CN109448028A - Fish disease caused by virus based on computer vision tests tracking and monitoring system - Google Patents
Fish disease caused by virus based on computer vision tests tracking and monitoring system Download PDFInfo
- Publication number
- CN109448028A CN109448028A CN201811297858.3A CN201811297858A CN109448028A CN 109448028 A CN109448028 A CN 109448028A CN 201811297858 A CN201811297858 A CN 201811297858A CN 109448028 A CN109448028 A CN 109448028A
- Authority
- CN
- China
- Prior art keywords
- fish
- video
- virus
- information
- monitoring
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 36
- 241000700605 Viruses Species 0.000 title claims abstract description 33
- 208000010824 fish disease Diseases 0.000 title claims abstract description 32
- 238000012360 testing method Methods 0.000 title claims abstract description 32
- 241000251468 Actinopterygii Species 0.000 claims abstract description 114
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000001914 filtration Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 239000003550 marker Substances 0.000 claims abstract description 12
- 230000000877 morphologic effect Effects 0.000 claims abstract description 9
- 239000000463 material Substances 0.000 claims abstract description 8
- 238000012806 monitoring device Methods 0.000 claims abstract description 6
- 238000007405 data analysis Methods 0.000 claims abstract description 5
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000003612 virological effect Effects 0.000 claims description 7
- 210000000006 pectoral fin Anatomy 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 6
- 238000009360 aquaculture Methods 0.000 claims description 5
- 244000144974 aquaculture Species 0.000 claims description 5
- 238000002347 injection Methods 0.000 claims description 5
- 239000007924 injection Substances 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 4
- 238000012258 culturing Methods 0.000 claims description 4
- 239000012530 fluid Substances 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims description 3
- 210000004279 orbit Anatomy 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 241000894007 species Species 0.000 claims description 3
- 238000009395 breeding Methods 0.000 claims description 2
- 230000001488 breeding effect Effects 0.000 claims description 2
- 230000014759 maintenance of location Effects 0.000 claims description 2
- 238000012512 characterization method Methods 0.000 abstract description 5
- 230000008901 benefit Effects 0.000 abstract description 2
- 230000006866 deterioration Effects 0.000 abstract description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 2
- 230000002265 prevention Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000000638 solvent extraction Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 210000004690 animal fin Anatomy 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 210000000746 body region Anatomy 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 208000029257 vision disease Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/10—Culture of aquatic animals of fish
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Environmental Sciences (AREA)
- Multimedia (AREA)
- Marine Sciences & Fisheries (AREA)
- Zoology (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of fish diseases caused by virus based on computer vision to test tracking and monitoring system, this method comprises: being first grouped fluorescent marker to the fish that will be tested, then illness processing is carried out to the fish chosen, and disposes monitoring device in the water environment of its cultivation；It extracts monitoring video information and carries out target processing, first carry out video pre-filtering using morphologic filtering algorithm and background subtraction carries out the detection of Fish of interest, reuse Mean Shift algorithm and carry out target following and positioning；Information carries out upload platform database after the video information and processing that will acquire.The morbidity characterization and deterioration that fish suffer from fish disease caused by virus are still not clear, to find illness fish as early as possible, prevent extensive virus spread, influence economic benefit, the foundation of the tracking and monitoring system will provide the true experimental material of fish disease state, facilitate the data analysis for carrying out monitoring and the prevention of fish disease caused by virus in the future and test.
Description
Technical field
The present invention relates to video information process fields, more particularly, to the disease based on computer vision based on video
Toxicity fish disease tests tracking and monitoring system.
Background technique
The morbidity characterization and deterioration that some fish suffer from fish disease caused by virus are still not clear, and to find illness fish as early as possible, prevent
Extensive virus spread, influences economic benefit.For fishes virus fish disease break out problem, viral tracking and monitoring system can and
When check fish disease condition, reduce economic loss to make corresponding adjustment.
Summary of the invention
The present invention provides a kind of fish diseases caused by virus based on computer vision to test tracking and monitoring system, is subsequent fish
Class disease condition provides true information material.
Fish disease caused by virus based on computer vision tests tracking and monitoring system, comprising: S1, chooses the fish that will be tested
Class is grouped the fluorescent marker for carrying out different colours to it, then carries out different degrees of illness processing to it (viral species are virus
Property fish disease), and dispose suitable monitoring device in the environment of its cultivation, it is plain to provide video for the fish target processing in video
Material；Video information in S2, extraction monitoring device, first carries out stage extraction to its lengthy and jumbled information, and in the information extracted
Database is passed as initial back-up.Video object processing is carried out using the video information extracted, is first calculated using morphologic filtering
Method carries out video pre-filtering, then background subtraction carries out the detection of Fish of interest, finally carries out mesh using Mean Shift algorithm
Mark tracking and positioning；S3, by video analysis treated uploading information data platform database, in case subsequent illness information is looked into
It askes and data are analyzed and test.
Preferably, include: S01 before step S1, choose fish progress fish disease caused by virus test；S02, to this four groups of fish
Visualization implantable marker is carried out respectively；S03, it this 16 tail fish is respectively put into the rainbow virus-culturing fluid of various concentration carries out
Normal cultivation；S04, in fish culture environment, video monitoring apparatus, at any time the morbidity shape of the illness fish of monitoring test are installed
State, and the video information that video monitoring apparatus is got uploads platform database at any time.
Preferably, include: S01 before step S2, extract video information upload platform database；S02, it will be regarded in database
Frequency information carries out stage extraction, and retention is marked.
Preferably, include: S01 before step S3, Preprocessing is carried out to segmenting video；S02, the target for carrying out fish
Detection；S03, the target positioning and target following for carrying out fish.
Preferably, step S1 is specifically included: being chosen 16 tail fish and is carried out fish disease caused by virus test, this 16 tail fish is divided into 4
Group, each group of fish needs are unanimous on the whole, i.e., body surface is similar, and body size is similar, and growth time is similar, and weight is similar etc.
Deng, while this 4 groups need differentiation again, need of different sizes, body surface difference, weight is different, growth time difference etc..
To this four groups of fish carry out respectively visualization implantable marker (implanted fluorescence digital label can by injection, from
External observation comes out, and the color of fluorescence usually has red, orange, yellow and green), fish are divided into four groups, are injected not
With the fluorescence of color, and at same group select fish different parts injected, such as fish body overhead, eye socket rear portion,
Position between dorsal fin and pectoral fin, close to pectoral fin, to distinguish and to mark.
Preferably, it is specifically included before step S2: being put into monitor camera in fish culture pond, can monitor at any time
The behavior state etc. of all fish in aquaculture pond, and the monitor video taken is uploaded into cloud platform at any time.
For whole day 24 hours video surveillance data, selecting extraction 12 times with length 20 minutes monitor video materials,
The information such as time deposit database is marked for future use in these video data informations.
Preferably, step S3 is specifically included: S01, carrying out video pre-filtering using morphologic filtering algorithm；S02, background subtraction
The detection of point-score progress Fish of interest；S03, Mean Shift algorithm carry out target following and positioning.
Fish disease caused by virus based on computer vision tests tracking and monitoring system, comprising: test preparation module, screening are suitble to
Fish individual, to test fish individual carry out fluorescent marker, fish illness processing, creation various concentration virus buffer support
Environment is grown, placement video monitoring apparatus grabs the daily audio-visual-materials of fish；Video processing module, using morphologic filtering algorithm into
Row video pre-filtering carries out the detection of Fish of interest using background subtraction, carries out target following using Mean Shift algorithm
With positioning；Database module, video and video data analysis data upload database, including the daily monitoring of fish, segmentation view
Frequently, pretreated video, target detection, positioning and the data of tracking.
Preferably, further includes: context update module, for by background difference algorithm judge in the monitor video whether
In the presence of the fish detected.
Detailed description of the invention
Fig. 1 is the flow chart that fish disease caused by virus based on computer vision of the embodiment of the present invention tests tracking and monitoring system.
Fig. 2 is the system letter that the embodiment of the present invention tests tracking and monitoring system based on the fish disease caused by virus that computer is vision
Change figure.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
The invention solves the characterization informations that record suffers from the fish of fish disease caused by virus.
Phenomenon unstructured problem is characterized for the fish for suffering from fish disease caused by virus, uses viral fish based on computer vision
Disease test tracking and monitoring system can recorde the fish for suffering from fish disease caused by virus since illness to the characterization state of illness death,
In case can detect the illness fish in aquaculture pond in time and make emergency measure.
It is put into monitor camera in fish culture pond, the behavior state of all fish in aquaculture pond can be monitored at any time
Deng, and the monitor video taken is uploaded into cloud platform at any time.For whole day 24 hours video surveillance data, selection was taken out
12 times are taken with length 20 minutes monitor video materials, the information such as time deposit data are marked in these video data informations
Library is for future use.For the video got, carries out the fish locomotion target monitoring based on video, tracks.For what is traced into
Fish locomotion video carries out key-frame extraction, gets different static images.For the different key frames got, extract
Fish fin, the illness characterization at the positions such as fish belly.Then repetitive operation, until the fish illness of the label is dead, so
Just fish disease caused by virus test tracking and monitoring system based on computer vision is completed.
Fig. 1 is the flow chart that fish disease caused by virus based on computer vision of the embodiment of the present invention tests tracking and monitoring system,
As shown in Figure 1, being grouped the fluorescence mark for carrying out different colours to it this method comprises: S1, choose the fish that will be tested
Note, then different degrees of illness processing (viral species are fish disease caused by virus) is carried out to it, and dispose in the environment of its cultivation
Suitable monitoring device provides video material for the fish target processing in video；S2, the video extracted in monitoring device are believed
Breath, the information that first its lengthy and jumbled information is carried out stage extraction, and extracted upload database as initial back-up.Use extraction
The video information arrived carries out video object processing, first carries out video pre-filtering, then background subtraction using morphologic filtering algorithm
The detection of Fish of interest is carried out, finally carries out target following and positioning using Mean Shift algorithm；S3, video analysis is handled
Uploading information data platform database afterwards, in case the inquiry of subsequent illness information and data analysis and test.
Choose fish carry out fish disease caused by virus test, visualization implantable marker is carried out respectively to this four groups of fish, by this 16
Tail fish are respectively put into the rainbow virus-culturing fluid of various concentration and are normally cultivated.
In fish culture environment, video monitoring apparatus is installed, at any time the morbidity state of the illness fish of monitoring test, and
The video information that video monitoring apparatus is got uploads platform database at any time.
It extracts video information and uploads platform database, video information in database is subjected to stage extraction, and be marked
It retains.To segmenting video carry out Preprocessing, carry out the target detection of fish, carry out fish target positioning and target with
Track, and video analysis treated data information is uploaded into database.
Fishes virus fish disease follow-up experiment monitors the preparation stage of system, and steps are as follows: first choosing the progress of 16 tail fish
Fish disease caused by virus test, this 16 tail fish are divided into 4 groups, and each group of fish needs are unanimous on the whole, i.e., body surface is similar, body size
Similar, growth time is similar, and weight is similar etc., while this 4 groups need differentiation again, needs of different sizes, body surface difference, body
Weight is different, growth time difference etc..Then visualization implantable marker (implanted fluorescence digital is carried out respectively to this four groups of fish
Label can be come out, the color of fluorescence usually has red, orange, yellow and green by injection from external observation), by fish
It is divided into four groups, carries out the fluorescence of injection different colours, and selects the different parts of fish to be injected at same group, such as fish
Body overhead, eye socket rear portion, the position between dorsal fin and pectoral fin, close to pectoral fin, to distinguish and to mark, finally by this 16
Tail fish are respectively put into the rainbow virus-culturing fluid of various concentration and are cultivated.
Video camera will be installed in each water environment pond of culture experiment fish, and carry out monocular camera calibration,
The active state for all fishes for being observed that video camera in whole aquaculture pond can monitor the illness to make marks at any time
The growth animation and the surface characteristics situation of illness phase of fish, and the obtained video information of each video camera is real-time
Platform database is uploaded, for future use.
Fishes virus fish disease follow-up experiment monitors the implementation phase of system, and steps are as follows: extracting the video in database
The Object Detecting and Tracking of information progress fish.The video information that four cameras are obtained carries out separating arrangement, and
For in each camera four fish carry out Object Detecting and Tracking, that is, need to obtain video information carry out 16
The target analysis of fish is handled.Here, carrying out the detailed description of target analysis processing by taking any one fish as an example.
Video pre-filtering.Obtained video information is pre-processed first, video is carried out using mathematical morphology filter
The closed operation of pretreatment, selection expansion post-etching can retain the morphological state of fish to the greatest extent.WithIt is rightCarry out shape
State closed operation can be denoted as, it is defined as。
Target detection and positioning.The sequence of video images handled herein is in laboratory environments, to use fixing camera
The fish body sport video of acquisition moveing freely.Fish locomotion is carried out under static background, and the background is relatively simple,
And the interference of ambient lighting is less.Therefore fish body moving target is detected using background subtraction herein.Firstly, obtaining Background
Picture carries out initial partitioning to fish body image using background subtraction；Then, based on automation threshold value to secondary point of fish body image
It cuts, moving target prospect is extracted in the positioning for carrying out four boundaries to moving object region；Finally, showing moving object region and to fortune
Animal body region carries out the positioning on four boundaries.
Background subtraction can efficiently accomplish the initial partitioning to colored fish body video image, using genetic algorithm to form
The fish body initial partitioning image for learning filtering carries out secondary splitting, finally uses element marking algorithm to the fish locomotion detected
Target carries out four boundary alignments.
Target following.The tracking that moving object is carried out using Mean Shift algorithm, should obtain related moving object first
The Mean Shift vector of body, that is, to obtain moving object mobile from the mobile object accurate location that is positioned against is started
Vector.The method for obtaining Mean Shift vector is the maximum value by seeking similarity function.The similarity function investigate be
Similitude between two models of object module about initial frame and the candidate family about present frame.Then constantly iterative calculation
Mean Shift vector.Since Mean Shift algorithm has convergence, finally moving object will be received in current video frame
The actual position of target is held back, and uploads the location informations of the fish at any time to database.
(1) object module: assuming that the center of target area is, have,A pixel belongs to target
Region existsA characteristic value, the then characteristic value of object moduleThe probability density of estimation is
It is a standardized constant factor, so that。
(2) candidate family: candidate family is the calculating to candidate region.Candidate region is referred in sequence of video images
In frame, since initial frame, all appearance may include the region of moving target in the picture.The pixel of candidate region is used,It indicates, centre coordinate is the centre coordinate of kernel function, is usedIt indicates.The characteristic value of candidate familyProbability density be
WhereinFor normalization constants coefficient.
(3) similarity function.Similarity function is for measuring between two model histograms of object module and candidate family
Similarity degree.In order to be positioned as close to truth during tracking, select Pasteur's coefficient as common phase
Like property function, describe it asTo obtain moving target in this frame
Position, it is maximum should just to make similarity degree between object module and candidate family, that is, calculate each in video frame this moment
The candidate family of candidate region.
Preferably, context update module, for being judged in the monitor video by background difference algorithm with the presence or absence of inspection
The fish measured.
Fishes virus fish disease follow-up experiment monitors the finishing phase of system, and steps are as follows: according to the position in database
Information, 24 hours select 48 groups of tests to transfer the location information of this fish, and carry out video using half an hour as the period
The interception of key frame, and the key frame information that will acquire is uploaded in the database of fish classification.Here, daily back and forth into
Row, until the fish death then completes all information data acquisitions.
The embodiment of the present invention also provides a kind of fish rainbow Viral Assay tracking and monitoring system, which includes: that test prepares
Module screens suitable fish individual, carries out fluorescent marker to test fish individual, fish illness processing creates various concentration
The breeding environment of virus buffer, placement video monitoring apparatus grab the daily audio-visual-materials of fish；Video processing module uses shape
State filtering algorithm carries out video pre-filtering, and the detection of Fish of interest is carried out using background subtraction, is calculated using Mean Shift
Method carries out target following and positioning；Database module, video and video data analysis data upload database, including fish day
Often monitoring, segmenting video, pretreated video, target detection, positioning and the data of tracking.The system embodiment it is specific
Implementation procedure is identical as the specific implementation procedure of corresponding embodiment of the method, and details please refer to the implementation procedure of embodiment of the method,
Details are not described herein again.
On the basis of the above embodiments, it is preferable that the system further include: context update module, for passing through background subtraction
Algorithm is divided to judge in the monitor video with the presence or absence of the fish detected.The specific implementation procedure of the system embodiment with it is corresponding
Embodiment of the method specific implementation procedure it is identical, details please refer to the implementation procedure of embodiment of the method, and details are not described herein again.
Finally, method of the invention is only preferable embodiment, it is not intended to limit the scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent replacement, improvement and so on should be included in protection of the invention
Within the scope of.
Claims (12)
1. the tracking and monitoring system of illness fish characterized by comprising S1, choose the fish that will be tested, it is grouped into
The fluorescent marker of row different colours, then different degrees of illness processing (viral species are fish disease caused by virus) is carried out to it, and
Suitable monitoring device is disposed in its environment cultivated, provides video material for the fish target processing in video；S2, prison is extracted
The video information in device is controlled, the information that first its lengthy and jumbled information is carried out stage extraction, and extracted uploads database conduct
Initial back-up.
2. carrying out video object processing using the video information extracted, first carried out at video preprocessor using morphologic filtering algorithm
Reason, then background subtraction carry out the detection of Fish of interest, finally carry out target following and positioning using Mean Shift algorithm；
S3, by video analysis treated uploading information data platform database, in case the inquiry of subsequent illness information and data point
Analysis and test.
3. method according to claim 1, which is characterized in that include: before step S1 S01, choose fish carry out it is viral
Fish disease test；S02, visualization implantable marker is carried out respectively to this four groups of fish；S03, this 16 tail fish is respectively put into difference
It is normally cultivated in the rainbow virus-culturing fluid of concentration；S04, in fish culture environment, install video monitoring apparatus, at any time
The morbidity state of the illness fish of monitoring test, and the video information that video monitoring apparatus is got uploads platform data at any time
Library.
4. method according to claim 1, which is characterized in that include: before step S2 S01, extract video information upload it is flat
Platform database；S02, video information in database is subjected to stage extraction, and retention is marked.
5. method according to claim 1, which is characterized in that include: S01 before step S3, located in advance to segmenting video
Reason analysis；S02, the target detection for carrying out fish；S03, the target positioning and target following for carrying out fish.
6. method according to claim 2, which is characterized in that step S1 is specifically included:
It chooses 16 tail fish and carries out fish disease caused by virus test, this 16 tail fish is divided into 4 groups, and each group of fish need substantially one
It causes, i.e., body surface is similar, and body size is similar, and growth time is similar, and weight is similar etc., while this 4 groups need differentiation again, need
Want of different sizes, body surface is different, and weight is different, growth time difference etc..
7. pair this four groups of fish carry out visualization implantable marker respectively, (implanted fluorescence digital label can be by injection, from outer
Portion, which observes, to be come, and the color of fluorescence usually has red, orange, yellow and green), fish are divided into four groups, it is different to carry out injection
The fluorescence of color, and select the different parts of fish to be injected at same group, such as fish body overhead, eye socket rear portion, back
Position between fin and pectoral fin, close to pectoral fin, to distinguish and to mark.
8. method according to claim 3, which is characterized in that specifically include before step S2: being put into fish culture pond
Monitor camera can monitor the behavior state etc. of all fish in aquaculture pond at any time, and at any time regard the monitoring taken
Frequency uploads to cloud platform.
9. be directed to whole day 24 hours video surveillance data, selecting extraction 12 times with length 20 minutes monitor video materials, will
The information such as time deposit database is marked for future use in these video data informations.
10. method according to claim 3, which is characterized in that step S3 is specifically included: S01, being calculated using morphologic filtering
Method carries out video pre-filtering；S02, background subtraction carry out the detection of Fish of interest；S03, Mean Shift algorithm carry out target
Tracking and positioning.
11. the tracking and monitoring system of illness fish characterized by comprising test preparation module screens suitable fish
Body carries out fluorescent marker to test fish individual, and fish illness processing creates the breeding environment of various concentration virus buffer,
Video monitoring apparatus is disposed to grab the daily audio-visual-materials of fish；Video processing module carries out video using morphologic filtering algorithm
Pretreatment carries out the detection of Fish of interest using background subtraction, carries out target following and positioning using Mean Shift algorithm；
Database module, video and video data analysis data upload database, including the daily monitoring of fish, and segmenting video is pre- to locate
Video after reason, target detection, positioning and the data of tracking.
12. system according to claim 8, which is characterized in that further include: context update module, for passing through background difference
Algorithm judges in the monitor video with the presence or absence of the fish detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811297858.3A CN109448028A (en) | 2018-11-02 | 2018-11-02 | Fish disease caused by virus based on computer vision tests tracking and monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811297858.3A CN109448028A (en) | 2018-11-02 | 2018-11-02 | Fish disease caused by virus based on computer vision tests tracking and monitoring system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109448028A true CN109448028A (en) | 2019-03-08 |
Family
ID=65550140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811297858.3A Pending CN109448028A (en) | 2018-11-02 | 2018-11-02 | Fish disease caused by virus based on computer vision tests tracking and monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109448028A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113598098A (en) * | 2021-08-06 | 2021-11-05 | 黑龙江八一农垦大学 | Fish disease recognition processing device based on machine vision |
| CN114916473A (en) * | 2022-05-23 | 2022-08-19 | 大连理工大学 | Overlook fish body length monitoring method and device used in farm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101305701A (en) * | 2008-07-08 | 2008-11-19 | 中国水产科学研究院黄海水产研究所 | Fish family establishing and disease-resistant high yield fine breeding method |
| CN103499675A (en) * | 2013-09-30 | 2014-01-08 | 苏州国环环境检测有限公司 | Method for monitoring toxicity of domestic sewage through zebra fishes |
| 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 |
-
2018
- 2018-11-02 CN CN201811297858.3A patent/CN109448028A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101305701A (en) * | 2008-07-08 | 2008-11-19 | 中国水产科学研究院黄海水产研究所 | Fish family establishing and disease-resistant high yield fine breeding method |
| CN103499675A (en) * | 2013-09-30 | 2014-01-08 | 苏州国环环境检测有限公司 | Method for monitoring toxicity of domestic sewage through zebra fishes |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 黄一凡: "《鱼类应激行为作用下的水质视频监测分析系统》", 厦门大学学报(自然科学版), vol. 56, no. 4, 31 July 2017 (2017-07-31), pages 1 - 6 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113598098A (en) * | 2021-08-06 | 2021-11-05 | 黑龙江八一农垦大学 | Fish disease recognition processing device based on machine vision |
| CN114916473A (en) * | 2022-05-23 | 2022-08-19 | 大连理工大学 | Overlook fish body length monitoring method and device used in farm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mohamed et al. | Msr-yolo: Method to enhance fish detection and tracking in fish farms | |
| Kulwa et al. | A state-of-the-art survey for microorganism image segmentation methods and future potential | |
| CA2629349C (en) | Time-lapse cell cycle analysis of unstained nuclei | |
| Schmid et al. | The LOKI underwater imaging system and an automatic identification model for the detection of zooplankton taxa in the Arctic Ocean | |
| Jambhekar | Red blood cells classification using image processing | |
| Saifullah | Segmentation for embryonated egg images detection using the K-means algorithm in image processing | |
| CN109448028A (en) | Fish disease caused by virus based on computer vision tests tracking and monitoring system | |
| Duan et al. | Automatic segmentation method for live fish eggs microscopic image analysis | |
| CN112528823A (en) | Striped shark movement behavior analysis method and system based on key frame detection and semantic component segmentation | |
| Saifullah | K-means Segmentation Based-on Lab Color Space for Embryo Egg Detection | |
| Mejias et al. | Automated marine mammal detection from aerial imagery | |
| Razzaq et al. | Stomatal state identification and classification in Quinoa microscopic imprints through deep learning | |
| Padfield et al. | Spatio-temporal cell cycle analysis using 3D level set segmentation of unstained nuclei in line scan confocal fluorescence images | |
| Zhang et al. | An approach for goose egg recognition for robot picking based on deep learning | |
| Fan et al. | Automatic video-based analysis of animal behaviors | |
| Peng et al. | Detecting coffee (Coffea arabica L.) sequential flowering events based on image segmentation | |
| Ma et al. | UAV equipped with infrared imaging for cervidae monitoring: Improving detection accuracy by eliminating background information interference | |
| Meng et al. | An extraction method of fish vector field for marine cage culture based on UAV vision | |
| Yuana et al. | Mobile sensing in Aedes aegypti larva detection with biological feature extraction | |
| Soleimany et al. | Image segmentation of liver stage malaria infection with spatial uncertainty sampling | |
| Theodoropoulos et al. | A digital image analysis and neural network based system for identification of third-stage parasitic strongyle larvae from domestic animals | |
| Wang et al. | Fish Behavior Detection Using Computer Vision: A Review | |
| Pal et al. | Automatic rice crop extraction using edge based color features and color indices | |
| Yew et al. | AUTOMATED CELL MIGRATION TRACKING TECHNIQUE: A REVIEW | |
| Kembhavi et al. | Tracking down under: Following the satin bowerbird |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |