CN105469079A - Object material identification method based on multi-sensor information fusion - Google Patents
Object material identification method based on multi-sensor information fusion Download PDFInfo
- Publication number
- CN105469079A CN105469079A CN201511028339.3A CN201511028339A CN105469079A CN 105469079 A CN105469079 A CN 105469079A CN 201511028339 A CN201511028339 A CN 201511028339A CN 105469079 A CN105469079 A CN 105469079A
- Authority
- CN
- China
- Prior art keywords
- sensor
- identified
- identification method
- information fusion
- material identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N21/6402—Atomic fluorescence; Laser induced fluorescence
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/71—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light thermally excited
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N22/00—Investigating or analysing materials by the use of microwaves or radio waves, i.e. electromagnetic waves with a wavelength of one millimetre or more
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
- G01N29/045—Analysing solids by imparting shocks to the workpiece and detecting the vibrations or the acoustic waves caused by the shocks
- G01N29/046—Analysing solids by imparting shocks to the workpiece and detecting the vibrations or the acoustic waves caused by the shocks using the echo of particles imparting on a surface; using acoustic emission of particles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/148—Wavelet transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N2021/6417—Spectrofluorimetric devices
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Mathematical Physics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Optics & Photonics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention provides an object material identification method based on multi-sensor information fusion. The method comprises steps: firstly, at least three kinds of sensors are provided; then, the sensors are used for transmitting source signals to a to-be-identified object, feature signals transmitted by the to-be-identified object under irradiation of the source signals are acquired respectively, or the sensors are directly used for acquiring the feature signals of the to-be-identified object, and object material information provided by each feature signal is extracted; and finally, the information is analyzed comprehensively to determine the material of the object. According to the object material identification method of the invention, data complementation and redundancy of different sensors are used, information is acquired from each independent piece of measurement space, the target object material can be identified through a fusion technology, the detection accuracy is high, and reliable data are provided for object material identification.
Description
Technical field
The present invention relates to Material Identification technical field, particularly relate to a kind of object Material Identification method based on multi-sensor information fusion.
Background technology
Material Identification, Quality Identification are the important topics in industrial material quality testing field.Along with the development of global industry, the demand of industrial automation also increases day by day, and the cost of manual labor also significantly improves simultaneously.The popularization of the automatic identification technology system of equipment, material, both can free manpower, also greatly can reduce human cost from work that is dull, that repeat.Meanwhile, the accuracy of mechanical detection and detection speed all will higher than manual detection.Visible, because Material Identification method is for the importance of industrial development, it is an important topic in process of industrialization always.
The material of current each type objects is varied, and the recognition capability of single-sensor to material is limited, is easy to cause and mixes the spurious with the genuine.The common method of current Material Identification has light identification, heat feels identification, colour recognition.Often kind of method has self limitation, and such as, visual light imaging equipment can the texture information of effective object analysis, but affected by environment larger; The object that ultrasound wave can penetrate radiowave, light wave cannot pass, but decay in atmosphere and not easily propagate too soon.So utilize single-sensor to differentiate object material, its accuracy is limited,
Current existing Material Identification method is owing to considering limited on the parameter affecting material reflective information, and discriminant approach is single, causes the accuracy of identification to have much room for improvement.
Therefore, a kind of new object Material Identification method is provided to be the problem that those skilled in the art need to solve.
Summary of the invention
The shortcoming of prior art in view of the above, the object of the present invention is to provide a kind of object Material Identification method based on multi-sensor information fusion, single for solving Material Identification method discriminant approach in prior art, cause the problem that the accuracy of identification is limited.
For achieving the above object and other relevant objects, the invention provides a kind of object Material Identification method based on multi-sensor information fusion, described object Material Identification method at least comprises:
1) at least three kinds of sensors are provided;
2) utilize described sensor to object emission source signal to be identified, gather the characteristic signal that described object to be identified is launched under described source signal irradiates respectively, or directly utilize described sensor to gather the characteristic signal of object to be identified;
3) analyze described characteristic signal by comprehensive, determine the material of described object.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, described sensor at least comprises infrared sensor, utilizes described infrared sensor to the process that described object to be identified identifies to be:
Utilize infrared sensor to object emission Infrared to be identified, described object to be identified launches feature light after Infrared is irradiated, the spectral signature that the spectral signature of described feature light is corresponding with each material that material classification comprises compares, and determines the material classification that object to be identified may belong to.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, described sensor at least comprises imageing sensor, utilizes described imageing sensor to the process that described object to be identified identifies to be:
By the image of camera collection body surface to be identified, by the texture analysis to image, from the various material classification preset, determine the material classification that object to be identified may belong to.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, described sensor at least comprises radar sensor, utilizes described radar sensor to the process that described object to be identified identifies to be:
Utilize radar sensor to the microwave signal of object emission radar to be identified, then from receiving the spectroscopic eigenvalue extracting echo data echo, process determines the material classification that object to be identified may belong to after calculating.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, described sensor at least comprises laser sensor, utilizes described laser sensor to the process that described object to be identified identifies to be:
Utilize laser sensor to object emission laser signal to be identified, then receive reflection, dispersion, heat radiation react the data provided and determine the material classification that object to be identified may belong to.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, described sensor at least comprises ultrasonic sensor, utilizes described ultrasound wave sensor to the process that described object to be identified identifies to be:
Utilize ultrasonic sensor to object emission ultrasonic signal to be identified, extract the eigenwert of echo data in the echo then received, process determines the material classification that object to be identified may belong to after calculating.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, described sensor at least comprises thermal sensor, judges the material classification that described object to be identified may belong to by measuring described object to be identified from the ratio that described thermal sensor absorbs heat.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, described step 3) in utilize linear to calculate or Nonlinear Calculation Method determines the material of described object.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, be describedly linearly calculated as ballot or weighting, described nonlinear computation is neural network.
As a kind of scheme of optimization of object Material Identification method that the present invention is based on multi-sensor information fusion, utilize the formula of the linear calculating of described weighting as follows:
Wherein, P
arepresent that object material is the probability of a, N represents sensor total quantity, P
nrepresent the weight of sensor n; P
narepresent that object Material Identification is the probability of a by sensor n; P
aprobable value is maximum, determines that the material of this object is a.
As mentioned above, the object Material Identification method of multi-sensor information fusion of the present invention, comprises step: first, provides at least three kinds of sensors; Then, utilize described sensor to object emission source signal to be identified, gather the characteristic signal that described object to be identified is launched under described source signal irradiates respectively, or directly utilize described sensor to gather the characteristic signal of object to be identified; Finally, by comprehensively analyzing described characteristic signal, the material of described object is determined.Object Material Identification method of the present invention is the data complement and the redundancy that utilize different sensors, from respective independently measurement space obtaining information, is identified target object material by integration technology.Recognition methods Detection accuracy of the present invention is high, for recognition object material provides reliable data.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the object Material Identification method of multi-sensor information fusion of the present invention.
Embodiment
Below by way of specific instantiation, embodiments of the present invention are described, those skilled in the art the content disclosed by this instructions can understand other advantages of the present invention and effect easily.The present invention can also be implemented or be applied by embodiments different in addition, and the every details in this instructions also can based on different viewpoints and application, carries out various modification or change not deviating under spirit of the present invention.
Refer to accompanying drawing.It should be noted that, the diagram provided in the present embodiment only illustrates basic conception of the present invention in a schematic way, then only the assembly relevant with the present invention is shown in graphic but not component count, shape and size when implementing according to reality is drawn, it is actual when implementing, and the kenel of each assembly, quantity and ratio can be a kind of change arbitrarily, and its assembly layout kenel also may be more complicated.
In prior art, utilize single-sensor can only collect the characteristic signal of a certain character of object to be identified, information is unilateral, and the accuracy rate of identification is low.Given this, the invention provides a kind of object Material Identification method based on multi-sensor information fusion, by utilizing the electromagnetic wave of various different-waveband, sound wave and laser etc., reflection object material information comprehensively, the accuracy rate of identification is higher.
The invention provides a kind of object Material Identification method based on multi-sensor information fusion, as shown in Figure 1, described object Material Identification method at least comprises the steps:
S1, provides at least three kinds of sensors;
S2, utilizes described sensor successively to object emission source signal to be identified, gathers the characteristic signal that described object to be identified is launched under described source signal irradiates respectively, or directly utilizes described sensor to gather the characteristic signal of object to be identified;
S3, by comprehensively analyzing described characteristic signal, determines the material of described object.
The object Material Identification method based on multi-sensor information fusion of the present invention is introduced in detail below by specific embodiment.
First perform step S1, at least three kinds of sensors are provided;
Then perform step S2, utilize described sensor successively to object emission source signal to be identified, gather the characteristic signal that described object to be identified is launched under described source signal irradiates respectively, or directly utilize described sensor to gather the characteristic signal of object to be identified.
Described sensor can be that three kind three in imageing sensor, infrared sensor, radar sensor, laser sensor, ultrasonic sensor and thermal sensor is two or more.Certainly, described kind of sensor is not limited to above-mentioned cited several, and any sensor that can be used for differentiating object material, does not limit at this.
In addition, the quantity of often kind of sensor is not limit, and the order utilizing often kind of sensor to carry out object Material Identification is not also restricted.All sensors can simultaneously to object emission source signal to be identified, also can successively to object emission source signal to be identified.
In the present embodiment, identify described object material respectively by imageing sensor, infrared sensor, radar sensor, laser sensor and ultrasonic sensor, the quantity of often kind of sensor is one, and detailed process is:
First, described imageing sensor is utilized to identify described object to be identified.Obtain the image directly being gathered body surface to be identified by camera, extracted by the shape facility to image, textural characteristics and color characteristic etc., then contrast with the various material classification preset, determine the classification that this object material may belong to.
Shape facility is the most direct visual signature of reaction objects in images, and most of object can by differentiating its shape to differentiate.Therefore, in the method utilizing imageing sensor recognition object material, the correct extraction of shape facility is extremely important.
The texture of image is the characteristics of image relevant with material with physical surface structure, and what reflect is the global characteristics of image.The method that image texture characteristic extracts has: statistical method (gray level co-occurrence matrixes analysis of texture method), geometric method (being based upon in basic texel theoretical foundation), modelling (using the parameter of the tectonic model of image as textural characteristics) and signal transacting method (mainly wavelet transformation is main) etc.
The color characteristic of image is the body surface character of image or image-region, reflection be the global characteristics of image.
The above-mentioned characteristics of image of object to be identified and known multiple standards material are compared, determines the classification that this object material may belong to.Such as, in this embodiment imageing sensor method, the possible generic identified is: wood, fiber, stone.
Then, described infrared sensor is utilized to identify described object to be identified.Utilize infrared sensor to object emission Infrared to be identified, described object to be identified launches feature light after Infrared is irradiated, the spectral signature that the spectral signature of described feature light is corresponding with each material that material classification comprises compares, and determines the material classification that object to be identified may belong to.
The component of unlike material is different, different elements excites through particular light ray high energy, the interphase interaction of atom can launch different feature light, so pass through to object emission Infrared to be identified, object to be identified launches feature light after Infrared is irradiated, the spectral signature that the spectral signature of this feature light is corresponding with each material that material classification comprises compares, and determines the material of object to be identified.Such as, in this embodiment infrared ray sensor method, possible generic is: wood, metal, rubber.
Then, radar sensor is utilized to identify described object to be identified.Elder generation to object emission microwave signal to be identified, then extracts the spectroscopic eigenvalue of echo data by radar sensor from the echo received, and process determines the material that article to be identified may belong to after calculating.
The microwave signal that radar sensor sends is a kind of electromagnetic wave, after electromagnetic wave runs into object to be identified in communication process, scattering and return the electromagnetic wave that receives by radar antenna be echo, the Material Identification to the target of burying can be realized.The inner structure of different material is different, and different with the coefficient of absorption to electromagnetic reflection, the echo of formation is also different.Such as, in this embodiment radar sensor method, possible generic is: wood, metal, stone.
Then, described laser sensor is utilized to identify described object to be identified.First utilize laser sensor to object emission laser signal to be identified, then receive reflection, dispersion, heat radiation react the data provided and determine the material classification that object to be identified may belong to.Laser sensor can realize contactless telemeasurement, has the advantages such as speed is fast, precision is high, range is large, anti-light, electrical interference ability is strong.
Also can with high-octane Laser Focusing on object to be identified, object is ionized and produces plasma, then can by the spectral unmixing material (LIBS) of plasma emission or laser is beaten the particle produced on object do mass spectrophotometry also can obtain about material composition information, know method for distinguishing do not limit.Such as, in this embodiment laser sensor method, possible generic is: wood, paper, stone.
Finally, described ultrasound wave sensor is utilized to identify described object to be identified.First utilize ultrasonic sensor to object emission ultrasonic signal to be identified, extract the eigenwert of echo data in the echo then received, process determines the material classification that object to be identified may belong to after calculating.
Ultrasound wave is the mechanical wave of a kind of vibration frequency higher than sound wave, is occurred to vibrate to produce by transducing wafer under the excitation of voltage, and it has, and frequency is high, wavelength is short, diffraction phenomenon is little, particularly good directionality, ray and the features such as direction propagation can be become.Ultrasound wave encounters object to be identified can produce remarkable reflection, forms reflection echo.Often kind of object to be identified has specific echo parameter, through the material classification that computing determination recognition object may belong to.Such as, in this embodiment ultrasonic sensor method, possible generic is: wood, fiber, leather.
It should be noted that, the above order carrying out recognition object material by various sensor is not limit.Be utilize above-mentioned five kinds of sensors to carry out recognition object material in the present embodiment, when not conflicting, five kinds of sensors can combine mutually.In other embodiments, other suitable sensors also can be adopted to carry out recognition object material, and such as thermal sensor etc., does not limit at this.Described thermal sensor is the material judging described object to be identified by measuring described object to be identified from the ratio that described thermal sensor absorbs heat
Finally performing step S3, by comprehensively analyzing described characteristic signal, determining the material of described object.
The linear method calculated can be utilized to determine the material of described object to be identified.In the present embodiment, the mode of ballot can be utilized from the information of each group possibility material classification, determine the material of described object.From step S2 in all possible object material, can find out all have wood in the middle of five kinds of sensor identifications, then determine that this object is wood.Therefore, for the material classification information that intuitive is stronger, adopt the mode of ballot can determine the material of object fast.
Certainly, in other embodiments, the linear computational method of weighting can also be adopted to determine the material of object, and computing formula is as follows:
Wherein, P
arepresent that object material is the probability of a, N represents sensor total quantity, P
nrepresent the weight of sensor n; P
narepresent that object Material Identification is the probability of a by sensor n; P
aprobable value is maximum, determines that the material of this object is a.
It should be noted that, weight is a relative concept, refers to the relative importance of a certain index in the overall evaluation, is the rationed of the significance level of the not ipsilateral being evaluated object.If the weighted value of sensor n is comparatively large, refer to that the confidence level of the accurate recognition object material of this sensor n energy is comparatively large, outbalance.
In addition, can also utilize Nonlinear Calculation Method from material information, determine the material of object, such as, utilize the method for neural network to determine object material.
After described object to be identified receives different sensor source signals, launch different characteristic signals, these feature instantiations be the different attribute of object, therefore, utilize object identification method of the present invention omnibearingly can distinguish object material, accuracy rate is also higher.
In sum, the invention provides a kind of object Material Identification method of multi-sensor information fusion, comprise step: first, at least three kinds of sensors are provided; Then utilize described sensor to object emission source signal to be identified, gather the characteristic signal that described object to be identified is launched under described source signal irradiates respectively, or directly utilize described sensor to gather the characteristic signal of object to be identified; Finally, by comprehensively analyzing described characteristic signal, the material of described object is determined.Object Material Identification method of the present invention is the data complement and the redundancy that utilize different sensors, from respective independently measurement space obtaining information, is identified target object material by integration technology.Recognition methods Detection accuracy of the present invention is high, for recognition object material provides reliable data.
So the present invention effectively overcomes various shortcoming of the prior art and tool high industrial utilization.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not for limiting the present invention.Any person skilled in the art scholar all without prejudice under spirit of the present invention and category, can modify above-described embodiment or changes.Therefore, such as have in art usually know the knowledgeable do not depart from complete under disclosed spirit and technological thought all equivalence modify or change, must be contained by claim of the present invention.
Claims (10)
1. based on an object Material Identification method for multi-sensor information fusion, it is characterized in that, described object Material Identification method at least comprises:
1) at least three kinds of sensors are provided;
2) utilize described sensor to object emission source signal to be identified, gather the characteristic signal that described object to be identified is launched under described source signal irradiates respectively, or directly utilize described sensor to gather the characteristic signal of object to be identified;
3) analyze described characteristic signal by comprehensive, determine the material of described object.
2. the object Material Identification method based on multi-sensor information fusion according to claim 1, is characterized in that: described sensor at least comprises infrared sensor, utilizes described infrared sensor to the process that described object to be identified identifies to be:
Utilize infrared sensor to object emission Infrared to be identified, described object to be identified launches feature light after Infrared is irradiated, the spectral signature that the spectral signature of described feature light is corresponding with each material that material classification comprises compares, and determines the material classification that object to be identified may belong to.
3. the object Material Identification method based on multi-sensor information fusion according to claim 1, is characterized in that: described sensor at least comprises imageing sensor, utilizes described imageing sensor to the process that described object to be identified identifies to be:
By the image of camera collection body surface to be identified, by analyzing picture shape feature, textural characteristics and color characteristic, then contrasting with known various material classification, determining the classification that this object material may belong to.
4. the object Material Identification method based on multi-sensor information fusion according to claim 1, is characterized in that: described sensor at least comprises radar sensor, utilizes described radar sensor to the process that described object to be identified identifies to be:
Utilize radar sensor to the microwave signal of object emission radar to be identified, then from receiving the spectroscopic eigenvalue extracting echo data echo, process determines the material classification that object to be identified may belong to after calculating.
5. the object Material Identification method based on multi-sensor information fusion according to claim 1, is characterized in that: described sensor at least comprises laser sensor, utilizes described laser sensor to the process that described object to be identified identifies to be:
Utilize laser sensor to object emission laser signal to be identified, then receive reflection, dispersion, heat radiation react the data provided and determine the material classification that object to be identified may belong to.
6. the object Material Identification method based on multi-sensor information fusion according to claim 1, is characterized in that: described sensor at least comprises ultrasonic sensor, utilizes described ultrasound wave sensor to the process that described object to be identified identifies to be:
Utilize ultrasonic sensor to object emission ultrasonic signal to be identified, extract the eigenwert of echo data in the echo then received, process determines the material classification that object to be identified may belong to after calculating.
7. the object Material Identification method based on multi-sensor information fusion according to claim 1, it is characterized in that: described sensor at least comprises thermal sensor, judging from the ratio that described thermal sensor absorbs heat the material classification that described object to be identified may belong to by measuring described object to be identified.
8. the object Material Identification method based on multi-sensor information fusion according to any one of claim 1 ~ 7, is characterized in that: described step 3) in utilize linear calculate or Nonlinear Calculation Method to determine the material of described object.
9. the object Material Identification method based on multi-sensor information fusion according to claim 8, is characterized in that: described being linearly calculated as is voted or weighting, and described nonlinear computation is neural network.
10. the object Material Identification method based on multi-sensor information fusion according to claim 9, is characterized in that: utilize the formula of the linear calculating of described weighting as follows:
Wherein, P
arepresent that object material is the probability of a, N represents sensor total quantity, P
nrepresent the weight of sensor n; P
narepresent that object Material Identification is the probability of a by sensor n; P
aprobable value is maximum, determines that the material of this object is a.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511028339.3A CN105469079A (en) | 2015-12-31 | 2015-12-31 | Object material identification method based on multi-sensor information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511028339.3A CN105469079A (en) | 2015-12-31 | 2015-12-31 | Object material identification method based on multi-sensor information fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105469079A true CN105469079A (en) | 2016-04-06 |
Family
ID=55606750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511028339.3A Pending CN105469079A (en) | 2015-12-31 | 2015-12-31 | Object material identification method based on multi-sensor information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105469079A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778787A (en) * | 2016-12-29 | 2017-05-31 | 王红军 | A kind of object based on color characteristic assists in identifying method |
| CN107169469A (en) * | 2017-06-02 | 2017-09-15 | 南京理工大学 | A kind of material identification method of the MIMO radar based on machine learning |
| CN107174184A (en) * | 2017-04-26 | 2017-09-19 | 北京小米移动软件有限公司 | Drying mode determines method and device |
| CN107192692A (en) * | 2017-06-07 | 2017-09-22 | 彭枭雄 | Mistake proofing detection method for structural member assembly in automobile, machinery or household appliances manufacturing |
| CN107202559A (en) * | 2017-05-08 | 2017-09-26 | 西北工业大学 | The object identification method analyzed based on room acoustics channel perturbation |
| CN108875935A (en) * | 2018-06-11 | 2018-11-23 | 兰州理工大学 | Based on the natural image target materials visual signature mapping method for generating confrontation network |
| CN108985333A (en) * | 2018-06-15 | 2018-12-11 | 浙江大学 | A kind of material acquisition methods neural network based and system |
| CN109521498A (en) * | 2018-11-12 | 2019-03-26 | 深圳市华讯方舟太赫兹科技有限公司 | Foreign matter detecting method, device and storage medium |
| CN109975799A (en) * | 2019-03-13 | 2019-07-05 | 谭伟 | A kind of method and its system of radar identification material |
| CN110245653A (en) * | 2019-06-06 | 2019-09-17 | 深圳市宏电技术股份有限公司 | A kind of object identification device and method |
| CN110298289A (en) * | 2019-06-24 | 2019-10-01 | Oppo广东移动通信有限公司 | Material identification method, apparatus, storage medium and electronic equipment |
| CN110766067A (en) * | 2019-10-21 | 2020-02-07 | 浙江工业大学之江学院 | Millimeter wave radar material identification method based on machine learning |
| CN111579520A (en) * | 2020-03-18 | 2020-08-25 | 浙江省平湖技师学院 | Workpiece material identification device and identification method thereof |
| CN111832433A (en) * | 2020-06-24 | 2020-10-27 | 科络克电子科技（上海）有限公司 | Device for extracting object characteristics from image and working method thereof |
| US10871468B2 (en) | 2018-11-05 | 2020-12-22 | Tata Consultancy Services Limited | Non-contact material inspection |
| CN112308892A (en) * | 2020-11-16 | 2021-02-02 | 中国海洋大学 | Shell texture analysis system and method based on LIBS technology |
| CN113325008A (en) * | 2021-06-02 | 2021-08-31 | 合肥工业大学 | Non-contact material identification system and method based on WIFI equipment |
| DE102021104855A1 (en) | 2021-03-01 | 2022-09-01 | Universität Augsburg, Körperschaft des öffentlichen Rechts | Material testing method and material testing device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102322974A (en) * | 2011-06-03 | 2012-01-18 | 东南大学 | Array temperature touch sensing device |
| CN102387248A (en) * | 2011-09-13 | 2012-03-21 | 华为终端有限公司 | Method and mobile terminal for configuring application mode |
| CN202671887U (en) * | 2012-06-26 | 2013-01-16 | 无锡小天鹅股份有限公司 | Washing machine capable of identifying clothes automatically |
| US20150062555A1 (en) * | 2013-09-04 | 2015-03-05 | Hyundai Mobis Co., Ltd. | Lidar sensor system |
-
2015
- 2015-12-31 CN CN201511028339.3A patent/CN105469079A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102322974A (en) * | 2011-06-03 | 2012-01-18 | 东南大学 | Array temperature touch sensing device |
| CN102387248A (en) * | 2011-09-13 | 2012-03-21 | 华为终端有限公司 | Method and mobile terminal for configuring application mode |
| CN202671887U (en) * | 2012-06-26 | 2013-01-16 | 无锡小天鹅股份有限公司 | Washing machine capable of identifying clothes automatically |
| US20150062555A1 (en) * | 2013-09-04 | 2015-03-05 | Hyundai Mobis Co., Ltd. | Lidar sensor system |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778787A (en) * | 2016-12-29 | 2017-05-31 | 王红军 | A kind of object based on color characteristic assists in identifying method |
| CN107174184A (en) * | 2017-04-26 | 2017-09-19 | 北京小米移动软件有限公司 | Drying mode determines method and device |
| CN107202559B (en) * | 2017-05-08 | 2020-04-03 | 西北工业大学 | Object identification method based on indoor acoustic channel disturbance analysis |
| CN107202559A (en) * | 2017-05-08 | 2017-09-26 | 西北工业大学 | The object identification method analyzed based on room acoustics channel perturbation |
| CN107169469A (en) * | 2017-06-02 | 2017-09-15 | 南京理工大学 | A kind of material identification method of the MIMO radar based on machine learning |
| CN107169469B (en) * | 2017-06-02 | 2020-06-19 | 南京理工大学 | Material identification method of MIMO radar based on machine learning |
| CN107192692A (en) * | 2017-06-07 | 2017-09-22 | 彭枭雄 | Mistake proofing detection method for structural member assembly in automobile, machinery or household appliances manufacturing |
| CN107192692B (en) * | 2017-06-07 | 2020-06-26 | 浙江世宝股份有限公司 | Error-proofing detection method for structural part assembly in automobile, machinery or household appliance manufacturing industry |
| CN108875935A (en) * | 2018-06-11 | 2018-11-23 | 兰州理工大学 | Based on the natural image target materials visual signature mapping method for generating confrontation network |
| CN108875935B (en) * | 2018-06-11 | 2020-08-11 | 兰州理工大学 | Natural image target material visual characteristic mapping method based on generation countermeasure network |
| CN108985333A (en) * | 2018-06-15 | 2018-12-11 | 浙江大学 | A kind of material acquisition methods neural network based and system |
| CN108985333B (en) * | 2018-06-15 | 2020-10-23 | 浙江大学 | Material obtaining method and system based on neural network |
| US10871468B2 (en) | 2018-11-05 | 2020-12-22 | Tata Consultancy Services Limited | Non-contact material inspection |
| CN109521498A (en) * | 2018-11-12 | 2019-03-26 | 深圳市华讯方舟太赫兹科技有限公司 | Foreign matter detecting method, device and storage medium |
| CN109975799A (en) * | 2019-03-13 | 2019-07-05 | 谭伟 | A kind of method and its system of radar identification material |
| CN110245653A (en) * | 2019-06-06 | 2019-09-17 | 深圳市宏电技术股份有限公司 | A kind of object identification device and method |
| CN110298289A (en) * | 2019-06-24 | 2019-10-01 | Oppo广东移动通信有限公司 | Material identification method, apparatus, storage medium and electronic equipment |
| CN110298289B (en) * | 2019-06-24 | 2021-11-02 | Oppo广东移动通信有限公司 | Material identification method, device, storage medium and electronic equipment |
| CN110766067A (en) * | 2019-10-21 | 2020-02-07 | 浙江工业大学之江学院 | Millimeter wave radar material identification method based on machine learning |
| CN111579520A (en) * | 2020-03-18 | 2020-08-25 | 浙江省平湖技师学院 | Workpiece material identification device and identification method thereof |
| CN111832433A (en) * | 2020-06-24 | 2020-10-27 | 科络克电子科技（上海）有限公司 | Device for extracting object characteristics from image and working method thereof |
| CN111832433B (en) * | 2020-06-24 | 2023-12-29 | 奇点微(上海)光电科技有限公司 | Device for extracting object characteristics from image and working method thereof |
| CN112308892A (en) * | 2020-11-16 | 2021-02-02 | 中国海洋大学 | Shell texture analysis system and method based on LIBS technology |
| DE102021104855A1 (en) | 2021-03-01 | 2022-09-01 | Universität Augsburg, Körperschaft des öffentlichen Rechts | Material testing method and material testing device |
| CN113325008A (en) * | 2021-06-02 | 2021-08-31 | 合肥工业大学 | Non-contact material identification system and method based on WIFI equipment |
| CN113325008B (en) * | 2021-06-02 | 2022-09-20 | 合肥工业大学 | Non-contact material identification system and method based on WIFI equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105469079A (en) | Object material identification method based on multi-sensor information fusion | |
| CN110018524B (en) | X-ray security inspection contraband identification method based on vision-attribute | |
| Pasolli et al. | Automatic analysis of GPR images: A pattern-recognition approach | |
| CN102799903B (en) | High-spectrum automatic cloud detection method based on space and spectral information | |
| CN102959354B (en) | Method and apparatus for for analyzing tree canopies with LiDAR data | |
| CN108416378A (en) | A kind of large scene SAR target identification methods based on deep neural network | |
| Borgioli et al. | The detection of buried pipes from time-of-flight radar data | |
| CN108182450A (en) | A kind of airborne Ground Penetrating Radar target identification method based on depth convolutional network | |
| Zhang et al. | A GANs-based deep learning framework for automatic subsurface object recognition from ground penetrating radar data | |
| CN102928435A (en) | Aircraft skin damage identification method and device based on image and ultrasound information fusion | |
| CN102621150A (en) | Airplane skin damage identification method based on gray level co-occurrence matrix and support vector machine | |
| JPWO2014065032A1 (en) | Electromagnetic field feature classification presentation device | |
| CN107193001B (en) | Karst tunnel unfavorable geology forecasting expert system based on ground penetrating radar and implementation method | |
| CN107169469A (en) | A kind of material identification method of the MIMO radar based on machine learning | |
| CN113850228A (en) | Road crack detection method and system based on multi-mode fusion | |
| CN110427878A (en) | A kind of sudden and violent signal recognition method of Rapid Radio and system | |
| Barkataki et al. | Classification of soil types from GPR B scans using deep learning techniques | |
| CN113866102A (en) | Soil health investigation monitoring method based on spectrum | |
| CN107300562B (en) | X-ray nondestructive testing method for measuring contact distance of finished relay product | |
| Ahmadvand et al. | 1D-CNNs for autonomous defect detection in bridge decks using ground penetrating radar | |
| Cromwell et al. | Lidar cloud detection with fully convolutional networks | |
| CN107727749A (en) | A kind of ultrasonic quantitative detection method based on wavelet packet fusion feature extraction algorithm | |
| CN102445712B (en) | Character window weighting related spectrum matching method facing rocks and minerals | |
| CN114355462A (en) | Human hidden dangerous object detection method and medium based on micro-Doppler characteristics | |
| Syambas | An approach for predicting the shape and size of a buried basic object on surface ground penetrating radar system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160406 |
|
| RJ01 | Rejection of invention patent application after publication |