CN1793913A - Biological water monitoring device based on machine vision - Google Patents
Biological water monitoring device based on machine vision Download PDFInfo
- Publication number
- CN1793913A CN1793913A CNA2005100623056A CN200510062305A CN1793913A CN 1793913 A CN1793913 A CN 1793913A CN A2005100623056 A CNA2005100623056 A CN A2005100623056A CN 200510062305 A CN200510062305 A CN 200510062305A CN 1793913 A CN1793913 A CN 1793913A
- Authority
- CN
- China
- Prior art keywords
- fish
- water quality
- fish jar
- water
- value
- 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.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 161
- 238000012806 monitoring device Methods 0.000 title claims description 23
- 241000251468 Actinopterygii Species 0.000 claims abstract description 212
- 230000002159 abnormal effect Effects 0.000 claims description 31
- 238000012544 monitoring process Methods 0.000 claims description 29
- 230000005856 abnormality Effects 0.000 claims description 26
- 239000003643 water by type Substances 0.000 claims description 26
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 238000011002 quantification Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000003707 image sharpening Methods 0.000 claims description 4
- 241001339245 Callirhoe digitata Species 0.000 claims description 3
- 235000002259 Callirhoe involucrata Nutrition 0.000 claims description 3
- 230000004075 alteration Effects 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 4
- 239000003651 drinking water Substances 0.000 description 9
- 235000020188 drinking water Nutrition 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 239000012141 concentrate Substances 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 201000010099 disease Diseases 0.000 description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 230000036541 health Effects 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000003911 water pollution Methods 0.000 description 5
- 238000011109 contamination Methods 0.000 description 4
- 239000010865 sewage Substances 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000002285 radioactive effect Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 235000012206 bottled water Nutrition 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 230000035622 drinking Effects 0.000 description 2
- 239000002384 drinking water standard Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- HDDSHPAODJUKPD-UHFFFAOYSA-N fenbendazole Chemical compound C1=C2NC(NC(=O)OC)=NC2=CC=C1SC1=CC=CC=C1 HDDSHPAODJUKPD-UHFFFAOYSA-N 0.000 description 2
- 238000005755 formation reaction Methods 0.000 description 2
- 239000013505 freshwater Substances 0.000 description 2
- 239000003673 groundwater Substances 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000001727 in vivo Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000001717 pathogenic effect Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 231100000614 poison Toxicity 0.000 description 2
- 230000007096 poisonous effect Effects 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 210000000697 sensory organ Anatomy 0.000 description 2
- 239000008399 tap water Substances 0.000 description 2
- 235000020679 tap water Nutrition 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- XFXPMWWXUTWYJX-UHFFFAOYSA-N Cyanide Chemical compound N#[C-] XFXPMWWXUTWYJX-UHFFFAOYSA-N 0.000 description 1
- 241000238557 Decapoda Species 0.000 description 1
- 206010012735 Diarrhoea Diseases 0.000 description 1
- 241000588724 Escherichia coli Species 0.000 description 1
- 206010020751 Hypersensitivity Diseases 0.000 description 1
- 208000015924 Lithiasis Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 206010033307 Overweight Diseases 0.000 description 1
- 241000114976 Themisto compressa Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- UELITFHSCLAHKR-UHFFFAOYSA-N acibenzolar-S-methyl Chemical compound CSC(=O)C1=CC=CC2=C1SN=N2 UELITFHSCLAHKR-UHFFFAOYSA-N 0.000 description 1
- 208000026935 allergic disease Diseases 0.000 description 1
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 description 1
- 230000003698 anagen phase Effects 0.000 description 1
- 229910052785 arsenic Inorganic materials 0.000 description 1
- RQNWIZPPADIBDY-UHFFFAOYSA-N arsenic atom Chemical compound [As] RQNWIZPPADIBDY-UHFFFAOYSA-N 0.000 description 1
- 125000004429 atom Chemical group 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
- 230000000903 blocking effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 231100000481 chemical toxicant Toxicity 0.000 description 1
- 239000000460 chlorine Substances 0.000 description 1
- 229910052801 chlorine Inorganic materials 0.000 description 1
- 125000001309 chloro group Chemical group Cl* 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012851 eutrophication Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000012010 growth Effects 0.000 description 1
- 208000006454 hepatitis Diseases 0.000 description 1
- 231100000283 hepatitis Toxicity 0.000 description 1
- 230000009610 hypersensitivity Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 239000010842 industrial wastewater Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 150000002500 ions Chemical class 0.000 description 1
- 150000001455 metallic ions Chemical class 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 235000020825 overweight Nutrition 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 230000036284 oxygen consumption Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000002957 persistent organic pollutant Substances 0.000 description 1
- 150000002989 phenols Chemical class 0.000 description 1
- 231100000683 possible toxicity Toxicity 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000010802 sludge Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 239000003440 toxic substance Substances 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- -1 turbidity Substances 0.000 description 1
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A water quality detection device of biological type based on machine vision is prepared as putting fishbowl in detected water area for detecting small body fish in fishbowl by virtual transducer and microprocessor, setting said transducer on top of fishbowl to monitor ecological state of small body fish, then sending state signal to microprocessor identification system for obtaining water quality comprehensive index of monitored water area according to result of calculating observed ecological state of small body fish.
Description
(1) technical field
The invention belongs to the biological application of ecological information water quality inspection technique aspect the water quality safety supervision such as computer image processing technology, the network communications technology and corpusculum fish, mainly be applicable to water monitoring device in rivers and lakes and system water industry.
(2) background technology
Along with the development of society, people require the index of water supply industry control tap water quality also more and more detailed.Issue, implement to comprise 23 the first cover drinking water standard from China in 1976, to the new potable water examination criteria that September calendar year 2001, the Ministry of Public Health issued again, require 96 of water quality detection projects as can be seen: the drinking water quality that people more and more require the demand of relying is high-quality, safety, reliable more.
At present, the water quality standard that various countries formulated mainly comprises the following aspects: bacteriology index, poisonous and harmful substance index, sense organ index and radioactive indicator.The World Health Organization (WHO), the European Economic Community (EC) and U.S.'s water quality standard for drinking water etc. think that all the bacteriology index is extremely important because it at one time in, can cause large stretch of crowd morbidity or dead.According to statistics, there is more than 1,200 ten thousand the Died Of Disease of children below five years old every year in developing country, surpasses 3,000,000 people and dies from diarrhoea, and is wherein most owing to contaminated water causes.Again according to communique, 64 of water quality accidents take place in 1991-1999 U.S. water undertaking altogether, pathogenic number reaches 422820 people, wherein 99% the cause of disease be the water quality accident poisonous and harmful substance index of enteron aisle aspect be prevent long-term drinking and in vivo accumulation cause the index of chronic disease or cancer, mainly comprise partial organic substances in the water body, inorganics and metallic ion, definite principle is that the people takes in and the amount of the health risk that nothing is discovered all the life.
Though the sense organ index may be directly not unhealthful, can cause the user to suspect, detest, so the organoleptic indicator will reach the acceptable degree of user in the water body.
Radioactive indicator also be prevent long-term drinking and in vivo accumulation cause the index of disease, comprise mainly producing radioactive element or material in the water body that definite principle is the lifelong absorption of people and the amount of the health risk that nothing is discovered.
