CN113570872B - Processing method and device for blocking parking space event - Google Patents
Processing method and device for blocking parking space event Download PDFInfo
- Publication number
- CN113570872B CN113570872B CN202110929115.9A CN202110929115A CN113570872B CN 113570872 B CN113570872 B CN 113570872B CN 202110929115 A CN202110929115 A CN 202110929115A CN 113570872 B CN113570872 B CN 113570872B
- Authority
- CN
- China
- Prior art keywords
- parking space
- vehicle
- image
- space image
- parking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the application discloses a method and a device for processing a parking space blocking event, which are used for reducing the occurrence of a parking space management problem caused by the fact that a parking space is blocked. The method in the embodiment of the application comprises the following steps: acquiring a first parking space image through a main image extraction device; acquiring a second parking space image through a side auxiliary image extraction device; determining parking space coordinates of parking spaces in the first parking space image and the second parking space image and parking space identity marks corresponding to the parking spaces; judging whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identity mark; if the first parking space image and the second parking space image exist, judging whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity mark by the first parking space image and the second parking space image is an occlusion type; if yes, generating a parking space shielding alarm according to the vehicle type and the parking space identity.
Description
Technical Field
The embodiment of the application relates to the field of parking space management, in particular to a method and a device for processing a blocking parking space event.
Background
In recent years, with economic growth, the living standard of people is increasing year by year, and the automobile industry is rapidly developing, resulting in the year by year rise of motor vehicles on roads.
As motor vehicles have become the vehicle of choice for people to travel, parking spaces have become an important infrastructure. With the increase of traveling vehicles, how to efficiently manage parking spaces becomes more and more important. The parking stall intelligent management technique's proposition uses high-order video technique management parking stall at present, monitors the sample through high-order image extraction element to the parking stall region promptly, discerns and the record to the parking vehicle.
However, the environments of the high-position roadside area and the high-position parking area are complex, when the high-position image extraction device monitors and samples the parking space areas, if a large motor vehicle enters the parking space of the area, other parking spaces can be shielded or the high-position image extraction device is shielded, at this time, if other motor vehicles enter the shielded parking space to park, the recognition and the recording of the high-position image extraction device on the vehicle can be influenced, and therefore the problem of parking space management is caused.
Disclosure of Invention
The first aspect of the embodiments of the present application provides a method for processing a parking space blocking event, where the method includes:
acquiring a first parking space image through a main high-level image extraction device;
acquiring a second parking space image through a side auxiliary high-level image extraction device, wherein the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
determining parking space coordinates of parking spaces in the first parking space image and the second parking space image and parking space identification marks corresponding to the parking spaces, wherein the parking space coordinates are area information of the parking spaces corresponding to the parking space identification marks in the first parking space image and the second parking space image;
judging whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identity mark or not;
if the first parking space image and the second parking space image exist, judging whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity mark by the first parking space image and the second parking space image is an occlusion type;
if yes, generating a parking space shielding alarm according to the vehicle type and the parking space identity.
Optionally, the determining whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identification includes:
and judging whether the same target vehicle exists on the parking space coordinate corresponding to the same parking space identity in the first parking space image and the second parking space image or not through a vehicle detection neural network model.
Optionally, the determining whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity identifier by the first parking space image and the second parking space image is an occlusion type includes:
generating first and second vehicle type data for the first and second parking space images according to a vehicle recognition neural network model, the first vehicle type data representing a vehicle type of the target vehicle in the first parking space image, the second vehicle type data representing a vehicle type of the target vehicle in the second parking space image;
and judging whether the vehicle type of the target vehicle is an occlusion type or not according to the first vehicle type data and the second vehicle type data.
Optionally, before generating the parking space blocking alarm according to the vehicle type information and the parking space identification, after determining whether the vehicle type of the target vehicle, which is displayed on the parking space coordinate corresponding to the same vehicle identification by the first parking space image and the second parking space image, is a blocking type, the processing method further includes:
judging whether the number of times that the vehicle type of the target vehicle is determined to be the shielding type reaches a preset threshold value or not;
if not, acquiring images again through the main high-level image extraction device and the side auxiliary high-level image extraction device to judge the type of the vehicle;
if yes, judging whether the vehicle type of the target vehicle is an occlusion type or not according to the first vehicle type data and the second vehicle type data.
Optionally, after the parking space shielding alarm is generated according to the vehicle type and the parking space identification, the processing method further includes:
and sending the parking space shielding alarm to a parking lot platform.
The second aspect of the embodiments of the present application provides a processing apparatus for blocking a parking space event, which includes:
a first acquisition unit configured to acquire a first parking space image by the master high-level image extraction device;
the second acquisition unit is used for acquiring a second parking space image through a side auxiliary high-level image extraction device, and the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
a determining unit, configured to determine parking space coordinates of parking spaces in the first parking space image and the second parking space image and a parking space identity corresponding to the parking spaces, where the parking space coordinates are area information of the parking spaces corresponding to the parking space identity in the first parking space image and the second parking space image;
the first judging unit is used for judging whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identity mark or not;
a second judging unit, configured to judge whether a vehicle type of a target vehicle displayed on the parking space coordinate corresponding to the same vehicle identifier by the first parking space image and the second parking space image is an occlusion type when the first judging unit determines that the same target vehicle exists on the parking space coordinate corresponding to the same vehicle identifier by the first parking space image and the second parking space image;
and a generating unit, configured to generate a parking space shielding alarm according to the vehicle type and the parking space identification when the second determining unit determines that the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identification by the first parking space image and the second parking space image is a shielding type.
Optionally, the first determining unit specifically includes:
and judging whether the same target vehicle exists on the parking space coordinate corresponding to the same parking space identity in the first parking space image and the second parking space image or not through a vehicle detection neural network model.
Optionally, the second determining unit includes:
generating first and second vehicle type data for the first and second parking space images according to a vehicle recognition neural network model, the first vehicle type data representing a vehicle type of the target vehicle in the first parking space image, the second vehicle type data representing a vehicle type of the target vehicle in the second parking space image;
and judging whether the vehicle type of the target vehicle is an occlusion type or not according to the first vehicle type data and the second vehicle type data.
Optionally, the processing apparatus further includes:
and the third judging unit is used for judging whether the frequency of the vehicle type of the target vehicle determined as the shielding type reaches a preset threshold value.
Optionally, the processing apparatus further includes:
and the sending unit is used for sending the parking space shielding alarm to the parking lot platform.
A third aspect of the embodiments of the present application provides a processing apparatus for blocking a parking space event, including:
the device comprises a processor, a memory, an input and output unit and a bus;
the processor is connected with the memory, the input and output unit and the bus;
the processor specifically performs the following operations:
acquiring a first parking space image through a main high-level image extraction device;
acquiring a second parking space image through a side auxiliary high-position image extraction device, wherein the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
determining parking space coordinates of parking spaces in the first parking space image and the second parking space image and parking space identification marks corresponding to the parking spaces, wherein the parking space coordinates are area information of the parking spaces corresponding to the parking space identification marks in the first parking space image and the second parking space image;
judging whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identity mark;
if yes, judging whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity mark by the first parking space image and the second parking space image is a shielding type;
if yes, generating a parking space shielding alarm according to the vehicle type and the parking space identity.
Optionally, the processor is further configured to perform the operations of any of the alternatives of the first aspect.
A computer readable storage medium having a program stored thereon, the program, when executed on a computer, performing the method of the first aspect as well as any of the alternatives of the first aspect.
According to the technical scheme, the embodiment of the application has the following advantages:
the method comprises the steps of obtaining a first parking space image through a main high-level image extraction device, obtaining a second parking space image through a side auxiliary high-level image extraction device, and obtaining real-time images of the same parking area at different angles respectively. And then determining the parking space coordinates of the parking spaces in the first parking space image and the second parking space image and the parking space identity corresponding to the parking spaces, namely determining the frame of the same parking space in the two real-time images with different angles and the parking space identity of the parking space. And judging whether the same target vehicle exists on the parking space coordinate corresponding to the same vehicle identity mark of the first parking space image and the second parking space image, if so, judging whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity mark of the first parking space image and the second parking space image is a shielding type, and if so, generating a parking space shielding alarm according to the vehicle type and the parking space identity mark. The real-time images of the same parking area at different angles are obtained through the main high-level image extraction device and the side auxiliary high-level image extraction device, whether the type of a vehicle on a parking space in the images is a sheltering type or not is determined, if the type of the vehicle is determined to be a sheltering type from the real-time images at different angles, a parking space sheltering warning needs to be generated, so that relevant personnel can take corresponding measures in time, and the problem of parking space management caused by the fact that the parking space is sheltered is reduced.
