CN107792008A - A kind of intelligent vehicle-carried control terminal management system - Google Patents

A kind of intelligent vehicle-carried control terminal management system Download PDF

Info

Publication number
CN107792008A
CN107792008A CN201710900900.5A CN201710900900A CN107792008A CN 107792008 A CN107792008 A CN 107792008A CN 201710900900 A CN201710900900 A CN 201710900900A CN 107792008 A CN107792008 A CN 107792008A
Authority
CN
China
Prior art keywords
mrow
msub
roi region
palmmprint
msup
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.)
Granted
Application number
CN201710900900.5A
Other languages
Chinese (zh)
Other versions
CN107792008B (en
Inventor
韦彩霞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Haihui Motor Co ltd
Haihui New Energy Motor Co Ltd
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201710900900.5A priority Critical patent/CN107792008B/en
Publication of CN107792008A publication Critical patent/CN107792008A/en
Application granted granted Critical
Publication of CN107792008B publication Critical patent/CN107792008B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R25/00—Fittings or systems for preventing or indicating unauthorised use or theft of vehicles
    • B60R25/20—Means to switch the anti-theft system on or off
    • B60R25/25—Means to switch the anti-theft system on or off using biometry
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
    • B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
    • B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
    • B60R16/0231—Circuits relating to the driving or the functioning of the vehicle

Abstract

The present invention provides a kind of intelligent vehicle-carried control terminal management system, is related to field of vehicle control, including：Central processing unit, power module, vehicle carried data collecting module, output driving module and palmmprint processing module；The power module connects central processing unit, for central processing unit continued power；The vehicle carried data collecting module is used to gather vehicle-mounted data and the vehicle-mounted data collected is transferred into central processing unit；The output driving module connects central processing unit, the central processing unit connects palmmprint processing module, the palmmprint processing module is used to gather palmprint information and analyze and process palmprint information, obtained result of determination is transferred to central processing unit, the central processing unit sends from central processing unit to output driving module and instructed according to result of determination.So as to realize that user by freely operation of the palmprint information to automobile, lifts the security that automobile uses.

Description

A kind of intelligent vehicle-carried control terminal management system
Technical field
The present invention relates to mobile unit application field, more particularly to a kind of intelligent vehicle-carried control terminal management system.
Background technology
GPS vehicle-mounted control terminal management systems are to rely on the technological means such as satellite fix, geography information and radio communication, real When grasp vehicle location and status data, provide management and running information for logistics transportation industry.GPS vehicle-mounted control terminal management systems Typically it is made up of host module, antenna and optional accessory, wherein host module and antenna constitute the foundation of car-mounted terminal, Positioning in real time can be achieved, detect the basic function of longitude and latitude, time, direct of travel and speed, data-interface is left on main frame, can External equipment and sensor as needed, to realize the functional requirement of annex.Simultaneously GPS car-mounted terminals product using internet as Carrier, realize and connection is communicated between terminal and center, its message transmission rate is high, the bit error rate is low, reliable and stable, monitoring range Extensively, whole nation roaming monitoring can be achieved in Development by Depending on Network covering.But existing door-opening mode is cumbersome, because of GPS vehicle-mounted control terminal managements system System lacks palm print identification function, i.e., controls car door folding by the palmmprint of identification.
The content of the invention
A kind of in view of the above-mentioned problems, the present invention is intended to provide intelligent vehicle-carried control terminal management system.
The purpose of the present invention is realized using following technical scheme：
A kind of intelligent vehicle-carried control terminal management system, it is characterised in that including：Power module, vehicle carried data collecting mould Block, palmmprint processing module, central processing unit, output driving module；
The power module is used for central processing unit continued power；
The vehicle carried data collecting module is used to gather vehicle-mounted data and the vehicle-mounted data collected is transferred into centre Manage device；
The palmmprint processing module is used to gather palmprint information and the palmprint information to collecting is analyzed, and will obtain Result of determination be transferred to central processing unit；
The central processing unit is used for according to result of determination, and car door is sent from the central processing unit to output driving module Switching information；The central processing unit is additionally operable to carry out calculation process to vehicle-mounted data；
The output driving module connects the central processing unit, and the output driving module is according to residing for central processing unit The vehicle-mounted data of reason sends corresponding instruction to automobile.
Beneficial effects of the present invention：Using the technical scheme of built-in palmmprint processing module control circuit, pass through centre The processing of device is managed, the folding of car door is controlled, accurate control is made to car door, it is simple to operate, it is easy to use, not only avoid people Work is unlocked cumbersome and convenient and swift, agrees with the allegro theory of city life.
Brief description of the drawings
Fig. 1 is the frame construction drawing of the present invention；
Fig. 2 is the frame construction drawing of palmmprint processing module of the present invention.
Reference：
Central processing unit 1；Vehicle carried data collecting module 2；Power module 3；Palmmprint processing module 4；Output driving module 5； GPS module 6；Gsm module 7；Palmmprint collecting device 40；Palmprint preprocessing unit 41；Palmmprint enhancement unit 42；Palmmprint extraction unit 43；Personal recognition unit 44；Palm print database 45.
Embodiment
With reference to following application scenarios, the invention will be further described.
Referring to Fig. 1, a kind of intelligent vehicle-carried control terminal management system, it is characterised in that including：It is central processing unit 1, vehicle-mounted Data acquisition module 2, power module 3, palmmprint processing module 4, output driving module 5.
The power module 3 is used for the continued power of central processing unit 1.
The vehicle carried data collecting module 2 is used to gather vehicle-mounted data and the vehicle-mounted data collected is transferred into centre Manage device 1.
The palmmprint processing module 4 is used to gather palmprint information and the palmprint information to collecting is analyzed, and will To result of determination be transferred to central processing unit 1.
The central processing unit 1 is used for according to result of determination, is sent from the central processing unit 1 to output driving module 5 Door contact interrupter information；The central processing unit 1 is additionally operable to carry out calculation process to vehicle-mounted data.
The output driving module 5 connects the central processing unit 1, and the output driving module 5 is according to central processing unit 1 Handled vehicle-mounted data sends corresponding instruction to automobile.
Described intelligent vehicle-carried control terminal management system, in addition to GPS module 6 and gsm module 7；The GPS module 6 Be connected with gsm module 7 respectively at central processing unit 1, for gather GPS information and GSM information and will collect GPS information and GSM information is sent to central processing unit 1 and handled.
Preferably, the power module includes reduction voltage circuit, overvoltage crowbar and threshold voltage circuit.
Preferably, the central processing unit 1 is 32 high-speed microprocessors for being 300M, and is connect including RAM, FLASH and GPIO Mouthful.
Preferably, referring to Fig. 2, the palmmprint processing module 4 include palmmprint collecting device 40, palmprint preprocessing unit 41, Palmmprint enhancement unit 42, palmmprint extraction unit 43, personal recognition unit 44 and palm print database 45；The palmmprint collecting device 40 For gathering palmprint information；The palmprint preprocessing unit 41 is used to carry out denoising, the palmmprint to the palmprint information collected Enhancement unit 42 is used to carry out the palmprint information after denoising enhancing processing, and the palmmprint extraction unit 43 is used to handle from enhancing Palmmprint textural characteristics are extracted in palmprint information afterwards, palm print database 45 is used to store the default palmmprint texture spy trained Sign；The personal recognition unit 44 is used in the palmmprint textural characteristics and palm print database 45 that obtain palmmprint extraction unit 43 Default palmmprint textural characteristics are compared, and obtained result of determination is transferred into central processing unit 1.
The above embodiment of the present invention, using the technical scheme of built-in personal recognition module control circuit, pass through centre The processing of device is managed, the folding of car door is controlled, accurate control is made to car door, it is simple to operate, it is easy to use, not only avoid people Work is unlocked cumbersome and convenient and swift, agrees with the allegro theory of city life.
Preferably, it is 256 that the palmprint preprocessing unit 41, which is used to extract a size from the palmprint information collected, × 256 region of interest area image is ROI region, and carries out smooth operation to ROI region, removes making an uproar at random in ROI region Sound, the ROI region after obtaining smoothly, it is specially：
1) positioning of feature is carried out according to the position of collection palm and palm feature, is split from the palmprint image having good positioning Go out region of interest area image i.e. ROI region containing abundant palmprint information, that size is 256 × 256；
2) smooth operation is carried out to the ROI region for being fourier transformed to obtain using transfer function H (u, v), it transmits letter Counting formula is：
Wherein, if (p, q) is pixel point coordinates in ROI region, (u, v) is pixel (x, y) in ROI region through Fourier Respective coordinates in frequency domain after conversion, in ROI region；H (u, v) is transfer function values, D0For cut-off frequency, D (u, v) is To the Euclidean distance of coordinate points (u, v), n is transmission factor for the origin of coordinates in the frequency domain of ROI region, is one to be more than 0 just Integer；
The high fdrequency component that by transfer function H (u, v) ROI region can be made to be fourier transformed to obtain is decayed, i.e., Less than cut-off frequency D0All frequencies all by and being higher than cut-off frequency D0Frequency according to the Euclidean distance of point (u, v) and Cut-off frequency D0Ratio progressively decayed；
3) using inverse Fourier transform function by the ROI region after smoothing processing from frequency transformation to spatial domain in, you can ROI region after obtaining smoothly.
This preferred embodiment, the palmprint image collected is split first, choose one and include abundant texture spy The ROI region of reference breath, is advantageous to subsequently obtain more palmprint informations, is advantageous to the palmprint information subsequently through acquisition Personnel identity is recognized, improves the degree of accuracy and resolution, ROI region is put down using transfer function H (u, v) afterwards Sliding processing, can effectively remove the random noise in palmprint image, and retain the details of the palmmprint in ROI region, in height Frequency forms a smooth intermediate zone to low-frequency transition region, and the presence of the intermediate zone can efficiently avoid palmprint image The generation of middle ringing.
Preferably, the palmmprint enhancement unit 42 is used to perform blurring mapping to the ROI region after smooth, after smooth ROI region is transformed in fuzzy field, and forms a Fuzzy property domain, carries out nonlinear transformation processing in fuzzy field afterwards Fuzzy property domain is transformed in spatial domain with fuzzy inverse transformation, you can obtain the ROI region after enhancing processing, be specially：
1) using sinusoidal membership function will it is smooth after ROI region by space field transformation to fuzzy field, one mould of composition Characteristic plane is pasted, its customized sinusoidal membership function is：
Wherein, Wj,kIt is subordinate to angle value, X for ROI region (j, k) place after smoothj,kExist for the ROI region after smoothing processing The gray value at (j, k) place, XminFor the minimum gradation value of the ROI region after smoothing processing, XmaxFor the ROI region after smoothing processing Maximum gradation value, r is a customized positive integer；
All pixels point in ROI region after traversal is smooth, obtains the angle value that is subordinate to of all pixels point, all pixels point Be subordinate to angle value form vague plane be it is smooth after ROI region Fuzzy property domain W；
2) conversion process is carried out to the angle value that is subordinate to of all pixels point using a transforming function transformation function, you can obtain a new mould Characteristic plane W ＇ are pasted, its transforming function transformation function formula defined is：
Wj,k＇=Tr(Wj,k)=Tr(Tr-1(Wj,k)), r=1,2,3 ...
Wherein, Wj,k＇ is the fuzzy membership at point (j, k) place obtained by conversion, XcGet over a little to be customized；Tr (Wj,k) it is an operator；
3) to Wj,k＇ carries out nonlinear inversion transformation, will it is smooth after ROI region spatial domain is transformed to by fuzzy field, its inversion Changing formula is：
Travel through fuzzy field in institute a little, all Xj,kThe image of ＇ compositions is the ROI region after enhancing processing.
This preferred embodiment, ROI region is changed into fuzzy field by transform of spatial domain, and degree of membership become in fuzzy field Change, be subordinate to angle value by increase above fuzzy membership threshold value, reduce and be subordinate to angle value less than fuzzy membership threshold value, enter And reached the purpose of image enhaucament in fuzzy field, without maintaining the brightness of palmprint image in itself, and can press down well The random noise of the appearance in palmprint image is gathered is made.
Preferably, the ROI region progress feature extraction that the palmmprint extraction unit 43 is used for after handling enhancing, is increased ROI region size after palmmprint textural characteristics after the reason of strength, wherein enhancing processing is 256 × 256, is specially：
1) ROI region after being handled using convolutional neural networks model enhancing carries out feature extraction；Implementation method is：Will ROI region after enhancing processing uses size to be rolled up for 11 × 11 convolution filter to input picture as input picture Product operation, the characteristic pattern that 96 sizes are 55 × 55 is obtained, line translation and normalized are entered to the data that convolution obtains, it is returned One, which changes formula, is：
Wherein,Represent that ROI region pixel (x, y) i-th of place convolution filter after enhancing processing is rolled up by application Product assesses the neuronal activation degree calculated, and n is in the close convolution nuclear mapping number of same spatial location, and N is that convolution kernel is total Number.K, α, β are preset value,For normalized value；
Data after normalized are carried out with down-sampling, wherein down-sampling window is 3 × 3, step-length 2, has obtained 96 Individual size is 27 × 27 characteristic pattern；It is 5 × 5 × 48 wave filter to spy that 96 sizes are 27 × 27 to use 256 sizes Sign figure carries out convolution operation, obtains the characteristic pattern of 384 13 × 13；Use 256 sizes for 3 × 3 × 192 wave filter pair The characteristic pattern of 384 13 × 13 carries out convolution operation, 256 13 × 13 characteristic patterns is obtained, by obtain 256 13 × 13 features Figure carries out down-sampling operation, and wherein down-sampling window size is 3 × 3, step-length 2, obtains the feature that 256 sizes are 6 × 6 Figure；The pixel for 256 6 × 6 characteristic patterns that down-sampling is obtained forms a line, and carries out dimensionality reduction operation using neutral net, obtains To the output result of 4096 dimensions；After result after dimension-reduction treatment is input into full Connection Neural Network, output is at enhancing 4096 dimensional features of the ROI region after reason；
2) dimensionality reduction is carried out to the data of extraction using Principal Component Analysis Algorithm, the palmmprint texture obtained after enhancing processing is special Sign.
This preferred embodiment, when carrying out convolution operation to input picture, by using normalization formula to neuronal activation Degree is normalized, with the error rate for beneficial to the extensive of implementation model, reducing convolutional layer, meanwhile, when carrying out convolution, Overlapping pondization operation has been carried out, has avoided the generation of over-fitting, has employed full articulamentum neutral net extraction palmmprint Textural characteristics, the full articulamentum can be good at the global characteristics of palmprint image, while be advantageous to follow-up and default palmprint information Contrasted, central processing unit 1 sends to output driving module 7 instruct like clockwork according to according to comparing result.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected The limitation of scope is protected, although being explained in detail with reference to preferred embodiment to the present invention, one of ordinary skill in the art should Understand, technical scheme can be modified or equivalent substitution, without departing from the essence of technical solution of the present invention And scope.

Claims (6)

  1. A kind of 1. intelligent vehicle-carried control terminal management system, it is characterised in that including：Power module, vehicle carried data collecting module, Palmmprint processing module, central processing unit, output driving module；
    The power module is used for central processing unit continued power；
    The vehicle carried data collecting module is used to gather vehicle-mounted data and the vehicle-mounted data collected is transferred into central processing unit；
    The palmmprint processing module is used to gather palmprint information and the palmprint information to collecting is analyzed, and sentences what is obtained Determine result and be transferred to central processing unit；
    The central processing unit is used for according to result of determination, and door contact interrupter is sent from the central processing unit to output driving module Information；The central processing unit is additionally operable to carry out calculation process to vehicle-mounted data；
    The output driving module connects the central processing unit, and the output driving module is according to handled by central processing unit Vehicle-mounted data sends corresponding instruction to automobile.
  2. 2. intelligent vehicle-carried control terminal management system according to claim 1, it is characterised in that also including GPS module and Gsm module；The GPS module is connected with gsm module respectively at central processing unit, for gathering GPS information and GSM information and inciting somebody to action Collect GPS information and GSM information is sent to central processing unit and handled.
  3. 3. intelligent vehicle-carried control terminal management system according to claim 2, it is characterised in that the palmmprint processing module Including palmmprint collecting device, palmprint preprocessing unit, palmmprint enhancement unit, palmmprint extraction unit, personal recognition unit and palmmprint Database；The palmmprint collecting device is used to gather palmprint information；The palmprint preprocessing unit is used for the palmmprint to collecting Information carries out denoising, and the palmmprint enhancement unit is used to carry out the palmprint information after denoising enhancing processing, the palmmprint extraction Unit is used to from the palmprint information after enhancing processing extract palmmprint textural characteristics, and palm print database is used to store what is trained Default palmmprint textural characteristics；The personal recognition unit is used for the palmmprint textural characteristics and palmmprint number for obtaining palmmprint extraction unit It is analyzed according to the default palmmprint textural characteristics in storehouse, and obtained result of determination is transferred to central processing unit.
  4. 4. intelligent vehicle-carried control terminal management system according to claim 3, it is characterised in that the palmprint preprocessing list Member is used to extract the region of interest area image i.e. ROI region that a size is 256 × 256 from the palmprint information collected, and Smooth operation is carried out to ROI region, removes the random noise in ROI region, the ROI region after obtaining smoothly, is specially：
    1) positioning of feature is carried out according to the position of collection palm and palm feature, is partitioned into and contains from the palmprint image having good positioning Region of interest area image i.e. ROI region that have abundant palmprint information, that size is 256 × 256；
    2) smooth operation is carried out to the ROI region for being fourier transformed to obtain using transfer function H (u, v), its transmission function is public Formula is：
    <mrow> <mi>H</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>,</mo> <mi>v</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mfrac> <mn>1</mn> <mrow> <mn>1</mn> <mo>+</mo> <msup> <mrow> <mo>&amp;lsqb;</mo> <mfrac> <mrow> <mi>D</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>,</mo> <mi>v</mi> <mo>)</mo> </mrow> </mrow> <msub> <mi>D</mi> <mn>0</mn> </msub> </mfrac> <mo>&amp;rsqb;</mo> </mrow> <mrow> <mn>2</mn> <mi>n</mi> </mrow> </msup> </mrow> </mfrac> </mtd> <mtd> <mrow> <mi>D</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>,</mo> <mi>v</mi> <mo>)</mo> </mrow> <mo>&gt;</mo> <msub> <mi>D</mi> <mn>0</mn> </msub> </mrow> </mtd> </mtr> <mtr> <mtd> <mn>0</mn> </mtd> <mtd> <mrow> <mi>D</mi> <mrow> <mo>(</mo> <mi>u</mi> <mo>,</mo> <mi>v</mi> <mo>)</mo> </mrow> <mo>&amp;le;</mo> <msub> <mi>D</mi> <mn>0</mn> </msub> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
