CN108399667A - Parking stall ground lock control device and method - Google Patents
Parking stall ground lock control device and method Download PDFInfo
- Publication number
- CN108399667A CN108399667A CN201810065623.5A CN201810065623A CN108399667A CN 108399667 A CN108399667 A CN 108399667A CN 201810065623 A CN201810065623 A CN 201810065623A CN 108399667 A CN108399667 A CN 108399667A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- vehicle identification
- image
- parking stall
- gradient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 28
- 238000000605 extraction Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of parking stall lock control device and method, described device include：Image capture module is used for collection vehicle image information, and the vehicle image information is sent to model analysis module；Model analysis module for extracting vehicle identification feature from the vehicle image information, and judges type of vehicle according to the vehicle identification feature, and will determine that result is sent to master controller；Master controller, if consistent with preset vehicle type, locks unlock instruction with sending for comparing the judging result and preset vehicle type.The present invention is that vehicle is locked with unlocking automatically by vehicle identification, and car owner seamless can use parking stall without any operation, and process for using is simple, shortens down time, promotion user experience.
Description
Technical field
The present invention relates to parking stall lock technology field more particularly to a kind of parking stall ground lock control device and method.
Background technology
In recent years, there is drastically shortage in being significantly increased with personal vehicle guaranteeding organic quantity, parking stall quantity, some are lived
Residence cell or parking lot usually face the situation of parking stall deficiency.Parking stall is occupied privately by other car owners in order to prevent, parking
The owner of position can lock with being installed on parking stall, to show ownership and the right to use.The mechanical, hand-driven that traditional ground lock uses
The mode of change, during use, car owner needs to get off to unlock or unlock by key again, not only not convenient, but also due to
The privately owned attribute of key makes parking stall special.
It is ripe day by day with Internet technology, it locks to some intelligent car positions and is also more and more widely used, be
User brings huge facility.User can be locked to remote operation by operating mobile terminal without getting off.But current
It intelligently locks and generally APP is used to carry out remote management, generally require to solve in conjunction with functions such as the APP combination bluetooths that operator provides
Lock ground lock, user can not avoid downloading, and register user, search and etc..It is required for relying on when car owner is locked using ground every time and move
Terminal is locked over the ground to be unlocked or is unlocked, and process for using is complicated, poor user experience.
Invention content
Technical problem to be solved by the present invention lies in lock control device and method, pass through vehicle with providing a kind of parking stall
Identification is automatically vehicle unlock ground lock, and car owner seamless can use parking stall without any operation, and process for using is simple, shortens parking
Time promotes user experience.
A kind of in order to solve the above technical problem, the present invention provides parking stall lock control device, including：
Image capture module is used for collection vehicle image information, and the vehicle image information is sent to model analysis
Module；
Model analysis module, for extracting vehicle identification feature from the vehicle image information, and according to the vehicle
Identification feature judges type of vehicle, and will determine that result is sent to master controller；
Master controller, for comparing the judging result and preset vehicle type, if with preset vehicle type one
It causes, then locks unlock instruction with sending.
Further, described image acquisition module includes one or more cameras, and the camera setting is described
It locks, or side described is locked in setting, the camera is used for captured in real-time video, obtains video data.
Further, the model analysis module includes vehicle region extraction unit, vehicle characteristics extraction unit and vehicle
Grader, wherein
The vehicle region extraction unit for from the video data identification into shooting area vehicle, and from institute
It states in video data and splits, obtain vehicle region image；
The vehicle characteristics extraction unit be used for from the vehicle region image obtain vehicle identification area image, and from
Vehicle identification feature is extracted in the vehicle identification area image；
The vehicle classification device is used to judge type of vehicle according to the vehicle identification feature.
Further, the vehicle identification region is front face region, and the front face region is rectangular area, the square
The lower boundary in shape region is bumper, and coboundary is headlight upper edge.
Further, the vehicle identification feature includes one or more in mark, color, shape, texture and gradient.
Further, the vehicle identification is characterized as that gradient, the vehicle characteristics extraction unit include：
Image preprocessing subelement for vehicle identification area image to be carried out gray processing processing, and gray processing is handled
Vehicle identification area image afterwards is divided into multiple images block, then each described image block is divided into multiple images unit；
First processing subelement, the horizontal direction gradient for extracting each pixel in each elementary area respectively,
Vertical gradient and pixel value, and according to the horizontal direction gradient extracted, vertical gradient and calculated for pixel values obtain
The gradient magnitude and gradient direction of each pixel；
Second processing subelement, for as unit of elementary area, using acquired each pixel gradient magnitude and
Gradient direction is voted into column hisgram, obtains the multidimensional histogram vectogram of each elementary area, and to multidimensional histogram vector
It is standardized；
Feature extraction subelement, for respectively connecting the standardization histogram vectogram of each image elementary area in the block
Dimension-reduction treatment is carried out to described eigenvector, as the feature vector of the image block to extract vehicle identification for a vector
Feature.
Further, the vehicle classification device includes multiple local classifiers, and each local classifiers correspond to different
The weight of vehicle also differs, and the vehicle identification feature is input to the vehicle classification device, is obtained according to nearest neighbouring rule
Corresponding type of vehicle.
According to a further aspect of the invention, a kind of parking stall is also provided lock control method, including:
Collection vehicle image information；
Vehicle identification feature is extracted from the vehicle image information, and vehicle class is judged according to the vehicle identification feature
Type obtains judging result；
The judging result and preset vehicle type are compared, if consistent with preset vehicle type, locked with sending
Unlock instruction.
Further, the collection vehicle image information includes the following steps：
It is locked on ground or side is locked on ground, one or more cameras are set；
By the camera captured in real-time video, video data is obtained.
Further, described that vehicle identification feature is extracted from the vehicle image information, and according to the vehicle identification
Feature judges type of vehicle, obtains judging result and includes the following steps：
Identification enters the vehicle of shooting area from the video data, and is split from the video data, obtains
To vehicle region image；
Vehicle identification area image is obtained from the vehicle region image, and is carried from the vehicle identification area image
Pick-up identification feature；
Judge type of vehicle according to the vehicle identification feature.
Further, the vehicle identification region is front face region, and the front face region is rectangular area, the square
The lower boundary in shape region is bumper, and coboundary is headlight upper edge.
Further, the vehicle identification feature includes one or more in mark, color, shape, texture and gradient.
Further, the vehicle identification is characterized as gradient, and vehicle identification is extracted from the vehicle identification area image
Feature includes the following steps：
Vehicle identification area image is subjected to gray processing processing, and gray processing treated vehicle identification area image is drawn
It is divided into multiple images block, then each described image block is divided into multiple images unit；
The horizontal direction gradient of each pixel in each elementary area, vertical gradient and pixel are extracted respectively
Value, and the gradient width of each pixel is obtained according to the horizontal direction gradient extracted, vertical gradient and calculated for pixel values
Value and gradient direction；
As unit of elementary area, thrown into column hisgram using the gradient magnitude and gradient direction of acquired each pixel
Ticket obtains the multidimensional histogram vectogram of each elementary area, and is standardized to the multidimensional histogram vector；
The standardization histogram vectogram of each image elementary area in the block is connected as a vector respectively, as the figure
As the feature vector of block, dimension-reduction treatment is carried out to described eigenvector, to extract vehicle identification feature.
Further, judge that type of vehicle includes the following steps according to the vehicle identification feature：
The vehicle identification feature is inputted into vehicle classification device, the vehicle classification device exports the judging result.
Further, the vehicle classification device includes multiple local classifiers, and each local classifiers correspond to different
The weight of vehicle also differs, and the vehicle identification feature is input to the vehicle classification device, is obtained according to nearest neighbouring rule
Corresponding type of vehicle.
Further, the method further includes：
The corresponding vehicle identification feature of each local classifiers is obtained in advance, and each of acquired part is classified respectively
The corresponding vehicle identification feature of device is fitted, and obtains each local classifiers；
All local classifiers are integrated, vehicle classification device is obtained.
According to another aspect of the invention, a kind of controller is provided comprising memory and processor, the memory storage
There is the step of computer program, described program can realize the method when being executed by the processor.
According to another aspect of the invention, a kind of computer readable storage medium is provided, it is described for storing computer program
The step of program realizes the method when by a computer or processor execution.
The present invention has clear advantage and advantageous effect compared with prior art.By above-mentioned technical proposal, the present invention
A kind of parking stall lock control device and method can reach comparable technological progress and practicability, and with the extensive profit in industry
With value, at least there are following advantages：
The present invention is that vehicle is locked with unlocking automatically by vehicle identification, is not necessarily to any user's operation, can not only simplify
Process for using shortens down time, promotes user experience, and car owner is allowed seamless can to use parking stall without any operation, and
The availability and utilization rate on parking stall can be greatlyd improve.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, and in order to allow the above and other objects, features and advantages of the present invention can
It is clearer and more comprehensible, it is special below to lift preferred embodiment, and coordinate attached drawing, detailed description are as follows.
Description of the drawings
Fig. 1 is one embodiment of the invention with providing parking stall lock control device schematic diagram；
Fig. 2 be the parking stall that provides of one embodiment of the invention the camera of lock control device schematic diagram is set；
Fig. 3 be the parking stall that provides of another embodiment of the present invention the camera of lock control device schematic diagram is set；
Fig. 4 is one embodiment of the invention with providing parking stall lock control method schematic diagram.
Specific implementation mode
It is of the invention to reach the technological means and effect that predetermined goal of the invention is taken further to illustrate, below in conjunction with
Attached drawing and preferred embodiment, to a kind of parking stall for proposing according to the present invention the specific implementation mode of lock control device and method and
Its effect is described in detail as after.
