CN114360288A - AI-based garage management method, system, equipment and readable storage medium - Google Patents
AI-based garage management method, system, equipment and readable storage medium Download PDFInfo
- Publication number
- CN114360288A CN114360288A CN202210274539.0A CN202210274539A CN114360288A CN 114360288 A CN114360288 A CN 114360288A CN 202210274539 A CN202210274539 A CN 202210274539A CN 114360288 A CN114360288 A CN 114360288A
- Authority
- CN
- China
- Prior art keywords
- parking
- information
- garage
- vehicle
- parking space
- 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.)
- Pending
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides an AI-based garage management method, a system, equipment and a readable storage medium, wherein the method comprises the following steps: monitoring at least three parking spaces through first camera equipment installed in a garage to acquire monitoring information of the at least three parking spaces; shielding information of the parking space by infrared sensing equipment arranged on the parking space; acquiring garage information based on the shielding information and the monitoring information; and sending the garage information to the terminal equipment so that the terminal equipment displays the garage information. By the aid of the mode, real-time garage information can be effectively acquired in real time and can be displayed on terminal equipment, automatic or unmanned garage management can be displayed, and users or car owners can conveniently and quickly know the garage condition.
Description
Technical Field
The invention relates to the technical field of garage management, in particular to a garage management method, a garage management system, garage management equipment and a readable storage medium based on AI.
Background
Along with parking area is bigger and bigger, and under the more and more circumstances of vehicle, on the market at present, how to realize the management to the garage, it is especially important if confirm the parking circumstances etc. in the garage, but now usually to the management method of parking, for example predetermine earth magnetic coil in the parking stall and assist staff's management method through earth magnetic coil, it sets up earth magnetic coil required cost higher, and still need manual management, and the cost of labor is higher, and can't link with the user for whole management efficiency is lower.
Disclosure of Invention
An objective of the present invention is to provide a garage management method, system, device and readable storage medium based on AI, so as to solve the above technical problems.
Embodiments of the invention may be implemented as follows:
in a first aspect, the present invention provides an AI-based garage management method, which is applied to an AI-based garage management system, where the garage management system includes a first camera device and an infrared sensing device, and the method includes:
monitoring at least three parking spaces through first camera equipment installed in a garage to acquire monitoring information of the at least three parking spaces, wherein the monitoring information comprises continuous multi-frame parking images of the at least three parking spaces;
shielding information of the parking space through infrared sensing equipment installed on the parking space;
acquiring garage information based on the shielding information and the monitoring information;
and sending the garage information to a terminal device so that the terminal device displays the garage information.
In an optional embodiment, the acquiring the garage information based on the shielding information and the monitoring information includes:
inputting the parking image into a preset target detection model to identify vehicle information, wherein the preset target detection model is a yolo model;
determining first parking information corresponding to each parking space based on the vehicle information corresponding to the continuous multi-frame parking images and a preset target position;
determining second parking information corresponding to each parking space based on the shielding information;
determining a parking condition for each parking space based on the first and second parking information;
obtaining the garage information based on the parking conditions of all parking spaces of the garage.
In an optional embodiment, the determining, based on the vehicle information corresponding to the consecutive multiple parking images and a preset target position, first parking information corresponding to each parking space includes:
selecting an identification frame of a corresponding vehicle based on the vehicle information;
if the vehicle information of the continuous preset number of frames indicates that the contact ratio of the identification frame in the continuous preset number of frames is greater than a threshold value, determining that the vehicle is in a stop state;
if the identification frame corresponding to the vehicle in the stopped state is located in a preset position area of the parking image, indicating that the vehicle is located in the parking space corresponding to the preset position area, and setting a first parking state of the parking space as yes;
selecting license plate information of a corresponding vehicle based on the vehicle information;
acquiring the matching condition of the license plate information and the preset license plate information of a parking space corresponding to the vehicle;
outputting the first parking state and the matching condition as first parking information;
wherein the matching condition comprises a corresponding dock or a non-corresponding dock.
In an optional embodiment, the second parking information includes a second parking status of the parking space, and the determining the parking status of each parking space based on the first parking information and the second parking information includes:
if the first parking state and the second parking state of the parking space are the same, taking the first parking state or the second parking state as the current parking state of the parking space;
and taking the current parking state and the matching condition as the parking condition.
In an optional embodiment, the obtaining the garage information based on the parking conditions of all parking spaces of the garage includes:
acquiring a preset parking space distribution map of the garage;
different identifications are adopted for different parking states and added to the preset parking space distribution map of the garage to obtain a real-time parking space distribution map;
and taking the real-time parking space distribution map as the garage information.
In an optional embodiment, the garage management method further comprises:
if the garage information indicates that the matching condition of the parking spaces is non-corresponding parking;
taking the parking space as a reminding parking space;
and the second camera equipment installed in the garage is used for photographing the vehicle corresponding to the reminding parking space so as to acquire the reserved number information of the vehicle.