Report according to the World Health Organization (WHO): the whole world 1/3rd residents lack safe drinking water at present, account for 80% of whole cases because water pollutes the disease that causes.The potable water of safety and capacity and pathogenic case has kind more than 50 for want of, the disease that take place to close with water average every day has 650,000, seizes 2.5 ten thousand people's valuable life every day, 5,000 ten thousand death of child are arranged every year approximately, 9,000 ten thousand people suffer from hepatitis, 7,000 ten thousand lithiasises, 3,500 ten thousand people's cardiovascular diseases.In developing country, situation more very, the case more than 80% and 18% dead all closely related with drinking water quality.
Environmental Protection Agency early annual report once pointed out: the U.S. has 20% city to be subjected to obvious pollution, and 63% rural quality of drinking water is overproof, contains the tap water that bacterium and toxic chemical substance reach hazard level so that 3,700 ten thousand Americans drink.
The gross amount of water resources of China is about 28000 billion cubic meters (referring to freshwater resources), actual can develop be about 12000 billion cubic meters, the 6th in the row world, by water resource of per capita, have only the world per capita the water yield 1/4th, only come 109, and, the spatial and temporal distributions of China's water resource is very inhomogeneous, and Nan Duobei is few, and 80% of national water resource is concentrated and to be distributed in cultivated area and to account for 36% the Yangtze river basin and areas to the south thereof.
China is one of 13 poor-water countries in the world, and water resource is in short supply state for a long time.Development ﹠ construction along with population growth, socio-economic development and town and country; industrial sewage and sanitary sewage discharge capacity constantly increase again; the unprocessed water body that directly enters of overwhelming majority sewage; cause many waters contaminated; drinking water source water quality goes from bad to worse; water pollutes and has aggravated the water resources crisis of China, and oneself threatens people health and has influenced sustainable development of economy.
In China, present annual industrial waste water and sanitary sewage discharge capacity surpass 36,000,000,000 tons more than, wherein 95% do not pass through any processing, also contain 1.5 hundred million tons of ight soil water.Make thus in 138 cities section, the whole nation 133 sections oneself be subjected in various degree pollution, 78% section is not suitable for doing the drinking water source.Only have 20% to meet country's " ground water environment quality standard " (GB3838-2002) I, 11 class standards in the emphasis section of the whole nation seven big water systems now.82% rivers and lakes are polluted, 92% city faces the water pollution threat, in 71 water head sites of 32 key cities in the whole nation, there are 30 not reach (GB3838-2002) II class drinking water standard of country's " ground water environment quality standard ", account for sum 42%, also have 90% above urban waters seriously polluted, cause the situation of water quality type lack of water.At present, there is 79% population to drink to be subjected to the water that pollutes in various degree in the whole nation, and wherein people more than 700,000,000 drinks the Escherichia coli water that exceeds standard, and 1.7 hundred million populations are drunk by the water of organic contamination.
City and near river thereof are still based on organic pollutants, and main contamination index is petroleum-type, permanganate indices and ammonia nitrogen.The city rivers pollution degree, the north overweights south.Near the more flourishing cities and towns of industry water pollution is outstanding.The quantity in contamination type lack of water city is in rising trend.The outstanding environmental problem of lake and reservoir is that serious eutrophication and oxygen consumption organic increase.
The Harbin incident of cutting off the water that take place in November, 2005 causes various circles of society's strong interest, and the various places water supply department has been formulated tight water source inspection supervision system, and emphasis is strengthened the monitoring to water-quality guideline such as prussiate, arsenic, Volatile Phenols.Some water factory also sets up the atom claire, observes the corpusculum fish and observes its ecology by putting in a suitable place to breed, in time grasps the safety of water quality.Selected test fish wants cube less, conditions such as will satisfying the essential hypersensitivity of test organisms simultaneously, draw materials conveniently, be convenient to raising or breeding, strain is pure.At present, mainly adopt Hind (T.albnubes) and fresh water shrimp (P.compressa) to make test organisms.
Biological monitoring is systematically to utilize biological respinse to estimate the variation of environment, and its information is applied to a science in the environmental quality control program.The purpose of biological monitoring is to wish before objectionable impurities does not also reach the system of being received, and just with the fastest speed it is detected in factory or scene, in order to avoid destroy the ecologic equilibrium of the system that received; Or can scout out potential toxicity, in order to avoid lead to bigger public hazards.
Biological monitoring is the important supplement of physics and chemistry monitoring, for estimating environmental quality crucial effect is arranged.Instantaneous pollution situation is generally only considered in the physics and chemistry monitoring, accomplish long-term continuous monitoring, and is inappropriate often economically.Understand the cumulative effect of pollution, adopt biological monitoring more suitable.Simultaneously, only utilize the concentration value of polluter to reflect that pollution level and harm also are incomplete, to be not equal to toxicity atomic because the content of some polluter in environment is atomic, and vice versa.Cooperate with biological monitoring, make full use of the susceptibility of indicator organism, just can reflect real pollution situation more exactly the pollutant toxic reaction.
Under certain condition, interknit, condition each other between community of aquatic organism and the water environment, keeping relative equilibrium relation nature, temporary transient.The polluter that enters in the water environment, must act on bion, population and group, influence quantity, species composition and diversity thereof, stability, yield-power and the physiological situation of intrinsic biotic population in the ecosystem, make some hydrobionts wither away gradually, other hydrobionts then can be survived down, and quantity individual and population increases gradually.The water pollution organism monitoring is exactly to utilize these to change the variation that characterizes quality of water environment.
Compare with the physics and chemistry monitoring, biological monitoring has the characteristics of oneself: biological monitoring can reflect the combined influence of all contaminations; The physics and chemistry monitoring is a periodic sampling, and the result can not reflect the situation that sampling is forward and backward, and organism in water has compiled the situation that whole growth phase environmental factor changes; Some hydrobiont is very sensitive to pollutant, and the trace element concentration that some exact instrument all can not surveyed but can act on biological cylinder accumulation and measured by " biological amplify ".Biological monitoring also has the weak point of oneself: biological monitoring can not be measured water pollution qualitative and quantitatively; Sensitivity that detects and selectivity aspect detect not as physics and chemistry; Some biological detection takes longer.
Present water quality physics and chemistry detect mainly by means of online PH, ORP, electricity lead, advanced water examination instruments such as dissolved oxygen DO, chlorine residue, compound chlorine, turbidity, sludge concentration (MLSS), ion concentration (electrode method), electric coupling plasma mass spectrometer measure, can detect various subitem water-quality guideline by various water examination instruments, have the accuracy of detection height, testing instruments cost an arm and a leg, large scale measurement is difficult for shortcomings such as enforcement but also exist.Though the aquatic organism that lives in the river is not sociable, be the loyal witness of quality of river water.And the ecological situation of biologies such as corpusculum fish can directly, synthetically reflect water-quality guideline, therefore can in time grasp the safety of water quality by the ecology of observing the corpusculum fish, and mainly still adopt the artificial mode of confirming to finish at present.
