CN110390250A - The electron assistant method of view-based access control model detection - Google Patents
The electron assistant method of view-based access control model detection Download PDFInfo
- Publication number
- CN110390250A CN110390250A CN201910391318.XA CN201910391318A CN110390250A CN 110390250 A CN110390250 A CN 110390250A CN 201910391318 A CN201910391318 A CN 201910391318A CN 110390250 A CN110390250 A CN 110390250A
- Authority
- CN
- China
- Prior art keywords
- image
- piecemeal
- equipment
- biede
- xie
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000001914 filtration Methods 0.000 claims abstract description 43
- 238000010438 heat treatment Methods 0.000 claims abstract description 16
- 238000003384 imaging method Methods 0.000 claims abstract description 13
- 230000002708 enhancing effect Effects 0.000 claims description 19
- 238000005728 strengthening Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 4
- 230000010355 oscillation Effects 0.000 claims description 3
- 239000010453 quartz Substances 0.000 claims description 3
- 230000002787 reinforcement Effects 0.000 claims description 3
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 3
- 230000003014 reinforcing effect Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000009514 concussion Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4023—Scaling of whole images or parts thereof, e.g. expanding or contracting based on decimating pixels or lines of pixels; based on inserting pixels or lines of pixels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/593—Recognising seat occupancy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30268—Vehicle interior
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of electron assistant methods of view-based access control model detection, it include: to use position extract equipment, one or more imaging regions where identifying one or more human body heads respectively from Real-Time Filtering image based on human body head imaging features, and the interior seat number where determining corresponding human body head in the relative position in the Real-Time Filtering image based on each imaging region；Using specific aim heating equipment, the seat for numbering corresponding car to each the interior seat received executes heating movement.
Description
Technical field
The present invention relates to a kind of electron assistant methods that field of visual inspection more particularly to view-based access control model detect.
Background technique
Vision-based detection is exactly to replace human eye with machine to measure and judge.Vision-based detection, which refers to, passes through machine vision product
(i.e. image-pickup device is divided to two kinds of CMOS and CCD) will be ingested target and be converted into picture signal, send at dedicated image
Reason system is transformed into digitized signal according to the information such as pixel distribution and brightness, color；Picture system carries out these signals
Clarification of objective is extracted in various operations, and then the device action at scene is controlled according to the result of differentiation.It is for producing, filling
The valuable mechanism matched or packed.It has in detection defect and in terms of preventing faulty goods to be dispensed into the function of consumer
Immeasurable value.
The characteristics of Machine Vision Detection is the flexibility and the degree of automation for improving production.It is not suitable for manual work some
Dangerous work environment or artificial vision be difficult to the occasion met the requirements, machine in normal service vision substitutes artificial vision；Exist simultaneously
In high-volume industrial processes, manually visual inspection product quality low efficiency and precision is not high, with Machine Vision Detection side
Method can greatly improve the degree of automation of production efficiency and production.And machine vision is easily achieved information integration, is to realize
The basic technology of computer integrated manufacturing system.
Summary of the invention
The present invention has inventive point crucial at following two:
(1) in view of on sedan seat whether there is human body detected used by weight sensor precision it is not high,
Use specific aim vision-based detection mechanism to improve human testing precision, to ensure that the accuracy of seat heating；
(2) it when executing identification maneuver failure in the image after Xie Biede interpolation processing, returns in Xie Biede interpolation processing
The real time enhancing movement to image is realized before, and the image after real time enhancing acts is executed again at Xie Biede interpolation
Reason, to reach balance between recognition effect and operand.
According to an aspect of the present invention, a kind of electron assistant method of view-based access control model detection is provided, which comprises make
With position extract equipment, be arranged in the instrument board of car, connect with wavelet filtering equipment, based on human body head imaging features from
One or more imaging regions where identifying one or more human body heads respectively in Real-Time Filtering image, and based on each
Interior seat where a imaging region determines corresponding human body head in the relative position in the Real-Time Filtering image is numbered；
It using specific aim heating equipment, is connect with the position extract equipment, for each the interior seat number pair received
The seat for the car answered executes heating movement, and stops executing to the seat for not receiving the accordingly car of interior seat number and add
Heat movement；Using miniature capture device, the central location of the roof of car is set, for taking scene to car below
Image capture operation is carried out, to obtain seating scene image；Equipment is adjusted using color range, the attached of miniature capture device is set
Closely, it is connect with the miniature capture device, takes scene image for receiving, color range adjustment is executed to the seating scene image
Processing, to obtain and export corresponding color range adjustment image；Using Xie Biede interpolation apparatus, connect with color range adjustment equipment
It connects, for receiving color range adjustment image, Xie Biede interpolation processing is executed to color range adjustment image, is thanked not with obtaining and exporting
Moral interpolation image；Chip is handled using ARM11, is connect with the Xie Biede interpolation apparatus, for being based on preset benchmark human body
Head shape executes shape matching to the Xie Biede interpolation image, to issue when being matched to corresponding human body head region
First drive command；The ARM11 processing chip is used for when not being matched to corresponding human body head region, issues the second driving
Order.
The electron assistant method control of view-based access control model detection of the invention is effective, convenient and practical.Due in view of to car seat
On position with the presence or absence of human body detected used by weight sensor precision it is not high, use specific aim vision-based detection mechanism with
Human testing precision is improved, to ensure that the accuracy of seat heating.
Specific embodiment
Embodiment of the present invention will be described in detail below.
Car, certain areas claim caravan or private car, and Amerenglish is known as Sedan, are then known as Saloon in Britain, usually
Refer to the automobile for personnel and luggage traffic.Car is in addition to passenger compartment, the headstock and the tailstock of visible obvious length in appearance, because
This can clearly tell engine chamber from shape, and (certain areas claim the classification of this shape for personnel's passenger compartment and luggage compartment
Be three compartments).Its external form of car has length to hold similar to ancient times dooly (England dooly is referred to as Sedan chairs) passenger compartment front and back
Handle, therefore named is " car ".Sometimes, car refers in particular to the kart for being different from lorry, pick up, SUV, bus and mini-bus,
It is commonly called as " car ".In Hong Kong, car is also known as private car, is the most commonly used vehicles, is used for manned and luggage.Including
Including driver, seating capacity is no more than 9, it is divided again with different types.
Currently, in order to guarantee that passenger is capable of providing warm seating environment, some sedan-chairs when cold snap is taken
Vehicle is to auxiliary heating mechanism is provided with below each seat, in order to passenger when sedan air conditioner just starts or weather is non-
Additional heat is obtained when Chang Hanleng, however, carrying out detecting used weight with the presence or absence of passenger on sedan seat at present
The precision of sensor is not high.
In order to overcome above-mentioned deficiency, the present invention has built a kind of electron assistant method of view-based access control model detection, can be effective
Solve corresponding technical problem.
Show according to an embodiment of the present invention view-based access control model detection electron assistant platform include:
Position extract equipment, is arranged in the instrument board of car, connect with wavelet filtering equipment, is imaged based on human body head
Feature identifies one or more imaging regions where one or more human body heads difference, and base from Real-Time Filtering image
Interior seat where each imaging region determines corresponding human body head in the relative position in the Real-Time Filtering image
Chair number；
Specific aim heating equipment is connect with the position extract equipment, for compiling to each the interior seat received
The seat of number corresponding car executes heating movement, and holds to the seat stopping for the car for not receiving corresponding interior seat number
Row heating movement；
The central location of the roof of car is arranged in miniature capture device, for below car take scene into
Row image capture operation, to obtain seating scene image；
Color range adjusts equipment, is arranged near miniature capture device, connect with the miniature capture device, for receiving
Scene image is taken, color range adjustment processing is executed to the seating scene image, to obtain and export corresponding color range adjustment figure
Picture；
Xie Biede interpolation apparatus is connect with color range adjustment equipment, for receiving color range adjustment image, to the color range
It adjusts image and executes Xie Biede interpolation processing, to obtain and export Xie Biede interpolation image；
ARM11 handles chip, connect with the Xie Biede interpolation apparatus, for being based on preset benchmark human head shapes
Shape matching is executed to the Xie Biede interpolation image, when being matched to corresponding human body head region, to issue the first driving
Order；
The ARM11 processing chip is used for when not being matched to corresponding human body head region, issues the second drive command；
Real time enhancing equipment is connect, for connecing respectively with the Xie Biede interpolation apparatus and ARM11 processing chip
When receiving second drive command, Real-time image enhancement processing is executed to color range adjustment image, to obtain real time enhancing
Image, and the real time enhancing image is sent to Xie Biede interpolation apparatus；
The Xie Biede interpolation apparatus is also used to when receiving real time enhancing image, is executed to the real time enhancing image
Xie Biede interpolation processing, to obtain and export quadratic interpolation image；
The Xie Biede interpolation apparatus is also used to when receiving first drive command, by the Xie Biede interpolation graphs
As being exported directly as quadratic interpolation image；
Wavelet filtering equipment is connect with the Xie Biede interpolation apparatus, for receiving the quadratic interpolation image, and to institute
It states quadratic interpolation image and executes wavelet filtering processing to obtain and export Real-Time Filtering image.
Then, continue to carry out further the specific structure of the electron assistant platform of view-based access control model detection of the invention
It is bright.
In the electron assistant platform of the view-based access control model detection:
The wavelet filtering equipment, ARM11 processing chip, the Xie Biede interpolation apparatus and color range adjustment are set
The standby and described real time enhancing equipment is used in conjunction with same quartz oscillation equipment.
Can also include: in the electron assistant platform of the view-based access control model detection
Contour searching equipment is connect with the miniature capture device, for receiving the seating scene image, is multiplied to described
It sits scene image and carries out uniform formula piecemeal processing, to obtain each image block, following operation is executed to each image block:
It detects whether each point in described image piecemeal is marginal point, the quantity of the marginal point in described image piecemeal is counted, when described
When the quantity of marginal point is more than or equal to preset quantity threshold value, described image piecemeal is labeled as profile piecemeal, and work as the side
When the quantity of edge point is less than the preset quantity threshold value, described image piecemeal is labeled as non-profile piecemeal.
Can also include: in the electron assistant platform of the view-based access control model detection
Directional process equipment is connect with the Contour searching equipment, for receiving each profile piecemeal and each non-wheel
Wide piecemeal executes following operation for each profile piecemeal: measuring the contrast of the profile piecemeal, be based on the contrast
The high frequency distribution frequency range in the profile piecemeal is determined, using the target frequency bands as the profile piecemeal, to the profile piecemeal
The high-pass filtering processing based on the target frequency bands is executed, to obtain corresponding high-pass filtering piecemeal, is also used to the profile
Piecemeal subtracts the high-pass filtering piecemeal pixel-by-pixel, to obtain and export corresponding low-pass filtering piecemeal, to the high-pass filtering
Piecemeal carries out feature reinforcement processing, reinforces piecemeal to obtain and export corresponding feature, is also used to the feature reinforcing piecemeal
It is added pixel-by-pixel with the low-pass filtering piecemeal, to obtain the corresponding local strengthening piecemeal of the profile piecemeal.
Can also include: in the electron assistant platform of the view-based access control model detection
Image restorer adjusts equipment with the color range respectively and the directional process equipment is connect, each for receiving
A non-profile piecemeal, and the corresponding each local strengthening piecemeal of each profile piecemeal is received, by each non-profile
Piecemeal and each local strengthening piecemeal are integrated, and to obtain piecemeal integral image, and the piecemeal integral image are replaced institute
It states seating scene image and is sent to the color range adjustment equipment；
Wherein, in described image restorer, the size of the piecemeal integral image and the seating scene image
Size is consistent.
