CN109447077A - A kind of license plate intelligent identifying system and method for parking lot - Google Patents
A kind of license plate intelligent identifying system and method for parking lot Download PDFInfo
- Publication number
- CN109447077A CN109447077A CN201811144705.5A CN201811144705A CN109447077A CN 109447077 A CN109447077 A CN 109447077A CN 201811144705 A CN201811144705 A CN 201811144705A CN 109447077 A CN109447077 A CN 109447077A
- Authority
- CN
- China
- Prior art keywords
- license plate
- control centre
- vehicle
- image
- character
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Traffic Control Systems (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
Abstract
The present invention relates to a kind of license plate intelligent identifying systems and method for parking lot, including image collecting device, secondary light source device, display device and control centre.The present invention can judge type of vehicle according to license plate color, and it gives priority in arranging for according to the automobile that the remaining capacity of electric car is not enough power supply and has the parking stall of charging pile, parking service is preferably provided, since license plate intelligent identification Method of the invention needs for vehicle allocation parking stall, therefore the parking lot that parking stall is fixed in cell is not suitable for, suitable for the parking lot in market or the Public Parking of outdoor；Charging pile is further divided into the direct-current charging post of fast charge and the alternating-current charging pile of trickle charge, when electricity is very low, preferential recommendation direct-current charging post, otherwise, it can recommend alternating-current charging pile, and the traveling guiding route from Entrance to parking stall can be generated, be sent to client, user is preferably guided to find the parking stall of distribution in parking lot.
Description
Technical field
The present invention relates to technical field of data processing, in particular to a kind of license plate intelligent identifying system for parking lot and
Method.
Background technique
In the prior art, Car license recognition is always one of research hotspot and key technology of Intelligent traffic management systems.Vehicle
Board identification using very extensive, such as highway automatic charging, parking lot fee collection management, criminal investigation detection etc..If made
Mode manually identifies these license plates, is bound to waste many manpower and material resources.
With the development of society, automatic Recognition of License Plate is applied in people's lives more and more, automatically
Identification equipment starts to be laid in cell doorway, community parking field and market parking lot etc., automatic identification license plate number and automatic charging,
Many convenience are brought to people's life.However, license plate recognition technology function in the prior art is relatively simple, it can not be according to knowledge
Not Chu license plate more miscellaneous functions are provided.
Summary of the invention
It is existing its object is to overcome the present invention provides a kind of license plate intelligent identifying system and method for parking lot
The defects of technology can judge type of vehicle according to license plate color, and be not enough power supply according to the remaining capacity of electric car
Automobile give priority in arranging for and have the parking stall of charging pile, preferably offer parking service.
To achieve the goals above, the present invention has following constitute:
This is used for the license plate intelligent identifying system in parking lot, including image collecting device, secondary light source device, display device
And control centre, in which:
Described image acquisition device acquires the vehicle image at Entrance；
The control centre identifies the rivet in the vehicle image at the Entrance, determines rivet location；
The control centre positions license plate according to rivet location, and license plate area figure is extracted from the vehicle image
Picture；
The control centre extracts the RGB color value of license plate color from the license plate area image；
The control centre carries out gray proces to the license plate area image, obtains gray level image；
The control centre carries out binary conversion treatment to the gray level image, obtains the binaryzation of the license plate area image
Image；
The control centre carries out Character segmentation to the binary image, obtains the binary picture of multiple character zones
Picture；
The control centre inputs the binary image of each character zone in trained character recognition model, obtains
The recognition result of each character zone, the input of the character recognition model are the binary image of single character zone, output
To identify obtained character；
The control centre puts in order according to each character zone, and the recognition result of each character zone is arranged
Sequence, the license plate number identified, and control the display device and show the license plate number identified；
The control centre judges whether the RGB color value of license plate color is located at the RGB face of preset electric car license plate
Within the scope of color value, if it is, the control centre determines that vehicle is electric car；
If vehicle is electric car, whether the control centre is to have infused according to the license plate number enquiring vehicle identified
Volume vehicle；
If it is, the control centre communicates with Vehicle Electronic Control Unit corresponding to vehicle, the surplus of vehicle is obtained
Remaining electricity；
If the remaining capacity of vehicle is less than preset threshold, the control centre, which searches, charging pile and not in parking lot
The parking stall occupied by other vehicles；
The control centre controls the display device and shows that is found has a charging pile and do not occupied by other vehicles
The position on parking stall.
Optionally, the system also includes luminance sensor, the control centre is also stored with different range of luminance values pair
The binary conversion treatment threshold value answered；
The control centre carries out binary conversion treatment to the gray level image, includes the following steps:
The control centre obtains the detected value of the luminance sensor, is selected according to the detected value of the luminance sensor
Corresponding binary conversion treatment threshold value；
Gray value in the gray level image is greater than the pixel of corresponding binary conversion treatment threshold value by the control centre
Gray value is set to 255, and gray value in the gray level image is less than or equal to the ash of the pixel of corresponding binary conversion treatment threshold value
Angle value is set to 0.
Optionally, the trained character recognition model be convolutional neural networks model, active shape identification model or
Supporting vector machine model.
Optionally, the control centre is also used to acquire multiple character zone images with known character label as instruction
Practice collection, training character recognition model obtains trained character recognition model.
Optionally, the binary image of each character zone is inputted trained character recognition model by the control centre
In, the recognition result of each character zone is obtained, is included the following steps:
The control centre inputs the binary image of each character zone in trained character recognition model, obtains
The probability value of possible character corresponding to each character zone, the highest character of select probability value is as corresponding character zone
The character identified.
Optionally, the control centre according to the vehicle image at Entrance after identifying to obtain license plate number, note
Record license plate number and entry time；
Described image acquisition device is also used to acquire the vehicle image at parking exit；
The control centre is also used to identify the rivet in the vehicle image at the parking exit, determines rivet position
It sets；
The control centre positions license plate according to rivet location, and license plate area figure is extracted from the vehicle image
Picture；
The control centre extracts the RGB color value of license plate color from the license plate area image；
The control centre carries out gray proces to the license plate area image, obtains gray level image；
The control centre carries out binary conversion treatment to the gray level image, obtains the binaryzation of the license plate area image
Image；
The control centre carries out Character segmentation to the binary image, obtains the binary picture of multiple character zones
Picture；
The control centre inputs the binary image of each character zone in trained character recognition model, obtains
The recognition result of each character zone, the input of the character recognition model are the binary image of single character zone, output
To identify obtained character；
The control centre puts in order according to each character zone, and the recognition result of each character zone is arranged
Sequence, the license plate number identified；
The license plate number that control centre's judgement identifies whether there is in the license plate number record entered；
If it does not exist, then the control centre extracts the ash of the license plate area image of the vehicle image at parking exit
Image is spent, the average gray value of more each character zone selects the wherein minimum character zone of average gray value, as wait adjust
Whole character zone；
The control centre inputs the binary image of character zone to be adjusted in trained character recognition model, obtains
The probability value of each character into the recognition result of the character zone to be adjusted, successively select probability value is second largest to probability value the
Multiple to be determined recognition results of the five big characters as the character zone to be adjusted；
The control centre is successively identified using multiple recognition result replacement originals to be determined of the character zone to be adjusted
Number in corresponding character, form multiple license plate numbers to be determined；
The control centre judges whether multiple license plate numbers to be determined have an at least number to be present in the license plate entered
In number record；
If it is present the control centre is according to the license plate number to be determined being present in the license plate number entered record
Code judges whether it is registered vehicle；
If it is registered vehicle, the contact details of client corresponding to the vehicle are inquired by the control centre, to this
Client corresponding to vehicle sends confirmation message, and the confirmation message includes alternative license plate number, parking lot title, vehicle
Entry time and vehicle time departure；
If the control centre receives the corresponding license plate number confirmation message of the client, according to the client
It holds determining license plate number as the license plate number finally identified, vehicle is allowed to pass through, and remember from the license plate number entered
The corresponding record of the license plate number is deleted in record.
Optionally, the control centre identifies the rivet in the vehicle image at the Entrance, determines rivet position
It sets, includes the following steps:
The control centre identifies the rivet in the vehicle image, judges the quantity of rivet detected；
If only detecting two rivets, and the angle of the line of the line and horizontal direction of two rivets is less than default folder
Angle threshold value judges two rivets then for the rivet of same a line, extends up the first pre-determined distance conduct from the line of two rivets
License plate area boundary extends downwards the second pre-determined distance as boundary on the downside of license plate area from the line of two rivets, from
Third pre-determined distance is extended to the left as license plate area left border, from across right side rivet across the vertical line of left most rivet
Vertical line extends to the right third pre-determined distance as license plate area right side boundary, extracts license plate area image；
If detecting four rivets, judge position is on the upper side in four rivets two rivets for uplink rivet, position
Two rivets on the lower side are downlink rivet, extend up the first pre-determined distance as license plate area from the line of two uplink rivets
Boundary extends downwards the second pre-determined distance as boundary on the downside of license plate area, from two from the line of two lower section rivets
The line of left most rivet extends third pre-determined distance as license plate area left border to the left, from the lines of two right side rivets to
Right extension third pre-determined distance extracts license plate area image as license plate area right side boundary.
Optionally, the system also includes the cameras for being set to inner part of parking lot, and the control centre is when subscribing
Between acquire the image of each camera, judge whether each parking stall occupied according to the image of each camera；
The control centre searches after having charging pile in parking lot and the parking stall that is not occupied by other vehicles, the control
Stopping guide route is planned also according to the position on the parking stall and Entrance found in center processed；
The contact details of client corresponding to the vehicle are inquired by the control centre, to client corresponding to the vehicle
Send the parking stall found and stopping guide route.
Optionally, the charging pile in the parking lot includes direct-current charging post and alternating-current charging pile, and the control centre deposits
Contain each charging pile position and each charging pile installation, and the control centre is stored with the first preset threshold and second
Preset threshold, the first preset threshold is less than the second preset threshold；
If the remaining capacity of vehicle is less than preset threshold, the control centre, which searches, charging pile and not in parking lot
The parking stall occupied by other vehicles, includes the following steps:
If the remaining capacity of vehicle is less than the first preset threshold, the control centre, which searches in parking lot, has direct current to fill
Electric stake and the parking stall not occupied by other vehicles, if searched less than the control centre, which searches in parking lot, exchange
Charging pile and the parking stall not occupied by other vehicles；
If the remaining capacity of vehicle is more than or equal to the first preset threshold and less than the second preset threshold, in the control
The heart searches the parking stall for having alternating-current charging pile in parking lot and not occupied by other vehicles.
The embodiment of the present invention also provides a kind of license plate intelligent identification Method for parking lot, using described for stopping
The license plate intelligent identifying system of field, described method includes following steps:
Acquire the vehicle image at Entrance；
It identifies the rivet in the vehicle image at the Entrance, determines rivet location；
License plate is positioned according to rivet location, license plate area image is extracted from the vehicle image；
The RGB color value of license plate color is extracted from the license plate area image；
Gray proces are carried out to the license plate area image, obtain gray level image；
Binary conversion treatment is carried out to the gray level image, obtains the binary image of the license plate area image；
Character segmentation is carried out to the binary image, obtains the binary image of multiple character zones；
The binary image of each character zone is inputted in trained character recognition model, each character zone is obtained
Recognition result, the input of the character recognition model is the binary image of single character zone, exports identification and obtains
Character；
According to putting in order for each character zone, the recognition result of each character zone is ranked up, is identified
License plate number out, and control the display device and show the license plate number identified；
Judge whether the RGB color value of license plate color is located within the scope of the RGB color value of preset electric car license plate,
If it is, determining that vehicle is electric car；
It whether is registered vehicle according to the license plate number enquiring vehicle identified if vehicle is electric car；
If it is, communicating with Vehicle Electronic Control Unit corresponding to vehicle, the remaining capacity of vehicle is obtained；
If the remaining capacity of vehicle is less than preset threshold, searching in parking lot has charging pile and is not accounted for by other vehicles
Parking stall；
The display device shows the position on the parking stall for having charging pile and not occupied by other vehicles found.
Using the license plate intelligent identifying system and method for parking lot in the invention, have the following beneficial effects:
(1) type of vehicle can be judged according to license plate color, and is not enough power supply according to the remaining capacity of electric car
Automobile, which is given priority in arranging for, the parking stall of charging pile, preferably offer parking service, due to license plate intelligent identification Method of the invention
Need for vehicle allocation parking stall, therefore be not suitable for the parking lot that parking stall is fixed in cell, suitable for market parking lot or
Outdoor Public Parking；
(2) charging pile is further divided into the direct-current charging post of fast charge and the alternating-current charging pile of trickle charge, excellent when electricity is very low
First recommend direct-current charging post, otherwise, alternating-current charging pile can be recommended, and can be generated from Entrance to parking stall
Traveling guiding route, be sent to client, preferably guidance user parking stall that distribution is found in parking lot；
(3) Car license recognition mechanism for correcting errors is introduced, when the license plate that the license plate number that exit recognizes can not enter again
When finding in number record, illustrate that license plate number may be wrong, can improve license plate with further progress error correction and corrigendum at this time and know
Other accuracy rate.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of the license plate intelligent identifying system for parking lot of the invention；
Fig. 2 is the flow chart of the license plate intelligent identification Method for parking lot of the invention；
Fig. 3 is the schematic diagram of the invention that license plate area is selected according to two rivet locations；
Fig. 4 is the schematic diagram of the invention that license plate area is selected according to two rivet locations.
Specific embodiment
It is further to carry out combined with specific embodiments below in order to more clearly describe technology contents of the invention
Description.
License plate intelligent identifying system for parking lot as shown in Figure 1, including image collecting device, secondary light source dress
It sets, display device and control centre, in which:
Described image acquisition device acquires the vehicle image at Entrance；
The control centre identifies the rivet in the vehicle image at the Entrance, determines rivet location；
The control centre positions license plate according to rivet location, and license plate area figure is extracted from the vehicle image
Picture；
The control centre extracts the RGB color value of license plate color from the license plate area image；
The control centre carries out gray proces to the license plate area image, obtains gray level image；
The control centre carries out binary conversion treatment to the gray level image, obtains the binaryzation of the license plate area image
Image；
The control centre carries out Character segmentation to the binary image, obtains the binary picture of multiple character zones
Picture；
The control centre inputs the binary image of each character zone in trained character recognition model, obtains
The recognition result of each character zone, the input of the character recognition model are the binary image of single character zone, output
To identify obtained character；
The control centre puts in order according to each character zone, and the recognition result of each character zone is arranged
Sequence, the license plate number identified, and control the display device and show the license plate number identified；
The control centre judges whether the RGB color value of license plate color is located at the RGB face of preset electric car license plate
Within the scope of color value, if it is, the control centre determines that vehicle is electric car；
If vehicle is electric car, whether the control centre is to have infused according to the license plate number enquiring vehicle identified
Volume vehicle；
If it is, the control centre communicates with Vehicle Electronic Control Unit corresponding to vehicle, the surplus of vehicle is obtained
Remaining electricity；
If the remaining capacity of vehicle is less than preset threshold, the control centre, which searches, charging pile and not in parking lot
The parking stall occupied by other vehicles；
The control centre controls the display device and shows that is found has a charging pile and do not occupied by other vehicles
The position on parking stall.
As shown in Fig. 2, the embodiment of the present invention also provides a kind of license plate intelligent identification Method for parking lot, using described
The license plate intelligent identifying system for parking lot, described method includes following steps:
Acquire the vehicle image at Entrance；
It identifies the rivet in the vehicle image at the Entrance, determines rivet location；
License plate is positioned according to rivet location, license plate area image is extracted from the vehicle image；
The RGB color value of license plate color is extracted from the license plate area image；
Gray proces are carried out to the license plate area image, obtain gray level image；
Binary conversion treatment is carried out to the gray level image, obtains the binary image of the license plate area image；
Character segmentation is carried out to the binary image, obtains the binary image of multiple character zones；
The binary image of each character zone is inputted in trained character recognition model, each character zone is obtained
Recognition result, the input of the character recognition model is the binary image of single character zone, exports identification and obtains
Character；
According to putting in order for each character zone, the recognition result of each character zone is ranked up, is identified
License plate number out, and control the display device and show the license plate number identified；
Judge whether the RGB color value of license plate color is located within the scope of the RGB color value of preset electric car license plate,
If it is, determining that vehicle is electric car；The license plate of general electric car is RGB that is green, therefore can setting green
Color value range is the RGB color value range of preset electric car license plate；
It whether is registered vehicle according to the license plate number enquiring vehicle identified if vehicle is electric car；
If it is, communicating with Vehicle Electronic Control Unit corresponding to vehicle, the remaining capacity of vehicle is obtained；
If the remaining capacity of vehicle is less than preset threshold, searching in parking lot has charging pile and is not accounted for by other vehicles
Parking stall；
The display device shows the position on the parking stall for having charging pile and not occupied by other vehicles found.
In this embodiment, the system also includes luminance sensors, are also stored with different range of luminance values corresponding two
Value handles threshold value；
Binary conversion treatment is carried out to the gray level image, is included the following steps:
The detected value for obtaining the luminance sensor selects corresponding binaryzation according to the detected value of the luminance sensor
Handle threshold value；
The gray value that gray value in the gray level image is greater than the pixel of corresponding binary conversion treatment threshold value is set to
255, the gray value that gray value in the gray level image is less than or equal to the pixel of corresponding binary conversion treatment threshold value is set to 0.
In this embodiment, the trained character recognition model is convolutional neural networks model, the knowledge of ASM active shape
Other model or SVM supporting vector machine model etc..
In this embodiment, the control centre is also used to acquire multiple character zone images with known character label
As training set, training character recognition model obtains trained character recognition model.Each character zone figure i.e. in training set
It include a character as in, and known to the character in each character zone image.
In this embodiment, the binary image of each character zone is inputted trained character and known by the control centre
In other model, the recognition result of each character zone is obtained, is included the following steps:
The control centre inputs the binary image of each character zone in trained character recognition model, obtains
The probability value of possible character corresponding to each character zone, the highest character of select probability value is as corresponding character zone
The character identified.For example, the binary image of a character zone is after inputting character recognition model, the result of output
Are as follows: the probability value that character is P is 60%, and the probability value that character is B is 30%, and the probability value that character is 8 is 10%.Then select P
The character identified as the character zone.
In this embodiment, the control centre identifies to obtain license plate number according to the vehicle image at Entrance
Afterwards, license plate number and entry time are recorded；
Described image acquisition device is also used to acquire the vehicle image at parking exit；
The control centre is also used to identify the rivet in the vehicle image at the parking exit, determines rivet position
It sets；
The control centre positions license plate according to rivet location, and license plate area figure is extracted from the vehicle image
Picture；
The control centre extracts the RGB color value of license plate color from the license plate area image；
The control centre carries out gray proces to the license plate area image, obtains gray level image；
The control centre carries out binary conversion treatment to the gray level image, obtains the binaryzation of the license plate area image
Image；
The control centre carries out Character segmentation to the binary image, obtains the binary picture of multiple character zones
Picture；
The control centre inputs the binary image of each character zone in trained character recognition model, obtains
The recognition result of each character zone, the input of the character recognition model are the binary image of single character zone, output
To identify obtained character；
The control centre puts in order according to each character zone, and the recognition result of each character zone is arranged
Sequence, the license plate number identified；
The license plate number that control centre's judgement identifies whether there is in the license plate number record entered；
If it does not exist, then the control centre extracts the ash of the license plate area image of the vehicle image at parking exit
Image is spent, the average gray value of more each character zone selects the wherein minimum character zone of average gray value, as wait adjust
Whole character zone；
The control centre inputs the binary image of character zone to be adjusted in trained character recognition model, obtains
The probability value of each character into the recognition result of the character zone to be adjusted, successively select probability value is second largest to probability value the
Multiple to be determined recognition results of the five big characters as the character zone to be adjusted；
The control centre is successively identified using multiple recognition result replacement originals to be determined of the character zone to be adjusted
Number in corresponding character, form multiple license plate numbers to be determined；
The control centre judges whether multiple license plate numbers to be determined have an at least number to be present in the license plate entered
In number record；
If it is present the control centre is according to the license plate number to be determined being present in the license plate number entered record
Code judges whether it is registered vehicle；
If it is registered vehicle, the contact details of client corresponding to the vehicle are inquired by the control centre, to this
Client corresponding to vehicle sends confirmation message, and the confirmation message includes alternative license plate number, parking lot title, vehicle
Entry time and vehicle time departure；
If the control centre receives the corresponding license plate number confirmation message of the client, according to the client
It holds determining license plate number as the license plate number finally identified, vehicle is allowed to pass through, and remember from the license plate number entered
The corresponding record of the license plate number is deleted in record, and automatic charging can be carried out according to entry time and time departure.
In this embodiment, the control centre identifies the rivet in the vehicle image at the Entrance, determines
Rivet location includes the following steps:
The control centre identifies the rivet in the vehicle image, judges the quantity of rivet detected；
As shown in figure 3, if only detect two rivets A1 and A2, and the line and horizontal direction of two rivets A1 and A2
The angle of line be less than default angle threshold value, illustrate that the line of the two rivets A1 and A2 are substantially parallel with horizontal plane
, presetting angle threshold value herein can choose smaller, such as 15 °, 10 ° etc., then judge that two rivets A1 and A2 are same
The rivet of a line extends up the first pre-determined distance h1 as license plate area boundary from the line of two rivets A1 and A2,
The second pre-determined distance h2 is extended downwards as boundary on the downside of license plate area, from across left side riveting from the line of two rivets A1 and A2
The vertical line of nail A1 extends third pre-determined distance h3 as license plate area left border, from across the vertical of right side rivet A2 to the left
Line extends to the right third pre-determined distance h3 as license plate area right side boundary, extracts license plate area image Q；
As shown in figure 4, judging position in four rivets A1, A2, B1, B2 if detecting four rivets A1, A2, B1, B2
Setting two rivets A1, A2 on the upper side is uplink rivet, and position two rivets B1, B2 on the lower side are downlink rivet, from two uplinks
The line of rivet A1, A2 extend up the first pre-determined distance h1 as license plate area boundary, from two lower sections rivet B1, B2
Line extend the second pre-determined distance h1 downwards as boundary on the downside of license plate area, from the line of two left most rivets A1, B1 to
Left extension third pre-determined distance h3 extends to the right the as license plate area left border, from the line of two right sides rivet A2, B2
Three pre-determined distance h3 extract license plate area image Q as license plate area right side boundary.
In this embodiment, the system also includes the camera for being set to inner part of parking lot, the control centre every
Ticket reserving time acquires the image of each camera, judges whether each parking stall is occupied according to the image of each camera；
The control centre searches after having charging pile in parking lot and the parking stall that is not occupied by other vehicles, the control
Stopping guide route is planned also according to the position on the parking stall and Entrance found in center processed；
The contact details of client corresponding to the vehicle are inquired by the control centre, to client corresponding to the vehicle
Send the parking stall found and stopping guide route.
In this embodiment, the charging pile in the parking lot includes direct-current charging post and alternating-current charging pile, the control
Central store have each charging pile position and each charging pile installation, and the control centre is stored with the first preset threshold
With the second preset threshold, the first preset threshold is less than the second preset threshold；For example, the first preset threshold can be set to 20%,
Second preset threshold can be set to 40% etc., and specific value, which can according to need, to be selected；
If the remaining capacity of vehicle is less than preset threshold, the control centre, which searches, charging pile and not in parking lot
The parking stall occupied by other vehicles, includes the following steps:
If the remaining capacity of vehicle is less than the first preset threshold, the control centre, which searches in parking lot, has direct current to fill
Electric stake and the parking stall not occupied by other vehicles, if searched less than the control centre, which searches in parking lot, exchange
Charging pile and the parking stall not occupied by other vehicles；
If the remaining capacity of vehicle is more than or equal to the first preset threshold and less than the second preset threshold, in the control
The heart searches the parking stall for having alternating-current charging pile in parking lot and not occupied by other vehicles.
Compared with prior art, using the license plate intelligent identifying system and method for parking lot in the invention, tool
It has the advantages that:
(1) type of vehicle can be judged according to license plate color, and is not enough power supply according to the remaining capacity of electric car
Automobile, which is given priority in arranging for, the parking stall of charging pile, preferably offer parking service, due to license plate intelligent identification Method of the invention
Need for vehicle allocation parking stall, therefore be not suitable for the parking lot that parking stall is fixed in cell, suitable for market parking lot or
Outdoor Public Parking；
(2) charging pile is further divided into the direct-current charging post of fast charge and the alternating-current charging pile of trickle charge, excellent when electricity is very low
First recommend direct-current charging post, otherwise, alternating-current charging pile can be recommended, and can be generated from Entrance to parking stall
Traveling guiding route, be sent to client, preferably guidance user parking stall that distribution is found in parking lot；
(3) Car license recognition mechanism for correcting errors is introduced, when the license plate that the license plate number that exit recognizes can not enter again
When finding in number record, illustrate that license plate number may be wrong, can improve license plate with further progress error correction and corrigendum at this time and know
Other accuracy rate.
In this description, the present invention is described with reference to its specific embodiment.But it is clear that can still make
Various modifications and alterations are without departing from the spirit and scope of the invention.Therefore, the description and the appended drawings should be considered as illustrative
And not restrictive.
Claims (10)
1. a kind of license plate intelligent identifying system for parking lot, which is characterized in that filled including image collecting device, secondary light source
It sets, display device and control centre, in which:
Described image acquisition device acquires the vehicle image at Entrance；
The control centre identifies the rivet in the vehicle image at the Entrance, determines rivet location；
The control centre positions license plate according to rivet location, and license plate area image is extracted from the vehicle image；
The control centre extracts the RGB color value of license plate color from the license plate area image；
The control centre carries out gray proces to the license plate area image, obtains gray level image；
The control centre carries out binary conversion treatment to the gray level image, obtains the binary picture of the license plate area image
Picture；
The control centre carries out Character segmentation to the binary image, obtains the binary image of multiple character zones；
The control centre inputs the binary image of each character zone in trained character recognition model, obtains each
The recognition result of character zone, the input of the character recognition model are the binary image of single character zone, are exported to know
The character not obtained；
The control centre puts in order according to each character zone, and the recognition result of each character zone is ranked up,
The license plate number identified, and control the display device and show the license plate number identified；
The control centre judges whether the RGB color value of license plate color is located at the RGB color value of preset electric car license plate
Within the scope of, if it is, the control centre determines that vehicle is electric car；
If vehicle is electric car, whether the control centre is registered vehicle according to the license plate number enquiring vehicle identified
?；
If it is, the control centre communicates with Vehicle Electronic Control Unit corresponding to vehicle, the residue electricity of vehicle is obtained
Amount；
If the remaining capacity of vehicle is less than preset threshold, the control centre, which searches in parking lot, has charging pile and not by it
The parking stall that his vehicle occupies；
The control centre controls the display device and shows the parking for having charging pile and do not occupied by other vehicles found
The position of position.
2. the license plate intelligent identifying system according to claim 1 for parking lot, which is characterized in that the system is also wrapped
Include luminance sensor, the control centre is also stored with the corresponding binary conversion treatment threshold value of different range of luminance values；
The control centre carries out binary conversion treatment to the gray level image, includes the following steps:
The control centre obtains the detected value of the luminance sensor, selects to correspond to according to the detected value of the luminance sensor
Binary conversion treatment threshold value；
Gray value in the gray level image is greater than the gray scale of the pixel of corresponding binary conversion treatment threshold value by the control centre
Value is set to 255, and gray value in the gray level image is less than or equal to the gray value of the pixel of corresponding binary conversion treatment threshold value
It is set to 0.
3. the license plate intelligent identifying system according to claim 1 for parking lot, which is characterized in that described trained
Character recognition model is convolutional neural networks model, active shape identification model or supporting vector machine model.
4. the license plate intelligent identifying system according to claim 3 for parking lot, which is characterized in that the control centre
It is also used to acquire multiple character zone images with known character label as training set, training character recognition model obtains
Trained character recognition model.
5. the license plate intelligent identifying system according to claim 4 for parking lot, which is characterized in that the control centre
The binary image of each character zone is inputted in trained character recognition model, the identification knot of each character zone is obtained
Fruit includes the following steps:
The control centre inputs the binary image of each character zone in trained character recognition model, obtains each
The probability value of possible character corresponding to character zone, knowledge of the highest character of select probability value as corresponding character zone
Not Chu character.
6. the license plate intelligent identifying system according to claim 5 for parking lot, which is characterized in that the control centre
After identifying to obtain license plate number according to the vehicle image at Entrance, license plate number and entry time are recorded；
Described image acquisition device is also used to acquire the vehicle image at parking exit；
The control centre is also used to identify the rivet in the vehicle image at the parking exit, determines rivet location；
The control centre positions license plate according to rivet location, and license plate area image is extracted from the vehicle image；
The control centre extracts the RGB color value of license plate color from the license plate area image；
The control centre carries out gray proces to the license plate area image, obtains gray level image；
The control centre carries out binary conversion treatment to the gray level image, obtains the binary picture of the license plate area image
Picture；
The control centre carries out Character segmentation to the binary image, obtains the binary image of multiple character zones；
The control centre inputs the binary image of each character zone in trained character recognition model, obtains each
The recognition result of character zone, the input of the character recognition model are the binary image of single character zone, are exported to know
The character not obtained；
The control centre puts in order according to each character zone, and the recognition result of each character zone is ranked up,
The license plate number identified；
The license plate number that control centre's judgement identifies whether there is in the license plate number record entered；
If it does not exist, then the control centre extracts the grayscale image of the license plate area image of the vehicle image at parking exit
Picture, the average gray value of more each character zone select the wherein minimum character zone of average gray value, as word to be adjusted
Accord with region；
The control centre inputs the binary image of character zone to be adjusted in trained character recognition model, is somebody's turn to do
The probability value of each character in the recognition result of character zone to be adjusted, successively select probability value is second largest the fifth-largest to probability value
Multiple to be determined recognition results of the character as the character zone to be adjusted；
The control centre successively replaces former number identified using multiple recognition results to be determined of the character zone to be adjusted
Corresponding character in code forms multiple license plate numbers to be determined；
The control centre judges whether multiple license plate numbers to be determined have an at least number to be present in the license plate number entered
In record；
If it is present the control centre is sentenced according to the license plate number to be determined being present in the license plate number entered record
Whether disconnected is registered vehicle；
If it is registered vehicle, the contact details of client corresponding to the vehicle are inquired by the control centre, to the vehicle
Corresponding client sends confirmation message, and the confirmation message includes alternative license plate number, parking lot title, vehicle entrance
Time and vehicle time departure；
If the control centre receives the corresponding license plate number confirmation message of the client, true according to the client
Fixed license plate number allows vehicle to pass through as the license plate number finally identified, and from the license plate number record entered
Delete the corresponding record of the license plate number.
7. the license plate intelligent identifying system according to claim 1 for parking lot, which is characterized in that the control centre
It identifies the rivet in the vehicle image at the Entrance, determines rivet location, include the following steps:
The control centre identifies the rivet in the vehicle image, judges the quantity of rivet detected；
If only detecting two rivets, and the angle of the line of the line and horizontal direction of two rivets is less than default angle threshold
Value, then judge two rivets for the rivet of same a line, extend up the first pre-determined distance as license plate from the line of two rivets
Region boundary extends downwards the second pre-determined distance as boundary on the downside of license plate area from the line of two rivets, from passing through
The vertical line of left most rivet extends third pre-determined distance as license plate area left border, from across the vertical of right side rivet to the left
Line extends to the right third pre-determined distance as license plate area right side boundary, extracts license plate area image；
If detecting four rivets, position is on the upper side in four rivets two rivets are judged for uplink rivet, position is on the lower side
Two rivets be downlink rivet, from the line of two uplink rivets extend up the first pre-determined distance as license plate area upside
Boundary extends downwards the second pre-determined distance as boundary on the downside of license plate area, from two left sides from the line of two lower section rivets
The line of rivet extends third pre-determined distance as license plate area left border to the left, expands to the right from the line of two right side rivets
Third pre-determined distance is opened up as license plate area right side boundary, extracts license plate area image.
8. the license plate intelligent identifying system according to claim 1 for parking lot, which is characterized in that the system is also wrapped
The camera for being set to inner part of parking lot is included, the control centre acquires the image of each camera every the ticket reserving time, according to
The image of each camera judges whether each parking stall is occupied；
The control centre searches after having charging pile in parking lot and the parking stall that is not occupied by other vehicles, in the control
The heart plans stopping guide route also according to the position on the parking stall and Entrance found；
The contact details of client corresponding to the vehicle are inquired by the control centre, send to client corresponding to the vehicle
The parking stall found and stopping guide route.
9. the license plate intelligent identifying system according to claim 1 for parking lot, which is characterized in that in the parking lot
Charging pile include direct-current charging post and alternating-current charging pile, the control centre is stored with the position of each charging pile and each fills
Electric pile installation, and the control centre is stored with the first preset threshold and the second preset threshold, the first preset threshold is less than
Two preset thresholds；
If the remaining capacity of vehicle is less than preset threshold, the control centre, which searches in parking lot, has charging pile and not by it
The parking stall that his vehicle occupies, includes the following steps:
If the remaining capacity of vehicle is less than the first preset threshold, the control centre, which searches in parking lot, direct-current charging post
And the parking stall not occupied by other vehicles, if searched less than the control centre, which searches in parking lot, AC charging
Stake and the parking stall not occupied by other vehicles；
If the remaining capacity of vehicle is more than or equal to the first preset threshold and less than the second preset threshold, the control centre is looked into
The parking stall for having alternating-current charging pile and not occupied by other vehicles is looked in parking lot.
10. a kind of license plate intelligent identification Method for parking lot, which is characterized in that use any one of claims 1 to 9 institute
The license plate intelligent identifying system for parking lot stated, described method includes following steps:
Acquire the vehicle image at Entrance；
It identifies the rivet in the vehicle image at the Entrance, determines rivet location；
License plate is positioned according to rivet location, license plate area image is extracted from the vehicle image；
The RGB color value of license plate color is extracted from the license plate area image；
Gray proces are carried out to the license plate area image, obtain gray level image；
Binary conversion treatment is carried out to the gray level image, obtains the binary image of the license plate area image；
Character segmentation is carried out to the binary image, obtains the binary image of multiple character zones；
The binary image of each character zone is inputted in trained character recognition model, the knowledge of each character zone is obtained
Not as a result, the input of the character recognition model is the binary image of single character zone, export to identify obtained character；
According to putting in order for each character zone, the recognition result of each character zone is ranked up, is identified
License plate number, and control the display device and show the license plate number identified；
Judge whether the RGB color value of license plate color is located within the scope of the RGB color value of preset electric car license plate, if
It is then to determine vehicle for electric car；
It whether is registered vehicle according to the license plate number enquiring vehicle identified if vehicle is electric car；
If it is, communicating with Vehicle Electronic Control Unit corresponding to vehicle, the remaining capacity of vehicle is obtained；
If the remaining capacity of vehicle is less than preset threshold, searching has a charging pile and is not occupied by other vehicles in parking lot
Parking stall；
The display device shows the position on the parking stall for having charging pile and not occupied by other vehicles found.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811144705.5A CN109447077A (en) | 2018-09-29 | 2018-09-29 | A kind of license plate intelligent identifying system and method for parking lot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811144705.5A CN109447077A (en) | 2018-09-29 | 2018-09-29 | A kind of license plate intelligent identifying system and method for parking lot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109447077A true CN109447077A (en) | 2019-03-08 |
Family
ID=65544725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811144705.5A Withdrawn CN109447077A (en) | 2018-09-29 | 2018-09-29 | A kind of license plate intelligent identifying system and method for parking lot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109447077A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110217120A (en) * | 2019-06-18 | 2019-09-10 | 环球车享汽车租赁有限公司 | Parking management method, system, equipment and medium based on charging balance scheduling |
| CN111816000A (en) * | 2020-08-07 | 2020-10-23 | 福建师范大学福清分校 | Management system of intelligent charging parking lot |
| CN112669645A (en) * | 2019-10-16 | 2021-04-16 | 现代自动车株式会社 | Parking guidance system for parking space and parking guidance method using the same |
| JP2022083327A (en) * | 2020-11-24 | 2022-06-03 | トヨタ自動車株式会社 | Navigation server, navigation program, and navigation system |
-
2018
- 2018-09-29 CN CN201811144705.5A patent/CN109447077A/en not_active Withdrawn
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110217120A (en) * | 2019-06-18 | 2019-09-10 | 环球车享汽车租赁有限公司 | Parking management method, system, equipment and medium based on charging balance scheduling |
| CN112669645A (en) * | 2019-10-16 | 2021-04-16 | 现代自动车株式会社 | Parking guidance system for parking space and parking guidance method using the same |
| CN111816000A (en) * | 2020-08-07 | 2020-10-23 | 福建师范大学福清分校 | Management system of intelligent charging parking lot |
| JP2022083327A (en) * | 2020-11-24 | 2022-06-03 | トヨタ自動車株式会社 | Navigation server, navigation program, and navigation system |
| JP7452391B2 (en) | 2020-11-24 | 2024-03-19 | トヨタ自動車株式会社 | Navigation server, navigation program, and navigation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109447077A (en) | A kind of license plate intelligent identifying system and method for parking lot | |
| CN107526845A (en) | Parking lot storehouse handheld terminal, parking lot base management system and method | |
| CN108877035B (en) | Intelligent garbage recycling cabinet and garbage recycling method | |
| CN109559395B (en) | Control method for identifying entrance charging of unlicensed vehicle and storage device | |
| CN110853391A (en) | Intelligent shared parking system | |
| CN105913685A (en) | Video surveillance-based carport recognition and intelligent guide method | |
| CN207198849U (en) | Parking lot storehouse handheld terminal and parking lot base management system | |
| CN107301682A (en) | The charging method and device in parking lot | |
| CN106792551A (en) | Distinguish the method for charging, order car terminal and system in shared vehicle parking position | |
| CN113071350A (en) | Electric automobile fills mutual intercommunication shared data platform of electric pile equipment wisdom | |
| CN108544941B (en) | Charging method, device, electronic equipment and storage medium | |
| CN108777074A (en) | A kind of parking space management system and its management method based on image processing techniques | |
| CN112347864A (en) | Method, device, equipment and system for sensing and inducing rail transit passenger flow | |
| CN114038231B (en) | Parking lot utilization rate scheduling method, system, equipment and storage medium | |
| CN106203654A (en) | Hire a car method according to reservation time of chartering and the reservation of the real-time volume of the flow of passengers | |
| CN106327918A (en) | Parking lot intelligent charging management system with vehicle license plate recognition | |
| CN113486262B (en) | Electric vehicle charging station site selection method, system and readable storage medium | |
| CN108320582A (en) | A kind of parking management system having remaining parking stall statistical function | |
| CN109903555A (en) | A kind of bus passenger based on big data is got off data predication method and system | |
| CN114757411A (en) | Electric automobile charging pile recommendation system based on target cooperation technology | |
| KR101819568B1 (en) | The method for operating a parking management system according to recognition of electric vehicle and Hi-pass | |
| CN115392520A (en) | Charging guiding method and system for large charging station and storage medium | |
| CN110276617A (en) | Unmanned convenience store enters recognition methods, device, equipment and storage medium | |
| CN107808548A (en) | A kind of parking lot management method | |
| CN109447054A (en) | A kind of license plate intelligent identifying system and method for parking lot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190308 |
|
| WW01 | Invention patent application withdrawn after publication |