In an optional embodiment, the garage management method further comprises:
acquiring an image of an entering vehicle at an inlet of the garage through a third camera device installed at the inlet of the garage;
inputting the image of the entering vehicle into the preset target detection model to identify the license plate information of the vehicle;
and if the license plate information is the same as the preset license plate information corresponding to the reminding parking space, sending the reserved number information and the parking condition corresponding to the reminding parking space to a binding terminal corresponding to the reminding parking space.
In a second aspect, the invention provides an AI-based garage management system, which includes a server, a first camera device, and an infrared sensing device, where the server is configured to:
monitoring at least three parking spaces through the first camera equipment installed in the garage to acquire monitoring information of the at least three parking spaces;
shielding information of the parking space through the infrared sensing equipment installed on the parking space;
acquiring garage information based on the shielding information and the monitoring information;
and sending the garage information to a terminal device so that the terminal device displays the garage information.
In a third aspect, the present invention provides a computer apparatus comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor being capable of executing the computer program to implement the AI-based garage management method of the first aspect.
In a fourth aspect, the present invention provides a readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the AI-based garage management method according to the first aspect.
According to the garage management method and system based on the AI, the computer equipment and the readable storage medium, the first camera equipment arranged in the garage is used for monitoring the at least three parking spaces so as to acquire the monitoring information of the at least three parking spaces; shielding information of the parking space through infrared sensing equipment installed on the parking space; acquiring garage information based on the shielding information and the monitoring information; and sending the garage information to a terminal device so that the terminal device displays the garage information. Therefore, real-time garage information can be effectively acquired in real time and can be displayed on the terminal equipment, automatic or unmanned garage management can be displayed, a user or a vehicle owner can conveniently and quickly know the garage condition, and quick parking is realized. And monitoring information and shielding information are combined, so that the accuracy of the information of the whole garage is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a first embodiment of an AI-based garage management method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram of a sub-step of step S13 of FIG. 1;
FIG. 3 is a schematic flow chart diagram of the substeps of step S132 of FIG. 2;
FIG. 4 is a schematic flow chart diagram of the substeps of step S135 of FIG. 2;
fig. 5 is a schematic flow chart of a second embodiment of an AI-based garage management method according to an embodiment of the present invention;
fig. 6 is a schematic flow chart of a third embodiment of an AI-based garage management method according to an embodiment of the present invention;
FIG. 7 is a diagram of an AI-based garage management system in accordance with an embodiment of the present invention;
fig. 8 is a block diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that if the terms "upper", "lower", "inside", "outside", etc. indicate an orientation or a positional relationship based on that shown in the drawings or that the product of the present invention is used as it is, this is only for convenience of description and simplification of the description, and it does not indicate or imply that the device or the element referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus should not be construed as limiting the present invention.
Furthermore, the appearances of the terms "first," "second," and the like, if any, are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
With the garage (whether a shopping mall, an office building or a residence, etc.), the garage is frequently used for one or more floors, and if the current idle position of the garage is calculated only by recording the number of vehicles entering the garage and the number of vehicles exiting the garage, the efficiency is extremely low, and the condition of the garage cannot be determined in real time.
If for example predetermine earth coil in the parking stall and through earth coil auxiliary work personnel's management method, it sets up that earth coil required cost is higher, and still needs manual management, and the cost of labor is higher, and can't link with the user for whole managerial efficiency is lower.
Above all kinds, not only make the garage management efficiency low, also can lead to the cost of labor higher to still can't satisfy the requirement that the user found the parking stall fast.
The embodiment of the invention provides an AI-based garage management method, which is particularly applicable to an AI-based garage management system 200, and the AI-based garage management system 200 particularly includes a first camera device 210 and an infrared sensing device 220. And optionally, the AI-based garage management system 200 may be installed in whole or in part in a garage.
Referring to fig. 1, fig. 1 is a schematic flow chart of a first embodiment of an AI-based garage management method according to an embodiment of the present invention, the method including:
and S11, monitoring at least three parking spaces through a first camera device installed in the garage so as to acquire monitoring information of the at least three parking spaces.
In an alternative embodiment, at least three parking spaces may be monitored by the first camera device installed in the garage, that is, a plurality of first camera devices may be installed in the garage, and each camera device may be aligned to three or more parking spaces, such as four parking spaces or five parking spaces. And continuously acquiring at least three parking space monitoring information.
In an alternative embodiment, the monitoring information may be a continuous multi-frame parking image of at least three parking spaces. Or may be considered as video information consisting of a plurality of consecutive frames of parking images.
And when the first camera device is installed, the shooting visual angle of the first camera device is fixed, namely, at least three parking spaces are positioned in the parking image area shot by the first camera device and are relatively fixed.
And S12, obtaining the shielding information of the parking space through the infrared sensing equipment installed on the parking space.
Optionally, infrared perception equipment also can install in the garage, and it all has the installation to correspond every parking stall specifically, can install on the floor of parking stall like this infrared perception equipment, thereby obtains sheltering from the information through detecting the vehicle information on the parking stall.
And S13, acquiring garage information based on the shielding information and the monitoring information.
After the monitoring information of the first camera devices and the shielding information of the infrared sensing devices are acquired, the garage information can be acquired based on the monitoring information and the shielding information.
Referring to fig. 2, fig. 2 is a schematic flow chart of the sub-step of step S13 in fig. 1, which specifically includes the following steps:
s131, the parking image is input into a preset target detection model to recognize vehicle information.
Optionally, the monitoring information includes multiple frames of parking images, and the parking images may be input into a preset target detection model, and the preset target detection model is used to identify the parking images, so as to obtain vehicle information through identification.
In an alternative embodiment, the preset target detection model may specifically be a yolo model.
Optionally, the preset target detection model may be obtained by training a preliminary detection model, and the training process may specifically be as follows:
and acquiring a training set of the preliminary detection model, and then training the preliminary detection based on the training set to obtain a preset target detection model. The training set comprises a plurality of groups of marked vehicle training image groups and license plate training image groups, wherein the vehicle training image groups comprise a plurality of training images of the same vehicle image, which are obtained after at least one of rotation angle, saturation, exposure and color tone processing.
Optionally, a plurality of training images obtained by processing at least one of a rotation angle, a saturation, an exposure and a hue of the same vehicle image can obtain a better sample size, so as to improve robustness and accuracy of a preset target detection model.
S132, determining first parking information corresponding to each parking space based on the vehicle information corresponding to the continuous multi-frame parking images and a preset target position.
And then, determining first parking information corresponding to each parking space based on the vehicle information corresponding to the continuous multi-frame parking images and the preset target position.
Referring to fig. 3, fig. 3 is a schematic view of a sub-step flow of step S132 in fig. 2, which specifically includes the following steps:
s1321, a recognition frame of the corresponding vehicle is selected based on the vehicle information.
Optionally, the vehicle information at least includes an identification frame of the corresponding vehicle, so that the identification frame of the vehicle corresponding to the vehicle information can be selected based on the vehicle information.
S1322, if the vehicle information of the consecutive preset number of frames indicates that the coincidence degree of the identification frame in the consecutive preset number of frames is greater than the threshold value, it is determined that the vehicle is in the stopped state.
The vehicle information of continuous multi-frames can be obtained based on the parking images of the continuous multi-frames, the multi-frame vehicle information of the same vehicle is corresponding, and if the coincidence degree of the vehicle information of the continuous preset number of frames, which indicates that the identification frame of the same vehicle is in the continuous preset number of frames, is greater than a threshold value, the vehicle can be determined to be in a stop state.
That is, for a stopped vehicle, the appearance in the parking image is still for a long period of time, and therefore the corresponding recognition frame is also still, that is, the coincidence of the recognition frames of consecutive frames is almost 100%, and therefore, if the coincidence of the recognition frames of the vehicle information of consecutive preset number of frames, which indicates the same vehicle, in consecutive preset number of frames is greater than the threshold value, it can be determined that the vehicle is in the stopped state.
And S1323, if the identification frame corresponding to the vehicle in the stopped state is located in the preset position area of the parking image, indicating that the vehicle is located in the parking space corresponding to the preset position area, and setting the first parking state of the parking space to be yes.
Optionally, after determining that the vehicle is in a stopped state, it may be further determined whether the vehicle is located in a parking space, and although the first camera device mainly acquires monitoring information of at least three parking spaces, images of other areas (such as garage roads) and the like are also attached, so it is further necessary to determine whether the vehicle is located in a parking space and in which parking space.
In the above embodiment, it is mentioned that, when the first camera device is installed, the range of the viewing angle is fixed, that is, there is a fixed area in the parking image for each parking space in the actual range, that is, each parking space corresponds to the preset position area of the parking image captured by the first camera device. For example, a parking image is 100 by 80, and there are three parking spaces from left to right, which correspond to the ranges of 0-30, 35-60, and 70-100.
Optionally, the first parking state of the parking space is generally defaulted to no.
If the recognition frame corresponding to the vehicle in the stopped state is located in the preset position area of the parking image, it indicates that the vehicle is located in the parking space corresponding to the preset position area, and the first parking state of the parking space is set to be yes.
In an alternative embodiment, each parking space and each first camera device have labels, and the labels have correlation, for example, the first camera device may be C-01, and the parking space corresponding to the first camera device may be C-0101, C-0102, and so on, so as to implement association.
When the parking images are acquired, the number corresponding to the first camera device is added corresponding to each parking image, so that the corresponding parking space can be determined subsequently.
After the monitoring information of all the first camera devices is processed, the first parking state of each parking space can be acquired.
S1324, the license plate information of the corresponding vehicle is selected based on the vehicle information.
In an optional embodiment, the vehicle information may further include license plate information of the corresponding vehicle, that is, the license plate information of the vehicle may be identified based on the preset target detection model.
And S1325, acquiring the matching condition of the license plate information and the preset license plate information of the parking space corresponding to the vehicle.
In a particular scenario, some parking spaces are public, i.e. there is no specific user, but some parking spaces are private, i.e. they correspond to fixed users (or fixed vehicles). Therefore, the license plate information needs to be matched with the preset license plate information of the parking space corresponding to the vehicle corresponding to the license plate information, so that the matching condition of the license plate information is obtained.
If the license plate information of the vehicle stopped at a certain parking space is matched with (namely identical to) the preset license plate information corresponding to the parking space, and the matching condition is corresponding parking. If the license plate information of the vehicle parked in a certain parking space is not matched with (namely is different from) the preset license plate information corresponding to the parking space, the matching condition is non-corresponding parking.
Optionally, the preset license plate information may be a plurality of license plates, and no matter which license plate the license plate information is the same as the preset license plate information, the license plate information is considered to be matched.
S1326, outputting the first parking state and the matching condition as first parking information.
Optionally, the first parking state and the matching condition are output as first parking information, that is, the first parking state and the matching condition (if the first parking state is no, the matching condition is an empty set or no matching condition) of each parking space are output as first parking information.
And S133, determining second parking information corresponding to each parking space based on the shielding information.
And then determining second parking information corresponding to each parking space based on the occlusion information, and optionally determining second parking information of each parking space based on the occlusion information corresponding to each parking space, where the second parking information includes a second parking status of the parking space, and the second parking status also includes yes or no.
Optionally, when the vehicle is parked on the parking space, the infrared sensing device is shielded, if the shielding information is shielding and shielding area, and if the shielding and shielding area is larger than the threshold value, the second parking state can be set to be yes.
S134, determining a parking condition for each parking space based on the first parking information and the second parking information.
And determining the parking state of each parking space based on the first parking information and the second parking information, wherein the parking state is determined by simultaneously utilizing the first parking state in the first parking information of the parking space and the second parking state of the second parking information for each parking space in consideration of accuracy.
Specifically, if the first parking state and the second parking state of the parking space are the same, namely both are yes or both are no, the first parking state or the second parking state is taken as the current parking state of the parking space; and the current parking state and the matching condition are used as the parking condition of the parking space.
In the above embodiment, the parking state of the parking space is determined according to the first parking state and the second parking state, so that the accuracy of the parking space can be enhanced, and the false detection of the first camera device or the infrared sensing device can be prevented.
And S135, obtaining garage information based on the parking conditions of all parking spaces of the garage.
And then, acquiring garage information according to the parking conditions of all parking spaces of the garage.
Referring to fig. 4, fig. 4 is a schematic view of a sub-step flow of step S135 in fig. 2, which specifically includes the following steps:
and S1351, acquiring a preset parking space distribution map of the garage.
Optionally, the preset parking space distribution map may be presented in a plan view form, including a distribution image corresponding to the parking space and a garage road image reaching each parking space. Or in multiple plan views when the garage includes multiple zones or multiple levels of zones.
And S1352, adopting different identifications for different parking states and adding the identifications to a preset parking space distribution map of the garage to obtain a real-time parking space distribution map.
And adopting different identifications for different parking states and adding the identifications to a preset parking space distribution map of the garage to obtain a real-time parking space distribution map.
Optionally, the parking state specifically includes the following three types:
1. the current parking state is yes, and the matching condition is corresponding parking.
2. The current parking state is yes, and the matching condition is non-corresponding parking.
3. If the current parking state is not, the matching condition is an empty set.
Three kinds of marks may be used to indicate different types, which may be distinguished by text, color or symbols. And adding corresponding identification to each parking space of the preset parking space distribution map to obtain a real-time parking space distribution map.
And S1353, using the real-time parking space distribution map as garage information.
And taking the real-time parking space distribution map as garage information.
And S14, sending the garage information to the terminal equipment so that the terminal equipment can display the garage information.
The garage information can be sent to the terminal device later, so that the terminal device can display the garage information (real-time parking space distribution map).
Optionally, the terminal device may be a large display screen arranged at a garage opening, or a mobile phone terminal of each user or vehicle owner.
In an optional embodiment, after responding to the connection request of the terminal device and connecting with the terminal device, the garage information may be sent to the terminal device, so that the terminal device may display the garage information. The specific mode can be that the terminal device pays attention to the public number, or scans a two-dimensional code and the like positioned at a garage opening to send a connection request, and after the connection is established, the terminal device can send garage information to the terminal device.
In the above embodiment, the first camera device installed in the garage is used for monitoring the at least three parking spaces to acquire monitoring information of the at least three parking spaces; shielding information of the parking space through infrared sensing equipment installed on the parking space; acquiring garage information based on the shielding information and the monitoring information; and sending the garage information to a terminal device so that the terminal device displays the garage information. Therefore, real-time garage information can be effectively acquired in real time and can be displayed on the terminal equipment, automatic or unmanned garage management can be displayed, a user or a vehicle owner can conveniently and quickly know the garage condition, and quick parking is realized. And monitoring information and shielding information are combined, so that the accuracy of the information of the whole garage is improved.
Referring to fig. 5, fig. 5 is a schematic flowchart of a second embodiment of the AI-based garage management method according to the embodiment of the present invention, and optionally, the AI-based garage management system 200 further includes a second camera 230 and a third camera 240. The method specifically comprises the following steps:
and S21, if the garage information indicates that the parking space is matched, the parking space is not correspondingly parked.
If the garage information indicates that the matching condition of a certain parking space is non-corresponding parking, the condition that the vehicle which is not the parking space is parked in the parking space occurs.
And S22, taking the parking space as a reminding parking space.
The parking space can be used as a reminding parking space.
And S23, photographing the vehicle corresponding to the reminding parking space through a second camera device installed in the garage to acquire the reserved number information of the vehicle.
And then, the second camera equipment installed in the garage is used for photographing the vehicle corresponding to the reminding parking space so as to obtain the reserved number information of the vehicle.
Optionally, a car moving telephone number is placed at the front end of a general vehicle, and the vehicle corresponding to the reminding parking space can be photographed through high-precision second camera equipment, so that reserved number information of the vehicle can be acquired.
And S24, acquiring an image of the vehicle entering the entrance of the garage through a third camera device installed at the entrance of the garage.
And then acquiring an image of the entering vehicle at the entrance of the garage through a third camera device installed at the entrance of the garage.
And S25, inputting the image of the entering vehicle into a preset target detection model to identify the license plate information of the vehicle.
And inputting an entering vehicle image of each vehicle entering from the garage inlet into a preset target detection model so as to identify the license plate information of the vehicle.
And S26, if the license plate information is the same as the preset license plate information corresponding to the reminding parking space, sending the reserved number information and the parking condition corresponding to the reminding parking space to the binding terminal corresponding to the reminding parking space.
And if the license plate information is the same as the preset license plate information corresponding to the reminding parking space, sending the reserved number information and the parking condition corresponding to the reminding parking space to the binding terminal corresponding to the reminding parking space.
If remind the car that corresponds in parking stall to begin to get into the garage after, then can remind the owner of this vehicle in advance, its parking stall is occupied, then can reserve number information and remind the parking situation that the parking stall corresponds to send for binding the terminal, optional this binding terminal specifically can be car owner or user's cell-phone, also can be the vehicle mounted terminal of vehicle, do not do the injecing here to be convenient for car owner or user to look for other parking stalls or call in advance and communicate with the vehicle owner who occupies, improve the convenience of parkking.
Referring to fig. 6, fig. 6 is a schematic flowchart of a second embodiment of the AI-based garage management method according to the embodiment of the present invention, and optionally, the AI-based garage management system 200 further includes a fourth camera 250. The method specifically comprises the following steps:
and S31, tracking the vehicle entering the garage through a fourth camera device installed in the garage to acquire the movement information of the vehicle.
And tracking the vehicle entering the garage through a fourth camera device installed in the garage to acquire the movement information of the vehicle.
Optionally, the fourth camera device may also include a plurality of fourth camera devices, and the plurality of fourth camera devices are installed on a garage road of the garage and are used for tracking the movement information of each vehicle on the garage road in real time.
And S32, obtaining IMU information and odometer information sent by the terminal equipment corresponding to the vehicle.
And then, further acquiring IMU information and odometer information sent by a terminal device corresponding to the vehicle, wherein optionally, the terminal device may be a vehicle-mounted terminal of the vehicle, or a mobile terminal of an owner of the vehicle, which is not limited herein.
And S33, determining the moving path of the vehicle based on the movement information, the IMU information and the odometer information.
Since most of the garage is indoor, the moving path of the vehicle can be determined by using the movement information, the IMU information and the odometer information, and then deviation is possible, but the deviation degree is not too large, and the specific calculation method can refer to an automatic driving positioning algorithm, which is not explained in redundant here.
And S34, binding the moving path and the real-time parking space distribution map in real time and displaying the moving path and the real-time parking space distribution map on the terminal equipment.
And after the moving path is obtained, the moving path and the real-time parking space distribution map are bound in real time and displayed on the terminal equipment. Therefore, the owner can determine the current position and information of the owner in real time, and the owner can drive the vehicle to find the parking space more quickly.
Referring to fig. 7, in fig. 7, for the AI-based garage management system according to the embodiment of the present invention, the AI-based garage management system 200 may include:
the system comprises a first camera device 210, an infrared sensing device 220 and a server 201. The server 201 is configured to: monitoring at least three parking spaces through the first camera device 210 installed in the garage to acquire monitoring information of the at least three parking spaces; shielding information of the parking space through an infrared sensing device 220 installed on the parking space; acquiring garage information based on the shielding information and the monitoring information; and sending the garage information to the terminal equipment so that the terminal equipment displays the garage information.
In an alternative embodiment, the AI-based garage management system 200 can further include a second camera device 230, a third camera device 240, and a fourth camera device 250.
In an optional embodiment, the server 201 is further configured to: if the garage information indicates that the matching condition of the parking spaces is non-corresponding parking; taking the parking space as a reminding parking space; and photographing the vehicle corresponding to the reminding parking space through a second camera device 230 installed in the garage to acquire the reserved number information of the vehicle. Acquiring an image of an entering vehicle at an entrance of the garage through a third camera device 240 installed at the entrance of the garage; inputting the image of the entering vehicle into the preset target detection model to identify the license plate information of the vehicle; and if the license plate information is the same as the preset license plate information corresponding to the reminding parking space, sending the reserved number information and the parking condition corresponding to the reminding parking space to a binding terminal corresponding to the reminding parking space.
In an optional embodiment, the server 201 is further configured to track, through a fourth camera device 250 installed in the garage, a vehicle entering the garage to obtain movement information of the vehicle; obtaining IMU information and odometer information sent by terminal equipment corresponding to the vehicle; determining a movement path of the vehicle based on the movement information, IMU information, and odometry information; and binding the moving path and the real-time parking space distribution map in real time and displaying the moving path and the real-time parking space distribution map on the terminal equipment.
It should be noted that each functional module in the AI-based garage management System 200 according to the embodiment of the present invention may be stored in a memory or solidified in an Operating System (OS) of a computer device in the form of software or Firmware (Firmware), and may be executed by a processor in the computer device. Meanwhile, data, codes of programs, and the like required to execute the above modules may be stored in the memory.
Therefore, an embodiment of the present invention further provides a computer device, as shown in fig. 8, and fig. 8 is a block diagram of a computer device provided in an embodiment of the present invention. The computer device 300 comprises a communication interface 301, a processor 302 and a memory 303. The processor 302, memory 303 and communication interface 301 are electrically connected to each other, directly or indirectly, to enable the transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 303 may be used for storing software programs and modules, such as program instructions/modules corresponding to the AI-based garage management method provided by the embodiment of the present invention, and the processor 302 executes various functional applications and data processing by executing the software programs and modules stored in the memory 303. The communication interface 301 may be used for communicating signaling or data with other node devices. The computer device 300 may have a plurality of communication interfaces 301 in the present invention.
The Memory 303 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor 302 may be an integrated circuit chip having signal processing capabilities. The Processor may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), etc.; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc.
Embodiments of the present invention further provide a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the AI-based garage management method according to any of the foregoing embodiments. The computer readable storage medium may be, but is not limited to, various media that can store program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a PROM, an EPROM, an EEPROM, a magnetic or optical disk, etc.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The garage management method based on the AI is applied to a garage management system based on the AI, the garage management system comprises a first camera device and an infrared sensing device, and the method comprises the following steps:
monitoring at least three parking spaces through first camera equipment installed in a garage to acquire monitoring information of the at least three parking spaces, wherein the monitoring information comprises continuous multi-frame parking images of the at least three parking spaces;
shielding information of the parking space through infrared sensing equipment installed on the parking space;
acquiring garage information based on the shielding information and the monitoring information;
and sending the garage information to a terminal device so that the terminal device displays the garage information.
2. The garage management method of claim 1, wherein the obtaining of garage information based on occlusion information and monitoring information comprises:
inputting the parking image into a preset target detection model to identify vehicle information, wherein the preset target detection model is a yolo model;
determining first parking information corresponding to each parking space based on the vehicle information corresponding to the continuous multi-frame parking images and a preset target position;
determining second parking information corresponding to each parking space based on the shielding information;
determining a parking condition for each parking space based on the first and second parking information;
obtaining the garage information based on the parking conditions of all parking spaces of the garage.
3. The garage management method of claim 2, wherein the determining the first parking information corresponding to each parking space based on the vehicle information corresponding to the plurality of consecutive parking images and a preset target position comprises:
selecting an identification frame of a corresponding vehicle based on the vehicle information;
if the vehicle information of the continuous preset number of frames indicates that the contact ratio of the identification frame in the continuous preset number of frames is greater than a threshold value, determining that the vehicle is in a stop state;
if the identification frame corresponding to the vehicle in the stopped state is located in a preset position area of the parking image, indicating that the vehicle is located in the parking space corresponding to the preset position area, and setting a first parking state of the parking space as yes;
selecting license plate information of a corresponding vehicle based on the vehicle information;
acquiring the matching condition of the license plate information and the preset license plate information of a parking space corresponding to the vehicle;
outputting the first parking state and the matching condition as first parking information;
wherein the matching condition comprises a corresponding dock or a non-corresponding dock.
4. The garage management method of claim 3, wherein the second parking information includes a second parking status of the parking spaces, and the determining the parking status of each parking space based on the first parking information and the second parking information includes:
if the first parking state and the second parking state of the parking space are the same, taking the first parking state or the second parking state as the current parking state of the parking space;
and taking the current parking state and the matching condition as the parking condition.
5. The garage management method of claim 3, wherein the obtaining the garage information based on the parking status of all parking spaces of the garage comprises:
acquiring a preset parking space distribution map of the garage;
different identifications are adopted for different parking states and added to the preset parking space distribution map of the garage to obtain a real-time parking space distribution map;
and taking the real-time parking space distribution map as the garage information.
6. The garage management method of claim 5, further comprising:
if the garage information indicates that the matching condition of the parking spaces is non-corresponding parking;
taking the parking space as a reminding parking space;
and the second camera equipment installed in the garage is used for photographing the vehicle corresponding to the reminding parking space so as to acquire the reserved number information of the vehicle.
7. The garage management method of claim 6, further comprising:
acquiring an image of an entering vehicle at an inlet of the garage through a third camera device installed at the inlet of the garage;
inputting the image of the entering vehicle into the preset target detection model to identify the license plate information of the vehicle;
and if the license plate information is the same as the preset license plate information corresponding to the reminding parking space, sending the reserved number information and the parking condition corresponding to the reminding parking space to a binding terminal corresponding to the reminding parking space.
8. The garage management system based on the AI is characterized by comprising a server, a first camera device and an infrared sensing device, wherein the server is used for:
monitoring at least three parking spaces through the first camera equipment installed in the garage to acquire monitoring information of the at least three parking spaces;
shielding information of the parking space through the infrared sensing equipment installed on the parking space;
acquiring garage information based on the shielding information and the monitoring information;
and sending the garage information to a terminal device so that the terminal device displays the garage information.
9. A computer apparatus comprising a processor and a memory, the memory storing a computer program executable by the processor to implement the AI-based garage management method of any of claims 1-7.
10. A readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the AI-based garage management method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210274539.0A CN114360288A (en) | 2022-03-21 | 2022-03-21 | AI-based garage management method, system, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210274539.0A CN114360288A (en) | 2022-03-21 | 2022-03-21 | AI-based garage management method, system, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114360288A true CN114360288A (en) | 2022-04-15 |
Family
ID=81095190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210274539.0A Pending CN114360288A (en) | 2022-03-21 | 2022-03-21 | AI-based garage management method, system, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114360288A (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240534A (en) * | 2014-09-19 | 2014-12-24 | 电子科技大学 | Intelligent cell garage management system based on fingerprint recognition and vehicle license plate recognition |
| CN106339768A (en) * | 2016-08-22 | 2017-01-18 | 重庆交通大学 | Parking space reservation system based on physical network |
| CN207131142U (en) * | 2016-11-30 | 2018-03-23 | 郑州蓝视科技有限公司 | Parking space state can monitor garage |
| CN110164141A (en) * | 2019-06-18 | 2019-08-23 | 西南交通大学 | Stop position guidance system and bootstrap technique |
| CN110264736A (en) * | 2019-07-15 | 2019-09-20 | 李元胜 | It is a kind of to avoid the asemantic interactive system of vehicle applied to parking lot |
| CN110533923A (en) * | 2019-08-29 | 2019-12-03 | 北京精英路通科技有限公司 | Parking management method, device, computer equipment and storage medium |
| CN110895888A (en) * | 2019-04-28 | 2020-03-20 | 腾讯科技（深圳）有限公司 | Intelligent parking method, device, system, electronic equipment and computer readable medium |
| CN110910655A (en) * | 2019-12-11 | 2020-03-24 | 深圳市捷顺科技实业股份有限公司 | Parking management method, device and equipment |
| CN111784857A (en) * | 2020-06-22 | 2020-10-16 | 浙江大华技术股份有限公司 | Parking space management method and device and computer storage medium |
| CN111882916A (en) * | 2019-12-20 | 2020-11-03 | 北京嘀嘀无限科技发展有限公司 | Parking space management method and system |
| CN111951594A (en) * | 2019-05-17 | 2020-11-17 | 享位科技有限公司 | Parking management system of registering |
| CN112053588A (en) * | 2020-10-16 | 2020-12-08 | 湖南聚沙信息技术有限公司 | Intelligent garage management system |
| CN112185158A (en) * | 2020-08-26 | 2021-01-05 | 领翌技术(横琴)有限公司 | Parking space and vehicle information matching method based on reverse vehicle finding and parking system |
| CN112466154A (en) * | 2020-12-18 | 2021-03-09 | 迪蒙智慧交通科技有限公司 | Vehicle parking method based on heavy identification technology, monitoring device and readable storage medium |
| CN113112855A (en) * | 2021-03-30 | 2021-07-13 | 合肥九一化工科技有限公司 | Parking space identification system and method |
| CN113223326A (en) * | 2021-04-28 | 2021-08-06 | 上海电科智能***股份有限公司 | Multi-vehicle multi-control multi-source low-speed auxiliary parking system based on road side |
| CN113299066A (en) * | 2021-05-21 | 2021-08-24 | 贵州车秘科技有限公司 | Guidance system and method in intelligent parking field based on parking space identification |
-
2022
- 2022-03-21 CN CN202210274539.0A patent/CN114360288A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240534A (en) * | 2014-09-19 | 2014-12-24 | 电子科技大学 | Intelligent cell garage management system based on fingerprint recognition and vehicle license plate recognition |
| CN106339768A (en) * | 2016-08-22 | 2017-01-18 | 重庆交通大学 | Parking space reservation system based on physical network |
| CN207131142U (en) * | 2016-11-30 | 2018-03-23 | 郑州蓝视科技有限公司 | Parking space state can monitor garage |
| CN110895888A (en) * | 2019-04-28 | 2020-03-20 | 腾讯科技（深圳）有限公司 | Intelligent parking method, device, system, electronic equipment and computer readable medium |
| CN111951594A (en) * | 2019-05-17 | 2020-11-17 | 享位科技有限公司 | Parking management system of registering |
| CN110164141A (en) * | 2019-06-18 | 2019-08-23 | 西南交通大学 | Stop position guidance system and bootstrap technique |
| CN110264736A (en) * | 2019-07-15 | 2019-09-20 | 李元胜 | It is a kind of to avoid the asemantic interactive system of vehicle applied to parking lot |
| CN110533923A (en) * | 2019-08-29 | 2019-12-03 | 北京精英路通科技有限公司 | Parking management method, device, computer equipment and storage medium |
| CN110910655A (en) * | 2019-12-11 | 2020-03-24 | 深圳市捷顺科技实业股份有限公司 | Parking management method, device and equipment |
| CN111882916A (en) * | 2019-12-20 | 2020-11-03 | 北京嘀嘀无限科技发展有限公司 | Parking space management method and system |
| CN111784857A (en) * | 2020-06-22 | 2020-10-16 | 浙江大华技术股份有限公司 | Parking space management method and device and computer storage medium |
| CN112185158A (en) * | 2020-08-26 | 2021-01-05 | 领翌技术(横琴)有限公司 | Parking space and vehicle information matching method based on reverse vehicle finding and parking system |
| CN112053588A (en) * | 2020-10-16 | 2020-12-08 | 湖南聚沙信息技术有限公司 | Intelligent garage management system |
| CN112466154A (en) * | 2020-12-18 | 2021-03-09 | 迪蒙智慧交通科技有限公司 | Vehicle parking method based on heavy identification technology, monitoring device and readable storage medium |
| CN113112855A (en) * | 2021-03-30 | 2021-07-13 | 合肥九一化工科技有限公司 | Parking space identification system and method |
| CN113223326A (en) * | 2021-04-28 | 2021-08-06 | 上海电科智能***股份有限公司 | Multi-vehicle multi-control multi-source low-speed auxiliary parking system based on road side |
| CN113299066A (en) * | 2021-05-21 | 2021-08-24 | 贵州车秘科技有限公司 | Guidance system and method in intelligent parking field based on parking space identification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106710291B (en) | Parking space obtaining method and device for parking lot | |
| CN107146468A (en) | The recognition methods of parking position and system and management method and system | |
| CN108694853B (en) | Method, terminal, server and system for realizing parking service | |
| CN112820137B (en) | Parking lot management method and device | |
| US11025865B1 (en) | Contextual visual dataspaces | |
| CN108174152A (en) | A kind of target monitoring method and target monitor system | |
| CN110826356B (en) | Non-motor vehicle violation detection system, method and server | |
| KR20180102284A (en) | Monitoring system and method of the handicap parking zone using visual display | |
| CN110853391A (en) | Intelligent shared parking system | |
| CN110972111B (en) | Method for detecting a caller by an autonomous vehicle | |
| CN114694385A (en) | Parking management method, device, system, electronic equipment and storage medium | |
| CN112802363A (en) | Intelligent guiding system and method based on panoramic video and face recognition technology | |
| AU2015282375B2 (en) | One-to-many-surface parking lot management system using omnidirectional camera and management method thereof | |
| JP2013089158A (en) | Parking state notification device by notation recognition | |
| CN111833637A (en) | Vehicle monitoring method, device, equipment and system | |
| KR20150061160A (en) | Robot for providing vehicle location, and system and method for guiding parking location employing the same | |
| CN115063746A (en) | Vehicle warehousing management method and device, computer equipment and storage medium | |
| KR20190004644A (en) | System for confirming parking position | |
| CN109671291B (en) | Panoramic monitoring method based on intelligent sensor | |
| CN114360288A (en) | AI-based garage management method, system, equipment and readable storage medium | |
| US20230274552A1 (en) | Image-surveilled security escort | |
| KR20200025384A (en) | Parking Information Providing Device Using Real-Time Image Processing and System thereof | |
| CN114724403A (en) | Parking space guiding method, system, equipment and computer readable storage medium | |
| KR20180115079A (en) | Vehicle recognition system and method for efficient parking control | |
| KR20180121094A (en) | Vehicle database management system for manless parking lot and method thereof |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220415 |