CN109461065A - A kind of cross-border e-commerce video safety monitoring system and control method - Google Patents
A kind of cross-border e-commerce video safety monitoring system and control method Download PDFInfo
- Publication number
- CN109461065A CN109461065A CN201811205656.1A CN201811205656A CN109461065A CN 109461065 A CN109461065 A CN 109461065A CN 201811205656 A CN201811205656 A CN 201811205656A CN 109461065 A CN109461065 A CN 109461065A
- Authority
- CN
- China
- Prior art keywords
- border
- indicate
- secret
- cross
- commerce
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 19
- 239000002245 particle Substances 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 230000009977 dual effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- FFBHFFJDDLITSX-UHFFFAOYSA-N benzyl N-[2-hydroxy-4-(3-oxomorpholin-4-yl)phenyl]carbamate Chemical compound OC1=C(NC(=O)OCC2=CC=CC=C2)C=CC(=C1)N1CCOCC1=O FFBHFFJDDLITSX-UHFFFAOYSA-N 0.000 claims description 3
- 238000007635 classification algorithm Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000009467 reduction Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/10—Tax strategies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Algebra (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Security & Cryptography (AREA)
- Evolutionary Biology (AREA)
- Bioethics (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to safety monitoring system technical fields, disclose a kind of cross-border e-commerce video safety monitoring system and monitoring method, monitoring system is provided with remote computer, remote computer connects transmitter, foreign trade router by conducting wire, and transmitter connects camera, sound pick-up, data reader by conducting wire；Storage chip is connected with inside transmitter；Storage chip lower end is connected with single-chip microcontroller；Single-chip microcontroller lower end is connected with ZigBee module.Mentality of designing of the present invention is clear, can monitor in real time to cross-border e-commerce, improve the safety of cross-border electric business；By the mutual cooperation of camera and sound pick-up, carries out that real-time audiovisual monitoring can be carried out to cross-border e-commerce in conjunction with remote computer, improve the safety of e-commerce overseas；Reading data is carried out to the transaction of electric business overseas by data reader simultaneously, can guarantee the safety of e-commerce transaction overseas, provides sound dealing record for tax verifier.
Description
Technical field
The invention belongs to safety monitoring system technical field more particularly to a kind of cross-border e-commerce Video security monitoring systems
System and control method.
Background technique
Currently, border e-commerce refers to the transaction agent for adhering to different customs boundaries separately, concluded the transaction by e-commerce platform, into
Row payment and settlement, and by cross-border logistics be sent to commodity, complete transaction a kind of international business transactions.And current cross-border electronics
Commercial affairs development is simultaneously immature, and for electric business overseas, there is also certain risks, so inventing a kind of cross-border e-commerce video peace
Full monitoring system is necessary；Since e-commerce is unfolded based on virtual Cyberspace, traditional friendship is lost
Geographic factor under easy mode, therefore this remote transaction brings many difficulties to tax revenue office, China, it sometimes can not be to transaction
Information is accurately recorded.
In conclusion problem of the existing technology is:
(1) camera used at present can not carry out effective binarization segmentation to image when handling image,
The target that cannot achieve infrared image is automatic, it is difficult to handle infrared image, influence the effect of monitoring.
(2) single-chip microcontroller POS algorithm used at present, arithmetic speed is low, and the number of iterations is larger, reduces the work of single-chip microcontroller
Efficiency, to the processing of information, there are time unmatched situations, it is difficult to reach the requirement of cross-border e-commerce video monitoring.
(3) current cross-border e-commerce development and immature, for electric business overseas, there is also certain risks；Electronics quotient
Business is unfolded based on virtual Cyberspace, and the geographic factor under traditional transaction way, therefore this remote transaction are lost
Many difficulties are brought to tax revenue office, China, Transaction Information can not accurately be recorded sometimes, traditional information classification side
Method, classification situation inaccuracy, slower to the classification of information, working efficiency is lower.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of cross-border e-commerce video safety monitoring system and
Monitoring method.
The invention is realized in this way a kind of cross-border e-commerce Video security monitoring method, the cross-border e-commerce
Video security monitoring method includes:
The VPN of foreign trade router is connected on IP overseas, real-time video is carried out to e-commerce overseas by camera
Monitoring, the picture that camera is recorded are sent to storage chip, and the picture after storage is transmitted to single-chip microcontroller again；It is handled by single-chip microcontroller
Afterwards, then by picture is recorded it is sent to remote computer terminal；
Sound pick-up is collected by sound of the microphone to ambient enviroment, then by audio amplifier circuit to collect sound into
Sound is monitored in row reduction, realization；The sound that sound pick-up is collected is transmitted to remote computer terminal by transmitter, realizes
Monitoring to cross-border implement business EC vision and acoustically；
Data reader is read out remote transaction data, and the data after reading are transmitted to remote computation by transmitter
Machine terminal.
Further, remote computer terminal encrypts the remote transaction data that data reader is read, specifically
Have:
1) it initializes:
2) enabling attribute set S is the layering subset of attribute set U, according to attribute set S, common parameter PK, message M and one
A layering thresholding access structure (M generated in advanceV, ρ) attribute of attribute set U all levels is carried out with an expression formula
Encryption obtains ciphertext CT, wherein function ρ indicates hierarchical access structure MVIn row to attribute mapping；Enable that attribute set S's is every
One layer of number of attributes is more than this layer of thresholding, and S is made to meet the access structure of layering；
3) by master key MSK and attribute set S, in conjunction with the subgroup in step S1Generate key SK；
Step 1) includes:
The operation rule of defined function f is as follows: as soon as every progress time f operation, becomes 0 for polynomial constant term, from change
The coefficient of amount is constant, and number subtracts 1, if a, b, c, d are determining normal real number, then has:
f(a+bx+cxd)=0+b+cxd-1；
f(1+2x+3x4)=0+2+3x3；
If (k, n) is the secret sharing systems of a layering, mainly by a secret distributor D and n patcicipant's gruop at,
Attribute set U is the set of n participant, and includes m level, i.e.,Wherein for i ≠ j, Ui∩Uj=φ；
It enablesIt is the 0 < k of integer sequence of a monotonic increase0< k1< ... < km, and km-1< km- 1, kiIt is each
The threshold value of layer, then the thresholding access structure of (k, n) layering seeks to distribute secret letter for participant u each in attribute set U
A secret shadow σ (u) for ceasing s, makes it meet following access structure:
The participant's subset S for meeting the layering of access structure described in above formula is known as authorized subset, can restore to lead secret
It is close, and any user's subset for being unsatisfactory for above-mentioned access structure will be unable to obtain any information about main secret；
Sub-secret distribution:
Secret distributor D arbitrarily chooses t-1 random number a1,...,at-1With a Big prime q, multinomial P is then constructed
(x)=s+a1x+...+at-1xt-1, wherein s is the main secret for needing to be shared；Inside each participant u corresponding domain in system
Element representation its identity, use ujIt indicates, D level i according to locating for participant calculates the secret shadow of participantWherein:
P0(x)=P (x)；
P1(x)=f1(P (x))=f (P (x))；
Pi(u)=f (Pi-1(u))；
Representative polynomial P (x) passes through ki-1In field element u after secondary f operationjThe value at place；ki-1It is (i-1)-th layer
Threshold value and enable k-1=0, D are disclosedlmIndicate the number of elements for possessing attribute set S in m layers；
Secret reconstruction:
It enables| S | indicate number of elements possessed by S, setting meets:
…
Wherein, U0,…,UmIndicate the 0th to m layer of set U, 0≤l0≤l1≤...≤lm=| S |, and if only if for institute
0≤i having≤m, li≥ki, S is an authorized subset, that is, meets access structure, then, can be with when participant all in S cooperates
Form coefficient matrix MV, wherein coefficient matrix is write by row are as follows:
All participants in S can cooperate to solve following equation group:
That is:
If S meets access structure, so that it may multinomial P (x) is reconstructed, to recover secret s；Further, this is visited
Ask that structure can be equivalent to the access structure of LSSS of hierarchical matrix, evenIt is defined as I={ j: ρ
(j) ∈ S }, if enabledIt is a sub-secret of secret s, then there is constant { ωj∈ZNMake ∑j∈Iωjλj
=s, whereinZNIndicate 1 integer set for arriving N；ωjIn the multinomial of privacy sharing generator matrix Mv size
It can be always found in the formula time, so that it may recover main secret；
Step 2) includes the following steps:
2.1) access structure M is enabledVIt is j × t matrix；
2.2) random vector is selected It indicates in 1 to N integer set
Any t, wherein s indicates secret value, y1,......,yt-1For the sharing of secret value s；
2.3) it enables| S | indicate number of elements possessed by S, setting meets:
…
Wherein, U0,…,UmIndicate the 0th to m layer of set U, 0≤l0≤l1≤...≤lm=| S |, and if only if for institute
0≤i having≤m, there is li≥ki, liIndicate the number of elements for possessing set S in i-th layer, kiIndicate the element of set S in i-th layer
Quantity thresholding；
Then for all j=1 ..., l0,...,lm, calculateMjIndicate MVIn jth row；
2.4) for the hierachy number i ∈ { 0 ..., m } of attribute set U, j=l is seti-1+ c, l-1=0, c are constant, are indicated
I-th layer of c-th of attribute, i.e. j-th of attribute in attribute set U correspond to i-th layer of c-th of attribute；
2.5) random number is selected
2.6) attribute of all levels is subjected to encryption by following formula and obtains ciphertext CT:
Wherein, hρ(j)Indicate that group element corresponding with a property element of ρ (j) in attribute set U, ρ (j) indicate attribute
The attribute of jth layer is to access structure M in set UvJth row mapping.
Further, camera is in the processing of image, using infrared binarization segmentation algorithm, comprising:
Step 1: being enhanced using algorithm of histogram equalization image degree of comparing；
In formula: DBFor the gray value after conversion；DAFor the gray value before conversion；HiFor the number of pixels of i-stage gray scale；A0
For sum of all pixels, two-dimensional gray histogram curve is drawn；
Step 2: setting f (x, y) is the two-dimensional gray histogram curve carried out after infrared image histogram equalization, wherein x
Indicate that grey level, y indicate the number that specific each grey level pixel occurs, seek gradient at point (x, y) to f (x, y):
In formula:For at point (x, y) f to the partial derivative of x；For at point (x, y) f to the partial derivative of y；Measurement of the amplitude of gradient as change rate size,
Its value are as follows:
And for two-dimensional discrete function f (i, j), use finite difference as an approximation of gradient magnitude:
To simplify the calculation, above formula approximation simplifies are as follows:
The formula is the foundation that local threshold is chosen；
Step 3: seeking the shade of gray mean value obtained in second step:
In formula: k is striked shade of gray value number.Give up the part that shade of gray value is less than gradient mean value, retains ash
The part that gradient value is greater than shade of gray mean value is spent,
Wherein: m=1,2,3 ..., n；
In formula: m is to give up shade of gray less than the shade of gray value number after average gray gradient value；Shade of gray value is big
It is combined into a set in the pixel gray level of gray average, constitutes global threshold face, global threshold face is that extraction target is main
The datum level of profile carries out infrared image binarization segmentation using this threshold value face.
Further, single-chip microcontroller is handled the picture of storage using improved PSO algorithm, in basic PSO algorithm, w
So that particle is kept motional inertia, so that it is had the tendency that expanded search space, when w is larger, the movement velocity of particle is very fast, makes particle
Region of search it is larger, and its can be made faster close to global optimum's particle, when w is smaller, the movement velocity of particle is slow,
So that particle is carried out fine search in subrange, be conducive to the convergence of algorithm, w often takes dynamic to adjust thus；
Wherein: wm axAnd wm inIndicate inertia weight maximum and minimum value, t indicates the number of iterations, I term axIndicate maximum
The number of iterations.
Further, single-chip microcontroller classifies to collected various information, and information classification is using the quick of support vector machines
Sorting algorithm specifically includes:
Given training sample set { (xi, yi), i=1,2 ..., l }, xi∈Rd, yi∈ { -1 ,+1 } is introduced from input space Rn
To the transformation of Hilbert (Hilbert) space H:
Then primal problem is constructed in the H of the space Hilbert:
Termination condition:
Using Lagrange multiplier method solution formula (1), obtained dual problem are as follows:
Termination condition:
Wherein K (xi, xj) it is kernel function:
Optimal solution α *=(α is obtained by solving above-mentioned dual problem1* ..., αl*)T, choose the 0 < α of a positive component of α *j*
< C, and threshold is calculated accordingly
b*=yj-∑yiαi *K(xi,xj), (5)
Finally construct decision function
Give two sample x1, x2∈RN, then the distance between two samples can be expressed as d (x1, x2),Indicate sample xl
I-th of component, in the case where linear, the distance between two samples are defined as follows:
Under nonlinear situation, the distance between two samples are defined as follows:
WhereinFor vector x in former space to be mapped to vector corresponding in high-dimensional vector space, For kernel function；
Assuming that a kind of sample is x1i, i=1 ..., l, another kind of sample is x2j, j=1, m, d (x1i, x2j) indicate
I-th of sample in the first kind to j-th of sample in the second class distance, then to each i value, di=mind (x1i,x2j)
(j=1,2, m) and, corresponding vector x2jIt is exactly a Margin Vector of the second class sample；
Distance screening is passed through to original sample, obtains the l initial training sample (x by retive boundary vector process1,
y1) ..., (xl, yl), wherein xi∈Rn, i=1 ..., l, yi∈ { -1,1 } is sample xiAffiliated classification, m are training sample
Class number, if the training sample set of k-th of support vector machines is combined into X={ (xi, yi)|yi>=k }, it obtains
Constraint condition:
Its dual problem is converted into be solved:
Obtain its corresponding decision function are as follows:
Another object of the present invention is to provide a kind of meters for realizing the cross-border e-commerce Video security monitoring method
Calculation machine program.
Another object of the present invention is to provide a kind of letters for realizing the cross-border e-commerce Video security monitoring method
Cease data processing terminal.
Another object of the present invention is to provide a kind of computer readable storage mediums, including instruction, when it is in computer
When upper operation, so that computer executes the cross-border e-commerce Video security monitoring method.
Another object of the present invention is to provide a kind of cross-border e-commerce video safety monitoring system, the cross-border electronics
Business video safety monitoring system is provided with
Remote computer；
The remote computer connects transmitter, foreign trade router by conducting wire, and the transmitter is taken the photograph by conducting wire connection
As head, sound pick-up, data reader, it is connected with storage chip inside the transmitter, the storage chip lower end is connected with list
Piece machine, the single-chip microcontroller lower end are connected with ZigBee module.
Further, the ZigBee module connects local network by cable；
The VPN broadband server of the foreign trade router connects foreign countries local IP.
Advantages of the present invention and good effect are as follows:
By the mutual cooperation of camera and sound pick-up, cross-border e-commerce can be carried out in conjunction with remote computer progress
Real-time audiovisual monitoring, improves the safety of e-commerce overseas；, the processing that camera sends out image is using infrared image two-value
Change partitioning algorithm, can be very good adapt to infrared image resolution ratio it is low, the low feature of image of contrast can be realized infrared image
Target is automatic, effectively binarization segmentation.
Reading data is carried out to the transaction of electric business overseas by data reader, can guarantee e-commerce transaction overseas
Safety provides sound dealing record for tax verifier, and single-chip microcontroller uses improved POS algorithm, is capable of changing for little data
Generation number improves the arithmetic speed of single-chip microcontroller, has reached the requirement of cross-border e-commerce video monitoring.
Fast Classification is carried out to information by using the fast classification algorithm of support vector machines, and it is accurate to classify, greatly
Improve the safety of video monitoring.
This system mentality of designing is clear, can monitor in real time to cross-border e-commerce, improve the safety of cross-border electric business
Property.
A kind of cross-border e-commerce Video security monitoring method, the cross-border e-commerce Video security monitoring method packet
It includes:
The VPN of foreign trade router is connected on IP overseas, real-time video is carried out to e-commerce overseas by camera
Monitoring, the picture that camera is recorded are sent to storage chip, and the picture after storage is transmitted to single-chip microcontroller again；It is handled by single-chip microcontroller
Afterwards, then by picture is recorded it is sent to remote computer terminal；
Sound pick-up is collected by sound of the microphone to ambient enviroment, then by audio amplifier circuit to collect sound into
Sound is monitored in row reduction, realization；The sound that sound pick-up is collected is transmitted to remote computer terminal by transmitter, realizes
Monitoring to cross-border implement business EC vision and acoustically；
Data reader is read out remote transaction data, and the data after reading are transmitted to remote computation by transmitter
Machine terminal.
Remote computer terminal of the present invention encrypts the remote transaction data that data reader is read, specifically
Have:
1) it initializes:
2) enabling attribute set S is the layering subset of attribute set U, according to attribute set S, common parameter PK, message M and one
A layering thresholding access structure (M generated in advanceV, ρ) attribute of attribute set U all levels is carried out with an expression formula
Encryption obtains ciphertext CT, wherein function ρ indicates hierarchical access structure MVIn row to attribute mapping；Enable that attribute set S's is every
One layer of number of attributes is more than this layer of thresholding, and S is made to meet the access structure of layering；
3) by master key MSK and attribute set S, in conjunction with the subgroup G in step S1p3Generate key SK；Above scheme
Implement, ensure that the safety of data.
Detailed description of the invention
Fig. 1 is cross-border e-commerce video safety monitoring system structural schematic diagram provided in an embodiment of the present invention；
Fig. 2 is transmitter schematic internal view provided in an embodiment of the present invention；
In figure: 1, camera；2, transmitter；3, remote computer；4, foreign trade router；5, sound pick-up；6, reading data
Device；7, storage chip；8, single-chip microcontroller；9, ZigBee module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As depicted in figs. 1 and 2, cross-border e-commerce video safety monitoring system provided in an embodiment of the present invention, comprising: take the photograph
As head 1, transmitter 2, remote computer 3, foreign trade router 4, sound pick-up 5, data reader 6, storage chip 7, single-chip microcontroller 8,
ZigBee module 9.
The remote computer 3 connects transmitter 2, foreign trade router 4 by conducting wire, and the transmitter 2 is connected by conducting wire
Camera 1, sound pick-up 5, data reader 6 are connect, is connected with storage chip 7 inside the transmitter 2, under the storage chip 7
End is connected with single-chip microcontroller 8, and 8 lower end of single-chip microcontroller is connected with ZigBee module 9.
The ZigBee module 9 connects local network by cable.The VPN broadband server of the foreign trade router 4 connects
Meet foreign countries local IP.
The working principle of the invention: the VPN of foreign trade router 4 is connected on IP overseas, and cross-border e-commerce provides fast
Fast, stable wireless network realizes the wireless telecommunications of camera 1, sound pick-up 5, data reader 6 by ZigBee module 9, leads to
It crosses camera 1 and real-time video monitoring is carried out to e-commerce overseas, the picture that camera 1 is recorded is sent to storage chip 7, stores
Picture afterwards is transmitted to single-chip microcontroller 8 again, after the simple process by single-chip microcontroller 8, then by record picture be sent to remote computer 3
Terminal, sound pick-up 5 are collected by sound of the microphone to ambient enviroment, then are carried out by audio amplifier circuit to sound is collected
Reduction, to monitor sound, the sound that sound pick-up 5 is collected is transmitted to 3 terminal of remote computer by transmitter 2, from
And monitoring to cross-border implement business EC vision and acoustically, guarantee the safety of cross-border e-commerce；Data reader 6 can
Remote transaction data are read out, the data after reading are transmitted to 3 terminal of remote computer by transmitter 2, guarantee overseas
The safety of e-commerce transaction provides sound dealing record for tax verifier.
The present invention is described further below with reference to concrete analysis.
Cross-border e-commerce Video security monitoring method provided in an embodiment of the present invention, comprising:
The VPN of foreign trade router is connected on IP overseas, real-time video is carried out to e-commerce overseas by camera
Monitoring, the picture that camera is recorded are sent to storage chip, and the picture after storage is transmitted to single-chip microcontroller again；It is handled by single-chip microcontroller
Afterwards, then by picture is recorded it is sent to remote computer terminal；
Sound pick-up is collected by sound of the microphone to ambient enviroment, then by audio amplifier circuit to collect sound into
Sound is monitored in row reduction, realization；The sound that sound pick-up is collected is transmitted to remote computer terminal by transmitter, realizes
Monitoring to cross-border implement business EC vision and acoustically；
Data reader is read out remote transaction data, and the data after reading are transmitted to remote computation by transmitter
Machine terminal.
The remote transaction that data reader is read as the preferred embodiment of the embodiment of the present invention, remote computer terminal
Data encrypt, and specifically have:
1) it initializes:
2) enabling attribute set S is the layering subset of attribute set U, according to attribute set S, common parameter PK, message M and one
A layering thresholding access structure (M generated in advanceV, ρ) attribute of attribute set U all levels is carried out with an expression formula
Encryption obtains ciphertext CT, wherein function ρ indicates hierarchical access structure MVIn row to attribute mapping；Enable that attribute set S's is every
One layer of number of attributes is more than this layer of thresholding, and S is made to meet the access structure of layering；
3) by master key MSK and attribute set S, in conjunction with the subgroup in step S1Generate key SK；
Step 1) includes:
The operation rule of defined function f is as follows: as soon as every progress time f operation, becomes 0 for polynomial constant term, from change
The coefficient of amount is constant, and number subtracts 1, if a, b, c, d are determining normal real number, then has:
f(a+bx+cxd)=0+b+cxd-1；
f(1+2x+3x4)=0+2+3x3；
If (k, n) is the secret sharing systems of a layering, mainly by a secret distributor D and n patcicipant's gruop at,
Attribute set U is the set of n participant, and includes m level, i.e.,Wherein for i ≠ j, Ui∩Uj=φ；
It enablesIt is the 0 < k of integer sequence of a monotonic increase0< k1< ... < km, and km-1< km- 1, kiIt is each
The threshold value of layer, then the thresholding access structure of (k, n) layering seeks to distribute secret letter for participant u each in attribute set U
A secret shadow σ (u) for ceasing s, makes it meet following access structure:
The participant's subset S for meeting the layering of access structure described in above formula is known as authorized subset, can restore to lead secret
It is close, and any user's subset for being unsatisfactory for above-mentioned access structure will be unable to obtain any information about main secret；
Sub-secret distribution:
Secret distributor D arbitrarily chooses t-1 random number a1,...,at-1With a Big prime q, multinomial P is then constructed
(x)=s+a1x+...+at-1xt-1, wherein s is the main secret for needing to be shared；Inside each participant u corresponding domain in system
Element representation its identity, use ujIt indicates, D level i according to locating for participant calculates the secret shadow of participantWherein:
P0(x)=P (x)；
P1(x)=f1(P (x))=f (P (x))；
Pi(u)=f (Pi-1(u))；
Representative polynomial P (x) passes through ki-1In field element u after secondary f operationjThe value at place；ki-1It is (i-1)-th layer
Threshold value and enable k-1=0, D are disclosedlmIndicate the number of elements for possessing attribute set S in m layers；
Secret reconstruction:
It enables| S | indicate number of elements possessed by S, setting meets:
…
Wherein, U0,…,UmIndicate the 0th to m layer of set U, 0≤l0≤l1≤...≤lm=| S |, and if only if for institute
0≤i having≤m, li≥ki, S is an authorized subset, that is, meets access structure, then, can be with when participant all in S cooperates
Form coefficient matrix MV, wherein coefficient matrix is write by row are as follows:
All participants in S can cooperate to solve following equation group:
That is:
If S meets access structure, so that it may multinomial P (x) is reconstructed, to recover secret s；Further, this is visited
Ask that structure can be equivalent to the access structure of LSSS of hierarchical matrix, evenIt is defined as I={ j: ρ
(j) ∈ S }, if enabledIt is a sub-secret of secret s, then there is constant { ωj∈ZNMake Σj∈Iωjλj
=s, whereinZNIndicate 1 integer set for arriving N；ωjIn privacy sharing generator matrix MvSize it is multinomial
It can be always found in the formula time, so that it may recover main secret；
Step 2) includes the following steps:
2.1) enable access structure MVIt is j × t matrix；
2.2) random vector is selected It indicates in 1 to N integer set
Any t, wherein s indicates secret value, y1,......,yt-1For the sharing of secret value s；
2.3) it enables| S | indicate number of elements possessed by S, setting meets:
…
Wherein, U0,…,UmIndicate the 0th to m layer of set U, 0≤l0≤l1≤...≤lm=| S |, and if only if for institute
0≤i having≤m, there is li≥ki, liIndicate the number of elements for possessing set S in i-th layer, kiIndicate the element of set S in i-th layer
Quantity thresholding；
Then for all j=1 ..., l0,...,lm, calculateMjIndicate MVIn jth row；
2.4) for the hierachy number i ∈ { 0 ..., m } of attribute set U, j=l is seti-1+ c, l-1=0, c are constant, are indicated
I-th layer of c-th of attribute, i.e. j-th of attribute in attribute set U correspond to i-th layer of c-th of attribute；
2.5) random number is selected
2.6) attribute of all levels is subjected to encryption by following formula and obtains ciphertext CT:
Wherein, hρ(j)Indicate that group element corresponding with a property element of ρ (j) in attribute set U, ρ (j) indicate attribute
The attribute of jth layer is to access structure M in set UvJth row mapping.
As the preferred embodiment of the embodiment of the present invention, camera is divided using infrared binaryzation in the processing of image
Cut algorithm, comprising:
Step 1: being enhanced using algorithm of histogram equalization image degree of comparing；
In formula: DBFor the gray value after conversion；DAFor the gray value before conversion；HiFor the number of pixels of i-stage gray scale；A0
For sum of all pixels, two-dimensional gray histogram curve is drawn；
Step 2: setting f (x, y) is the two-dimensional gray histogram curve carried out after infrared image histogram equalization, wherein x
Indicate that grey level, y indicate the number that specific each grey level pixel occurs, seek gradient at point (x, y) to f (x, y):
In formula:For at point (x, y) f to the partial derivative of x；For at point (x, y) f to the partial derivative of y；Measurement of the amplitude of gradient as change rate size,
Its value are as follows:
And for two-dimensional discrete function f (i, j), use finite difference as an approximation of gradient magnitude:
To simplify the calculation, above formula approximation simplifies are as follows:
The formula is the foundation that local threshold is chosen；
Step 3: seeking the shade of gray mean value obtained in second step:
In formula: k is striked shade of gray value number.Give up the part that shade of gray value is less than gradient mean value, retains ash
The part that gradient value is greater than shade of gray mean value is spent,
Wherein: m=1,2,3 ..., n；
In formula: m is to give up shade of gray less than the shade of gray value number after average gray gradient value；Shade of gray value is big
It is combined into a set in the pixel gray level of gray average, constitutes global threshold face, global threshold face is that extraction target is main
The datum level of profile carries out infrared image binarization segmentation using this threshold value face.
As the preferred embodiment of the embodiment of the present invention, single-chip microcontroller is carried out using picture of the improved PSO algorithm to storage
Processing, in basic PSO algorithm, w makes particle keep motional inertia, it is made to have the tendency that expanded search space, when w is larger, grain
The movement velocity of son is very fast, keeps the region of search of particle larger, and its can be made faster close to global optimum's particle, w compared with
Hour, the movement velocity of particle is slow, and particle is enable to carry out fine search in subrange, is conducive to the convergence of algorithm, is
This w often takes dynamic to adjust；
Wherein: wm axAnd wm inIndicate inertia weight maximum and minimum value, t indicates the number of iterations, I term axIndicate maximum
The number of iterations.
As the preferred embodiment of the embodiment of the present invention, single-chip microcontroller classifies to collected various information, information point
Class uses the fast classification algorithm of support vector machines, specifically includes:
Given training sample set { (xi, yi), i=1,2 ..., l }, xi∈Rd, yi∈ { -1 ,+1 } is introduced from input space Rn
To the transformation of Hilbert (Hilbert) space H:
Then primal problem is constructed in the H of the space Hilbert:
Termination condition:
Using Lagrange multiplier method solution formula (1), obtained dual problem are as follows:
Termination condition:
Wherein K (xi, xj) it is kernel function:
Optimal solution α is obtained by solving above-mentioned dual problem*=(α1 *..., αl *)T, choose the 0 < α of a positive component of α *j*
< C, and threshold is calculated accordingly
b*=yj-∑yiαi *K(xi,xj), (5)
Finally construct decision function
Give two sample x1, x2∈RN, then the distance between two samples can be expressed as d (x1, x2),Indicate sample xl
I-th of component, in the case where linear, the distance between two samples are defined as follows:
Under nonlinear situation, the distance between two samples are defined as follows:
WhereinFor vector x in former space to be mapped to vector corresponding in high-dimensional vector space, For kernel function；
Assuming that a kind of sample is x1i, i=1 ..., l, another kind of sample is x2j, j=1, m, d (x1i, x2j) indicate
I-th of sample in the first kind to j-th of sample in the second class distance, then to each i value, di=mind (x1i,x2j)
(j=1,2, m) and, corresponding vector x2jIt is exactly a Margin Vector of the second class sample；
Distance screening is passed through to original sample, obtains the l initial training sample (x by retive boundary vector process1,
y1) ..., (xl, yl), wherein xi∈Rn, i=1 ..., l, yi∈ { -1,1 } is sample xiAffiliated classification, m are training sample
Class number, if the training sample set of k-th of support vector machines is combined into X={ (xi, yi)|yi>=k }, it obtains
Constraint condition:
Its dual problem is converted into be solved:
Obtain its corresponding decision function are as follows:
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one
Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one
A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)
Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center
Transmission).The computer-readable storage medium can be any usable medium or include one that computer can access
The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie
Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid
State Disk (SSD)) etc..
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of cross-border e-commerce Video security monitoring method, which is characterized in that the cross-border e-commerce Video security prison
Prosecutor method includes:
The VPN of foreign trade router is connected on IP overseas, real-time video monitoring is carried out to e-commerce overseas by camera,
The picture that camera is recorded is sent to storage chip, and the picture after storage is transmitted to single-chip microcontroller again；After being handled by single-chip microcontroller, then
Picture will be recorded and be sent to remote computer terminal；
Sound pick-up is collected by sound of the microphone to ambient enviroment, then is gone back by audio amplifier circuit to sound is collected
Sound is monitored in original, realization；The sound that sound pick-up is collected is transmitted to remote computer terminal by transmitter, realization to across
Border implement business EC vision and monitoring acoustically；
Data reader is read out remote transaction data, and the data after reading are transmitted to remote computer end by transmitter
End.
2. cross-border e-commerce Video security monitoring method as described in claim 1, which is characterized in that remote computer terminal
The remote transaction data read to data reader encrypt, and specifically have:
1) it initializes:
2) enabling attribute set S is the layering subset of attribute set U, is mentioned according to attribute set S, common parameter PK, message M and one
Previous existence at layering thresholding access structure (MV, ρ) attribute of attribute set U all levels is encrypted with an expression formula
Obtain ciphertext CT, wherein function ρ indicates hierarchical access structure MVIn row to attribute mapping；Enable each layer of attribute set S
Number of attributes be more than this layer of thresholding, make S meet layering access structure；
3) by master key MSK and attribute set S, in conjunction with the subgroup G in step S1p3Generate key SK；
Step 1) includes:
The operation rule of defined function f is as follows: as soon as every progress time f operation, becomes 0 for polynomial constant term, independent variable
Coefficient is constant, and number subtracts 1, if a, b, c, d are determining normal real number, then has:
f(a+bx+cxd)=0+b+cxd-1；
f(1+2x+3x4)=0+2+3x3；
If (k, n) is the secret sharing systems of a layering, mainly by a secret distributor D and n patcicipant's gruop at attribute
Set U is the set of n participant, and includes m level, i.e.,Wherein for i ≠ j, Ui∩Uj=φ；It enablesIt is the 0 < k of integer sequence of a monotonic increase0< k1< ... < km, and km-1< km- 1, kiIt is each layer
Threshold value, then (k, n) layering thresholding access structure seek to for participant u each in attribute set U distribute secret information s
A secret shadow σ (u), so that it is met following access structure:
The participant's subset S for meeting the layering of access structure described in above formula is known as authorized subset, can restore main secret, and
Any user's subset for being unsatisfactory for above-mentioned access structure will be unable to obtain any information about main secret；
Sub-secret distribution:
Secret distributor D arbitrarily chooses t-1 random number a1,...,at-1With a Big prime q, then construct multinomial P (x)=
s+a1x+...+at-1xt-1, wherein s is the main secret for needing to be shared；One inside each participant u corresponding domain in system
Its identity of a element representation, uses ujIt indicates, D level i according to locating for participant calculates the secret shadow of participantWherein:
P0(x)=P (x)；
P1(x)=f1(P (x))=f (P (x))；
Pi(u)=f (Pi-1(u))；
Representative polynomial P (x) passes through ki-1In field element u after secondary f operationjThe value at place；ki-1It is (i-1)-th layer of threshold value
And enable k-1=0, D are disclosedlmIndicate the number of elements for possessing attribute set S in m layers；
Secret reconstruction:
It enables| S | indicate number of elements possessed by S, setting meets:
…
Wherein, U0,…,UmIndicate the 0th to m layer of set U, 0≤l0≤l1≤...≤lm=| S |, and if only if for all
0≤i≤m, li≥ki, S is an authorized subset, that is, meets access structure, then when participant all in S cooperates, can form
Coefficient matrix MV, wherein coefficient matrix is write by row are as follows:
All participants in S can cooperate to solve following equation group:
That is:
If S meets access structure, so that it may multinomial P (x) is reconstructed, to recover secret S；Further, this access knot
Structure can be equivalent to the access structure of the LSSS of hierarchical matrix, evenIt is defined as I={ j: ρ (j) ∈
S }, if enabledIt is a sub-secret of secret s, then there is constant { ωj∈ZNMake ∑j∈Iωjλj=s,
In,ZNIndicate 1 integer set for arriving N；ωjIn privacy sharing generator matrix MvThe polynomial time of size
It inside can always be found, so that it may recover main secret；
Step 2) includes the following steps:
2.1) enable access structure MVIt is j × t matrix；
2.2) random vector is selected Indicate appointing in 1 to N integer set
It anticipates t, wherein s indicates secret value, y1,......,yt-1For the sharing of secret value s；
2.3) it enables| S | indicate number of elements possessed by S, setting meets:
…
Wherein, U0,…,UmIndicate the 0th to m layer of set U, 0≤l0≤l1≤...≤lm=| S |, and if only if for all
0≤i≤m, there is li≥ki, liIndicate the number of elements for possessing set S in i-th layer, kiIndicate the number of elements of set S in i-th layer
Thresholding；
Then for all j=1 ..., l0,...,lm, calculateMjIndicate MVIn jth row；
2.4) for the hierachy number i ∈ { 0 ..., m } of attribute set U, j=l is seti-1+ c, l-1=0, c are constant, indicate i-th
C-th of attribute of layer, i.e. j-th of attribute in attribute set U correspond to i-th layer of c-th of attribute；
2.5) random number is selected
2.6) attribute of all levels is subjected to encryption by following formula and obtains ciphertext CT:
Wherein, hρ(j)Indicate that group element corresponding with a property element of ρ (j) in attribute set U, ρ (j) indicate attribute set U
The attribute of middle jth layer is to access structure MvJth row mapping.
3. cross-border e-commerce Video security monitoring method as described in claim 1, which is characterized in that camera is to image
In processing, using infrared binarization segmentation algorithm, comprising:
Step 1: being enhanced using algorithm of histogram equalization image degree of comparing；
In formula: DBFor the gray value after conversion；DAFor the gray value before conversion；HiFor the number of pixels of i-stage gray scale；A0For pixel
Sum draws two-dimensional gray histogram curve；
Step 2: setting f (x, y) is the two-dimensional gray histogram curve carried out after infrared image histogram equalization, wherein x is indicated
Grey level, y indicate the number that specific each grey level pixel occurs, seek gradient at point (x, y) to f (x, y):
In formula:For at point (x, y) f to the partial derivative of x；For
Partial derivative of the f to y at point (x, y)；Measurement of the amplitude of gradient as change rate size, value are as follows:
And for two-dimensional discrete function f (i, j), use finite difference as an approximation of gradient magnitude:
To simplify the calculation, above formula approximation simplifies are as follows:
The formula is the foundation that local threshold is chosen；
Step 3: seeking the shade of gray mean value obtained in second step:
In formula: k is striked shade of gray value number.Give up the part that shade of gray value is less than gradient mean value, retains gray scale ladder
Angle value is greater than the part of shade of gray mean value,
Wherein: m=1,2,3 ..., n；
In formula: m is to give up shade of gray less than the shade of gray value number after average gray gradient value；Shade of gray value is greater than ash
The pixel gray level of degree mean value is combined into a set, constitutes global threshold face, and global threshold face is to extract target principal outline
Datum level, using this threshold value face carry out infrared image binarization segmentation.
4. cross-border e-commerce Video security monitoring method as described in claim 1, which is characterized in that single-chip microcontroller is using improvement
PSO algorithm the picture of storage is handled, in basic PSO algorithm, w make particle keep motional inertia, so that it is had extension
The trend of search space, when w is larger, the movement velocity of particle is very fast, keeps the region of search of particle larger, and can make it more
Fast close global optimum's particle, when w is smaller, the movement velocity of particle is slow, and particle is enable to carry out in subrange finely
Search, is conducive to the convergence of algorithm, and w often takes dynamic to adjust thus；
Wherein: wmaxAnd wminIndicate inertia weight maximum and minimum value, t indicates the number of iterations, ItermaxIndicate greatest iteration time
Number.
5. cross-border e-commerce Video security monitoring method as described in claim 1, which is characterized in that single-chip microcontroller is to collecting
Various information classify, information classification use support vector machines fast classification algorithm, specifically include:
Given training sample set { (xi, yi), i=1,2 ..., l }, xi∈Rd, yi∈ { -1 ,+1 } is introduced from input space Rn to uncommon
The transformation of your Bert (Hilbert) space H:
Rn→H
Then primal problem is constructed in the H of the space Hilbert:
Termination condition:
Using Lagrange multiplier method solution formula (1), obtained dual problem are as follows:
Termination condition:
Wherein K (xi, xj) it is kernel function:
Optimal solution α is obtained by solving above-mentioned dual problem*=(α1 *..., αl *)T, choose the 0 < α of a positive component of α *j* < C, and
Threshold is calculated accordingly
b*=yj-∑yiαi *K(xi,xj), (5)
Finally construct decision function
Give two sample x1, x2∈RN, then the distance between two samples can be expressed as d (x1, x2),Indicate sample xl?
I component, in the case where linear, the distance between two samples are defined as follows:
Under nonlinear situation, the distance between two samples are defined as follows:
WhereinFor vector x in former space to be mapped to vector corresponding in high-dimensional vector space, For kernel function；
Assuming that a kind of sample is x1i, i=1 ..., l, another kind of sample is x2j, j=1, m, d (x1i, x2j) indicate first
I-th of sample in class to j-th of sample in the second class distance, then to each i value, di=mind (x1i,x2j) (j=
1,2, m), corresponding vector x2jIt is exactly a Margin Vector of the second class sample；
Distance screening is passed through to original sample, obtains the l initial training sample (x by retive boundary vector process1, y1) ...,
(xlyl), wherein xi∈Rn, i=1 ..., l, yi∈ { -1,1 } is sample xiAffiliated classification, m are the class number of training sample, if
The training sample set of k-th of support vector machines is combined into X={ (xi, yi)|yi>=k }, it obtains
Constraint condition:
Its dual problem is converted into be solved:
Obtain its corresponding decision function are as follows:
6. a kind of computer journey for realizing cross-border e-commerce Video security monitoring method described in Claims 1 to 5 any one
Sequence.
7. a kind of information data for realizing cross-border e-commerce Video security monitoring method described in Claims 1 to 5 any one
Processing terminal.
8. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed
Benefit requires cross-border e-commerce Video security monitoring method described in 1-5 any one.
9. a kind of cross-border e-commerce video safety monitoring system, which is characterized in that the cross-border e-commerce Video security prison
Control system is provided with
Remote computer；
The remote computer by conducting wire connect transmitter, foreign trade router, the transmitter by conducting wire connection camera,
Sound pick-up, data reader are connected with storage chip inside the transmitter, and the storage chip lower end is connected with single-chip microcontroller,
The single-chip microcontroller lower end is connected with ZigBee module.
10. cross-border e-commerce video safety monitoring system as claimed in claim 9, which is characterized in that the ZigBee module
Local network is connected by cable；
The VPN broadband server of the foreign trade router connects foreign countries local IP.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811205656.1A CN109461065A (en) | 2018-10-17 | 2018-10-17 | A kind of cross-border e-commerce video safety monitoring system and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811205656.1A CN109461065A (en) | 2018-10-17 | 2018-10-17 | A kind of cross-border e-commerce video safety monitoring system and control method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109461065A true CN109461065A (en) | 2019-03-12 |
Family
ID=65607754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811205656.1A Pending CN109461065A (en) | 2018-10-17 | 2018-10-17 | A kind of cross-border e-commerce video safety monitoring system and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109461065A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115631529A (en) * | 2022-12-16 | 2023-01-20 | 成方金融科技有限公司 | Face feature privacy protection method, face recognition method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050071236A1 (en) * | 2002-01-28 | 2005-03-31 | Innovative Aftermarket Systems, Lp | System and business method for memorializing vehicle purchase transactions |
| CN101619984A (en) * | 2009-07-28 | 2010-01-06 | 重庆邮电大学 | Mobile robot visual navigation method based on colorful road signs |
| CN105406967A (en) * | 2015-12-10 | 2016-03-16 | 西安电子科技大学 | Hierarchical attribute encryption method |
| CN108540475A (en) * | 2018-04-11 | 2018-09-14 | 湖南城市学院 | A kind of electronic communication system based on DSP |
-
2018
- 2018-10-17 CN CN201811205656.1A patent/CN109461065A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050071236A1 (en) * | 2002-01-28 | 2005-03-31 | Innovative Aftermarket Systems, Lp | System and business method for memorializing vehicle purchase transactions |
| CN101619984A (en) * | 2009-07-28 | 2010-01-06 | 重庆邮电大学 | Mobile robot visual navigation method based on colorful road signs |
| CN105406967A (en) * | 2015-12-10 | 2016-03-16 | 西安电子科技大学 | Hierarchical attribute encryption method |
| CN108540475A (en) * | 2018-04-11 | 2018-09-14 | 湖南城市学院 | A kind of electronic communication system based on DSP |
Non-Patent Citations (2)
| Title |
|---|
| 张龙，乔铁柱: "一种红外图像的二值化分割算法研究", 《红外技术》 * |
| 徐红敏，王若鹏，张怀念: "支持向量机的快速分类算法", 《北京石油化工学院学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115631529A (en) * | 2022-12-16 | 2023-01-20 | 成方金融科技有限公司 | Face feature privacy protection method, face recognition method and device |
| CN115631529B (en) * | 2022-12-16 | 2023-04-28 | 成方金融科技有限公司 | Face feature privacy protection method, face recognition method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11687384B2 (en) | Real-time synthetically generated video from still frames | |
| JP6594329B2 (en) | System and method for facial expression | |
| CN110502592B (en) | Project domain topic analysis system based on big data analysis technology | |
| US10990810B2 (en) | Automated facial recognition detection | |
| Akey Sungheetha | Classification of remote sensing image scenes using double feature extraction hybrid deep learning approach | |
| CN106030654A (en) | Face authentication system | |
| US20170323149A1 (en) | Rotation invariant object detection | |
| CN112446310A (en) | Age identification system, method and device based on block chain | |
| Niu et al. | Boundary-aware RGBD salient object detection with cross-modal feature sampling | |
| AU2015218184A1 (en) | Processing hyperspectral or multispectral image data | |
| CN109461065A (en) | A kind of cross-border e-commerce video safety monitoring system and control method | |
| Li et al. | A discriminative self‐attention cycle GAN for face super‐resolution and recognition | |
| CN108776972B (en) | Object tracking method and device | |
| Zeng et al. | Multi-view self-supervised learning for 3D facial texture reconstruction from single image | |
| Zhang et al. | Edge Detection from RGB‐D Image Based on Structured Forests | |
| Gireeshan et al. | RETRACTED ARTICLE: Feature reduced blind steganalysis using DCT and spatial transform on JPEG images with and without cross validation using ensemble classifiers | |
| KR20230006079A (en) | Method for face image transformation based on artificial intelligence learning | |
| Zhang et al. | Video denoising for security and privacy in fog computing | |
| Tiwari et al. | Performance improvement of image enhancement methods using statistical moving average histogram modification filter | |
| Wang et al. | Multi‐DS Strategy for Source Camera Identification in Few‐Shot Sample Data Sets | |
| Wang et al. | MDM-CPS: a few-shot sample approach for source camera identification | |
| CN116456127B (en) | Video processing system, method, device, electronic equipment and storage medium | |
| Yang et al. | Generative Target Tracking Method with Improved Generative Adversarial Network | |
| CN113706428B (en) | Image generation method and device | |
| US20220374891A1 (en) | Transaction data processing |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190312 |
|
| WD01 | Invention patent application deemed withdrawn after publication |