CN107292264B - A kind of information processing method and electronic equipment - Google Patents
A kind of information processing method and electronic equipment Download PDFInfo
- Publication number
- CN107292264B CN107292264B CN201710466610.4A CN201710466610A CN107292264B CN 107292264 B CN107292264 B CN 107292264B CN 201710466610 A CN201710466610 A CN 201710466610A CN 107292264 B CN107292264 B CN 107292264B
- Authority
- CN
- China
- Prior art keywords
- information
- information processing
- multispectral
- target
- verification
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
Abstract
The present invention relates to a kind of information processing processing method and electronic equipments more particularly to a kind of information processing method and electronic equipment differentiated to target.This method includes:Multispectral information handling step, directivity information processing step, analytical procedure, step display.The electronic equipment includes:Multispectral information processing unit, directivity information processing unit, analytical equipment, display device.By this method and electronic equipment, redundancy feature can be removed, obtained to differentiating contributive feature, so as to improve the speed of differentiation, precision and accuracy.
Description
Technical field
The invention belongs to image domains, are related to a kind of information processing method and electronic equipment, and in particular, to a kind of to mesh
The information processing method and electronic equipment that target structure and classification are differentiated.
Background technology
Having great importance in actual life is differentiated to the structure and classification of target in image domains.Existing skill
There are the method and electronic equipment for carrying out artificial cognition to target using experience in art, also have by extracting clarification of objective and week
The feature in collarette border carries out sentencing method for distinguishing and electronic equipment, but the image of object includes different features, how to go
Fall redundancy feature, how to extract to differentiating contributive feature, be image so as to improve the speed of differentiation, precision and accuracy
The main problem that target-recognition faces in field.
The content of the invention
To solve the above-mentioned problems, it is an object of the invention to provide the information processing methods and electronics of a kind of image domains
Equipment differentiates available for the structure to target and classification, such as the structure and classification of ground object target progress are differentiated
Information processing method and electronic equipment.This method and electronic equipment can obtain shape by handling multispectral characteristic
The shape factor, bonding position information are handled, and required different parameters are calculated to build discriminant index, to target
Structure and classification are differentiated, so as to improve the extraction quality to target information, target is differentiated with reference to multiple parameters, from
And rapidly classified to target, and improve the accuracy to target classification and precision.
It is as follows to invent the technical solution used:
The invention discloses a kind of information processing method for being differentiated to target, this method includes multispectral information
Processing step, directivity information processing step, analytical procedure, step display.
Preferably, multispectral information handling step includes:Spectral signature, composing training sample are extracted from multispectral information
Vector.
Preferably, directivity information processing step includes:The target shape factor is obtained according to training sample vector, with reference to side
Different parameters is calculated in tropism information.
Preferably, analytical procedure includes:Discriminant index I (λ) is obtained with reference to multispectral information and directivity information, according to I
The numberical range of (λ) differentiates object construction and classification.
Preferably, step display is exported and shown to the result differentiated in analytical procedure.
Preferably, this method further includes spectral information discriminating step and verification step.
Preferably, the spectral information discriminating step includes directly differentiating target according to the spectral signature of extraction.
Preferably, the verification step includes:According to what is obtained in real measured data data verification spectral information discriminating step
What differentiation result and analytical procedure obtained differentiates as a result, the precision of the two is compared verification.
Preferably, the step display, which is further included, is exported the result for comparing verification and is shown.
The invention also discloses a kind of for the electronic equipment of the information processing differentiated to target, the electronic equipment
Including multispectral information processing unit, directivity information processing unit, analytical equipment, display device.
Preferably, multispectral information processing unit, extracts spectral signature from multispectral information, composing training sample to
Amount.
Preferably, directivity information processing unit obtains the target shape factor, bonding position according to training sample vector
Different parameters is calculated in information.
Preferably, analytical equipment obtains discriminant index I (λ), according to I's (λ) with reference to multispectral information and directivity information
Numberical range differentiates object construction and classification.
Preferably, display device is exported and shown to the result differentiated in analytical procedure.
Preferably, this method further includes spectral information discriminating gear and verification device.
Preferably, the spectral information discriminating gear includes directly differentiating target according to the spectral signature of extraction.
Preferably, the verification device includes:According to what is obtained in real measured data data verification spectral information discriminating step
What differentiation result and analytical procedure obtained differentiates as a result, the precision of the two is compared verification.
Preferably, the display device, which is further included, is exported the result for comparing verification and is shown.
Description of the drawings
Below in conjunction with the accompanying drawings and embodiment the present invention is described in further detail:
Fig. 1 is the flow chart of information processing method embodiment 1.
Fig. 2 is the flow chart of information processing method embodiment 2.
Fig. 3 is the schematic diagram of information processing electronic apparatus embodiment 1.
Fig. 4 is the schematic diagram of information processing electronic apparatus embodiment 2.
Specific embodiment
The present invention is described below in more detail to contribute to the understanding of the present invention.
It should be appreciated that the term or word that use in the specification and in the claims are not construed as having
The meaning limited in dictionary, and be interpreted as on the basis of following principle having and its meaning one in the context of the present invention
The meaning of cause:The concept of term can be limited suitably by inventor for the best illustration to the present invention.
The invention discloses a kind of information processing method for being differentiated to target, this method includes multispectral information
Processing step, directivity information processing step, analytical procedure, step display.
Further, multispectral information handling step includes:Spectral signature, composing training sample are extracted from multispectral information
This vector.
Further, directivity information processing step includes:The target shape factor is obtained according to training sample vector, with reference to
Different parameters is calculated in directivity information.
Further, analytical procedure includes:Discriminant index I (λ) is obtained with reference to multispectral information and directivity information, according to
The numberical range of I (λ) differentiates object construction and classification.
Further, step display is exported and shown to the result differentiated in analytical procedure.
Further, the multispectral information handling step includes:Spectral signature is extracted from multispectral information, gives one
A data acquisition system A={ (ai), i=1,2 ..., N }, wherein, aiIt is the spectral signature institute structure extracted from multispectral information
Into training sample vector.
Further, the target shape factor is obtained according to training sample vector, difference is calculated in bonding position information
Parameter:
R (θ, λ)=f1(λ)k1(θ)+f2(λ)k2(θ)+f3(λ)k3(θ)+...fn(λ)kn(θ)
Wherein, R (θ, λ) is target shape indicator, comes from spectral signature, knTo be entered according to difference in spectral signature
Firing angle θ provides the different parameter cores of target shape, fn(λ) is the different parameters being calculated, and λ is wavelength.
Further, the discriminant index I (λ) is obtained by the following formula:
I (λ)=1+f1(λ)/f3(λ)*0.2-f2(λ)/f3(λ)*0.1。
The invention also discloses a kind of information processing method for being differentiated to target, this method includes multispectral letter
Cease processing step, spectral information discriminating step, directivity information processing step, analytical procedure, verification step, step display;
Further, multispectral information handling step includes:Spectral signature, composing training sample are extracted from multispectral information
This vector.
Further, spectral information discriminating step includes:Directly target is differentiated according to the spectral signature of extraction.
Further, directivity information processing step includes:The target shape factor is obtained according to training sample vector, with reference to
Different parameters is calculated in directivity information.
Further, analytical procedure includes:Discriminant index I (λ) is obtained with reference to multispectral information and directivity information, according to
The numberical range of I (λ) differentiates object construction and classification.
Further, verification step includes:Sentenced according to what is obtained in real measured data data verification spectral information discriminating step
What other result and analytical procedure obtained differentiates as a result, the precision of the two is compared verification.
Further, step display includes the result differentiated in analytical procedure is exported and shown.
Further, step display, which is further included, is exported the result for comparing verification and is shown.
Further, the multispectral information handling step includes:Spectral signature is extracted from multispectral information, gives one
A data acquisition system A={ (ai), i=1,2 ..., N }, wherein, aiIt is the spectral signature institute structure extracted from multispectral information
Into training sample vector.
Further, the target shape factor is obtained according to training sample vector, difference is calculated in bonding position information
Parameter:
R (θ, λ)=f1(λ)k1(θ)+f2(λ)k2(θ)+f3(λ)k3(θ)+...fn(λ)kn(θ)
Wherein, R (θ, λ) is target shape indicator, comes from spectral signature, knTo be entered according to difference in spectral signature
Firing angle θ provides the different parameter cores of target shape, fn(λ) is the different parameters being calculated, and λ is wavelength.
Further, the discriminant index I (λ) is obtained by the following formula:
I (λ)=1+f1(λ)/f3(λ)*0.2-f2(λ)/f3(λ)*0.1。
The invention also discloses a kind of for the electronic equipment of the information processing differentiated to target, the electronic equipment
Including multispectral information processing unit, directivity information processing unit, analytical equipment, display device.
Further, multispectral information processing unit, extracts spectral signature from multispectral information, composing training sample to
Amount.
Further, directivity information processing unit obtains the target shape factor, bonding position according to training sample vector
Different parameters is calculated in property information.
Further, analytical equipment obtains discriminant index I (λ), according to I (λ) with reference to multispectral information and directivity information
Numberical range differentiate object construction and classification.
Further, display device is exported and shown to the result differentiated in analytical procedure.
Further, the multispectral information processing unit includes:Spectral signature is extracted from multispectral information, gives one
A data acquisition system A={ (ai), i=1,2 ..., N }, wherein, aiIt is the spectral signature institute structure extracted from multispectral information
Into training sample vector.
Further, described to obtain the target shape factor according to training sample vector, bonding position information is calculated
Different parameters:
R (θ, λ)=f1(λ)k1(θ)+f2(λ)k2(θ)+f3(λ)k3(θ)+...fn(λ)kn(θ)
Wherein, R (θ, λ) is target shape indicator, comes from spectral signature, knTo be entered according to difference in spectral signature
Firing angle θ provides the different parameter cores of target shape, fn(λ) is the different parameters being calculated, and λ is wavelength.
Further, the discriminant index I (λ) is obtained by the following formula:
I (λ)=1+f1(λ)/f3(λ)*0.2-f2(λ)/f3(λ)*0.1。
The invention also discloses a kind of for the electronic equipment of the information processing differentiated to target, the electronic equipment
Including multispectral information processing unit, directivity information processing unit, analytical equipment, display device;
Further, multispectral information processing unit, extracts spectral signature from multispectral information, composing training sample to
Amount.
Further, directivity information processing unit obtains the target shape factor, bonding position according to training sample vector
Different parameters is calculated in property information.
Further, analytical equipment obtains discriminant index I (λ), according to I (λ) with reference to multispectral information and directivity information
Numberical range differentiate object construction and classification.
Further, display device is exported and shown to the result differentiated in analytical equipment.
Further, which further includes spectral information discriminating gear and verification device
Further, the spectral information discriminating gear includes directly sentencing target according to the spectral signature of extraction
Not.
Further, the verification device includes:It is obtained according in real measured data data verification spectral information discriminating step
Differentiation result and analytical procedure obtain differentiate as a result, the precision of the two is compared verification.
Further, the display device, which is further included, is exported the result for comparing verification and is shown.
Further, the multispectral information handling step includes:Spectral signature is extracted from multispectral information, gives one
A data acquisition system A={ (ai), i=1,2 ..., N }, wherein, aiIt is the spectral signature institute structure extracted from multispectral information
Into training sample vector.
Further, the target shape factor is obtained according to training sample vector, difference is calculated in bonding position information
Parameter:
R (θ, λ)=f1(λ)k1(θ)+f2(λ)k2(θ)+f3(λ)k3(θ)+...fn(λ)kn(θ)
Wherein, R (θ, λ) is target shape indicator, comes from spectral signature, knTo be entered according to difference in spectral signature
Firing angle θ provides the different parameter cores of target shape, fn(λ) is the different parameters being calculated, and λ is wavelength.
Further, the discriminant index I (λ) is obtained by the following formula:
I (λ)=1+f1(λ)/f3(λ)*0.2-f2(λ)/f3(λ)*0.1。
The foregoing describe the preferred embodiment for the present invention, and however, it is not to limit the invention.Those skilled in the art couple
Embodiment disclosed herein can carry out improvement and the variation without departing from scope and spirit.
Claims (4)
1. a kind of information processing method for being differentiated to target, which is characterized in that this method is included at multispectral information
Manage step, spectral information discriminating step, directivity information processing step, analytical procedure, verification step, step display;
Multispectral information handling step includes:Spectral signature is extracted from multispectral information, gives a data acquisition system, A=
{(ai), i=1,2 ..., N }, wherein, aiIt is the training sample vector that the spectral signature extracted from multispectral information is formed;
Directivity information processing step includes:The target shape factor, bonding position information meter are obtained according to training sample vector
Calculation obtains different parameters:
R (θ, λ)=f1(λ)k1(θ)+f2(λ)k2(θ)+f3(λ)k3(θ)+...+fn(λ)kn(θ),
Wherein, R (θ, λ) is the target shape factor, comes from spectral signature, knTo be provided according to different incidence angles θ in spectral signature
The different parameter cores of target shape, fn(λ) is the different parameters being calculated, and λ is wavelength;
Analytical procedure includes:Discriminant index I (λ) is obtained with reference to multispectral information and directivity information, according to the numerical value model of I (λ)
It encloses and differentiates object construction and classification;The discriminant index I (λ) is obtained by the following formula:
I (λ)=1+f1(λ)/f3(λ)*0.2-f2(λ)/f3(λ)*0.1;
Step display is exported and shown to the result differentiated in analytical procedure.
2. a kind of information processing method for being differentiated to target according to claim 1, the spectral information are sentenced
Other step includes directly differentiating target according to the spectral signature of extraction;The verification step includes:According to real measured data
What the differentiation result and analytical procedure obtained in data verification spectral information discriminating step obtained differentiates the essence as a result, by the two
Degree is compared verification;The step display, which is further included, to be exported the result for comparing verification and is shown.
It is 3. a kind of for the electronic equipment of the information processing differentiated to target, which is characterized in that the electronic equipment includes
Multispectral information processing unit, spectral information discriminating gear, directivity information processing unit, analytical equipment verify device, display
Device;
Multispectral information processing unit extracts spectral signature from multispectral information, gives a data acquisition system A={ (ai), i=
1,2 ..., N }, wherein, aiIt is the training sample vector that the spectral signature extracted from multispectral information is formed;
Directivity information processing unit obtains the target shape factor according to training sample vector, and bonding position information calculates
To different parameters:
R (θ, λ)=f1(λ)k1(θ)+f2(λ)k2(θ)+f3(λ)k3(θ)+...+fn(λ)kn(θ),
Wherein, R (θ, λ) is the target shape factor, comes from spectral signature, knTo be provided according to different incidence angles θ in spectral signature
The different parameter cores of target shape, fn(λ) is the different parameters being calculated, and λ is wavelength;
Analytical equipment obtains discriminant index I (λ) with reference to multispectral information and directivity information, is sentenced according to the numberical range of I (λ)
Other object construction and classification;The discriminant index I (λ) is obtained by the following formula:
I (λ)=1+f1(λ)/f3(λ)*0.2-f2(λ)/f3(λ)*0.1;
Display device is exported and shown to the result differentiated in analytical equipment.
It is 4. according to claim 3 a kind of for the electronic equipment of the information processing differentiated to target, the spectrum
Information discriminating gear includes directly differentiating target according to the spectral signature of extraction;
The verification device includes:According to the differentiation result obtained in real measured data data verification spectral information discriminating step and
What analytical procedure obtained differentiates as a result, the precision of the two is compared verification;
The display device, which is further included, to be exported the result for comparing verification and is shown.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710466610.4A CN107292264B (en) | 2017-06-19 | 2017-06-19 | A kind of information processing method and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710466610.4A CN107292264B (en) | 2017-06-19 | 2017-06-19 | A kind of information processing method and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107292264A CN107292264A (en) | 2017-10-24 |
CN107292264B true CN107292264B (en) | 2018-05-29 |
Family
ID=60097366
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710466610.4A Expired - Fee Related CN107292264B (en) | 2017-06-19 | 2017-06-19 | A kind of information processing method and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107292264B (en) |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB0405741D0 (en) * | 2004-03-15 | 2004-04-21 | Bae Systems Plc | Apparatus for enhancing a signal and related method |
CN103927756B (en) * | 2014-04-28 | 2017-04-19 | 中国国土资源航空物探遥感中心 | Spectral characteristic index extraction method based on spectral characteristic space centralization |
CN106326905A (en) * | 2015-06-16 | 2017-01-11 | 征图新视(江苏)科技有限公司 | Multispectral vision imaging big-leaf crop leaf classification method and system |
CN106503727B (en) * | 2016-09-30 | 2019-09-24 | 西安电子科技大学 | A kind of method and device of classification hyperspectral imagery |
CN106503739A (en) * | 2016-10-31 | 2017-03-15 | 中国地质大学(武汉) | The target in hyperspectral remotely sensed image svm classifier method and system of combined spectral and textural characteristics |
-
2017
- 2017-06-19 CN CN201710466610.4A patent/CN107292264B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN107292264A (en) | 2017-10-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105975941B (en) | A kind of multi-direction vehicle detection identifying system based on deep learning | |
CN109583324A (en) | A kind of pointer meters reading automatic identifying method based on the more box detectors of single-point | |
CN107229930A (en) | A kind of pointer instrument numerical value intelligent identification Method and device | |
CN109983482A (en) | Learning model generation method, learning model generating means, signal data method of discrimination, signal data discriminating gear and signal data discriminating program | |
CN103499585A (en) | Non-continuity lithium battery thin film defect detection method and device based on machine vision | |
CN109784383B (en) | Rail crack identification method based on graph domain feature and DS evidence theory fusion | |
CN106529571A (en) | Multilayer image characteristics extraction modeling, image recognition method and apparatus based on neural network | |
CN106295665A (en) | A kind of transformer station readings of pointer type meters automatic identifying method | |
CN111860459A (en) | Gramineous plant leaf stomata index measuring method based on microscopic image | |
CN107092906A (en) | A kind of Chinese traditional medicinal materials recognition device based on deep learning | |
CN110533069A (en) | A kind of two-dimentional chaff distribution character recognition methods based on algorithm of support vector machine | |
CN106295658A (en) | A kind of transformer station readings of pointer type meters automatic recognition system | |
CN114091606A (en) | Tunnel blasting blast hole half-hole mark identification and damage flatness evaluation classification method | |
CN107358252A (en) | A kind of unmanned plane sorting technique and device | |
CN107103608A (en) | A kind of conspicuousness detection method based on region candidate samples selection | |
TWI832435B (en) | Water quality monitoring system and computer-readable recording media | |
CN107292264B (en) | A kind of information processing method and electronic equipment | |
CN105300267B (en) | Plate thickness measuring method based on electromagnetic eddy and data anastomosing algorithm | |
CN112215060A (en) | Hough transform-based high-precision mechanical instrument reading identification method | |
CN114897655A (en) | Vision-based epidemic prevention control method and device, storage medium and electronic equipment | |
CN116883394B (en) | Diamond quality detection method based on image data processing | |
CN107729877B (en) | Face detection method and device based on cascade classifier | |
CN108549899A (en) | A kind of image-recognizing method and device | |
CN113435442A (en) | Water level measuring method and device, water gauge and electronic equipment | |
CN115169504B (en) | Equipment abnormity identification method in coal gas fine desulfurization process |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180529 Termination date: 20190619 |