CN112184699A - Aquatic product health detection method, terminal device and storage medium - Google Patents
Aquatic product health detection method, terminal device and storage medium Download PDFInfo
- Publication number
- CN112184699A CN112184699A CN202011126337.9A CN202011126337A CN112184699A CN 112184699 A CN112184699 A CN 112184699A CN 202011126337 A CN202011126337 A CN 202011126337A CN 112184699 A CN112184699 A CN 112184699A
- Authority
- CN
- China
- Prior art keywords
- aquatic product
- liver
- percentage
- target image
- intestinal tract
- 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
- 230000036541 health Effects 0.000 title claims abstract description 70
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 210000004185 liver Anatomy 0.000 claims abstract description 86
- 210000001035 gastrointestinal tract Anatomy 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000010801 machine learning Methods 0.000 claims abstract description 32
- 210000000936 intestine Anatomy 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 20
- 210000001630 jejunum Anatomy 0.000 claims description 18
- 230000008961 swelling Effects 0.000 claims description 12
- 230000000968 intestinal effect Effects 0.000 claims description 8
- 201000010099 disease Diseases 0.000 claims description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 238000005070 sampling Methods 0.000 abstract description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000002349 favourable effect Effects 0.000 abstract description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 51
- 241000238557 Decapoda Species 0.000 description 43
- 241000251468 Actinopterygii Species 0.000 description 34
- 230000008569 process Effects 0.000 description 20
- 239000000463 material Substances 0.000 description 14
- 230000006870 function Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000003902 lesion Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 231100000915 pathological change Toxicity 0.000 description 4
- 230000036285 pathological change Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 230000001174 ascending effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 208000035143 Bacterial infection Diseases 0.000 description 1
- 241000590002 Helicobacter pylori Species 0.000 description 1
- 208000036142 Viral infection Diseases 0.000 description 1
- 241000700605 Viruses Species 0.000 description 1
- 238000009360 aquaculture Methods 0.000 description 1
- 244000144974 aquaculture Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001580 bacterial effect Effects 0.000 description 1
- 208000022362 bacterial infectious disease Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 230000001079 digestive effect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000037406 food intake Effects 0.000 description 1
- 229940037467 helicobacter pylori Drugs 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000496 pancreas Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000009385 viral infection Effects 0.000 description 1
- 230000002087 whitening effect Effects 0.000 description 1
- 238000004383 yellowing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30028—Colon; Small intestine
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30056—Liver; Hepatic
Abstract
The application is suitable for the technical field of artificial intelligence, and provides an aquatic product health detection method, terminal equipment and a storage medium, wherein the method comprises the following steps: acquiring a target image of an aquatic product; the aquatic product in the target image is in a stable state; recognizing the liver and/or the intestinal tract in the target image according to a preset machine learning model; and performing health detection on the aquatic product according to the identified liver and/or intestinal tract. The aquatic product health detection method, the terminal device and the storage medium provided by the embodiment of the application can avoid manual operation, solve the problem that the traditional aquatic product health monitoring completely depends on manual operation, are favorable for improving the sampling frequency of aquatic product health detection, improve the condition that the continuity of traditional manual statistical information is poor, and eliminate the interference of subjective factors existing in artificial observation.
Description
Technical Field
The application belongs to the technical field of artificial intelligence, and particularly relates to an aquatic product health detection method, terminal equipment and a storage medium.
Background
The aquatic products in aquaculture, such as fish, shrimp, etc., live in water, the artificial observation difficulty of their shapes, forms and habits is large, the observation and analysis of their growth rate, health condition, ingestion condition and behavior habits in the actual production process are difficult to be accurately carried out, or the qualitative description of their biological and behavioral characteristics can only be carried out by stage sampling measurement and observation. In the actual production process, the technical personnel mainly observe the fishes and the shrimps by sampling survey. For example, in the process of fish culture, a certain number of fishes in a culture pond are fished out, body indexes such as body length and body weight of the fishes are measured, the body surface of the fishes is observed, the health condition of the fishes is judged, and data recording is carried out. The existing aquatic product observation technology relying on manual operation has the following defects:
1. the operation is complicated, and the working efficiency is low;
2. the sampling quantity is limited, and the accuracy rate is low;
3. the observation frequency is low, and the information continuity is poor;
4. subjective factor interference exists in human observation, qualitative description is taken as the main factor, and quantitative analysis and statistics are difficult to realize.
Disclosure of Invention
In view of this, the embodiment of the application provides an aquatic product health detection method, a terminal device and a storage medium, so as to solve the problem that the aquatic product health observation is completely performed by manual operation at present.
According to a first aspect, an embodiment of the present application provides a method for detecting health of aquatic products, including: acquiring a target image of an aquatic product; the aquatic product in the target image is in a stable state; identifying a liver and/or an intestinal tract in the target image according to a preset machine learning model; and performing health detection on the aquatic product according to the identified liver and/or intestinal tract.
With reference to the first aspect, in some embodiments of the present application, the step of performing a health check on the aquatic product based on the identified liver and/or intestine includes: calculating the percentage of redness and color mottle in the liver, respectively; determining whether the aquatic product is healthy or unhealthy based on the percentage of redness occurring in the liver and/or the percentage of mottled color occurring in the liver.
With reference to the first aspect, in some embodiments of the present application, the step of performing health detection on the aquatic product according to the identified liver and/or intestine further includes: calculating the percentage of the intestinal tract in which the intestinal sections and the jejunum appear respectively; determining whether the aquatic product is healthy or unhealthy based on the percentage of redness and swelling in the liver, the percentage of mottled color in the liver, the percentage of broken intestine in the intestine, and/or the percentage of jejunum in the intestine.
With reference to the first aspect, in some embodiments of the present application, the step of determining the health or unhealthy of the aquatic product based on the percentage of redness occurring in the liver, the percentage of color mottle occurring in the liver, the percentage of open bowel occurring in the intestine, and/or the percentage of jejunum occurring in the intestine is: and when the percentage of the red and swollen liver, the percentage of the color mottled liver, the percentage of the broken intestine and the percentage of the jejunum in the intestinal tract do not reach the corresponding preset threshold values, determining that the aquatic product is healthy.
With reference to the first aspect, in some embodiments of the present application, the step of performing health detection on the aquatic product according to the identified liver and/or intestine further includes: when the aquatic product is determined to be unhealthy, outputting health early warning information of the aquatic product according to the percentage of redness and swelling in the liver, the percentage of mottled color in the liver, the percentage of broken intestines in the intestinal tract and/or the percentage of jejunum in the intestinal tract; the health early warning information comprises the disease types of the aquatic products and corresponding morbidity.
With reference to the first aspect, in some embodiments of the present application, after the step of acquiring a target image of a marine product and before the step of identifying a liver and/or a intestine in the target image according to a preset machine learning model, the marine product health detection method further includes: and identifying aquatic product individuals in the target image according to the machine learning model or a preset other machine learning model.
With reference to the first aspect, in some embodiments of the present application, the step of identifying the liver and/or the intestine in the target image according to a preset machine learning model is: and respectively identifying the liver and/or intestinal tract of each aquatic product individual according to the machine learning model and each identified aquatic product individual.
According to a second aspect, an embodiment of the present application provides a terminal device, including: the input unit is used for acquiring a target image of an aquatic product; the aquatic product in the target image is in a stable state; the individual identification unit is used for identifying the liver and/or the intestinal tract in the target image according to a preset machine learning model; and the detection unit is used for carrying out health detection on the aquatic product according to the identified liver and/or intestinal tract.
According to a third aspect, an embodiment of the present application provides another terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect or any embodiment of the first aspect when executing the computer program.
According to a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the method according to the first aspect or any embodiment of the first aspect.
The aquatic product health detection method, the terminal device and the storage medium provided by the embodiment of the application acquire the target image through machine vision, further recognize the liver and the intestinal tract of the aquatic product in the target image by utilizing the machine learning model, realize automatic aquatic product health detection and monitoring, and automatically acquire the image and automatically detect the health condition of the aquatic product in all weather. The aquatic product health detection method, the terminal device and the storage medium provided by the embodiment of the application can avoid manual operation, solve the problem that the traditional aquatic product health monitoring completely depends on manual operation, are favorable for improving the sampling frequency of aquatic product health detection, improve the condition that the continuity of traditional manual statistical information is poor, and eliminate the interference of subjective factors existing in artificial observation.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flow chart of a specific example of a method for detecting health of aquatic products according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of another specific example of a method for detecting the health of aquatic products according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a terminal device provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of another terminal device provided in the embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.
The embodiment of the application provides a method for detecting the health of aquatic products, and as shown in fig. 1, the method can comprise the following steps:
step S101: and acquiring a target image of the aquatic product.
