CN110796197A - Fish seed identification method and system - Google Patents
Fish seed identification method and system Download PDFInfo
- Publication number
- CN110796197A CN110796197A CN201911041081.9A CN201911041081A CN110796197A CN 110796197 A CN110796197 A CN 110796197A CN 201911041081 A CN201911041081 A CN 201911041081A CN 110796197 A CN110796197 A CN 110796197A
- Authority
- CN
- China
- Prior art keywords
- fish
- detected
- image
- identification
- layer
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a fish identification method and a system, which are applied to the technical field of aquatic product identification and solve the problems that in the prior art, identification can only be carried out manually, the efficiency is low, the labor intensity is high, and the identification result is inaccurate, wherein the method comprises the steps of obtaining an image of fish to be detected; inputting the image into a pre-trained fish species recognition model to extract the characteristic information of the image, and recognizing the fish to be detected according to the characteristic information to obtain a fish species recognition result of the fish to be detected; and outputting a fish species identification result.
Description
Technical Field
The invention relates to the technical field of aquatic product identification, in particular to a fish species identification method and system.
Background
China is a fishery big country and also a world-level aquaculture big country. China is the only country in the world with aquaculture yield higher than the fishing amount of aquatic products. The total culture yield of China accounts for more than seven percent of the aquaculture yield of the world, and the sum of the mariculture area and the freshwater culture area can reach more than 8500 hectares. Aquaculture is one of the important sources of national economy in China.
No matter mariculture and freshwater aquaculture, in order to increase the market price of the cultured fishes, the maximum economic benefit is ensured to the maximum extent, and an important process is carried out before pretreatment and deep processing of the cultured fishes: the fish is identified.
In the related art, the method of manual identification is mainly adopted in the process of classifying cultured fishes, but the method has low efficiency and high labor intensity, and fatigue is easily caused by long-time judgment of people with eyes, so that the identification result is inaccurate.
Disclosure of Invention
In view of the above, the present invention provides a fish identification method and system to overcome at least some of the problems in the related art.
In order to solve the technical problems, the invention adopts the following technical scheme:
in a first aspect, a fish species identification method includes:
acquiring an image of a fish to be detected;
inputting the image into a pre-trained fish species recognition model to extract the characteristic information of the image, and recognizing the fish to be detected according to the characteristic information to obtain a fish species recognition result of the fish to be detected;
and outputting the fish species identification result.
Optionally, after the image of the fish to be detected is obtained, the method further includes: and preprocessing the images to ensure that the formats of the images of the fishes to be detected are consistent, wherein the formats of the images comprise a color mode and an image size.
Optionally, before the obtaining of the image of the fish to be detected, the method further includes:
and transmitting the fish to be detected to an image acquisition area so as to acquire the image through image acquisition equipment of the image acquisition area, wherein when the fish to be detected is multiple, the distance between the fish to be detected is larger than a preset distance.
Optionally, the fish species identification model is a convolutional neural network model, and the convolutional neural network model includes:
an input layer;
the convolution layer is connected with the input layer and is a small-dimension convolution kernel layer;
a pooling layer connected to the convolutional layer, the pooling layer being a maximum pooling layer;
a fully connected layer connected to the pooled layer.
Optionally, the method further includes:
an activation function layer, wherein the activation function layer is a ReLU nonlinear activation function.
Optionally, the method further includes:
acquiring training images, wherein the training images comprise images of different types of fish, images of the same type of fish in different postures and images of the same type of fish in different angles;
and training to obtain the fish species recognition model by adopting the training image.
Optionally, the method further includes:
and counting the identification result to obtain the number of the identified fishes to be detected, the identified types of the fishes to be detected and the number of the fishes to be detected of various types in a preset time period.
In a second aspect, a fish species identification device includes:
the acquisition module is used for acquiring an image of the fish to be detected;
the recognition module is used for inputting the image into a pre-trained fish species recognition model so as to extract the characteristic information of the image and recognize the fish to be detected according to the characteristic information to obtain a fish species recognition result of the fish to be detected;
and the output module is used for outputting the fish species identification result.
In a third aspect, a fish species identification system includes:
the image acquisition equipment is arranged above the image acquisition area and used for acquiring an image of the fish to be detected entering the image acquisition area;
the fish identification equipment is used for acquiring an image of the fish to be detected and identifying the image based on a convolutional neural network to obtain an identification result, wherein the identification result comprises the fish to which the fish to be detected belongs; and outputting the recognition result.
Optionally, the method further includes:
and the conveying device is used for conveying the fish to be detected to the image acquisition equipment, wherein when the fish to be detected is multiple, the distance between the fish to be detected is greater than the preset distance.
Optionally, the method further includes:
and the storage equipment is used for storing the image in real time and sending the image to the fish identification equipment.
In a fourth aspect, a storage medium stores a computer program which, when executed by a processor, implements the fish species identification method according to any one of the first aspect of the invention.
By adopting the technical scheme, the invention can realize the following technical effects:
in the application, the image of the fish to be detected is firstly acquired, then the image is input into the fish species recognition model trained in advance so as to extract the characteristic information of the image, the fish to be detected is recognized according to the characteristic information, the fish species recognition result of the fish to be detected is obtained, and the fish species recognition result is output. So, only acquire the image of the fish that awaits measuring to through the fish species recognition model of training in advance, alright discern the fish that awaits measuring, for the mode of manual sorting among the prior art, efficiency is higher, has saved the manpower.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a fish identification method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a fish identification method according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram of a fish identification device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a fish identification device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
Examples
Fig. 1 is a schematic flow chart of a fish identification method according to an embodiment of the present invention. As shown in fig. 1, the present embodiment provides a fish identification method, including:
The image of the fish to be detected can be acquired in real time through the arranged camera device, and can also be uploaded through images acquired by a user in other equipment, so that the image of the fish to be detected is acquired.
And 102, inputting the image into a pre-trained fish species recognition model to extract the characteristic information of the image, and recognizing the fish to be detected according to the characteristic information to obtain a fish species recognition result of the fish to be detected.
In some embodiments, the pre-trained fish species identification model may be a convolutional neural network model, which is trained by a training image set having a plurality of fish species, so that the convolutional neural network can identify fish species. The convolutional neural network firstly extracts the characteristic information in the image, and then identifies the fish to be detected according to the extracted characteristic information, so that a fish species identification result of the fish to be detected is obtained.
And step 103, outputting a fish species identification result.
In some embodiments, the fish species identification result can be output through the PC.
In the application, the image of the fish to be detected is firstly acquired, then the image is input into the fish species recognition model trained in advance so as to extract the characteristic information of the image, the fish to be detected is recognized according to the characteristic information, the fish species recognition result of the fish to be detected is obtained, and the fish species recognition result is output. So, only acquire the image of the fish that awaits measuring to through the fish species recognition model of training in advance, alright discern the fish that awaits measuring, for the mode of manual sorting among the prior art, efficiency is higher, has saved the manpower.
Fig. 2 is a schematic flow chart of a fish identification method according to another embodiment of the present invention. As shown in fig. 2, the present embodiment provides a fish identification method, including:
In some embodiments, the fish to be detected may be of different types, such as carp, silver carp, bighead carp, large yellow croaker, saury, and the like, and the fish to be detected may be transmitted by a conveyor belt and kept for 1s after being transported to a designated image acquisition area, so that the image acquisition device acquires a clear and complete image. In the process that the conveying belt conveys the fishes to be detected to the appointed picture collecting area, the fishes to be detected are manually separated into single fishes, namely, a plurality of fishes to be detected are sequentially conveyed to the picture collecting area in a mode of being arranged in an approximate straight line and spaced at a certain distance, so that the situation that the plurality of fishes appear in the same picture, the recognition difficulty is increased, and the recognition result is inaccurate can be avoided.
In the process of transporting the fish by the conveyor belt according to the approximate straight line, the fish is considered and estimated according to the particle model, and the specific posture of the fish to be detected has no requirement or limitation. In addition, the conveying speed of the conveying belt should be kept at a constant speed, and the speed is not too fast or too slow, so that the situations of fish body drifting, too low efficiency and the like are prevented.
In some embodiments, the image of the fish to be detected can be acquired in real time through the set image acquisition device, and can also be uploaded through images acquired by a user in other devices, so that the image of the fish to be detected is acquired.
The image acquisition equipment can adopt a USB3.0 color CMOS industrial camera to acquire color picture data of the fish to be detected in the picture acquisition area. The picture acquisition area is against white, the length of the whole test area is 40cm, the width is 40cm, and the color industrial camera is located 0.5m above the conveyor belt. The resolution of the color industrial camera is 0.4Mp, the frame rate is 539fps, a CMOS photosensitive component and a global shutter are adopted, and the operating environment parameters are as follows: temperature-5 ℃ to 45 ℃, humidity: 20% -80% does not coagulate. It will be appreciated that the holding time, the size of the test area, and the distance between the image capture device and the conveyor belt may be set according to the actual situation, and other dimensions or times are within the scope of the present application.
In some embodiments, the image is preprocessed in a processing mode including color mode unification, image size scaling and the like, then the image is sent to a convolutional neural network for feature extraction and layer-by-layer optimization, and the features of the fish to be detected are stored.
In the image preprocessing process, RGB format conversion is carried out on the image, and the input format of the fish species recognition model is ensured to be uniform and meet the requirements. The picture is scaled to 224 x 224, a convolutional neural network is used for feature extraction, features are continuously optimized, dimensionality is reduced, and then feature vectors are stored.
And 204, inputting the image into a pre-trained fish species recognition model to extract the characteristic information of the image, and recognizing the fish to be detected according to the characteristic information to obtain a fish species recognition result of the fish to be detected.
In some embodiments, the pre-trained fish species identification model may be a convolutional neural network model, which is trained by a training image set having a plurality of fish species, so that the convolutional neural network can identify fish species. The convolutional neural network firstly extracts the characteristic information in the image, and then identifies the fish to be detected according to the extracted characteristic information, so that a fish species identification result of the fish to be detected is obtained.
The characteristic information of the image may include gray information and two-dimensional distribution information of RGB spatial pixels.
Specifically, a training image set of the convolutional neural network model is a large number of multi-pose, multi-position and multi-angle pictures for pre-judging fishes. After the training data set is preprocessed, data enhancement processing is carried out to improve the generalization capability of the model. The data enhancement processing may include, among other things, random rotation of the image, random cropping, scaling, noising, and so forth.
Generally, the convolutional neural network model mainly comprises 3 parts: input layer, convolution layer, full connection layer. The input layer is used for inputting color images, namely an RGB three-channel matrix; in the convolutional layer, the number of channels is equal to the number of convolution kernels, and feature extraction and dimension reduction are carried out on input; the core of the full-connection layer is a matrix vector dot product which is transformed from one feature space to another feature space.
Compared with the prior art, the two layers of 5 × 5 convolution kernels reduce convolution operation, double convolution operation is carried out on a training image unit, the number of convolution layers can be deepened, and a fish species identification model can obtain a finer feature extraction effect.
The pooling layer is the largest pooling layer, and the feature map is compressed through the pooling layer, so that the complexity of the convolutional neural network is simplified while the main features are extracted.
In addition, the convolutional neural network further comprises an activation function layer, and the activation function layer is a ReLU nonlinear activation function. The Relu activation function is adopted, the convergence problem of a deep network is solved, the Relu function can be sparsely expressed, the training time of the model is shortened, and the performance of the algorithm is improved.
The adopted classifier is Softmax, and is a classifier oriented to multiple classifications based on a Softmax function, and is suitable for the situation that the classes are mutually exclusive.
The pre-training mode of the fish species recognition model can be as follows:
acquiring training images, wherein the training images comprise images of different types of fish, images of the same type of fish in different postures and images of the same type of fish in different angles;
and training by adopting a training image to obtain a fish species recognition model.
In order to further determine whether the fish species identification model trained in the above steps is accurate, the inventor further provides a verification method, specifically, the verification method includes:
acquiring a test image;
testing the fish species identification model according to the test image;
if the accuracy of the test result reaches a preset value, taking the fish species identification model as a pre-trained fish species identification model;
and if the accuracy of the test result does not reach the preset value, continuing training the fish species identification model.
Through the verification of the fish species identification model, the identification accuracy of the model in application can be determined, and the fish species identification model with high identification accuracy is used for identification, so that a more accurate result can be obtained.
And step 205, outputting a fish species identification result.
In some embodiments, the fish species identification result can be output through the PC.
And step 206, counting the identification results to obtain the number of the identified fishes to be detected, the identified types of the fishes to be detected and the number of the fishes to be detected of each type in a preset time period.
In some embodiments, the identification result of the fish to be tested is transmitted to the PC, and data statistics is performed on the identification data every 0.5 hour after the test is started, including identification of the number of the fishes, identification of the types of the fishes, identification of the number of the types of the fishes, average time of the identification, identification accuracy, identification list, and the like.
Fig. 3 is a schematic structural diagram of a fish identification device according to an embodiment of the present invention. As shown in fig. 3, the present embodiment provides a fingerling identification device, including:
an obtaining module 301, configured to obtain an image of a fish to be detected;
the identification module 302 is configured to input the image into a pre-trained fish species identification model to extract feature information of the image, and identify the fish to be detected according to the feature information to obtain a fish species identification result of the fish to be detected;
and the output module 303 is used for outputting the fish identification result.
For a specific implementation of this embodiment, reference may be made to the fish identification method and the related descriptions in the method embodiments described in the foregoing embodiments, and details are not described herein again.
Fig. 4 is a schematic structural diagram of a fish identification system according to an embodiment of the present application. Referring to fig. 4, an embodiment of the present application provides a fish identification system, including:
the image acquisition equipment 401 is arranged above the image acquisition area and is used for acquiring an image of the fish to be detected entering the image acquisition area;
the fish identification equipment 402 is used for acquiring an image of the fish to be detected and identifying the image based on a convolutional neural network to obtain an identification result, wherein the identification result comprises the fish to which the fish to be detected belongs; and outputting the recognition result.
Optionally, the method further includes:
and a conveying device 403, configured to convey multiple fish to be detected to the image acquisition device, where the distance between the fish to be detected is greater than the preset distance.
Optionally, the method further includes:
a storage device 404 for storing the images in real time and sending the images to the fish identification device
For a specific implementation of this embodiment, reference may be made to the fish identification method and the related descriptions in the method embodiments described in the foregoing embodiments, and details are not described herein again.
An embodiment of the present invention provides a storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps in the fish identification method are implemented.
For a specific implementation of this embodiment, reference may be made to the relevant description in the above embodiment of the fish identification method, and details are not described here.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by suitable instruction execution devices. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A fish species identification method is characterized by comprising the following steps:
acquiring an image of a fish to be detected;
inputting the image into a pre-trained fish species recognition model to extract the characteristic information of the image, and recognizing the fish to be detected according to the characteristic information to obtain a fish species recognition result of the fish to be detected;
and outputting the fish species identification result.
2. The method of claim 1, wherein after the obtaining the image of the fish to be tested, further comprising: and preprocessing the images to ensure that the formats of the images of the fishes to be detected are consistent, wherein the formats of the images comprise a color mode and an image size.
3. The method of claim 1, wherein before the obtaining the image of the fish to be tested, further comprising:
and transmitting the fish to be detected to an image acquisition area so as to acquire the image through image acquisition equipment of the image acquisition area, wherein when the fish to be detected is multiple, the distance between the fish to be detected is larger than a preset distance.
4. The method of claim 1, wherein the fish species identification model is a convolutional neural network model, the convolutional neural network model comprising:
an input layer;
the convolution layer is connected with the input layer and is a small-dimension convolution kernel layer;
a pooling layer connected to the convolutional layer, the pooling layer being a maximum pooling layer;
a fully connected layer connected to the pooled layer.
5. The method of claim 4, further comprising:
an activation function layer, wherein the activation function layer is a ReLU nonlinear activation function.
6. The method of claim 1, further comprising:
acquiring training images, wherein the training images comprise images of different types of fish, images of the same type of fish in different postures and images of the same type of fish in different angles;
and training to obtain the fish species recognition model by adopting the training image.
7. The method of claim 1, further comprising:
and counting the identification result to obtain the number of the identified fishes to be detected, the identified types of the fishes to be detected and the number of the fishes to be detected of various types in a preset time period.
8. A fingerling identification system, comprising:
the image acquisition equipment is arranged above the image acquisition area and used for acquiring an image of the fish to be detected entering the image acquisition area;
the fish identification equipment is used for acquiring an image of the fish to be detected and identifying the image based on a convolutional neural network to obtain an identification result, wherein the identification result comprises the fish to which the fish to be detected belongs; and outputting the recognition result.
9. The system of claim 8, further comprising:
and the conveying device is used for conveying the fish to be detected to the image acquisition equipment, wherein when the fish to be detected is multiple, the distance between the fish to be detected is greater than the preset distance.
10. The system of claim 8, further comprising:
and the storage equipment is used for storing the image in real time and sending the image to the fish identification equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911041081.9A CN110796197A (en) | 2019-10-30 | 2019-10-30 | Fish seed identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911041081.9A CN110796197A (en) | 2019-10-30 | 2019-10-30 | Fish seed identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110796197A true CN110796197A (en) | 2020-02-14 |
Family
ID=69441892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911041081.9A Pending CN110796197A (en) | 2019-10-30 | 2019-10-30 | Fish seed identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110796197A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112906510A (en) * | 2021-02-02 | 2021-06-04 | 中国水利水电科学研究院 | Fishery resource statistical method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921058A (en) * | 2018-06-19 | 2018-11-30 | 厦门大学 | Fish identification method, medium, terminal device and device based on deep learning |
-
2019
- 2019-10-30 CN CN201911041081.9A patent/CN110796197A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921058A (en) * | 2018-06-19 | 2018-11-30 | 厦门大学 | Fish identification method, medium, terminal device and device based on deep learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112906510A (en) * | 2021-02-02 | 2021-06-04 | 中国水利水电科学研究院 | Fishery resource statistical method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fernandes et al. | Deep Learning image segmentation for extraction of fish body measurements and prediction of body weight and carcass traits in Nile tilapia | |
| Yang et al. | Computer vision models in intelligent aquaculture with emphasis on fish detection and behavior analysis: a review | |
| Zion | The use of computer vision technologies in aquaculture–a review | |
| Hu et al. | Fish species classification by color, texture and multi-class support vector machine using computer vision | |
| An et al. | Application of computer vision in fish intelligent feeding system—A review | |
| Hao et al. | The measurement of fish size by machine vision-a review | |
| Hu et al. | Real-time nondestructive fish behavior detecting in mixed polyculture system using deep-learning and low-cost devices | |
| US20220071180A1 (en) | Analysis and sorting in aquaculture | |
| WO2019245722A1 (en) | Sea lice detection and classification in an aquaculture environment | |
| US20230071265A1 (en) | Quantifying plant infestation by estimating the number of biological objects on leaves, by convolutional neural networks that use training images obtained by a semi-supervised approach | |
| Navotas et al. | Fish identification and freshness classification through image processing using artificial neural network | |
| CN112232978B (en) | Aquatic product length and weight detection method, terminal equipment and storage medium | |
| Ibrahim Aliyu et al. | A proposed fish counting algorithm using digital image processing technique | |
| Wang et al. | Fast detection of cannibalism behavior of juvenile fish based on deep learning | |
| Kaewchote et al. | Image recognition method using Local Binary Pattern and the Random forest classifier to count post larvae shrimp | |
| US20220004760A1 (en) | Splash detection for surface splash scoring | |
| Isa et al. | CNN transfer learning of shrimp detection for underwater vision system | |
| Liu et al. | Deep residual convolutional neural network based on hybrid attention mechanism for ecological monitoring of marine fishery | |
| Zhang et al. | Intelligent fish feeding based on machine vision: A review | |
| CN110796197A (en) | Fish seed identification method and system | |
| Muñoz-Benavent et al. | Impact evaluation of deep learning on image segmentation for automatic bluefin tuna sizing | |
| Adhikary | Fish species identification on low resolution-a study with enhanced super resolution generative adversarial network (esrgan), yolo and vgg-16 | |
| CN113284164A (en) | Shrimp swarm automatic counting method and device, electronic equipment and storage medium | |
| Han et al. | Mask_LaC R-CNN for measuring morphological features of fish | |
| CN116830162A (en) | Systems, methods, and computer-executable code for organism quantification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200214 |