Drawings
Fig. 1 is a schematic flowchart illustrating an embodiment of a method for processing a blocked parking space event according to an embodiment of the present application;
fig. 2 is a schematic flowchart illustrating another embodiment of a processing method for blocking a parking space event according to the embodiment of the present application;
FIG. 3 is a flowchart illustrating an embodiment of a device for processing a blocked parking space event according to the present application;
fig. 4 is a schematic flowchart of another embodiment of a processing apparatus for blocking a parking space event in the embodiment of the present application;
fig. 5 is a flowchart illustrating another embodiment of a processing device for blocking a parking space event in the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
The embodiment of the application discloses a method and a device for processing a parking space blocking event, which are used for reducing the occurrence of parking space management problems caused by the fact that a parking space is blocked.
In this embodiment, the method for processing the parking space blocking event may be implemented in a system, may be implemented in a server, may also be implemented in a terminal, and is not specifically limited. For convenience of description, the embodiment of the present application uses a terminal as an example for description of an execution subject.
Referring to fig. 1, an embodiment of the present application provides a method for processing a parking stall blocking event, including:
101. acquiring a first parking space image through a main high-level image extraction device;
the terminal obtains a first parking space image through a main high-level image extraction device, and the main high-level image extraction device is used for obtaining an image of a parked vehicle on each parking space in a parking area so as to obtain vehicle information capable of identifying the vehicle. In an actual scene, the main high-level image extraction device is mainly a high-level camera, and the parking space image shooting is carried out by rotating the camera. The shooting angle of the main high-level image extraction device is mainly related to the arrangement mode of the parking spaces, when the parking spaces are arranged in a serial mode of head-to-tail connection (for example, the parking spaces beside a road), the installation position of the main high-level image extraction device is in a linear area extending from the parking spaces, the shooting angle is parallel to the parking spaces, and therefore the license plate information and the vehicle type information of the parking vehicles can be shot. When parking spaces are arranged in a parallel manner with right and left sides in contact with each other (for example, parking spaces in indoor parking lots), the main high-level image pickup device is installed in a region diagonally to the parking spaces, and the imaging angle is also diagonally. The installation position and the shooting angle of the main high-level image extraction device are closely related to the arrangement mode of the parking spaces, the two modes are only main modes, and any shooting mode of the main high-level image extraction device for acquiring the vehicle information of the vehicle on the parking spaces belongs to the protection scope of the embodiment.
The vehicle information includes license plate information, vehicle type information, vehicle color, and the like, and is not limited herein.
102. Acquiring a second parking space image through a side auxiliary high-position image extraction device, wherein the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
the terminal acquires a second parking space image through the side auxiliary high-level image extraction device, and the side auxiliary high-level image extraction device is mainly used for acquiring an image of another angle of the vehicle on the parking space through a shooting angle different from that of the main high-level image extraction device. The side auxiliary high-level image extraction device and the main high-level image extraction device have the functions of shooting images of vehicles on parking spaces, and the main difference is that the shooting positions and the shooting angles are different.
103. Determining parking space coordinates of parking spaces in the first parking space image and the second parking space image and parking space identification marks corresponding to the parking spaces, wherein the parking space coordinates are area information of the parking spaces corresponding to the parking space identification marks in the first parking space image and the second parking space image;
the terminal determines parking space coordinates of parking spaces in the first parking space image and the second parking space image and parking space identity marks corresponding to the parking spaces, the main high-level image extraction device and the side auxiliary high-level image extraction device mainly acquire images of the parking spaces at different angles, and the terminal needs to match parking space frames in the two images and determine marks (parking space identity marks) and areas (parking space coordinates) corresponding to the parking spaces in the two images. In actual operation, the parking spaces in the photos need to be depicted, each frame on the image represents a parking space coordinate of one parking space, and each frame has a parking space identity.
The specific operation mode can be that the parking space frame is obtained by comparing the parking space frame with the historical parking space image, wherein the historical parking space is the parking space image without vehicles, and the parking space frame of the image shot by the main high-level image extraction device and the side auxiliary high-level image in real time can be obtained by comparing the parking space frame with the parking space image without vehicles. Or may be reversely drawn through an existing frame in the image captured in real time, which is not limited herein.