Aquatic products such as fish, shrimp and the like will bounce violently in a short time just after leaving the water surface. If the machine vision analysis is carried out on the images of the fishes and shrimps just in the bouncing process, the analysis effect is not ideal due to the problems of image definition and the like. In order to improve the accuracy of identifying livers and intestinal tracts of aquatic products such as fishes and shrimps, a target image of the aquatic products in a stable state needs to be acquired.
The underwater shooting technology can be used for collecting stable images of aquatic products such as fishes, shrimps and the like, but the use cost and the maintenance cost of the underwater shooting equipment are high, the applicable scene is limited, pictures must be collected in a clear and bright water area environment, and the production scenes meeting the conditions are few. For example, the water environment for prawn culture is relatively turbid; when high-density industrial fish culture is carried out, the water environment is also cloudy, and at the moment, the underwater camera is difficult to realize the functions.
In the process that aquatic products such as fishes, shrimps and the like slowly rise in water, once the aquatic products completely leave the water surface, the fishes, shrimps and the like can be stimulated to bounce. If the material platform carrying aquatic products such as fish, shrimp and the like rises slowly and stops at the water surface, namely the water surface is half submerged or just submerged, the fish and the shrimp cannot bounce under stress and are in a quiet creeping state instead of a side lying state, the shape is stable, and the image processing and measurement work of the next step is easier.
In order to acquire a target image of an aquatic product in a stable state, in a specific embodiment, a video of the aquatic product from leaving the water surface to hovering on the water surface for a period of time can be acquired, and then the target image meeting the requirements is intercepted in the video. Specifically, a first image frame corresponding to the aquatic product rising to the water surface can be determined and collected in the video; then, taking the time of the first image frame in the video as a starting point, and intercepting a second image frame in the video according to a preset time interval, wherein the second image frame is a target image.
In the process that the material platform filled with aquatic products such as fish, shrimp and the like rises from water to the water surface, when the material platform is immersed in the water, accurate observation cannot be carried out, and the actual observation stage is to begin when the material platform is exposed out of the water surface, to leave the water surface and finish hovering, and to end when the material platform begins to descend. In the process, the fish and the shrimp can violently beat from the moment when the material platform just leaves the water surface to a certain time point in the hovering process, and the video process at the moment has less parts which can be used for machine vision observation (high-quality pictures or available frames which can be intercepted), so that the cost of data storage and transmission is increased. In practical application, the data cleaning can be completed at the front end, for example, the video recording is not performed on the ascending process of the material platform, but only the video suspended by the material platform is recorded.
Dynamic indexes such as jumping strength, duration, jumping height and the like of the fishes and shrimps directly reflect the health degree and the activity of the fishes and the shrimps, and the videos of the parts can be used for judging the health degree and the activity, but are not suitable for intercepting high-quality stable pictures for machine vision identification. The material platform ascending process can be used for judging the liveness and health degree of aquatic products.
After the material platform reaches the hovering height, or the video after the material platform reaches the hovering height for 5 seconds can be used for intercepting a target image, and subsequent work such as individual identification, counting, liver and intestinal tracts can be carried out. And the material platform stays for a short time after reaching the hovering height, and the aim is to wait for the fishes and shrimps to stop bouncing and stay in a relatively stable posture.
Aquatic products such as fish, shrimps and the like are in a quiet creeping state when the aquatic products are not away from the water surface but are about to leave the water surface. Therefore, the video that the aquatic product gradually rises to the water surface from the water can be obtained, the time of the corresponding first image frame in the video when the aquatic product rises to the water surface is taken as the starting point, and the target image is captured in the video according to the preset time interval, wherein the target image is the image that the aquatic product does not leave the water surface yet but is about to leave the water surface. The preset time interval can be determined according to the rising speed of the material platform carrying aquatic products such as fish, shrimp and the like. The image that still leaves the surface of water but will leave the surface of water to aquatic products, water height wherein is lower, even water itself is comparatively muddy, nevertheless because muddy water is very shallow, can not produce great influence to the definition of image, can not influence follow-up image analysis's process and result generally.
According to the habits of aquatic products such as fishes and shrimps, the fishes and shrimps can violently bounce after leaving the water surface, the duration is generally short, and the fishes and shrimps can still stand within 10 seconds, which is a good time for acquiring target images. In practical application, a first image frame corresponding to the aquatic product rising to the water surface can be determined and collected in a video; then, taking the time of the first image frame in the video as a starting point, and backward intercepting a second image frame in the video according to a preset time interval, wherein the second image frame is a target image of the fish and the shrimp in a stable state after leaving the water surface for a period of time. The second image frame is free of water, the image definition is good, and the second image frame cannot be influenced by turbidity of the water. The preset time interval can be determined according to the time of the fishes and shrimps after leaving the water and continuously bouncing, for example, the preset time interval is set to be 10 seconds.
The method of capturing a video and capturing an image of a target has its advantages. The video shooting time is long, wherein a large number of effective frames (pictures) can be captured to collect samples for machine learning or training, and a large number of effective samples are needed to train the work of machine vision identification, measurement and the like in the initial stage, so that the video shooting is adopted. Meanwhile, a dynamic picture is shot in the video, the bounce duration and the bounce strength (height and strength) of the fishes and the shrimps visually reflect the health state (activity) of the fishes and the shrimps, and the fishes and the shrimps are also an index for health degree evaluation, but the evaluation standard needs to be artificially quantized.
Video shooting also has the defects that the transmission, storage and data cleaning pressure caused by large data volume is large. In order to avoid the problem of overlarge video data, in practical application, the process of shooting the video can be omitted, and the target image meeting the requirements is directly acquired.
In one embodiment, the distance from the aquatic product to the water surface during the ascent of the aquatic product in the water can be detected. And when the distance from the aquatic product to the water surface is within a preset distance range, acquiring a target image of the aquatic product. Through the distance of aquatic products to the surface of water to and the distance scope of predetermineeing, can accurately catch aquatic products such as fish and shrimp and do not leave the surface of water yet but will leave the image of the surface of water.
In another embodiment, the duration of time the water product leaves the water surface may be obtained as the water product gradually rises from the water to the surface and leaves the surface. And when the duration time of the aquatic product leaving the water surface reaches a preset time threshold value, acquiring a target image of the aquatic product. Through the duration that aquatic products leave the surface of water and the time threshold of predetermineeing, can accurately catch the target image that aquatic products such as fish and shrimp are in stable state after leaving the surface of water for a period of time.
Step S102: and identifying the liver and the intestinal tract in the target image according to a preset machine learning model. Machine learning models such as neural networks and deep learning are widely applied to various fields of artificial intelligence, and the most common application scenario is classification. The nature of liver and gut identification in aquatic products is also a classification problem. The existing machine learning model is adopted and trained, so that the liver and intestinal tract of the aquatic product can be effectively identified.
In order to achieve a better image recognition effect, the following preprocessing step for the target image may be added between step S101 and step S102. Specifically, the target image can be preprocessed by adopting image processing technologies such as edge sharpening, so that the edges of the liver and the intestinal tract in the aquatic product in the target image are more prominent, and preparation is made for the next step of machine learning model identification.
In addition to pre-processing the target image, the pre-processing also includes pre-processing the video. The aquatic product health judgment needs to carry out pretreatment aiming at 'dynamic', namely, a video is cut, and only one section of 'dynamic' picture is reserved.
The machine learning model needs to be trained through a large number of samples until the output recognition accuracy reaches a preset threshold, and for this reason, a training step for the machine learning model may be added before step S102. The machine learning model with the trained and recognized accuracy reaching the standard can be applied to actual production.
Step S103: and performing health detection on the aquatic product according to the identified liver and/or intestinal tract. Specifically, the health condition of the aquatic product can be judged according to the percentage of red and swollen liver and mottled color and the percentage of broken intestine and jejunum in the intestinal tract.
The liver color of the shrimps is greatly influenced by the color of the feed, but the pathological changes can show the pathological conditions with obvious characteristics such as red swelling, mottled depth, yellowing or whitening and the like. The characteristics of the pathological changes can be described and counted on the basis of comparison with normal colors. The determination of the normal color needs to manually set a reference value, and an image of the normal color of the liver can be manually input as a standard value for comparison and reference.
The normal color of liver is dark brown or black, and the liver color changes such as redness, mottle, yellow or white in pathological changes. Redness and swelling (including liver redness and swelling of different degrees such as light, medium and deep), mostly corresponds to the digestive problems, and generally refers to the initial color of lesions of various diseases; the liver becomes lighter after the lesion is severe (e.g., the liver becomes yellow or white); in the transition phase of the lesion, the liver may develop mottled colors, such as reddish-white or reddish-yellow, and gradually turn to full-yellow or full-white. The appearance of a yellowish white color in the liver is generally indicative of organic lesions. In the present embodiment, transparent is also defined as a color, which may be defined as a lighter color of white. The thickness degree and the continuity degree of the intestinal tracts of the aquatic products are also reliable indicators for reflecting the health state of the aquatic products. Wherein the "continuity" is a main judgment index, for example, healthy shrimps normally show full intestines, i.e. a continuous black line; however, the rupture of the intestine (discontinuous, discontinuous black line) or the jejunum (disappearance of the intestinal tract, no black line) is often the manifestation of the disease of shrimps. When the health status is reduced and digestion problems or virus and bacteria infection occurs, the shrimps have the conditions of 'intestine breaking' and 'jejunum'. The larger the size of the intestinal tract, the better the intestinal tract is, and the healthy shrimp intestinal tract is generally relatively thick.
As an example, the percentage of redness and mottle in the liver, and the percentage of open and jejunum in the intestine, respectively, can be calculated; and determining whether the aquatic product is healthy or unhealthy according to the percentage of redness and swelling in the liver, the percentage of mottled color in the liver, the percentage of full intestine in the intestinal tract, the percentage of broken intestine in the intestinal tract and/or the percentage of empty intestine in the intestinal tract. Corresponding threshold values can be set for the liver redness and swelling, the liver color mottle, the full intestine, the broken intestine and the jejunum respectively, and only when the percentage of redness and swelling in the liver, the percentage of color mottle in the liver, the percentage of broken intestine in the intestinal tract and the percentage of jejunum in the intestinal tract do not reach the corresponding preset threshold values, the aquatic product health can be determined. When any percentage of the water reaches or exceeds the corresponding threshold value, the aquatic product cannot be determined to be in a healthy state.
In a specific embodiment, the percentage threshold of liver redness and swelling may be set to 10%, the percentage threshold of liver color mottle may be set to 10%, the percentage threshold of jejunum rate may be set to 15%, the percentage threshold of intestine-cutoff rate may be set to 10%, and the current health status of the aquatic product may be determined according to the calculated actual percentage.
In addition, the intestinal thickness degree can also be introduced into the aquatic product health judgment. For example, a reference value of 1 to 8 points is set manually for the degree of intestinal thickness, and it is required that the degree of intestinal thickness is 90% or more for 7 points or more, 5% or less for 5 to 7 points, and 5% or less for 5 points.
The above contents are only qualitative identification and detection aiming at the health state of the aquatic product, and in practical application, on the premise of determining that the aquatic product is unhealthy, the health early warning information of the aquatic product can be output by predicting the current disease possibly suffered by the aquatic product and the corresponding incidence probability according to the percentage of redness and swelling in the liver, the percentage of mottled color in the liver, the percentage of broken intestines in the intestinal tract and/or the percentage of empty intestines in the intestinal tract.
The shrimps in a healthy state are pure and transparent in body color, have no spots and have no turbid areas, the liver color of the shrimps is black or dark brown (the liver color of healthy shrimps is slightly changed but is mostly dark according to different feed colors), and the intestinal tracts are thick, continuous and full. When bacterial or viral infection occurs, for example, after shrimps are infected by helicobacter pylori, the stomach of the shrimps is slightly reddish in the early stage, the color of liver pancreas begins to be changed, and the intestinal tract becomes fuzzy; if conception vessel is infected to worsen, the intestinal tracts of shrimps gradually have intestinal sections or even jejunums, and the color of livers further becomes lighter and lighter; serious pathological changes can appear in the later stage of infection, shrimps are in an endangered state, the liver of the shrimps becomes white or even transparent, and the intestinal tract completely disappears.
The aquatic product health detection method shown in fig. 1 directly performs feature learning and recognition on the liver and the intestinal tract, is biased to independent recognition of each feature, such as simply extracting and labeling the liver of shrimps on the whole material table, weakens or even does not endow the concept of individual fishes and shrimps, and replaces various independent features, so that the overall function of the health monitoring method can be developed and optimized in parallel.
In addition, aquatic product individuals can be identified by using the target image, and then the body length, the liver and the intestinal characteristics can be further identified and extracted on each individual. The aquatic product health detection method shown in fig. 2 adopts the above-mentioned idea. As shown in fig. 2, after step S101, the following steps for individual identification of aquatic products are added:
step S102': and identifying aquatic product individuals in the target image according to the machine learning model or a preset other machine learning model.
Accordingly, step S102 is replaced with the following steps:
step S102': and respectively identifying the liver and/or intestinal tract of each aquatic product individual according to the machine learning model and each identified aquatic product individual.
The remaining steps of the aquatic product health detection method shown in fig. 2 are the same as those shown in fig. 1, and are not repeated herein to avoid repetition. The aquatic product health detection method shown in fig. 2 focuses on extracting, labeling and describing features of the liver and the like on the basis of realizing individual identification and individual labeling and positioning, and the overall function may be iteratively completed step by step.
The aquatic product health detection method, the terminal device and the storage medium provided by the embodiment of the application acquire the target image through machine vision, further recognize the liver and the intestinal tract of the aquatic product in the target image by utilizing the machine learning model, realize automatic aquatic product health detection and monitoring, and automatically acquire the image and automatically detect the health condition of the aquatic product in all weather. The aquatic product health detection method, the terminal device and the storage medium provided by the embodiment of the application can avoid manual operation, solve the problem that the traditional aquatic product health monitoring completely depends on manual operation, are favorable for improving the sampling frequency of aquatic product health detection, improve the condition that the continuity of traditional manual statistical information is poor, and eliminate the interference of subjective factors existing in artificial observation.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
The embodiment of the present application further provides a terminal device, as shown in fig. 3, the terminal device may include an input unit 301, an identification unit 302, and a detection unit 303.
Specifically, the input unit 301 is configured to obtain a target image of an aquatic product, where the aquatic product in the target image is in a stable state; the corresponding working process can be referred to the description of step S101 in the above method embodiment.
The identification unit 302 is configured to identify a liver and/or an intestinal tract in the target image according to a preset machine learning model; the corresponding working process can be referred to the description of step S102 and step S102 ″ in the above method embodiment.
In practical application, the recognition unit 302 may also be configured to pre-process a target image and train a machine learning model; or identifying aquatic product individuals in the target image according to the machine learning model or a preset other machine learning model.
The detection unit 303 is configured to perform health detection on the aquatic product according to the identified liver and/or intestinal tract; the corresponding working process can be referred to the description of step S103 in the above method embodiment.
Fig. 4 is a schematic diagram of another terminal device provided in an embodiment of the present application. As shown in fig. 4, the terminal device 400 of this embodiment includes: a processor 401, a memory 402, and a computer program 403, such as a water health detection program, stored in the memory 402 and executable on the processor 401. The processor 401, when executing the computer program 403, implements the steps in the above-mentioned various embodiments of the aquatic product health detection method, such as the steps S101 to S103 shown in fig. 1. Alternatively, the processor 401, when executing the computer program 403, implements the functions of the modules/units in the device embodiments, such as the functions of the input unit 301, the individual identification unit 302, and the quantity statistics unit 303 shown in fig. 3.
The computer program 403 may be partitioned into one or more modules/units that are stored in the memory 402 and executed by the processor 401 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program 403 in the terminal device 400. For example, the computer program 403 may be partitioned into a synchronization module, a summarization module, an acquisition module, a return module (a module in a virtual device).
The terminal device 400 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 401, a memory 402. Those skilled in the art will appreciate that fig. 4 is merely an example of a terminal device 400 and does not constitute a limitation of terminal device 400 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., the terminal device may also include input-output devices, network access devices, buses, etc.
The Processor 401 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 402 may be an internal storage unit of the terminal device 400, such as a hard disk or a memory of the terminal device 400. The memory 402 may also be an external storage device of the terminal device 400, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the terminal device 400. Further, the memory 402 may also include both an internal storage unit and an external storage device of the terminal device 400. The memory 402 is used for storing the computer programs and other programs and data required by the terminal device. The memory 402 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method of the embodiments described above can be realized by a computer program, which can be stored in a computer-readable storage medium and can realize the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A method for detecting the health of aquatic products is characterized by comprising the following steps:
acquiring a target image of an aquatic product; the aquatic product in the target image is in a stable state;
identifying a liver and/or an intestinal tract in the target image according to a preset machine learning model;
and performing health detection on the aquatic product according to the identified liver and/or intestinal tract.
2. The method of claim 1, wherein the step of performing the health test on the aquatic product based on the identified liver and/or intestine comprises:
calculating the percentage of redness and color mottle in the liver, respectively;
determining whether the aquatic product is healthy or unhealthy based on the percentage of redness occurring in the liver and/or the percentage of mottled color occurring in the liver.
3. The method of claim 2, wherein the step of performing the health test on the aquatic product based on the identified liver and/or intestine further comprises:
calculating the percentage of the intestinal tract in which the intestinal sections and the jejunum appear respectively;
determining whether the aquatic product is healthy or unhealthy based on the percentage of redness and swelling in the liver, the percentage of mottled color in the liver, the percentage of broken intestine in the intestine, and/or the percentage of jejunum in the intestine.
4. The aquatic product health detecting method according to claim 3, wherein the step of determining whether the aquatic product is healthy or unhealthy based on the percentage of redness occurring in the liver, the percentage of mottled color occurring in the liver, the percentage of intestinal rupture occurring in the intestine, and/or the percentage of jejunum occurring in the intestine is:
and when the percentage of the red and swollen liver, the percentage of the color mottled liver, the percentage of the broken intestine and the percentage of the jejunum in the intestinal tract do not reach the corresponding preset threshold values, determining that the aquatic product is healthy.
5. The method of claim 4, wherein the step of performing the health test on the aquatic product based on the identified liver and/or intestine further comprises:
when the aquatic product is determined to be unhealthy, outputting health early warning information of the aquatic product according to the percentage of redness and swelling in the liver, the percentage of mottled color in the liver, the percentage of broken intestines in the intestinal tract and/or the percentage of jejunum in the intestinal tract; the health early warning information comprises the disease types of the aquatic products and corresponding morbidity.
6. The aquatic product health detecting method of claim 5, wherein after the step of acquiring the target image of the aquatic product and before the step of identifying the liver and/or the intestinal tract in the target image according to a preset machine learning model, the aquatic product health detecting method further comprises:
and identifying aquatic product individuals in the target image according to the machine learning model or a preset other machine learning model.
7. The aquatic product health detection method according to claim 6, wherein the step of identifying the liver and/or the intestinal tract in the target image according to a preset machine learning model comprises:
and respectively identifying the liver and/or intestinal tract of each aquatic product individual according to the machine learning model and each identified aquatic product individual.
8. A terminal device, comprising:
the input unit is used for acquiring a target image of an aquatic product; the aquatic product in the target image is in a stable state;
the identification unit is used for identifying the liver and/or the intestinal tract in the target image according to a preset machine learning model;
and the detection unit is used for carrying out health detection on the aquatic product according to the identified liver and/or intestinal tract.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011126337.9A CN112184699A (en) | 2020-10-20 | 2020-10-20 | Aquatic product health detection method, terminal device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011126337.9A CN112184699A (en) | 2020-10-20 | 2020-10-20 | Aquatic product health detection method, terminal device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112184699A true CN112184699A (en) | 2021-01-05 |
Family
ID=73922384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011126337.9A Pending CN112184699A (en) | 2020-10-20 | 2020-10-20 | Aquatic product health detection method, terminal device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112184699A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112841099A (en) * | 2021-03-19 | 2021-05-28 | 东营市阔海水产科技有限公司 | Detection apparatus for detect shrimp head pathological change based on image |
| CN112884763A (en) * | 2021-03-19 | 2021-06-01 | 东营市阔海水产科技有限公司 | Prawn head heterochrosis detection method, terminal device and readable storage medium |
| CN112907566A (en) * | 2021-03-19 | 2021-06-04 | 东营市阔海水产科技有限公司 | Prawn eye disease detection method, terminal device and storage medium |
| CN112967349A (en) * | 2021-04-02 | 2021-06-15 | 青岛丰禾星普科技有限公司 | Foam-based aquaculture monitoring and early warning method, terminal equipment and readable storage medium |
| CN113052114A (en) * | 2021-04-02 | 2021-06-29 | 东营市阔海水产科技有限公司 | Dead shrimp identification method, terminal device and readable storage medium |
| CN115130859A (en) * | 2022-06-28 | 2022-09-30 | 华采科技(北京)有限公司 | Aquatic product quality management informatization method, system, device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109591982A (en) * | 2018-12-29 | 2019-04-09 | 浙江大学 | A kind of no worker monitor underwater culture robot |
| CN111062929A (en) * | 2019-12-20 | 2020-04-24 | 周升志 | Intelligent analysis and diagnosis system for livestock and poultry disease pictures through software design |
| CN111242920A (en) * | 2020-01-10 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Biological tissue image detection method, device, equipment and medium |
-
2020
- 2020-10-20 CN CN202011126337.9A patent/CN112184699A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109591982A (en) * | 2018-12-29 | 2019-04-09 | 浙江大学 | A kind of no worker monitor underwater culture robot |
| CN111062929A (en) * | 2019-12-20 | 2020-04-24 | 周升志 | Intelligent analysis and diagnosis system for livestock and poultry disease pictures through software design |
| CN111242920A (en) * | 2020-01-10 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Biological tissue image detection method, device, equipment and medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112841099A (en) * | 2021-03-19 | 2021-05-28 | 东营市阔海水产科技有限公司 | Detection apparatus for detect shrimp head pathological change based on image |
| CN112884763A (en) * | 2021-03-19 | 2021-06-01 | 东营市阔海水产科技有限公司 | Prawn head heterochrosis detection method, terminal device and readable storage medium |
| CN112907566A (en) * | 2021-03-19 | 2021-06-04 | 东营市阔海水产科技有限公司 | Prawn eye disease detection method, terminal device and storage medium |
| CN112967349A (en) * | 2021-04-02 | 2021-06-15 | 青岛丰禾星普科技有限公司 | Foam-based aquaculture monitoring and early warning method, terminal equipment and readable storage medium |
| CN113052114A (en) * | 2021-04-02 | 2021-06-29 | 东营市阔海水产科技有限公司 | Dead shrimp identification method, terminal device and readable storage medium |
| CN115130859A (en) * | 2022-06-28 | 2022-09-30 | 华采科技(北京)有限公司 | Aquatic product quality management informatization method, system, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112184699A (en) | Aquatic product health detection method, terminal device and storage medium | |
| CN112232977A (en) | Aquatic product cultivation evaluation method, terminal device and storage medium | |
| CN112232978B (en) | Aquatic product length and weight detection method, terminal equipment and storage medium | |
| CN112257564B (en) | Aquatic product quantity statistical method, terminal equipment and storage medium | |
| CN111178197B (en) | Mass R-CNN and Soft-NMS fusion based group-fed adherent pig example segmentation method | |
| JP6503414B2 (en) | Apparatus and method for determining crustaceans from images | |
| Rosen et al. | DeepVision: a stereo camera system provides highly accurate counts and lengths of fish passing inside a trawl | |
| CN111406693A (en) | Marine ranch fishery resource maintenance effect evaluation method based on bionic sea eels | |
| CN110532899B (en) | Sow antenatal behavior classification method and system based on thermal imaging | |
| CN108596237A (en) | A kind of endoscopic polyp of colon sorting technique of LCI laser based on color and blood vessel | |
| CN109086696B (en) | Abnormal behavior detection method and device, electronic equipment and storage medium | |
| CN115861721B (en) | Livestock and poultry breeding spraying equipment state identification method based on image data | |
| CN111696114A (en) | Method and device for identifying hunger degree of penaeus vannamei based on underwater imaging analysis | |
| CN114898405B (en) | Portable broiler chicken anomaly monitoring system based on edge calculation | |
| Muñoz-Benavent et al. | Impact evaluation of deep learning on image segmentation for automatic bluefin tuna sizing | |
| CN112461342B (en) | Aquatic product weighing method, terminal equipment and storage medium | |
| Lai et al. | Automatic measuring shrimp body length using CNN and an underwater imaging system | |
| CN110956198A (en) | Visual weight measuring method for monocular camera | |
| CN109118540B (en) | Sturgeon rapid statistical method based on ridge line extraction | |
| Rao et al. | Computer aided shrimp disease diagnosis in aquaculture | |
| CN116152718A (en) | Intelligent observation device and method for prawn culture | |
| CN115512215A (en) | Underwater biological monitoring method and device and storage medium | |
| CN115578423A (en) | Fish key point detection, individual tracking and biomass estimation method and system based on deep learning | |
| CN112215107A (en) | Pig behavior identification method and device, electronic equipment and storage medium | |
| Hashisho et al. | AI-assisted Automated Pipeline for Length Estimation, Visual Assessment of the Digestive Tract and Counting of Shrimp in Aquaculture Production. |
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: 20210105 |