Show according to an embodiment of the present invention view-based access control model detection electron assistant method include:
Using position extract equipment, it is arranged in the instrument board of car, is connect with wavelet filtering equipment, is based on human body head
Imaging features identify one or more imaging regions where one or more human body heads difference from Real-Time Filtering image,
And the vehicle where based on each imaging region determining corresponding human body head in the relative position in the Real-Time Filtering image
Interior seat number；
It using specific aim heating equipment, is connect with the position extract equipment, for each the interior seat received
The seat that chair numbers corresponding car executes heating movement, and stops to the seat for the car for not receiving corresponding interior seat number
Only execute heating movement；
Using miniature capture device, the central location of the roof of car is set, for taking field to car below
Scape carries out image capture operation, to obtain seating scene image；
Equipment is adjusted using color range, is arranged near miniature capture device, is connect, be used for the miniature capture device
It receives and takes scene image, color range adjustment processing is executed to the seating scene image, to obtain and export corresponding color range tune
Whole image；
It using Xie Biede interpolation apparatus, is connect with color range adjustment equipment, for receiving color range adjustment image, to described
Color range adjusts image and executes Xie Biede interpolation processing, to obtain and export Xie Biede interpolation image；
Chip is handled using ARM11, is connect with the Xie Biede interpolation apparatus, for being based on preset benchmark human body head
Shape executes shape matching to the Xie Biede interpolation image, to issue first when being matched to corresponding human body head region
Drive command；
The ARM11 processing chip is used for when not being matched to corresponding human body head region, issues the second drive command；
Using real time enhancing equipment, it connect, is used for the Xie Biede interpolation apparatus and ARM11 processing chip respectively
When receiving second drive command, Real-time image enhancement processing is executed to color range adjustment image, it is real-time to obtain
Enhance image, and the real time enhancing image is sent to Xie Biede interpolation apparatus；
The Xie Biede interpolation apparatus is also used to when receiving real time enhancing image, is executed to the real time enhancing image
Xie Biede interpolation processing, to obtain and export quadratic interpolation image；
The Xie Biede interpolation apparatus is also used to when receiving first drive command, by the Xie Biede interpolation graphs
As being exported directly as quadratic interpolation image；
Using wavelet filtering equipment, it is connect with the Xie Biede interpolation apparatus, for receiving the quadratic interpolation image, and
Wavelet filtering processing is executed to obtain and export Real-Time Filtering image to the quadratic interpolation image.
Then, continue to carry out further the specific steps of the electron assistant method of view-based access control model detection of the invention
It is bright.
In the electron assistant method of the view-based access control model detection:
The wavelet filtering equipment, ARM11 processing chip, the Xie Biede interpolation apparatus and color range adjustment are set
The standby and described real time enhancing equipment is used in conjunction with same quartz oscillation equipment.
The electron assistant method of view-based access control model detection can also include:
It using Contour searching equipment, is connect with the miniature capture device, for receiving the seating scene image, to institute
It states and takes the uniform formula piecemeal processing of scene image progress, it is following to the execution of each image block to obtain each image block
Operation: whether each point is marginal point in detection described image piecemeal, counts the quantity of the marginal point in described image piecemeal, when
When the quantity of the marginal point is more than or equal to preset quantity threshold value, described image piecemeal is labeled as profile piecemeal, and work as institute
When stating the quantity of marginal point less than the preset quantity threshold value, described image piecemeal is labeled as non-profile piecemeal.
The electron assistant method of view-based access control model detection can also include:
It using directional process equipment, is connect with the Contour searching equipment, for receiving each profile piecemeal and each
Non- profile piecemeal executes following operation for each profile piecemeal: the contrast of the profile piecemeal is measured, based on described right
The high frequency distribution frequency range in the profile piecemeal is determined than degree, using the target frequency bands as the profile piecemeal, to the profile
Piecemeal executes the high-pass filtering processing based on the target frequency bands, and to obtain corresponding high-pass filtering piecemeal, being also used to will be described
Profile piecemeal subtracts the high-pass filtering piecemeal pixel-by-pixel, to obtain and export corresponding low-pass filtering piecemeal, to the high pass
It filters piecemeal and carries out feature reinforcement processing, reinforce piecemeal to obtain and export corresponding feature, be also used to reinforce the feature
Piecemeal is added pixel-by-pixel with the low-pass filtering piecemeal, to obtain the corresponding local strengthening piecemeal of the profile piecemeal.
The electron assistant method of view-based access control model detection can also include:
Using image restorer, equipment is adjusted with the color range respectively and the directional process equipment is connect, for connecing
Each non-profile piecemeal is received, and receives the corresponding each local strengthening piecemeal of each profile piecemeal, it will be described each non-
Profile piecemeal and each local strengthening piecemeal are integrated, and to obtain piecemeal integral image, and the piecemeal integral image are replaced
It changes the seating scene image and is sent to the color range adjustment equipment；
Wherein, in described image restorer, the size of the piecemeal integral image and the seating scene image
Size is consistent.
In addition, small echo (Wavelet) this term, as its name suggests, " small echo " is exactly small waveform.It is so-called " small " to refer to him
With Decay Rate；And it is referred to as the fluctuation that " wave " then refers to it, the concussion form of amplitude alternate positive and negative.Become with Fourier
Commutation ratio, wavelet transformation are the localization analyses of time (space) frequency, he by flexible shift operations to signal (function) by
Step carries out multi-scale refinement, is finally reached high frequency treatment time subdivision, and frequency is segmented at low frequency, can adapt to time frequency signal analysis automatically
Requirement, so as to focus on any details of signal, solve Fourier transformation difficult problem, become after Fourier become
Important breakthrough since changing in scientific method.Wavelet transformation is called " school microscop " by someone.Wavelet analysis application be
Theoretical research with wavelet analysis is bound tightly together ground.He achieves in scientific and technological information industrial field and attracts people's attention
Achievement.Electronic information technology is a field important in six big new and high technologies, his importance is at image and signal
Reason.Now, signal processing has become the pith of contemporary science and technology work, and the purpose of signal processing is exactly: accurately
Analysis, diagnosis, coding compression and quantization, quickly transmitting or storage, accurately reconstruct (or recovery).From the point of view of mathematically angle,
Signal and image procossing can uniformly regard signal processing (image can be regarded as 2D signal) as, in wavelet analysis many
In many applications of analysis, signal processing problems can be attributed to.It is to stablize constant signal at any time for its property, place
The ideal tools of reason are still Fourier analysis.But most signals in practical applications are non-stable, and special
Tool suitable for unstable signal is exactly wavelet analysis.
It is last it is noted that each function device in each embodiment of the present invention can integrate and set in a processing
In standby, it is also possible to each equipment and physically exists alone, it can also be with two or more integration of equipments within one device.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function equipment
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. a kind of electron assistant method of view-based access control model detection, which is characterized in that the described method includes:
Using position extract equipment, it is arranged in the instrument board of car, is connect with wavelet filtering equipment, is imaged based on human body head
Feature identifies one or more imaging regions where one or more human body heads difference, and base from Real-Time Filtering image
Interior seat where each imaging region determines corresponding human body head in the relative position in the Real-Time Filtering image
Chair number；
It using specific aim heating equipment, is connect with the position extract equipment, for being compiled to each the interior seat received
The seat of number corresponding car executes heating movement, and holds to the seat stopping for the car for not receiving corresponding interior seat number
Row heating movement；
Using miniature capture device, the central location of the roof of car is set, for below car take scene into
Row image capture operation, to obtain seating scene image；
Equipment is adjusted using color range, is arranged near miniature capture device, is connect with the miniature capture device, for receiving
Scene image is taken, color range adjustment processing is executed to the seating scene image, to obtain and export corresponding color range adjustment figure
Picture；
It using Xie Biede interpolation apparatus, is connect with color range adjustment equipment, for receiving color range adjustment image, to the color range
It adjusts image and executes Xie Biede interpolation processing, to obtain and export Xie Biede interpolation image；
Chip is handled using ARM11, is connect with the Xie Biede interpolation apparatus, for being based on preset benchmark human head shapes
Shape matching is executed to the Xie Biede interpolation image, when being matched to corresponding human body head region, to issue the first driving
Order；
The ARM11 processing chip is used for when not being matched to corresponding human body head region, issues the second drive command；
Using real time enhancing equipment, it is connect respectively with the Xie Biede interpolation apparatus and ARM11 processing chip, for connecing
When receiving second drive command, Real-time image enhancement processing is executed to color range adjustment image, to obtain real time enhancing
Image, and the real time enhancing image is sent to Xie Biede interpolation apparatus；
The Xie Biede interpolation apparatus is also used to when receiving real time enhancing image, is thanked not real time enhancing image execution
Moral interpolation processing, to obtain and export quadratic interpolation image；
The Xie Biede interpolation apparatus is also used to when receiving first drive command, and the Xie Biede interpolation image is straight
It connects and is exported as quadratic interpolation image；
It using wavelet filtering equipment, is connect with the Xie Biede interpolation apparatus, for receiving the quadratic interpolation image, and to institute
It states quadratic interpolation image and executes wavelet filtering processing to obtain and export Real-Time Filtering image.
