CN104749334A - Mode-recognition-based design method for biological abnormal water quality evaluation system - Google Patents
Mode-recognition-based design method for biological abnormal water quality evaluation system Download PDFInfo
- Publication number
- CN104749334A CN104749334A CN201510086346.2A CN201510086346A CN104749334A CN 104749334 A CN104749334 A CN 104749334A CN 201510086346 A CN201510086346 A CN 201510086346A CN 104749334 A CN104749334 A CN 104749334A
- Authority
- CN
- China
- Prior art keywords
- water quality
- evaluation
- fish
- model
- quality assessment
- 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
Abstract
The invention discloses a mode-recognition-based design method for a biological abnormal water quality evaluation system. The basic idea is that: aiming at the characteristics of multiple factors, high dimension, nonlinearity and the like showed in water quality evaluation, and the problem of a complicated relationship between an evaluation factor and water quality, with a common biological indicator fish in biological abnormal water quality evaluation as a research object, a rapid abnormal water quality evaluation system is provided by adopting a computer image processing technique. The method comprises the following steps: firstly, collecting a fish movement video image capable of reflecting the water quality condition on the basis of computer vision; obtaining water quality evaluation indexes, namely fish behavior characteristic parameters by adopting an image processing technique; simultaneously building a semantic mapping model capable of reflecting the water quality condition and the fish behavior characteristic parameters on the basis of mode recognition; and finally investigating the feasibility of the model. The effects caused by environment illumination change and noise change can be overcome when the fish movement information is extracted; a water quality abnormality evaluation model is constructed by adopting a support vector machine (SVM); and the robustness of the model is updated and improved in real time.
Description
Technical field
The present invention relates to computer vision and area of pattern recognition, especially a kind of biological formula quality evaluation method successfully overcoming multiple-factor that traditional water quality assessment shows, higher-dimension, the shortcoming such as non-linear and the complex relationship between evaluation points and water quality.
Technical background
Water is lifespring, is the important natural resources that we depend on for existence, is the important substance basis of society and economic development.But along with urbanization and industrialized develop rapidly, countries in the world are faced with shortage of water resources, with serious pollution challenge substantially.Therefore, water quality assessment has great importance and acts in water resources management, protection and planning, but how accurate, objective, scientifically carry out evaluation to water quality and be still a difficult problem.At present, most scholar is that the Water Quality Evaluation pollution factor (evaluation index) gathered based on physico-chemical analysis technology and Automatic Measurement Technique carries out detection analysis to water quality, and then obtains water quality condition.But when detecting water quality like this, first evaluating data has the shortcomings such as multiple-factor, non-linear, higher-dimension, to such an extent as to be difficult to set up the model identified water quality fast; Secondly evaluation method is not there is larger subjectivity, profoundly can not reflect water quality condition exactly comprehensively.In recent years, Measurement for Biotechnique, owing to having comprehensive, the advantage such as enriching, continuity, reaction sensitivity are high, intuitive, attract attention in water quality assessment.In biological formula water quality assessment, fish are convenient to owing to having advantages such as identifying, motion feature is obvious, by as important indicator organism.The water ecological environment of fish and its existence constitutes an interactional integrated system, both interdependences, coevolution.The unitarity of water environment and fish and coevolution are the bases of carrying out water quality assessment, and fish are then the foundations of carrying out water quality assessment to various ecological responses during hydro-environmental change simultaneously.Therefore adopt Fish behavior feature as evaluation index, not only can relate to less index but also the potential impact of water quality composite pollution can be reacted.
Computer vision mainly simulates the visual performance of people with computing machine, information extraction from the image of objective things, carries out process being understood, finally for the detection of reality, measurement and control.Therefore, many scholars are successfully extracted fish locomotion characteristic parameter based on computer vision technique both at home and abroad.But only have minority scholar to establish Water Quality Assessment Model based on these parameters, annotated the qualitative relationships of water ecological environment and fish.The people such as Cigdem propose a kind of rule-based trace filtering mechanism, the track monitored utilizing computer vision technique filters, successfully extract the abnormal track of fish, the method is expected to the understanding being applied to Fish behavior and water quality relation, especially normal and exception water quality detection field.The people such as Carlos are by definition fish locomotion behavior state, background subtraction technology is utilized to obtain fish at the difference polluted and in uncontamined water, then recurrence plot algorithm is adopted to draw track, define the descriptor based on recurrence plot, obtain a binary recursive vector matrix along with passage of time, successfully judged according to the difference of matrix the exception water quality adding chlopyrifos pesticides.The people such as Liao adopt support vector machine (SVM) learn the behavior of zebra fish under different Cu ion concentration and test, and have studied the measuring accuracy under different IPs type function, and research shows that the method effectively can carry out water quality anomaly evaluation.Although Carlos with Liao passes through to extract the parameter evaluation water quality condition about fish track, all do not provide concrete water quality assessment system flow.The people such as Cheng Shuhong establish the water quality abnormality detection model based on computer vision and SVM, experimental result shows that this model fast and effeciently can carry out water quality abnormality detection, but there is no the robustness of verification model, especially to the anti-interference that illumination or external extraneous events are disturbed, and only give the scheme of Modling model, do not provide complete water quality anomaly evaluation system equally.
In sum, biological formula water quality assessment has vital effect at water quality safety detection field, provides theoretical foundation for detecting that water quality is abnormal accurately and timely.But the robustness how designing perfect exception water quality evaluation system and the system of investigation is emphasis of the present invention.
Summary of the invention
The object of the invention is (1) and design complete exception water quality evaluation system; (2) robustness of system is improved, especially for the impact that ambient lighting change and noise change; (3) feasibility of verification system.
Basic thought of the present invention is: the multiple-factor shown for water quality assessment, higher-dimension, the feature such as non-linear, and the problem of complex relationship between evaluation points and water quality, the present invention for research object, uses computer image processing technology to propose one exception water quality evaluation system fast with bionidicator fish common in biological formula water quality assessment.First the fish locomotion video image of water quality condition can be reflected based on computer vision collection, then image processing techniques is utilized to obtain water quality assessment index and Fish behavior characteristic parameter, set up the Semantic mapping model that can reflect water quality condition and Fish behavior characteristic parameter simultaneously based on pattern-recognition, finally investigate the feasibility of model.
For the technical matters solving above-mentioned existence realizes above-mentioned purpose, the present invention is achieved by the following technical solutions:
Based on a biological formula exception water quality evaluation system method for designing for pattern-recognition, its content comprises the steps:
(1) water quality assessment platform is built
Build water quality assessment platform, utilize computer vision technique that live body fish movement is converted into vedio data;
(2) Image semantic classification
Adopting image processing techniques to carry out pre-service to the image obtained, first bilateral filtering process is carried out to video frame images, remaining marginal information again while denoising, then dct transform being carried out to eliminate the impact of illumination to filtered image;
(3) detection and tracking of fish movement target
Due to Kalman filtering, to have track algorithm calculated amount less and can realize the advantage of real-time follow-up, therefore adopt it to follow the tracks of fish, obtains the movement locus of fish;
(4) water quality assessment index is extracted
The movement locus obtaining fish by following the tracks of institute obtain water quality assessment index and swimming rate, travelling apart from, move about acceleration, four, corner direction parameter;
(5) characteristic parameter database is set up
Pre-service is carried out to the kinematic parameter under the normal and exception water quality extracted, rejects gross error, obtain the data after normalization, set up characteristic parameter database;
(6) Water Quality Assessment Model is set up
In order to set up Water Quality Assessment Model fast, first PCA dimension-reduction treatment being carried out to the evaluation index obtained, then adopting support vector machines structure water quality anomaly evaluation model;
(7) feasibility of water quality assessment system is investigated
In order to verify the feasibility of the biological formula exception water quality evaluation system method for designing based on pattern-recognition, when carrying out water quality anomaly evaluation, environment detector is adopted to verify that whether the result of evaluation is correct;
(8) online water quality assessment
Online design exception water quality evaluation system, On-line testing water quality Mesichthyes motor behavior parameter, utilizes Water Quality Assessment Model to carry out water quality anomaly evaluation; Meanwhile, evaluation result regeneration characteristics parameter database and evaluation model is adopted, to improve the robustness of model.
Owing to adopting technique scheme, a kind of biological formula exception water quality evaluation system method for designing based on pattern-recognition provided by the invention compared with prior art has such beneficial effect:
The present invention devises complete exception water quality evaluation system and improves the robustness of system, especially for the impact that ambient lighting change and noise change, has certain theoretical foundation and reference value to online water quality assessment.
The present invention can overcome the impact of ambient lighting change and noise change when extracting fish locomotion information, and adopt Kalman filtering accurate tracking fish locomotion trajectory extraction kinematic parameter structural attitude matrix, utilize support vector machines to construct water quality anomaly evaluation model and real-time update raising model robustness.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the biological formula exception water quality evaluation system method for designing based on pattern-recognition;
Fig. 2 is the water quality assessment platform schematic diagram built;
Fig. 3 is the process flow diagram of Image semantic classification;
Fig. 4 is the result figure after Image semantic classification;
Fig. 5 is the trajectory diagram based on Kalman filtering, fish being carried out to real-time follow-up;
Fig. 6 is Water Quality Assessment Model process flow diagram;
Fig. 7 is online exception water quality evaluation system schematic diagram.
Embodiment
Below in conjunction with accompanying drawing and embodiment, the present invention is described in further detail:
The process flow diagram of a kind of biological formula exception water quality evaluation system method for designing based on pattern-recognition that the present invention proposes as shown in Figure 1, is below divided into several introduction embodiment:
(1) water quality assessment platform is built
Build water quality detection platform, utilize computer vision technique that live body fish movement is converted into vedio data, build result as shown in Figure 2.
(2) Image semantic classification
The process flow diagram of Image semantic classification as shown in Figure 3, wherein pre-service is carried out to original RGB image---after gray processing process as shown in Fig. 4 (a), after bilateral filtering process, the result of stress release treatment is as shown in Fig. 4 (b), and the result after DCT domain strengthens is as shown in Fig. 4 (c).
Known as shown in Figure 4, image pre-processing method bilateral filtering edge while stress release treatment that the present invention proposes is also comparatively clear, and dct transform restrained effectively the impact of photoenvironment.The pre-service of this step can be increased water quality the robustness of evaluation system, especially for the impact that ambient lighting change and noise change.
(3) detection and tracking of fish movement target
Utilize pretreated image in step (2), carry out real-time follow-up based on Kalman filtering to fish, obtain the movement locus of fish, its tracking results as shown in Figure 5.
(4) water quality assessment index is extracted
The movement locus of the fish under utilizing step 3 to follow the tracks of normal water quality and under exception water quality, extracts the kinematic parameter that can reflect water quality condition: swimming rate, travelling distance, travelling acceleration, corner direction.
(5) characteristic parameter database is set up
Kinematic parameter under the normal and exception water quality extract step 4 carries out pre-service, rejects gross error, obtains the data after normalization, set up normal and off-note parameter database respectively.
(6) Water Quality Assessment Model is set up
In order to set up Water Quality Assessment Model fast, first PCA dimension-reduction treatment is carried out to the evaluation index obtained, from the characteristic parameter database that step (5) is set up, selected part data are as the training sample set of support vector machine (SVM), PCA dimension-reduction treatment is carried out to the evaluation index obtained, then adopt support vector machine (SVM) to construct water quality anomaly evaluation model, Water Quality Assessment Model flow process as shown in Figure 6; From the sample characteristics parameter database that step 5 is set up, random selecting part normal sample notebook data and exceptional sample data are as training sample set, in order to set up Water Quality Assessment Model fast and reduce data redudancy, PCA is adopted to carry out dimension-reduction treatment to the sample data chosen, using the input of the data after dimensionality reduction as SVM, and the parameter of SVM is optimized, training obtains water quality anomaly evaluation model.
Table 1 evaluates discrimination (%) based on the exception water quality of the different models of SVM
Table 1 sets up Water Quality Assessment Model based on SVM and to exception water quality test result accuracy rate, wherein model 1,2,3,4 is adopt wall scroll fish 1 respectively, the model that the training sample set of 2,3,4 is set up, model 5 is based on wall scroll fish 1,2,3, the training sample set in 4 combine set up Water Quality Assessment Model.From the data (going out with bold in figure) the diagonal line of table 1, can find out and the result that selftest collection is tested obviously is better than to result that the test set of other 3 fishes is tested with the model that the data of wall scroll fish own are set up, therefore obtain the property of there are differences between fish individual, and the model that wall scroll fish is set up do not have robustness.With the test sample book collection 1 of model 5 pairs of wall scroll fishes, 2,3, though the result that the model that the test result of 4 is set up not as good as wall scroll fish its data is tested selftest collection, but be better than model that wall scroll fish sets up to the test result of the test set of other 3 fishes and test result all higher than 84%, therefore the model adopting the data of many fishes to set up has good robustness.
(7) feasibility of water quality assessment system is investigated
In order to the feasibility of test evaluation systems approach, when carrying out water quality anomaly evaluation, whether we adopt environment detector correct to verify the result of evaluation.
(8) online water quality assessment
As shown in Figure 7, Real-Time Evaluation water quality condition, On-line testing water quality Mesichthyes motor behavior parameter, utilizes Water Quality Assessment Model to carry out water quality anomaly evaluation to online design exception water quality evaluation system.Meanwhile, according to evaluation result regeneration characteristics parameter database and evaluation model, to improve the robustness of model.Utilization assessment result on-line training SVM classifier, namely carry out training every certain video sequence image frame number to SVM to upgrade, by constantly training and online renewal make the continuous adaptive change in time series of water quality assessment system, even if evaluation system still can stably run in the situations such as temperature, illumination, complex background interference.Upgrade Water Quality Assessment Model by Real-Time Evaluation result like this, improve the robustness of evaluation system.
Claims (1)
1., based on a biological formula exception water quality evaluation system method for designing for pattern-recognition, its content comprises the steps:
(1) water quality assessment platform is built
Build water quality assessment platform, utilize computer vision technique that live body fish movement is converted into vedio data;
(2) Image semantic classification
Adopting image processing techniques to carry out pre-service to the image obtained, first bilateral filtering process is carried out to video frame images, remaining marginal information again while denoising, then dct transform being carried out to eliminate the impact of illumination to filtered image;
(3) detection and tracking of fish movement target
Due to Kalman filtering, to have track algorithm calculated amount less and can realize the advantage of real-time follow-up, therefore adopt it to follow the tracks of fish, obtains the movement locus of fish;
(4) water quality assessment index is extracted
The movement locus obtaining fish by following the tracks of institute obtain water quality assessment index and swimming rate, travelling apart from, move about acceleration, four, corner direction parameter;
(5) characteristic parameter database is set up
Pre-service is carried out to the kinematic parameter under the normal and exception water quality extracted, rejects gross error, obtain the data after normalization, set up characteristic parameter database;
(6) Water Quality Assessment Model is set up
In order to set up Water Quality Assessment Model fast, first PCA dimension-reduction treatment being carried out to the evaluation index obtained, then adopting support vector machines structure water quality anomaly evaluation model;
(7) feasibility of water quality assessment system is investigated
In order to verify the feasibility of the biological formula exception water quality evaluation system method for designing based on pattern-recognition, when carrying out water quality anomaly evaluation, environment detector is adopted to verify that whether the result of evaluation is correct;
(8) online water quality assessment
Online design exception water quality evaluation system, On-line testing water quality Mesichthyes motor behavior parameter, utilizes Water Quality Assessment Model to carry out water quality anomaly evaluation; Meanwhile, evaluation result regeneration characteristics parameter database and evaluation model is adopted, to improve the robustness of model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510086346.2A CN104749334A (en) | 2015-02-16 | 2015-02-16 | Mode-recognition-based design method for biological abnormal water quality evaluation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510086346.2A CN104749334A (en) | 2015-02-16 | 2015-02-16 | Mode-recognition-based design method for biological abnormal water quality evaluation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104749334A true CN104749334A (en) | 2015-07-01 |
Family
ID=53589327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510086346.2A Pending CN104749334A (en) | 2015-02-16 | 2015-02-16 | Mode-recognition-based design method for biological abnormal water quality evaluation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104749334A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 quality toxicity detection method based on fish activity analysis |
| CN107087562A (en) * | 2017-06-14 | 2017-08-25 | 上海海洋大学 | The construction method of fish monomer behavior sequence spectrum |
| CN107403188A (en) * | 2017-06-28 | 2017-11-28 | 中国农业大学 | A kind of quality evaluation method and device |
| CN107730495A (en) * | 2017-10-25 | 2018-02-23 | 重庆祺璨科技有限公司 | A kind of fish pond anoxic detection method based on background modeling |
| CN110031597A (en) * | 2019-04-19 | 2019-07-19 | 燕山大学 | A kind of biological water monitoring method |
| CN110702869A (en) * | 2019-11-01 | 2020-01-17 | 无锡中科水质环境技术有限公司 | Fish stress avoidance behavior water quality monitoring method based on video image analysis |
| CN111274775A (en) * | 2020-01-20 | 2020-06-12 | 清华大学 | Watershed water environment model verification system |
| CN111476765A (en) * | 2020-03-30 | 2020-07-31 | 深圳市水务(集团)有限公司 | Water quality judging method and device |
| CN112507869A (en) * | 2020-12-07 | 2021-03-16 | 广州博进信息技术有限公司 | Underwater target behavior observation and water body environment monitoring method based on machine vision |
| CN113607782A (en) * | 2021-07-28 | 2021-11-05 | 浙江工业大学 | Visual perception type water quality early warning system and method enhanced by olfactory signal |
| CN113730983A (en) * | 2021-09-14 | 2021-12-03 | 忻州师范学院 | Water pollution early warning system based on plankton |
| CN113822233A (en) * | 2021-11-22 | 2021-12-21 | 青岛杰瑞工控技术有限公司 | Method and system for tracking abnormal fishes cultured in deep sea |
| CN116660486A (en) * | 2023-05-24 | 2023-08-29 | 重庆交通大学 | Water quality evaluation standard determining method based on large benthonic animal BI index |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1555683A (en) * | 1977-09-23 | 1979-11-14 | Water Res Centre | Continuous monitoring of water quality using fish |
| CH682601A5 (en) * | 1992-10-13 | 1993-10-15 | Gas Wasser Und Fernwaermeverso | Water quality monitoring - uses succession of pictures of fish for comparison with an alarm raised when there is no fish movement |
| US5903305A (en) * | 1996-02-20 | 1999-05-11 | Anima Electronics Co., Ltd. | Apparatus for monitoring water quality using aquatic living thing |
| CN101477630A (en) * | 2009-02-17 | 2009-07-08 | 吴俊� | System and method for intelligent water treatment micro-organism machine vision identification |
| 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 |
| CN102156964A (en) * | 2011-03-31 | 2011-08-17 | 杭州海康威视软件有限公司 | Color image denoising method and system thereof |
| CN102339521A (en) * | 2011-06-14 | 2012-02-01 | 华南理工大学 | Early warning method for burst pollution of source water through aquatic organism behavior image extraction |
| JP2012098150A (en) * | 2010-11-02 | 2012-05-24 | Kankyo Denshi Kk | Automatic water quality monitoring device and method for detecting low-concentration toxicity |
| CN102679957A (en) * | 2012-04-26 | 2012-09-19 | 燕山大学 | Background information and color feature combined fish body detection method |
| CN102866237A (en) * | 2012-09-06 | 2013-01-09 | 华南理工大学 | Water quality safety online biological early warning and monitoring system based on video identification |
-
2015
- 2015-02-16 CN CN201510086346.2A patent/CN104749334A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1555683A (en) * | 1977-09-23 | 1979-11-14 | Water Res Centre | Continuous monitoring of water quality using fish |
| CH682601A5 (en) * | 1992-10-13 | 1993-10-15 | Gas Wasser Und Fernwaermeverso | Water quality monitoring - uses succession of pictures of fish for comparison with an alarm raised when there is no fish movement |
| US5903305A (en) * | 1996-02-20 | 1999-05-11 | Anima Electronics Co., Ltd. | Apparatus for monitoring water quality using aquatic living thing |
| CN101477630A (en) * | 2009-02-17 | 2009-07-08 | 吴俊� | System and method for intelligent water treatment micro-organism machine vision identification |
| JP2012098150A (en) * | 2010-11-02 | 2012-05-24 | Kankyo Denshi Kk | Automatic water quality monitoring device and method for detecting low-concentration toxicity |
| 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 |
| CN102156964A (en) * | 2011-03-31 | 2011-08-17 | 杭州海康威视软件有限公司 | Color image denoising method and system thereof |
| CN102339521A (en) * | 2011-06-14 | 2012-02-01 | 华南理工大学 | Early warning method for burst pollution of source water through aquatic organism behavior image extraction |
| CN102679957A (en) * | 2012-04-26 | 2012-09-19 | 燕山大学 | Background information and color feature combined fish body detection method |
| CN102866237A (en) * | 2012-09-06 | 2013-01-09 | 华南理工大学 | Water quality safety online biological early warning and monitoring system based on video identification |
Non-Patent Citations (2)
| Title |
|---|
| YUE LIAO，ET AL.: "Application of biomonitoring and support vector machine in water quality assessment", 《JOURNAL OF ZHEJIANG UNIVERSITY-SCIENCE B(BIOMEDICINE & BIOTECHNOLOGY)》 * |
| 程淑红 等: "基于计算机视觉与 SVM 的水质异常监测方法", 《光电工程》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 quality toxicity detection method based on fish activity analysis |
| CN107087562A (en) * | 2017-06-14 | 2017-08-25 | 上海海洋大学 | The construction method of fish monomer behavior sequence spectrum |
| CN107403188A (en) * | 2017-06-28 | 2017-11-28 | 中国农业大学 | A kind of quality evaluation method and device |
| CN107730495A (en) * | 2017-10-25 | 2018-02-23 | 重庆祺璨科技有限公司 | A kind of fish pond anoxic detection method based on background modeling |
| CN110031597A (en) * | 2019-04-19 | 2019-07-19 | 燕山大学 | A kind of biological water monitoring method |
| CN110702869A (en) * | 2019-11-01 | 2020-01-17 | 无锡中科水质环境技术有限公司 | Fish stress avoidance behavior water quality monitoring method based on video image analysis |
| CN111274775A (en) * | 2020-01-20 | 2020-06-12 | 清华大学 | Watershed water environment model verification system |
| CN111476765A (en) * | 2020-03-30 | 2020-07-31 | 深圳市水务(集团)有限公司 | Water quality judging method and device |
| CN112507869A (en) * | 2020-12-07 | 2021-03-16 | 广州博进信息技术有限公司 | Underwater target behavior observation and water body environment monitoring method based on machine vision |
| CN112507869B (en) * | 2020-12-07 | 2024-04-09 | 广州博进信息技术有限公司 | Underwater target behavior observation and water environment monitoring method based on machine vision |
| CN113607782A (en) * | 2021-07-28 | 2021-11-05 | 浙江工业大学 | Visual perception type water quality early warning system and method enhanced by olfactory signal |
| CN113730983A (en) * | 2021-09-14 | 2021-12-03 | 忻州师范学院 | Water pollution early warning system based on plankton |
| CN113822233A (en) * | 2021-11-22 | 2021-12-21 | 青岛杰瑞工控技术有限公司 | Method and system for tracking abnormal fishes cultured in deep sea |
| CN116660486A (en) * | 2023-05-24 | 2023-08-29 | 重庆交通大学 | Water quality evaluation standard determining method based on large benthonic animal BI index |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104749334A (en) | Mode-recognition-based design method for biological abnormal water quality evaluation system | |
| Sony et al. | A systematic review of convolutional neural network-based structural condition assessment techniques | |
| Tian et al. | A dual neural network for object detection in UAV images | |
| CN103258213B (en) | A kind of for the dynamic vehicle model recognizing method in intelligent transportation system | |
| CN103632382B (en) | A kind of real-time multiscale target tracking based on compressed sensing | |
| Zhang et al. | Spatiotemporal causal convolutional network for forecasting hourly PM2. 5 concentrations in Beijing, China | |
| CN102663454B (en) | Method and device for evaluating character writing standard degree | |
| CN110738247A (en) | fine-grained image classification method based on selective sparse sampling | |
| CN108986142A (en) | Shelter target tracking based on the optimization of confidence map peak sidelobe ratio | |
| CN106021671B (en) | In conjunction with the circuit health grading evaluation method of correlative relationship and grey cluster technology | |
| Li et al. | IncepTCN: A new deep temporal convolutional network combined with dictionary learning for strong cultural noise elimination of controlled-source electromagnetic data | |
| CN103617413A (en) | Method for identifying object in image | |
| CN114926825A (en) | Vehicle driving behavior detection method based on space-time feature fusion | |
| Li et al. | A grid‐based classification and box‐based detection fusion model for asphalt pavement crack | |
| CN115035334A (en) | Multi-classification change detection method and system for multi-scale fusion double-temporal remote sensing image | |
| Elbaz et al. | Real time image-based air quality forecasts using a 3D-CNN approach with an attention mechanism | |
| Shui et al. | End-to-end cell recognition by point annotation | |
| Zhang et al. | A precise apple leaf diseases detection using BCTNet under unconstrained environments | |
| Yang et al. | Research on coal gangue recognition based on multi-layer time domain feature processing and recognition features cross-optimal fusion | |
| CN105825215A (en) | Instrument positioning method based on local neighbor embedded kernel function and carrier of method | |
| Zhang et al. | Detection of coronal mass ejections using multiple features and space–time continuity | |
| CN112084941A (en) | Target detection and identification method based on remote sensing image | |
| Li et al. | An identification method of dangerous driving behavior in rush hour based on apriori algorithm. | |
| Yi et al. | An efficient method of pavement distress detection based on improved YOLOv7 | |
| Song et al. | Instrument identification technology based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150701 |