CN109242821A - Air Quality Evaluation method, system, equipment and storage medium based on image quality evaluation - Google Patents
Air Quality Evaluation method, system, equipment and storage medium based on image quality evaluation Download PDFInfo
- Publication number
- CN109242821A CN109242821A CN201810783240.1A CN201810783240A CN109242821A CN 109242821 A CN109242821 A CN 109242821A CN 201810783240 A CN201810783240 A CN 201810783240A CN 109242821 A CN109242821 A CN 109242821A
- Authority
- CN
- China
- Prior art keywords
- air quality
- index
- quality evaluation
- image
- haze image
- 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
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 4
- 235000008434 ginseng Nutrition 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- 239000003570 air Substances 0.000 description 156
- 239000003344 environmental pollutant Substances 0.000 description 16
- 231100000719 pollutant Toxicity 0.000 description 16
- 238000011156 evaluation Methods 0.000 description 10
- RAHZWNYVWXNFOC-UHFFFAOYSA-N Sulphur dioxide Chemical compound O=S=O RAHZWNYVWXNFOC-UHFFFAOYSA-N 0.000 description 6
- 239000013256 coordination polymer Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- MGWGWNFMUOTEHG-UHFFFAOYSA-N 4-(3,5-dimethylphenyl)-1,3-thiazol-2-amine Chemical compound CC1=CC(C)=CC(C=2N=C(N)SC=2)=C1 MGWGWNFMUOTEHG-UHFFFAOYSA-N 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 2
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 2
- 239000012080 ambient air Substances 0.000 description 2
- 229910002091 carbon monoxide Inorganic materials 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- JCXJVPUVTGWSNB-UHFFFAOYSA-N nitrogen dioxide Inorganic materials O=[N]=O JCXJVPUVTGWSNB-UHFFFAOYSA-N 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 239000000809 air pollutant Substances 0.000 description 1
- 231100001243 air pollutant Toxicity 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000010419 fine particle Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 231100000206 health hazard Toxicity 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
- G01N15/075—Investigating concentration of particle suspensions by optical means
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
-
- 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
- G06T2207/30181—Earth observation
- G06T2207/30192—Weather; Meteorology
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Dispersion Chemistry (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The present invention relates to Air Quality Evaluation method, system, equipment and storage mediums based on image quality evaluation, Air Quality Evaluation method based on image quality evaluation of the invention, comprising the following steps: the haze image under S1, the multiple and different air quality indexs of acquisition；S2, the picture appraisal index that haze image is obtained by no-reference image quality evaluation algorithms, and establish the picture appraisal index of haze image and the corresponding relationship of air quality index；S3, it obtains a real-time haze image and calculates the picture appraisal index of real-time haze image by no-reference image quality evaluation algorithms；S4, the picture appraisal index air quality index corresponding with the corresponding relationship of the air quality index real-time haze image of acquisition by haze image.Implement the real-time air quality grade of acquisition that the present invention can be simple and fast, at low cost, application scenarios are wide.
Description
Technical field
The present invention relates to Air Quality Evaluation technical field, more specifically to a kind of based on image quality evaluation
Air Quality Evaluation method, system, equipment and storage medium.
Background technique
It is well known that the air quality index under monitoring haze weather has important practical significance.Once index value is super
Warning line is crossed, the obligated timely publication warning information of national weather department instructs society to carry out the precautionary measures.Wherein:
Air monitering refer to the polluter being present in air is pinpointed, continuous or timing sampling and measurement.
In order to be monitored to air, several air monitering points generally are set up in a city, installation automatic monitor is made continuous
Automatic monitoring, monitoring result is sent someone periodically to fetch, is analyzed and obtains relevant data.The project of air monitering is mainly wrapped
Include sulfur dioxide, nitric oxide, hydrocarbon, floating dust etc..Air monitering is air quality air and carries out to air quality
The basis of rational evaluation.
Air quality index (Air quality index, AQI) is according to ambient air quality and every pollutant
Influence to human health, ecology, environment, several air pollutant concentrations of routine monitoring, which are simplified, becomes single conceptual
Index value form, it indicates air pollution degree and Air Quality classification, is suitable for indicating the short-term air matter in city
Amount situation and variation tendency.For individual event pollutant, air quality separate index number is alsied specify.Participate in the main of Air Quality Evaluation
Pollutant is fine particle (PM2.5), pellet (PM10), sulfur dioxide (SO2), nitrogen dioxide (NO2), ozone
(O3), carbon monoxide (CO) etc. six.
Air quality is divided into six grades according to air quality index size by air quality classification, and the six of corresponding air quality
A classification, index is bigger, rank is higher illustrates that the case where polluting is more serious, also bigger to the health hazard of human body, from level-one
Excellent, second level is good, three-level slight pollution, level Four intermediate pollution, until Pyatyi serious pollution, six grades of serious pollutions.
