CN104966122A - System for automatically counting live fishes based on machine vision - Google Patents
System for automatically counting live fishes based on machine vision Download PDFInfo
- Publication number
- CN104966122A CN104966122A CN201510437308.7A CN201510437308A CN104966122A CN 104966122 A CN104966122 A CN 104966122A CN 201510437308 A CN201510437308 A CN 201510437308A CN 104966122 A CN104966122 A CN 104966122A
- Authority
- CN
- China
- Prior art keywords
- fish
- district
- filtering tank
- counting
- computer vision
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- Farming Of Fish And Shellfish (AREA)
Abstract
The invention relates to a system for automatically counting live fishes based on the machine vision, and the system comprises a fish channel, and a water-filtering tank which is disposed at a side of a fishway and is communicated with the fishway. The bottom of the water-filtering tank is provided with a water-filtering part, and the water-filtering tank is connected with an external fish absorption pump and a fish dividing machine through quick connectors. The fishway is arranged in an inclined manner, and the bottom of the fishway is provided with a camera system. The top of the fishway is provided with an illumination system, and the camera system and the illumination system are connected with an embedded processing unit of a computer and an LED touch screen based on video analysis fish-counting software. The system can achieve the video analysis of live fishes flowing through a detection region so as to achieve the quick, accurate and automatic counting, achieves automatic, high-efficiency, precise and no-stress counting of live fishes for the aquaculture industry, and improves the automation level of the aquaculture industry.
Description
Technical field
The present invention relates to live fish automatic counter system in a kind of aquaculture (fishery machinery instrument and equipment field), be applicable to fry numeration, fry counting, adult fish counting, can be connected with fishpump, fish grader and realize the automatic accurate counting of live fish.
Background technology
In the development of culture fishery, the basic guarantee of the cultivation standardized management such as the accurate metering of fish is science bait throwing in, cultivation density controls, the assessment of fish survival rate, fry sale.The counting of current fish also generally adopts traditional artificial naked eyes statistical method, exist count accuracy difference, efficiency low, limit by artificial experience, the shortcomings such as error is indefinite, and have damage to fish, cannot adapt to the demand of scale aquaculture and sale.In recent years, in succession emerge the various device for automatic fry counting both at home and abroad, such as, Weighting type fry numeration, fry counting device, the fry numeration, fry counting device based on Photoelectric Detection and the fry numeration, fry counting device etc. based on computer vision.Existing several fish device mainly pays close attention to fry numeration, fry counting problem on a small scale, not yet has live fish continuous counter in enormous quantities to equip and is seen in report.Along with the cultivation such as domestic fishpump, fish grader are equipped in applying in aquatic products industry, be starved of several fish equipment that research and development match with it.
In order to solve the band water live fish accurate counting problem in standardization cultivation, native system utilizes computer vision and automatic control techniques to solve live fish Auto-counting problem, and system can be used for industrial aquaculture enterprise, pond net box breeding enterprise and nursery factory etc.
Summary of the invention
The object of the invention is the defect in order to solve in prior art existing for number fish device, there is provided a kind of can the live fish in convection current district after testing carry out video analysis to realize fast, accurately, Auto-counting, make culture fishery can automatically, efficient, precisely, stress not ground to live fish counting, the live fish automatic counter system based on computer vision of lifting aquaculture automatization level.
To achieve these goals, the technical solution used in the present invention is:
Based on a live fish automatic counter system for computer vision, comprise fish pass, be arranged on this fish pass side and the water filtering tank be communicated with, the bottom of described water filtering tank is provided with drainage parts, and water filtering tank is connected with extraneous fishpump, fish grader by rapid-acting coupling;
Described fish pass is obliquely installed, and is provided with camera system in the bottom of fish pass, and the top of fish pass is provided with illuminator, and embedded processing unit, the LED touch of camera system and illuminator and computing machine are shielded the several fish softwares run based on video analysis and be connected.
Above-mentioned a kind of live fish automatic counter system based on computer vision, described drainage parts comprise the water strainer be arranged on bottom water filtering tank and the freeing port be arranged on below water strainer.