2. the electron assistant method of view-based access control model detection as described in claim 1, it is characterised in that:
The wavelet filtering equipment, the ARM11 processing chip, the Xie Biede interpolation apparatus and the color range adjustment equipment and
The real time enhancing equipment is used in conjunction with same quartz oscillation equipment.
3. the electron assistant method of view-based access control model detection as claimed in claim 2, which is characterized in that the method also includes:
It using Contour searching equipment, connect with the miniature capture device, for receiving the seating scene image, multiplies to described
It sits scene image and carries out uniform formula piecemeal processing, to obtain each image block, following operation is executed to each image block:
It detects whether each point in described image piecemeal is marginal point, the quantity of the marginal point in described image piecemeal is counted, when described
When the quantity of marginal point is more than or equal to preset quantity threshold value, described image piecemeal is labeled as profile piecemeal, and work as the side
When the quantity of edge point is less than the preset quantity threshold value, described image piecemeal is labeled as non-profile piecemeal.
4. the electron assistant method of view-based access control model detection as claimed in claim 3, which is characterized in that the method also includes:
It using directional process equipment, is connect with the Contour searching equipment, for receiving each profile piecemeal and each non-wheel
Wide piecemeal executes following operation for each profile piecemeal: measuring the contrast of the profile piecemeal, be based on the contrast
The high frequency distribution frequency range in the profile piecemeal is determined, using the target frequency bands as the profile piecemeal, to the profile piecemeal
The high-pass filtering processing based on the target frequency bands is executed, to obtain corresponding high-pass filtering piecemeal, is also used to the profile
Piecemeal subtracts the high-pass filtering piecemeal pixel-by-pixel, to obtain and export corresponding low-pass filtering piecemeal, to the high-pass filtering
Piecemeal carries out feature reinforcement processing, reinforces piecemeal to obtain and export corresponding feature, is also used to the feature reinforcing piecemeal
It is added pixel-by-pixel with the low-pass filtering piecemeal, to obtain the corresponding local strengthening piecemeal of the profile piecemeal.
5. the electron assistant method of view-based access control model detection as claimed in claim 4, which is characterized in that the method also includes:
Using image restorer, equipment is adjusted with the color range respectively and the directional process equipment is connect, it is each for receiving
A non-profile piecemeal, and the corresponding each local strengthening piecemeal of each profile piecemeal is received, by each non-profile
Piecemeal and each local strengthening piecemeal are integrated, and to obtain piecemeal integral image, and the piecemeal integral image are replaced institute
It states seating scene image and is sent to the color range adjustment equipment；
Wherein, in described image restorer, the size of the piecemeal integral image and the size for taking scene image
Unanimously.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910391318.XA CN110390250B (en) | 2019-05-12 | 2019-05-12 | Electronic auxiliary method based on visual detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910391318.XA CN110390250B (en) | 2019-05-12 | 2019-05-12 | Electronic auxiliary method based on visual detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110390250A true CN110390250A (en) | 2019-10-29 |
| CN110390250B CN110390250B (en) | 2021-01-26 |
Family
ID=68285306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910391318.XA Active CN110390250B (en) | 2019-05-12 | 2019-05-12 | Electronic auxiliary method based on visual detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110390250B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150186736A1 (en) * | 2013-12-27 | 2015-07-02 | Foundation of Soongsil University-lndustry Cooperation | Method of detecting pedestrians using integral image of feature information, computer readable recording medium, and terminal device for the same |
| CN105096280A (en) * | 2015-06-17 | 2015-11-25 | 浙江宇视科技有限公司 | Method and device for processing image noise |
| CN108016386A (en) * | 2017-12-29 | 2018-05-11 | 爱驰汽车有限公司 | Environment inside car configuration system, device, method, equipment and storage medium |
| CN108319933A (en) * | 2018-03-19 | 2018-07-24 | 广东电网有限责任公司中山供电局 | A kind of substation's face identification method based on DSP technologies |
-
2019
- 2019-05-12 CN CN201910391318.XA patent/CN110390250B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150186736A1 (en) * | 2013-12-27 | 2015-07-02 | Foundation of Soongsil University-lndustry Cooperation | Method of detecting pedestrians using integral image of feature information, computer readable recording medium, and terminal device for the same |
| CN105096280A (en) * | 2015-06-17 | 2015-11-25 | 浙江宇视科技有限公司 | Method and device for processing image noise |
| CN108016386A (en) * | 2017-12-29 | 2018-05-11 | 爱驰汽车有限公司 | Environment inside car configuration system, device, method, equipment and storage medium |
| CN108319933A (en) * | 2018-03-19 | 2018-07-24 | 广东电网有限责任公司中山供电局 | A kind of substation's face identification method based on DSP technologies |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110390250B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110194085B (en) | The electron assistant platform of view-based access control model detection | |
| CN107230218B (en) | Method and apparatus for generating confidence measures for estimates derived from images captured by vehicle-mounted cameras | |
| CN106462968B (en) | Method and device for calibrating a camera system of a motor vehicle | |
| CN108139484A (en) | The control method of range unit and range unit | |
| CN103593981B (en) | A kind of model recognizing method based on video | |
| US20200304774A1 (en) | Method and device for detecting height-limiting rod, and automatic driving system | |
| CN107702663A (en) | A kind of point cloud registration method based on the rotation platform with index point | |
| JP6738079B1 (en) | Asphalt mixture component information estimation system, asphalt plant, and asphalt mixture component information estimation method | |
| CN109977954A (en) | The identification of electric vehicle charge interface and localization method and system | |
| CN115272655A (en) | Multi-type battery pack visual positioning method and system device for battery replacement robot | |
| DE102022126464A1 (en) | SYSTEM FOR CALIBRATION OF EXTRINSICAL PARAMETERS FOR A CAMERA IN AN AUTONOMOUS VEHICLE | |
| CN111242888A (en) | Image processing method and system based on machine vision | |
| CN107085869B (en) | A kind of vehicle that the data handling system based on Internet of Things and cloud computing is set | |
| US10706589B2 (en) | Vision system for a motor vehicle and method of controlling a vision system | |
| CN110738668B (en) | Method and system for intelligently controlling high beam and vehicle | |
| CN110390250A (en) | The electron assistant method of view-based access control model detection | |
| CN110285870A (en) | Vehicle spindle-type and wheel number determination method and its system | |
| US20220396322A1 (en) | Image based trailer wheelbase determination | |
| EP3486871B1 (en) | A vision system and method for autonomous driving and/or driver assistance in a motor vehicle | |
| CN117058151B (en) | Hub detection method and system based on image analysis | |
| CN111415378A (en) | Image registration method for automobile glass detection and automobile glass detection method | |
| CN105129295A (en) | Reversing control method, device and system and garbage transfer truck | |
| CN113177557B (en) | Bowling prevention method and system based on machine vision and deep learning | |
| CN106909936A (en) | A kind of vehicle checking method based on double vehicle deformable part models | |
| CN113044045A (en) | Self-adaptive adjustment method for seats in intelligent cockpit |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Han Tao Inventor after: Yu Baozhong Inventor after: Yuan Fen Inventor before: Yuan Fen |
|
| CB03 | Change of inventor or designer information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201228 Address after: 1224, 1st floor, No.1 Kaifa Road, Shangdi Information Industry base, Haidian District, Beijing Applicant after: KangQian Dacheng (Beijing) Technology Co.,Ltd. Address before: 221000 No.200 Jiefang South Road, Quanshan District, Xuzhou City, Jiangsu Province Applicant before: Yuan Fen |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |