CN107341788A - A kind of assessment method of unmanned plane inspection operation image - Google Patents
A kind of assessment method of unmanned plane inspection operation image Download PDFInfo
- Publication number
- CN107341788A CN107341788A CN201610029971.8A CN201610029971A CN107341788A CN 107341788 A CN107341788 A CN 107341788A CN 201610029971 A CN201610029971 A CN 201610029971A CN 107341788 A CN107341788 A CN 107341788A
- Authority
- CN
- China
- Prior art keywords
- image
- mrow
- quality
- grade
- unmanned plane
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of assessment method of unmanned plane inspection operation image, establishes the sample image storehouse by grade classification;Establish quality of image grade evaluation equation;Unmanned plane cruising inspection system is controlled to carry out operation image collection;Performance rating is carried out to operation image according to sample image storehouse and quality of image grade evaluation equation.Method proposed by the present invention can realize the objective evaluation of the equipment performance to power transmission line unmanned machine cruising inspection system, be efficiently and accurately the unmanned plane of Corporation system screening high-quality;Inspection quality that simultaneously also can be to production unit carries out objective evaluation, reliably improves circuit fortune inspection quality.
Description
Technical field
The present invention relates to power transmission and transforming equipment running status to overhaul field, and in particular to a kind of unmanned plane inspection operation image is commented
Determine method.
Background technology
In terms of circuit operation maintenance, unmanned plane cruising inspection system is mainly used in patrolling power transmission lines apparatus body and passage is walked
Corridor, detection device and channel defect.Depopulated helicopter, which is laid particular emphasis on, carries out transmission line of electricity single column or section inspection, failure inspection,
It is easy to find overhead line structures bottleneck disadvantages described above.Although task device type is more, application is more, can be directly used in and sentence
Determine defect is still visible image.
In inspection operation, unmanned plane cruising inspection system can be by the inspection image transmission of airborne acquisition to ground, but is transmitted
The limitation of bandwidth, the quality of image of transmission are affected, it is difficult to for defect dipoles.In general working method is:Nobody
Task device on machine cruising inspection system by the different parts of examined in determination quickly to continuously being taken pictures, after gathering high-resolution image,
Manual or automatic judgement is carried out on ground.The complexity of determining defects has much relations, but existing shadow with the quality of image
As evaluation index is difficult to fully meet power industry application demand, at present there is no for power transmission line unmanned machine inspection image
Grade scale.
The content of the invention
In view of this, the assessment method of a kind of unmanned plane inspection operation image provided by the invention, this method can be realized pair
The objective evaluation of the equipment performance of power transmission line unmanned machine cruising inspection system, it is efficiently and accurately Corporation system screening high-quality
Unmanned plane;Inspection quality that simultaneously also can be to production unit carries out objective evaluation, reliably improves circuit fortune inspection quality.
The purpose of the present invention is achieved through the following technical solutions:
A kind of assessment method of unmanned plane inspection operation image, methods described comprise the following steps:
Step 1. establishes the sample image storehouse by grade classification;
Step 2. establishes quality of image grade evaluation equation;
Step 3. control unmanned plane cruising inspection system carries out operation image collection;
Step 4. carries out quality to the operation image according to the sample image storehouse and quality of image grade evaluation equation and commented
It is fixed.
Preferably, the step 1 includes:
1-1. obtains the sample image that each unmanned plane inspection operation collecting device gathers in the range of different distance, wherein each institute
State unmanned plane inspection operation collecting device and be respectively provided with different detector sizes and focusing mode;
Polling transmission line image is divided into multiple grades by 1-2. by the height of interpretation degree;
1-3. is classified to the sample image by the level of the polling transmission line image, obtains evaluation result;
1-4. screens the evaluation result, obtains the sample image storehouse.
Count the evaluation result, and the sample shadow of the selection standard difference between 0.6-0.8 in the evaluation result
As being used as sample image storehouse.