Above-mentioned a kind of live fish automatic counter system based on computer vision, described camera system is industrial camera, described illuminator comprise the LED case that is arranged on bottom fish pass and be sealed on LED case with fish pass bottom the light-passing board of contact position.
Above-mentioned a kind of live fish automatic counter system based on computer vision, described water strainer is welded by stainless-steel tube and removably connects with water filtering tank, and water strainer guarantees that fish can against through detection zone bottom fish pass, prevents from occurring overlap during shooting.
Above-mentioned a kind of live fish automatic counter system based on computer vision, the angle of inclination of described fish pass is 5 °-20 °, and one end that fish pass is connected with water filtering tank is higher than the one end away from water filtering tank.
Above-mentioned a kind of live fish automatic counter system based on computer vision, be provided with LED lamp tube in the LED case of described illuminator, light-passing board is preferably PC diffuser plate.
Based on a method of counting for the live fish automatic counter system of computer vision, comprise the steps:
A) taken without detection zone image during fish by camera system, extract detection zone mask image according to brightness binaryzation;
B) Real-time Collection number fish video, analyzes every two field picture, and present image and mask image are carried out AND operation, extracts the fish diagram picture in surveyed area;
C) Da-Jin algorithm binaryzation fish diagram picture is utilized, and the connection district area in result of calculation image;
D) compare each connection district area and the area threshold preset in present image one by one, the lower limit lower than this value thinks that noise or dirt give filtering, is greater than this threshold value and then preserves in this connection district information (area, center of gravity etc.) insertion chained list;
E) because same fish appears in a few frame picture of continuous print, analyze each connection district in present frame chained list one by one and whether count;
F) the connection district that present frame occurs is communicated with district one by one with previous frame and compares centre of gravity place (x, y), because fish pass has inclination angle, if belong to same fish, then present frame is communicated with district center of gravity y coordinate and will be communicated with district y coordinate lower than previous frame correspondence, if find, current connection district counts, otherwise counting adds 1;
G) when be communicated with district area exceed predetermined threshold value more time, think that may there be many fishes in this connection district, extract and be communicated with district's morphological feature (area, skeleton, number of endpoint etc.), adopt the fish quantity that this connection district of neural net method identification comprises;
H) display screen exports count results.
Beneficial effect of the present invention is:
1, the present invention can support the use with the aquaculture installation such as fishpump or fish grader;
2, the present invention's counting is more accurate, and adopt methods of video analyses to make use of than still image more information, counting precision reaches more than 95%;
3, counting efficiency of the present invention is high, per hourly can count 5000 ~ 20000, can meet the counting needs of large-scale corporation.
4, the present invention can carry out Auto-counting to band water live fish, to fish stress not, damage very little;
5, software and hardware one of the present invention, is applicable to execute-in-place and use;
6, the present invention is applied widely, is not only applicable to fry numeration, fry counting but also applicable adult fish counting.
Accompanying drawing explanation
Fig. 1 is the side view of the live fish robot scaler that the present invention is based on computer vision;
Fig. 2 is the vertical view of the live fish robot scaler that the present invention is based on computer vision;
Fig. 3 is the process flow diagram of the live fish Auto-counting software that the present invention is based on computer vision.
Embodiment
Further understand for making to have architectural feature of the present invention and effect of reaching and be familiar with, coordinate detailed description in order to preferred embodiment and accompanying drawing, be described as follows:
As shown in Figure 1, Figure 2, Figure 3 shows, a kind of live fish automatic counter system based on computer vision, comprise support 1, be arranged on the fish pass 2 on support 1, be arranged on this fish pass 2 side and the water filtering tank 3 be communicated with, the bottom of water filtering tank 3 is provided with drainage parts, and water filtering tank 3 is connected with extraneous fishpump, fish grader by rapid-acting coupling 4;
Wherein, fish pass 2 is obliquely installed, and the angle of inclination of fish pass 2 is 5 °-20 °, and one end that fish pass 2 is connected with water filtering tank 3, higher than the one end away from water filtering tank 3, is provided with camera system in the bottom of fish pass 2, and the top of fish pass 2 is provided with illuminator; Drainage parts comprise the water strainer 5 be arranged on bottom water filtering tank 3 and the freeing port 6 be arranged on below water strainer 5, water strainer 5 is welded by stainless-steel tube and removably connects with water filtering tank 3, water strainer 5 guarantees that fish can against through detection zone bottom fish pass 2, and when preventing from taking, appearance is overlapping.Camera system is preferably industrial camera 7, illuminator comprise the LED case 8 that is arranged on bottom fish pass 2 and be sealed on LED case 8 with fish pass 2 bottom the light-passing board 9 of contact position, LED lamp tube is provided with in LED case 8, light-passing board 9 is preferably PC diffuser plate, and embedded processing unit 10, the LED touch of camera system and illuminator and computing machine are shielded the 11 several fish softwares run based on video analysis and be connected.
In the present invention, rapid-acting coupling 4 is stainless steel rapid-acting coupling, for fixing plastic tube of drawing from fish grader or fishpump, caliber size is 250mm, according to the specification of fish, conventional plastic tube bore has 110mm, 160mm, 200mm and 250mm, and the present invention selects 250mm bore, the plastic tube of various bore can be connected by an external X-over easily, there is fine versatility.Stainless steel fish pass 2 width is 40cm, fish can be made to scatter from rapid-acting coupling 4 to water strainer 5, avoids fish overlap in vertical direction.Industrial camera 7 is fixed on square stainless steel magazine, and camera lens is inwardly taken.LED white light source in LED case 8 appears and illuminates detection zone by light-passing board 9, and like this, in time not having fish, detection zone is imaged as white, and once there be fish to flow through detection zone, having fish image areas is then black, and profile is very clear, thus image recognition accuracy is high.
Based on the method for counting of the live fish automatic counter system of computer vision, comprise the steps:
A) taken without detection zone image during fish by camera system, extract detection zone mask image according to brightness binaryzation;
B) Real-time Collection number fish video, analyzes every two field picture, and present image and mask image are carried out AND operation, extracts the fish diagram picture in surveyed area;
C) Da-Jin algorithm binaryzation fish diagram picture is utilized, and the connection district area in result of calculation image;
D) compare each connection district area and the area threshold preset in present image one by one, the lower limit lower than this value thinks that noise or dirt give filtering, is greater than this threshold value and then preserves in this connection district information (area, center of gravity etc.) insertion chained list;
E) because same fish appears in a few frame picture of continuous print, analyze each connection district in present frame chained list one by one and whether count;
F) the connection district that present frame occurs is communicated with district one by one with previous frame and compares centre of gravity place (x, y), because fish pass has inclination angle, if belong to same fish, then present frame is communicated with district center of gravity y coordinate and will be communicated with district y coordinate lower than previous frame correspondence, if find, current connection district counts, otherwise counting adds 1;
G) when be communicated with district area exceed predetermined threshold value more time, think that may there be many fishes in this connection district, extract and be communicated with district's morphological feature (area, skeleton, number of endpoint etc.), adopt the fish quantity that this connection district of neural net method identification comprises;
H) display screen exports count results.
This example employing size is the atlantic salmon 3265 of about 300g, and utilize the fishpump that bore is 160mm to extract out from culturing pool, count results is 3189, and counting accuracy rate of the present invention is 97.7%.
Beneficial effect of the present invention is:
1, the present invention can support the use with the aquaculture installation such as fishpump or fish grader;
2, the present invention's counting is more accurate, and adopt methods of video analyses to make use of than still image more information, counting precision reaches more than 95%;
3, counting efficiency of the present invention is high, per hourly can count 5000 ~ 20000, can meet the counting needs of large-scale corporation.
4, the present invention can carry out Auto-counting to band water live fish, to fish stress not, damage very little;
5, software and hardware one of the present invention, is applicable to execute-in-place and use;
6, the present invention is applied widely, is not only applicable to fry numeration, fry counting but also applicable adult fish counting.
More than show and describe ultimate principle of the present invention, principal character and advantage of the present invention.The technician of the industry should understand; the present invention is not restricted to the described embodiments; the just principle of the present invention described in above-described embodiment and instructions; the present invention also has various changes and modifications without departing from the spirit and scope of the present invention, and these changes and improvements all fall in claimed scope of the present invention.The protection domain of application claims is defined by appending claims and equivalent thereof.
Claims (7)
1. the live fish automatic counter system based on computer vision, comprise fish pass, be arranged on this fish pass side and the water filtering tank be communicated with, it is characterized in that, the bottom of described water filtering tank is provided with drainage parts, and water filtering tank is connected with extraneous fishpump, fish grader by rapid-acting coupling;
Described fish pass is obliquely installed, and is provided with camera system in the bottom of fish pass, and the top of fish pass is provided with illuminator, and camera system and illuminator and embedded processing unit, LED touch are shielded the several fish softwares run based on video analysis and be connected.
2. a kind of live fish automatic counter system based on computer vision according to claim 1, it is characterized in that, described drainage parts comprise the water strainer be arranged on bottom water filtering tank and the freeing port be arranged on below water strainer.
3. a kind of live fish automatic counter system based on computer vision according to claim 1, it is characterized in that, described camera system is industrial camera, described illuminator comprise the LED case that is arranged on bottom fish pass and be sealed on LED case with fish pass bottom the light-passing board of contact position.
4. a kind of live fish automatic counter system based on computer vision according to claim 2, it is characterized in that, described water strainer is welded by stainless-steel tube and removably connects with water filtering tank, and water strainer guarantees that fish can against through detection zone bottom fish pass, prevents from occurring overlap during shooting.
5. a kind of live fish automatic counter system based on computer vision according to claim 1, is characterized in that, the angle of inclination of described fish pass is 5 °-20 °, and one end that fish pass is connected with water filtering tank is higher than the one end away from water filtering tank.
6. a kind of live fish automatic counter system based on computer vision according to claim 3, it is characterized in that, be provided with LED lamp tube in the LED case of described illuminator, light-passing board is preferably PC diffuser plate.
7., based on a method of counting for a kind of live fish automatic counter system based on computer vision according to claim 1, it is characterized in that, comprise the steps:
A) taken without detection zone image during fish by camera system, extract detection zone mask image according to brightness binaryzation;
B) Real-time Collection number fish video, analyzes every two field picture, and present image and mask image are carried out AND operation, extracts the fish diagram picture in surveyed area;
C) Da-Jin algorithm binaryzation fish diagram picture is utilized, and the connection district area in result of calculation image;
D) compare each connection district area and the area threshold preset in present image one by one, the lower limit lower than this value thinks that noise or dirt give filtering, is greater than this threshold value and then preserves in this connection district information (area, center of gravity etc.) insertion chained list;
E) because same fish appears in a few frame picture of continuous print, analyze each connection district in present frame chained list one by one and whether count;
F) the connection district that present frame occurs is communicated with district one by one with previous frame and compares centre of gravity place (x, y), because fish pass has inclination angle, if belong to same fish, then present frame is communicated with district center of gravity y coordinate and will be communicated with district y coordinate lower than previous frame correspondence, if find, current connection district counts, otherwise counting adds 1;
G) when be communicated with district area exceed predetermined threshold value more time, think that may there be many fishes in this connection district, extract and be communicated with district's morphological feature (area, skeleton, number of endpoint etc.), adopt the fish quantity that this connection district of neural net method identification comprises;
H) display screen exports count results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510437308.7A CN104966122A (en) | 2015-07-11 | 2015-07-11 | System for automatically counting live fishes based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510437308.7A CN104966122A (en) | 2015-07-11 | 2015-07-11 | System for automatically counting live fishes based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104966122A true CN104966122A (en) | 2015-10-07 |
Family
ID=54220156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510437308.7A Pending CN104966122A (en) | 2015-07-11 | 2015-07-11 | System for automatically counting live fishes based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104966122A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105374042A (en) * | 2015-11-30 | 2016-03-02 | 中国计量学院 | Device and method of on-line automatic count of fries on the basis of machine vision |
| CN106022459A (en) * | 2016-05-23 | 2016-10-12 | 三峡大学 | Automatic counting system for fish passing amount of fish passage based on underwater videos |
| CN106172142A (en) * | 2016-08-31 | 2016-12-07 | 长江勘测规划设计研究有限责任公司 | To the system and method sorted by the Fish of fish pass |
| CN106447672A (en) * | 2016-09-14 | 2017-02-22 | 燕山大学 | Identifying and counting method for intersecting and shielded fish |
| CN107103602A (en) * | 2017-04-19 | 2017-08-29 | 凌美芯（北京）科技有限责任公司 | A kind of intelligent material method of counting based on computer vision technique |
| CN107372274A (en) * | 2017-09-20 | 2017-11-24 | 浙江大学宁波理工学院 | Fishes and shrimps seedling counting machine |
| CN107909137A (en) * | 2017-11-27 | 2018-04-13 | 南瑞集团有限公司 | A kind of fish pass crosses fish counting and recognition methods |
| CN108040948A (en) * | 2017-12-13 | 2018-05-18 | 阜阳市颍东区兴牧禽业专业合作社 | Breed in stew automatic feeding system |
| CN108244017A (en) * | 2018-02-13 | 2018-07-06 | 贵州省水利水电勘测设计研究院 | A kind of fish screening plant for fish lift |
| CN108364059A (en) * | 2018-03-07 | 2018-08-03 | 中国水产科学研究院南海水产研究所 | A kind of shrimp seedling counting device and method of counting |
| CN108739591A (en) * | 2018-04-13 | 2018-11-06 | 中国海洋大学 | It is a kind of based on dynamic structure light measurement cross fish pass cross fish amount automatic counter system and method for counting |
| CN109145808A (en) * | 2018-08-17 | 2019-01-04 | 郑州轻工业学院 | A kind of tuna recognition methods based on adaptive fish body bending die |
| CN109509175A (en) * | 2018-10-15 | 2019-03-22 | 浙江大学 | A kind of fry portable counters and method of counting based on machine vision and deep learning |
| CN109543679A (en) * | 2018-11-16 | 2019-03-29 | 南京师范大学 | A kind of dead fish recognition methods and early warning system based on depth convolutional neural networks |
| CN109566512A (en) * | 2018-12-04 | 2019-04-05 | 中国水产科学研究院渔业机械仪器研究所 | A kind of fry automatic separating apparatus and control method |
| CN110114782A (en) * | 2017-12-01 | 2019-08-09 | 日本电气方案创新株式会社 | Fish photographic device and fish counting device |
| RU2716418C1 (en) * | 2019-07-11 | 2020-03-11 | Общество с ограниченной ответственностью "Конструкторское бюро морской электроники "Вектор" (ООО КБМЭ "Вектор") | Fish counting device |
| CN110945533A (en) * | 2017-08-16 | 2020-03-31 | 古野电气株式会社 | Fish number measuring device, fish number measuring system, and fish number measuring method |
| CN111652842A (en) * | 2020-04-26 | 2020-09-11 | 佛山读图科技有限公司 | Real-time visual detection method and system for high-speed penicillin bottle capping production line |
| CN111882451A (en) * | 2020-08-12 | 2020-11-03 | 滨州学院 | Economic data analysis system for marine culture area |
| CN113160052A (en) * | 2021-04-01 | 2021-07-23 | 华南理工大学 | Offshore culture area image splicing method based on non-uniform precision |
| CN113758577A (en) * | 2021-09-09 | 2021-12-07 | 易科捷(武汉)生态科技有限公司成都分公司 | Accurate type fish identification technology system based on big data |
