CN109948482A - A kind of black and odorous water image zooming-out and recognition methods - Google Patents
A kind of black and odorous water image zooming-out and recognition methods Download PDFInfo
- Publication number
- CN109948482A CN109948482A CN201910170314.9A CN201910170314A CN109948482A CN 109948482 A CN109948482 A CN 109948482A CN 201910170314 A CN201910170314 A CN 201910170314A CN 109948482 A CN109948482 A CN 109948482A
- Authority
- CN
- China
- Prior art keywords
- image
- black
- odorous water
- color
- moment
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 8
- 239000000284 extract Substances 0.000 claims abstract description 6
- 238000005070 sampling Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 230000035945 sensitivity Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 abstract description 2
- 239000013307 optical fiber Substances 0.000 abstract description 2
- JEGUKCSWCFPDGT-UHFFFAOYSA-N h2o hydrate Chemical compound O.O JEGUKCSWCFPDGT-UHFFFAOYSA-N 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 239000010865 sewage Substances 0.000 description 2
- VHUUQVKOLVNVRT-UHFFFAOYSA-N Ammonium hydroxide Chemical compound [NH4+].[OH-] VHUUQVKOLVNVRT-UHFFFAOYSA-N 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- DNJIEGIFACGWOD-UHFFFAOYSA-N ethanethiol Chemical compound CCS DNJIEGIFACGWOD-UHFFFAOYSA-N 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- IJGRMHOSHXDMSA-UHFFFAOYSA-N nitrogen Substances N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 1
- 230000033116 oxidation-reduction process Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000009418 renovation Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of black and odorous water image zooming-out and recognition methods comprising the steps of: A, data prediction；3 Color Channels are divided the image into, pixel matrix is converted, extract the image of water sample image center 101*101 pixel；B, each rank color moment is extracted in image characteristics extraction；C, sampling 80% is used as training sample, and remaining 20% is used as test sample；D, model is trained with training set sample；E, model performance is assessed with test sample, the present invention by being sampled, taking pictures to black and odorous water, optical fiber transmission technology, obtain black and odorous water image, image is being identified using the methods of machine learning and provides black and odorous water classification registration, black and odorous water can be carried out to regional scope quickly to identify, it monitors black and odorous water and administers situation, time saving and energy saving, use easy to spread.
Description
Technical field
The present invention relates to a kind of electricity-saving system, specifically a kind of black and odorous water image zooming-out and recognition methods.
Background technique
City black and odorous water refers in completed region of the city, presents unpleasant color (black or blacking up color), and (or)
Give out the general designation for making us the water body of foreign odor (smelly or stench).According to the difference of black smelly degree, can be subdivided into " slight
It is black smelly " and " severe is black smelly " two-stage." slight black smelly " and the grade scale of " severe is black smelly " are as follows: water transparency is at 25 centimetres
It is slight black smelly between 10 centimetres；It is then black smelly for severe less than 10 centimetres.Every liter of water ammonia nitrogen concentration is at 8 to 15 milligrams
It is that severe is black smelly greater than 15 milligrams to be slight black smelly.
Black and odorous water identification is mainly judged by on-site inspection, is felt to the judgement of black and odorous water using the subjective of human body
It is carried out by the method for combining water quality indicator to measure.Water body color exception (usually blackish green, grey black on subjective feeling finger vision
Deng), the more impurity of floating on water is whole more muddy, and flow velocity is slow not to be flowed even, usually there is sewage draining exit sewage effluent；Water quality refers to
Mark then referring to " city black and odorous water renovation guide " regulation, specific transparency, dissolved oxygen, oxidation-reduction potential, pH value,
The water quality indicators such as total phosphorus.Field investigation result is accurate, but is only used for the identification of acquired sampling point, can not infer whole region
Black smelly situation, furthermore this method needs water sample, time and effort consuming are acquired on the spot.Water quality indicator can quantitatively divide Water quality
Analysis, but it is equally based on field sampling, it cannot quickly identify the distribution of whole region black and odorous water.
Summary of the invention
The purpose of the present invention is to provide a kind of black and odorous water image zooming-out and recognition methods, to solve above-mentioned background technique
The problem of middle proposition.
To achieve the above object, the invention provides the following technical scheme:
A kind of black and odorous water image zooming-out and recognition methods comprising the steps of:
A, data prediction；3 Color Channels are divided the image into, pixel matrix is converted, extract water sample image center
The image of 101*101 pixel；
B, each rank color moment is extracted in image characteristics extraction；
C, sampling 80% is used as training sample, and remaining 20% is used as test sample；
D, model is trained with training set sample；
E, model performance is assessed with test sample.
As further technical solution of the present invention: the step A is specifically: the size for setting original image is M × N, then
Intercept wide from -50 pixels of fix (M/2) to+50 pixels of fix (M/2), -50 pixels of Gao Cong fix (M/2)
To the subgraph of fix (M/2)+50 pixels.
As further technical solution of the present invention: each rank color moment include single order color moment, second order color moment and
Three rank color moments.
As further technical solution of the present invention: the single order color moment uses first moment about the origin, reflects image
Whole sensitivity, formula are as follows:
As further technical solution of the present invention: the second order color moment uses the square root of second-order moment around mean, reflection
The distribution of color of image, formula are as follows:
As further technical solution of the present invention: the three ranks color moment uses the cubic root of third central moment, reflection
The symmetry of color of image distribution, formula are as follows:
As further technical solution of the present invention: described image feature includes color characteristic, textural characteristics, shape feature
And spatial relation characteristics.
Compared with prior art, the beneficial effects of the present invention are: the present invention by being sampled, taking pictures to black and odorous water,
The technology of optical fiber transmission, obtains black and odorous water image, is identifying image using the methods of machine learning and is providing black and odorous water point
Class registration can carry out black and odorous water to regional scope and quickly identify, monitoring black and odorous water administers situation, time saving and energy saving, be easy to
It promotes the use of.
Detailed description of the invention
Fig. 1 is work flow diagram of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment 1: referring to Fig. 1, a kind of black and odorous water image zooming-out and recognition methods comprising the steps of:
A, data prediction；3 Color Channels are divided the image into, pixel matrix is converted, extract water sample image center
The image of 101*101 pixel；If the size of original image is M × N, then intercept wide from -50 pixels of fix (M/2) to fix
(M/2)+50 pixels, the subgraph of -50 pixels of Gao Cong fix (M/2) to fix (M/2)+50 pixels；
B, image characteristics extraction extracts single order color moment, second order color moment and three rank color moments, wherein single order color moment
Using first moment about the origin, the whole sensitivity of image is reflected, formula is as follows:Second order color moment uses two
The square root of rank central moment reflects the distribution of color of image, and formula is as follows:Three rank face
Colour moment uses the cubic root of third central moment, reflects the symmetry of color of image distribution, and formula is as follows:
C, sampling 80% is used as training sample, and remaining 20% is used as test sample；
D, model is trained with training set sample；
E, model performance is assessed with test sample.
Embodiment 2, on the basis of embodiment 1, the characteristics of image of the design mainly include color characteristic, textural characteristics,
Shape feature, spatial relation characteristics etc., compared with geometrical characteristic, color characteristic is more steady, for the size and Orientation of object
It is insensitive, show stronger robustness；Because black and odorous water water colour image is uniformly, to be primarily upon color spy
Sign.
Color characteristic includes:
Color histogram: which color the composition distribution of color in reflection image occurs and various colors occurs
Probability.It the advantage is that the global distribution of color in piece image can be briefly described in it, i.e., different color is in entire image
Shared ratio, especially suitable for describing image that those are difficult to divide automatically and without the concern for the figure of object space position
Picture.Its shortcoming is that it can not describe spatial position locating for the local distribution of color and every kind of color in image, i.e., can not retouch
State a certain specific object or the object in image.
Color moment: any distribution of color can be indicated with its square in image.According to probability theory, stochastic variable
Probability distribution uniquely can be indicated and be described by its each rank matrix.The COLOR COMPOSITION THROUGH DISTRIBUTION of one sub-picture is also believed to a kind of probability
Distribution, then image can be described by its each rank square.Color moment includes the single order of each Color Channel away from, second moment and three ranks
Square has tri- Color Channels of R, G and B, then has 9 components for the image of a width RGB color.
Color histogram generates the intrinsic dimensionality that intrinsic dimensionality is generally higher than color moment, after crossing multivariable influence
Continuous classifying quality, black and odorous water water quality extract the feature of water sample image using color moment.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (7)
1. a kind of black and odorous water image zooming-out and recognition methods, which is characterized in that comprise the steps of:
A, data prediction；3 Color Channels are divided the image into, pixel matrix is converted, extract water sample image center 101*101
The image of pixel；
B, each rank color moment is extracted in image characteristics extraction；
C, sampling 80% is used as training sample, and remaining 20% is used as test sample；
D, model is trained with training set sample；
E, model performance is assessed with test sample.
2. a kind of black and odorous water image zooming-out according to claim 1 and recognition methods, which is characterized in that the step A
Specifically: the size for setting original image is M × N, then intercepts wide from -50 pixels of fix (M/2) to fix (M/2)+50
Pixel, the subgraph of -50 pixels of Gao Cong fix (M/2) to fix (M/2)+50 pixels.
3. a kind of black and odorous water image zooming-out according to claim 1 and recognition methods, which is characterized in that each rank face
Colour moment includes single order color moment, second order color moment and three rank color moments.
4. a kind of black and odorous water image zooming-out according to claim 3 and recognition methods, which is characterized in that the single order face
Colour moment uses first moment about the origin, reflects the whole sensitivity of image, formula is as follows:
5. a kind of black and odorous water image zooming-out according to claim 4 and recognition methods, which is characterized in that the second order face
Colour moment uses the square root of second-order moment around mean, reflects the distribution of color of image, formula is as follows:
6. a kind of black and odorous water image zooming-out according to claim 5 and recognition methods, which is characterized in that the three ranks face
Colour moment uses the cubic root of third central moment, reflects the symmetry of color of image distribution, and formula is as follows:
7. a kind of -6 any described black and odorous water image zooming-outs and recognition methods according to claim 1, which is characterized in that described
Characteristics of image includes color characteristic, textural characteristics, shape feature and spatial relation characteristics.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910170314.9A CN109948482A (en) | 2019-03-07 | 2019-03-07 | A kind of black and odorous water image zooming-out and recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910170314.9A CN109948482A (en) | 2019-03-07 | 2019-03-07 | A kind of black and odorous water image zooming-out and recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109948482A true CN109948482A (en) | 2019-06-28 |
Family
ID=67009171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910170314.9A Pending CN109948482A (en) | 2019-03-07 | 2019-03-07 | A kind of black and odorous water image zooming-out and recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109948482A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112903945A (en) * | 2021-02-26 | 2021-06-04 | 珠江水利委员会珠江水利科学研究院 | Urban black and odorous water body identification method based on conventional water quality parameters |
| CN112926674A (en) * | 2021-03-19 | 2021-06-08 | 广东好太太智能家居有限公司 | Image classification prediction method and device based on support vector machine model |
| CN113792689A (en) * | 2021-09-18 | 2021-12-14 | 安徽师范大学 | Urban black and odorous water body remote sensing identification method based on deep learning |
| CN114882130A (en) * | 2022-06-16 | 2022-08-09 | 平安普惠企业管理有限公司 | Water quality grading method, device, equipment and medium based on water color image |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106874948A (en) * | 2017-02-08 | 2017-06-20 | 武汉海卓科科技有限公司 | A kind of black smelly water automatic identification and appraisal procedure |
| CN107167431A (en) * | 2017-05-26 | 2017-09-15 | 中国科学院遥感与数字地球研究所 | A kind of black and odorous water recognition methods and system based on spectral index model |
| CN107292339A (en) * | 2017-06-16 | 2017-10-24 | 重庆大学 | The unmanned plane low altitude remote sensing image high score Geomorphological Classification method of feature based fusion |
| CN107808161A (en) * | 2017-10-26 | 2018-03-16 | 江苏科技大学 | A kind of Underwater targets recognition based on light vision |
| CN108645853A (en) * | 2018-05-11 | 2018-10-12 | 南京吉泽信息科技有限公司 | A kind of Ratio index method of black and odorous water remote sensing recognition |
| CN109034269A (en) * | 2018-08-22 | 2018-12-18 | 华北水利水电大学 | A kind of bollworm female male imago method of discrimination based on computer vision technique |
-
2019
- 2019-03-07 CN CN201910170314.9A patent/CN109948482A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106874948A (en) * | 2017-02-08 | 2017-06-20 | 武汉海卓科科技有限公司 | A kind of black smelly water automatic identification and appraisal procedure |
| CN107167431A (en) * | 2017-05-26 | 2017-09-15 | 中国科学院遥感与数字地球研究所 | A kind of black and odorous water recognition methods and system based on spectral index model |
| CN107292339A (en) * | 2017-06-16 | 2017-10-24 | 重庆大学 | The unmanned plane low altitude remote sensing image high score Geomorphological Classification method of feature based fusion |
| CN107808161A (en) * | 2017-10-26 | 2018-03-16 | 江苏科技大学 | A kind of Underwater targets recognition based on light vision |
| CN108645853A (en) * | 2018-05-11 | 2018-10-12 | 南京吉泽信息科技有限公司 | A kind of Ratio index method of black and odorous water remote sensing recognition |
| CN109034269A (en) * | 2018-08-22 | 2018-12-18 | 华北水利水电大学 | A kind of bollworm female male imago method of discrimination based on computer vision technique |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112903945A (en) * | 2021-02-26 | 2021-06-04 | 珠江水利委员会珠江水利科学研究院 | Urban black and odorous water body identification method based on conventional water quality parameters |
| CN112903945B (en) * | 2021-02-26 | 2022-02-22 | 珠江水利委员会珠江水利科学研究院 | Urban black and odorous water body identification method based on conventional water quality parameters |
| CN112926674A (en) * | 2021-03-19 | 2021-06-08 | 广东好太太智能家居有限公司 | Image classification prediction method and device based on support vector machine model |
| CN113792689A (en) * | 2021-09-18 | 2021-12-14 | 安徽师范大学 | Urban black and odorous water body remote sensing identification method based on deep learning |
| CN113792689B (en) * | 2021-09-18 | 2022-09-09 | 安徽师范大学 | Urban black and odorous water body remote sensing identification method based on deep learning |
| CN114882130A (en) * | 2022-06-16 | 2022-08-09 | 平安普惠企业管理有限公司 | Water quality grading method, device, equipment and medium based on water color image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109948482A (en) | A kind of black and odorous water image zooming-out and recognition methods | |
| US20210199579A1 (en) | Method and system for urban impervious surface extraction based on remote sensing | |
| CN106529429B (en) | A kind of skin of face analysis system based on image recognition | |
| Hagerhall et al. | Fractal dimension of landscape silhouette outlines as a predictor of landscape preference | |
| CN101840581B (en) | Method for extracting profile of building from satellite remote sensing image | |
| Lee et al. | Sub-pixel estimation of urban land cover components with linear mixture model analysis and Landsat Thematic Mapper imagery | |
| CN101853286B (en) | Intelligent selection method of video thumbnails | |
| CN102592272A (en) | Extracting method and device of picture dominant tone | |
| CN102254159B (en) | Interpretation method for digital readout instrument | |
| CN107066972B (en) | Natural scene Method for text detection based on multichannel extremal region | |
| Berezhnoy et al. | Computer analysis of van Gogh’s complementary colours | |
| Scopélitis et al. | The next step in shallow coral reef monitoring: Combining remote sensing and in situ approaches | |
| CN109934154A (en) | A kind of remote sensing image variation detection method and detection device | |
| CN102855485B (en) | The automatic testing method of one grow wheat heading | |
| CN112287838B (en) | Cloud and fog automatic identification method and system based on static meteorological satellite image sequence | |
| CN108898096A (en) | A kind of quick accurate extracting method of the information towards high score image | |
| CN106228157A (en) | Coloured image word paragraph segmentation based on image recognition technology and recognition methods | |
| CN101673405A (en) | Representative color designating method using reliability | |
| CN105512622A (en) | Visible remote-sensing image sea-land segmentation method based on image segmentation and supervised learning | |
| CN110390322A (en) | A kind of unginned cotton mulch EO-1 hyperion visual mark algorithm for deep learning | |
| CN111028244A (en) | Remote sensing image semantic segmentation method based on super-pixel under condition of known sample imbalance | |
| Torkko et al. | How to best map greenery from a human perspective? Comparing computational measurements with human perception | |
| CN108648200A (en) | A kind of indirect city high-resolution impervious surface extracting method | |
| CN106355596A (en) | Edge detection method fusing uniform color information and compound receptive field model | |
| MacEachren et al. | The role of brightness differences in figure-ground: is darker figure? |
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: 20190628 |