104. Judging whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identity mark; if yes, go to step 105;
the terminal judges whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identity mark, namely after the terminal marks the parking space coordinate of the same parking space identity mark of the two images, the terminal judges whether the characteristic of the vehicle exists on the whole parking space coordinate and determines whether the vehicle is the same vehicle. The specific determination method may be to perform image feature analysis through a convolutional neural network, or to determine the occlusion degree and the occlusion profile of the parking space frame, which is not limited herein.
105. If the first parking space image and the second parking space image exist, judging whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity mark by the first parking space image and the second parking space image is an occlusion type; if yes, go to step 106;
when the terminal determines that the same target vehicle exists in the first parking space image and the second parking space image on the parking space coordinate corresponding to the same vehicle identity identification, the terminal judges whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity identification by the first parking space image and the second parking space image is the shielding type. Whether the occlusion type is determined mainly by determining the vehicle volume of the target vehicle, and the specific determination method may be performing image feature analysis through a convolutional neural network, or determining the occlusion degree and the occlusion profile of the parking space frame, which is not limited herein.
106. If yes, generating a parking space shielding alarm according to the vehicle type and the parking space identity.
When the terminal determines that the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identification by the first parking space image and the second parking space image is the shielding type, a parking space shielding alarm needs to be generated according to the vehicle type and the parking space identification, so that a worker on a parking space site can check the parking space of the parking space identification and take corresponding measures.
The method comprises the steps of obtaining a first parking space image through a main high-level image extraction device, obtaining a second parking space image through a side auxiliary high-level image extraction device, namely obtaining real-time images of the same parking area at different angles respectively. And then determining the parking space coordinates of the parking spaces in the first parking space image and the second parking space image and the parking space identity corresponding to the parking spaces, namely determining the frame of the same parking space in the two real-time images with different angles and the parking space identity of the parking space. And judging whether the same target vehicle exists on the parking space coordinate corresponding to the same vehicle identity identification of the first parking space image and the second parking space image, if so, judging whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity identification of the first parking space image and the second parking space image is a shielding type, and if so, generating a parking space shielding alarm according to the vehicle type and the parking space identity identification. The real-time images of the same parking area at different angles are obtained through the main high-level image extraction device and the side auxiliary high-level image extraction device, whether the type of a vehicle on a parking space in the images is a sheltering type or not is determined, if the type of the vehicle is determined to be a sheltering type from the real-time images at different angles, a parking space sheltering warning needs to be generated, so that relevant personnel can take corresponding measures in time, and the problem of parking space management caused by the fact that the parking space is sheltered is reduced.
Referring to fig. 2, an embodiment of the present application provides a method for processing a parking stall blocking event, including:
201. acquiring a first parking space image through a main high-level image extraction device;
202. acquiring a second parking space image through a side auxiliary high-level image extraction device, wherein the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
203. determining parking space coordinates of parking spaces in the first parking space image and the second parking space image and parking space identification marks corresponding to the parking spaces, wherein the parking space coordinates are area information of the parking spaces corresponding to the parking space identification marks in the first parking space image and the second parking space image;
steps 201 to 203 in this embodiment are similar to steps 101 to 103 in the previous embodiment, and are not described again here.
204. Judging whether the same target vehicle exists on the parking space coordinate corresponding to the same parking space identity in the first parking space image and the second parking space image or not through a vehicle detection neural network model; if yes, go to step 205; if not, ending;
the terminal judges whether the same target vehicle exists on the parking space coordinate corresponding to the same parking space identity in the first parking space image and the second parking space image or not through the vehicle detection neural network model, specifically, the first parking space image and the second parking space image are input into the vehicle detection neural network model, whether the vehicle exists on the parking space coordinate or not is determined through extraction and comparison of vehicle characteristics, whether the vehicles of the two images are the same vehicle or not is determined, and if the vehicles are the same target vehicle, the next step can be carried out. The vehicle detection neural network model is mainly used for detecting the characteristics of the vehicle, and can analyze each characteristic in the image, determine whether the vehicle characteristics exist in the image, and further determine whether the vehicle characteristics of the two images in the same parking space coordinate area are the same vehicle.