As shown in Figure 1, a kind of with providing parking stall lock control device, including image capture module 1, vehicle of the embodiment of the present invention
Analysis module 2 and master controller 3, wherein image capture module 1 is used for collection vehicle image information, and by the vehicle image
Information is sent to model analysis module 2；Model analysis module 2 is used to extract vehicle identification from the vehicle image information special
Sign, and type of vehicle is judged according to the vehicle identification feature, and will determine that result is sent to master controller 3；Master controller 3 is used
It is compared in by the judging result and preset vehicle type, if consistent with preset vehicle type, lock unlock with sending and refer to
It enables, locks automatic unlocking with making parking stall.
In order to extract effective information as much as possible, as an example, image capture module 1 includes a camera, with ground
Lock is bound and is locked with being mounted on, position 1 as shown in Figure 2.Or locked independently of ground, it is mounted on ground lock side, is located at parking stall
Surrounding any position, the position positions 2- 8 as shown in Figure 3.The camera is used for captured in real-time video, obtains video data.
The video data includes the ordered set being made of a frame frame video image, i.e. video sequence, as an example, the video counts
Can also include segmenting video sequence according to may include single hop video sequence.Image capture module may also include monitoring unit, when
Dangerous situation is monitored, is alerted, such as sends out warning information.The unsafe condition is preset depending on specific requirements,
Such as when under vehicle chassis there are children, send out carry out alarm prompt.Or changed using thermal imaging monitoring domain battery characteristics, it fills
Alarm is sent out when electricity overheat or stops charging.
Model analysis module 2 includes vehicle region extraction unit, vehicle characteristics extraction unit and vehicle classification device, wherein
When there is vehicle to drive towards parking stall, vehicle region extraction unit from the video data for identifying the vehicle into shooting area
, and split from the video data, obtain vehicle region image, it should be noted that due to the position of camera
Fixed, the background of camera shooting does not have big variation in a short time, therefore the algorithm identification of image recognition may be used
Go out to enter the vehicle of shooting area, and split from video data, to obtain vehicle region image, the calculation of image recognition
Method can be that background subtraction divides detection method or other image recognition algorithms.Vehicle characteristics extraction unit is used for from the vehicle region
Vehicle identification area image is obtained in image, and vehicle identification feature is extracted from the vehicle identification area image.Wherein, vehicle
Feature extraction unit can be used the extracting operation method in morphology and isolate the parts such as bonnet, vehicle window, to obtain vehicle
Identification region image.Vehicle classification device is used to judge type of vehicle according to the vehicle identification feature.
As an example, the vehicle identification region is front face region, and the front face region is rectangular area, institute
The lower boundary for stating rectangular area is bumper, and coboundary is headlight upper edge, and vehicle width direction the right and left is rectangular area other two
Side.Face region includes a large amount of feature, such as mark, color, shape, texture and gradient before vehicle, chooses one of which or more
Vehicle identification feature carried out by feature is planted to identify vehicle.
It is described in detail below using gradient as vehicle identification feature, vehicle characteristics extraction unit includes image preprocessing
Subelement, the first processing subelement, second processing subelement and feature extraction subelement, wherein image preprocessing subelement is used
In vehicle identification area image is carried out gray processing processing, and by gray processing, treated that vehicle identification area image is divided into is more
A image block, then each described image block is divided into multiple smaller elementary areas, if elementary area includes p × q pixel.
First processing subelement is used to extract the horizontal direction ladder of each pixel (x, y) in each elementary area respectively
Spend Gx(x, y), vertical gradient Gy(x, y) and pixel value H (x, y), and according to the horizontal direction gradient G extractedx(x, y),
Vertical gradient GyThe gradient magnitude G (x, y) and ladder of each pixel (x, y) is calculated in (x, y) and pixel value H (x, y)
Direction α (x, y) is spent, calculation formula is as follows：
Gx(x, y)=H (x+1, y)-H (x-1, y)
Gy(x, y)=H (x, y+1)-H (x, y-1)
Second processing subelement be used for as unit of elementary area, using acquired each pixel gradient magnitude G (x,
Y) it votes into column hisgram with gradient direction α (x, y), wherein ballot region of the gradient direction as histogram, from 0-180 ° point
For N (for positive integer) a deflection, and the weight that gradient magnitude is voted as histogram, the N-dimensional for obtaining each elementary area are straight
Direction spirogram, and the N-dimensional histogram vector is standardized.
Feature extraction subelement is for respectively connecting the standardization histogram vectogram of each image elementary area in the block
Dimension-reduction treatment is carried out to described eigenvector using dimension-reduction algorithm as the feature vector of the image block for a vector, to
Vehicle identification feature is extracted, dimension-reduction algorithm can be linear discriminant analysis.
Vehicle classification device includes multiple local classifiers, and each local classifiers correspond to the weights of different automobile types also not
It is identical, the vehicle identification feature is input to the vehicle classification device, corresponding type of vehicle is obtained according to nearest neighbouring rule.
The corresponding vehicle identification feature of each local classifiers obtained, and acquired each local classifiers are corresponded to
Vehicle identification feature be fitted, obtain local classifiers.Multiple local classifiers of gained are carried out using integrated approach
It is integrated, improve the effect of vehicle cab recognition, obtains vehicle cab recognition grader.In use, it can be carried with a large amount of test datas
Previous existence is at vehicle cab recognition grader.
In application process, first master controller can be initialized, then carries out the authentication of vehicle again, in addition, master control
Device processed is additionally operable to, and after detecting that vehicle leaves, is sent ground lock out code, is lockked ground lock.
Described ground lock control device can be applied to energy express delivery, generation visitor's power-up, the services such as valet parking.Ground lock control device
Vehicle characteristics can be imported, are specific vehicle automatic unlocking in conjunction with vehicle authentication process.It is illustrated below in conjunction with electric vehicle power-up：
When the free time of parking stall, parking stall charging pile is idle, locks to parking stall and is in the lock state, while camera is opened WIFI and closed.Or it will
Camera is set as opening on demand, such as can trigger camera unlatching when needed, when without camera shooting, closes camera shooting
Head reduces cost to save electric energy, improves availability.Car owner asks power-up, system worksheet processing to parking stall charging pile.Power-up personnel
It drives near vehicle to parking stall, camera identifies face before vehicle, opens charging pile WIFI and starts to authenticate.WIFI is after the authentication is passed
WIFI is closed, and master controller is locked to ground sends unlock instruction, and prompt unit can be arranged sends out acousto-optic response prompt user and drive into
Parking stall, plug in rifle are begun to power up.Power-up finishes, and charging gun resets, vehicle sail out of behind parking stall lock it is automatic locking.
Ground of the present invention lock control device can also increase vehicle interactive unit, and realization such as provides for autonomous driving vehicle
Aid parking, automatic unlocking parking stall charging pile open the functions such as charging.
Ground of the present invention lock control device is that vehicle is locked with unlocking automatically by vehicle identification, is grasped without any user
Make, can not only simplify process for using, shorten down time, promote user experience, allow car owner can be seamless without any operation
Using parking stall, and the availability and utilization rate on parking stall can be greatlyd improve.
According to a further aspect of the invention, as shown in figure 4, a kind of with also providing parking stall lock control method of the embodiment of the present invention,
Including:
Step S1, collection vehicle image information；
In order to extract effective information as much as possible, as an example,
Step S1 may include：
Step S11, it is locked on ground or side is locked on ground, one or more cameras are set；
As an example, a camera can be arranged, locks with ground and lock with binding and be mounted on, position 1 as shown in Figure 2.Or
Person locks independently of ground, is mounted on ground lock side, is located at any position around parking stall, the position positions 2- 8 as shown in Figure 3.Institute
Camera is stated for captured in real-time video.
Step S12, by the camera captured in real-time video, video data is obtained.
The video data includes the ordered set being made of a frame frame video image, i.e. video sequence, as an example, institute
It may include single hop video sequence to state video data, can also include segmenting video sequence.
Step S1 can also include the steps of：
Step S13, when camera gets default dangerous information, warning information is sent out.
The dangerous information is preset depending on specific requirements, such as when having children under vehicle chassis, is sent out and is accused
Alert prompt.Alarm is sent out when either using thermal imaging monitoring domain battery characteristics variation charging overheat or stops charging.
Step S2, vehicle identification feature is extracted from the vehicle image information, and is sentenced according to the vehicle identification feature
Disconnected type of vehicle, obtains judging result；
The step S2 includes the following steps：
When step S21, having vehicle to drive towards parking stall, the vehicle into shooting area is identified from the video data, and
It is split from the video data, obtains vehicle region image；
It should be noted that the position due to camera is fixed, the background of camera shooting does not have greatly in a short time
Variation, therefore the algorithm that image recognition may be used identifies the vehicle into shooting area, and divides from video data
Out, to obtain vehicle region image, the algorithm of image recognition can be that background subtraction divides detection method or other image recognitions
Algorithm.
Step S22, vehicle identification area image is obtained from the vehicle region image, and from the vehicle identification region
Vehicle identification feature is extracted in image；
Wherein, the extracting operation method that can be used in morphology isolates the parts such as bonnet, vehicle window, to obtain vehicle
Identification region image.
Judge type of vehicle according to the vehicle identification feature.
As an example, the vehicle identification region is front face region, and the front face region is rectangular area, institute
The lower boundary for stating rectangular area is bumper, and coboundary is headlight upper edge.Vehicle width direction the right and left is rectangular area other two
Side.Face region includes a large amount of feature, such as mark, color, shape, texture and gradient before vehicle, chooses one of which or more
Vehicle identification feature carried out by feature is planted to identify vehicle.
Be described in detail below using gradient as vehicle identification feature, step S22 from the vehicle identification administrative division map
Extraction vehicle identification feature specifically includes as in：
Step S201, vehicle identification area image is subjected to gray processing processing, and by gray processing treated vehicle identification
Area image is divided into multiple images block, then each described image block is divided into multiple smaller elementary areas, if image list
Member includes p × q pixel.
Step S202, the horizontal direction gradient G of each pixel (x, y) in each elementary area is extracted respectivelyx(x,
Y), vertical gradient Gy(x, y) and pixel value H (x, y), and according to the horizontal direction gradient G extractedx(x, y), Vertical Square
To gradient GyThe gradient magnitude G (x, y) and gradient direction α of each pixel (x, y) is calculated in (x, y) and pixel value H (x, y)
(x, y), calculation formula are as follows：
Gx(x, y)=H (x+1, y)-H (x-1, y)
Gy(x, y)=H (x, y+1)-H (x, y-1)
Step S203, as unit of elementary area, using the gradient magnitude G (x, y) and gradient of acquired each pixel
Direction α (x, y) votes into column hisgram, wherein ballot region of the gradient direction as histogram is divided into N from 0-180 ° (for just
Integer) a deflection, and the weight that gradient magnitude is voted as histogram, the N-dimensional histogram vectogram of each elementary area is obtained,
And the N-dimensional histogram vector is standardized.
Step S204, respectively by the standardization histogram vectogram of each image elementary area in the block be connected as one to
Amount carries out dimension-reduction treatment, to extract vehicle using dimension-reduction algorithm as the feature vector of the image block to described eigenvector
Identification feature, dimension-reduction algorithm can be linear discriminant analysis.
In step S2, judge that type of vehicle includes the following steps according to the vehicle identification feature：
The vehicle identification feature is inputted into vehicle classification device, the vehicle classification device exports the judging result.
Vehicle classification device includes multiple local classifiers, and each local classifiers correspond to the weights of different automobile types also not
It is identical, the vehicle identification feature is input to the vehicle classification device, corresponding type of vehicle is obtained according to nearest neighbouring rule.
The method further includes step S4, the corresponding vehicle identification feature that obtains each local classifiers in advance, and by institute
The corresponding vehicle identification feature of each local classifiers obtained is fitted, and obtains each local classifiers.Using integrated side
Method integrates obtained multiple local classifiers, improves the effect of vehicle cab recognition, obtains vehicle cab recognition grader.Make
With in the process, vehicle cab recognition grader can be generated in advance with a large amount of test datas.
Step S3, the judging result and preset vehicle type are compared, if consistent with preset vehicle type, is sent out
It locks unlock instruction with sending, locks automatic unlocking with making parking stall.
In application process, drop institute's control method can first lock master controller over the ground before progress and be initialized, so
It carries out the authentication of vehicle again afterwards, in addition, the method may also include step S5, after detecting that vehicle leaves, sends ground lock and close
Instruction is closed, ground lock is lockked.
Described ground lock control method can be applied to energy express delivery, generation visitor's power-up, the services such as valet parking.Vehicle can be imported in advance
Feature is specific vehicle automatic unlocking in conjunction with vehicle authentication process.It is illustrated below in conjunction with electric vehicle power-up：Parking stall is idle
When, parking stall charging pile is idle, locks to parking stall and is in the lock state, while camera is opened, and WIFI is closed.Or camera is set
It is set to on-demand opening, such as camera unlatching can be triggered when needed, when without camera shooting, camera is closed, with section
Electric energy is saved, cost is reduced, improves availability.Car owner asks power-up, system worksheet processing to parking stall charging pile.Power-up personnel drive vehicle
To parking stall, camera identifies face before vehicle, opens charging pile WIFI and starts to authenticate.WIFI after the authentication is passed WIFI close,
Master controller is locked to ground sends unlock instruction, and can be arranged and send out acousto-optic response prompt user and drive into parking stall, and plug in rifle is begun to power up.
Power-up finishes, and charging gun resets, vehicle sail out of behind parking stall lock it is automatic locking.
Ground of the present invention lock control method can also increase vehicle interactive step, and realization such as provides for autonomous driving vehicle
Aid parking, automatic unlocking parking stall charging pile open the functions such as charging.
Ground of the present invention lock control method is that vehicle is locked with unlocking automatically by vehicle identification, is grasped without any user
Make, can not only simplify process for using, shorten down time, promote user experience, allow car owner can be seamless without any operation
Using parking stall, and the availability and utilization rate on parking stall can be greatlyd improve.
The embodiment of the present invention also provides a kind of controller comprising memory and processor, the memory are stored with meter
The step of calculation machine program, described program can realize the method when being executed by the processor.
Inventive embodiments also provide a kind of computer readable storage medium, and for storing computer program, described program exists
The step of the method being realized when being executed by a computer or processor.
The above described is only a preferred embodiment of the present invention, be not intended to limit the present invention in any form, though
So the present invention has been disclosed as a preferred embodiment, and however, it is not intended to limit the invention, any technology people for being familiar with this profession
Member, without departing from the scope of the present invention, when the technology contents using the disclosure above make a little change or modification
For the equivalent embodiment of equivalent variations, as long as being the content without departing from technical solution of the present invention, according to the technical essence of the invention
To any simple modification, equivalent change and modification made by above example, in the range of still falling within technical solution of the present invention.
Claims (18)
1. a kind of parking stall ground lock control device, it is characterised in that：Including：
Image capture module is used for collection vehicle image information, and the vehicle image information is sent to model analysis module；
Model analysis module, for extracting vehicle identification feature from the vehicle image information, and according to the vehicle identification
Feature judges type of vehicle, and will determine that result is sent to master controller；
Master controller, for the judging result and preset vehicle type to be compared, if consistent with preset vehicle type,
Send ground lock unlock instruction.
2. parking stall according to claim 1 ground lock control device, it is characterised in that：
Described image acquisition module includes one or more cameras, and the camera setting described is locked, or setting exists
Side is locked describedly, and the camera is used for captured in real-time video, obtains video data.
3. parking stall according to claim 2 ground lock control device, it is characterised in that：
The model analysis module includes vehicle region extraction unit, vehicle characteristics extraction unit and vehicle classification device, wherein
The vehicle region extraction unit is regarded for identifying the vehicle into shooting area from the video data from described
Frequency is split in, obtains vehicle region image；
The vehicle characteristics extraction unit is used to obtain vehicle identification area image from the vehicle region image, and from described
Vehicle identification feature is extracted in vehicle identification area image；
The vehicle classification device is used to judge type of vehicle according to the vehicle identification feature.
4. parking stall according to claim 3 ground lock control device, it is characterised in that：
The vehicle identification region be front face region, the front face region be rectangular area, the rectangular area it is following
Boundary is bumper, and coboundary is headlight upper edge.
5. parking stall according to any one of claim 1-4 ground lock control device, it is characterised in that：
The vehicle identification feature includes one or more in mark, color, shape, texture and gradient.
6. parking stall according to claim 3 ground lock control device, it is characterised in that：
The vehicle identification is characterized as that gradient, the vehicle characteristics extraction unit include：
Image preprocessing subelement, for vehicle identification area image to be carried out gray processing processing, and treated by gray processing
Vehicle identification area image is divided into multiple images block, then each described image block is divided into multiple images unit；
First processing subelement, the horizontal direction gradient for extracting each pixel in each elementary area respectively, vertically
Direction gradient and pixel value, and according to the horizontal direction gradient extracted, vertical gradient and calculated for pixel values obtain each
The gradient magnitude and gradient direction of pixel；
Second processing subelement is used for as unit of elementary area, using the gradient magnitude and gradient of acquired each pixel
Direction is voted into column hisgram, obtains the multidimensional histogram vectogram of each elementary area, and carry out to the multidimensional histogram vector
Standardization；
Feature extraction subelement, for the standardization histogram vectogram of each image elementary area in the block to be connected as one respectively
A vector carries out dimension-reduction treatment as the feature vector of the image block to described eigenvector, to extract vehicle identification spy
Sign.
7. parking stall according to claim 3 ground lock control device, it is characterised in that：
The vehicle classification device includes multiple local classifiers, and each local classifiers correspond to the weights of different automobile types also not
It is identical, the vehicle identification feature is input to the vehicle classification device, corresponding type of vehicle is obtained according to nearest neighbouring rule.
8. a kind of parking stall ground lock control method, it is characterised in that：Including:
Collection vehicle image information；
Vehicle identification feature is extracted from the vehicle image information, and type of vehicle is judged according to the vehicle identification feature,
Obtain judging result；
The judging result and preset vehicle type are compared, if consistent with preset vehicle type, lock unlock with sending
Instruction.
9. parking stall according to claim 8 ground lock control method, it is characterised in that：
The collection vehicle image information includes the following steps：
It is locked on ground or side is locked on ground, one or more cameras are set；
By the camera captured in real-time video, video data is obtained.
10. parking stall according to claim 9 ground lock control method, it is characterised in that：
It is described that vehicle identification feature is extracted from the vehicle image information, and vehicle class is judged according to the vehicle identification feature
Type obtains judging result and includes the following steps：
Identification enters the vehicle of shooting area from the video data, and is split from the video data, obtains vehicle
Area image；
Vehicle identification area image is obtained from the vehicle region image, and extracts vehicle from the vehicle identification area image
Identification feature；
Judge type of vehicle according to the vehicle identification feature.
11. parking stall according to claim 10 ground lock control method, it is characterised in that：
The vehicle identification region be front face region, the front face region be rectangular area, the rectangular area it is following
Boundary is bumper, and coboundary is headlight upper edge.
12. parking stall according to any one of claim 8-11 ground lock control method, it is characterised in that：
The vehicle identification feature includes one or more in mark, color, shape, texture and gradient.
13. parking stall according to claim 10 ground lock control method, it is characterised in that：
The vehicle identification is characterized as gradient, and it includes following step that vehicle identification feature is extracted from the vehicle identification area image
Suddenly：
Vehicle identification area image is subjected to gray processing processing, and treated that vehicle identification area image is divided by gray processing
Multiple images block, then each described image block is divided into multiple images unit；
The horizontal direction gradient of each pixel in each elementary area, vertical gradient and pixel value are extracted respectively, and
According to the horizontal direction gradient extracted, vertical gradient and calculated for pixel values obtain the gradient magnitude and ladder of each pixel
Spend direction；
As unit of elementary area, voted into column hisgram using the gradient magnitude and gradient direction of acquired each pixel,
The multidimensional histogram vectogram of each elementary area is obtained, and the multidimensional histogram vector is standardized；
The standardization histogram vectogram of each image elementary area in the block is connected as a vector respectively, as the image block
Feature vector, to described eigenvector carry out dimension-reduction treatment, to extract vehicle identification feature.
14. parking stall according to claim 10 ground lock control method, it is characterised in that：
Judge that type of vehicle includes the following steps according to the vehicle identification feature：
The vehicle identification feature is inputted into vehicle classification device, the vehicle classification device exports the judging result.
15. parking stall according to claim 14 ground lock control method, it is characterised in that：
The vehicle classification device includes multiple local classifiers, and each local classifiers correspond to the weights of different automobile types also not
It is identical, the vehicle identification feature is input to the vehicle classification device, corresponding type of vehicle is obtained according to nearest neighbouring rule.
16. parking stall according to claim 15 ground lock control method, it is characterised in that：
The method further includes：
The corresponding vehicle identification feature of each local classifiers is obtained in advance, and respectively by acquired each local classifiers pair
The vehicle identification feature answered is fitted, and obtains each local classifiers；
All local classifiers are integrated, vehicle classification device is obtained.
17. a kind of controller comprising memory and processor, the memory are stored with computer program, and described program exists
The step of capable of realizing the method described in any one of claim 8 to 16 claim when being executed by the processor.
18. a kind of computer readable storage medium, for storing computer program, described program is by a computer or processor
The step of method as described in any one of claim 8 to 16 claim is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810065623.5A CN108399667A (en) | 2018-01-23 | 2018-01-23 | Parking stall ground lock control device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810065623.5A CN108399667A (en) | 2018-01-23 | 2018-01-23 | Parking stall ground lock control device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108399667A true CN108399667A (en) | 2018-08-14 |
Family
ID=63094222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810065623.5A Pending CN108399667A (en) | 2018-01-23 | 2018-01-23 | Parking stall ground lock control device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108399667A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111063063A (en) * | 2019-11-29 | 2020-04-24 | 上海钧正网络科技有限公司 | Shared vehicle unlocking method and device, computer equipment and storage medium |
| CN111267665A (en) * | 2020-02-17 | 2020-06-12 | 国网安徽电动汽车服务有限公司 | Method for realizing electric automobile charging by judging automobile type through image |
| CN111359122A (en) * | 2020-02-17 | 2020-07-03 | 国网安徽电动汽车服务有限公司 | Anti-theft intelligent fire-fighting cabinet used in electric charging occasion and intelligent fire-fighting method thereof |
| CN111696378A (en) * | 2019-03-25 | 2020-09-22 | 泰州腾翔信息科技有限公司 | Automatic image data analysis method |
| CN112037369A (en) * | 2020-07-23 | 2020-12-04 | 汇纳科技股份有限公司 | Unlocking method, system, medium and device of automatic parking spot lock based on vehicle identification |
| CN112289070A (en) * | 2020-10-20 | 2021-01-29 | 广州小鹏自动驾驶科技有限公司 | Parking space detection method and device, vehicle and readable medium |
| CN113205059A (en) * | 2021-05-18 | 2021-08-03 | 北京纵目安驰智能科技有限公司 | Parking space detection method, system, terminal and computer readable storage medium |
| CN115171420A (en) * | 2022-05-30 | 2022-10-11 | 东风柳州汽车有限公司 | Vehicle parking and taking control method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299416A (en) * | 2014-09-29 | 2015-01-21 | 浙江宇视科技有限公司 | Automatic parking space locking method and system based on video license plate detection |
| CN105427667A (en) * | 2016-01-18 | 2016-03-23 | 江苏工程职业技术学院 | Intelligent stall ground lock control method and device |
| US20160093127A1 (en) * | 2014-09-29 | 2016-03-31 | Ncr Corporation | Entry point validation systems and methods |
| CN106677092A (en) * | 2017-01-12 | 2017-05-17 | 李良杰 | Carport lock capable of automatically identifying vehicle license plate |
| CN206178414U (en) * | 2016-11-29 | 2017-05-17 | 四川农业大学 | Car parking stall lock intelligence control system based on car plate number identification module |
-
2018
- 2018-01-23 CN CN201810065623.5A patent/CN108399667A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299416A (en) * | 2014-09-29 | 2015-01-21 | 浙江宇视科技有限公司 | Automatic parking space locking method and system based on video license plate detection |
| US20160093127A1 (en) * | 2014-09-29 | 2016-03-31 | Ncr Corporation | Entry point validation systems and methods |
| CN105427667A (en) * | 2016-01-18 | 2016-03-23 | 江苏工程职业技术学院 | Intelligent stall ground lock control method and device |
| CN206178414U (en) * | 2016-11-29 | 2017-05-17 | 四川农业大学 | Car parking stall lock intelligence control system based on car plate number identification module |
| CN106677092A (en) * | 2017-01-12 | 2017-05-17 | 李良杰 | Carport lock capable of automatically identifying vehicle license plate |
Non-Patent Citations (1)
| Title |
|---|
| 马蓓蓓: "基于HOG特征的车辆检测技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111696378A (en) * | 2019-03-25 | 2020-09-22 | 泰州腾翔信息科技有限公司 | Automatic image data analysis method |
| CN111696378B (en) * | 2019-03-25 | 2020-12-08 | 六安同辉智能科技有限公司 | Automatic image data analysis method |
| CN111063063A (en) * | 2019-11-29 | 2020-04-24 | 上海钧正网络科技有限公司 | Shared vehicle unlocking method and device, computer equipment and storage medium |
| CN111267665A (en) * | 2020-02-17 | 2020-06-12 | 国网安徽电动汽车服务有限公司 | Method for realizing electric automobile charging by judging automobile type through image |
| CN111359122A (en) * | 2020-02-17 | 2020-07-03 | 国网安徽电动汽车服务有限公司 | Anti-theft intelligent fire-fighting cabinet used in electric charging occasion and intelligent fire-fighting method thereof |
| CN112037369A (en) * | 2020-07-23 | 2020-12-04 | 汇纳科技股份有限公司 | Unlocking method, system, medium and device of automatic parking spot lock based on vehicle identification |
| CN112289070A (en) * | 2020-10-20 | 2021-01-29 | 广州小鹏自动驾驶科技有限公司 | Parking space detection method and device, vehicle and readable medium |
| CN112289070B (en) * | 2020-10-20 | 2021-12-07 | 广州小鹏自动驾驶科技有限公司 | Parking space detection method and device, vehicle and readable medium |
| CN113205059A (en) * | 2021-05-18 | 2021-08-03 | 北京纵目安驰智能科技有限公司 | Parking space detection method, system, terminal and computer readable storage medium |
| CN113205059B (en) * | 2021-05-18 | 2024-03-12 | 北京纵目安驰智能科技有限公司 | Parking space detection method, system, terminal and computer readable storage medium |
| CN115171420A (en) * | 2022-05-30 | 2022-10-11 | 东风柳州汽车有限公司 | Vehicle parking and taking control method, device, equipment and storage medium |
| CN115171420B (en) * | 2022-05-30 | 2024-01-30 | 东风柳州汽车有限公司 | Vehicle parking and taking control method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108399667A (en) | Parking stall ground lock control device and method | |
| CN103434484B (en) | Vehicle-mounted identification authenticate device, mobile terminal, intelligent vehicle key control system and method | |
| JP7145887B2 (en) | Vehicle, vehicle door unlocking control method, device, and vehicle door unlocking system | |
| US9965610B2 (en) | Physical system access control | |
| CN107967806A (en) | Vehicle fake-license detection method, device, readable storage medium storing program for executing and electronic equipment | |
| CN106803301A (en) | A kind of recognition of face guard method and system based on deep learning | |
| CN107590492B (en) | A kind of vehicle-logo location and recognition methods based on convolutional neural networks | |
| CN108304830A (en) | Personnel identity on-line monitoring method, device and storage medium in vehicle | |
| CN101949241A (en) | Intelligent switch device and method of car door | |
| US20130250108A1 (en) | Access Control System by Face Recognition in An Automobile | |
| CN102708691B (en) | False license plate identification method based on matching between license plate and automobile type | |
| US11279321B2 (en) | Imaging apparatus having a reduced power consumption mode and mode that generates a captured image | |
| US9208172B2 (en) | Method and system for vehicle identification | |
| CN108877009B (en) | Intelligent access control system based on face recognition | |
| CN106895553A (en) | Air-conditioning and its control method and device, alarm method and device | |
| CN108846938A (en) | The antitheft management method and device in intelligent Community parking lot | |
| CN106951846A (en) | A kind of face 3D models typing and recognition methods and device | |
| CN111223303B (en) | Charging pile parking space management method, device and system | |
| CN108038920A (en) | Parking lot management method, system and the server to parking lot management | |
| CN109460787A (en) | IDS Framework method for building up, device and data processing equipment | |
| CN103612617A (en) | Automobile anti-theft anti-robbery system | |
| CN106586731A (en) | Visitor identifying system and method and cat eye | |
| CN115914584B (en) | Dynamic early warning monitoring method, system and readable storage medium | |
| CN206741505U (en) | Identify management equipment and device | |
| CN109410250B (en) | Visual image-based vehicle arrival identification method and terminal |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200724 Address after: Susong Road West and Shenzhen Road North, Hefei Economic and Technological Development Zone, Anhui Province Applicant after: Weilai (Anhui) Holding Co., Ltd Address before: 30 Floor of Yihe Building, No. 1 Kangle Plaza, Central, Hong Kong, China Applicant before: NIO NEXTEV Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180814 |
|
| RJ01 | Rejection of invention patent application after publication |