Preferably, the grade of the polling transmission line image in the step 1-2 includes:
1 grade-Ambiguity resolution steel tower, 2 grades-it is secondary it is clear differentiate steel tower, 3 grades-clearly differentiate steel tower, 4 grades-it is clear differentiate it is exhausted
Edge, 5 grades-clearly differentiate stockbridge damper, 6 grades-clear differentiate nut and 7 grades-clearly differentiate pin.
Preferably, the step 1-4 includes:
Count the evaluation result, and the sample shadow of the selection standard difference between 0.6-0.8 in the evaluation result
As being used as sample image storehouse.
Preferably, the step 2 includes:
2-1. carries out primary treatment to the image in each grade in the sample image storehouse respectively;
The quality of image of each image after 2-2. calculating processing;
2-3. establishes quality of image grade evaluation equation according to the quality of image and grade of each image.
Preferably, the primary treatment in the step 2-1 includes noise measuring and filtering;
The noise measuring includes carrying out Fourier transformation to the image, asks to obtain the power spectrum of polar coordinate representation;
The filtering includes being modified the power spectrum with wiener noise filter.
Preferably, the step 2-2 includes:
The quality of image IQM of each image after calculating processing:
In formula (1), M*N is the pixel count in image;S(θ1) for proportionality coefficient andW(ρ)
To correct Wiener filter;A2(Tρ) be human visual system MTF square;P (ρ, θ) is shadow in the case of polar coordinates
The two-dimensional power spectrum of picture.
Preferably, the step 2-3 includes:
According to the quality of image and grade of each image, the relation being fitted between image grade and the quality of image, shadow is obtained
As quality grade of evaluation equation:
I=2.2log10IQM+8.4 (2)
In formula (2), I is the grade of the image;IQM is the quality of image of the image.
Preferably, the step 3 includes:
3-1. control unmanned plane cruising inspection systems are shot in the range of 10-30m to photographic subjects, and in the scene shot
Including steel tower, insulator, stockbridge damper, nut and pin target;
3-2. records the focal length f and pel spacing q of unmanned plane inspection operation collecting device in the unmanned plane cruising inspection system;
Unmanned plane obtains operation image to the distance D of the photographic subjects when measuring simultaneously records photographing.
Preferably, the step 4 includes:
The operation image that 4-1. is shot to unmanned plane cruising inspection system carries out noise measuring and filtering process;
4-2. is calculated described by described in after processing according to the sample image storehouse and quality of image grade evaluation equation
The quality of image and grade I of operation image;
4-3. I is rounded up after as the operation image final mass grade, complete the matter to the operation image
Amount evaluation.
It can be seen from the above technical scheme that the invention provides a kind of assessment method of unmanned plane inspection operation image,
Establish the sample image storehouse by grade classification;Establish quality of image grade evaluation equation;Unmanned plane cruising inspection system is controlled to carry out
Operation image collection;Performance rating is carried out to operation image according to sample image storehouse and quality of image grade evaluation equation.This
The method that invention proposes can realize the objective evaluation of the equipment performance to power transmission line unmanned machine cruising inspection system, effectively and accurate
It is really the unmanned plane of Corporation system screening high-quality;Inspection quality that simultaneously also can be to production unit carries out objective evaluation, can
That leans on improves circuit fortune inspection quality.
With immediate prior art ratio, technical scheme provided by the invention has following excellent effect:
1st, in technical scheme provided by the present invention, entirely it is imaged by quantitative evaluation in link and has an impact image interpretation
Degree single or multiple factors, the mission requirements of user are connected with the quality of image, to image carry out quality grading and
Interpretation of result, realize the objective evaluation of the equipment performance to power transmission line unmanned machine cruising inspection system, efficiently and accurately for
The unmanned plane of Corporation system screening high-quality;Inspection quality that simultaneously also can be to production unit carries out objective evaluation, reliably carries
High circuit fortune inspection quality.
2nd, technical scheme provided by the present invention, performance rating, energy can be carried out to the visible image of unmanned plane inspection
The quality of reflection unmanned plane cruising inspection system directly perceived, screen the unmanned plane cruising inspection system of qualified polling transmission line;And energy
The manipulation technical ability of reflection patrol officer indirectly, improve the quality and efficiency of unmanned plane inspection transmission line of electricity.