(3) summary of the invention
Be difficult for the deficiency implemented in order to overcome existing water monitoring device use cost height, large scale measurement, the invention provides a kind of good economy performance, can realize large scale measurement, biological water monitoring device that can rapid and reliable grasp water quality safety based on machine vision.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of biological water monitoring device based on machine vision, described water monitoring device comprise fish jar, the vision sensor that be used to detect fish jar in corpusculum fish and the microprocessor of sinking in the monitoring waters; Described fish jar is a wine cup shape, and the top of described fish jar comprises loam cake fixed mount, the transparent frame of looking around, and the middle part of described fish jar is a cylindrical mesh, and described fish jar bottom is dead fish collecting region; Described loam cake fixed mount is fixedlyed connected with the upper end of cylindrical mesh, fixedlys connected with the fish jar bottom in the lower end of described cylindrical mesh; The described transparent frame of looking around is positioned at fish jar, describedly transparently looks around the below that frame is installed in the loam cake fixed mount, and describedly transparently looks around frame and the loam cake fixed mount is tightly connected; The described transparent frame of looking around is following spill, fish collecting region for being at death's door between the described transparent top of looking around frame and cylindrical mesh, the surface level in described waters to be monitored is positioned at the fish collecting region of being at death's door, and the middle and lower part of described cylindrical mesh is corpusculum fish behaviour area; Described vision sensor is installed in the central authorities of loam cake fixed mount, and the monitoring range of described vision sensor is the middle and lower part of described cylindrical mesh;
Described microprocessor comprises:
The view data read module is used to read the video image information of coming from the vision sensor biography;
The data file memory module, the video image information that is used for reading is kept at data-carrier store by file mode;
The image pretreatment module is used for carrying out at rgb color space filtering and eliminating noise, image sharpening, the contrast enhancing operation of fish jar internal image;
The color space conversion module is used for the image rgb color space is transformed into yuv space;
Corpusculum fish identification module, be used for according to selected fish jar corpusculum fish, obtain this fish image at (Cr, Cb) spatial distributions model, calculate light emitting source and whether drop on the fish image at (Cr, Cb) in the spatial distributions model, be used as judging the foundation of fish, computing formula is formula (1):
Cr in the formula (2), Cb is the sample standard average of corpusculum fish Cr, Cb in the fish jar, A, B, C are respectively the coefficients that is come out by sample standard deviation and mean value computation;
Area size computing module, be used for result of calculation by the color space conversion module, set up a matrix M with the identical size of fish jar internal image pixel, in this matrix M, drop on the fish image at (Cr by what confirm, Cb) pixel of light emitting source is set at 1 in the spatial distributions model, all the other are set at 0, and pixel is that 1 number obtains the fish bulk area among the statistical matrix M;
The water quality judge module is used for comparing with existing standard mean value, minimum value according to the big or small counting statistics value of the above-mentioned area that obtains:
More than or equal to standard means, be judged as water quality safety as this statistical value;
Less than standard means, and greater than minimum value, alerting is observed as this statistical value;
Less than minimum value, judge that water quality is unusual as this statistical value, send alarm signal.
Further, described water quality judge module also comprises:
Water quality abnormality degree computing unit is used for after judging that water quality is unusual above-mentioned area size counting statistics value and existing minimum value being compared, and calculating formula is (2):
In the formula (3), Water quality
AbnormalBe abnormality degree quantification value;
The abnormality degree output unit is used for comparing according to above-mentioned abnormality degree quantification value and preset threshold value, exports the abnormality degree report of different brackets respectively.
Further again, preset threshold value is 7 grades in the described abnormality degree output unit, comprises-10 ,-20 ,-30 ,-40 ,-50 ,-60, and less than-70, abnormality degree comprises:
Water quality
Abnormal, be severely subnormal at＜-70 o'clock;
-70≤Water quality
Abnormal＜-60 o'clock, for than severely subnormal;
-60≤Water quality
Abnormal＜-50 o'clock, for having unusual and having severely subnormal trend;-50≤Water quality
Abnormal＜-40 o'clock, for unusually;
-40≤Water quality
Abnormal＜-30 o'clock, for moderate unusual;
-20≤Water quality
Abnormal＜-30 o'clock, for the part abnormal occurrence is arranged;
-20≤Water quality
Abnormal＜-10 o'clock, for abnormal occurrence is arranged slightly;
-10≤Water quality
Abnormal＜0 o'clock,, the mile abnormality phenomenon to note for being arranged.
Further, described water monitoring device also comprises and extraneous communication module of communicating by letter, described microprocessor also comprises: water quality exception reporting module, be used for after judging that water quality is unusual, the ground domain information and the liaison method that obtain waters to be monitored from database send to managerial personnel by communication module.
Described color space conversion module, the relational expression that is transformed into yuv space from rgb color space is formula (3):
Y＝0.301*R+0.586*G+0.113*B
U＝-0.301*R-0.586*G+0.887*B (3)
V＝0.699*R-0.586*G-0.113*B
In the following formula, Y represents the brightness of YUV color model, and U, V are two chrominance components of YUV color model, the expression aberration; R represents the redness of rgb color space; G represents the green of rgb color space; B represents the blueness of rgb color space.
On the described loam cake fixed mount illuminating lamp is installed, described illuminating lamp is positioned at the top of vision sensor; Described microprocessor also comprises the brightness judge module, is used for the luminance component according to the Y of yuv space, if, connect illuminating lamp when the value of Y during less than thresholding Ymin, when the value of Y surpass thresholding Ymin 20% the time, turn-off illuminating lamp.
Described microprocessor, data-carrier store are installed on the loam cake fixed mount, and described transparent bottom center of looking around frame is installed the buoyancy adjustment cylinder, and the bottom of described fish jar is an infundibulate, and described fish jar bottom connects the center of gravity hammer.
Described vision sensor is the omni-directional visual camera.
Principle of work of the present invention is: the top that is installed in the fish jar cylinder body that is holding the corpusculum fish as the machine vision unit (camera) of water area water-quality security monitoring function, monitoring the ecological situation of corpusculum fish in the cylinder body, for the ecological situation with corpusculum fish in the fish jar makes a distinction, such as the fish in moving about, be at death's door and dead fish, relate to the Several Key Problems of the housing structure design that is holding the corpusculum fish:
(1) institute's employing fish jar shape of block can make a distinction the ecological situation of corpusculum fish, in general, be at death's door or dead fish all can be kept afloat or sunk to cylinder bottom, the designed fish jar shape of block of the present invention for as the Y word of a hollow along the center line column type that rotates a circle, outward appearance looks like a wineglass, as shown in Figure 1.Fish during the shaped design of fish jar is wanted will to move about, be at death's door and dead fish automatic distinguishing comes, fish of being at death's door and dead fish all will concentrate on the top or the bottom of fish jar, and see that from the depression angle of fish jar the fish of being at death's door and dead fish all will concentrate in the middle circle of bottom or float near the cylindrical of bottom, and the good fish of ecological situation will move about in round body type broad in the middle;
(2) round body type broad in the middle of fish jar cylinder body is made of net, makes that the water in the cylinder body can monitor the exchange of flowing of water in the waters with this; The transition portion of the little circle of round body type broad in the middle and bottom of fish jar cylinder body adopts certain gradient transition and any surface finish friction little, so that be at death's door or dead fish can rely on buoyancy or gravity automatically to climb up on top of the water or sinks to cylinder bottom; Guarantee when making whole device can be placed in the waters of supervision with at the machine vision camera perpendicular to surface level, at the bottom of whole device configuration center of gravity hammer; Simultaneously the gravity in water of whole device is in the water surface all the time with the top of its floatage energy assurance fish jar cylinder body, so that can the fish that ecological situation is bad focus on the top of cylinder body;
(3) adopt the machine vision camera only round body type space broad in the middle to be monitored, whether the water area water-quality that the size of the area by adding up the fish that move about in the round body type space broad in the middle among the present invention is judged this supervision safety;
(4) fish of being adopted can select a kind of fish that apparent in view color characteristic is arranged as the object of observation according to the waters and the ambient conditions of locality, obtain the elemental area of the fish in the fish jar on the two dimensional surface by color space.
Because above-mentioned water quality safety judgement is to obtain according to the area of adding up the fish that move about in the cylinder body, what of fish in this area and the cylinder body are relevant with size, therefore when judging water quality safety, adopted the notion of a relative average area value among the present invention, concern standard value and the minimum value that obtains under this seasonal climate situation according to seasonal climate, as find that measured value is lower than minimum value, system can submit measurement report to automatically according to the ratio size of measured value and minimum value, so that the water quality safety managerial personnel detect in more detail to the scene, waters, clear and definite water quality situation and in time find out pollution source and Corresponding Countermeasures.Because having adopted in the system is relative value, therefore can remove complicated work such as the demarcation of Vision Builder for Automated Inspection and the conversion between the various different coordinates from.
The computer vision technique that developed recently gets up provides a kind of new solution for the ecology of observing the corpusculum fish, simultaneously along with communication and development of internet technology, for the ecological situations of remote reviewing corpusculum fish provides various new means.Therefore how the ecological information observational technique by computer image processing technology, the network technology communication technology and corpusculum fish provides a kind of security means of quick, reliable, comprehensive timely grasp water quality for the water-quality monitoring field, and the real-time omnidirectional images that obtains according to the ODVS camera, monitor water quality safety whether in the waters by calculating automatic judgement, also can obtain the water quality information that monitors in the waters simultaneously by various remote access means.
The shoal of fish area that moves about in the camera visual field is discerned statistics, because the fish in will moving about in the shaped design of above-mentioned fish jar, be at death's door and dead fish automatic distinguishing comes, fish of being at death's door and dead fish all will concentrate on the top or the bottom of fish jar, and see that from the depression angle of fish jar the fish of being at death's door and dead fish all will concentrate in the middle circle of bottom or float near the cylindrical of bottom, as shown in Figure 1, the former is owing to there be blocking of a column type in these two fields, the latter is because not in the machine vision scope, therefore when the shoal of fish area that statistics is moved about, can give no thought to the fish in moving about or be at death's door and dead fish, as long as the area of fish is just passable in the statistics fish jar, in the identification statistical treatment, mainly by the image pretreatment module, the color space conversion module, brightness judgement and electricity-saving lamp switch module, area size computing module, formations such as water quality situation judge module.
Shoal of fish area account form in the described fish jar is discerned and is added up by color characteristic, in order to avoid the number of the fish in moving about such as is added up at the complicated calculations problem among the present invention, in the structural design of fish jar, got rid of simultaneously being at death's door or the statistics of dead fish, therefore hold the color characteristic of the fish in the moving about in the fish jar, the area statistics value of calculating the fish in moving about just can obtain the composite water quality situation in this supervision waters.Outdoor intensity of illumination can since sunlit variation and from weak to strong again by by force to a little less than, and these variations mainly change on the Y component, and the variation on U and the V component is little, the present invention has utilized the brightness independence of this supervision background to carry out pattern-recognition.
Set up a matrix M with the identical size of fish jar internal image pixel, in this matrix M, drop on the fish image at (Cr by what confirm, Cb) pixel of light emitting source is set at 1 in the spatial distributions model, all the other are set at 0, pixel is 1 number among we the statistical matrix M then, just obtain how many integrated informations of fish that can reflect in moving about in the fish jar, this statistical value greater than, equal standard means and just think that present water quality is safe, system will point out the supvr to note often observing during less than standard means and greater than minimum value, is judged as unusual during less than minimum value (safe-guard line).And can further abnormal conditions be divided into several processing grades.
Beneficial effect of the present invention mainly shows: 1, good economy performance; 2, can realize large scale measurement; 3, can rapid and reliable grasp water quality safety.
(4) description of drawings
Fig. 1 is based on the structure principle chart of the biological water monitoring device of machine vision;
The synoptic diagram of corpusculum fish image in Fig. 2 fish jar that to be machine vision observe from depression angle;
The variation diagram of the corpusculum fish area (overlooking) that moves about in the interim supervision waters (fish jar) that obtains by computer vision when Fig. 3 is;
Fig. 4 calculates the process flow diagram that monitors the ecological situation of corpusculum fish in the waters (fish jar) in the computer vision means.
(5) embodiment
Below in conjunction with accompanying drawing the present invention is further described.
With reference to Fig. 1, Fig. 2, Fig. 3, Fig. 4, a kind of biological water monitoring device based on machine vision, described water monitoring device comprise fish jar 1, the vision sensor 2 that be used to detect fish jar in corpusculum fish and the microprocessor 3 of sinking in the monitoring waters; Described fish jar 1 is a wine cup shape, and the top of described fish jar comprises loam cake fixed mount 4, the transparent frame 5 of looking around, and the middle part of described fish jar is a cylindrical mesh 6, and described fish jar bottom is dead fish collecting region 7; Described loam cake fixed mount 4 is fixedlyed connected with the upper end of cylindrical mesh 6, fixedlys connected with the fish jar bottom in the lower end of described cylindrical mesh 6; The described transparent frame 5 of looking around is positioned at fish jar 1, describedly transparently looks around the below that frame 5 is installed in the loam cake fixed mount, and the described transparent frame 5 of looking around is tightly connected with loam cake fixed mount 4; The described transparent frame 5 of looking around is following spill, fish collecting region 8 for being at death's door between the described transparent top of looking around frame 5 and cylindrical mesh 6, the surface level in described waters to be monitored is positioned at the fish collecting region 8 of being at death's door, and the middle and lower part of described cylindrical mesh 6 is corpusculum fish behaviour area 9; Described vision sensor peace 2 is contained in the central authorities of loam cake fixed mount 4, and the monitoring range of described vision sensor 2 is the middle and lower part of described cylindrical mesh 6; Described microprocessor 3 comprises:
View data read module 10 is used to read the video image information of coming from the vision sensor biography;
Data file memory module 11, the video image information that is used for reading is kept at data-carrier store by file mode;
Image pretreatment module 10 is used for carrying out at rgb color space filtering and eliminating noise, image sharpening, the contrast enhancing operation of fish jar internal image;
Color space conversion module 12 is used for the image rgb color space is transformed into yuv space;
Corpusculum fish identification module 13, be used for according to selected fish jar corpusculum fish, obtain this fish image at (Cr, Cb) spatial distributions model, calculate light emitting source and whether drop on the fish image at (Cr, Cb) in the spatial distributions model, be used as judging the foundation of fish, computing formula is formula (1):
Cr in the formula (1), Cb is the sample standard average of corpusculum fish Cr, Cb in the fish jar, A, B, C are respectively the coefficients that is come out by sample standard deviation and mean value computation;
Area size computing module 14, be used for result of calculation by the color space conversion module, set up a matrix M with the identical size of fish jar internal image pixel, in this matrix M, drop on the fish image at (Cr by what confirm, Cb) pixel of light emitting source is set at 1 in the spatial distributions model, all the other are set at 0, and pixel is that 1 number obtains the fish bulk area among the statistical matrix M;
Water quality judge module 15 is used for comparing with existing standard mean value, minimum value according to the big or small counting statistics value of the above-mentioned area that obtains:
More than or equal to standard means, be judged as water quality safety as this statistical value;
Less than standard means, and greater than minimum value, alerting is observed as this statistical value;
Less than minimum value, judge that water quality is unusual as this statistical value, send alarm signal.
