CN110148262A - A kind of third party's automobile leasing management system and automobile starting authorization method based on recognition of face - Google Patents
A kind of third party's automobile leasing management system and automobile starting authorization method based on recognition of face Download PDFInfo
- Publication number
- CN110148262A CN110148262A CN201910417530.9A CN201910417530A CN110148262A CN 110148262 A CN110148262 A CN 110148262A CN 201910417530 A CN201910417530 A CN 201910417530A CN 110148262 A CN110148262 A CN 110148262A
- Authority
- CN
- China
- Prior art keywords
- face
- vehicle
- information
- car
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/483—Physical analysis of biological material
- G01N33/497—Physical analysis of biological material of gaseous biological material, e.g. breath
- G01N33/4972—Determining alcohol content
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisious for transferring data to distant stations, e.g. from a sensing device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
- G07F17/0042—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for hiring of objects
- G07F17/0057—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for hiring of objects for the hiring or rent of vehicles, e.g. cars, bicycles or wheelchairs
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Pathology (AREA)
- Economics (AREA)
- Biochemistry (AREA)
- Marketing (AREA)
- Immunology (AREA)
- Medicinal Chemistry (AREA)
- Computer Security & Cryptography (AREA)
- Food Science & Technology (AREA)
- Urology & Nephrology (AREA)
- Analytical Chemistry (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Development Economics (AREA)
- Hematology (AREA)
- Biophysics (AREA)
Abstract
The present invention provides a kind of third party's automobile leasing management system and automobile starting authorization method based on recognition of face, the system comprises entity user, automobile rental corporation, mobile module, third-party platform and onboard systems, comprising: two dimensional code module, main control module, face recognition module, vehicle-mounted control module, alcohol sensor and alcohol detection module.Automobile starting authorization is realized using face recognition technology, car borrowing people by authorization need to only use two dimensional code personal account and vehicle binding before for the first time using the vehicle and stop the several seconds to recognition of face camera and make the expression of requirement, it is detected finally by alcohol, so that it may start automobile.Without the people of authorization, because there is no corresponding face information authorization in system, vehicle can not be started taking the key of the vehicle, the antitheft purpose after reaching key loss.
Description
Technical field
The present invention relates to authorization and technical field of burglary prevention, more particularly to and a kind of third party's automobile rent based on recognition of face
Management system of renting and automobile starting authorization method.
Background technique
With the rapid development of society, automobile enters family and is come true by dream, and people's daily trip habit changes
Become so that automobile becomes one of main vehicles.However, non-car owner, which authorizes, to be driven with the continuous improvement for borrowing vehicle demand
The accident and dispute and vehicle that vehicle causes are stolen repeated for phenomenon, have developed into the social concern got worse.
Mass data is the study found that driver drives a vehicle in the case where not drinking, the dangerous situation in discovery front, from visually perceiving
The reaction time stepped among brakeage is 0.75 second, and the reaction time will slow down 2-3 in the case where capable of still driving after drinking
Times, the braking distance under synchronized traveling also will accordingly extend, and increase a possibility that accident occurs after drinking.And the hair of traffic accident
It is raw not only cause a tremendous loss of lives, property loss, also bring on a disaster to countless families, and drastically influence social stability and system
About household economy accumulation, and then restrict entire society's economic development.
Currently, so-called car owner authorizes driving vehicle to remain in the original oral stage, it can not be by long-range effective
Control vehicle unauthorized driving.Although having developed many relevant technologies in terms of vehicle anti-theft, these technologies exist
Certain effect is also functioned in terms of vehicle anti-theft, but the theft problem for caused by key loss still lacks cost and fits
In, effective means.
Two dimensional code is with specific geometric figure according to certain rules in the chequered with black and white of plane (on two-dimensional directional) distribution
The barcode technology of new generation of rectangle square matrix record data symbol information, which has, to contain much information, and error correcting capability is strong, and recognition speed is fast, protects
The characteristics such as close property is high, and traceability is high, and damage resistance is strong, and redundant is big, and cost is cheap.Mobile phone two-dimension code is planar bar code technology in mobile phone
On application, have been widely used for asking beam at present, poster is registered, business card, direction board, the various occasions such as exploitation.If making
With two dimensional code when certain important events transmitting has the more demanding data of identity information, timeliness, need to calculate its encryption and decryption
Method optimizes.
Recognition of face is a kind of biological identification technology for carrying out identification based on facial feature information of people.Face with
Other biological characteristics (fingerprint, iris etc.) of human body are equally inherent, its uniqueness and are not easy the superperformance being replicated
Necessary premise is provided for identity identification, recognition of face has a characteristic that non-strong compared with other types of bio-identification
Property processed；It is untouchable；Concurrency.Face recognition products are widely used to medical treatment, the administration of justice, army, public security, electric power, government, boat
It, frontier inspection, factory, education, the fields such as finance and numerous enterprises and institutions.With the further mature and Social Agree of technology
Raising, face recognition technology is applied in more fields.
The encryption technologies such as MD5, which are widely used in, encrypts various information, current safety with higher, and in hand
It is also easy to realize on machine platform.
Alcohol sensor, for detecting whether human body takes in alcohol and intake alcohol how many degree.It can be used as traffic
Driver's wine-drinking how many detection instrument of drinking is detected when police enforces the law, to effectively reduce the generation of major traffic accidents；It can also be with
Alcohol content in other occasions detection characteristics of contaminated respiratory droplets gas, avoids the heavy losses of casualties and property, such as some
Forbid the enterprise being on duty after drinking in high-risk field.It can be used for judging whether driving when intoxicated.The common detection driven when intoxicated has two
Kind method: first is that the blood alcohol concentration of detection human body, one is detection expiration alcohol concentration.In theory, to judge be
No to drive when intoxicated, most accurate method should be the alcohol content checked in driver's blood.But illegal activities processing or
In person's highway communication routine inspection, scene to extract, blood is often unpractical, and the method for most simple possible is on-site test
Alcohol content in driver's expiration.
2DPCA algorithm is the improvement based on PCA (principal component analysis) method, and the method for directly utilizing two-dimensional projection is special
Two-dimensional matrix is based on when sign is extracted rather than one-dimensional vector.The covariance matrix calculated using 2DPCA is calculated with PCA
Covariance matrix compare, relative straightforward with it is convenient, calculation amount also greatly reduces, time-consuming reduce, extract feature it is more efficient.
In view of the above-mentioned problems, it is necessary to provide a kind of third party's automobile leasing management system and automobile based on recognition of face
Start authorization method.
Summary of the invention
The present invention is based on third party's automobile leasing management systems of recognition of face and automobile starting authorization method using two dimension
Code technology is combined with recognition of face and alcohol detection, for preventing car stealer from stealing automobile to automobile implementation preferably protection,
It prevents car borrowing people from lending others and prevents drunk driving.It introduces now using very extensive face recognition technology, and by that will add
Close algorithm, such as MD5 Encryption Algorithm are transplanted to intelligent mobile phone platform, encrypt to the information of transmission.
To achieve the goals above, it is as follows to implement the technical solution provided by the present invention:
The system comprises sequentially connected mobile module, third-party platform and onboard system,
The third-party platform is used for the different vehicle provided according to the demand of each user and each automobile rental corporation
Carry out matching recommendation；After user returns the car, automobile rental corporation checks whether vehicle is intact, and third-party platform can be rent
It gets in the account of rent-a-car company；User refers to car borrowing people, and automobile rental corporation provides information of hiring a car；
The mobile module places an order payment for car borrowing people's register account number；It is also used to add the information such as car borrowing people's account
It is close, and the information generated after encryption is generated into two dimensional code；
The onboard system includes: two dimensional code module, main control module, face recognition module, alcohol detection module and vehicle-mounted
Control module；Wherein:
The face recognition module acquires facial image feature, is sent into main control module for scanning face；
The Response Code scan module is for interpreting two-dimensional barcode information；
The alcohol detection module is used to measure the concentration of alcohol in gas；And it is surveyed according to the accurate data that sensor transmits
Amount driver drinks situation, generates decision instruction and is sent into main control module；
The main control module is used for decryption and authorization information, and the information after decryption is interpreted by specified protocol, makes and sentencing
Disconnected and operation；Facial image feature and inventory's facial image feature for being sent into according to face recognition module compare, and confirm vehicle
Owner identification, and generate discriminant information and be sent into vehicle-mounted control module；The main control module, which is also used to identify by the corners of the mouth, to be judged whether
Be car owner go forward side by side serve a round of liquor to the guests drive detection identification.
As a further improvement of the present invention, the mobile module places an order payment for car borrowing people's register account number；It is also used to
The information such as car borrowing people's account are encrypted, and the information generated after encryption is generated into two dimensional code；
As a further improvement of the present invention, the face recognition module is used to scan face, acquires facial image feature,
It is sent into main control module；
As a further improvement of the present invention, the two dimensional code module is for interpreting two-dimensional barcode information；
As a further improvement of the present invention, the main control module is used for decryption and authorization information, and the information after decryption is pressed
Specified protocol is interpreted, and is judged and is operated；Facial image feature and inventory for being sent into according to face recognition module
Facial image feature compares, and confirms owner identity, and generates discriminant information and be sent into vehicle-mounted control module；
As a further improvement of the present invention, the system also includes the vehicle-mounted control module being connected with main control module, institutes
Judgement information of the vehicle-mounted control module for sending according to main control module is stated, vehicle control instruction is generated.
As a further improvement of the present invention, the encryption in the mobile module be by improved md5 encryption algorithm into
Row encryption.
As a further improvement of the present invention, the information such as described car borrowing people's account include car borrowing people's identity, car borrowing people's account,
Timestamp, binding account password.
As a further improvement of the present invention, the alcohol sensor is used to measure the concentration of alcohol in gas；
As a further improvement of the present invention, the accurate data that the alcohol detection module is used to be transmitted according to sensor is surveyed
Amount driver drinks situation, generates decision instruction and is sent into main control module；
As a further improvement of the present invention, which is characterized in that the face recognition algorithms be improved two dimension it is main at
Analysis (2DPCA) algorithm.
Correspondingly, a kind of automobile starting authorization method based on recognition of face, which comprises
Step 2.1: if the registered account of car borrowing people, step 2.2 is directly executed, if it is not, then car borrowing people is flat in third party
Platform mobile phone app carries out register account number, fills in personal information, uploads identity card picture and driver's license photo, acquires facial image；
Step 2.2: verifying and borrow whether automobile-used family prepays vehicle violation guarantee fund, if so, thening follow the steps 2.3；
Step 2.3 car borrowing people selects the vehicle that oneself to be rented, and places an order, and improves personal information, updates facial image, and determination takes
It the vehicle time and returns the car the time, checks order, on-line payment；
Step 2.4: third-party platform according to order information, to automobile rental corporation ask for the vehicle system password and with
Machine number generates binding account password on this basis, binding account password and random number is sent on user mobile phone；
Step 2.5: user clicks " generate two dimensional code " on mobile phone order interface, thus the information such as car borrowing people's account by
It encrypts and generates two dimensional code；
Step 2.6: car borrowing people can add the personal information of other two driver on third-party platform mobile phone app
(identity card picture, driver's license photo etc.), acquires its facial image；
Step 2.7: camera in car is scanned two-dimensional barcode information, interprets two-dimensional barcode information, and judges that two dimensional code is believed
Whether breath is effective, if so, onboard system binds its account, the information such as face can be executed by transmission of network into onboard system
Step 2.8；If it is not, then interior voice broadcast two dimensional code is wrong, do not respond；
Step 2.8: interior voice broadcast informs that driver will carry out recognition of face, and quotes car borrowing people setting driver and do
Human face expression out, judge its face whether be car borrowing people license the face and human face expression that can directly drive vehicle people
It is whether correct, if so, step 2.9 is executed, if it is not, not responding；
Step 2.9: interior voice broadcast informs that driver will carry out alcohol detection, and driver is prompted to draw alcohol sensor
It blows three times to driver, and after requiring driver to deeply breathe against alcohol sensor, while face identification system is again
Driver is monitored, by the corners of the mouth feature extraction for opening one's mouth to blow into Database Systems.If it is detected that generation has without drinking behavior
Effect authorization enabled instruction；If it is not, voice broadcast prompt driver please don't drunk driving, vehicle can not start.
Further, the Encryption Algorithm in the mobile module is that improved md5 encryption algorithm is encrypted.
Further, improved md5 encryption algorithm are as follows: first by car borrowing people's identity information, car borrowing people's account, timestamp, binding
Account password progress sequence is upset, it is assumed that and random number n will be connected to the tail portion of remaining character string after n character interception before MD,
Then using the encryption of a MD5.
Further, the face recognition algorithms in the face recognition module are the two-dimensional principal component analysis 2DPCA improved
Algorithm: using the method for characteristic block, will there is the sample of similar features (facial expression, face angle, illuminance) to be divided into one
Then a matrix inhibits noise with histogram equalization sample, finally identify the whole minimum area that can represent main feature,
Feature extraction and subsequent identification are carried out to pretreated training sample set by 2DPCA algorithm.
Further, two-dimensional principal component analysis (2DPCA) the algorithm detailed process improved are as follows:
(4) partitioning pretreatment:
Due to the complexity in vehicle environmental, often makes the sample of facial image be unable to satisfy Gaussian Profile, lead to figure
Noise and redundancy as in cannot accurately be indicated with covariance and variance, caused it that can not obtain and adequately reflected training space
Proper subspace, to reduce the discrimination of 2DPCA algorithm.Due to the sample after piecemeal have similar features (facial expression,
Face's angle, intensity of illumination), tend to Gaussian Profile, helps to improve algorithm identification.For this defect, present patent application is mentioned
Improved method out takes the mode of piecemeal.The detailed process of partitioning pretreatment are as follows: by original standard exercise matrix A=
[a11,a12,...,aij]TIt is divided into multiple sub-block matrix As1,A2,...,Am, wherein A1,A2,...,AmIndicate have in training sample
Same facial expression, face's angle, the sample intersection of intensity of illumination；
(5) histogram equalization
Histogram equalization can extend the dynamic range of grey scale pixel value, improve contrast, can finally protrude sample
Feature.The process of histogram equalization can be g=EQ (f), wherein f is gray value of the original image at (x, y), and g is conversion
Gray value of the image afterwards at (x, y), the first step ask original image [f (x, y)]M×NHistogram, use hfIt indicates；Second step, by
hfThe intensity profile probability for seeking original image, is denoted as pf,Third step is counted and is calculated
Gray value of image distribution situation, is denoted as pa,Step 4: calculating histogram equalization
As a result, obtaining image pixel value g (i, j)；
(6) noise suppressed
The gray value of pixel is usually bigger than non-noise point grey scale pixel value or small at noise spot, can use some suitable ashes
Angle value replaces the gray value of noise spot pixel, and to reach ideal filter effect, the main thought of median filtering is, to entire figure
The gray value of picture is resequenced, and the noise spot of (small) that gray value is become larger suddenly is placed on most left (right side) side, at final research
In intermediate non-noise point data, to realize the effect for inhibiting noise；
(4) overall Minimum Area is identified
If sample XijIn to become clear with the boundary lines of grey parts be Bi(j), if sample XijEvery row first side from left to right
The collection of edge point coordinate is combined into { Li(j) }, if sample XijEvery row is combined into { R from the collection of right first marginal point coordinate of turning lefti(j)}。
If gathering { Li(j) } there is H (X inij) a element, the i.e. height of the image, gather { Li(j) } k-th of element in is image sample
This XijFirst marginal point of kth row；If gathering { Ri(j) } there is N (X inij) a element, the i.e. height of the image, gather { Ri
(j) } k-th of element in is image pattern XijThe last one marginal point coordinate of row k；
Thus, totality line of demarcation YD are as follows:
Overall leftmost edge point set { YL } are as follows:
Overall the right edge point set { YR } are as follows:
Wherein, c indicates the line number of sample total, and n indicates that the columns of sample total, N indicate sample total；
Therefore, overall Minimum Area may be expressed as: { (x, y) | x ∈ (YL, YR), y > YD }
Finally, using 2DPCA algorithm to pretreated training sample set { XijCarry out face characteristic extraction and identification.
The invention has the following beneficial effects:
Realize automobile starting authorization using face recognition technology, car borrowing people by authorization before using the vehicle for the first time only
Two dimensional code need to be used personal account and vehicle binding and stop the several seconds to recognition of face camera and make the expression of requirement, most
Automobile can be started by alcohol detection afterwards.Without the people of authorization, because there is no corresponding face information authorization in system, i.e.,
Make the key for taking the vehicle that can not also start vehicle, the antitheft purpose after reaching key loss, and the driver to drink without
Method starts automobile.
Another inventive point of the invention is that interior voice broadcast informs that driver will carry out alcohol detection, and prompt is driven
Alcohol sensor is pulled in face of driver by the person of sailing, and is blown several times after requiring driver to deeply breathe against alcohol sensor,
Face identification system monitors driver again simultaneously, by the corners of the mouth feature extraction for opening one's mouth to blow into Database Systems, it is contemplated that
Environment inside car is complicated, and the influence of shading value unevenness, the present invention improves the Encryption Algorithm in mobile module, while to face
Face recognition algorithms in identification module are improved, and the corners of the mouth feature extraction for opening one's mouth to blow is introduced, and improve drunk driving especially
It is the precision of indoor drunk driving judgement under complex environment.
Detailed description of the invention
Fig. 1 is total module diagram in the embodiment of the invention；
Fig. 2 is car owner's authorization message data frame format schematic diagram in the embodiment of the invention；
Fig. 3 is the interaction figure between mobile module and main control module in the embodiment of the invention；
Fig. 4 is car owner's mobile phone onboard system special-purpose software authorization interface schematic diagram in the embodiment of the invention；
Fig. 5 is the module diagram of main control module in the embodiment of the invention；
Specific embodiment
Hereinafter, the present invention will be described in detail with reference to various embodiments shown in the accompanying drawings.But these embodiments are not
The limitation present invention, structure that those skilled in the art are made according to these embodiments, method or change functionally
It changes and is included within the scope of protection of the present invention.
Join shown in Fig. 1, in a specific embodiment of the invention, automobile leasing management system and vapour based on recognition of face
Vehicle starts authorization method, and the system comprises user 10, automobile rental corporation 20, mobile module 30, third-party platform 40 and vehicles
Loading system 50, wherein onboard system includes: two dimensional code module 60, main control module 70, face recognition module 80, vehicle-mounted control mould
Block 90, alcohol detection module 100 and alcohol sensor 110.
Line module 10: referring to car borrowing people, and registrable to place an order, pick-up is returned the car, starting automobile etc..
Automobile rental corporation 20: for providing a user information of hiring a car etc. by third-party platform.
Mobile module 30: it places an order payment for car borrowing people's register account number；It is also used to the information such as car borrowing people's account carrying out MD5
Algorithm for encryption, and the information generated after encryption is generated into two dimensional code.
A third-party platform 40: for being carried out according to the demand of each car borrowing people different vehicle that each company provides of summing
With recommendation；After car borrowing people returns the car, company checks whether vehicle is intact (with by means of the state as Chinese herbaceous peony), and third party can be
Rent is got in the account of rent-a-car company.
Onboard system 50: for controlling entire onboard system comprising two dimensional code module 60, main control module 70, face are known
Other module 80, vehicle-mounted control module 90, alcohol detection module 100 and alcohol sensor 110.
Two dimensional code module 60: for scanning and interpreting two-dimensional barcode information and the authorization message after interpretation is sent into master control mould
Block.
Main control module 70: it is used for decryption and authorization information, the information after decryption is interpreted by specified protocol, is judged
And operation；Facial image feature and inventory's facial image feature for being sent into according to face recognition module compare, and confirm car owner
Identity, and generate discriminant information and be sent into vehicle-mounted control module.
Face recognition module 80: for scanning face, acquiring facial image feature and characteristic information being sent into main control module.
Vehicle-mounted control module 90: the judgement information for being sent into according to main control module generates vehicle control instruction.
Alcohol detection module 100: the accurate data measurement driver for being transmitted according to sensor drinks situation, and generation is sentenced
Severed finger, which enables, is sent into main control module；
Alcohol sensor 110: for measuring the concentration of alcohol in gas.
The information such as car borrowing people's account include car borrowing people's identity, car borrowing people's account, timestamp, binding account mouth in the present invention
It enables.Ginseng Fig. 2 show two dimensional code authorization message in present embodiment and defines, and data frame format is exemplified below:
(1) car borrowing people's identity information 64bit, is provided by car owner, and system will record in database；
(2) car borrowing people's account 64bit；
(3) timestamp 32bit indicates the generation time of authorization message, onboard system after authorized information, pass through by
Also before the deadline whether the value and current time of the field do comparison and judge authorization message；
(4) account password 16bit is bound；
The improved md5 encryption treatment process of the present invention:
First car borrowing people's identity information, car borrowing people's account, timestamp, binding account password progress sequence are upset, it is assumed that with
Machine number is n, the tail portion of remaining character string will be connected to after n character interception before MD, then using the encryption of a MD5:
(1) message is filled, so that its bit long is 448 under mould 512, wherein 64 bits reserved are in case (2) step
It uses.The message-length of authorization message is 176bit, fills 272.Filling mode is fixed: the 1st is 1, thereafter
Everybody is all 0.
(2) length of additional information, before 64 bits reserved with step (1) indicate that message is filled in a manner of small end
Length 176bit.If message is long to be greater than 264, then with 264For modulus.Small end mode refers to the least significant word by data
Save (byte) preferential sequential storage data.
(3) buffer area MD is initialized, using the buffer area of 128 bit longs to store intermediate result and final hash value,
Buffer area is represented by the register (A, B, C, D) of 4 32 bit longs, each register storing data in a manner of small end,
Initial value is taken as A=01234567, B=89ABCDEF, C=FEDCBA98, D=76543210 (with storage mode), is actually
67452301, EFCDAB89,98BADCFE, 10325476.
(4) compression function H is carried out to the authorization message of this 512 bit lengthMD5Processing, wherein have 4 wheel treatment processes again,
HMD54 wheel processing logical functions be respectively F, G, H, I.The input of every wheel is currently processed information block YqThe buffer area and
Current value A, B, C, D.Every wheel treatment process is also needed plus a quarter element in constant table T, respectively T [1..16], T
[17..32], T [33..48], T [49..64].Table T has 64 elements, and i-th of element T [i] is 232× abs's (sin (i))
Integer part, wherein sin is SIN function, and i is as unit of radian.Since (sin (i) is greater than 0 less than 1, so T [i] can to abs
It is indicated by the word of 32 bits.The defeated people CV that the output of 4th wheel is taken turns with the 1st againqIt is added, by CV when additionqRegard 4 32 bits as
Word, each word press mould 2 with the corresponding word of the 4th wheel output32It is added, the result of addition is compression function HMD5Output.
The treatment process of step (3) to step (5) may be summarized as follows:
CV0=IV；
CVq+1=CVq+RFI[Yq,RFH[Yq,RFG[Yq,RFF[Yq,CVq]]]]；
MD=CVL；
Wherein IV is the initial value for the buffer area ABCD that step (3) is taken, YqIt is the grouping of q-th of 512 bit longs of message,
L is message by step (1) and step (2) treated packet count, and L value is 1, CV hereqFor q for handling message
The link variable (output of preceding compression function a one by one) of defeated people, RE when groupingxFor the wheel letter for using basic logic function x
Number ,+it is the mould 2 for corresponding to word32Addition, MD are final cryptographic Hash.
(5) it is encrypted again according to random number:
The algorithm is MD*=MD5 (MD5 (string (n)+string (0, n)+n)+n)
By upsetting to original character string sequence, to the character string addition random number upset, repeatedly encrypt again,
The safety that can guarantee data, improves the safety of former algorithm, while also enhancing the anti-collision of password.Have in MD*
Random number, system password, timestamp, attacker want to crack MD*, achieve the purpose that start vehicle, extremely difficult.
In view of the unstable factor of environment in vehicle, improved two-dimensional principal component analysis (2DPCA) algorithm of the invention
It is as follows:
Innovatory algorithm of the invention use characteristic block method, will have similar features (facial expression, face angle,
Illuminance) sample be divided into a matrix, with histogram equalization sample, then inhibit noise, finally identify can represent it is main
The whole minimum area of feature carries out feature extraction and subsequent identification to pretreated training sample set by 2DPCA algorithm.
Specifically includes the following steps:
(1) partitioning pretreatment:
Due to the complexity in vehicle environmental, often makes the sample of facial image be unable to satisfy Gaussian Profile, lead to figure
Noise and redundancy as in cannot accurately be indicated with covariance and variance, caused it that can not obtain and adequately reflected training space
Proper subspace, to reduce the discrimination of 2DPCA algorithm.Due to the sample after piecemeal have similar features (facial expression,
Face's angle, intensity of illumination), tend to Gaussian Profile, helps to improve algorithm identification.For this defect, present patent application is mentioned
Improved method out takes the mode of piecemeal, improves the ability for detecting to drunk driving and carrying out corners of the mouth identification.Partitioning pretreatment it is specific
Process are as follows: by original standard exercise matrix A=[a11,a12,...,aij]TIt is divided into multiple sub-block matrix As1,A2,...,Am.Its
Middle A1,A2,...,AmIndicate that there is same facial expression, face's angle, the sample intersection of intensity of illumination in training sample.
(2) histogram equalization
Histogram equalization can extend the dynamic range of grey scale pixel value, improve contrast, can finally protrude sample
Feature.The process of histogram equalization can be g=EQ (f), wherein f is gray value of the original image at (x, y), and g is conversion
Gray value of the image afterwards at (x, y).The first step asks original image [f (x, y)]M×NHistogram, use hfIt indicates；Second step, by
hfThe intensity profile probability for seeking original image, is denoted as pf,Third step is counted and is calculated
Gray value of image distribution situation, is denoted as pa,Step 4: calculating histogram equalization
As a result, obtaining image pixel value g (i, j).
(3) noise suppressed
The gray value of pixel is usually bigger than non-noise point grey scale pixel value or small at noise spot, can use some suitable ashes
Angle value replaces the gray value of noise spot pixel, to reach ideal filter effect.The main thought of median filtering is, to entire figure
The gray value of picture is resequenced, and the noise spot of (small) that gray value is become larger suddenly is placed on most left (right side) side, at final research
In intermediate non-noise point data, to realize the effect for inhibiting noise.
(4) overall Minimum Area is identified
If sample XijIn to become clear with the boundary lines of grey parts be Bi(j), if sample XijEvery row first side from left to right
The collection of edge point coordinate is combined into { Li(j) }, if sample XijEvery row is combined into { R from the collection of right first marginal point coordinate of turning lefti(j)}。
If gathering { Li(j) } there is H (X inij) a element, the i.e. height of the image, gather { Li(j) } k-th of element in is image sample
This XijFirst marginal point of kth row；If gathering { Ri(j) } there is N (X inij) a element, the i.e. height of the image, gather { Ri
(j) } k-th of element in is image pattern XijThe last one marginal point coordinate of row k.
Thus, totality line of demarcation YD are as follows:
Overall leftmost edge point set { YL } are as follows:
Overall the right edge point set { YR } are as follows:
Wherein, c indicates the line number of sample total, and n indicates that the columns of sample total, N indicate sample total.
Therefore, overall Minimum Area may be expressed as: { (x, y) | x ∈ (YL, YR), y > YD }
Finally, using 2DPCA algorithm to pretreated training sample set { XijCarry out face characteristic extraction and identification.
Automobile starting authorization method in present implementation based on recognition of face includes:
Step 3.1: if the registered account of car borrowing people, step 3.2 is directly executed, if it is not, then car borrowing people is flat in third party
Platform mobile phone app carries out register account number, fills in personal information, uploads identity card picture and driver's license photo, acquires facial image；
Step 3.2: verifying and borrow whether automobile-used family prepays vehicle violation guarantee fund, if so, thening follow the steps 3.3；
Step 3.3 car borrowing people selects the vehicle that oneself to be rented, and places an order, and improves personal information, updates facial image, and determination takes
It the vehicle time and returns the car the time, checks order, on-line payment；
Step 3.4: third-party platform according to order information, to automobile rental corporation ask for the vehicle system password and with
Machine number generates binding account password on this basis, binding account password and random number is sent on user mobile phone；
Step 3.5: user clicks " generate two dimensional code " on mobile phone order interface, thus the information such as car borrowing people's account by
It encrypts and generates two dimensional code；
Step 3.6: car borrowing people can add the personal information of other two driver on third-party platform mobile phone app
(identity card picture, driver's license photo etc.), acquires its facial image；
Step 3.7: camera in car is scanned two-dimensional barcode information, interprets two-dimensional barcode information, and judges that two dimensional code is believed
Whether breath is effective, if so, onboard system binds its account, the information such as face can be executed by transmission of network into onboard system
Step 3.8；If it is not, then interior voice broadcast two dimensional code is wrong, do not respond；
Step 3.8: interior voice broadcast informs that driver will carry out recognition of face, and quotes car borrowing people setting driver and do
Human face expression out, judge its face whether be car borrowing people license the face and human face expression that can directly drive vehicle people
It is whether correct, if so, step 3.9 is executed, if it is not, not responding；
Step 3.9: interior voice broadcast informs that driver will carry out alcohol detection, and driver is prompted to draw alcohol sensor
It blows three times to driver, and after requiring driver to deeply breathe against alcohol sensor, while face identification system is again
Driver is monitored, by the corners of the mouth feature extraction for opening one's mouth to blow into Database Systems.If it is detected that generation has without drinking behavior
Effect authorization enabled instruction；If it is not, voice broadcast prompt driver please don't drunk driving, vehicle can not start.
This method specifically:
It picks up the car as shown in Figure 1, user first registers after placing an order, the two dimensional code and automobile generated with mobile phone is bound, then carries out people
Face identification can start automobile.
As shown in Fig. 2, the authorization message to be encrypted is followed successively by car borrowing people's identity, car borrowing people's account, timestamp, binding account
Password.
As shown in figure 3, car borrowing people needs that information md5 encryption is generated authorization message with mobile phone, then this information is generated two
Code is tieed up, is scanned for two dimensional code module, if information is correct, onboard system binds its account, and the information such as face can pass through net
Network is transmitted in onboard system main control module, and automobile can carry out recognition of face vehicle to car borrowing people.
As shown in figure 4, being equipped with the cooperation dedicated licensed software of onboard system in car borrowing people's mobile phone, clicks and " generate two dimension
Information is carried out md5 encryption by code ", mobile module first, regenerates two dimensional code；
As shown in figure 5, MD5 decryption is carried out to obtained information first after main control module receives authorization message, it is decrypted
Information afterwards is again by using authorization data frame format to be interpreted, then the value of each field is parsed, and judges Authorized operation
Whether effectively, this is generated if effectively and generates effective account binding instruction, and sends it to vehicle-mounted control module；Conversely, not
It responds.Judge whether recognition of face image feature information is effective, effectively then generates effectively authorization enabled instruction；Conversely, not doing
Response.
If someone has stolen the mobile phone of car owner, because it does not know the entry password of mobile phone car loading system special-purpose software, with regard to nothing
Method carries out Authorized operation.
It can be seen from embodiment of above compared with prior art, the present invention realizes automobile using face recognition technology
Starting authorization, the car borrowing people by authorization need to only use two dimensional code that personal account and the vehicle are bound before using the vehicle for the first time
And stop the several seconds to recognition of face camera and make the expression of requirement, automobile can be started finally by alcohol detection.Not
By the people of authorization, because not having corresponding face information authorization in system, vehicle can not be started taking the key of the vehicle
, the antitheft purpose after reaching key loss.If someone has stolen the mobile phone of car owner, because it does not know that mobile phone car loading system is dedicated
The login account password of software can not just carry out Authorized operation.
It should be appreciated that although this specification is described in terms of embodiments, but not each embodiment only includes one
A independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should will say
As a whole, the technical solution in each embodiment may also be suitably combined to form those skilled in the art can for bright book
With the other embodiments of understanding.
The series of detailed descriptions listed above only for feasible embodiment of the invention specifically
Protection scope bright, that they are not intended to limit the invention, it is all without departing from equivalent implementations made by technical spirit of the present invention
Or change should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of third party's automobile leasing management system based on recognition of face, which is characterized in that the system comprises successively connect
Mobile module, third-party platform and the onboard system connect,
The third-party platform is used to be carried out according to the different vehicle that the demand of each user and each automobile rental corporation provide
Matching is recommended；After user returns the car, automobile rental corporation checks whether vehicle is intact, and third-party platform can get to rent
In the account of rent-a-car company；User refers to car borrowing people, and automobile rental corporation provides information of hiring a car；
The mobile module places an order payment for car borrowing people's register account number；It is also used to encrypt the information such as car borrowing people's account,
And the information generated after encryption is generated into two dimensional code；
The onboard system includes: two dimensional code module, main control module, face recognition module, alcohol detection module and vehicle-mounted control
Module；Wherein:
The face recognition module acquires facial image feature, is sent into main control module for scanning face；
The Response Code scan module is for interpreting two-dimensional barcode information；
The alcohol detection module is used to measure the concentration of alcohol in gas；And the accurate data measurement transmitted according to sensor is driven
The person of sailing drinks situation, generates decision instruction and is sent into main control module；
The main control module be used for decryption and authorization information, the information after decryption is interpreted by specified protocol, judge and
Operation；Facial image feature and inventory's facial image feature for being sent into according to face recognition module compare, and confirm car owner's body
Part, and generate discriminant information and be sent into vehicle-mounted control module；The main control module is also used to identify judge whether it is vehicle by the corners of the mouth
Master, which goes forward side by side to serve a round of liquor to the guests in person, drives detection identification.
2. system according to claim 1, which is characterized in that it further include the vehicle-mounted control module being connected with main control module,
The vehicle-mounted control module is used for the judgement information sent according to main control module, generates vehicle control instruction.
3. system according to claim 1, which is characterized in that the information such as described car borrowing people's account include car borrowing people's identity,
Car borrowing people's account, timestamp, binding account password.
4. binding account password according to claim 3, which is characterized in that the binding account password is third-party platform
Mobile phone user is sent to, for binding car borrowing people's account and vehicle.
5. a kind of automobile starting authorization of third party's automobile leasing management system based on recognition of face as described in claim 1
Method, which is characterized in that the described method includes:
Step 1.1: if the registered account of car borrowing people, step 1.2 is directly executed, if it is not, then car borrowing people is in third-party platform hand
Machine app carries out register account number, fills in personal information, uploads identity card picture and driver's license photo, acquires facial image；
Step 1.2: verifying whether car borrowing people prepays vehicle violation guarantee fund, if so, thening follow the steps 1.3；
Step 1.3 car borrowing people selects the vehicle that oneself to be rented, and places an order, and improves personal information, updates facial image, when determining pick-up
Between and return the car the time, check order, on-line payment；
Step 1.4: third-party platform asks for the system password of the vehicle and random according to order information, to automobile rental corporation
Number generates binding account password on this basis, binding account password and random number is sent on user mobile phone；
Step 1.5: user clicks " generating two dimensional code " on the order interface in mobile module, thus the information such as car borrowing people's account
It has been encrypted and has generated two dimensional code；
Step 1.6: car borrowing people can add the personal information (identity of other two driver on third-party platform mobile phone app
License piece, driver's license photo etc.), acquire its facial image；
Step 1.7: camera in car is scanned two-dimensional barcode information, interprets two-dimensional barcode information, and judge that two-dimensional barcode information is
No effective, if so, onboard system binds its account, the information such as face can execute step by transmission of network into onboard system
1.8；If it is not, then interior voice broadcast two dimensional code is wrong, do not respond；
Step 1.8: interior voice broadcast informs that driver will carry out recognition of face, and quotes car borrowing people and be arranged what driver made
Human face expression, judge its face whether be car borrowing people license the face that can directly drive vehicle people and human face expression whether
Correctly, if so, step 1.9 is executed, if it is not, not responding；
Step 1.9: interior voice broadcast informs that driver will carry out alcohol detection, prompts driver to be pulled to alcohol sensor and drives
In face of the person of sailing, and blow several times after requiring driver to deeply breathe against alcohol sensor, while face identification system is supervised again
Driver is controlled, by the corners of the mouth feature extraction for opening one's mouth to blow into Database Systems, if it is detected that generating effective without drinking behavior
Authorize enabled instruction；If it is not, voice broadcast prompt driver please don't drunk driving, vehicle can not start.
6. automobile starting authorization method as claimed in claim 5, which is characterized in that the Encryption Algorithm in the mobile module is
Improved md5 encryption algorithm is encrypted.
7. automobile starting authorization method as claimed in claim 6, which is characterized in that improved md5 encryption algorithm are as follows: will first borrow
Vehicle people identity information, car borrowing people's account, timestamp, binding account password progress sequence are upset, it is assumed that random number n, by n before MD
The tail portion of remaining character string is connected to after a character interception, then using the encryption of a MD5.
8. automobile starting authorization method as claimed in claim 5, which is characterized in that the face in the face recognition module is known
Other algorithm is the two-dimensional principal component analysis 2DPCA algorithm improved: using the method for characteristic block, will have similar features (face
Portion's expression, face angle, illuminance) sample be divided into a matrix, with histogram equalization sample, then inhibit noise, finally
It identifies the whole minimum area that can represent main feature, pretreated training sample set is carried out by 2DPCA algorithm special
Sign is extracted and subsequent identification.
9. automobile starting authorization method as claimed in claim 8, which is characterized in that the two-dimensional principal component analysis improved
(2DPCA) algorithm detailed process are as follows:
(1) partitioning pretreatment:
The detailed process of partitioning pretreatment are as follows: by original standard exercise matrix A=[a11,a12,...,aij]TIt is divided into multiple sub-blocks
Matrix A1,A2,...,Am, wherein A1,A2,...,AmIndicate have same facial expression, face's angle, illumination strong in training sample
The sample intersection of degree；
(2) histogram equalization
Histogram equalization can extend the dynamic range of grey scale pixel value, improve contrast, can finally protrude sample characteristics；
The process of histogram equalization can be g=EQ (f), wherein f is gray value of the original image at (x, y), and g is after converting
Gray value of the image at (x, y), the first step ask original image [f (x, y)]M×NHistogram, use hfIt indicates；Second step, by hfIt asks
The intensity profile probability of original image, is denoted as pf,Third step counts and calculates image
Grey value profile situation, is denoted as pa,Step 4: calculate histogram equalization as a result,
Obtain image pixel value g (i, j)；
(3) noise suppressed
(4) overall Minimum Area is identified
If sample XijIn to become clear with the boundary lines of grey parts be Bi(j), if sample XijEvery row first marginal point from left to right
The collection of coordinate is combined into { Li(j) }, if sample XijEvery row is combined into { R from the collection of right first marginal point coordinate of turning lefti(j) }, if collection
Close { Li(j) } there is H (X inij) a element, the i.e. height of the image, gather { Li(j) } k-th of element in is image pattern Xij
First marginal point of row k；If gathering { Ri(j) } there is N (X inij) a element, the i.e. height of the image, gather { Ri(j) } in
K-th of element be image pattern XijThe last one marginal point coordinate of row k；
Thus, totality line of demarcation YD are as follows:
Overall leftmost edge point set { YL } are as follows:
Overall the right edge point set { YR } are as follows:
Wherein, c indicates the line number of sample total, and n indicates that the columns of sample total, N indicate sample total；
Therefore, overall Minimum Area may be expressed as: { (x, y) x ∈ (YL, YR), y > YD }
Finally, using 2DPCA algorithm to pretreated training sample set { XijCarry out face characteristic extraction and identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910417530.9A CN110148262A (en) | 2019-05-20 | 2019-05-20 | A kind of third party's automobile leasing management system and automobile starting authorization method based on recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910417530.9A CN110148262A (en) | 2019-05-20 | 2019-05-20 | A kind of third party's automobile leasing management system and automobile starting authorization method based on recognition of face |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110148262A true CN110148262A (en) | 2019-08-20 |
Family
ID=67591872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910417530.9A Pending CN110148262A (en) | 2019-05-20 | 2019-05-20 | A kind of third party's automobile leasing management system and automobile starting authorization method based on recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110148262A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826434A (en) * | 2019-10-23 | 2020-02-21 | 上海能塔智能科技有限公司 | Face recognition verification method and device, vehicle-mounted equipment and storage medium |
| CN110995654A (en) * | 2019-11-05 | 2020-04-10 | 合肥优尔电子科技有限公司 | Remote terminal temporary authorization method, device and system based on dynamic two-dimensional code |
| CN111127767A (en) * | 2019-12-19 | 2020-05-08 | 广州赛特智能科技有限公司 | Control system, method, equipment and medium for sharing automobile |
| CN112053505A (en) * | 2020-08-21 | 2020-12-08 | 杭州小电科技股份有限公司 | Mobile power supply leasing method, device and system, electronic device and storage medium |
| CN114492687A (en) * | 2022-01-06 | 2022-05-13 | 深圳市锐明技术股份有限公司 | Pre-post detection method and device, terminal equipment and computer readable storage medium |
| CN114655160A (en) * | 2021-01-28 | 2022-06-24 | 北京新能源汽车股份有限公司 | Method and device for controlling vehicle starting |
| CN114919532A (en) * | 2022-04-29 | 2022-08-19 | 东风汽车集团股份有限公司 | Vehicle control method and system based on face recognition |
| CN116977037A (en) * | 2023-07-06 | 2023-10-31 | 重庆蓝鲸智联科技有限公司 | Method for lending based on personal vehicle |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130047667A (en) * | 2011-10-31 | 2013-05-08 | 제너럴 일렉트릭 캄파니 | Systems and methods for use in communicating with a charging station |
| CN103241215A (en) * | 2013-04-28 | 2013-08-14 | 江苏大学 | QR-code-based (quick response code-based) vehicle operation authorization and burglary protection system and method |
| CN104184589A (en) * | 2014-08-26 | 2014-12-03 | 重庆邮电大学 | Identity authentication method, terminal device and system |
| CN106094618A (en) * | 2016-06-20 | 2016-11-09 | 奇瑞汽车股份有限公司 | A kind of electric automobile starts authoring system and starts authorization method |
| US20160325755A1 (en) * | 2012-03-14 | 2016-11-10 | Autoconnect Holdings Llc | Facial recognition database created from social networking sites |
| CN107944780A (en) * | 2018-01-17 | 2018-04-20 | 上海钛捷信息科技有限公司 | A kind of vehicle scheduling platform and automobile leasing method based on automobile resources dynamic dispatching with distribution |
| CN108263336A (en) * | 2018-01-29 | 2018-07-10 | 程伟 | Communal automobile dangerous driving Intelligent preventive control system and method |
| CN108297823A (en) * | 2018-01-27 | 2018-07-20 | 厦门市金福冠包装用品有限公司 | The intelligence control system of automobile |
| CN109766870A (en) * | 2019-01-26 | 2019-05-17 | 南京云计趟信息技术有限公司 | A kind of unattended alcohol detection method based on action recognition |
-
2019
- 2019-05-20 CN CN201910417530.9A patent/CN110148262A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130047667A (en) * | 2011-10-31 | 2013-05-08 | 제너럴 일렉트릭 캄파니 | Systems and methods for use in communicating with a charging station |
| US20160325755A1 (en) * | 2012-03-14 | 2016-11-10 | Autoconnect Holdings Llc | Facial recognition database created from social networking sites |
| CN103241215A (en) * | 2013-04-28 | 2013-08-14 | 江苏大学 | QR-code-based (quick response code-based) vehicle operation authorization and burglary protection system and method |
| CN104184589A (en) * | 2014-08-26 | 2014-12-03 | 重庆邮电大学 | Identity authentication method, terminal device and system |
| CN106094618A (en) * | 2016-06-20 | 2016-11-09 | 奇瑞汽车股份有限公司 | A kind of electric automobile starts authoring system and starts authorization method |
| CN107944780A (en) * | 2018-01-17 | 2018-04-20 | 上海钛捷信息科技有限公司 | A kind of vehicle scheduling platform and automobile leasing method based on automobile resources dynamic dispatching with distribution |
| CN108297823A (en) * | 2018-01-27 | 2018-07-20 | 厦门市金福冠包装用品有限公司 | The intelligence control system of automobile |
| CN108263336A (en) * | 2018-01-29 | 2018-07-10 | 程伟 | Communal automobile dangerous driving Intelligent preventive control system and method |
| CN109766870A (en) * | 2019-01-26 | 2019-05-17 | 南京云计趟信息技术有限公司 | A kind of unattended alcohol detection method based on action recognition |
Non-Patent Citations (4)
| Title |
|---|
| 任杰麟: "MD5加密算法的安全性分析与改进", 《农业图书情报学刊》 * |
| 周松锋等: "改进的PCA人脸识别算法研究", 《软件导刊》 * |
| 张杨等: "基于改进PCA算法的人脸识别", 《软件导刊》 * |
| 王波涛等: "基于FPGA的MD5算法设计与实现", 《通信技术》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826434A (en) * | 2019-10-23 | 2020-02-21 | 上海能塔智能科技有限公司 | Face recognition verification method and device, vehicle-mounted equipment and storage medium |
| CN110995654A (en) * | 2019-11-05 | 2020-04-10 | 合肥优尔电子科技有限公司 | Remote terminal temporary authorization method, device and system based on dynamic two-dimensional code |
| CN110995654B (en) * | 2019-11-05 | 2022-11-18 | 合肥优尔电子科技有限公司 | Terminal temporary authorization method, device and system based on dynamic two-dimensional code |
| CN111127767A (en) * | 2019-12-19 | 2020-05-08 | 广州赛特智能科技有限公司 | Control system, method, equipment and medium for sharing automobile |
| CN112053505A (en) * | 2020-08-21 | 2020-12-08 | 杭州小电科技股份有限公司 | Mobile power supply leasing method, device and system, electronic device and storage medium |
| CN114655160A (en) * | 2021-01-28 | 2022-06-24 | 北京新能源汽车股份有限公司 | Method and device for controlling vehicle starting |
| CN114492687A (en) * | 2022-01-06 | 2022-05-13 | 深圳市锐明技术股份有限公司 | Pre-post detection method and device, terminal equipment and computer readable storage medium |
| CN114919532A (en) * | 2022-04-29 | 2022-08-19 | 东风汽车集团股份有限公司 | Vehicle control method and system based on face recognition |
| CN114919532B (en) * | 2022-04-29 | 2024-04-19 | 东风汽车集团股份有限公司 | Vehicle control method and system based on face recognition |
| CN116977037A (en) * | 2023-07-06 | 2023-10-31 | 重庆蓝鲸智联科技有限公司 | Method for lending based on personal vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148262A (en) | A kind of third party's automobile leasing management system and automobile starting authorization method based on recognition of face | |
| CN103241215B (en) | Automobile based on Quick Response Code uses mandate, burglary-resisting system and method | |
| CN107332659B (en) | Identity authentication method, storage medium and system based on biological characteristics | |
| US7519558B2 (en) | Biometrically enabled private secure information repository | |
| US20030023882A1 (en) | Biometric characteristic security system | |
| JP2009543176A (en) | Traceless biometric identification system and method | |
| CN101561873B (en) | Multimode authentication equipment with functions of iris recognition and USB Key | |
| US20040006699A1 (en) | Secure token access distributed database system | |
| CN105261105A (en) | Safety access control method | |
| KR20210101313A (en) | Face recognition method, neural network training method, apparatus and electronic device | |
| AU2010282394A1 (en) | An intelligent peripheral device and system for the authentication and verification of individuals and/ or documents through a secure multifunctional authentication service with data storage capability | |
| CN106971159A (en) | A kind of image definition recognition methods, identity identifying method and device | |
| CN103699995A (en) | Payment authentication method based on fingerprints and finger veins | |
| US7757942B1 (en) | Biometric charge card verification system and associated method | |
| CN111831995A (en) | Trusted identity authentication method and system based on eID and human body biological information | |
| CN112905965A (en) | Financial big data processing system based on block chain | |
| CN110009780A (en) | A kind of car door unlocking method, server and storage medium based on car networking | |
| CN113111330A (en) | Enterprise legal identity authentication management method and system based on enterprise chain code | |
| US8316050B2 (en) | Identification and authorization system | |
| Ma et al. | Mobidiv: A privacy-aware real-time driver identity verification on mobile phone | |
| CN115393997A (en) | Automobile electronic unlocking method and device based on multi-dimensional data identification and electronic equipment | |
| CN106203166A (en) | A kind of auto navigation information data sharing method | |
| Faisal et al. | Autonomous car system using facial recognition and geo location services | |
| Chang et al. | [Retracted] Application of Face Recognition in E‐commerce Security Authentication in the Era of Big Data | |
| US20230155836A1 (en) | Secure serverless multi-factor authentication |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190820 |
|
| RJ01 | Rejection of invention patent application after publication |