CN109118548A - A kind of comprehensive intelligent water quality recognition methods - Google Patents
A kind of comprehensive intelligent water quality recognition methods Download PDFInfo
- Publication number
- CN109118548A CN109118548A CN201810785404.4A CN201810785404A CN109118548A CN 109118548 A CN109118548 A CN 109118548A CN 201810785404 A CN201810785404 A CN 201810785404A CN 109118548 A CN109118548 A CN 109118548A
- Authority
- CN
- China
- Prior art keywords
- image
- textural characteristics
- water quality
- sample image
- detected
- 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
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention discloses a kind of comprehensive intelligent water quality recognition methods, belong to water quality identification field, comprising the following steps: image when 1) obtaining different conditions and color in waters to be detected obtains sample image；2) color identification is carried out to sample image, and water quality color classification is carried out to the image after identification；3) sorted image is subjected to texture feature extraction respectively, the textural characteristics data of image is obtained, and be averaged to the textural characteristics data of all figures in every class image, obtains one group of textural characteristics data model；4) the water sample image to be detected in waters to be detected is obtained；5) step 2) is carried out to water sample image to be detected and step 3) is handled, obtain the textural characteristics data of water sample image to be detected；6) Classification and Identification is carried out using Euclidean distance classification and according to textural characteristics data of the textural characteristics data model to water sample image to be detected.This method is not necessarily to specific device, only need to carry out data connection with camera existing around waters.
Description
Technical field
The present invention relates to water quality to identify field, specifically, being related to a kind of comprehensive intelligent water quality recognition methods.
Background technique
With the industrialized progress of human society, environmental pollution is increasingly severe, and the pollution of water resource is also aggravating.It is special
It is not on the soil of the African length and breadth of land, water resource becomes its important resource, and because the disease that water resource is propagated is propagated wantonly,
The crowd for living in this area is allowed to get impoverished and weak.However, traditional water quality detection is needed through a variety of instruments to water resource
Various aspects are identified, finally can carry out comprehensive descision to water quality according to the resulting data of identification.
Video monitoring equipment is assembled at many row's mouths at present, but the mode monitored is mainly staff by dig-inning
The mode of screen monitors monitored picture, goes to review monitoring video lookup clue again after sometimes environmentally friendly accident, can not be pre-
The generation of anti-environmental protection accident.Simultaneously because monitoring point enormous amount, it is impossible to allow limited monitoring personnel and display equipment simultaneously
All monitoring points are paid close attention to, the mode for mostly using poll to play greatly, in most cases, the video pictures of monitoring point are not
Monitored personnel see, it is likely that just have noticeable abnormal phenomenon to occur within these times.And simultaneously due to monitoring personnel
It does not find on the spot, and misses the chance handled in time.There are also monitoring personnel attentions to concentrate for a long time, in face of so many
Monitoring image, often due to one of monitoring personnel carelessness just misses the opportunity eliminated accident in the budding stage.Therefore,
It is difficult to realize that instant detection and identification is carried out to the quality of water resource.
There are also the methods of many on-line checking water quality, such as:
Publication No. is that the Chinese patent literature of CN104568797A discloses a kind of on-line monitoring system of Colority of Sewage Water, should
System includes clear water absorption cell, sample water absorption cell, fibre-optical probe a, fibre-optical probe b, CCD array detector, data acquisition with
Processing equipment, clear water absorption cell are connected by fibre-optical probe a connection CCD array detector, sample water absorption cell by fibre-optical probe b
CCD array detector is connect, CCD array detector connects data acquisition and processing equipment.
Publication No. is that the Chinese patent literature of CN108051442A discloses a kind of water quality identification side based on intelligent terminal
Method and water quality identifying system.Water quality recognition methods includes the following steps: the current of to be measured water resource of the acquisition comprising pictorial symbolization
Image；According to the color of present image, the current chroma of water resource to be measured is detected；According to the clarity of pictorial symbolization, extract to
Survey the current turbidity of water resource；Calculate the current concentration of suspended matter for including in present image；According to current chroma, current muddy
Turbidity and current concentration of suspended matter, judge the current Quality of water resource to be measured.Water quality identifying system includes acquisition module, detection
Module, extraction module, computing module and processing module.Using the water quality recognition methods and water quality identifying system, can help to use
Family is measured in real time convenient for quality of the user to local water resource.
The above technology generally requires specific device, is restricted use scope.Such as: when some remote region water quality go out
When now abnormal, tend not to find and prevent in time；And there is also chemical agent concentration is unstable in chemical detection method,
It is easy to cause the drawbacks such as secondary pollution.
Summary of the invention
It is an object of the present invention to provide a kind of comprehensive intelligent water quality recognition methods, this method is not necessarily to specific device, only needs
Data connection is carried out with camera existing around waters, the waters can be carried out in real time by obtaining the video image in camera
Water quality identification, and can be used for isolated area's water quality monitoring.
To achieve the goals above, comprehensive intelligent water quality recognition methods provided by the invention the following steps are included:
1) image when obtaining different conditions and color in waters to be detected obtains sample image；
2) color identification is carried out to sample image, and water quality color classification is carried out to the image after identification；
3) sorted image is subjected to texture feature extraction respectively, obtains the textural characteristics data of image, and to every class
The textural characteristics data of all figures in image are averaged, and obtain one group of textural characteristics data model；
4) original video data for obtaining water quality monitoring region in waters to be detected, extracts figure from original video data
As data, and single frames is carried out to image data and handles to obtain single-frame images, and single-frame images is sampled, extracted to be detected
Water sample image；
5) step 2) is carried out to water sample image to be detected and step 3) is handled, obtain the textural characteristics of water sample image to be detected
Data；
6) using Euclidean distance classification and according to textural characteristics data model to the textural characteristics of water sample image to be detected
Data carry out Classification and Identification.
In above-mentioned technical proposal, using high-definition camera from certain angle, a certain distance to the water surface for monitoring region
It is recorded, it should be noted that the parameters such as angle, distance of the video camera need to fix, and cannot arbitrarily change.Then to obtaining
The video information taken carries out single-frame images processing, according to the color characteristic for the water surface that processing obtains, to carry out water quality identification.
This process be quite analogous to people with the naked eye come identify various colors water water quality principle, since video camera can uninterrupted work
Make, this method can provide warning information in time, provide the foundation of decision for artificial disposition in time, have very strong practical valence
Value, this point are especially of great significance for the monitoring in remote waters.
Specific scheme is to carry out color to sample image in step 2) to know method for distinguishing are as follows:
2-1) the range of corresponding tri- components of HSV of predefined each color, obtains a predefined model, and will predefine
Model is stored into processor；
Sample image 2-2) is converted into HSV mode by RGB mode, conversion formula is as follows,
V=MAX
Wherein MAX, MIN are derived from tri- components of RGB, and maximum is MAX, and the smallest is MIN；
The H range being calculated is [0,360], and the range of S and V are [0,1]；
It is pure grey if MAX=MIN, H=do not have color；
If H <'s 0, H is worth along with 360；
If MAX=0, S=0 are exactly no color；
It is ater if V=0；
Tri- component input processors of H, S, V after 2-3) converting sample image, are compared with predefined model, place
It manages device and exports comparison result.
The present invention carries out the identification of water quality color using HSV model, rather than uses RGB method, and RGB represents red
(R), the color in green (G), blue three channels (B), rgb color mode is a kind of color standard of industry, be by it is red,
The variation of green, blue three Color Channels and their mutual superpositions are to obtain miscellaneous color.And HSV refers to
Form and aspect (hue), saturation degree (saturation) and the tone (value) of color, due to combining the content of three aspects, so
HSV model compares RGB model, more close to perception for color in people's reality.Each object has corresponding color to believe
Breath, if can not accurately extract color characteristic with RGB channel.In contrast, HSV can be easier also more acurrate
The comparison of ground progress color.Because HSV can go to carry out the classification of color from the tone of color, light and shade and bright-coloured degree.Example
Such as, in HSV space, blue range is " 100 < H < 124&43 < S < 255&46 < V < 255 ", and in RGB, with regard to none
True scope indicates, therefore is more convenient for identifying using HSV model.