205. If so, generating first vehicle type data and second vehicle type data for the first parking space image and the second parking space image according to the vehicle recognition neural network model, wherein the first vehicle type data represent the vehicle type of the target vehicle in the first parking space image, and the second vehicle type data represent the vehicle type of the target vehicle in the second parking space image;
and when the terminal determines that the same target vehicle exists on the parking space coordinate corresponding to the same parking space identity in the first parking space image and the second parking space image through the vehicle detection neural network model, generating first vehicle type data and second vehicle type data for the first parking space image and the second parking space image according to the vehicle identification neural network model. And inputting the first parking space image and the second parking space image into a vehicle recognition neural network model, extracting vehicle characteristics, analyzing which vehicle type corresponds to the vehicle characteristics, and finally generating first vehicle type data and second vehicle type data.
206. Judging whether the vehicle type of the target vehicle is an occlusion type or not according to the first vehicle type data and the second vehicle type data; if yes, go to step 207; if not, ending;
the terminal judges whether the vehicle type of the target vehicle is an occlusion type according to the first vehicle type data and the second vehicle type data, specifically, the terminal determines whether the first vehicle type data and the second vehicle type data are consistent to be the occlusion type, and if so, step 207 is executed.
207. If so, judging whether the number of times that the vehicle type of the target vehicle is determined to be the shielding type reaches a preset threshold value or not; if yes, go to step 208; if not, go to step 201;
when the terminal determines whether the first vehicle type data and the second vehicle type data are consistent as the shielding type, whether the number of times of determining the vehicle type of the target vehicle as the shielding type reaches a preset threshold value is judged, so that the vehicle type of the target vehicle is determined for multiple times, and the error rate is low.
208. If yes, generating a parking space shielding alarm according to the type of the vehicle and the parking space identity;
step 208 in this embodiment is similar to step 106 in the previous embodiment, and is not described herein again.
209. And sending the parking space shielding alarm to the parking lot platform.
The terminal sends the parking space shielding alarm to the parking lot platform and records the event.
The method comprises the steps of obtaining a first parking space image through a main high-level image extraction device, obtaining a second parking space image through a side auxiliary high-level image extraction device, namely obtaining real-time images of the same parking area at different angles respectively. And then determining the parking space coordinates of the parking spaces in the first parking space image and the second parking space image and the parking space identity corresponding to the parking spaces, namely determining the frame of the same parking space in the two real-time images with different angles and the parking space identity of the parking space. And judging whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identity through the vehicle detection neural network model, if so, judging whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity by the first parking space image and the second parking space image is a shielding type through the vehicle identification neural network model, and if so, generating a parking space shielding alarm according to the vehicle type and the parking space identity. The real-time images of the same parking area at different angles are obtained through the main high-level image extraction device and the side auxiliary high-level image extraction device, whether the type of a vehicle on a parking space in the images is a sheltering type or not is determined, if the type of the vehicle is determined to be a sheltering type from the real-time images at different angles, a parking space sheltering warning needs to be generated, so that relevant personnel can take corresponding measures in time, and the problem of parking space management caused by the fact that the parking space is sheltered is reduced.
And secondly, analyzing and identifying the vehicle characteristics of the image through a vehicle detection neural network model and a vehicle identification neural network model, and increasing the identification speed.
Referring to fig. 3, an embodiment of the present application provides a device for processing a parking space blocking event, including:
a first acquisition unit 301 configured to acquire a first parking space image by the master high-level image extraction device;
a second obtaining unit 302, configured to obtain a second parking space image through the side-assisted high-level image extraction device, where the first parking space image and the second parking space image are real-time images of the same parking area from different angles;
the determining unit 303 is configured to determine a parking space coordinate of a parking space in the first parking space image and the second parking space image and a parking space identity corresponding to the parking space, where the parking space coordinate is area information of the parking space corresponding to the parking space identity in the first parking space image and the second parking space image;
a first determining unit 304, configured to determine whether the first parking space image and the second parking space image have the same target vehicle in a parking space coordinate corresponding to the same vehicle identity;
a second judging unit 305, configured to judge whether a vehicle type of a target vehicle displayed on a parking space coordinate corresponding to the same vehicle identifier by the first parking space image and the second parking space image is an occlusion type when the first judging unit determines that the same target vehicle exists on the parking space coordinate corresponding to the same vehicle identifier by the first parking space image and the second parking space image;
the generating unit 306 is configured to generate a parking space shielding alarm according to the vehicle type and the parking space identifier when the second determining unit determines that the vehicle type of the target vehicle, which is displayed on the parking space coordinate corresponding to the same vehicle identifier by the first parking space image and the second parking space image, is the shielding type.
Referring to fig. 4, an embodiment of the present application provides another processing apparatus for blocking a parking space event, including:
a first obtaining unit 401, configured to obtain a first parking space image through the master high-level image extraction device;
a second obtaining unit 402, configured to obtain a second parking space image through a side-assisted high-level image extraction device, where the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
a determining unit 403, configured to determine a parking space coordinate of a parking space in the first parking space image and the second parking space image and a parking space identity corresponding to the parking space, where the parking space coordinate is area information of the parking space corresponding to the parking space identity in the first parking space image and the second parking space image;
a first determining unit 404, configured to determine whether the first parking space image and the second parking space image have the same target vehicle on a parking space coordinate corresponding to the same vehicle identity;
optionally, the first determining unit 404 specifically includes:
and judging whether the same target vehicle exists on the parking space coordinate corresponding to the same parking space identity in the first parking space image and the second parking space image or not through the vehicle detection neural network model.
The second determining unit 405 is configured to determine whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identifier by the first parking space image and the second parking space image is an occlusion type when the first determining unit determines that the same target vehicle exists on the parking space coordinate corresponding to the same vehicle identifier by the first parking space image and the second parking space image.
Optionally, the second determining unit 405 specifically includes:
generating first vehicle type data and second vehicle type data for the first parking space image and the second parking space image according to the vehicle recognition neural network model, wherein the first vehicle type data represent the vehicle type of the target vehicle in the first parking space image, and the second vehicle type data represent the vehicle type of the target vehicle in the second parking space image;
and judging whether the vehicle type of the target vehicle is an occlusion type or not according to the first vehicle type data and the second vehicle type data.
A third judging unit 406, configured to judge whether the number of times that the vehicle type of the target vehicle is determined to be the occlusion type reaches a preset threshold;
the first obtaining unit 401 is further configured to obtain a first parking space image through the master high-level image extracting device when the third determining unit 406 determines that the number of times that the vehicle type of the target vehicle is determined to be the shielding type does not reach the preset threshold;
a generating unit 407, configured to generate a parking space shielding alarm according to the vehicle type and the parking space identity when the third determining unit 406 determines that the number of times that the vehicle type of the target vehicle is determined to be the shielding type reaches a preset threshold;
a sending unit 408, configured to send the parking space blocking alarm to the parking lot platform.
Referring to fig. 5, an embodiment of the present application provides another processing apparatus for blocking a parking space event, including:
a processor 501, a memory 502, an input/output unit 503, and a bus 504;
the processor 501 is connected with the memory 502, the input/output unit 503 and the bus 504;
the processor 501 specifically performs the following operations:
acquiring a first parking space image through a main high-level image extraction device;
acquiring a second parking space image through a side auxiliary high-level image extraction device, wherein the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
determining parking space coordinates of parking spaces in the first parking space image and the second parking space image and parking space identification marks corresponding to the parking spaces, wherein the parking space coordinates are area information of the parking spaces corresponding to the parking space identification marks in the first parking space image and the second parking space image;
judging whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same vehicle identity mark;
if the first parking space image and the second parking space image exist, judging whether the vehicle type of the target vehicle displayed on the parking space coordinate corresponding to the same vehicle identity mark by the first parking space image and the second parking space image is an occlusion type;
if yes, generating a parking space shielding alarm according to the vehicle type and the parking space identity.
In this embodiment, the functions of the processor 501 correspond to the steps in the embodiments shown in fig. 1 to fig. 2, and are not described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one type of logical functional division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
Claims (2)
1. A method for processing a blocked parking space event is characterized by comprising the following steps:
acquiring a first parking space image through a main high-level image extraction device;
acquiring a second parking space image through a side auxiliary high-level image extraction device, wherein the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
determining parking space coordinates of parking spaces in the first parking space image and the second parking space image and parking space identification marks corresponding to the parking spaces, wherein the parking space coordinates are area information of the parking spaces corresponding to the parking space identification marks in the first parking space image and the second parking space image;
judging whether the same target vehicle exists on the parking space coordinate corresponding to the same parking space identity in the first parking space image and the second parking space image or not through a vehicle detection neural network model;
if the first parking space image and the second parking space image exist, generating first vehicle type data and second vehicle type data for the first parking space image and the second parking space image according to a vehicle identification neural network model, wherein the first vehicle type data represent the vehicle type of the target vehicle in the first parking space image, and the second vehicle type data represent the vehicle type of the target vehicle in the second parking space image;
judging whether the vehicle type of the target vehicle is an occlusion type or not according to the first vehicle type data and the second vehicle type data;
judging whether the number of times that the vehicle type of the target vehicle is determined to be the shielding type reaches a preset threshold value or not;
if not, acquiring images again through the main high-level image extraction device and the side auxiliary high-level image extraction device to judge the type of the vehicle;
if yes, judging whether the vehicle type of the target vehicle is an occlusion type or not according to the first vehicle type data and the second vehicle type data;
if the vehicle type of the target vehicle is the shielding type, generating a parking space shielding alarm according to the vehicle type and the parking space identity;
and sending the parking space shielding alarm to a parking lot platform.
2. A device for processing a blocked parking space event, comprising:
a first acquisition unit configured to acquire a first parking space image by the master high-level image extraction device;
the second acquisition unit is used for acquiring a second parking space image through a side auxiliary high-level image extraction device, and the first parking space image and the second parking space image are real-time images of the same parking area at different angles;
a determining unit, configured to determine parking space coordinates of parking spaces in the first parking space image and the second parking space image and a parking space identity corresponding to the parking spaces, where the parking space coordinates are area information of the parking spaces corresponding to the parking space identity in the first parking space image and the second parking space image;
the first judging unit is used for judging whether the first parking space image and the second parking space image have the same target vehicle on the parking space coordinate corresponding to the same parking space identity mark or not;
the first judgment unit includes:
judging whether the same target vehicle exists on the parking space coordinate corresponding to the same parking space identity in the first parking space image and the second parking space image or not through a vehicle detection neural network model;
a second determination unit including:
generating first and second vehicle type data for the first and second parking space images according to a vehicle recognition neural network model, the first vehicle type data representing a vehicle type of the target vehicle in the first parking space image, the second vehicle type data representing a vehicle type of the target vehicle in the second parking space image;
judging whether the vehicle type of the target vehicle is an occlusion type or not according to the first vehicle type data and the second vehicle type data;
the third judgment unit is used for judging whether the number of times that the vehicle type of the target vehicle is determined to be the shielding type reaches a preset threshold value or not;
the generating unit is used for generating a parking space shielding alarm according to the vehicle type and the parking space identity when the third judging unit determines whether the number of times that the vehicle type of the target vehicle is determined to be the shielding type reaches a preset threshold value;
and the sending unit is used for sending the parking space shielding alarm to the parking lot platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110929115.9A CN113570872B (en) | 2021-08-13 | 2021-08-13 | Processing method and device for blocking parking space event |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110929115.9A CN113570872B (en) | 2021-08-13 | 2021-08-13 | Processing method and device for blocking parking space event |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113570872A CN113570872A (en) | 2021-10-29 |
| CN113570872B true CN113570872B (en) | 2022-10-14 |
Family
ID=78171578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110929115.9A Active CN113570872B (en) | 2021-08-13 | 2021-08-13 | Processing method and device for blocking parking space event |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113570872B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894529A (en) * | 2016-06-03 | 2016-08-24 | 北京精英智通科技股份有限公司 | Parking lot state detection method, device and system |
| WO2018076281A1 (en) * | 2016-10-28 | 2018-05-03 | 富士通株式会社 | Detection method and detection apparatus for parking space status, and electronic device |
| JP2021051460A (en) * | 2019-09-24 | 2021-04-01 | パナソニックＩｐマネジメント株式会社 | Information processing device, information processing system, arrangement plan method, and arrangement plan program |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8139115B2 (en) * | 2006-10-30 | 2012-03-20 | International Business Machines Corporation | Method and apparatus for managing parking lots |
| EP2184208A4 (en) * | 2007-07-31 | 2012-11-21 | Toyota Jidoshokki Kk | Parking assistance device, vehicle-side device for parking assistance device, parking assistance method, and parking assistance program |
| US9129524B2 (en) * | 2012-03-29 | 2015-09-08 | Xerox Corporation | Method of determining parking lot occupancy from digital camera images |
| CN103473950B (en) * | 2012-06-06 | 2017-04-12 | 刘鉵 | Parking lot parking space monitoring method |
| US11244171B2 (en) * | 2014-01-22 | 2022-02-08 | Conduent Business Services Llc | Video-based system for automated detection of double parking violations |
| CN106023594A (en) * | 2016-06-13 | 2016-10-12 | 北京精英智通科技股份有限公司 | Parking stall shielding determination method and device and vehicle management system |
| CN105869182B (en) * | 2016-06-17 | 2018-10-09 | 北京精英智通科技股份有限公司 | A kind of parking stall condition detection method and system |
| CN108305466B (en) * | 2018-03-13 | 2020-05-08 | 北京智芯原动科技有限公司 | Roadside parking detection method and device based on vehicle characteristic analysis |
| CN111899558A (en) * | 2020-07-28 | 2020-11-06 | 北京筑梦园科技有限公司 | Parking space management method, server and parking management system |
| CN111899559B (en) * | 2020-07-28 | 2024-01-09 | 北京筑梦园科技有限公司 | Parking space management method, server and parking management system |
| CN112509364B (en) * | 2020-11-17 | 2021-11-09 | 北京精英路通科技有限公司 | Method and device for determining parking state of vehicle, computer equipment and storage medium |
| CN112804519A (en) * | 2020-12-28 | 2021-05-14 | 深圳市捷顺科技实业股份有限公司 | Camera shielding detection method and device, electronic equipment and channel gate |
| CN112927556B (en) * | 2021-02-01 | 2022-06-17 | 深圳市捷顺科技实业股份有限公司 | Monitoring system for high-order video curb parking |
| CN113052008A (en) * | 2021-03-01 | 2021-06-29 | 深圳市捷顺科技实业股份有限公司 | Vehicle weight recognition method and device |
-
2021
- 2021-08-13 CN CN202110929115.9A patent/CN113570872B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894529A (en) * | 2016-06-03 | 2016-08-24 | 北京精英智通科技股份有限公司 | Parking lot state detection method, device and system |
| WO2018076281A1 (en) * | 2016-10-28 | 2018-05-03 | 富士通株式会社 | Detection method and detection apparatus for parking space status, and electronic device |
| JP2021051460A (en) * | 2019-09-24 | 2021-04-01 | パナソニックＩｐマネジメント株式会社 | Information processing device, information processing system, arrangement plan method, and arrangement plan program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113570872A (en) | 2021-10-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8682036B2 (en) | System and method for street-parking-vehicle identification through license plate capturing | |
| US8744132B2 (en) | Video-based method for detecting parking boundary violations | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| CN105493502A (en) | Video monitoring method, video monitoring system, and computer program product | |
| CN114037924A (en) | Vehicle brake-passing judgment method based on image recognition technology and related device | |
| CN113055823B (en) | Method and device for managing shared bicycle based on road side parking | |
| WO2016201804A1 (en) | Object positioning method and device | |
| CN112733598A (en) | Vehicle law violation determination method and device, computer equipment and storage medium | |
| CN113139410B (en) | Pavement detection method, device, equipment and storage medium | |
| CN110880205B (en) | Parking charging method and device | |
| CN111985295A (en) | Electric bicycle behavior recognition method and system, industrial personal computer and camera | |
| CN111768630A (en) | Violation waste image detection method and device and electronic equipment | |
| CN113408364B (en) | Temporary license plate recognition method, system, device and storage medium | |
| CN113570872B (en) | Processing method and device for blocking parking space event | |
| CN110619256A (en) | Road monitoring detection method and device | |
| CN113076852A (en) | Vehicle-mounted snapshot processing system occupying bus lane based on 5G communication | |
| CN112183206A (en) | Traffic participant positioning method and system based on roadside monocular camera | |
| CN115880632A (en) | Timeout stay detection method, monitoring device, computer-readable storage medium, and chip | |
| CN113449624B (en) | Method and device for determining vehicle behavior based on pedestrian re-identification | |
| CN115909313A (en) | Illegal parking board identification method and device based on deep learning | |
| CN114863372A (en) | Parking management method, parking management device and computer readable storage medium | |
| CN113870185A (en) | Image processing method based on image snapshot, terminal and storage medium | |
| CN113052058A (en) | Vehicle-mounted passenger flow statistical method and device and storage medium | |
| CN112347853A (en) | License plate data desensitization method based on video, storage medium and server | |
| CN113963571B (en) | Method and device for processing identification event of vehicle entering and exiting parking lot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |