CN107800996A - Road vehicles traveling monitoring system based on Internet of Things - Google Patents
Road vehicles traveling monitoring system based on Internet of Things Download PDFInfo
- Publication number
- CN107800996A CN107800996A CN201610778862.6A CN201610778862A CN107800996A CN 107800996 A CN107800996 A CN 107800996A CN 201610778862 A CN201610778862 A CN 201610778862A CN 107800996 A CN107800996 A CN 107800996A
- Authority
- CN
- China
- Prior art keywords
- equipment
- pixel
- image
- binaryzation
- positive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of road vehicles based on Internet of Things to travel monitoring system, including vehicle control apparatus, AVR32 chips, high-definition camera and image processing equipment, high-definition camera, it is arranged on inside road vehicles, for being taken pictures to driver to obtain high definition face image, image processing equipment is used to carry out image procossing to high definition face image, AVR32 chips are connected with vehicle control apparatus and image processing equipment respectively, and the control model to vehicle control apparatus is determined for the output based on image processing equipment.By means of the invention it is possible to ensure the legal driving of authorized user's road pavement vehicle.
Description
Technical field
The present invention relates to field of vehicle control, more particularly to a kind of road vehicles traveling monitoring system based on Internet of Things.
Background technology
Vehicle is " car " and the general name of the unit " " of car.Car, refer to the vehicles that land wheel rotates;,
Metering method from ancient times to car.Car at that time is usually two wheels, therefore Che Yicheng claims one or two, just writes later
.As can be seen here, the literal sense of vehicle refers to do not have dynamic car in itself, is carriage with Malaysia traction, employment is people to draw or push away
Power car.With the development of science and technology, have again with steam engine automobile for drawing etc..
Although the species of vehicle is more, construction is similar.This is the contribution of standardization, and large-scale production stream
The needs of waterline.With the developing of society, the progress of science and technology and the change of demand, the profile of rolling stock begun with change,
Especially passenger car is no longer whole-colored familiar faces.But their essential structure does not have great change, simply has
The parts of body have more scientific advanced structure design.In general, the essential structure of vehicle is by car body, body frame, traveling
Portion, coupler and draft gear and the most of composition of brake apparatus five.
In the prior art, the road vehicles of the road vehicles of traditional energy and the electronic energy turn into family expenses or public main flow
Vehicle, generally, the personnel that road vehicles are all recognized by car owner or car owner drive, but criminal's hijacking vehicle also occurs
Situation occurs, therefore, it is desirable to which road vehicles differentiate to criminal in itself, and make the action that refusal continues traveling, so
The criminal offence of criminal can be contained, avoid traffic accident generation, protects personal safety and the economic interests of car owner.
However, in the prior art and in the absence of such authentication scheme, therefore a kind of, it is necessary to new road vehicles monitoring side
Case, authentication scheme can be introduced unauthorized person is effectively differentiated.
The content of the invention
In order to solve the above problems, the invention provides a kind of road vehicles based on Internet of Things to travel monitoring system, changes
Road vehicles traveling monitoring system in the prior art is made, human face detection tech is introduced and introduces technology of Internet of things road pavement vehicle
Driver carries out identity discriminating, and is reacted in time when finding unauthorized user, is automatically stopped traveling behavior.
According to an aspect of the present invention, there is provided a kind of road vehicles traveling monitoring system based on Internet of Things, the system
System includes vehicle control apparatus, AVR32 chips, high-definition camera and image processing equipment, high-definition camera, is arranged on road surface car
Inside, for being taken pictures to driver to obtain high definition face image, image processing equipment is used for high definition face image
Image procossing is carried out, AVR32 chips are connected with vehicle control apparatus and image processing equipment respectively, for being set based on image procossing
Standby output determines the control model to vehicle control apparatus.
More specifically, in the road vehicles traveling monitoring system based on Internet of Things, including:Vehicle control apparatus,
Road pavement vehicle is controlled, for when receiving validated user signal, safeguarding that driver's road pavement vehicle continues to drive,
It is additionally operable to when receiving disabled user's signal, road vehicles pulling over observing is controlled according to surface conditions;AVR32 chips, respectively
More sub- with characteristic vector equipment and vehicle control apparatus are connected, for when receiving recognition of face pass signal, sending conjunction
Method subscriber signal, it is additionally operable to receiving recognition of face failure signal, sends disabled user's signal;High-definition camera, it is arranged on
Inside road vehicles, for being taken pictures to driver to obtain high definition face image;Intensity compensation devices, with high-definition camera
Connection, for receiving high definition face image, the gray value based on each pixel in high definition face image determines high definition face image
Mean flow rate, and by the mean flow rate of high definition face image compared with predetermined luminance, when being averaged for high definition face image
Brightness is more than or equal to predetermined luminance, and luminance-reduction adjustment is carried out to high definition face image to obtain brightness adjustment image, works as high definition
The mean flow rate of face image is less than predetermined luminance, and luminance raising adjustment is carried out to high definition face image to obtain brightness adjustment figure
Picture;Gaussian smoothing equipment, it is connected with intensity compensation devices to receive brightness adjustment image, carrying out Gauss to brightness adjustment image puts down
It is sliding to handle to obtain smoothed image;Gray processing processing equipment, it is connected with Gaussian smoothing equipment to receive smoothed image, and to smooth
Image performs gray processing processing to obtain gray level image;Histogram equalization equipment, it is connected with gray processing processing equipment to receive
Gray level image, and histogram equalization processing is performed to gray level image to obtain equilibrium figures picture;Feature extracting device, respectively with
Histogram equalization equipment unpacks equipment with IP and connected, and the equilibrium figures picture received is handled;Feature extracting device includes ripple
Dynamic threshold value selects sub- equipment, the sub- equipment of processes pixel, the sub- equipment of matrix-split, the decimal system to change sub- equipment, characteristic vector acquisition
The sub- more sub- equipment of equipment and characteristic vector;Fluctuation threshold selects sub- equipment to be connected with histogram equalization equipment, for calculating
The complexity of weighing apparatus image, the complexity selection fluctuation threshold size based on equilibrium figures picture, the complexity of equilibrium figures picture is higher, selection
Fluctuation threshold it is bigger, fluctuation threshold is positive number;The sub- equipment of processes pixel selects sub- equipment and histogram with fluctuation threshold respectively
Balancing equipment is connected, and for receiving equilibrium figures picture, following locate is performed as object pixel for each pixel of equilibrium figures picture
Reason:The pixel centered on object pixel, the object pixel matrix of 3 × 3 sizes is obtained in equilibrium figures picture, by object pixel matrix
Interior each pixel in addition to object pixel as reference pixel compared with object pixel, to obtain binaryzation square
Battle array, binaryzation matrix is 3 × 3 sizes, and binaryzation matrix is made up of 8 binaryzation pixels, and reference pixel is more than or equal to subject image
Element and fluctuation threshold sum, then the pixel value of binaryzation pixel corresponding to reference pixel is 1, and reference pixel subtracts less than object pixel
The difference gone after fluctuation threshold, then the pixel value of binaryzation pixel corresponding to reference pixel is ﹣ 1, the reference pixel of other values
The pixel value of corresponding binaryzation pixel is 0;The sub- equipment of matrix-split is connected with the sub- equipment of processes pixel, for each is right
Binaryzation matrix conversion is into a positive binaryzation matrix and a negative binaryzation matrix as corresponding to pixel, positive binaryzation matrix by
8 binaryzation pixel values composition, negative binaryzation matrix are also made up of 8 binaryzation pixel values, positive binaryzation matrix each
Binaryzation pixel value subtracts the binaryzation pixel value of negative binaryzation matrix relevant position, and can to obtain corresponding binaryzation matrix corresponding
The pixel value of the binaryzation pixel of position;The decimal system is changed sub- equipment and is connected with the sub- equipment of matrix-split, for each is right
All binaryzation pixel values of positive binaryzation matrix as corresponding to pixel press its position in positive binaryzation matrix with first left back
Right first up and then down order again forms a binary number and changed into as the positive binary number of target, then by the positive binary number of target
Decimal number is as the positive decimal number of target, to be additionally operable to that all the two of binaryzation matrix will be born corresponding to each object pixel
Value pixel value forms a binary system by its position in negative binaryzation matrix with first left and then right first up and then down order again
Number is used as target negative binary number, then target negative binary number is changed into decimal number to bear decimal number as target;It is special
Sign vector, which obtains sub- equipment, to be changed sub- equipment with histogram equalization equipment and the decimal system respectively and be connected, for will be in equilibrium figures picture often
The pixel value of one object pixel is substituted for positive goal decimal number corresponding to the object pixel and according to object pixel in equilibrium
Positive goal decimal number corresponding to all object pixels is formed positive one-dimensional characteristic vector by the position in image, special as positive goal
Sign vector output, it is additionally operable to equilibrium figures the pixel value of each object pixel as in and is substituted for bear mesh corresponding to the object pixel
Mark decimal number and target decimal number will be born corresponding to all object pixels according to position of the object pixel in equilibrium figures as in
Negative one dimensional feature vector is formed, is exported as negative target feature vector;The more sub- equipment of characteristic vector obtains with characteristic vector respectively
Take sub- equipment and IP to unpack equipment connect, for by the characteristic vector progress positive with each benchmark respectively of positive goal characteristic vector
Match somebody with somebody, negative target feature vector is matched with each benchmark negative feature vector respectively, all the match is successful and matches for the two
The authorized user's title phase corresponding with the benchmark negative feature vector matched of authorized user's title corresponding to the positive characteristic vector of benchmark
Meanwhile recognition of face pass signal and the corresponding authorized user's title of the positive characteristic vector of the benchmark with matching then are exported, it is no
Recognition of face failure signal will then be exported;IP unpacks equipment, for being connected with long-range data server network, is connect by network
The IP packets at data server are received, and IP packets are unpacked to obtain 6LowPAN packets;Wherein, IP data
Bag is that 6LowPAN packets are carried out to beat after IP bags the packet obtained, and the load in 6LowPAN packets includes data clothes
The positive characteristic vector of each benchmark and each benchmark negative feature at business device is vectorial, and the head in 6LowPAN packets is compression number
According to the head in 6LowPAN packets after decompression is used to parse the load in 6LowPAN packets;Wherein, it is each
The individual positive characteristic vector of benchmark is that corresponding authorized user's benchmark face-image is carried out and feature extracting device same operation in advance
Positive characteristic vector pickup and the vector obtained, each benchmark negative feature vector are pre- to corresponding authorized user's benchmark face-image
First carry out the vector for extracting and obtaining with the negative feature of feature extracting device same operation vector;Edge sensing equipment, solved with IP
Bag equipment is connected, and the 6LowPAN packets of equipment output are unpacked for receiving IP, obtains the 6LowPAN for being rendered as compressed data
The head of packet, the heads of 6LowPAN packets is decompressed with the head in the 6LowPAN packets after being decompressed;
6LowPAN unpacks equipment, is connected with edge sensing equipment, for receiving 6LowPAN packets to obtain in 6LowPAN packets
Load, and the load in 6LowPAN packets is parsed based on the head in the 6LowPAN packets after decompression, with
Obtain the positive characteristic vector of each benchmark and each benchmark negative feature vector;Wherein, alternatively, replaced using wavelet filtering equipment high
This smoothing arrangement, wavelet filtering equipment are connected to receive brightness adjustment image with intensity compensation devices, brightness adjustment image are entered
Row wavelet filtering is handled to obtain smoothed image.
More specifically, in the road vehicles traveling monitoring system based on Internet of Things:High-definition camera also includes dodging
Light lamp controller and flash lamp.
More specifically, in the road vehicles traveling monitoring system based on Internet of Things:High-definition camera also includes bright
Sensor is spent, for detecting real time environment brightness.
More specifically, in the road vehicles traveling monitoring system based on Internet of Things:Photoflash controller is based on real
When ambient brightness control flash lamp opening and closing.
More specifically, in the road vehicles traveling monitoring system based on Internet of Things:Photoflash controller is based on real
When ambient brightness control flash lamp opening and closing include:When real time environment brightness is more than predetermined luminance threshold value, flash lamp is closed.
More specifically, in the road vehicles traveling monitoring system based on Internet of Things:Photoflash controller is based on real
When ambient brightness control flash lamp opening and closing include:When real time environment brightness is less than or equal to predetermined luminance threshold value, flash of light is opened
Lamp and according to the flash luminance of real time environment brightness adjustment flash lamp, real time environment brightness is lower, and the flash luminance of flash lamp is got over
It is high.
Brief description of the drawings
Embodiment of the present invention is described below with reference to accompanying drawing, wherein:
Fig. 1 is the structure side of the traveling monitoring system of the road vehicles based on Internet of Things according to embodiment of the present invention
Block diagram.
Reference:1 vehicle control apparatus;2AVR32 chips;3 high-definition cameras;4 image processing equipments
Embodiment
The embodiment of the traveling monitoring system of the road vehicles based on Internet of Things of the present invention is entered below with reference to accompanying drawings
Row describes in detail.
Currently, road vehicles traveling monitoring system lacks the safe access control equipment differentiated to driver identity,
Cause the security performance of road vehicles not high, it is easy to carry out criminal offence to criminal's hijacking vehicle and bring convenience, so as to
Infringement is produced in personal safety and economic interests to car owner.
In order to overcome above-mentioned deficiency, the present invention has built a kind of road vehicles traveling monitoring system based on Internet of Things, profit
Monitoring system is travelled with existing road vehicles, it is transformed to increase face recognition device and network communication equipment, it is complete
The accurate discriminating of paired road vehicles driver identity.
Fig. 1 is the structure side of the traveling monitoring system of the road vehicles based on Internet of Things according to embodiment of the present invention
Block diagram, the system include vehicle control apparatus, AVR32 chips, high-definition camera and image processing equipment, high-definition camera,
It is arranged on inside road vehicles, for being taken pictures to driver to obtain high definition face image, image processing equipment is used for pair
High definition face image carries out image procossing, and AVR32 chips are connected with vehicle control apparatus and image processing equipment respectively, for base
The control model to vehicle control apparatus is determined in the output of image processing equipment.
Then, continue to enter traveling one to the concrete structure of the traveling monitoring system of the road vehicles based on Internet of Things of the present invention
The explanation of step.
The system includes:Vehicle control apparatus, road pavement vehicle are controlled, for receiving validated user signal
When, safeguard that driver's road pavement vehicle continues to drive, and is additionally operable to when receiving disabled user's signal, according to surface conditions control
Road vehicles pulling over observing processed.
The system includes:AVR32 chips, respectively more sub- with characteristic vector equipment and vehicle control apparatus be connected, use
When recognition of face pass signal is being received, validated user signal is sent, is additionally operable to receiving recognition of face failure signal,
Send disabled user's signal;High-definition camera, it is arranged on inside road vehicles, for being taken pictures driver to obtain high definition
Face image.
The system includes:Intensity compensation devices, it is connected with high-definition camera, for receiving high definition face image, is based on
The gray value of each pixel determines the mean flow rate of high definition face image, and putting down high definition face image in high definition face image
Equal brightness is compared with predetermined luminance, when the mean flow rate of high definition face image is more than or equal to predetermined luminance, to high definition face
Image carries out luminance-reduction adjustment to obtain brightness adjustment image, when the mean flow rate of high definition face image is less than predetermined luminance,
Luminance raising adjustment is carried out to high definition face image to obtain brightness adjustment image.
The system includes:Gaussian smoothing equipment, it is connected with intensity compensation devices to receive brightness adjustment image, to brightness
Adjustment image carries out Gaussian smoothing to obtain smoothed image;Gray processing processing equipment, it is connected with Gaussian smoothing equipment to connect
Smoothed image is received, and gray processing processing is performed to smoothed image to obtain gray level image.
The system includes:Histogram equalization equipment, it is connected with gray processing processing equipment to receive gray level image, and it is right
Gray level image performs histogram equalization processing to obtain equilibrium figures picture.
The system includes:Feature extracting device, unpack equipment with histogram equalization equipment and IP respectively and be connected, to receiving
To equilibrium figures picture handled;Feature extracting device includes fluctuation threshold and selects sub- equipment, the sub- equipment of processes pixel, matrix to tear open
Molecular Devices, the decimal system change sub- equipment, characteristic vector obtains sub- equipment and the more sub- equipment of characteristic vector;Fluctuation threshold selects
Sub- equipment is connected with histogram equalization equipment, for calculating the complexity of equilibrium figures picture, the complexity selection based on equilibrium figures picture
Fluctuation threshold size, the complexity of equilibrium figures picture is higher, and the fluctuation threshold of selection is bigger, and fluctuation threshold is positive number;Processes pixel
Sub- equipment selects sub- equipment and histogram equalization equipment to be connected with fluctuation threshold respectively, for receiving equilibrium figures picture, for equilibrium
Each pixel of image performs following handle as object pixel:The pixel centered on object pixel, obtained in equilibrium figures picture
The object pixel matrix of 3 × 3 sizes is taken, using each pixel in object pixel matrix in addition to object pixel as reference
Pixel is compared with object pixel, and to obtain binaryzation matrix, binaryzation matrix is 3 × 3 sizes, and binaryzation matrix is by 8
Binaryzation pixel forms, and reference pixel is more than or equal to object pixel and fluctuation threshold sum, then binaryzation corresponding to reference pixel
The pixel value of pixel is 1, and reference pixel subtracts the difference after fluctuation threshold less than object pixel, then two-value corresponding to reference pixel
The pixel value for changing pixel is ﹣ 1, and the pixel value of binaryzation pixel corresponding to the reference pixel of other values is 0;Matrix-split is set
It is standby to be connected with the sub- equipment of processes pixel, for by binaryzation matrix conversion corresponding to each object pixel into a positive binaryzation
Matrix and a negative binaryzation matrix, positive binaryzation matrix are made up of 8 binaryzation pixel values, bear binaryzation matrix also by 8
Binaryzation pixel value forms, and each binaryzation pixel value of positive binaryzation matrix subtracts the two of negative binaryzation matrix relevant position
Value pixel value can obtain the pixel value of the binaryzation pixel of corresponding binaryzation matrix relevant position;The decimal system changes sub- equipment
It is connected with the sub- equipment of matrix-split, for by all binaryzation pixel values of positive binaryzation matrix corresponding to each object pixel
One binary number is formed using first left and then right first up and then down order again by its position in positive binaryzation matrix and is used as target
Positive binary number, then the positive binary number of target is changed into decimal number so that as the positive decimal number of target, being additionally operable to will be each
All binaryzation pixel values that binaryzation matrix is born corresponding to individual object pixel press its position in negative binaryzation matrix with elder generation
Left back right first up and then down order again forms a binary number as target negative binary number, then by target negative binary number turn
Decimal number is melted into bear decimal number as target;Characteristic vector obtains sub- equipment and entered respectively with histogram equalization equipment and ten
System changes sub- equipment connection, for by equilibrium figures, the pixel value of each object pixel to be substituted for corresponding to the object pixel as in
Positive goal decimal number simultaneously enters positive goal ten corresponding to all object pixels according to position of the object pixel in equilibrium figures as in
Array processed is exported as positive goal characteristic vector, is additionally operable to each subject image in equilibrium figures picture into positive one-dimensional characteristic vector
The pixel value of element, which is substituted for, bears target decimal number and the position according to object pixel in equilibrium figures picture corresponding to the object pixel
Target decimal number composition negative one dimensional feature vector will be born by putting corresponding to all object pixels, defeated as negative target feature vector
Go out;The more sub- equipment of characteristic vector obtains sub- equipment with characteristic vector respectively and IP unpacks equipment and is connected, for positive goal is special
Sign vector is matched respectively with the positive characteristic vector of each benchmark, by negative target feature vector respectively with each benchmark negative feature to
Amount matched, the two all the match is successful and the positive characteristic vector of benchmark that matches corresponding to authorized user's title and match
When authorized user's title corresponding to benchmark negative feature vector is identical, then recognition of face pass signal and the base with matching are exported
Authorized user's title corresponding to accurate positive characteristic vector, otherwise will export recognition of face failure signal.
The system includes:IP unpack equipment, for being connected with long-range data server network, by network reception come
Unpacked from the IP packets at data server, and to IP packets to obtain 6LowPAN packets;Wherein, IP packets are
To 6LowPAN packets beat the packet of acquisition after IP bags, the load in 6LowPAN packets includes data server
The positive characteristic vector of each benchmark and each benchmark negative feature at place are vectorial, and the head in 6LowPAN packets is compressed data, solution
The head in 6LowPAN packets after pressure is used to parse the load in 6LowPAN packets;Wherein, each base
Accurate positive characteristic vector is to carry out the positive spy with feature extracting device same operation in advance to corresponding authorized user's benchmark face-image
The vector that sign vector is extracted and obtained, each benchmark negative feature vector are pre- advanced to corresponding authorized user's benchmark face-image
The vector that row and the negative feature vector of feature extracting device same operation are extracted and obtained.
The system includes:Edge sensing equipment, unpack equipment with IP and be connected, equipment output is unpacked for receiving IP
6LowPAN packets, the head for the 6LowPAN packets for being rendered as compressed data is obtained, the head of 6LowPAN packets is solved
Pressure is with the head in the 6LowPAN packets after being decompressed.
The system includes:6LowPAN unpacks equipment, is connected with edge sensing equipment, for receiving 6LowPAN packets
To obtain the load in 6LowPAN packets, and based on the head in the 6LowPAN packets after decompression to 6LowPAN data
Load in bag is parsed, to obtain the positive characteristic vector of each benchmark and each benchmark negative feature vector.
Wherein, alternatively, Gaussian smoothing equipment is replaced using wavelet filtering equipment, wavelet filtering equipment is set with luminance compensation
Standby connection carries out wavelet filtering processing to brightness adjustment image to obtain smoothed image to receive brightness adjustment image.
Alternatively, in the control platform:High-definition camera also includes photoflash controller and flash lamp;High-definition camera
Head also includes luminance sensor, for detecting real time environment brightness;Photoflash controller is glistened based on real time environment brilliance control
The opening and closing of lamp;Opening and closing of the photoflash controller based on real time environment brilliance control flash lamp includes:When real time environment brightness is more than
During predetermined luminance threshold value, flash lamp is closed;And opening and closing bag of the photoflash controller based on real time environment brilliance control flash lamp
Include:When real time environment brightness is less than or equal to predetermined luminance threshold value, opens flash lamp and glistened according to real time environment brightness adjustment
The flash luminance of lamp, real time environment brightness is lower, and the flash luminance of flash lamp is higher.
In addition, wave filter, is the device filtered to ripple as its name suggests." ripple " is that a very extensive physics is general
Read, in electronic technology field, the value that " ripple " is narrowly confined to refer in particular to describe various physical quantitys is with time fluctuations
Process.The process is converted into the function of time of voltage or electric current, referred to as various physical quantitys by the effect of various kinds of sensors
Time waveform, or referred to as signal.Because the independent variable time is continuous value, referred to as continuous time signal,
Habitually it is referred to as analog signal again.
With the generation and rapid development of digital electronic computer technology, for the ease of computer to signal at
Reason, generate the complete theoretical and method that continuous time signal is transformed into discrete-time signal under sampling theorem guidance.
That is, primary signal only can be expressed without losing with sample value of the original analog signal on series of discrete time coordinate point
Lose any information since the expression of ripple, waveform, signal these concepts be various physical quantitys in objective world change, naturally
It is the carrier for the various information that modern society depends on for existence.Information needs to propagate, and what is leaned on is exactly the transmission of waveform signal.Signal exists
Its generation, conversion, each link of transmission may be distorted due to the presence of environment and interference, even quite a lot of
In the case of, this distortion is also very serious, causes signal and its entrained information to be embedded in dearly among noise.In order to
These noises are filtered out, recover the signal of script, it is necessary to be filtered processing using various wave filters.
Monitoring system is travelled using the road vehicles based on Internet of Things of the present invention, can not be road surface car for prior art
Provide driver identity authentication scheme technical problem, pass through road vehicles travel monitoring system in integrate high-precision people
The network communication equipment of face feature extraction matching unit and Large Copacity, criminal is found in time, and braked rapidly, so as to
The security performance of road vehicles is improved on the whole.
It is understood that although the present invention is disclosed as above with preferred embodiment, but above-described embodiment and it is not used to
Limit the present invention.For any those skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications are all made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as
With the equivalent embodiment of change.Therefore, every content without departing from technical solution of the present invention, the technical spirit pair according to the present invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments, still fall within the scope of technical solution of the present invention protection
It is interior.
Claims (7)
1. a kind of road vehicles traveling monitoring system based on Internet of Things, the system include vehicle control apparatus, AVR32 cores
Piece, high-definition camera and image processing equipment, high-definition camera, are arranged on inside road vehicles, for clapping driver
According to obtain high definition face image, image processing equipment is used to carry out high definition face image image procossing, AVR32 chips difference
It is connected with vehicle control apparatus and image processing equipment, is determined for the output based on image processing equipment to vehicle control apparatus
Control model.
2. the road vehicles traveling monitoring system based on Internet of Things as claimed in claim 1, it is characterised in that the system bag
Include:
Vehicle control apparatus, road pavement vehicle are controlled, for when receiving validated user signal, safeguarding that driver satisfies the need
Face vehicle continues to drive, and is additionally operable to when receiving disabled user's signal, controls road vehicles to keep to the side to stop according to surface conditions
Car;
AVR32 chips, respectively more sub- with characteristic vector equipment and vehicle control apparatus be connected, for receiving recognition of face
During pass signal, validated user signal is sent, is additionally operable to receiving recognition of face failure signal, sends disabled user's signal;
High-definition camera, it is arranged on inside road vehicles, for being taken pictures to driver to obtain high definition face image;
Intensity compensation devices, it is connected with high-definition camera, for receiving high definition face image, based on each in high definition face image
The gray value of pixel determines the mean flow rate of high definition face image, and the mean flow rate of high definition face image is entered with predetermined luminance
Row compares, when the mean flow rate of high definition face image is more than or equal to predetermined luminance, to high definition face image progress luminance-reduction tune
It is whole to obtain brightness adjustment image, when the mean flow rate of high definition face image is less than predetermined luminance, high definition face image is carried out
Luminance raising is adjusted to obtain brightness adjustment image;
Gaussian smoothing equipment, it is connected with intensity compensation devices to receive brightness adjustment image, Gauss is carried out to brightness adjustment image
Smoothing processing is to obtain smoothed image;
Gray processing processing equipment, it is connected with Gaussian smoothing equipment to receive smoothed image, and smoothed image is performed at gray processing
Manage to obtain gray level image;
Histogram equalization equipment, it is connected to receive gray level image, and gray level image is performed straight with gray processing processing equipment
Square figure equilibrium treatment is to obtain equilibrium figures picture;
Feature extracting device, unpack equipment with histogram equalization equipment and IP respectively and be connected, the equilibrium figures picture received is carried out
Processing;Feature extracting device includes fluctuation threshold and selects sub- equipment, the sub- equipment of processes pixel, the sub- equipment of matrix-split, the decimal system
Change sub- equipment, characteristic vector obtains sub- equipment and the more sub- equipment of characteristic vector;Fluctuation threshold selects sub- equipment and histogram
Balancing equipment connects, for calculating the complexity of equilibrium figures picture, the complexity selection fluctuation threshold size based on equilibrium figures picture,
The complexity of weighing apparatus image is higher, and the fluctuation threshold of selection is bigger, and fluctuation threshold is positive number;The sub- equipment of processes pixel respectively with fluctuation
Threshold value selects sub- equipment to be connected with histogram equalization equipment, for receiving equilibrium figures picture, for each pixel of equilibrium figures picture
Following handle is performed as object pixel:The pixel centered on object pixel, the object of 3 × 3 sizes is obtained in equilibrium figures picture
Picture element matrix, each pixel in object pixel matrix in addition to object pixel is entered as reference pixel and object pixel
Row compares, and to obtain binaryzation matrix, binaryzation matrix is 3 × 3 sizes, and binaryzation matrix is made up of 8 binaryzation pixels, ginseng
Pixel is examined more than or equal to object pixel and fluctuation threshold sum, then the pixel value of binaryzation pixel corresponding to reference pixel is 1, ginseng
Examine pixel and subtract the difference after fluctuation threshold less than object pixel, then the pixel value of binaryzation pixel corresponding to reference pixel is ﹣
1, the pixel value of binaryzation pixel corresponding to the reference pixel of other values is 0;The sub- equipment of matrix-split is set with processes pixel
Standby connection, for by binaryzation matrix conversion corresponding to each object pixel into a positive binaryzation matrix and a negative two-value
Change matrix, positive binaryzation matrix is made up of 8 binaryzation pixel values, and negative binaryzation matrix is also made up of 8 binaryzation pixel values,
The binaryzation pixel value that each binaryzation pixel value of positive binaryzation matrix subtracts negative binaryzation matrix relevant position can obtain
To the pixel value of the binaryzation pixel of corresponding binaryzation matrix relevant position;The decimal system changes sub- equipment and the sub- equipment of matrix-split
Connection, for all binaryzation pixel values of positive binaryzation matrix corresponding to each object pixel to be pressed into it in positive binaryzation square
Position in battle array forms a binary number as the positive binary number of target using first left and then right first up and then down order again, then by mesh
Mark positive binary number and change into decimal number as the positive decimal number of target, to be additionally operable to bear corresponding to each object pixel
All binaryzation pixel values of binaryzation matrix are by its position in negative binaryzation matrix with first left and then right first up and then down again
Order form a binary number as target negative binary number, then by target negative binary number change into decimal number using as
Target bears decimal number;Characteristic vector obtains sub- equipment and is connected respectively with histogram equalization equipment and the sub- equipment of decimal system conversion,
For by equilibrium figures, the pixel value of each object pixel to be substituted for positive goal decimal number corresponding to the object pixel simultaneously as in
Positive goal decimal number corresponding to all object pixels is formed into just one-dimensional spy according to position of the object pixel in equilibrium figures as in
Sign vector, exports as positive goal characteristic vector, is additionally operable to the pixel value of each object pixel in equilibrium figures picture being substituted for
Target decimal number is born corresponding to the object pixel and according to position of the object pixel in equilibrium figures picture by all object pixels
Corresponding negative target decimal number composition negative one dimensional feature vector, is exported as negative target feature vector;Characteristic vector is more sub
Equipment obtains sub- equipment with characteristic vector respectively and IP unpacks equipment and is connected, for by positive goal characteristic vector respectively with each base
Accurate positive characteristic vector is matched, and negative target feature vector is matched with each benchmark negative feature vector respectively, the two is all
Authorized user's title corresponding to the positive characteristic vector of benchmark that the match is successful and matches and the benchmark negative feature vector matched are right
When the authorized user's title answered is identical, then exports recognition of face pass signal and the positive characteristic vector of the benchmark with matching is corresponding
Authorized user's title, otherwise will export recognition of face failure signal;
IP unpacks equipment, for being connected with long-range data server network, is received by network at data server
IP packets, and IP packets are unpacked to obtain 6LowPAN packets;Wherein, IP packets are that 6LowPAN packets are entered
Row beats the packet of acquisition after IP bags, and each benchmark that the load in 6LowPAN packets is included at data server is just special
Levy vector sum each benchmark negative feature vector, the head in 6LowPAN packets is compressed data, the 6LowPAN numbers after decompression
It is used to parse the load in 6LowPAN packets according to the head in bag;Wherein, the positive characteristic vector of each benchmark is pair
Corresponding authorized user's benchmark face-image carries out the positive characteristic vector pickup with feature extracting device same operation in advance and obtained
Vector, each benchmark negative feature vector be to corresponding authorized user's benchmark face-image in advance carry out and feature extracting device
The vector that the negative feature vector of same operation is extracted and obtained;
Edge sensing equipment, unpack equipment with IP and be connected, the 6LowPAN packets of equipment output are unpacked for receiving IP, are obtained
The head of the 6LowPAN packets of compressed data is rendered as, after decompressing the heads of 6LowPAN packets to be decompressed
Head in 6LowPAN packets;
6LowPAN unpacks equipment, is connected with edge sensing equipment, for receiving 6LowPAN packets to obtain 6LowPAN data
Load in bag, and the load in 6LowPAN packets is solved based on the head in the 6LowPAN packets after decompression
Analysis, to obtain the positive characteristic vector of each benchmark and each benchmark negative feature vector;
Wherein, alternatively, Gaussian smoothing equipment is replaced using wavelet filtering equipment, wavelet filtering equipment connects with intensity compensation devices
Connect to receive brightness adjustment image, wavelet filtering processing is carried out to brightness adjustment image to obtain smoothed image.
3. the road vehicles traveling monitoring system based on Internet of Things as claimed in claim 2, it is characterised in that:
High-definition camera also includes photoflash controller and flash lamp.
4. the road vehicles traveling monitoring system based on Internet of Things as claimed in claim 3, it is characterised in that:
High-definition camera also includes luminance sensor, for detecting real time environment brightness.
5. the road vehicles traveling monitoring system based on Internet of Things as claimed in claim 4, it is characterised in that:
Opening and closing of the photoflash controller based on real time environment brilliance control flash lamp.
6. the road vehicles traveling monitoring system based on Internet of Things as claimed in claim 5, it is characterised in that:
Opening and closing of the photoflash controller based on real time environment brilliance control flash lamp includes:When real time environment brightness is bright more than default
When spending threshold value, flash lamp is closed.
7. the road vehicles traveling monitoring system based on Internet of Things as claimed in claim 5, it is characterised in that:
Opening and closing of the photoflash controller based on real time environment brilliance control flash lamp includes:When real time environment brightness is less than or equal in advance
If during luminance threshold, open flash lamp and got over according to the flash luminance of real time environment brightness adjustment flash lamp, real time environment brightness
Low, the flash luminance of flash lamp is higher.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610778862.6A CN107800996A (en) | 2016-08-31 | 2016-08-31 | Road vehicles traveling monitoring system based on Internet of Things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610778862.6A CN107800996A (en) | 2016-08-31 | 2016-08-31 | Road vehicles traveling monitoring system based on Internet of Things |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107800996A true CN107800996A (en) | 2018-03-13 |
Family
ID=61527662
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610778862.6A Withdrawn CN107800996A (en) | 2016-08-31 | 2016-08-31 | Road vehicles traveling monitoring system based on Internet of Things |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107800996A (en) |
-
2016
- 2016-08-31 CN CN201610778862.6A patent/CN107800996A/en not_active Withdrawn
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107851195B (en) | Target detection using neural networks | |
CN103246876B (en) | Image feature comparison based counterfeit vehicle registration plate identification method | |
CN108447219A (en) | System and method for detecting fire hazard based on video image | |
Won et al. | DeepWiTraffic: Low cost WiFi-based traffic monitoring system using deep learning | |
CN108877009B (en) | Intelligent access control system based on face recognition | |
CN108399667A (en) | Parking stall ground lock control device and method | |
CN103434484A (en) | Vehicle-mounted identification and authentication device, mobile terminal and intelligent vehicle key control system and method | |
CN107909040B (en) | Car renting verification method and device | |
KR101999985B1 (en) | Method and system for recognizing vehicle license plate | |
CN110636048B (en) | Vehicle-mounted intrusion detection method and system based on ECU signal characteristic identifier | |
CN107293011A (en) | A kind of gate control system of smart home | |
CN110188715A (en) | A kind of video human face biopsy method of multi frame detection ballot | |
Krichen et al. | Iris identification using wavelet packets | |
CN104573680B (en) | Image detecting method, image detection device and traffic offence detecting system | |
CN105447503A (en) | Sparse-representation-LBP-and-HOG-integration-based pedestrian detection method | |
CN109460787A (en) | IDS Framework method for building up, device and data processing equipment | |
CN103714326A (en) | One-sample face identification method | |
CN109493470B (en) | Intelligent access control system based on block chain | |
CN104156691A (en) | Monitoring method based on picture processing for detecting behavior of pedestrian climbing over turnstile | |
CN110633655A (en) | Attention-attack face recognition attack algorithm | |
CN106650566A (en) | Internet of things based road surface vehicle driving monitoring system | |
CN110363070A (en) | The method, apparatus and computer program product of intelligent recognition road condition | |
CN101711399B (en) | Vein pattern management system, vein pattern registration device, vein pattern authentication device, vein pattern registration method, vein pattern authentication method, vein data storage device | |
CN103699888A (en) | Human face detection method and device | |
CN107800996A (en) | Road vehicles traveling monitoring system based on Internet of Things |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180313 |