Described water quality judge module comprises: water quality abnormality degree computing unit 16, be used for after judging that water quality is unusual, above-mentioned area size counting statistics value and existing minimum value being compared, and calculating formula is (2):
In the formula (3), Water quality
AbnormalBe abnormality degree quantification value;
Abnormality degree output unit 17 is used for comparing according to above-mentioned abnormality degree quantification value and preset threshold value, exports the abnormality degree report of different brackets respectively.
Described water monitoring device also comprises and extraneous communication module of communicating by letter, described microprocessor also comprises: water quality exception reporting module, be used for after judging that water quality is unusual, the ground domain information and the liaison method that obtain waters to be monitored from database send to managerial personnel by communication module.On the described loam cake fixed mount 4 illuminating lamp 20 is installed, described illuminating lamp 20 is positioned at the top of vision sensor 2; Described microprocessor 3 also comprises brightness judge module 21, is used for the luminance component according to the Y of yuv space, if, connect illuminating lamp when the value of Y during less than thresholding Ymin, when the value of Y surpass thresholding Ymin 20% the time, turn-off illuminating lamp.Described microprocessor 3, data-carrier store 22 are installed on the loam cake fixed mount 4, and described transparent bottom center of looking around frame 5 is installed buoyancy adjustment cylinder 23, and the bottom of described fish jar is an infundibulate, and described fish jar bottom connects center of gravity hammer 24.Described vision sensor 2 is the omni-directional visual camera.
Just be in the top of the fish jar cylinder body that is holding the corpusculum fish according to above-mentioned formation machine vision unit camera 2, monitoring the ecological situation of corpusculum fish in the cylinder body, for the ecological situation with corpusculum fish in the fish jar 1 makes a distinction, the designed fish jar shape of block of the present invention just as the Y word of a hollow along the center line formed shape that rotates a circle, look like a wineglass from outward appearance, as shown in Figure 1.Because the fish during the shape and structure of above-mentioned fish jar can will move about, be at death's door and dead fish automatic distinguishing comes, fish of being at death's door and dead fish all will concentrate on the top or the bottom of fish jar, and see that from the depression angle of fish jar the fish of being at death's door and dead fish all will concentrate in the middle circle of bottom or float near the cylindrical of bottom, make it not in the machine vision scope, and the good fish of ecological situation will in the big round body type in fish jar middle part, move about (guarantee its can in the machine vision scope), camera 1 sends the image that monitors to microprocessor 3 by USB interface, and at this moment the image that is read in microprocessor 3 as shown in Figure 2; Can carry out following identification statistical treatment in the microprocessor 3 with that, in these are handled, mainly constitute by institutes such as image pretreatment module 10, color space conversion module 12, brightness judgement and electricity-saving lamp switch module 21, corpusculum fish identification module 13, area size computing module 14, water quality situation judge module 15, water quality abnormality degree computing unit 16, abnormality degree output unit 17 and water quality exception reporting modules 19;
Described image pretreatment module 10 is mainly finished the filtering and eliminating noise that carries out the fish jar internal image in rgb color space, image sharpening, work such as contrast enhancing;
Described color space conversion module 12 is mainly finished the conversion of fish jar internal image rgb color space to yuv space, does homework for the shoal of fish area in the fish jar calculates;
The YUV color model is a kind of color model commonly used, its essential characteristic is that luminance signal is separated with color signal, Y represents brightness, and U, V are two chrominance components, the expression aberration, generally be blue, red relative value is because human eye is to the variation comparison change in color sensitivity of brightness, therefore, the shared bandwidth of the value of Y component provides more than or equal to linear dependence between shared bandwidth YUV of chrominance component and the RGB model such as formula (3) in the YUV model
Y＝0.301*R+0.586*G+0.113*B
U＝-0.301*R-0.586*G+0.887*B (3)
V＝0.699*R-0.586*G-0.113*B
Shoal of fish area account form in the described fish jar is discerned and is added up by color characteristic, in order to avoid the number of the fish in moving about such as is added up at the complicated calculations problem among the present invention, in the structural design of fish jar, got rid of simultaneously being at death's door or the statistics of dead fish, therefore hold the color characteristic of the fish in the moving about in the fish jar, the area statistics value of calculating the fish in moving about just can obtain the composite water quality situation in this supervision waters.Outdoor intensity of illumination can since sunlit variation and from weak to strong again by by force to a little less than, and these variations mainly change on the Y component, and the variation on U and the V component is little, the present invention has utilized the brightness independence of this supervision background to carry out pattern-recognition;
In the corpusculum fish identification module, according to corpusculum fish in the selected fish jar, obtain this fish image at (Cr, Cb) spatial distributions model, calculate light emitting source and whether drop on the fish image in that (Cr Cb) in the spatial distributions model, is used as judging the foundation of fish, computing formula is provided by formula (1)
Cr in the formula (1), Cb is corpusculum fish Cr in the fish jar, the sample standard average of Cb, A, B, C is respectively the coefficient that is come out by sample standard deviation and mean value computation, corpusculum fish Cr in the fish jar, the sample standard average of Cb can mode by experiment obtain, in case obtained just can not changing arbitrarily after this sample standard average the classification of corpusculum fish in the fish jar, if the words of changing, just must change corpusculum fish Cr the fish jar of back from newly being provided with, the sample standard average of Cb, the corpusculum fish will be chosen in the individuality that aspects such as color and physical size are close as far as possible in addition.
Described brightness judgement and electricity-saving lamp switch module 21, it is the luminance component that obtains Y according to fish jar internal image rgb color space to the result of the conversion of yuv space, if when the value of Y during less than thresholding Ymin, system turns on the electricity-saving lamp above the camera automatically, the brightness of electricity-saving lamp is as long as can surpass about 10% of thresholding Ymin, when the value of Y surpass thresholding Ymin 20% the time, system's automatic cutout is to the power supply of electricity-saving lamp.
Described area size computing module 14, by above-mentioned result of calculation, set up a matrix M with the identical size of fish jar internal image pixel, in this matrix M, drop on the fish image at (Cr by what confirm, Cb) pixel of light emitting source is set at 1 in the spatial distributions model, all the other are set at 0, and pixel is 1 number among we the statistical matrix M then, just obtains how many integrated informations of fish that can reflect in moving about in the fish jar;
Described water quality situation judge module 15, judge according to above-mentioned area size counting statistics value, this statistical value greater than, equal standard means and just think that present water quality is safe, system will point out the supvr to note often observing during less than standard means and greater than minimum value, during less than minimum value (safe-guard line), and the situation of ordering as T1 among Fig. 3, system is divided into several processing grades, at first adopt among the present invention and calculate abnormality degree, computing formula is provided by formula (2)
In one embodiment of the invention the abnormality degree that sets in advance is divided into 7 grades, (10 ,-20 ,-30 ,-40 ,-50 ,-60), Water quality less than-70
Abnormal＜=-70 o'clock be severely subnormal ,-70＜=Water quality
Abnormal＞-60 o'clock be than severely subnormal ,-60＜=Water quality
Abnormal＞-50 o'clock for have unusual and have severely subnormal trend ,-50＜=Water quality
Abnormal＞-40 o'clock be unusual ,-40＜=Water quality
Abnormal＞-30 o'clock be moderate unusual ,-20＜=Water quality
Abnormal＞-30 o'clock for have the part abnormal occurrence ,-10＜=Water quality
Abnormal＞-20 o'clock for having abnormal occurrence, 0＜=Water quality slightly
Abnormal＞-10 o'clock for there being the mile abnormality phenomenon classification such as will note.Above-mentioned data are default initial values, move an end after the time in system, the user can revise or adjust the size of these numerical value according to statistics, so that more can reflect kind individual difference and because the deviation that season and water temperature variation produce of corpusculum fish.
Described water quality exception reporting module 19, be unusual judged result of judging according to above-mentioned water quality situation and ground domain information and the liaison side's information that from master database 18, obtains local waters, to send to liaison side after these information combination processing, also can release by video server in the embedded system:
Include ground domain information and liaison side's information in local waters in the master database 18, these information are input in the master database 18 by man-machine interaction mode and go.
The biological corpusculum fish of using among the embodiment 1 also can be with obvious color characteristic being arranged in other water such as spiral shell, the relatively more responsive biology of water pollution being substituted.
Described microprocessor 15 adopts flush bonding processor, adopt the EmbeddedLinux+Embedded linux software platform of combination like this among the present invention, adopted ARM9 processor S3C2410X plank in the experiment based on Samsung, integrated the free Embedded A rm-Linux operating system that MIZI company is announced on this plank, the present invention has been transplanted to Wonka (Embedded JVM) in the embedded Linux, Wonka itself had to serial ports, input equipment etc. drive to support.Selection Java or C language are used as the software development language based on the biological formula water-quality monitoring method and apparatus of machine vision, as java applet being operated in the support that needs embedded Java virtual machine (Embedded JVM) on the embedded Linux, used the free Java Virtual Machine of oneself transplanting successfully among the present invention.
The invention effect that the above embodiments 1 and embodiment 2 are produced is to make that by the biological water monitoring device based on machine vision the scope of water-quality monitoring of rivers and lakes and system water industry is broader, move more convenient, information more promptly and accurately, provide one fast, reliably, the means of economic timely grasp water quality safety, obtain the ecological visual information of the corpusculum fish that monitor the waters by machine vision, ecological situation according to viewed corpusculum fish is calculated, obtain monitoring the water quality overall target in the waters, thereby reach comprehensive supervision water quality safety, hold the pollution condition in waters.
Claims (8)
1, a kind of biological water monitoring device based on machine vision is characterized in that: described water monitoring device comprises fish jar, the vision sensor that be used to detect fish jar in corpusculum fish and the microprocessor of sinking in the monitoring waters;
Described fish jar is a wine cup shape, and the top of described fish jar comprises loam cake fixed mount, the transparent frame of looking around, and the middle part of described fish jar is a cylindrical mesh, and described fish jar bottom is dead fish collecting region; Described loam cake fixed mount is fixedlyed connected with the upper end of cylindrical mesh, fixedlys connected with the fish jar bottom in the lower end of described cylindrical mesh; The described transparent frame of looking around is positioned at fish jar, describedly transparently looks around the below that frame is installed in the loam cake fixed mount, and describedly transparently looks around frame and the loam cake fixed mount is tightly connected; The described transparent frame of looking around is following spill, fish collecting region for being at death's door between the described transparent top of looking around frame and cylindrical mesh, the surface level in described waters to be monitored is positioned at the fish collecting region of being at death's door, and the middle and lower part of described cylindrical mesh is corpusculum fish behaviour area; Described vision sensor is installed in the central authorities of loam cake fixed mount, and the monitoring range of described vision sensor is the middle and lower part of described cylindrical mesh;
Described microprocessor comprises:
The view data read module is used to read the video image information of coming from the vision sensor biography;
The data file memory module, the video image information that is used for reading is kept at data-carrier store by file mode;
The image pretreatment module is used for carrying out at rgb color space filtering and eliminating noise, image sharpening, the contrast enhancing operation of fish jar internal image;
The color space conversion module is used for the image rgb color space is transformed into yuv space;
Corpusculum fish identification module, be used for according to selected fish jar corpusculum fish, obtain this fish image at (Cr, Cb) spatial distributions model, calculate light emitting source and whether drop on the fish image at (Cr, Cb) in the spatial distributions model, be used as judging the foundation of fish, computing formula is formula (1):
Cr in the formula (1), Cb is the sample standard average of corpusculum fish Cr, Cb in the fish jar, A, B, C are respectively the coefficients that is come out by sample standard deviation and mean value computation;
Area size computing module, be used for result of calculation by the color space conversion module, set up a matrix M with the identical size of fish jar internal image pixel, in this matrix M, drop on the fish image at (Cr by what confirm, Cb) pixel of light emitting source is set at 1 in the spatial distributions model, all the other are set at 0, and pixel is that 1 number obtains the fish bulk area among the statistical matrix M;
The water quality judge module is used for comparing with existing standard mean value, minimum value according to the big or small counting statistics value of the above-mentioned area that obtains:
More than or equal to standard means, be judged as water quality safety as this statistical value;
Less than standard means, and greater than minimum value, alerting is observed as this statistical value;
Less than minimum value, judge that water quality is unusual as this statistical value, send alarm signal.
2, the biological water monitoring device based on machine vision as claimed in claim 1 is characterized in that: described water quality judge module comprises:
Water quality abnormality degree computing unit is used for after judging that water quality is unusual above-mentioned area size counting statistics value and existing minimum value being compared, and calculating formula is (2):
In the formula (3), Water quality
AbnormalBe abnormality degree quantification value;
The abnormality degree output unit is used for comparing according to above-mentioned abnormality degree quantification value and preset threshold value, exports the abnormality degree report of different brackets respectively.
3, the biological water monitoring device based on machine vision as claimed in claim 2 is characterized in that: preset threshold value is 7 grades in the described abnormality degree output unit, comprises-10 ,-20 ,-30 ,-40 ,-50 ,-60, and less than-70, abnormality degree comprises:
Water quality
Abnormal, be severely subnormal at＜-70 o'clock;
-70≤Water quality
Abnormal＜-60 o'clock, for than severely subnormal;
-60≤Water quality
Abnormal＜-50 o'clock, for having unusual and having severely subnormal trend;-50≤Water quality
Abnormal＜-40 o'clock, for unusually;
-40≤Water quality
Abnormal＜-30 o'clock, for moderate unusual;
-20≤Water quality
Abnormal＜-30 o'clock, for the part abnormal occurrence is arranged;
-20≤Water quality
Abnormal＜-10 o'clock, for abnormal occurrence is arranged slightly;
-10≤Water quality
Abnormal＜0 o'clock,, the mile abnormality phenomenon to note for being arranged.
3, as the described biological water monitoring device of one of claim 1-3 based on machine vision, it is characterized in that: described water monitoring device also comprises and extraneous communication module of communicating by letter, described microprocessor also comprises: water quality exception reporting module, be used for after judging that water quality is unusual, the ground domain information and the liaison method that obtain waters to be monitored from database send to managerial personnel by communication module.
4, as the described biological water monitoring device of one of claim 1-3, it is characterized in that based on machine vision: described color space conversion module, the relational expression that is transformed into yuv space from rgb color space is formula (3):
Y＝0.301*R+0.586*G+0.113*B
U＝-0.301*R-0.586*G+0.887*B (3)
V＝0.699*R-0.586*G-0.113*B
In the following formula, Y represents the brightness of YUV color model, and U, V are two chrominance components of YUV color model, the expression aberration; R represents the redness of rgb color space; G represents the green of rgb color space; B represents the blueness of rgb color space.
5, as the described biological water monitoring device based on machine vision of one of claim 1-3, it is characterized in that: on the described loam cake fixed mount illuminating lamp is installed, described illuminating lamp is positioned at the top of vision sensor; Described microprocessor also comprises the brightness judge module, is used for the luminance component according to the Y of yuv space, if, connect illuminating lamp when the value of Y during less than thresholding Ymin, when the value of Y surpass thresholding Ymin 20% the time, turn-off illuminating lamp.
6, the biological water monitoring device based on machine vision as claimed in claim 5, it is characterized in that: described microprocessor, data-carrier store are installed on the loam cake fixed mount, described transparent bottom center of looking around frame is installed the buoyancy adjustment cylinder, the bottom of described fish jar is an infundibulate, and described fish jar bottom connects the center of gravity hammer.
7, as the described biological water monitoring device based on machine vision of one of claim 1-3, it is characterized in that: described vision sensor is the omni-directional visual camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2005100623056A CN1793913B (en) | 2005-12-28 | 2005-12-28 | Biological water monitoring device based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2005100623056A CN1793913B (en) | 2005-12-28 | 2005-12-28 | Biological water monitoring device based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1793913A true CN1793913A (en) | 2006-06-28 |
| CN1793913B CN1793913B (en) | 2010-09-15 |
Family
ID=36805480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2005100623056A Expired - Fee Related CN1793913B (en) | 2005-12-28 | 2005-12-28 | Biological water monitoring device based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1793913B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170682B (en) * | 2007-11-12 | 2010-09-01 | 中国水产科学研究院黄海水产研究所 | Remote monitoring system for deep water mesh box |
| CN102012419A (en) * | 2010-11-03 | 2011-04-13 | 浙江工业大学 | Biologic water quality monitoring system for perceiving fish behaviors based on vision |
| CN102175825A (en) * | 2010-12-24 | 2011-09-07 | 烟台凯思环境技术有限公司 | Biological monitoring system and method for monitoring sudden change of high-turbidity and low-temperature water quality |
| CN102565295A (en) * | 2010-11-02 | 2012-07-11 | 环境电子株式会社 | An automatic water quality-monitoring device and a low-concentration toxic material detecting method using same |
| CN102749100A (en) * | 2012-06-27 | 2012-10-24 | 烟台凯思环境技术有限公司 | Biological behavior sensor and monitoring method based on quadrupole impedance and three-dimensional tracing |
| CN103150576A (en) * | 2013-03-19 | 2013-06-12 | 上海理工大学 | Monitoring method of cyanobacterial bloom condition |
| CN103743366A (en) * | 2014-01-02 | 2014-04-23 | 浙江海洋学院 | Fish body dimension measuring system |
| CN103926386A (en) * | 2014-04-23 | 2014-07-16 | 北京师范大学 | Field device for biologically monitoring water quality online |
| CN104807970A (en) * | 2015-04-30 | 2015-07-29 | 青岛中仁药业有限公司 | Portable device for biologically detecting toxicity of grains, fruits, vegetables and water |
| CN105724324A (en) * | 2016-04-13 | 2016-07-06 | 朱德进 | Intelligent fishing device |
| CN106338590A (en) * | 2016-09-22 | 2017-01-18 | 首都师范大学 | Water quality monitoring method based on computer vision monitoring of vital signs of fins |
| CN106442908A (en) * | 2016-09-09 | 2017-02-22 | 厦门大学 | Water quality abnormity detection and grading alarm method based on red zebra fish stress behaviors |
| CN106526112A (en) * | 2016-10-25 | 2017-03-22 | 浙江工业大学 | Water toxicity detection method based on fish activity analysis |
| CN106769893A (en) * | 2016-11-22 | 2017-05-31 | 西安建筑科技大学 | A kind of characterizing method of the sludge microbe COMMUNITY CHARACTERISTICS based on color space |
| CN106841199A (en) * | 2017-01-22 | 2017-06-13 | 西安建筑科技大学 | It is a kind of to judge the method whether anaerobic ammonia oxidation process sludge system is subject to impact |
| CN107514626A (en) * | 2017-09-01 | 2017-12-26 | 浙江大唐国际绍兴江滨热电有限责任公司 | A kind of boiler determines blowoff basin draining recovery method and device |
| CN107817323A (en) * | 2016-09-14 | 2018-03-20 | 环境电子株式会社 | Water quality automatic monitoring device |
| CN108008104A (en) * | 2017-12-04 | 2018-05-08 | 湖南理工学院 | A kind of water monitoring device and method |
| CN108051560A (en) * | 2017-12-29 | 2018-05-18 | 成都智泉世纪科技有限公司 | A kind of pure water water quality remote monitoring system and its monitoring method |
| CN108490933A (en) * | 2018-03-13 | 2018-09-04 | 苏州诚满信息技术有限公司 | A kind of intelligent fishing platform and its working method based on environment measuring |
| WO2018166083A1 (en) * | 2017-03-13 | 2018-09-20 | 深圳市嘉和顺信息科技有限公司 | Application of contrast enhancement and visual saliency optimization method in golf course image |
| CN110399774A (en) * | 2019-04-18 | 2019-11-01 | 绿桥(泰州)生态修复有限公司 | Fishery monitoring administration system |
| CN110456722A (en) * | 2019-08-14 | 2019-11-15 | 安徽中青检验检测有限公司 | A kind of lake water monitoring water quality and forecasting system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09127099A (en) * | 1995-11-06 | 1997-05-16 | Anima Denshi Kk | Water-quality monitoring apparatus |
| US20040147030A1 (en) * | 2000-05-22 | 2004-07-29 | Nebert Daniel W | Transgenic animals for monitoring water quality |
| CN1177209C (en) * | 2000-05-30 | 2004-11-24 | 李敬生 | Method and equipment for diagnosing and restoring physiological safety of water |
-
2005
- 2005-12-28 CN CN2005100623056A patent/CN1793913B/en not_active Expired - Fee Related
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170682B (en) * | 2007-11-12 | 2010-09-01 | 中国水产科学研究院黄海水产研究所 | Remote monitoring system for deep water mesh box |
| CN102565295A (en) * | 2010-11-02 | 2012-07-11 | 环境电子株式会社 | An automatic water quality-monitoring device and a low-concentration toxic material detecting method using same |
| CN102565295B (en) * | 2010-11-02 | 2015-09-16 | 环境电子株式会社 | Water quality automatic monitoring device and the low concentration noxious material detection method about water quality automatic monitoring device |
| CN102012419B (en) * | 2010-11-03 | 2013-07-24 | 浙江工业大学 | Biologic water quality monitoring system for perceiving fish behaviors based on vision |
| CN102012419A (en) * | 2010-11-03 | 2011-04-13 | 浙江工业大学 | Biologic water quality monitoring system for perceiving fish behaviors based on vision |
| CN102175825A (en) * | 2010-12-24 | 2011-09-07 | 烟台凯思环境技术有限公司 | Biological monitoring system and method for monitoring sudden change of high-turbidity and low-temperature water quality |
| CN102749100A (en) * | 2012-06-27 | 2012-10-24 | 烟台凯思环境技术有限公司 | Biological behavior sensor and monitoring method based on quadrupole impedance and three-dimensional tracing |
| CN103150576A (en) * | 2013-03-19 | 2013-06-12 | 上海理工大学 | Monitoring method of cyanobacterial bloom condition |
| CN103743366A (en) * | 2014-01-02 | 2014-04-23 | 浙江海洋学院 | Fish body dimension measuring system |
| CN103743366B (en) * | 2014-01-02 | 2016-06-01 | 浙江海洋学院 | Fish body Size Measuring System |
| CN103926386A (en) * | 2014-04-23 | 2014-07-16 | 北京师范大学 | Field device for biologically monitoring water quality online |
| CN104807970A (en) * | 2015-04-30 | 2015-07-29 | 青岛中仁药业有限公司 | Portable device for biologically detecting toxicity of grains, fruits, vegetables and water |
| CN105724324A (en) * | 2016-04-13 | 2016-07-06 | 朱德进 | Intelligent fishing device |
| CN106442908A (en) * | 2016-09-09 | 2017-02-22 | 厦门大学 | Water quality abnormity detection and grading alarm method based on red zebra fish stress behaviors |
| CN106442908B (en) * | 2016-09-09 | 2019-02-26 | 厦门大学 | Based on Red zebra fish stress behavior water quality abnormality detection and classifying alarm method |
| CN107817323A (en) * | 2016-09-14 | 2018-03-20 | 环境电子株式会社 | Water quality automatic monitoring device |
| CN107817323B (en) * | 2016-09-14 | 2020-07-03 | 环境电子株式会社 | Automatic water quality monitoring device |
| CN106338590A (en) * | 2016-09-22 | 2017-01-18 | 首都师范大学 | Water quality monitoring method based on computer vision monitoring of vital signs of fins |
| CN106526112A (en) * | 2016-10-25 | 2017-03-22 | 浙江工业大学 | Water toxicity detection method based on fish activity analysis |
| CN106769893A (en) * | 2016-11-22 | 2017-05-31 | 西安建筑科技大学 | A kind of characterizing method of the sludge microbe COMMUNITY CHARACTERISTICS based on color space |
| CN106769893B (en) * | 2016-11-22 | 2019-04-05 | 西安建筑科技大学 | A kind of characterizing method of the sludge microbe COMMUNITY CHARACTERISTICS based on color space |
| CN106841199A (en) * | 2017-01-22 | 2017-06-13 | 西安建筑科技大学 | It is a kind of to judge the method whether anaerobic ammonia oxidation process sludge system is subject to impact |
| CN106841199B (en) * | 2017-01-22 | 2019-04-16 | 西安建筑科技大学 | A method of determining whether anaerobic ammonia oxidation process sludge system is impacted |
| WO2018166083A1 (en) * | 2017-03-13 | 2018-09-20 | 深圳市嘉和顺信息科技有限公司 | Application of contrast enhancement and visual saliency optimization method in golf course image |
| CN107514626A (en) * | 2017-09-01 | 2017-12-26 | 浙江大唐国际绍兴江滨热电有限责任公司 | A kind of boiler determines blowoff basin draining recovery method and device |
| CN108008104A (en) * | 2017-12-04 | 2018-05-08 | 湖南理工学院 | A kind of water monitoring device and method |
| CN108051560A (en) * | 2017-12-29 | 2018-05-18 | 成都智泉世纪科技有限公司 | A kind of pure water water quality remote monitoring system and its monitoring method |
| CN108490933A (en) * | 2018-03-13 | 2018-09-04 | 苏州诚满信息技术有限公司 | A kind of intelligent fishing platform and its working method based on environment measuring |
| CN110399774A (en) * | 2019-04-18 | 2019-11-01 | 绿桥(泰州)生态修复有限公司 | Fishery monitoring administration system |
| CN110456722A (en) * | 2019-08-14 | 2019-11-15 | 安徽中青检验检测有限公司 | A kind of lake water monitoring water quality and forecasting system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1793913B (en) | 2010-09-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1793913B (en) | Biological water monitoring device based on machine vision | |
| Skordas et al. | Assessment of nutrients and heavy metals in the surface sediments of the artificially lake water reservoir Karla, Thessaly, Greece | |
| CN106501195B (en) | Methods of Assessment for Water Entrophication based on Suspended Particles in Water absorption coefficient | |
| Shih et al. | The impact of eddies on nutrient supply, diatom biomass and carbon export in the Northern South China Sea | |
| Li et al. | Derivation of water quality criteria of zinc to protect aquatic life in Taihu Lake and the associated risk assessment | |
| Prato et al. | Ecotoxicological evaluation of sediments by battery bioassays: application and comparison of two integrated classification systems | |
| Zhang et al. | Initial ecological restoration assessment of an urban river in the subtropical region in China | |
| Sarker et al. | Assessment of coastal water pollution in Greater Noakhali-Bangladesh | |
| Howell | Influences on water quality and abundance of cladophora, a shore-fouling green algae, over urban shoreline in Lake Ontario | |
| Werme et al. | Outfall monitoring overview | |
| Teame et al. | Seasonal variation in physico-chemical parameters of tekeze reservoir, northern Ethiopia | |
| Ghervase et al. | Evaluation of lentic ecosystems from Bucharest City | |
| Zhao et al. | Effects and prediction of nonpoint source pollution on the structure of aquatic food webs | |
| CN112986512B (en) | Method for testing ecological toxicity of solid waste leachate based on acute toxicity test of zebra fish | |
| Shumchenia et al. | A re-assessment of Narragansett Bay benthic habitat quality between 1988 and 2008 | |
| Schintu et al. | Monitoring of trace metals in coastal sediments from sites around Sardinia, Western Mediterranean | |
| CN112269001A (en) | Lake ecological health convenient monitoring system and method based on phytoplankton community | |
| Mahmood et al. | GIS ASSESSMENT FOR GROUNDWATER QUALITY OF DISTRICT MULTAN, PAKISTAN | |
| Ni et al. | Structural characteristics of zooplankton communities in Hongze Lake driven by water environmental factors from 2016 to 2020 | |
| Alexandrov et al. | Eutrophication of Lake Tasaul, Romania—proposals for rehabilitation | |
| Tibebe et al. | Analysis of internal nutrient load dynamics from the sediment in Lake Ziway | |
| Liu et al. | Seasonal shift in zooplankton communities in two sub-tropical urban wetlands, Southern China | |
| Dagne et al. | Plankton Based Trophic Status of Lakes Abaya and Chamo | |
| Chakraborty et al. | Interrelationship between limnological parameters of a floodplain lake in Dwarkeshwar river basin and their impact on fish biodiversity | |
| Wu et al. | Optical properties as indicators of in-lake dissolved organic matter components, sources and transformation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100915 Termination date: 20121228 |