    Wherein, if (p, q) is pixel point coordinates in ROI region, (u, v) is that pixel (x, y) is fourier transformed in ROI region Afterwards, respective coordinates in frequency domain in ROI region；H (u, v) is transfer function values, D0For cut-off frequency, D (u, v) be For the origin of coordinates in the frequency domain of ROI region to the Euclidean distance of coordinate points (u, v), n is transmission factor, is one just whole more than 0 Number；
    The high fdrequency component that by transfer function H (u, v) ROI region can be made to be fourier transformed to obtain is decayed, that is, is less than Cut-off frequency D0All frequencies all by and being higher than cut-off frequency D0Euclidean distance and cut-off of the frequency according to point (u, v) Frequency D0Ratio progressively decayed；
    3) using inverse Fourier transform function by the ROI region after smoothing processing from frequency transformation to spatial domain in, you can obtain ROI region after smooth.
  5. 5. intelligent vehicle-carried control terminal management system according to claim 4, it is characterised in that the palmmprint enhancement unit For carrying out blurring mapping to the ROI region after smooth, will it is smooth after ROI region transform in fuzzy field, in fuzzy field Nonlinear transformation processing and fuzzy inverse transformation are carried out to the ROI region in fuzzy field, obtain the ROI region after enhancing processing, tool Body is：
    1) using sinusoidal membership function will it is smooth after ROI region by space field transformation to fuzzy field, its customized sine Membership function is：
    <mrow> <msub> <mi>W</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>=</mo> <msup> <mrow> <mo>&amp;lsqb;</mo> <mi>s</mi> <mi>i</mi> <mi>n</mi> <mrow> <mo>(</mo> <mfrac> <mrow> <msub> <mi>X</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>X</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> </mrow> </mfrac> <mo>&amp;times;</mo> <mfrac> <mi>&amp;pi;</mi> <mn>2</mn> </mfrac> <mo>)</mo> </mrow> <mo>&amp;rsqb;</mo> </mrow> <mi>a</mi> </msup> </mrow>
    Wherein, WJ, kIt is subordinate to angle value, X for ROI region pixel (j, k) place after smoothJ, kFor the ROI region after smoothing processing The gray value at middle pixel (j, k) place, XminFor the minimum gradation value of the ROI region after smoothing processing, XmaxAfter smoothing processing ROI region maximum gradation value, a is fuzzy field regulatory factor, for the picture material according to ROI region and image enhaucament mesh Sinusoidal membership function is modified；
    All pixels point in ROI region after traversal is smooth, obtain it is smooth after ROI region all pixels point be subordinate to angle value；
    2) conversion process is carried out to the angle value that is subordinate to of all pixels point using a transforming function transformation function, you can obtain a new fuzzy spy Plane W ' is levied, its transforming function transformation function formula defined is：
    WJ, k'=Tr(WJ, k)=Tr(Tr-1(WJ, k)), r=1,2,3...
    <mrow> <msub> <mi>T</mi> <mi>r</mi> </msub> <mrow> <mo>(</mo> <msub> <mi>W</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <mrow> <mn>2</mn> <msup> <mrow> <mo>(</mo> <msub> <mi>W</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </mtd> <mtd> <mrow> <mn>0</mn> <mo>&amp;le;</mo> <msub> <mi>W</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>&lt;</mo> <msub> <mi>X</mi> <mi>c</mi> </msub> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <mn>1</mn> <mo>-</mo> <mn>2</mn> <msup> <mrow> <mo>(</mo> <mn>1</mn> <mo>-</mo> <msub> <mi>W</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </mtd> <mtd> <mrow> <msub> <mi>X</mi> <mi>c</mi> </msub> <mo>&amp;le;</mo> <msub> <mi>W</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>&lt;</mo> <mn>1</mn> </mrow> </mtd> </mtr> </mtable> </mfenced> </mrow>
    Wherein, WJ, k' for the fuzzy membership angle value that is obtained by conversion, XcFor customized fuzzy membership threshold value；Tr(WJ, k) be One mapping function；
    3) to WJ, k' carry out nonlinear inversion transformation, will it is smooth after ROI region spatial domain is transformed to by fuzzy field, its inverse transformation is public Formula is：
    <mrow> <msup> <msub> <mi>X</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>&amp;prime;</mo> </msup> <mo>=</mo> <msup> <mi>T</mi> <mrow> <mo>-</mo> <mn>1</mn> </mrow> </msup> <mrow> <mo>(</mo> <msup> <msub> <mi>W</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>&amp;prime;</mo> </msup> <mo>)</mo> </mrow> <mo>=</mo> <msub> <mi>X</mi> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> <mo>+</mo> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>-</mo> <msub> <mi>X</mi> <mrow> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> <mo>)</mo> </mrow> <mo>&amp;times;</mo> <mi>a</mi> <mi>r</mi> <mi>c</mi> <mi>s</mi> <mi>i</mi> <mi>n</mi> <msup> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mrow> <mi>j</mi> <mo>,</mo> <mi>k</mi> </mrow> </msub> <mo>)</mo> </mrow> <msqrt> <mi>r</mi> </msqrt> </msup> <mo>&amp;times;</mo> <mfrac> <mn>2</mn> <mi>&amp;pi;</mi> </mfrac> </mrow>
    Wherein：XJ, k' it is the inverse transform function value obtained through inverse transformation；
    Travel through fuzzy field in institute a little, all XJ, kThe set of ' composition is the ROI region after enhancing processing.
  6. 6. intelligent vehicle-carried control terminal management system according to claim 5, it is characterised in that the palmmprint extraction unit Feature extraction is carried out for the ROI region after handling enhancing, the palmmprint textural characteristics after enhancing processing are obtained, wherein at enhancing ROI region size after reason is 256 × 256, is specially：
    1) ROI region after being handled using convolutional neural networks model enhancing carries out feature extraction；Implementation method is：Will enhancing ROI region after processing uses size to carry out convolution behaviour to input picture for 11 × 11 convolution filter as input picture Make, obtain the characteristic pattern that 96 sizes are 55 × 55, line translation and normalized are entered to the data that convolution obtains, it is normalized Formula is：
    <mrow> <msubsup> <mi>b</mi> <mrow> <mi>x</mi> <mo>,</mo> <mi>y</mi> </mrow> <mi>i</mi> </msubsup> <mo>=</mo> <msubsup> <mi>a</mi> <mrow> <mi>x</mi> <mo>,</mo> <mi>y</mi> </mrow> <mi>i</mi> </msubsup> <mo>/</mo> <msup> <mrow> <mo>(</mo> <mi>k</mi> <mo>+</mo> <mi>&amp;alpha;</mi> <munderover> <mo>&amp;Sigma;</mo> <mrow> <mi>max</mi> <mrow> <mo>(</mo> <mn>0</mn> <mo>,</mo> <mi>i</mi> <mo>-</mo> <mfrac> <mi>n</mi> <mn>2</mn> </mfrac> <mo>)</mo> </mrow> </mrow> <mrow> <mi>m</mi> <mi>a</mi> <mi>x</mi> <mrow> <mo>(</mo> <mi>N</mi> <mo>-</mo> <mn>1</mn> <mo>,</mo> <mi>i</mi> <mo>+</mo> <mfrac> <mi>n</mi> <mn>2</mn> </mfrac> <mo>)</mo> </mrow> </mrow> </munderover> <msup> <mrow> <mo>(</mo> <msubsup> <mi>a</mi> <mrow> <mi>x</mi> <mo>,</mo> <mi>y</mi> </mrow> <mi>i</mi> </msubsup> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mo>)</mo> </mrow> <mi>&amp;beta;</mi> </msup> </mrow>
    Wherein,Represent that ROI region pixel (x, y) i-th of place convolution filter after enhancing processing passes through using convolution kernel The neuronal activation degree calculated, n are that N is convolution kernel total number in same spatial location close convolution nuclear mapping number； K, α, β are preset value,For normalized value；
    Data after normalized are carried out with down-sampling, wherein down-sampling window is 3 × 3, step-length 2, has been obtained 96 big It is small be 27 × 27 characteristic pattern；It is 5 × 5 × 48 wave filter to characteristic pattern that 96 sizes are 27 × 27 to use 256 sizes Convolution operation is carried out, obtains the characteristic pattern of 384 13 × 13；It is 3 × 3 × 192 wave filter to 384 to use 256 sizes 13 × 13 characteristic pattern carries out convolution operation, obtains 256 13 × 13 characteristic patterns, obtain 256 13 × 13 characteristic patterns are entered Row down-sampling operates, and wherein down-sampling window size is 3 × 3, step-length 2, obtains the characteristic pattern that 256 sizes are 6 × 6；Will The pixel for 256 6 × 6 characteristic patterns that down-sampling obtains forms a line, and carries out dimensionality reduction operation using neutral net, obtains 4096 The output result of dimension；After result after dimension-reduction treatment is input into full Connection Neural Network, output is after enhancing is handled 4096 dimensional features of ROI region；
    2) dimensionality reduction is carried out to the data of extraction using Principal Component Analysis Algorithm, obtains the palmmprint textural characteristics after enhancing processing.
CN201710900900.5A 2017-09-28 2017-09-28 A kind of intelligent vehicle-carried control terminal management system Active CN107792008B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710900900.5A CN107792008B (en) 2017-09-28 2017-09-28 A kind of intelligent vehicle-carried control terminal management system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710900900.5A CN107792008B (en) 2017-09-28 2017-09-28 A kind of intelligent vehicle-carried control terminal management system

Publications (2)

Publication Number Publication Date
CN107792008A true CN107792008A (en) 2018-03-13
CN107792008B CN107792008B (en) 2018-10-12

Family

ID=61532845

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710900900.5A Active CN107792008B (en) 2017-09-28 2017-09-28 A kind of intelligent vehicle-carried control terminal management system

Country Status (1)

Country Link
CN (1) CN107792008B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109270394A (en) * 2018-10-16 2019-01-25 江苏佳源科技有限公司 A kind of intelligent low-pressure branch monitoring system
CN109670471A (en) * 2018-12-28 2019-04-23 广州市久邦数码科技有限公司 A kind of Palmprint feature extraction and palmistry recognition methods
CN113128511A (en) * 2021-03-31 2021-07-16 武汉钢铁有限公司 Coke tissue identification method and device

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060274921A1 (en) * 2003-04-04 2006-12-07 Lumidigm, Inc. Texture-biometrics sensor
CN101464945A (en) * 2008-11-14 2009-06-24 清华大学深圳研究生院 Identification characteristic identification method based on finger back arthrosis veins
CN102254188A (en) * 2011-08-04 2011-11-23 汉王科技股份有限公司 Palmprint recognizing method and device
CN203237210U (en) * 2013-05-14 2013-10-16 国家电网公司 Intelligent vehicle-mounted palmprint identification system
CN104228767A (en) * 2014-07-30 2014-12-24 哈尔滨工业大学深圳研究生院 Palm print authentication-based car starting method
CN105984429A (en) * 2015-02-04 2016-10-05 鸿富锦精密工业（深圳）有限公司 Power-free intelligent key, vehicle unlocking system and vehicle unlocking method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060274921A1 (en) * 2003-04-04 2006-12-07 Lumidigm, Inc. Texture-biometrics sensor
CN101464945A (en) * 2008-11-14 2009-06-24 清华大学深圳研究生院 Identification characteristic identification method based on finger back arthrosis veins
CN102254188A (en) * 2011-08-04 2011-11-23 汉王科技股份有限公司 Palmprint recognizing method and device
CN203237210U (en) * 2013-05-14 2013-10-16 国家电网公司 Intelligent vehicle-mounted palmprint identification system
CN104228767A (en) * 2014-07-30 2014-12-24 哈尔滨工业大学深圳研究生院 Palm print authentication-based car starting method
CN105984429A (en) * 2015-02-04 2016-10-05 鸿富锦精密工业（深圳）有限公司 Power-free intelligent key, vehicle unlocking system and vehicle unlocking method

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109270394A (en) * 2018-10-16 2019-01-25 江苏佳源科技有限公司 A kind of intelligent low-pressure branch monitoring system
CN109670471A (en) * 2018-12-28 2019-04-23 广州市久邦数码科技有限公司 A kind of Palmprint feature extraction and palmistry recognition methods
CN113128511A (en) * 2021-03-31 2021-07-16 武汉钢铁有限公司 Coke tissue identification method and device
CN113128511B (en) * 2021-03-31 2023-07-25 武汉钢铁有限公司 Coke tissue identification method and device

Also Published As

Publication number Publication date
CN107792008B (en) 2018-10-12

Similar Documents

Publication Publication Date Title
CN108573276B (en) Change detection method based on high-resolution remote sensing image
CN109508710A (en) Based on the unmanned vehicle night-environment cognitive method for improving YOLOv3 network
CN107792008B (en) A kind of intelligent vehicle-carried control terminal management system
CN105354866A (en) Polygon contour similarity detection method
US7567715B1 (en) System and method for representing and encoding images
CN101813475B (en) Method for adaptively detecting remote obstacle
CN101425137A (en) Face Image Fusion Method Based on Laplacian Pyramid
CN109816040B (en) Deep learning-based urban inland inundation water depth detection method
CN106846322B (en) The SAR image segmentation method learnt based on curve wave filter and convolutional coding structure
CN109447069A (en) Collecting vehicle information recognition methods and system towards intelligent terminal
CN104778457A (en) Video face identification algorithm on basis of multi-instance learning
CN105335975B (en) Polarization SAR image segmentation method based on low-rank decomposition and statistics with histogram
CN106683102A (en) SAR image segmentation method based on ridgelet filters and convolution structure model
CN106373146A (en) Target tracking method based on fuzzy learning
CN103714326A (en) One-sample face identification method
CN104680180A (en) Polarimetric SAR image classification method on basis of K-Means and sparse own coding
CN104732186A (en) Single sample face recognition method based on local subspace sparse representation
CN106897999A (en) Apple image fusion method based on Scale invariant features transform
CN102663724A (en) Method for detecting remote sensing image change based on adaptive difference images
CN106228136A (en) Panorama streetscape method for secret protection based on converging channels feature
CN105205460A (en) Face expression feature extraction and recognition method based on maximum direction encoding
CN108090913A (en) A kind of image, semantic dividing method based on object level Gauss-Markov random fields
CN108882152A (en) A kind of privacy of user guard method reported based on Path selection
CN104268513B (en) Road guides the acquisition methods and device of data
CN103661102A (en) Method and device for reminding passersby around vehicles in real time

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20180822

Address after: 276500 1 Rizhao East Road, Juxian Economic Development Zone, Rizhao City, Shandong

Applicant after: HAIHUI NEW ENERGY MOTOR Co.,Ltd.

Address before: 542800 the Guangxi Zhuang Autonomous Region Hezhou eight step area east road 155

Applicant before: Wei Caixia

GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20211229

Address after: 276500 No. 23, Caihong Road, Zhaoxian Town, Ju county, Rizhao City, Shandong Province

Patentee after: HAIHUI MOTOR Co.,Ltd.

Patentee after: HAIHUI NEW ENERGY MOTOR Co.,Ltd.

Address before: 276500 1 Rizhao East Road, Juxian Economic Development Zone, Rizhao City, Shandong

Patentee before: HAIHUI NEW ENERGY MOTOR Co.,Ltd.

PE01 Entry into force of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: An Intelligent Vehicle Control Terminal Management System

Effective date of registration: 20230614

Granted publication date: 20181012

Pledgee: Bank of Rizhao Co.,Ltd. Juxian sub branch

Pledgor: HAIHUI MOTOR Co.,Ltd.

Registration number: Y2023980043838