When PM2.5 annual average concentration reaches 150 micrograms/cubic meter, AQI reaches 200；When the average daily concentration of PM2.5 reaches
When to 250 micrograms/cubic meter, AQI is i.e. up to 300；When the average daily concentration of PM2.5 reaches 500 micrograms/cubic meter, corresponding AQI index
Reach 500.It is provided according to " ambient air quality index (AQI) technical stipulation (tentative) " (HJ 633-2012): air pollution
Index is divided into 0-50,51-100,101-150,151-200,201-300 and is greater than 300 6 grades, corresponding to air matter
Six ranks of amount, index is bigger, and rank is higher, illustrates that pollution is more serious, the influence to human health is also more obvious.
And existing Air Quality Evaluation method AQI index characterization be pollution level calculating process it is as follows:
Firstly, calculated separately by following formula obtain air quality separate index number (Individual air quality index,
IAQI)；
In formula:
IAQIP --- the air quality separate index number of pollutant project P；
CP --- the mass concentration value of pollutant project P；
In BPHi --- table 1 (the air quality separate index number of corresponding area and corresponding pollutant project concentration index table) with
The high-value of pollutant concentration limit value similar in CP；
In BPLo --- table 1 (the air quality separate index number of corresponding area and corresponding pollutant project concentration index table) with
The low-value of pollutant concentration limit value similar in CP；
In IAQIHi --- table 1 (the air quality separate index number of corresponding area and corresponding pollutant project concentration index table)
Air quality separate index number corresponding with BPHi；
In IAQILo --- table 1 (the air quality separate index number of corresponding area and corresponding pollutant project concentration index table)
Air quality separate index number corresponding with BPLo.
Then, maximum value is selected to be determined as AQI from the IAQI of every pollutant referring to following formula.It, will when AQI is greater than 50
The maximum pollutant of IAQI is determined as primary pollutant.
AQI=max { IAQI1,IAQI2,IAQI3..., IAQIn}
In formula:
IAQI --- air quality separate index number；
N --- pollutant project.
Finally, AQI grade scale can be compareed, determine air quality rank, classification and indicate color, it is analyzed to health
It influences, and suggests the measure taken.
According to existing AQI acquisition methods, under the conditions of haze weather, existing air quality index calculation method exists certain
Limitation.It is specific as follows:
1) it, can not reflect real-time air quality (haze pollution level).It is well known that haze weather primary pollutant comes from
PM2.5 and PM10, and by IAQI formula of index it is found that PM2.5, PM10 are 24 hour average concentrations, not real-time concentration
Value.
2), existing calculation method instrument quantity monitored, cost restrict, it is impossible to the sky in each area in precise measurement city
Makings volume index can only obtain the air quality sampled data near limited several measurement points.
3), existing method is limited to the physical feasibility of monitoring site, for air quality monitor device not easy to place
Place can not acquire and calculate naturally air quality index.
Summary of the invention
The technical problem to be solved in the present invention is that being provided a kind of based on figure for the above-mentioned segmental defect of the prior art
As Air Quality Evaluation method, system, equipment and the storage medium of quality evaluation.
The technical solution adopted by the present invention to solve the technical problems is: constructing a kind of air based on image quality evaluation
Quality evaluating method, comprising the following steps:
Haze image under S1, the multiple and different air quality indexs of acquisition；
S2, the picture appraisal index that the haze image is obtained by no-reference image quality evaluation algorithms, and establish
The picture appraisal index of the haze image and the corresponding relationship of the air quality index；
S3, it obtains a real-time haze image and calculates the real-time mist by the no-reference image quality evaluation algorithms
The picture appraisal index of haze image；
Described in S4, the corresponding relationship acquisition by the picture appraisal index and the air quality index of the haze image
The corresponding air quality index of real-time haze image.
Preferably, in the step S2, the picture appraisal index for establishing the haze image and the air matter
The corresponding relationship of volume index includes:
S2-1, the scatter plot for drawing the haze image corresponding picture appraisal index and air quality index, and calculate
Matched curve.
Preferably, in the step S2-1, the digital simulation curve includes calculating three rank multinomial matched curves.
Preferably, in the step S2, the no-reference image quality evaluation algorithms include BLIINDS2, M3,
Any one in BRISQUE, STAIND, BIQI, CurveletQA and DIIVINE image quality evaluation algorithm.
The present invention also constructs a kind of Air Quality Evaluation system based on image quality evaluation, comprising: monitoring unit and institute
State the first processing units and the second processing unit, the output unit that connect with described the second processing unit of monitoring unit connection；
The monitoring unit is used to obtain the haze image under multiple and different air quality indexs；
The first processing units are used to obtain the figure of the haze image by no-reference image quality evaluation algorithms
As evaluation index, and establish the picture appraisal index of the haze image and the corresponding relationship of the air quality index；
The monitoring unit is also used to obtain a real-time haze image；
Described the second processing unit is used to calculate the real-time haze by the no-reference image quality evaluation algorithms
The picture appraisal index of image；And it is closed by the way that the picture appraisal index of the haze image is corresponding with the air quality index
System obtains the corresponding air quality index of the real-time haze image；
The output unit is for exporting the air quality index.
Preferably, the monitoring unit is high-definition camera.
Preferably, further include storage unit, the storage unit for store BLIINDS2, M3, BRISQUE, STAIND,
One of BIQI, CurveletQA and DIIVINE image quality evaluation algorithm is a variety of, and the first processing units are according to it
In any one obtain the picture appraisal index of the haze image.
Preferably, further include user terminal, the user terminal include the first processing units, the second processing unit and
Output unit.
The present invention also constructs a kind of computer equipment, including memory, processor and is stored on reservoir and can locate
The computer program run on reason device, the processor are realized recited above based on image matter when executing the computer program
The step of measuring the Air Quality Evaluation method of evaluation.
The present invention also constructs a kind of computer storage medium, the computer-readable recording medium storage program, the journey
Sequence can be executed by processor, the step of to realize Air Quality Evaluation method based on image quality evaluation as described above.
Implement Air Quality Evaluation method, system, equipment and the storage medium of the invention based on image quality evaluation, has
Have it is following the utility model has the advantages that can be simple and fast the real-time air quality grade of acquisition, at low cost, application scenarios are wide.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the program flow diagram of the Air Quality Evaluation method the present invention is based on image quality evaluation；
Fig. 2 is the schematic diagram of the corresponding relationship of picture appraisal index and air quality index in the present invention；
Fig. 3 is that haze image in one embodiment of haze image is obtained in Fig. 1；
Fig. 4 is the corresponding air quality index of haze image in Fig. 3；
Fig. 5 is the structural schematic diagram of one embodiment of Air Quality Evaluation system the present invention is based on image quality evaluation.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, now control attached drawing is described in detail
A specific embodiment of the invention.
As shown in Figure 1, in Air Quality Evaluation method one embodiment of the invention based on image quality evaluation, including
Following steps:
Haze image under S1, the multiple and different air quality indexs (AQI) of acquisition；Specifically, passing through the same camera
The same position is repeatedly shot, the haze image got is shot here as far as possible and can correspond to multiple and different quality and refer to
Number, it will be understood that herein, the corresponding air quality index of haze image (AQI) is more, behind to Air Quality Evaluation
Accuracy is higher.For example, common air quality index (AQI) include 0-50,51-100,101-150,151-200,
201-300 and it is greater than 300 6 grades, then when obtaining from different air quality indexs (AQI) corresponding haze image, it can be with
Making in haze image corresponding air quality index (AQI) as far as possible includes six shelves above, and in the conceived case, every
It all include an appropriate number of haze image in a air quality index (AQI) shelves.
S2, the picture appraisal index (NRIQA) that haze image is obtained by no-reference image quality evaluation algorithms, and build
The picture appraisal index (NRIQA) of vertical haze image and the corresponding relationship of air quality index (AQI)；Specifically, getting
After haze image corresponding with each air quality index (AQI), pass through common no-reference image quality evaluation algorithms pair
Multiple haze image carries out image quality evaluation, corresponding picture appraisal index (NRIQA) is obtained, in this manner it is possible to understand
For, the corresponding air quality index (AQI) of haze image, as soon as and corresponding picture appraisal index (NRIQA), then
It can be by the way that the air quality index (AQI) of the same haze image and its picture appraisal index (NRIQA) (NRIQA) be established
Corresponding relationship.Herein, it will be understood that can be by certain Mathematical treatment means to the air quality index of multiple haze images
(AQI) and picture appraisal index (NRIQA) carries out the confirmation of particular kind of relationship, for example, in many times most of haze image
The relationship of air quality index (AQI) and picture appraisal index (NRIQA) all meets a kind of particular kind of relationship, then can be by the spy
Determine relationship and is set as the air quality index (AQI) of haze image and the corresponding relationship of picture appraisal index (NRIQA).
S3, it obtains a real-time haze image and calculates real-time haze image by no-reference image quality evaluation algorithms
Picture appraisal index (NRIQA)；Specifically, working as the air quality index (AQI) and picture appraisal index (NRIQA) of haze image
Corresponding relationship have been able to confirm, it is available herein then the monitoring that can be carried out real-time haze image obtains
Any real-time haze image, and calculate by no-reference image quality evaluation algorithms the picture appraisal of real-time haze image
Index (NRIQA), it is to be noted here that the accuracy in order to guarantee air quality index (AQI), here to real-time haze figure
The picture appraisal index (NRIQA) of picture calculating use no-reference image quality evaluation algorithms will in step S2 without ginseng
It is identical to examine type image quality evaluation algorithm.
S4, it is obtained by the picture appraisal index (NRIQA) of haze image and the corresponding relationship of air quality index (AQI)
The real-time corresponding air quality index of haze image (AQI).Specifically, when the air quality index (AQI) and figure of haze image
As the corresponding relationship of evaluation index (NRIQA) has been able to confirm, the picture appraisal index (NRIQA) of real-time haze image is obtained
Afterwards, so that it may be obtained by the corresponding relationship of the picture appraisal index (NRIQA) of haze image and air quality index (AQI)
The real-time corresponding air quality index of haze image (AQI).
Further, in step s 2, the picture appraisal index (NRIQA) and air quality index of haze image are established
(AQI) corresponding relationship includes: S2-1, draws the corresponding picture appraisal index (NRIQA) of haze image and air quality index
(AQI) scatter plot, and digital simulation curve.Specifically, as shown in Fig. 2, establishing the picture appraisal index of haze image
(NRIQA) with the mathematical method of the corresponding relationship of air quality index (AQI), picture appraisal index can be first established herein
(NRIQA) picture appraisal index (NRIQA) is established as in some embodiments with the coordinate system of air quality index (AQI)
Ordinate, coordinate scale are arranged according to the scoring of picture appraisal index (NRIQA), such as common range is 1.5 to 5 points, often
Air quality index (AQI) is established as abscissa by 0.5 point of scale, and the scale of abscissa is according to common air quality
Index (AQI) includes 0-50,51-100,101-150,151-200,201-300 and is established greater than 300 6 grades,
The scatter plot of haze image corresponding picture appraisal index (NRIQA) and air quality index (AQI) is drawn in coordinate system, then
It is fitted according to scatter plot, establishes the matched curve of picture appraisal index (NRIQA) Yu air quality index (AQI).In this way,
The corresponding relationship of picture appraisal index (NRIQA) and air quality index (AQI) are the matched curve.
Further, in step S2-1, digital simulation curve includes calculating three rank multinomial matched curves.Specifically,
As described above, the matched curve of picture appraisal index (NRIQA) and air quality index (AQI) are entire air qualities
The key of index (AQI) evaluation, herein, it is possible to understand that the goodness of fit plaintiff of matched curve, to the sky of real-time haze image
The result of gas quality evaluation is more accurate, and to establish the matched curve of the high goodness of fit, and calculating process is more complicated, then guaranteeing
While the accuracy of the result of the Air Quality Evaluation of real-time haze image, calculation amount is reduced, in the method using suitable
Three rank multinomial matched curves can both guarantee accuracy.Such as common three rank multinomials matched curve is f (x)=ax3+
bx2+ cx+d, wherein f (x) is the score value of described image evaluation index (NRIQA), and x is the air quality index (AQI).Its
Middle a, b, c and d are constant, its value is same when some here obtains multiple and different air quality indexs in step sl
(AQI) there is particular kind of relationship for the quantity of the haze image under, but optimally its variation will not be because of for its value
The quantity occurs compared with macrorelief.As can be seen that haze image early period can be reduced in step sl by three rank multinomial
It obtains, to reduce entire calculating task, that is, can guarantee the accuracy to the air quality index (AQI) of real-time haze image.
Further, in step s 2, no-reference image quality evaluation algorithms include BLIINDS2, M3, BRISQUE,
Any one in STAIND, BIQI, CurveletQA and DIIVINE image quality evaluation algorithm.Specifically, in the present invention
In, it obtains image quality evaluation algorithm used by the picture appraisal index (NRIQA) of haze image and does not specially require.
Herein, a specific embodiment, Fig. 2 and Fig. 3 are respectively in the continuous 40 days daily 8:00-9 in same shooting location:
00 haze image and at that time corresponding air quality index (AQI) statistical average.Be respectively adopted BLIINDS2, M3,
BRISQUE, STAIND, BIQI, CurveletQA and DIIVINE calculate the picture appraisal index of each haze image
(NRIQA), and the air quality index (AQI) of wherein 80% haze image is randomly selected with picture appraisal index (NRIQA)
It is corresponded to, establishes air quality index (AQI) with the scatter plot of picture appraisal index (NRIQA), be then fitted, here
Three rank multinomial matched curves of fitting can refer to above description, then be verified with remaining 20% haze image, count
It calculates its corresponding picture appraisal index (NRIQA) and its air quality index (AQI) calculated is obtained according to matched curve,
It this is defined herein as air quality index (AQI) calculated value, then (this is defined herein as with its actual air quality index (AQI)
Air quality index (AQI) measured value) it compares.
Here pass through the calculation formula of linearly dependent coefficient (Linear Correlation Coefficient, LCC):
Wherein, x, y respectively represent air quality index (AQI) calculated value and air quality index of individual haze picture
(AQI) measured value, i represent picture number, and N represents picture sum,Respectively represent the air quality index of whole pictures
(AQI) calculated value average value and air quality index (AQI) average value.Air quality index (AQI) can also be counted herein
Calculation value directly corresponds to picture appraisal index (NRIQA) corresponding with air quality index (AQI) calculated value, calculates figure in this way
As the correlation of evaluation index (NRIQA) and air quality index (AQI) measured value, specifically join the following table 1, it can be seen that figure
Picture evaluation index (NRIQA) and the correlation of air quality index (AQI) measured value are higher, in this case, refer to from picture appraisal
The accuracy that mark (NRIQA) obtains air quality index (AQI) can satisfy requirement.
Here can also by rank correlation coefficient (Spearman Rank Order Correlation Coefficient,
SROCC):
Wherein, D represents difference between grade, is herein air quality index (AQI) calculated value and air quality index (AQI)
The absolute difference of measured value.Air quality index (AQI) calculated value can also directly be corresponded to herein and air quality
The corresponding picture appraisal index (NRIQA) of index (AQI) calculated value, calculates picture appraisal index (NRIQA) and air in this way
The correlation of performance figure (AQI) measured value, specifically joins the following table 1, it can be seen that picture appraisal index (NRIQA) and air
The correlation of performance figure (AQI) measured value is higher, in this case, obtains air quality from picture appraisal index (NRIQA) and refers to
The accuracy of number (AQI) can satisfy requirement.
Further, it is also possible to by root-mean-square error (Root Mean Squared Error, RMSE) formula:
Wherein, x, y respectively represent air quality index (AQI) calculated value and air quality index (AQI) of single picture
Measured value, N are test picture number.Here smaller by RMSE value it can be seen that coming, indicate that difference is smaller, then using the party
Air quality index (AQI) accuracy that method obtains is higher.Specifically it is referred to the following table 1.
In addition, here by the intermediate value LCC of the various no-reference image quality evaluation algorithms to use, intermediate value
SROCC and intermediate value RMSE are averaged, it is seen that, the air quality of the acquisition of various no-reference image quality evaluation algorithms
Index (AQI) closely, so various air quality no-reference image quality evaluation algorithms can be applicable in herein, and
Accuracy is able to satisfy requirement.
| NRIQA algorithm | Intermediate value LCC | Intermediate value SROCC | Intermediate value RMSE |
| BLIINDS2 | 0.9280 | 0.9167 | 24.5670 |
| M3 | 0.9344 | 0.9141 | 23.7349 |
| BRISQUE | 0.9426 | 0.9167 | 22.8049 |
| STAIND | 0.9614 | 0.9500 | 18.2564 |
| BIQI | 0.9511 | 0.9333 | 20.6651 |
| CurveletQA | 0.9467 | 0.9333 | 22.0918 |
| DIIVINE | 0.9545 | 0.9456 | 19.1929 |
| Average value | 0.9455 | 0.9300 | 21.6161 |
Table 1
In addition, as shown in figure 5, the Air Quality Evaluation system of the invention based on image quality evaluation, comprising: monitoring is single
Member, the first processing units being connect with monitoring unit and the second processing unit, the output unit being connect with the second processing unit；Prison
Control unit is used to obtain the haze image under multiple and different air quality indexs (AQI)；First processing units are for passing through no ginseng
The picture appraisal index (NRIQA) that type image quality evaluation algorithm obtains haze image is examined, and the image for establishing haze image is commented
The corresponding relationship of valence index (NRIQA) and air quality index (AQI)；Monitoring unit is also used to obtain a real-time haze image；
The second processing unit is used to calculate the picture appraisal index of real-time haze image by no-reference image quality evaluation algorithms
(NRIQA)；And it is obtained by the corresponding relationship of the picture appraisal index (NRIQA) of haze image and air quality index (AQI)
The real-time corresponding air quality index of haze image (AQI)；Output unit is used for delivery air performance figure (AQI).
Specifically, obtaining haze image by the same monitoring single unit, the haze image got here as far as possible can
Corresponding multiple and different performance figures, it will be understood that herein, the corresponding air quality index of haze image (AQI) is more, thereafter
Accuracy in face of Air Quality Evaluation is higher.For example, common air quality index (AQI) include 0-50,51-100,
101-150,151-200,201-300 and be greater than 300 6 grades, then obtain with different air quality indexs (AQI) correspondence
Haze image when, can make in haze image corresponding air quality index (AQI) as far as possible includes six shelves above, and
It include an appropriate number of haze image in each air quality index (AQI) shelves in possible situation.Get with respectively
It is more to this by common no-reference image quality evaluation algorithms after the corresponding haze image of a air quality index (AQI)
A haze image carries out image quality evaluation, corresponding picture appraisal index (NRIQA) is obtained, in this manner it is possible to be interpreted as, one
The corresponding air quality index (AQI) of a haze image, as soon as and corresponding picture appraisal index (NRIQA), then can
By the way that the air quality index (AQI) of the same haze image and its picture appraisal index (NRIQA) are established corresponding relationship.?
Here, it can be appreciated that can be by certain Mathematical treatment means to the air quality index (AQI) and image of multiple haze images
Evaluation index (NRIQA) carries out the confirmation of particular kind of relationship, for example, in the air quality index of many times most of haze image
(AQI) and the relationship of picture appraisal index (NRIQA) all meets a kind of particular kind of relationship, then the particular kind of relationship can be set as
The air quality index (AQI) of haze image and the corresponding relationship of picture appraisal index (NRIQA).When the air matter of haze image
Volume index (AQI) and the corresponding relationship of picture appraisal index (NRIQA) have been able to confirm, then can be carried out real-time haze
The monitoring of image obtains, herein available any real-time haze image, and is commented by no-reference image quality
Valence algorithm calculates the picture appraisal index (NRIQA) of real-time haze image, it is to be noted here that in order to guarantee that air quality refers to
The accuracy of number (AQI), the second processing unit uses the calculating of the picture appraisal index (NRIQA) of real-time haze image here
No-reference image quality evaluation algorithms will with first processing units to haze image picture appraisal index (NRIQA) calculate when
The no-reference image quality evaluation algorithms of use are identical.After the picture appraisal index (NRIQA) for obtaining real-time haze image, just
It can be real-time to obtain by the picture appraisal index (NRIQA) of haze image and the corresponding relationship of air quality index (AQI)
The corresponding air quality index of haze image (AQI).The air quality index (AQI) that output unit finally will acquire carries out
Output.
Further, monitoring unit is high-definition camera.Specifically, high-definition camera here is protected as far as possible when obtaining image
It holds in the same angle.
Further, further include storage unit, storage unit for store BLIINDS2, M3, BRISQUE, STAIND,
One of BIQI, CurveletQA and DIIVINE image quality evaluation algorithm is a variety of, and first processing units are according to wherein appointing
A kind of picture appraisal index (NRIQA) for acquisition haze image of anticipating.Specifically, obtaining the picture appraisal index of haze image
(NRIQA) image quality evaluation algorithm used by does not specially require.Illustrated by test data above, commonly without ginseng
It examines type image quality evaluation algorithm and is able to satisfy requirement.
It further, further include user terminal, user terminal includes the first processing units, the second processing unit and defeated
Unit out.Specifically, user terminal here can be PC, plate even mobile phone is obtained by obtaining high-definition camera
The haze picture taken can carry out the acquisition of implementation air quality index (AQI).And can be shown by image, number display or
The modes such as list display are shown in display screen, can also be broadcasted by sound.In some embodiments, monitoring unit and use
Family terminal can also be integrated design, such as the computer with camera etc..
Separately, a kind of computer equipment of the invention, including memory, processor and be stored on reservoir and can handle
The computer program run on device, processor realize the air matter based on image quality evaluation above when executing computer program
The step of measuring evaluation method.As long as can be obtained Air Quality Evaluation specifically, carrying out above-mentioned method on a computing device
Result.Computer equipment can be the terminals such as notebook, desktop computer, tablet computer, smart phone, can also be server.
In addition, a kind of computer storage medium of the invention, computer-readable recording medium storage program, program can be processed
Device executes, the step of to realize Air Quality Evaluation method based on image quality evaluation as described above.Specifically, above
The method of description can be used as program storage, and carry out duplicate copy, in this way, formation air quality monitoring that can be simple and quick
The layout of point.Here computer readable storage medium can be, but not limited to, keep and store and be made by instruction execution equipment
The tangible device of instruction.Computer readable storage medium can for example be but not limited to storage device electric, magnetic storage apparatus,
Light storage device, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned any appropriate combination.And it is deposited comprising above-mentioned
Store up the device combination of equipment.
It should be understood that above embodiments only express the preferred embodiment of the present invention, description is more specific and detailed
Carefully, but it cannot be understood as limitations on the scope of the patent of the present invention；It should be pointed out that for the common skill of this field
For art personnel, without departing from the inventive concept of the premise, above-mentioned technical characterstic can be freely combined, can also be done
Several modifications and improvements out, these are all within the scope of protection of the present invention；Therefore, all to be done with scope of the invention as claimed
Equivalents and modification, should belong to the covering scope of the claims in the present invention.
Claims (10)
1. a kind of Air Quality Evaluation method based on image quality evaluation, which comprises the following steps:
Haze image under S1, the multiple and different air quality indexs of acquisition；
S2, the picture appraisal index that the haze image is obtained by no-reference image quality evaluation algorithms, and described in foundation
The picture appraisal index of haze image and the corresponding relationship of the air quality index；
S3, it obtains a real-time haze image and calculates the real-time haze figure by the no-reference image quality evaluation algorithms
The picture appraisal index of picture；
S4, by the corresponding relationship of the picture appraisal index of the haze image and the air quality index obtain it is described in real time
The corresponding air quality index of haze image.
2. Air Quality Evaluation method according to claim 1, which is characterized in that in the step S2, described in foundation
The picture appraisal index and the corresponding relationship of the air quality index of haze image include:
S2-1, the scatter plot for drawing the haze image corresponding picture appraisal index and air quality index, and digital simulation
Curve.
3. Air Quality Evaluation method according to claim 2, which is characterized in that in the step S2-1, the meter
Calculating matched curve includes calculating three rank multinomial matched curves.
4. Air Quality Evaluation method according to claim 3, which is characterized in that in the step S2, the no ginseng
Examining type image quality evaluation algorithm includes BLIINDS2, M3, BRISQUE, STAIND, BIQI, CurveletQA and DIIVINE figure
As any one in quality evaluation algorithm.
5. a kind of Air Quality Evaluation system based on image quality evaluation characterized by comprising monitoring unit, with it is described
The first processing units and the second processing unit of monitoring unit connection, the output unit being connect with described the second processing unit；
The monitoring unit is used to obtain the haze image under multiple and different air quality indexs；
The first processing units by the image that no-reference image quality evaluation algorithms obtain the haze image for being commented
Valence index, and establish the picture appraisal index of the haze image and the corresponding relationship of the air quality index；
The monitoring unit is also used to obtain a real-time haze image；
Described the second processing unit is used to calculate the real-time haze image by the no-reference image quality evaluation algorithms
Picture appraisal index；And it is obtained by the picture appraisal index and the corresponding relationship of the air quality index of the haze image
Take the corresponding air quality index of the real-time haze image；
The output unit is for exporting the air quality index.
6. Air Quality Evaluation system according to claim 5, which is characterized in that the monitoring unit is high-definition camera
Head.
7. Air Quality Evaluation system according to claim 5, which is characterized in that it further include storage unit, the storage
Unit is for storing BLIINDS2, M3, BRISQUE, STAIND, BIQI, CurveletQA and DIIVINE image quality evaluation calculation
One of method is a variety of, and the first processing units refer to according to the picture appraisal that any of them obtain the haze image
Mark.
8. Air Quality Evaluation system according to claim 5, which is characterized in that it further include user terminal, the user
Terminal includes the first processing units, the second processing unit and output unit.
9. a kind of computer equipment including memory, processor and is stored in the meter that can be run on reservoir and on a processor
Calculation machine program, which is characterized in that the processor is realized described in any one of Claims 1-4 when executing the computer program
The Air Quality Evaluation method based on image quality evaluation the step of.
10. a kind of computer storage medium, which is characterized in that the computer-readable recording medium storage program, described program
It can be executed by processor, to realize such as the described in any item Air Quality Evaluations based on image quality evaluation of Claims 1-4
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810783240.1A CN109242821A (en) | 2018-07-17 | 2018-07-17 | Air Quality Evaluation method, system, equipment and storage medium based on image quality evaluation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810783240.1A CN109242821A (en) | 2018-07-17 | 2018-07-17 | Air Quality Evaluation method, system, equipment and storage medium based on image quality evaluation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109242821A true CN109242821A (en) | 2019-01-18 |
Family
ID=65072717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810783240.1A Pending CN109242821A (en) | 2018-07-17 | 2018-07-17 | Air Quality Evaluation method, system, equipment and storage medium based on image quality evaluation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109242821A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108872040A (en) * | 2018-09-30 | 2018-11-23 | 徐州工业职业技术学院 | A kind of city haze monitoring system |
| CN110082283A (en) * | 2019-05-23 | 2019-08-02 | 山东科技大学 | A kind of Atmospheric particulates SEM image recognition methods and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140177960A1 (en) * | 2012-12-24 | 2014-06-26 | Korea University Research And Business Foundation | Apparatus and method of processing image |
| CN104198657A (en) * | 2014-09-04 | 2014-12-10 | 西华师范大学 | Comprehensive evaluation method for environmental air quality |
| US9129369B1 (en) * | 2014-05-01 | 2015-09-08 | The United States Of America As Represented By Secretary Of The Navy | Method for characterizing an atmospheric channel |
| CN105445204A (en) * | 2015-12-07 | 2016-03-30 | 太原理工大学 | Method for discriminating air quality grade based on lens blue light wave analysis |
| CN105527232A (en) * | 2015-12-07 | 2016-04-27 | 太原理工大学 | Air quality grade discrimination system and control method thereof |
| CN107221130A (en) * | 2017-04-26 | 2017-09-29 | 南京信息工程大学 | A kind of domestic air pollution classification prior-warning device and method |
| CN107451608A (en) * | 2017-07-21 | 2017-12-08 | 西安电子科技大学 | Based on the SAR image reference-free quality evaluation methods for regarding amplitude statistics characteristic more |
| CN108052980A (en) * | 2017-12-21 | 2018-05-18 | 南京理工大学 | Air quality grade detection method based on image |
-
2018
- 2018-07-17 CN CN201810783240.1A patent/CN109242821A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140177960A1 (en) * | 2012-12-24 | 2014-06-26 | Korea University Research And Business Foundation | Apparatus and method of processing image |
| US9129369B1 (en) * | 2014-05-01 | 2015-09-08 | The United States Of America As Represented By Secretary Of The Navy | Method for characterizing an atmospheric channel |
| CN104198657A (en) * | 2014-09-04 | 2014-12-10 | 西华师范大学 | Comprehensive evaluation method for environmental air quality |
| CN105445204A (en) * | 2015-12-07 | 2016-03-30 | 太原理工大学 | Method for discriminating air quality grade based on lens blue light wave analysis |
| CN105527232A (en) * | 2015-12-07 | 2016-04-27 | 太原理工大学 | Air quality grade discrimination system and control method thereof |
| CN107221130A (en) * | 2017-04-26 | 2017-09-29 | 南京信息工程大学 | A kind of domestic air pollution classification prior-warning device and method |
| CN107451608A (en) * | 2017-07-21 | 2017-12-08 | 西安电子科技大学 | Based on the SAR image reference-free quality evaluation methods for regarding amplitude statistics characteristic more |
| CN108052980A (en) * | 2017-12-21 | 2018-05-18 | 南京理工大学 | Air quality grade detection method based on image |
Non-Patent Citations (2)
| Title |
|---|
| MAOZHENG ZHAO: "No-reference image quality assessment based on phase congruency and spectral entropies", 《2015 PICTURE CODING SYMPOSIUM (PCS)》 * |
| 范赐恩: "颜色空间统计联合纹理特征的无参考图像质量评价", 《光学精密工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108872040A (en) * | 2018-09-30 | 2018-11-23 | 徐州工业职业技术学院 | A kind of city haze monitoring system |
| CN110082283A (en) * | 2019-05-23 | 2019-08-02 | 山东科技大学 | A kind of Atmospheric particulates SEM image recognition methods and system |
| CN110082283B (en) * | 2019-05-23 | 2021-12-14 | 山东科技大学 | Atmospheric particulate SEM image recognition method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180321208A1 (en) | Determining the net emissions of air pollutants | |
| CN108106979B (en) | PM2.5 inversion method based on MODIS and machine learning model fusion | |
| CN110378232B (en) | Improved test room examinee position rapid detection method of SSD dual-network | |
| CN112819207A (en) | Geological disaster space prediction method, system and storage medium based on similarity measurement | |
| CN112070134A (en) | Power equipment image classification method and device, power equipment and storage medium | |
| CN109242821A (en) | Air Quality Evaluation method, system, equipment and storage medium based on image quality evaluation | |
| Cassel et al. | Evaluating a 2D image-based computerized approach for measuring riverine pebble roundness | |
| Guan et al. | Development of verification methodology for extreme weather forecasts | |
| CN105809249A (en) | Double neural network-based PM2.5 concentration detection and prediction system and method | |
| CN113808132B (en) | Three-dimensional network model quality detection method and device and computer equipment | |
| CN110716998B (en) | Fine scale population data spatialization method | |
| CN114973090A (en) | Experiment scoring method and device, electronic equipment and storage medium | |
| CN109547960A (en) | A kind of intelligent detecting method and system | |
| CN109222220A (en) | For evaluating and testing the method and system of cigarette manufacturing quality index | |
| CN113158558A (en) | High-speed railway roadbed continuous compaction analysis method, device and analyzer | |
| CN108830444A (en) | A kind of assessment of raob data and modification method and device | |
| CN104156312B (en) | A kind of method for assessing software reliability | |
| Korn et al. | Exact analytical solution for the normal SABR model | |
| CN115035340B (en) | Remote sensing image classification result verification method | |
| Liu et al. | Fractal scaling of soot packing density across five size decades | |
| Er et al. | Estimate of dark halo ellipticity by lensing flexion | |
| WO2023184281A9 (en) | Inspection parameter analysis method and apparatus | |
| WO2020014863A1 (en) | Air quality assessment method and system based on image quality assessment, and device and storage medium | |
| CN115879594A (en) | Urban settlement population distribution trend prediction method based on geographic detector | |
| Mehanna et al. | Completeness Issues in Mobile Crowd-sensing Environments. |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |