further comprises: Under the condition that a plurality of parking spaces within the field of view of the target camera are in an unparked state, a calibration image is acquired; a parking area of ​​each parking space is calibrated in the calibration image; The image of each parking area in the calibration image is intercepted according to the preset interception ratio to obtain a fourth image; the fourth image includes multiple intercepted images of the parking areas.

3. The method according to claim 1, characterized in that Intercepting a regional image of each boundary box in the second image within a corresponding parking area according to a preset interception ratio, including: For any one of the plurality of bounding boxes, determining a first area image of the bounding box in the first image within a corresponding parking area; A corresponding second region image is captured from the first region image according to the preset capture ratio.

4. The method according to claim 2, characterized in that: Judging whether there is cross-parking parking in each parking area according to the target pixel area image includes: Determining the proportion of pixels of each vehicle in the corresponding intercepted parking area through the target pixel area image and the fourth image; It is determined whether there is cross-parking space parking in the parking area according to the proportion.

5. The method according to claim 4, characterized in that Judging whether there is cross-parking space parking in the parking area according to the proportion includes: If the proportion is greater than the first preset proportion, or less than the second preset proportion, it is determined that there is no cross-parking parking in the parking area; If the proportion is less than or equal to the first preset proportion, and the proportion is greater than or equal to the second preset proportion, it is determined that there is cross-parking parking in the parking area.

6. The method according to claim 4 or 5, characterized in that: After determining whether there is cross-parking space parking in each parking area according to the target pixel area image, the method further includes: When it is determined that any parking area is continuously in a cross-parking parking state, an alarm message is sent to the client.

7. The method according to claim 6, characterized in that The method further comprises: For any one of the plurality of parking areas, when it is detected that the parking area is in a cross-parking space parking state, the number of cross-parking space parking times of the parking area is accumulated; When the number of times of parking across parking spaces in the parking area reaches a preset number, it is determined that the parking area is continuously in a state of parking across parking spaces; When the parking area is in an idle state or an occupied state, the number of times of parking across parking spaces in the parking area is cleared.

8. A parking recognition device for crossing parking spaces, characterized in that: The device comprises: An image acquisition module, used to acquire a first image captured by a target camera; A bounding box adding module, used to add bounding boxes to the positions of multiple vehicles in the first image respectively to obtain a second image; A regional image capture module, used to capture a regional image of each boundary box in the second image within a corresponding parking area according to a preset capture ratio; the preset capture ratio is set according to the angle of the target camera; A pixel region labeling module, used for labeling the pixel region of each vehicle in the first image to obtain a third image; An image segmentation module, used for segmenting a target pixel region image corresponding to the region image from the third image; The cross-parking space parking judgment module is used to judge whether there is cross-parking space parking in each parking area according to the target pixel area image to obtain the camera image.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for identifying cross-parking spaces according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method for identifying cross-parking spaces according to any one of claims 1 to 7.

Images