3rd, technical scheme provided by the invention, is widely used, and has significant Social benefit and economic benefit.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the assessment method of unmanned plane inspection operation image of the present invention;
Fig. 2 is the schematic flow sheet of step 1 in assessment method of the invention;
Fig. 3 is the schematic flow sheet of step 2 in assessment method of the invention;
Fig. 4 is the schematic flow sheet of step 3 in assessment method of the invention;
Fig. 5 is the schematic flow sheet of step 4 in assessment method of the invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Base
In embodiments of the invention, those of ordinary skill in the art obtained under the premise of creative work is not made it is all its
His embodiment, belongs to the scope of protection of the invention.
As shown in figure 1, the present invention provides a kind of assessment method of unmanned plane inspection operation image, comprise the following steps:
Step 1. establishes the sample image storehouse by grade classification;
Step 2. establishes quality of image grade evaluation equation;
Step 3. control unmanned plane cruising inspection system carries out operation image collection;
Step 4. carries out performance rating according to sample image storehouse and quality of image grade evaluation equation to operation image.
As shown in Fig. 2 step 1 includes:
1-1. obtains the sample image that each unmanned plane inspection operation collecting device gathers in the range of different distance, wherein each nothing
Man-machine inspection operation collecting device is respectively provided with different detector sizes and focusing mode;
Polling transmission line image is divided into multiple grades by 1-2. by the height of interpretation degree;
1-3. is classified to sample image by the level of polling transmission line image, obtains evaluation result;
1-4. screens evaluation result, obtains sample image storehouse.
Statistical evaluation result, and in evaluation result sample image of the selection standard difference between 0.6-0.8 as sample shadow
As storehouse.
Wherein, the grade of the polling transmission line image in step 1-2 includes:
1 grade-Ambiguity resolution steel tower, 2 grades-it is secondary it is clear differentiate steel tower, 3 grades-clearly differentiate steel tower, 4 grades-it is clear differentiate it is exhausted
Edge, 5 grades-clearly differentiate stockbridge damper, 6 grades-clear differentiate nut and 7 grades-clearly differentiate pin.
Wherein, step 1-4 includes:
Statistical evaluation result, and in evaluation result sample image of the selection standard difference between 0.6-0.8 as sample shadow
As storehouse.
As shown in figure 3, step 2 includes:
2-1. carries out primary treatment to the image in each grade in sample image storehouse respectively;
The quality of image of each image after 2-2. calculating processing;
2-3. establishes quality of image grade evaluation equation according to the quality of image and grade of each image.
Wherein, the primary treatment in step 2-1 includes noise measuring and filtering;
Noise measuring includes carrying out Fourier transformation to image, asks to obtain the power spectrum of polar coordinate representation;
Filtering includes being modified power spectrum with wiener noise filter.
Wherein, step 2-2 includes:
The quality of image IQM of each image after calculating processing:
In formula (1), M*N is the pixel count in image;S(θ1) for proportionality coefficient andW(ρ)
To correct Wiener filter;A2(Tρ) be human visual system MTF square;P (ρ, θ) is shadow in the case of polar coordinates
The two-dimensional power spectrum of picture.
Wherein, step 2-3 includes:
According to the quality of image and grade of each image, the relation being fitted between image grade and the quality of image, image matter is obtained
Measure grade evaluation equation:
I=2.2log10IQM+8.4 (2)
In formula (2), I is the grade of image;IQM is the quality of image of image.
As shown in figure 4, step 3 includes:
3-1. control unmanned plane cruising inspection systems are shot in the range of 10-30m to photographic subjects, and in the scene shot
Including steel tower, insulator, stockbridge damper, nut and pin target;
The focal length f and pel spacing q of unmanned plane inspection operation collecting device in 3-2. record unmanned plane cruising inspection systems;Measurement
And unmanned plane to the distance D of photographic subjects, obtains operation image during records photographing.
As shown in figure 5, step 4 includes:
The operation image that 4-1. is shot to unmanned plane cruising inspection system carries out noise measuring and filtering process;
4-2. is calculated the shadow of the operation image after processing according to sample image storehouse and quality of image grade evaluation equation
As quality and grade I;
4-3. I is rounded up after as operation image final mass grade, complete the performance rating to operation image.