| CN115953725A (en) * | 2023-03-14 | 2023-04-11 | 浙江大学 | Fish egg automatic counting system based on deep learning and counting method thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06243311A (en) * | 1993-02-15 | 1994-09-02 | Keisuke Ueno | Method and device for counting live fishes |
| CN201838030U (en) * | 2010-11-15 | 2011-05-18 | 浙江海洋学院 | Automatic fish-fry counting device |
| CN102805044A (en) * | 2012-07-16 | 2012-12-05 | 宁波大学 | Fish, shrimp and crab seed automatic counting device and method based on computer video processing |
-
2015
- 2015-07-11 CN CN201510437308.7A patent/CN104966122A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06243311A (en) * | 1993-02-15 | 1994-09-02 | Keisuke Ueno | Method and device for counting live fishes |
| CN201838030U (en) * | 2010-11-15 | 2011-05-18 | 浙江海洋学院 | Automatic fish-fry counting device |
| CN102805044A (en) * | 2012-07-16 | 2012-12-05 | 宁波大学 | Fish, shrimp and crab seed automatic counting device and method based on computer video processing |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105374042A (en) * | 2015-11-30 | 2016-03-02 | 中国计量学院 | Device and method of on-line automatic count of fries on the basis of machine vision |
| CN105374042B (en) * | 2015-11-30 | 2018-11-02 | 中国计量学院 | The on-line automatic counting device of fry based on machine vision and method |
| CN106022459A (en) * | 2016-05-23 | 2016-10-12 | 三峡大学 | Automatic counting system for fish passing amount of fish passage based on underwater videos |
| CN106022459B (en) * | 2016-05-23 | 2018-11-30 | 三峡大学 | A kind of fish pass based on underwater video crosses fish amount automatic counter system |
| CN106172142B (en) * | 2016-08-31 | 2022-01-14 | 长江勘测规划设计研究有限责任公司 | System and method for sorting fish passing through fishway |
| CN106172142A (en) * | 2016-08-31 | 2016-12-07 | 长江勘测规划设计研究有限责任公司 | To the system and method sorted by the Fish of fish pass |
| CN106447672A (en) * | 2016-09-14 | 2017-02-22 | 燕山大学 | Identifying and counting method for intersecting and shielded fish |
| CN106447672B (en) * | 2016-09-14 | 2019-03-26 | 燕山大学 | It is a kind of intersection block fish body identification method of counting |
| CN107103602A (en) * | 2017-04-19 | 2017-08-29 | 凌美芯（北京）科技有限责任公司 | A kind of intelligent material method of counting based on computer vision technique |
| CN110945533A (en) * | 2017-08-16 | 2020-03-31 | 古野电气株式会社 | Fish number measuring device, fish number measuring system, and fish number measuring method |
| CN110945533B (en) * | 2017-08-16 | 2023-08-04 | 古野电气株式会社 | Fish number measuring device, fish number measuring system, and fish number measuring method |
| CN107372274B (en) * | 2017-09-20 | 2020-04-03 | 浙江大学宁波理工学院 | Fish and shrimp fry counter |
| CN107372274A (en) * | 2017-09-20 | 2017-11-24 | 浙江大学宁波理工学院 | Fishes and shrimps seedling counting machine |
| CN107909137A (en) * | 2017-11-27 | 2018-04-13 | 南瑞集团有限公司 | A kind of fish pass crosses fish counting and recognition methods |
| CN110114782A (en) * | 2017-12-01 | 2019-08-09 | 日本电气方案创新株式会社 | Fish photographic device and fish counting device |
| CN108040948B (en) * | 2017-12-13 | 2019-11-08 | 许挺俊 | Breed in stew automatic feeding system |
| CN108040948A (en) * | 2017-12-13 | 2018-05-18 | 阜阳市颍东区兴牧禽业专业合作社 | Breed in stew automatic feeding system |
| CN108244017B (en) * | 2018-02-13 | 2023-12-26 | 贵州省水利水电勘测设计研究院 | Fish screening device for fish lifting machine |
| CN108244017A (en) * | 2018-02-13 | 2018-07-06 | 贵州省水利水电勘测设计研究院 | A kind of fish screening plant for fish lift |
| CN108364059A (en) * | 2018-03-07 | 2018-08-03 | 中国水产科学研究院南海水产研究所 | A kind of shrimp seedling counting device and method of counting |
| CN108739591A (en) * | 2018-04-13 | 2018-11-06 | 中国海洋大学 | It is a kind of based on dynamic structure light measurement cross fish pass cross fish amount automatic counter system and method for counting |
| CN109145808A (en) * | 2018-08-17 | 2019-01-04 | 郑州轻工业学院 | A kind of tuna recognition methods based on adaptive fish body bending die |
| CN109509175A (en) * | 2018-10-15 | 2019-03-22 | 浙江大学 | A kind of fry portable counters and method of counting based on machine vision and deep learning |
| CN109509175B (en) * | 2018-10-15 | 2020-09-04 | 浙江大学 | Portable fry counter based on machine vision and deep learning and counting method |
| CN109543679A (en) * | 2018-11-16 | 2019-03-29 | 南京师范大学 | A kind of dead fish recognition methods and early warning system based on depth convolutional neural networks |
| CN109566512A (en) * | 2018-12-04 | 2019-04-05 | 中国水产科学研究院渔业机械仪器研究所 | A kind of fry automatic separating apparatus and control method |
| RU2716418C1 (en) * | 2019-07-11 | 2020-03-11 | Общество с ограниченной ответственностью "Конструкторское бюро морской электроники "Вектор" (ООО КБМЭ "Вектор") | Fish counting device |
| CN111652842B (en) * | 2020-04-26 | 2021-05-11 | 佛山读图科技有限公司 | Real-time visual detection method and system for high-speed penicillin bottle capping production line |
| CN111652842A (en) * | 2020-04-26 | 2020-09-11 | 佛山读图科技有限公司 | Real-time visual detection method and system for high-speed penicillin bottle capping production line |
| CN111882451A (en) * | 2020-08-12 | 2020-11-03 | 滨州学院 | Economic data analysis system for marine culture area |
| CN113160052A (en) * | 2021-04-01 | 2021-07-23 | 华南理工大学 | Offshore culture area image splicing method based on non-uniform precision |
| CN113160052B (en) * | 2021-04-01 | 2022-10-25 | 华南理工大学 | Offshore culture area image splicing method based on non-uniform precision |
| CN113758577A (en) * | 2021-09-09 | 2021-12-07 | 易科捷(武汉)生态科技有限公司成都分公司 | Accurate type fish identification technology system based on big data |
| CN115953725A (en) * | 2023-03-14 | 2023-04-11 | 浙江大学 | Fish egg automatic counting system based on deep learning and counting method thereof |
| CN115953725B (en) * | 2023-03-14 | 2023-05-30 | 浙江大学 | Automatic fish egg counting system and method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104966122A (en) | System for automatically counting live fishes based on machine vision | |
| CN104112370B (en) | Parking lot based on monitoring image intelligent car position recognition methods and system | |
| Zion et al. | In-vivo fish sorting by computer vision | |
| EP2948753B1 (en) | System and method for counting zooplankton | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN103674857B (en) | Based on forage detection system and the method for machine vision | |
| CN104539937B (en) | A kind of method and apparatus of camera module dust detection | |
| EP3143559B1 (en) | Concentration control of living organisms in fluid | |
| CN105318944A (en) | Rod-shaped platform chicken on-site weighing system and method | |
| Keyvani et al. | A fully-automated image processing technique to improve measurement of suspended particles and flocs by removing out-of-focus objects | |
| Kaixuan et al. | Target detection method for moving cows based on background subtraction | |
| CN106680448A (en) | Water combined-pollution biological early warning and monitoring device and testing method | |
| CN113408687B (en) | High-flux fry online counting device and method | |
| Kollis et al. | Weight estimation using image analysis and statistical modelling: A preliminary study | |
| CN112802064A (en) | Visual identification system for fishway of hydro-junction | |
| CN116019023A (en) | Electronic information management system and management method | |
| CN204594856U (en) | Contactless sandstone aggregate granularity particle shape detector | |
| CN109118540B (en) | Sturgeon rapid statistical method based on ridge line extraction | |
| Alver et al. | Automatic measurement of rotifer Brachionus plicatilis densities in first feeding tanks | |
| CN201302730Y (en) | Automatic fish fry counting system based on computer vision | |
| CN106417104A (en) | Cultured fish swimming direction detecting system and method | |
| CN109472797A (en) | Aquaculture fish three-dimensional coordinate acquisition methods based on computer vision technique | |
| CN208207889U (en) | Egg of oak silkworm counting device in a kind of agricultural breeding | |
| CN115600829A (en) | Method and device for predicting culture water quality | |
| JPH0668489B2 (en) | Aquatic animal monitoring device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for 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: 20151007 |