For the ease of classification, the range that the range of H becomes 0~180, S and V is become 0~255 by the present invention；It is above-mentioned predetermined
Adopted model is as follows:
Another specific scheme is that step 3) includes:
Gray processing processing 3-1) is carried out to each component of the RGB of sorted image；Obtain gray scale image；
Gray scale image 3-2) is subjected to gray-scale compression, gray scale is dropped to 16 grades；
3-3) calculate the mean value and mark of this four parameters of energy, entropy, the moment of inertia and correlation in compressed gray scale image
Quasi- poor, distance is taken as 1, and angle takes 0 °, 45 °, 90 ° and 135 °, generates the co-occurrence matrix of gray level image；
3-4) co-occurrence matrix is normalized, obtains octuple textural characteristics data；
3-5) the octuple textural characteristics data of all figures in every class image are averaged, obtain one group of octuple texture
Feature-based data model is stored into processor.
It is respectively 0.3,0.59,0.11 that more specific scheme, which handles ratio for each component gray processing of RGB in step 3-1),.
Another specific scheme is that step 6) includes:
Calculate the texture of a kind of image of certain in the textural characteristics data and textural characteristics data model of water sample image to be detected
A cut off value d is arranged in the Euclidean distance d of characteristic0, as d < d0When, belong to this kind of images, otherwise, is not belonging to this kind of figures
Picture.
More specific scheme is Euclidean distance d1Calculation formula are as follows:
D=sqrt (∑ (xi1-xi2)2)
Wherein, d indicates two n-dimensional vector a (x11,x21,,…,xn1) and b (x12,x22,…,xn2) between Euclidean distance.
Further more specifically scheme is above-mentioned cut off value d0Take 0.5.
Compared with prior art, the invention has the benefit that
(1) Video Image processing technique is introduced into water quality identification by the present invention, and introducing is sentenced based on image chroma
Fixed water quality recognition methods is realized by the method for color gamut classification and pixel superposition in HSV space and is based on water colour
The water quality of color identifies.For the water quality identification containing impurity such as fallen leaves, mosses, texture is carried out again on the basis of color identification
Identification obtains octuple textural characteristics by the gray level co-occurrence matrixes based on statistic law, then realizes water using Euclidean distance classification
The comprehensive identification of matter.After identifying by computer generalization, superiority and inferiority classification is carried out to water quality, and be in time to determine according to the variation of water quality
Plan person provides warning information.The present invention is to provide early warning as target, signal an alert after computer discovery water quality exception,
By manually confirming to scene and carrying out subsequent processing, the real-time monitoring of water quality is realized.The present invention is directed to imitate people with intelligent vision
Eye judges water colour there is very strong practicability.
(2) present invention can online for a long time, dynamic monitoring, reduce a large amount of labor workloads, to solving current water quality
The water quality safety early warning system that the subsequent property problem and management of monitoring are more effectively more inexpensive is of great significance.
Detailed description of the invention
Fig. 1 is the flow chart of the comprehensive intelligent water quality recognition methods of the embodiment of the present invention；
Fig. 2 is the clear water picture that leaf is free of in the embodiment of the present invention；
Fig. 3 is the clear water picture containing a small amount of leaf in the embodiment of the present invention；
Fig. 4 is red sewage picture in the embodiment of the present invention；
Fig. 5 is blue sewage picture in the embodiment of the present invention；
Fig. 6 is the black sewage picture that moss is free of in the embodiment of the present invention；
Fig. 7 is the black sewage picture containing moss in the embodiment of the present invention；
Fig. 8 is the flow chart that the image texture characteristic of the embodiment of the present invention extracts；
Fig. 9 is that the picture of the embodiment of the present invention samples schematic diagram.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, with reference to embodiments and its attached drawing is to this hair
It is bright to be described further.
Embodiment
Referring to Fig. 1 to Fig. 9, the comprehensive intelligent water quality recognition methods of the present embodiment the following steps are included:
Image when S1 obtains different conditions and color in waters to be detected obtains sample image, and sample image is original graph
As the picture after, as shown in figure 9, purpose is excessive redundancy in removal original image.
S2 carries out color identification to sample image, and carries out water quality color classification to the image after identification.
Carrying out color knowledge method for distinguishing to sample image includes:
The range of corresponding tri- components of HSV of the predefined each color of S201, obtains a predefined model, and will predefine
Model is stored into processor；
Above-mentioned predefined model is
Sample image is converted to HSV mode by RGB mode by S202, and conversion formula is as follows,
V=MAX
Wherein MAX, MIN are derived from tri- components of RGB, and maximum is MAX, and the smallest is MIN；
S203 sample image is converted after tri- component input processors of H, S, V, compared with the predefined model
Right, processor exports comparison result.
By reading picture size in the present embodiment, to obtain pixel quantity, color one by one is carried out to pixel and is known
Not, pixel is divided into colourless, red, blue and four class of black, the quantity of each pixel is calculated, further according to each pixel quantity
Between comparison, carry out water quality color classification.
Sorted image is carried out texture feature extraction by S3 respectively, obtains the textural characteristics data of image.And to every class
The textural characteristics data of all figures in image are averaged, and obtain one group of textural characteristics data model.Referring to Fig. 8, specifically
Include the following steps:
S301 carries out gray processing processing to each component of the RGB of sorted image；Obtain gray scale image；Each component ash of RGB
Degreeization processing ratio is respectively 0.3,0.59,0.11, and the influence by color to texture is preferably minimized；
Gray scale image is carried out gray-scale compression by S302, and gray scale is dropped to 16 grades；
S303 calculates the mean value and mark of this four parameters of energy, entropy, the moment of inertia and correlation in compressed gray scale image
Quasi- poor, distance is taken as 1, and angle takes 0 °, 45 °, 90 ° and 135 °, generates the co-occurrence matrix of gray level image；
Co-occurrence matrix is normalized S304, obtains octuple textural characteristics data；Following table show the portion of clear water
Divide octuple textural characteristics data:
S305 is averaged the octuple textural characteristics data of all figures in every class image, obtains one group of octuple texture
Feature-based data model is stored into processor, as the basic data of classification, so as to algorithm analysis later.
S4 obtains the original video data in water quality monitoring region in waters to be detected, and figure is extracted from original video data
As data, and single frames is carried out to described image data and handles to obtain single-frame images, and single-frame images is sampled, extract to
Detect water sample image.The present embodiment reads single-frame images using VideoReader function.
S5 carries out step S2 and step S3 to water sample image to be detected and handles, and obtains the textural characteristics of water sample image to be detected
Data.
S6 is using Euclidean distance classification and according to textural characteristics data model to the textural characteristics of water sample image to be detected
Data carry out Classification and Identification.Specifically, calculating in textural characteristics data and the textural characteristics data model of water sample image to be detected
The Euclidean distance d of the textural characteristics data of certain a kind of image, is arranged a cut off value d0, as d < d0When, belong to this kind of images, it is no
Then, this kind of images are not belonging to.
Euclidean distance d1Calculation formula are as follows:
D=sqrt (∑ (xi1-xi2)2)
Wherein, d indicates two n-dimensional vector a (x11,x21,,…,xn1) and b (x12,x22,…,xn2) between Euclidean distance.
Cut off value d0Take 0.5.
Classification results are exported and are shown by S7, set alarm and reminding to certain colour types, if image belongs to the category,
Warning system sounds an alarm, and reminds and manually arrives in-situ processing.
Fig. 2 to Fig. 7 is water sample image to be tested, the quantity such as following table of each pixel of six figures after S03 measuring and calculation
It is shown:
| Haematochrome quantity | Cyanine quantity | Melanin quantity | Classification results | |
| Fig. 2 | 56 | 5 | 36 | Clear water (is free of leaf) |
| Fig. 3 | 65 | 17 | 30 | Clear water (contains a small amount of leaf) |
| Fig. 4 | 640 | 0 | 29 | Red sewage |
| Fig. 5 | 77 | 614 | 28 | Blue sewage |
| Fig. 6 | 364 | 90 | 377 | Black sewage (is free of moss) |
| Fig. 7 | 341 | 93 | 338 | Black sewage (contains moss) |
Wherein, haematochrome, cyanine, melanin according in S01 predefined model determine, according to the reality of the present embodiment
Data are tested, are defined as follows:
(1) if haematochrome quantity < 100& cyanine quantity < 100& melanin quantity < 100, which is " clear
Water "；
(2) if haematochrome quantity > cyanine quantity & haematochrome quantity > melanin quantity & haematochrome quantity > 100& is black
Pigment amount < 100, then the moisture class is " red sewage "；
(3) if cyanine quantity > haematochrome quantity & cyanine quantity > melanin quantity & cyanine quantity > 100,
The moisture class is " blue sewage "；
(4) if melanin quantity > cyanine quantity & melanin quantity > 100, which is " black sewage ".
The quantity of Fig. 2 and Fig. 3 colors vegetarian refreshments relatively, is divided all as " clear water " class, Fig. 6 and Fig. 7 according to color
Equally, divide according to color all as " black sewage " class.The case where to distinguish impurity, carries out the texture knowledge of S3 to S7 step
Not, specific octuple characteristic parameter is as shown in the table:
Classify further according to Euclidean distance, Fig. 2 is classified as " clear water (without leaf) ", Fig. 3 is classified as that " clear water is (containing a small amount of
Leaf) "；Fig. 6 is classified as " black sewage (without moss) ", and Fig. 7 is classified as " black sewage (containing moss) ".
Claims (8)
1. a kind of comprehensive intelligent water quality recognition methods, which comprises the following steps:
1) image when obtaining different conditions and color in waters to be detected obtains sample image；
2) color identification is carried out to the sample image, and water quality color classification is carried out to the image after identification；
3) sorted image is subjected to texture feature extraction respectively, obtains the textural characteristics data of image, and to every class image
In the textural characteristics data of all figures be averaged, obtain one group of textural characteristics data model；
4) original video data for obtaining water quality monitoring region in the waters to be detected, extracts figure from original video data
As data, and single frames is carried out to described image data and handles to obtain single-frame images, and the single-frame images is sampled, extracted
Water sample image to be detected out；
5) step 2) is carried out to the water sample image to be detected and step 3) is handled, obtain the textural characteristics of water sample image to be detected
Data；
6) using Euclidean distance classification and according to the textural characteristics data model to the texture of the water sample image to be detected
Characteristic carries out Classification and Identification.
2. comprehensive intelligent water quality recognition methods according to claim 1, which is characterized in that in step 2) to sample image into
Row color knows method for distinguishing are as follows:
2-1) the range of corresponding tri- components of HSV of predefined each color, obtains a predefined model, and by predefined model
It is stored into processor；
Sample image 2-2) is converted into HSV mode by RGB mode, conversion formula is as follows,
V=MAX
Wherein, MAX, MIN are derived from tri- components of RGB, and maximum is MAX, and the smallest is MIN；
Tri- component input processors of H, S, V after 2-3) converting sample image, are compared with the predefined model, place
It manages device and exports comparison result.
3. comprehensive intelligent water quality recognition methods according to claim 2, which is characterized in that the predefined model is such as
Under:
4. comprehensive intelligent water quality recognition methods according to claim 1, which is characterized in that step 3) includes:
Gray processing processing 3-1) is carried out to each component of the RGB of sorted image；Obtain gray scale image；
The gray scale image 3-2) is subjected to gray-scale compression, gray scale is dropped to 16 grades；
The mean value and standard deviation of this four parameters of energy, entropy, the moment of inertia and correlation in compressed gray scale image 3-3) are calculated,
Distance is taken as 1, and angle takes 0 °, 45 °, 90 ° and 135 °, generates the co-occurrence matrix of gray level image；
3-4) co-occurrence matrix is normalized, obtains octuple textural characteristics data；
3-5) the octuple textural characteristics data of all figures in every class image are averaged, obtain one group of octuple textural characteristics
Data model is stored into processor.
5. comprehensive intelligent water quality recognition methods according to claim 4, which is characterized in that step 3-1) in each point of RGB
Measuring gray processing processing ratio is respectively 0.3,0.59,0.11.
6. comprehensive intelligent water quality recognition methods according to claim 1, which is characterized in that step 6) includes:
Calculate a kind of image of certain in the textural characteristics data and the textural characteristics data model of the water sample image to be detected
A cut off value d is arranged in the Euclidean distance d of textural characteristics data0, as d < d0, belong to this kind of images, otherwise, be not belonging to this
A kind of image.
7. comprehensive intelligent water quality recognition methods according to claim 6, which is characterized in that Euclidean distance d1Calculation formula
Are as follows:
D=sqrt (∑ (xi1-xi2)2)
Wherein, d indicates two n-dimensional vector a (x11, x21..., xn1) and b (x12, x22..., xn2) between Euclidean distance.
8. comprehensive intelligent water quality recognition methods according to claim 7, it is characterised in that: cut off value d0Take 0.5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810785404.4A CN109118548A (en) | 2018-07-17 | 2018-07-17 | A kind of comprehensive intelligent water quality recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810785404.4A CN109118548A (en) | 2018-07-17 | 2018-07-17 | A kind of comprehensive intelligent water quality recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109118548A true CN109118548A (en) | 2019-01-01 |
Family
ID=64862765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810785404.4A Pending CN109118548A (en) | 2018-07-17 | 2018-07-17 | A kind of comprehensive intelligent water quality recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109118548A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110261560A (en) * | 2019-07-05 | 2019-09-20 | 安徽大学 | The water source recognition methods of complex hydrologic geology water bursting in mine and system |
| CN110334673A (en) * | 2019-07-10 | 2019-10-15 | 青海中水数易信息科技有限责任公司 | The long information system processed in river with intelligent recognition image function and method |
| CN110414334A (en) * | 2019-06-20 | 2019-11-05 | 浙江大学 | A kind of smart water quality recognition methods maked an inspection tour based on unmanned plane |
| CN110533626A (en) * | 2019-06-19 | 2019-12-03 | 浙江大学 | A kind of round-the-clock water quality recognition methods |
| CN110751643A (en) * | 2019-10-21 | 2020-02-04 | 睿视智觉（厦门）科技有限公司 | Water quality abnormity detection method, device and equipment |
| CN112816480A (en) * | 2021-02-01 | 2021-05-18 | 奎泰斯特(上海)科技有限公司 | Water quality enzyme substrate identification method |
| CN113466421A (en) * | 2021-06-21 | 2021-10-01 | 海南掌上天下网络技术有限公司 | Water quality monitoring system based on internet |
| CN114764861A (en) * | 2022-04-19 | 2022-07-19 | 江苏禹润水务研究院有限公司 | Sewage treatment verification method based on computer vision |
| CN115690502A (en) * | 2022-11-02 | 2023-02-03 | 珠江水利委员会珠江水利科学研究院 | Method and system for eliminating water ripples of near-shore and inland water bodies and readable storage medium |
| CN117152747A (en) * | 2023-10-31 | 2023-12-01 | 南通鼎城船舶技术有限公司 | Microorganism identification method for ship ballast water |
| CN117576550A (en) * | 2023-10-26 | 2024-02-20 | 广东理工学院 | Intelligent shrimp pond water quality monitoring method and system based on deep learning and decision tree |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101900687A (en) * | 2010-07-06 | 2010-12-01 | 重庆大学 | Method for monitoring and early warning water bloom in small water area based on image processing |
| CN103198325A (en) * | 2013-03-19 | 2013-07-10 | 上海理工大学 | Cyanophyta algal bloom monitoring system |
| CN105675623A (en) * | 2016-01-29 | 2016-06-15 | 重庆扬讯软件技术有限公司 | Real-time analysis method for sewage color and flow detection on basis of sewage port video |
| US20160171302A1 (en) * | 2014-12-12 | 2016-06-16 | Kristin Lavigne | System and method for managing water |
| CN106295653A (en) * | 2016-07-29 | 2017-01-04 | 宁波大学 | A kind of water quality image classification method |
| CN108051442A (en) * | 2017-12-28 | 2018-05-18 | 上海传英信息技术有限公司 | A kind of water quality recognition methods and water quality identifying system based on intelligent terminal |
-
2018
- 2018-07-17 CN CN201810785404.4A patent/CN109118548A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101900687A (en) * | 2010-07-06 | 2010-12-01 | 重庆大学 | Method for monitoring and early warning water bloom in small water area based on image processing |
| CN103198325A (en) * | 2013-03-19 | 2013-07-10 | 上海理工大学 | Cyanophyta algal bloom monitoring system |
| US20160171302A1 (en) * | 2014-12-12 | 2016-06-16 | Kristin Lavigne | System and method for managing water |
| CN105675623A (en) * | 2016-01-29 | 2016-06-15 | 重庆扬讯软件技术有限公司 | Real-time analysis method for sewage color and flow detection on basis of sewage port video |
| CN106295653A (en) * | 2016-07-29 | 2017-01-04 | 宁波大学 | A kind of water quality image classification method |
| CN108051442A (en) * | 2017-12-28 | 2018-05-18 | 上海传英信息技术有限公司 | A kind of water quality recognition methods and water quality identifying system based on intelligent terminal |
Non-Patent Citations (8)
| Title |
|---|
| KWOKHOLD: "HSV颜色相似度", 《HTTPS://BLOG.CSDN.NET/A2009374138/ARTICLE/DETAILS/52174856》 * |
| LSKYNE: "纹理特征分析的灰度共生矩阵（GLCM）", 《HTTPS://BLOG.CSDN.NET/LSKYNE/ARTICLE/DETAILS/8659225》 * |
| 吴曙光等: "基于HIS模型的污水颜色识别处理", 《电子技术》 * |
| 张丽: "基于颜色和纹理特征的图像检索技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李昂: "基于SVM支持向量机的水质图像分析", 《电脑知识》 * |
| 王丽霞等: "基于数码摄像的蓝藻识别研究及工程实现", 《安徽农业科学》 * |
| 章智儒: "SVM在图像分类中的应用", 《信息技术》 * |
| 胡焯源: "基于HSV颜色空间的车身颜色识别算法", 《辽宁工业大学学报（自然科学版）》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533626B (en) * | 2019-06-19 | 2021-11-09 | 浙江大学 | All-weather water quality identification method |
| CN110533626A (en) * | 2019-06-19 | 2019-12-03 | 浙江大学 | A kind of round-the-clock water quality recognition methods |
| CN110414334A (en) * | 2019-06-20 | 2019-11-05 | 浙江大学 | A kind of smart water quality recognition methods maked an inspection tour based on unmanned plane |
| CN110414334B (en) * | 2019-06-20 | 2021-05-11 | 浙江大学 | Intelligent water quality identification method based on unmanned aerial vehicle inspection |
| CN110261560A (en) * | 2019-07-05 | 2019-09-20 | 安徽大学 | The water source recognition methods of complex hydrologic geology water bursting in mine and system |
| CN110334673A (en) * | 2019-07-10 | 2019-10-15 | 青海中水数易信息科技有限责任公司 | The long information system processed in river with intelligent recognition image function and method |
| CN110751643A (en) * | 2019-10-21 | 2020-02-04 | 睿视智觉（厦门）科技有限公司 | Water quality abnormity detection method, device and equipment |
| CN112816480A (en) * | 2021-02-01 | 2021-05-18 | 奎泰斯特(上海)科技有限公司 | Water quality enzyme substrate identification method |
| CN113466421A (en) * | 2021-06-21 | 2021-10-01 | 海南掌上天下网络技术有限公司 | Water quality monitoring system based on internet |
| CN114764861A (en) * | 2022-04-19 | 2022-07-19 | 江苏禹润水务研究院有限公司 | Sewage treatment verification method based on computer vision |
| CN114764861B (en) * | 2022-04-19 | 2022-10-28 | 江苏禹润水务研究院有限公司 | Sewage treatment verification method based on computer vision |
| CN115690502A (en) * | 2022-11-02 | 2023-02-03 | 珠江水利委员会珠江水利科学研究院 | Method and system for eliminating water ripples of near-shore and inland water bodies and readable storage medium |
| CN115690502B (en) * | 2022-11-02 | 2023-06-13 | 珠江水利委员会珠江水利科学研究院 | Method, system and readable storage medium for eliminating water wave of inland and coastal water body |
| CN117576550A (en) * | 2023-10-26 | 2024-02-20 | 广东理工学院 | Intelligent shrimp pond water quality monitoring method and system based on deep learning and decision tree |
| CN117152747A (en) * | 2023-10-31 | 2023-12-01 | 南通鼎城船舶技术有限公司 | Microorganism identification method for ship ballast water |
| CN117152747B (en) * | 2023-10-31 | 2023-12-29 | 南通鼎城船舶技术有限公司 | Microorganism identification method for ship ballast water |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109118548A (en) | A kind of comprehensive intelligent water quality recognition methods | |
| CN109961426B (en) | Method for detecting skin of human face | |
| US8385638B2 (en) | Detecting skin tone in images | |
| CN105868722A (en) | Identification method and system of abnormal power equipment images | |
| CN105023008A (en) | Visual saliency and multiple characteristics-based pedestrian re-recognition method | |
| CN106960182B (en) | A kind of pedestrian's recognition methods again integrated based on multiple features | |
| CN103034838A (en) | Special vehicle instrument type identification and calibration method based on image characteristics | |
| CN112149543B (en) | Building dust recognition system and method based on computer vision | |
| CN113887412B (en) | Detection method, detection terminal, monitoring system and storage medium for pollution emission | |
| CN106483143A (en) | A kind of solar energy photovoltaic panel dust stratification on-Line Monitor Device and its detection method | |
| CN109886146B (en) | Flood information remote sensing intelligent acquisition method and device based on machine vision detection | |
| CN106934377A (en) | A kind of improved face detection system | |
| CN105466921A (en) | Simultaneous detection method of many samples | |
| CN105184308B (en) | Remote sensing image building detection classification method based on global optimization decision | |
| WO2021217764A1 (en) | Human face liveness detection method based on polarization imaging | |
| CN106599880A (en) | Discrimination method of the same person facing examination without monitor | |
| WO2022032675A1 (en) | Product testing method and apparatus, computer readable storage medium, and electronic device | |
| CN111274871B (en) | Forest fire damage degree extraction method based on light and small unmanned aerial vehicle | |
| Marcos et al. | Automated benthic counting of living and non-living components in Ngedarrak Reef, Palau via subsurface underwater video | |
| CN110728212A (en) | Road well lid monitoring device and method based on computer vision | |
| CN108563997A (en) | It is a kind of establish Face datection model, recognition of face method and apparatus | |
| CN102542304B (en) | Region segmentation skin-color algorithm for identifying WAP (Wireless Application Protocol) mobile porn image | |
| CN116052041A (en) | Indicating lamp state identification method based on depth network | |
| CN108830238A (en) | The adaptively selected system of lipstick color | |
| CN114973104A (en) | Dynamic flame detection algorithm and system based on video image |
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: 20190101 |