The present invention provides a kind of concrete application example of the assessment method of unmanned plane inspection operation image, as follows:
1) different grades of sample image storehouse is established, establishes quality of image grade evaluation equation:
1-1) use different detector sizes, the equipment of different focus mode different apart from collecting sample image.
Polling transmission line image interpretation degree 1-2) is divided into seven levels, 1 grade be Ambiguity resolution steel tower, 2 grades be time clear
Clear 3 grades of steel tower of resolution for can clearly differentiate steel tower, 4 grades be it is clear differentiate insulator, 5 grades for can clearly differentiate stockbridge damper,
6 grades can clearly to differentiate nut, 7 grades is can clearly differentiate pin.
Evaluation classification 1-3) is carried out to sample image storehouse by several professional image analysing computer personnel, evaluation result is counted
Analysis, the image that selection standard difference is 0.7 is as sample image storehouse.
1-4) establish the calculation formula of quality of image grade:
1-4-1) image of each grade in sample image storehouse is handled as follows respectively, calculates the image of every width image
Quality.
1-4-1-1) noise measuring.Fourier transformation is carried out to image, seeks the power spectrum of polar coordinate representation.
1-4-1-2) filter.The image power spectrum of calculating is modified using wiener noise filter.
The quality of image 1-4-1-3) is calculated as follows:
Wherein, M*N is the pixel count in image (image size is M × N pixels);For ratio system
Number,;W (ρ) is amendment Wiener filter;A2(Tρ) be human visual system MTF square;P (ρ, θ) is polar coordinates
In the case of image two-dimensional power spectrum.
1-4-2) according to the IQM of every width image and its corresponding quality of image grade be fitted quality of image grade and IQM it
Between relation, it is as a result as follows:
I=2.2log10IQM+8.4
2) image collection:
2-1) unmanned plane cruising inspection system is shot in the range of 20m to target, scene domestic demand include part steel tower, absolutely
Edge, stockbridge damper, nut and pin target;
2-2) record the focal length f, pel spacing q of task device in unmanned plane cruising inspection system;Measure shooting time unmanned plane
Range-to-go D is simultaneously recorded.
3) quality of image is evaluated:
Noise measuring, filtering are carried out to the image of shooting, according to step 1-4-1-3) in formula calculate its IQM, according to
Step 1-4-2) in formula calculate its quality of image grade, as quality of the image etc. after I result is rounded up
Level.
The above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, although with reference to above-described embodiment to this
Invention is described in detail, and those of ordinary skill in the art can still enter to the embodiment of the present invention
Row modification or equivalent substitution, and these are without departing from any modification of spirit and scope of the invention or equivalent substitution, its is equal
Applying within pending claims of the invention.
Claims (10)
1. a kind of assessment method of unmanned plane inspection operation image, it is characterised in that methods described comprises the following steps:
Step 1. establishes the sample image storehouse by grade classification;
Step 2. establishes quality of image grade evaluation equation;
Step 3. control unmanned plane cruising inspection system carries out operation image collection;
Step 4. carries out quality to the operation image according to the sample image storehouse and quality of image grade evaluation equation and commented
It is fixed.
2. method as claimed in claim 2, it is characterised in that the step 1 includes:
1-1. obtains the sample image that each unmanned plane inspection operation collecting device gathers in the range of different distance, wherein each institute
State unmanned plane inspection operation collecting device and be respectively provided with different detector sizes and focusing mode;
Polling transmission line image is divided into multiple grades by 1-2. by the height of interpretation degree;
1-3. is classified to the sample image by the level of the polling transmission line image, obtains evaluation result;
1-4. screens the evaluation result, obtains the sample image storehouse.
Count the evaluation result, and the sample shadow of the selection standard difference between 0.6-0.8 in the evaluation result
As being used as sample image storehouse.
3. method as claimed in claim 2, it is characterised in that the polling transmission line in the step 1-2
The grade of image includes:
1 grade-Ambiguity resolution steel tower, 2 grades-it is secondary it is clear differentiate steel tower, 3 grades-clearly differentiate steel tower, 4 grades-it is clear differentiate it is exhausted
Edge, 5 grades-clearly differentiate stockbridge damper, 6 grades-clear differentiate nut and 7 grades-clearly differentiate pin.
4. method as claimed in claim 2, it is characterised in that the step 1-4 includes:
Count the evaluation result, and the sample shadow of the selection standard difference between 0.6-0.8 in the evaluation result
As being used as sample image storehouse.
5. the method as described in claim 1, it is characterised in that the step 2 includes:
2-1. carries out primary treatment to the image in each grade in the sample image storehouse respectively;
The quality of image of each image after 2-2. calculating processing;
2-3. establishes quality of image grade evaluation equation according to the quality of image and grade of each image.
6. method as claimed in claim 5, it is characterised in that the primary treatment in the step 2-1 includes
Noise measuring and filtering;
The noise measuring includes carrying out Fourier transformation to the image, asks to obtain the power spectrum of polar coordinate representation;
The filtering includes being modified the power spectrum with wiener noise filter.
7. method as claimed in claim 5, it is characterised in that the step 2-2 includes:
The quality of image IQM of each image after calculating processing:
<mrow>
<mi>I</mi>
<mi>Q</mi>
<mi>M</mi>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>M</mi>
<mo>*</mo>
<mi>N</mi>
</mrow>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>&theta;</mi>
<mo>=</mo>
<mo>-</mo>
<mn>180</mn>
</mrow>
<mn>180</mn>
</munderover>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>&rho;</mi>
<mo>=</mo>
<mn>0.01</mn>
</mrow>
<mn>0.5</mn>
</munderover>
<mrow>
<mi>S</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>&theta;</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
<mi>W</mi>
<mrow>
<mo>(</mo>
<mi>&rho;</mi>
<mo>)</mo>
</mrow>
<msup>
<mi>A</mi>
<mn>2</mn>
</msup>
<mrow>
<mo>(</mo>
<msub>
<mi>T</mi>
<mi>&rho;</mi>
</msub>
<mo>)</mo>
</mrow>
<mi>P</mi>
<mrow>
<mo>(</mo>
<mrow>
<mi>&rho;</mi>
<mo>,</mo>
<mi>&theta;</mi>
</mrow>
<mo>)</mo>
</mrow>
</mrow>
</mrow>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
In formula (1), M*N is the pixel count in image;S(θ1) for proportionality coefficient andW(ρ)
To correct Wiener filter;A2(Tρ) be human visual system MTF square;P (ρ, θ) is shadow in the case of polar coordinates
The two-dimensional power spectrum of picture.
8. method as claimed in claim 5, it is characterised in that the step 2-3 includes:
According to the quality of image and grade of each image, the relation being fitted between image grade and the quality of image, shadow is obtained
As quality grade of evaluation equation:
I=2.2log10IQM+8.4 (2)
In formula (2), I is the grade of the image;IQM is the quality of image of the image.
9. the method as described in claim 1, it is characterised in that the step 3 includes:
3-1. control unmanned plane cruising inspection systems are shot in the range of 10-30m to photographic subjects, and in the scene shot
Including steel tower, insulator, stockbridge damper, nut and pin target;
3-2. records the focal length f and pel spacing q of unmanned plane inspection operation collecting device in the unmanned plane cruising inspection system;
Unmanned plane obtains operation image to the distance D of the photographic subjects when measuring simultaneously records photographing.
10. the method as described in claim 1, it is characterised in that the step 4 includes:
The operation image that 4-1. is shot to unmanned plane cruising inspection system carries out noise measuring and filtering process;
4-2. is calculated described by described in after processing according to the sample image storehouse and quality of image grade evaluation equation
The quality of image and grade I of operation image;
4-3. I is rounded up after as the operation image final mass grade, complete the matter to the operation image
Amount evaluation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610029971.8A CN107341788A (en) | 2016-01-18 | 2016-01-18 | A kind of assessment method of unmanned plane inspection operation image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610029971.8A CN107341788A (en) | 2016-01-18 | 2016-01-18 | A kind of assessment method of unmanned plane inspection operation image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107341788A true CN107341788A (en) | 2017-11-10 |
Family
ID=60221694
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610029971.8A Pending CN107341788A (en) | 2016-01-18 | 2016-01-18 | A kind of assessment method of unmanned plane inspection operation image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107341788A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109213189A (en) * | 2018-07-19 | 2019-01-15 | 安徽共生物流科技有限公司 | A kind of unmanned plane inspection system and movement determination method |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011097696A1 (en) * | 2010-02-12 | 2011-08-18 | Ecole De Technologie Superieure | Method and system for determining a quality measure for an image using a variable number of multi-level decompositions |
CN103941746A (en) * | 2014-03-29 | 2014-07-23 | 国家电网公司 | System and method for processing unmanned aerial vehicle polling image |
-
2016
- 2016-01-18 CN CN201610029971.8A patent/CN107341788A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011097696A1 (en) * | 2010-02-12 | 2011-08-18 | Ecole De Technologie Superieure | Method and system for determining a quality measure for an image using a variable number of multi-level decompositions |
CN103941746A (en) * | 2014-03-29 | 2014-07-23 | 国家电网公司 | System and method for processing unmanned aerial vehicle polling image |
Non-Patent Citations (2)
Title |
---|
王昱等: "面向测绘任务的光学遥感影像质量分级评定", 《中国图象图形学报》 * |
白宏刚: "基于NIIRS的遥感系统像质预估与评价方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109213189A (en) * | 2018-07-19 | 2019-01-15 | 安徽共生物流科技有限公司 | A kind of unmanned plane inspection system and movement determination method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10269138B2 (en) | UAV inspection method for power line based on human visual system | |
CN110648364B (en) | Multi-dimensional space solid waste visual detection positioning and identification method and system | |
CN104729718B (en) | A kind of processing system and method for infrared imaging system NETD | |
CN104914111A (en) | Strip steel surface defect on-line intelligent identification and detection system and detection method | |
CN107063949A (en) | Measure the methods, devices and systems of mist droplet deposition distribution situation | |
CN109934811A (en) | A kind of optical element surface defect inspection method based on deep learning | |
CN104976960A (en) | Raindrop physical property observation method and device | |
CN107392247A (en) | Atural object safe distance real-time detection method below a kind of power line | |
CN103413150A (en) | Power line defect diagnosis method based on visible light image | |
CN103808723A (en) | Exhaust gas blackness automatic detection device for diesel vehicles | |
CN103234475B (en) | Sub-pixel surface morphology detecting method based on laser triangular measuring method | |
CN107527037A (en) | Blue-green algae identification and analysis system based on unmanned aerial vehicle remote sensing data | |
CN104236859A (en) | Satellite-borne area array CCD camera point spread function measuring device and method | |
CN104713486B (en) | One kind is puted the palms together before one product width on-line measuring device and method | |
CN103674968A (en) | Method and device for evaluating machine vision original-value detection of exterior corrosion appearance characteristics of material | |
CN102621154B (en) | Method and device for automatically detecting cloth defects on line based on improved differential box multi-fractal algorithm | |
CN105606619A (en) | Detection and grinding optimization method for casting blank grinding machine | |
CN107218891A (en) | A kind of dimension measurement method, apparatus and system | |
CN110020691A (en) | LCD screen defect inspection method based on the training of convolutional neural networks confrontation type | |
CN108931774A (en) | Convective precipitation based on lightning data identifies examination and test of products method and system | |
CN106320173B (en) | Vehicle-mounted unmanned aerial vehicle bridge routine safety detection system and detection method | |
CN102589415A (en) | Metering type digital image plane equal thickness interferometer and method for measuring flatness of object surface by employing the same | |
CN107341788A (en) | A kind of assessment method of unmanned plane inspection operation image | |
CN102135415A (en) | Device and method for measuring aperture of foamed aluminum based on machine vision | |
CN112734732B (en) | Railway tunnel cable leakage clamp detection method based on improved SSD algorithm |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171110 |
|
RJ01 | Rejection of invention patent application after publication |