CN107195198B - Roadside parking management method and system based on image recognition technology - Google Patents
Roadside parking management method and system based on image recognition technology Download PDFInfo
- Publication number
- CN107195198B CN107195198B CN201710640795.6A CN201710640795A CN107195198B CN 107195198 B CN107195198 B CN 107195198B CN 201710640795 A CN201710640795 A CN 201710640795A CN 107195198 B CN107195198 B CN 107195198B
- Authority
- CN
- China
- Prior art keywords
- parking
- parking space
- information
- vehicle
- module
- 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
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/147—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is within an open public zone, e.g. city centre
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention provides a roadside parking management method and a system based on an image recognition technology.A parking acquisition unit shoots an image picture, carries out parking space calibration and then sends parking space GPS information, parking space calibration information and parking space initial information to a big data unit through a network transmission device; the parking space state is updated by the parking space image collected by the image processing device, and the detection result is sent to the big data unit through the network transmission device; the big data unit receives and stores the parking space information sent by the network transmission device, and a parking space owner registers the parking space information by himself; if the parking place owner does not register, the information processing unit triggers and pushes reminding data to the inspection unit to arrive at the parking place site to finish shooting and evidence obtaining and license plate inputting, and the reminding data is transmitted to the data center unit through the mobile communication terminal to finish vehicle registration; the information processing unit calculates the parking time, generates a parking bill and pushes the parking bill to the vehicle owner unit. The parking spaces can be automatically calibrated through the image recognition technology, parking space management is carried out, and implementation cost is reduced.
Description
Technical Field
The invention relates to the technical field of roadside parking management, in particular to a roadside parking management method and a system based on an image recognition technology.
Background
With the rapid development of current economy, the number of automobiles increases in a geometric progression every year, traffic congestion is increasingly serious, and roadside parking management is disordered and road-occupied parking is serious. The conventional parking lot management cannot be suitable for roadside parking, and parking spaces and vehicles are integrated together by technical means through constructing a management method and a management system related to roadside parking management and service.
Chinese patent 201610172781.1 discloses a parking management method, apparatus and system, including obtaining a first image of a monitoring area sent by a monitoring camera, determining whether there is a vehicle parked in the parking area according to the first image, if there is a vehicle parked in the parking area, obtaining license plate information of the parked vehicle identified by a second image, and sending the license plate information and parking time of the parked vehicle to a parking server, so that the parking server charges for the parked vehicle. However, the method and the system have the problem that only the existing parking spaces can be monitored.
Chinese patent 201410728397.6 discloses an intelligent roadside parking management system based on a cloud platform, which uses a cloud platform server to process and store parking data information of a user, parking request data information and parking transaction record information; the system comprises a parking acquisition unit, a data processing unit and a data processing unit, wherein the parking acquisition unit is arranged on each parking space of a road and used for acquiring the parking state data of roadside parking spaces in real time and uploading the information data; the parking application service unit is used for inquiring the information related to roadside parking and applying for parking at a parking space, and a user applies and inquires for parking service through an APP, a telephone or a website; the parking transaction processing unit is used for processing the parking application and the parking state, generating a parking order, paying and settling the parking order, judging the parking service and correcting the parking order, generating a parking order, paying and settling the parking order, and judging the parking service and correcting the parking order; the operation management unit comprises an operation maintenance subsystem, which is used for monitoring the roadside parking condition and the parking equipment in real time, and sending the operation instruction to set various parameters of the parking equipment; and the patrol PDA subsystem is used for processing the information uploaded by the patrol PDA client, and the patrol PDA client inputs the violation information of the parking space and carries out punishment. However, the system has the problem that a parking acquisition unit needs to be arranged on each parking space, and the cost is high.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the roadside parking management method and the system based on the image recognition technology, the parking spaces can be automatically calibrated through the image recognition technology, the parking spaces are managed, the implementation cost is greatly reduced, and the method and the system are convenient to apply and popularize.
The invention provides a roadside parking management method based on an image recognition technology, which comprises the following steps:
s1, the parking acquisition unit shoots an image picture, carries out parking space calibration and then sends parking space GPS information, parking space calibration information and parking space initial information to the big data unit through the network transmission device;
s2, carrying out parking space state updating on the parking space image acquired by the image processing device, and sending the detection result to a big data unit through a network transmission device;
s3, the big data unit receives and stores the parking space information sent by the network transmission device, and a parking space vehicle owner registers the parking space information by himself;
s4, if the parking space vehicle owner is not registered, the information processing unit triggers and pushes reminding data to the inspection unit to arrive at the parking space site to finish shooting and evidence obtaining and license plate inputting, and the reminding data is transmitted to the data center unit through the mobile communication terminal to finish vehicle registration;
and S5, the information processing unit calculates the parking time length, generates a parking bill and pushes the parking bill to the vehicle owner unit.
Further, the method for parking space calibration in S1 includes:
s11, marking four vertex angles of the parking space by using a marking tool in the obtained video image to form a self-closed image interval, wherein each self-closed interval is a parking space;
s12, after marking all parking space intervals, saving the parking space outline as an image detection range;
s13, generating parking spaces according to the parking space outline map, and automatically numbering each generated parking space by the system;
and S14, initializing the generated parking space and judging the parking state of the current parking space.
Further, the method for updating the parking space state in S2 includes:
s21, reference frame acquisition: the camera collects parking space images at a set frequency to serve as a reference frame;
s22, acquiring a background image: when the parking space state is idle, comparing the acquired reference frame with the existing background images one by one, if the similarity of the characteristic value is smaller than a threshold value, saving the reference frame as the parking space background image, and if no background image which can be compared exists at present, directly saving the reference frame as the background image;
s23, vehicle entering and exiting recognition: and monitoring the frame difference of the parking space area, wherein the information amount of the frame difference exceeds a threshold value, starting a motion detection unit to track a motion target, and updating the parking space state.
Further, the method for tracking the moving object in S23 includes: and determining that the target is a vehicle according to the ratio of the rigid body area to the parking space area of the target, and judging whether the vehicle is abnormally parked.
Further, the moving object tracking in S23 further includes multi-object tracking.
Further, the roadside parking management system based on the image recognition technology comprises a parking acquisition unit, a big data unit, an information processing unit, a patrol unit and an owner unit, wherein the parking acquisition unit is used for acquiring a shot image picture in real time, calibrating a parking space and uploading information data to the big data unit; the big data unit is used for storing data, processing parking data and charging data; the information processing unit is used for analyzing and processing the parking conditions of all parking spaces at the roadside; the inspection unit is used for monitoring the use condition of the parking space and the vehicle information of the abnormal parking space; the vehicle owner unit is used for registering information of a vehicle owner and paying parking fee.
The parking acquisition unit comprises a camera device, an image processing device and a network transmission device, wherein the camera device acquires parking space images as reference frames according to set frequency, the image processing device carries out parking space calibration and target tracking according to the shot images and transmits the processed data to the big data unit through the network transmission device; the camera device comprises a camera for shooting pictures and a GPS module for positioning.
Further, the image processing apparatus includes: the parking space calibration module generates parking spaces according to the shot images and numbers the generated parking spaces; the storage module is used for storing a background picture; the comparison module is used for comparing the acquired reference frame with the existing background image one by one; the motion detection module is used for tracking a target and judging whether the vehicle is abnormally parked; the night identification module is used for judging vehicle access according to the characteristics of the vehicle lamp; and the exception handling module is used for informing the patrol unit to carry out manual verification when the parking space abnormal state occurs.
Further, the big data unit includes: the vehicle owner data module is used for recording the registered information of a vehicle owner unit; the parking space data module is used for recording parking space GPS information, parking space calibration information, parking space initial information and updated parking space state information; the vehicle data module is used for recording vehicle information; the information supplementing module is used for supplementing information according to the contour pictures of different types of vehicles acquired by the camera device; and the charging data module is used for recording charging information.
Further, the information processing unit includes: the parking space management module is used for allocating parking spaces to vehicle owners according to the monitored parking space state information; the system comprises an owner management module, a registration module and a registration module, wherein the owner management module is used for processing owner registration information; the inspection management module is used for distributing inspection units according to the camera device and pushing abnormal information to the corresponding inspection units; the charging management module is used for calculating the parking time length, generating a parking bill and pushing the parking bill to the vehicle owner unit; and the parking record statistical analysis module is used for statistically analyzing all parking data.
According to the technical scheme, the invention has the beneficial effects that:
the invention provides a roadside parking management method and a system based on an image recognition technology.A parking acquisition unit shoots an image picture, performs parking space calibration and then sends parking space GPS information, parking space calibration information and parking space initial information to a big data unit through a network transmission device; the parking space state is updated by the parking space image collected by the image processing device, and the detection result is sent to the big data unit through the network transmission device; the big data unit receives and stores the parking space information sent by the network transmission device, and a parking space owner registers the parking space information by himself; if the parking place owner does not register, the information processing unit triggers and pushes reminding data to the inspection unit to arrive at the parking place site to finish shooting and evidence obtaining and license plate inputting, and the reminding data is transmitted to the data center unit through the mobile communication terminal to finish vehicle registration; the information processing unit calculates the parking time, generates a parking bill and pushes the parking bill to the vehicle owner unit. The parking spaces can be automatically calibrated through the image recognition technology, and the parking spaces are managed, so that the implementation cost is greatly reduced, and the application and popularization are facilitated.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 is a schematic flow chart of a roadside parking management method based on an image recognition technology according to the present invention.
Fig. 2 is a parking space calibration diagram of a roadside parking management method based on an image recognition technology.
Fig. 3 is a block diagram of a roadside parking management system based on image recognition technology.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
Referring to fig. 1 to fig. 3, the method for managing roadside parking based on image recognition technology according to the present embodiment includes the following steps:
s1, the parking acquisition unit shoots an image picture, carries out parking space calibration and then sends parking space GPS information, parking space calibration information and parking space initial information to the big data unit through the network transmission device;
the parking space calibration method comprises the following steps:
firstly, marking four vertex angles of a parking space by using a marking tool in a video image acquired by a camera device to form a self-closed image interval, wherein each self-closed interval is a parking space;
secondly, after marking all parking space intervals, storing parking space outlines as image detection ranges;
thirdly, generating parking spaces according to the parking space outline graph, and automatically numbering each generated parking space by the system;
and fourthly, initializing the generated parking space and judging the parking state of the current parking space.
And S2, carrying out parking space state updating on the parking space image acquired by the image processing device, and sending the detection result to the big data unit through the network transmission device, wherein the sent detection result comprises a changed parking space, changed time, changed state, vehicle type, vehicle color and a changed parking space mark screenshot.
The specific method for updating the parking space state comprises the following steps:
firstly, a camera collects parking space images every 5 minutes at a set frequency to serve as a reference frame;
secondly, when the parking space is idle, comparing the collected reference frame with the existing background pictures one by one, if the similarity of the characteristic values is smaller than a threshold value, saving the reference frame as the parking space background picture, and if no background picture which can be compared exists at present, directly saving the reference frame as the background picture, so that the image processing device can automatically learn the parking space background pictures in rainy days, cloudy days, sunny days and nights conveniently;
and thirdly, monitoring the difference value between N frames and N-12 frames in the parking space area, starting a motion detection unit to track a motion target once the frame difference information quantity exceeds a threshold value, subtracting the motion target from each frame, and entering or exiting a vehicle if the frame difference is larger and larger. When the frame difference is not changed within 10 seconds, comparing the reference frames, and if the reference frames are not changed, processing is not needed; and if the similarity with the reference frame is smaller than the threshold value after comparison, updating the parking space state. And the updated parking space state needs to be compared with the background image of the parking space, and if the similarity with the background image is smaller than a threshold value, the state is parking. And if the similarity with the background image is greater than the threshold value, the state is idle.
The moving target tracking method is that when the frame difference identification exceeds a threshold value, a moving detection module is started to track the moving target. When the frame difference does not change within 10 seconds, the target tracking is discarded. And determining that the target is a vehicle according to the ratio of the rigid body area of the target to the parking space area. And then, a pattern recognition module is used for carrying out similarity comparison, and a machine learning algorithm is used for the pattern recognition module to learn the outlines of different types of vehicles at different shooting angles. Further confirmation of vehicle type: buses, coaches, four-wheel trucks, six-wheel trucks, tricycles, motorcycles, people, etc. The motion detection module is also used for detecting whether the vehicle is parked in a compliance manner, and if the projection area of the rigid body is not completely fused into the parking space area, judging that the vehicle is parked in a pressing line mode. And if the projection area of the rigid body occupies two parking space areas, judging that the parking in the parking space is abnormal. And when the target tracking result is abnormal parking or the vehicle type cannot be identified, the abnormal monitoring result is sent to the data center unit through the network transmission device, and a patrolman is coordinated to perform manual verification processing.
The moving target tracking can also be multi-target tracking and is used for coping with the monitoring that one image processing device deals with the simultaneous parking of a plurality of parking spaces, particularly the situation that the same parking space faces two parking spaces for fast parking and grabbing the parking spaces one by one. Since the vehicle in-out interval may be smaller than the vehicle in-out recognition time. Namely, the situation that the front vehicle drives away from the parking space, the system does not complete the parking space idle state confirmation, and the rear vehicle drives into the parking space. When two targets enter and exit the parking space simultaneously, the system records to ensure that the frame difference is unchanged within 10 seconds, and when the reference frame comparison is carried out, the former vehicle is not mistakenly considered to have not been driven away.
The machine learning algorithm automatically adopts a feedback type learning model for the parking space, and the feedback type learning model is used as supplement of the existing background, so that the recognition performance is improved. Firstly, learning parking space background images collected in different time period environments; then, a decision feedback module is utilized to continuously train the pattern recognition capability to accurately recognize the vehicle type: the image pickup unit acquires contour pictures of different types of vehicle rigid bodies at different shooting angles, the contour pictures are stored in the big data unit through the network transmission device, and the information supplement module supplements data. If the target type which cannot be identified is met, the target type is submitted to the inspection unit, the inspection unit informs an inspector of manual identification feedback, a new model is recognized after the feedback, and the information supplement module supplements data.
S3, the big data unit receives and stores the parking space information sent by the network transmission device, and a parking space vehicle owner registers the parking space information by himself;
and S4, if the vehicle parked in the parking space is not registered within 5 minutes, triggering to push reminding data to the inspection unit in the corresponding area through the information processing unit, and informing an inspector to finish inspection and registration on the parking space site through the inspection unit. The inspection mode is that the parking stall is selected for the point on APP, opens the camera and carries out license plate discernment, and the discernment is successful, and automatic shooting is uploaded, accomplishes the vehicle and registers.
And S5, the information processing unit calculates the parking time length, generates a parking bill and pushes the parking bill to the vehicle owner unit.
A roadside parking management system based on an image recognition technology comprises a parking acquisition unit, a big data unit, an information processing unit, a patrol unit and an owner unit, wherein the parking acquisition unit is used for acquiring a shot image picture in real time, calibrating a parking space and uploading information data to the big data unit; the big data unit is used for storing data, processing parking data and charging data; the information processing unit is used for analyzing and processing the parking conditions of all parking spaces at the roadside; the inspection unit is used for monitoring the use condition of the parking space and the vehicle information of the abnormal parking space; the vehicle owner unit is used for registering information of a vehicle owner and paying parking fee.
The parking acquisition unit comprises a camera device, an image processing device and a network transmission device, wherein the camera device acquires parking space images as reference frames according to a set frequency, the image processing device carries out parking space calibration and target tracking according to the shot images and transmits the processed data to the big data unit through the network transmission device; the camera device comprises a camera for shooting pictures and a GPS module for positioning.
The image processing apparatus includes: the parking space calibration module generates parking spaces according to the shot images and numbers the generated parking spaces; the storage module is used for storing the background picture; the comparison module is used for comparing the acquired reference frame with the existing background image one by one; the motion detection module is used for tracking a target and judging whether the vehicle is abnormally parked; the night identification module is used for judging whether the vehicle enters or exits according to the characteristics of the vehicle lamp; and the exception handling module is used for informing the patrol unit to carry out manual verification when the parking space abnormal state occurs.
The unable module of discernment at night judges the vehicle discrepancy according to car light characteristic, and the unable effective filtration reflection of light of discernment module at night dazzles the influence of light etc. to image quality, and the error rate of discernment is higher, needs unusual self-checking module to carry out the self-checking and handles. And the abnormity self-checking processing collects parking space images at the frequency of 5 minutes per time to be used as a reference frame. Comparing the reference frame with the background image, and if the similarity is smaller than a threshold value, judging that the vehicle is parked; if the similarity with the background image is greater than the threshold value, the body is idle. If the current parking state is not consistent with the self-checking state, the parking space is in an abnormal state, an abnormal monitoring result needs to be sent to the big data unit through the network transmission device, and the inspection unit informs an inspector to carry out manual verification processing.
The big data unit includes: the vehicle owner data module is used for recording the registered information of the vehicle owner unit; the parking space data module is used for recording parking space GPS information, parking space calibration information, parking space initial information and updated parking space state information; the vehicle data module is used for recording vehicle information; the information supplementing module is used for supplementing information according to the contour pictures of different types of vehicles acquired by the camera device by the information supplementing unit; and the charging data module is used for recording charging information.
The information processing unit includes: the parking space management module is used for allocating parking spaces to the car owners according to the monitored parking space state information; the vehicle owner management module is used for processing vehicle owner registration information; the inspection management module is used for distributing inspection units according to the camera device and pushing abnormal information to the corresponding inspection units; the charging management module is used for calculating the parking time length, generating a parking bill and pushing the parking bill to the vehicle owner unit; and the parking record statistical analysis module is used for statistically analyzing all parking data.
The APP is opened by the vehicle owner unit, the idle parking space in the target area is selected, and navigation is conducted. And after parking, obtaining the parking space information of which the current position is not registered from the big data unit, and confirming the registration. When the vehicle leaves, the information processing unit calculates the parking time to generate a charging bill, the charging bill is pushed to the vehicle main unit, and the vehicle owner pays the fee autonomously or binds the payment account number to automatically deduct the fee.
The specific operation is as follows:
1. erecting a camera device at a verification position of a road parking environment, and calibrating a parking space at the parking position in a video picture;
2. the camera device monitors whether a vehicle is parked in the parking space or not in real time, and when the vehicle is parked or driven away, the network transmission device reports parking space information to the big data unit, wherein the reported parking space information comprises the parking space, parking time, vehicle type, color and whether parking is illegal or not.
3. After the vehicle owner parks, the current position is automatically positioned through the APP, and the unregistered parking picture and the parked time length of the current position pushed by the big data unit are obtained. The car owner selects the own car picture to complete the parking space registration operation. After the vehicle is driven away, the information processing unit automatically calculates the parking time and the parking cost and pushes the parking time and the parking cost to the vehicle owner unit, and the vehicle owner unit pays the fee.
As a supplementary scheme of the scheme, more than two camera devices are arranged in the same scene, and the parking spaces repeatedly calibrated in different devices are subjected to linkage identification and mutual verification, so that the identification accuracy is improved. If the street that big tree sheltered from, adopt about to dispose camera device respectively and can monitor the parking stall on the highway section completely, to the parking stall of two camera device common monitoring, then need mark as the linkage.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (4)
1. A roadside parking management method based on an image recognition technology is characterized by comprising the following steps: the method comprises the following steps:
s1, the parking acquisition unit shoots an image picture, carries out parking space calibration and then sends parking space GPS information, parking space calibration information and parking space initial information to the big data unit through the network transmission device;
the parking space calibration specifically comprises the following steps:
s11, marking four vertex angles of the parking space by using a marking tool in the obtained video image to form a self-closed image interval, wherein each self-closed interval is a parking space;
s12, after marking all parking space intervals, saving the parking space outline as an image detection range;
s13, generating parking spaces according to the parking space outline map, and automatically numbering each generated parking space by the system;
s14, carrying out initialization operation on the generated parking space and judging the parking state of the current parking space;
s2, carrying out parking space state updating on the parking space image acquired by the image processing device, and sending the detection result to a big data unit through a network transmission device;
the method for updating the parking space state in the step S2 comprises the following steps:
s21, reference frame acquisition: the camera collects parking space images at a set frequency to serve as a reference frame;
s22, acquiring a background image: when the parking space state is idle, comparing the acquired reference frame with the existing background images one by one, if the similarity of the characteristic value is smaller than a threshold value, saving the reference frame as the parking space background image, and if no background image which can be compared exists at present, directly saving the reference frame as the background image;
s23, vehicle entering and exiting recognition: monitoring the frame difference of the parking space area, wherein the information amount of the frame difference exceeds a threshold value, starting a motion detection unit to track a motion target, and updating the state of the parking space;
the moving target tracking in the step S23 further includes multi-target tracking, which is used for monitoring that one image processing device is used for simultaneously parking in multiple parking spaces, and when two targets enter and exit the parking spaces simultaneously, the system records;
the method for tracking the moving target comprises the following steps: determining that the target is a vehicle according to the ratio of the rigid body area to the parking space area of the target, and judging whether the vehicle is abnormally parked;
the method specifically comprises the following steps: determining that the target is a vehicle, then performing similarity comparison by using a pattern recognition module, and using a machine learning algorithm by using the pattern recognition module to learn the outlines of different types of vehicles at different shooting angles so as to further confirm the vehicle types; the motion detection module is also used for detecting whether the vehicle is in a parking compliance or not, and judging whether the line pressing parking is abnormal if the projection area of the rigid body is not completely integrated into the parking space area; if the projection area of the rigid body occupies two parking space areas, judging that parking in the parking space is abnormal;
the machine learning algorithm automatically adopts a feedback type learning model for the parking space as a supplement of the existing background, and specifically comprises the following steps: firstly, learning parking space background images collected in different time period environments; then, a decision feedback module is utilized to continuously train the pattern recognition capability to accurately recognize the vehicle type: the camera unit obtains profile pictures of different types of vehicle rigid bodies at different shooting angles, the profile pictures are stored in the big data unit through the network transmission device, and the data supplement is carried out by the information supplement module;
s3, the big data unit receives and stores the parking space information sent by the network transmission device, and a parking space vehicle owner registers the parking space information by himself;
s4, if the parking space vehicle owner is not registered, the information processing unit triggers and pushes reminding data to the inspection unit to arrive at the parking space site to finish shooting and evidence obtaining and license plate inputting, and the reminding data is transmitted to the data center unit through the mobile communication terminal to finish vehicle registration;
and S5, the information processing unit calculates the parking time length, generates a parking bill and pushes the parking bill to the vehicle owner unit.
2. The utility model provides a curb parking management system based on image recognition technology which characterized in that: the system comprises a parking acquisition unit, a big data unit, an information processing unit, a patrol unit and an owner unit, wherein the parking acquisition unit is used for acquiring a shot image picture in real time, calibrating a parking space and uploading information data to the big data unit; the big data unit is used for storing data, processing parking data and charging data; the information processing unit is used for analyzing and processing the parking conditions of all parking spaces at the roadside; the inspection unit is used for monitoring the use condition of the parking space and the vehicle information of the abnormal parking space; the vehicle owner unit is used for registering information of a vehicle owner and paying parking fee;
the parking acquisition unit comprises a camera device, an image processing device and a network transmission device, wherein the camera device acquires parking space images as reference frames according to a set frequency, the image processing device carries out parking space calibration and target tracking according to the shot images and transmits the processed data to the big data unit through the network transmission device; the camera device comprises a camera for shooting pictures and a GPS module for positioning;
the image processing apparatus includes: the parking space calibration module generates parking spaces according to the shot images and numbers the generated parking spaces; the storage module is used for storing a background picture; the comparison module is used for comparing the acquired reference frame with the existing background image one by one; the motion detection module is used for tracking a target and judging whether the vehicle is abnormally parked; the system comprises a night identification module and an exception handling module, wherein the night identification module is used for judging vehicle access according to the characteristics of vehicle lamps, and the exception handling module is used for informing the patrol unit to carry out manual verification when a parking space exception state occurs; the abnormity processing module is also used for collecting the parking space images at the frequency of 5 minutes/time as a reference frame, comparing the reference frame with the background image, and if the similarity is less than a threshold value, the state is parking; if the similarity with the background image is greater than a threshold value, the state is idle;
the motion detection module is used for tracking the target and specifically comprises the following steps: the moving target tracking also comprises multi-target tracking, and is used for coping with monitoring that one image processing device copes with the simultaneous parking of a plurality of parking spaces, and when two targets enter and exit the parking spaces simultaneously, the system records; the method for tracking the moving target comprises the following steps: determining that the target is a vehicle according to the ratio of the rigid body area to the parking space area of the target, and judging whether the vehicle is abnormally parked; the method specifically comprises the following steps: determining that the target is a vehicle, then performing similarity comparison by using a pattern recognition module, and using a machine learning algorithm by using the pattern recognition module to learn the outlines of different types of vehicles at different shooting angles so as to further confirm the vehicle types; the motion detection module is also used for detecting whether the vehicle is in a parking compliance or not, and judging whether the line pressing parking is abnormal if the projection area of the rigid body is not completely integrated into the parking space area; if the projection area of the rigid body occupies two parking space areas, judging that parking in the parking space is abnormal; the machine learning algorithm automatically adopts a feedback type learning model for the parking space as a supplement of the existing background, and specifically comprises the following steps: firstly, learning parking space background images collected in different time period environments; then, a decision feedback module is utilized to continuously train the pattern recognition capability to accurately recognize the vehicle type: the image pickup unit acquires contour pictures of different types of vehicle rigid bodies at different shooting angles, the contour pictures are stored in the big data unit through the network transmission device, and the information supplement module supplements data.
3. The system according to claim 2, wherein the system comprises: the big data unit includes: the vehicle owner data module is used for recording the registered information of a vehicle owner unit;
the parking space data module is used for recording parking space GPS information, parking space calibration information, parking space initial information and updated parking space state information;
the vehicle data module is used for recording vehicle information;
the information supplementing module is used for supplementing information according to the contour pictures of different types of vehicles acquired by the camera device;
and the charging data module is used for recording charging information.
4. The system according to claim 3, wherein the system comprises: the information processing unit includes:
the parking space management module is used for allocating parking spaces to vehicle owners according to the monitored parking space state information;
the system comprises an owner management module, a registration module and a registration module, wherein the owner management module is used for processing owner registration information;
the inspection management module is used for distributing inspection units according to the camera device and pushing abnormal information to the corresponding inspection units;
the charging management module is used for calculating the parking time length, generating a parking bill and pushing the parking bill to the vehicle owner unit;
and the parking record statistical analysis module is used for statistically analyzing all parking data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710640795.6A CN107195198B (en) | 2017-07-31 | 2017-07-31 | Roadside parking management method and system based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710640795.6A CN107195198B (en) | 2017-07-31 | 2017-07-31 | Roadside parking management method and system based on image recognition technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107195198A CN107195198A (en) | 2017-09-22 |
| CN107195198B true CN107195198B (en) | 2020-11-24 |
Family
ID=59884375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710640795.6A Active CN107195198B (en) | 2017-07-31 | 2017-07-31 | Roadside parking management method and system based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107195198B (en) |
Families Citing this family (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730985A (en) * | 2017-10-18 | 2018-02-23 | 冯迎安 | A kind of unmanned plane seeks stall system and its control method |
| CN107610523A (en) * | 2017-10-18 | 2018-01-19 | 冯迎安 | A kind of parking stall automatic monitoring alarm method |
| CN107644548A (en) * | 2017-11-01 | 2018-01-30 | 迪蒙智慧交通（深圳）有限公司 | A kind of Roadside Parking position management method and system |
| CN107610524A (en) * | 2017-11-02 | 2018-01-19 | 济南浪潮高新科技投资发展有限公司 | A kind of method and device that parking position Intelligent Recognition is carried out using laser radar |
| CN107886761A (en) * | 2017-11-14 | 2018-04-06 | 金陵科技学院 | A kind of parking lot monitoring method based on unmanned plane |
| CN107959825A (en) * | 2017-11-14 | 2018-04-24 | 浙江浙大中控信息技术有限公司 | Police vehicle-mounted videograph evidence-obtaining system and monitoring method |
| CN107945566A (en) * | 2017-11-17 | 2018-04-20 | 张慧 | Curb parking management system and method based on multiple target tracking and deep learning |
| CN108182378A (en) * | 2017-11-27 | 2018-06-19 | 西安艾润物联网技术服务有限责任公司 | Vehicle is marched into the arena data correcting method, equipment and computer readable storage medium |
| CN108198431A (en) * | 2017-12-29 | 2018-06-22 | 西安艾润物联网技术服务有限责任公司 | Vehicle parking detection device |
| CN107945573A (en) * | 2017-12-29 | 2018-04-20 | 西安艾润物联网技术服务有限责任公司 | Vehicle parking detecting system |
| CN110310506A (en) * | 2018-03-21 | 2019-10-08 | 昱通资讯事业股份有限公司 | Curb parking lattice management system |
| CN108520236A (en) * | 2018-04-09 | 2018-09-11 | 迪蒙智慧交通（深圳）有限公司 | It drives into and outgoing vehicles information collecting method, device and information of vehicles processing system |
| CN108765593A (en) * | 2018-06-04 | 2018-11-06 | 四川能投光电有限公司 | Wisdom lamp stand parking management system |
| CN108766022B (en) * | 2018-06-11 | 2020-02-04 | 青岛串并联电子科技有限公司 | Parking lot parking space state identification method and system based on machine learning |
| CN108765975B (en) * | 2018-06-21 | 2020-09-25 | 智慧互通科技有限公司 | Roadside vertical parking lot management system and method |
| CN108765976B (en) * | 2018-06-21 | 2020-09-25 | 智慧互通科技有限公司 | Roadside parallel parking information management system and method |
| CN110958421A (en) * | 2018-09-25 | 2020-04-03 | 刘景丽 | Parking meter device with video image recognition, monitoring and charging functions |
| CN109767626B (en) * | 2018-12-20 | 2021-03-16 | 北京筑梦园科技有限公司 | Roadside parking inspection method and system, patrol car and server |
| CN110119730A (en) * | 2019-06-03 | 2019-08-13 | 齐鲁工业大学 | A kind of monitor video processing method, system, terminal and storage medium |
| CN110310378B (en) * | 2019-07-24 | 2022-07-05 | 广东艾科智泊科技股份有限公司 | Open parking lot parking charging method and system based on double technologies |
| CN110491168B (en) * | 2019-08-09 | 2020-09-25 | 智慧互通科技有限公司 | Method and device for detecting vehicle parking state based on wheel landing position |
| CN111079575B (en) * | 2019-11-29 | 2023-06-23 | 拉货宝网络科技有限责任公司 | Material identification method and system based on package image characteristics |
| CN111091718B (en) * | 2019-12-31 | 2022-02-15 | 广东华车智库智能科技有限公司 | Parking monitoring early warning method and parking monitoring early warning system |
| CN111325858B (en) * | 2020-03-06 | 2022-01-07 | 赛特斯信息科技股份有限公司 | Method for realizing automatic charging management aiming at roadside temporary parking space |
| CN113470196B (en) * | 2020-03-31 | 2023-06-13 | 武汉巴别塔科技有限公司 | Parking information processing method, storage medium and electronic device |
| 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 |
| CN112309121A (en) * | 2020-11-05 | 2021-02-02 | 广州信息投资有限公司 | Parking guidance method and system based on intelligent lamp pole platform |
| CN112509360A (en) * | 2020-11-05 | 2021-03-16 | 南京市德赛西威汽车电子有限公司 | Parking lot parking space information calibration method, management system and parking lot |
| CN112885136A (en) * | 2021-01-27 | 2021-06-01 | 安徽蓝鸟智能停车科技产业化有限公司 | Parking space position dynamic right confirming method and system based on block chain |
| CN112560814A (en) * | 2021-02-20 | 2021-03-26 | 成都申亚科技有限公司 | Method for identifying vehicles entering and exiting parking spaces |
| CN115019546A (en) * | 2022-05-26 | 2022-09-06 | 北京精英路通科技有限公司 | Parking prompting method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090177388A1 (en) * | 2008-01-08 | 2009-07-09 | Schmidt Thorsten W | Method For Operating A Navigation System |
| CN101656023A (en) * | 2009-08-26 | 2010-02-24 | 西安理工大学 | Management method of indoor car park in video monitor mode |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102915638A (en) * | 2012-10-07 | 2013-02-06 | 复旦大学 | Surveillance video-based intelligent parking lot management system |
| CN104463992A (en) * | 2014-12-10 | 2015-03-25 | 江苏东大金智信息***有限公司 | Unattended curb parking management method |
| CN205920509U (en) * | 2016-01-22 | 2017-02-01 | 智慧互通科技有限公司 | Vehicle charging information acquisition device who removes |
| CN105809972B (en) * | 2016-03-24 | 2018-08-24 | 牛力伟 | A kind of parking management method and device, system |
| CN106373405B (en) * | 2016-09-29 | 2019-04-12 | 浙江宇视科技有限公司 | Parking position monitoring system and method |
-
2017
- 2017-07-31 CN CN201710640795.6A patent/CN107195198B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090177388A1 (en) * | 2008-01-08 | 2009-07-09 | Schmidt Thorsten W | Method For Operating A Navigation System |
| CN101656023A (en) * | 2009-08-26 | 2010-02-24 | 西安理工大学 | Management method of indoor car park in video monitor mode |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107195198A (en) | 2017-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107195198B (en) | Roadside parking management method and system based on image recognition technology | |
| CN108765976B (en) | Roadside parallel parking information management system and method | |
| CN108986539B (en) | Parking management system, method, vehicle information acquisition device and management server | |
| CN205788779U (en) | A kind of Roadside Parking management system | |
| CN104981377B (en) | The control using single many parking spaces of multiple photographic head uses | |
| CN102521986B (en) | Control method for automatic detection system for fake plate vehicle | |
| CN108765975B (en) | Roadside vertical parking lot management system and method | |
| US10445592B2 (en) | Method for surveilling a tolling system | |
| KR102287051B1 (en) | Parking space managing system by using image recognizing device | |
| CN110070729B (en) | Illegal parking vehicle detection system and method based on fog calculation | |
| CN108491782A (en) | A kind of vehicle identification method based on driving Image Acquisition | |
| CN113744420B (en) | Road parking charge management method, system and computer readable storage medium | |
| CN112509325B (en) | Video deep learning-based off-site illegal automatic discrimination method | |
| CN113055823B (en) | Method and device for managing shared bicycle based on road side parking | |
| CN108932850B (en) | Method and device for recording low-speed driving illegal behaviors of motor vehicle | |
| CA3113494A1 (en) | Parking lot management system based on real-time computer vision processing | |
| TWI607323B (en) | Method and system for vehicle data integration | |
| CN116504068A (en) | Statistical method, device, computer equipment and storage medium for lane-level traffic flow | |
| CN115311891B (en) | Roadside and parking lot free parking space sharing method, system and storage medium | |
| CN111260953A (en) | In-road parking management method, device and system | |
| KR20020032049A (en) | A fare collection a means | |
| CN115761915A (en) | Parking arrearage following payment method and system based on parking big data | |
| CN110599764B (en) | Vehicle-mounted terminal anti-disassembly method, device and medium based on highway charging | |
| CN113821924A (en) | Vehicle real-time data acquisition system, positioning check method and mileage analysis method | |
| CN113345116A (en) | Roadside parking charging system and device based on automatic inspection equipment |
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 | ||
| CB02 | Change of applicant information |
Address after: 400000 No. 2, No. 2, No.2 village, Guanyin Bridge, Jiangbei District, Chongqing City, 7-4 Applicant after: Chongqing Cqbay Technology Development Co., Ltd. Address before: 400000 Chongqing city Shapingba District Longhu Xiyong micro electronics industrial park lats defense 23-2-901 Applicant before: Chongqing Cqbay Technology Development Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |