A shrimp group living body health monitoring method based on a large model

Abstract

The present application relates to the field of living health monitoring, and more particularly to a method for intelligent identification of shrimp group living health monitoring based on a large model, the present application continuously acquires shrimp group images in a breeding pond, extracts active distribution characteristics of the shrimp group, analyzes active offset characteristic values of the shrimp group in combination with swimming speed of shrimp clusters, marks the shrimp group, and in response to the marking result, analyzes the shrimp group, including: identifying a trajectory swimming dispersion stage of the shrimp group, and analyzing a plurality of shrimp clusters in the trajectory swimming dispersion stage; acquiring swimming trajectories of a plurality of remaining shrimp clusters, determining trajectory trend values of the remaining shrimp clusters, matching the trajectory trend values with a trajectory trend reference range, and determining whether to isolate the remaining shrimp clusters, the present application improves the accuracy of shrimp group health monitoring on the basis of real-time and continuous monitoring of the shrimp group, and through hierarchical management of the shrimp clusters, reduces the influence of shrimp clusters that may have health problems on the overall shrimp group, and ensures the overall health level of the shrimp group.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of living body health monitoring, and in particular to a method for intelligent identification of shrimp group living body health monitoring based on a large model. BACKGROUND

[0002] With the continuous expansion of shrimp farming scale and the improvement of the degree of intensification, the problems such as frequent shrimp group diseases and difficult real-time monitoring of growth status are increasingly prominent, which seriously restricts the sustainable development of the industry. At the same time, in view of the characteristics of high-density intensive shrimp culture, such as high density, closed environment, high risk of disease, etc., a real-time, accurate and automated health monitoring system is needed to ensure the health of shrimp groups and improve the efficiency of aquaculture.

[0003] Chinese patent application publication No. CN119646725A discloses a fish health condition monitoring device based on fish behavior analysis, relating to aquaculture technology, comprising a water surface unit, a water unit, a water bottom unit and a data processing center. The water surface unit, the water unit and the water bottom unit are respectively installed on the water surface, in the water and at the water bottom of the culture pond. The water surface unit, the water unit and the water bottom unit respectively collect real-time data of the water surface, in the water and at the water bottom of the culture pond. The data processing center receives the real-time data and processes the real-time data through a Stacking stacked learning model to judge the health condition of the fish group in the culture pond and the position where the abnormality occurs. When the fish group in a certain position in the judged area behaves abnormally, an abnormal alarm signal is generated. The application also discloses a fish health condition monitoring method based on fish behavior analysis. The application can realize real-time detection and early warning of the health condition of the fish group, effectively improving the risk resistance and economic benefits of the culture process.

[0004] However, the prior art still has the following problems,

[0005] The traditional method for detecting the health of shrimp groups mainly relies on manual inspection and sampling detection. The former relies on the relevant experience of the breeding personnel, and the latter has problems such as insufficient sample representativeness and long detection period, which cannot realize real-time and continuous monitoring of shrimp groups. At the same time, shrimp bodies with health problems cannot be effectively treated in a timely manner. SUMMARY

[0006] Therefore, the present application provides a method for intelligent identification of shrimp group living body health monitoring based on a large model to overcome the problems in the prior art that shrimp groups cannot be monitored in real time and continuously, and shrimp bodies with health problems cannot be effectively treated in a timely manner.

[0007] To achieve the above purpose, the present application provides a method for intelligent identification of shrimp group living body health monitoring based on a large model, which comprises:

[0008] Continuously acquire images of the shrimp group in the culture pond to extract active distribution characteristics of the shrimp group, the active distribution characteristics including a swimming offset shrimp cluster density and a swimming depth variation amount of a corresponding shrimp cluster;

[0009] According to the active distribution characteristics and the swimming speed of the shrimp cluster, an active offset characteristic value of the shrimp group is analyzed to label the shrimp group;

[0010] In response to the labeling result, the shrimp group is analyzed, including,

[0011] A trajectory swimming dispersion stage of the shrimp group is identified, and a plurality of shrimp clusters in the trajectory swimming dispersion stage are analyzed, including acquiring respective branch trajectories corresponding to the trajectory swimming dispersion stage, extracting swimming data of a corresponding minimum shrimp cluster in each branch trajectory, calling a horizontal shortest distance of the corresponding minimum shrimp cluster from an obstacle in the culture pond and a stacking amount of the minimum shrimp cluster to evaluate a health abnormality characteristic coefficient of the minimum shrimp cluster to determine whether to clean the minimum shrimp cluster.

[0012] Swimming trajectories of a plurality of remaining shrimp clusters are acquired, trajectory tendency values of each of the remaining shrimp clusters are determined, and the trajectory tendency values are matched with a trajectory tendency reference range to determine whether to isolate the remaining shrimp clusters.

[0013] Further, the process of analyzing the active offset characteristic value of the shrimp group according to the active distribution characteristics and the swimming speed of the shrimp cluster includes,

[0014] a ratio of the swimming offset shrimp cluster density to a shrimp cluster density threshold value and a ratio of the swimming depth variation amount of the corresponding shrimp cluster to a swimming depth variation threshold value are summed as a first active offset feature;

[0015] a ratio of the swimming speed threshold value to the swimming speed of the shrimp cluster is taken as a second active offset feature;

[0016] The first active offset feature and the second active offset feature are weighted and summed to determine the active offset characteristic value.

[0017] Further, the labeling of the shrimp group includes,

[0018] If the active offset characteristic value of the shrimp group is greater than or equal to an active offset characteristic threshold value, the shrimp group is labeled with a high offset degree label.

[0019] Further, in response to the labeling result, the shrimp group is analyzed, including,

[0020] If any shrimp group is labeled with a high offset degree label, the shrimp group is analyzed.

[0021] Further, the process of identifying the trajectory swimming discrete phase of the shrimp group comprises,

[0022] calling the shrimp group image to identify the swimming trajectory of the shrimp group;

[0023] if the swimming trajectory meets the trajectory discrete condition, determining that the shrimp group enters the trajectory swimming discrete phase;

[0024] wherein the trajectory meets the trajectory forming condition includes the appearance of two or more swimming trajectories and the maintenance of a predetermined time length.

[0025] Further, the process of evaluating the health abnormality representation coefficient of the minimum shrimp cluster comprises,

[0026] the ratio of the horizontal minimum distance threshold value to the horizontal minimum distance of the minimum shrimp cluster from the obstacle in the culture pond as the first health abnormality feature;

[0027] the ratio of the stacking amount of the minimum shrimp cluster to the stacking amount threshold value as the second health abnormality feature;

[0028] the sum of the first health abnormality feature and the second health abnormality feature as the health abnormality representation coefficient.

[0029] Further, the process of determining whether to clean the minimum shrimp cluster comprises,

[0030] if the health abnormality representation coefficient of the minimum shrimp cluster is greater than or equal to the health abnormality representation coefficient threshold value, determining to clean the minimum shrimp cluster.

[0031] Further, the process of determining the trajectory tendency value of each of the remaining shrimp clusters comprises,

[0032] generating a plurality of vectors corresponding to the swimming trajectories of a plurality of remaining shrimp clusters, respectively;

[0033] selecting a plurality of remaining target shrimp clusters whose vector directions of the vectors remain unchanged within a predetermined time;

[0034] determining the distance shortening amount of each of the remaining target shrimp clusters from the minimum shrimp cluster within the predetermined time;

[0035] taking the distance shortening amount as the trajectory tendency value.

[0036] Further, the process of determining whether to isolate the remaining shrimp cluster comprises,

[0037] if the trajectory tendency value of any remaining target shrimp cluster is not within the trajectory tendency reference range, determining to isolate the remaining target shrimp cluster;

[0038] wherein the trajectory tendency reference range is pre-set.

[0039] Further, also comprising, setting a prompt signal in response to the minimum shrimp cluster being cleaned up or the remaining target shrimp cluster being isolated.

[0040] In response to the minimum shrimp cluster being cleaned up or the remaining target shrimp cluster being isolated, a prompt signal is sent out.

[0041] Compared with the prior art, the present application continuously acquires the image of the shrimp group in the culture pond to extract the active distribution characteristics of the shrimp group; the active distribution characteristics are combined with the swimming speed of the shrimp cluster to analyze the active offset characteristic value of the shrimp group, and the shrimp group is marked; in response to the marking result, the shrimp group is analyzed, including: identifying the trajectory swimming dispersion stage of the shrimp group, and analyzing a plurality of shrimp clusters in the trajectory swimming dispersion stage; acquiring the swimming trajectory of a plurality of remaining shrimp clusters, determining the trajectory trend value of each remaining shrimp cluster, and matching the trajectory trend value with a trajectory trend reference range to determine whether to isolate the remaining shrimp cluster; or, adjusting the monitoring frequency of the shrimp group based on the active offset characteristic value. The present application improves the accuracy of health monitoring of the shrimp group on the basis of real-time and continuous monitoring of the shrimp group, and reduces the influence of shrimp clusters that may have health problems on the overall shrimp group through hierarchical management of the shrimp clusters, thereby ensuring the overall health level of the shrimp group.

[0042] In particular, based on the factors such as the decline of the physiological function and the decrease of the environmental adaptability of the sick and weak shrimp that have health problems, the sick and weak shrimp separate from the shrimp group and form separate swimming trajectories, the swimming active distribution of the shrimp group in the culture pond is considered, the density of the shrimp cluster that deviates from the swimming of the shrimp group reflects the degree of damage of the sick and weak shrimp to the overall shrimp group; compared with the normal shrimp group that is evenly distributed in the upper layer or the flow area of the water body, the sick and weak shrimp usually gather in the deep parts such as the bottom and the corner of the culture pond, so the change amount of the swimming depth of the shrimp cluster can reflect the degree of physical exhaustion and the degree of decline of the swimming ability of the sick and weak shrimp, and the swimming speed can directly reflect the vitality level of the shrimp cluster, therefore, the present application can comprehensively capture the activity and health status of the overall shrimp group by combining the above characteristics, the active offset characteristic value is used to represent the severity of the dispersion of the swimming trajectory of the shrimp group and the degree of deviation of the swimming trajectory of the dispersed shrimp cluster, data support is provided for subsequent marking of the shrimp group, and the shrimp group is adaptively analyzed, the present application improves the accuracy of health monitoring of the shrimp group on the basis of real-time and continuous monitoring of the shrimp group, and reduces the influence of shrimp clusters that may have health problems on the overall shrimp group through hierarchical management of the shrimp clusters, thereby ensuring the overall health level of the shrimp group.

[0043] Especially, the application carries out differential treatment monitoring for shrimp groups provided with high offset degree labels, focuses on analyzing the discrete swimming trajectories of the whole shrimp group, locks high-risk weak areas, realizes dynamic positioning of weak shrimp clusters and preferentially carries out waste cleaning and other treatments. Weak shrimps are unable to resist water flow impact due to their physical exhaustion or damaged nerves, are easily pushed to the vicinity of obstacles, shorten the horizontal distance from the obstacles in the culture pond, and can also reflect the severity of the disease of weak shrimps. Weak shrimps are usually piled together due to decreased activity or avoidance, forming multi-layer stacking, which reflects the risk degree of cross-infection of weak shrimp clusters, and reflects the deterioration degree of the local environment. Therefore, the application evaluates the health abnormality characteristic coefficient by the shortest horizontal distance of the smallest shrimp cluster from the obstacle and the corresponding stacking amount to represent the disease deterioration degree of the smallest shrimp cluster, and provides data support for subsequent determination of whether to clean the smallest shrimp cluster. The application improves the accuracy of health monitoring of the shrimp group on the basis of real-time and continuous monitoring of the shrimp group, and reduces the influence of shrimp clusters with possible health problems on the whole shrimp group through hierarchical management of the shrimp clusters, thereby ensuring the health level of the whole shrimp group.

[0044] Especially, the application also considers the health risks of the remaining shrimp clusters on the basis of locking high-risk weak areas, identifies abnormal approaching behaviors of the remaining shrimp clusters to the smallest shrimp cluster, analyzes and verifies the abnormal approaching behaviors, excludes random swimming interference through the vector direction corresponding to the swimming trajectory of the remaining shrimp clusters, accurately identifies the abnormal approaching behaviors, and quantifies the initiative of the remaining shrimp clusters to approach the smallest shrimp cluster and the attraction degree of other factors such as stress secretions induced by weak shrimps or release of chemical signals by pathogens to other shrimp clusters through the distance shortening amount between the remaining shrimp clusters and the smallest shrimp cluster, thereby reducing the risk of cross-infection of the remaining shrimp clusters. Therefore, the application isolates the remaining shrimp clusters in time based on the above considerations. The application improves the accuracy of health monitoring of the shrimp group on the basis of real-time and continuous monitoring of the shrimp group, and reduces the influence of shrimp clusters with possible health problems on the whole shrimp group through hierarchical management of the shrimp clusters, thereby ensuring the health level of the whole shrimp group. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 The figure is a step schematic diagram of the intelligent identification shrimp group living body health monitoring method based on a large model of the application embodiment;

[0046] Figure 2 The figure is a logic determination diagram for marking the shrimp group of the application embodiment;

[0047] Figure 3 The figure is a logic determination diagram for determining whether to clean the smallest shrimp cluster of the application embodiment;

[0048] Figure 4A logic decision diagram for determining whether to isolate the rest of the shrimp cluster for the inventive embodiment. DETAILED DESCRIPTION

[0049] In order to make the objects and advantages of the present application clearer, the following further describes the present application with reference to the embodiments; it should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0050] The preferred embodiments of the present application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0051] It should be noted that in the description of the present application, the terms indicating the direction or positional relationship of "inner" and the like are based on the direction or positional relationship shown in the drawings, which is only for the convenience of description, and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application.

[0052] In addition, it should also be noted that in the description of the present application, unless otherwise explicitly specified and limited, the term "mounting" should be understood broadly. Those skilled in the art can understand the specific meaning of the above-mentioned term in the present application according to the specific circumstances.

[0053] Please refer to Figure 1 As shown in the figure, it is a step schematic diagram of the intelligent identification shrimp group living body health monitoring method based on a large model of the embodiment of the present application, the intelligent identification shrimp group living body health monitoring method based on a large model of the embodiment of the present application comprises:

[0054] Step S1, continuously acquiring shrimp group images in the culture pond to extract active distribution features of the shrimp group, wherein the active distribution features include a moving offset shrimp cluster density and a corresponding shrimp cluster moving depth change amount;

[0055] Step S2, analyzing active offset representation values of the shrimp group according to the active distribution features combined with the moving speed of the shrimp cluster to label the shrimp group;

[0056] Step S3, in response to the labeling result, analyzing the shrimp group, including,

[0057] identify a trajectory swimming discrete phase of the shrimp group, analyze a plurality of shrimp clusters in the trajectory swimming discrete phase, including, obtaining each branch trajectory corresponding to the trajectory swimming discrete phase, extracting swimming data of a corresponding minimum shrimp cluster in each branch trajectory, calling a horizontal shortest distance of the corresponding minimum shrimp cluster from an obstacle in the culture pond and a stacking amount of the minimum shrimp cluster, to evaluate a health abnormality representation coefficient of the minimum shrimp cluster, to determine whether to clean the minimum shrimp cluster;

[0058] obtain swimming trajectories of a plurality of remaining shrimp clusters, determine a trajectory trend value of each of the remaining shrimp clusters, and match the trajectory trend value with a trajectory trend reference range, to determine whether to isolate the remaining shrimp clusters.

[0059] Specifically, the way of obtaining the shrimp group image in the culture pond is not specifically limited, as long as the shrimp group image can be collected, and a plurality of rotating cameras can be installed on the inner wall of the culture pond, the camera view angle can be adjusted through the holder to cover a larger collection range, and a dirt-proof cover is matched to prevent algae from adhering to the camera and affecting the collection of the shrimp group image. Of course, other ways of obtaining the shrimp group image can also be used.

[0060] Among them, the spatial-temporal features of the shrimp group, such as the swimming offset shrimp cluster density and the stacking amount, can be learned from the image through the ViT (Vision Transformer) model.

[0061] Specifically, the process of analyzing the active offset representation value of the shrimp group according to the active distribution feature and the swimming speed of the shrimp cluster includes,

[0062] the ratio of the swimming offset shrimp cluster density to the shrimp cluster density threshold value and the ratio of the swimming depth change amount of the corresponding shrimp cluster to the swimming depth change amount threshold value are summed as the first active offset feature;

[0063] the ratio of the swimming speed threshold value to the swimming speed of the shrimp cluster is taken as the second active offset feature;

[0064] the first active offset feature and the second active offset feature are weighted and summed to determine the active offset representation value.

[0065] Specifically, in the actual swimming process of the shrimp group, the shrimp clusters with swimming deviation and the corresponding quantity range in the shrimp group can intuitively reflect the health risk degree of the whole shrimp group, and the depth change of the swimming position corresponding to the shrimp cluster with swimming deviation can clearly reflect the severity of the health damage of the corresponding shrimp cluster, therefore, in the implementation, the active distribution characteristics, i.e., the density of the shrimp cluster with swimming deviation and the swimming depth change amount of the corresponding shrimp cluster, are preferentially considered, so a slightly higher weight is given to the first active deviation feature calculated based on the active distribution characteristics, therefore, when the weighted sum is performed, the weight of the first active deviation feature is set to 0.6, and the weight of the second active deviation feature is set to 0.4.

[0066] In the embodiment, the purpose of setting the shrimp cluster density threshold value, the swimming depth change amount threshold value and the swimming speed threshold value is to represent the severity of the dispersion of the swimming trajectory of the shrimp group, and further represent the severity of the health damage of the weak shrimp cluster, the historical shrimp cluster density data, the swimming depth change amount historical data and the swimming speed historical data of the shrimp group are extracted by calling the historical shrimp group images in the plurality of breeding ponds, the shrimp cluster density mean value, the swimming depth change amount mean value and the swimming speed mean value are solved, based on the purpose of setting the above three threshold values, the shrimp cluster density threshold value is determined as the product of the shrimp cluster density mean value and the density deviation coefficient, the swimming depth change amount threshold value is determined as the product of the swimming depth change amount mean value and the depth deviation coefficient, and the swimming speed threshold value is determined as the product of the swimming speed mean value and the speed deviation coefficient, wherein the density deviation coefficient is selected in the interval [1.15, 1.2], the depth deviation coefficient is selected in the interval [1.2, 1.25], and the speed deviation coefficient is selected in the interval [0.9, 0.95].

[0067] Specifically, please refer to Figure 2 The logic judgment diagram for marking the shrimp group by the embodiment of the application is shown in the figure, marking the shrimp group includes,

[0068] If the active deviation representation value of the shrimp group is greater than or equal to the active deviation representation threshold value, a high deviation degree label is set for the shrimp group;

[0069] If the active deviation representation value of the shrimp group is less than the active deviation representation threshold value, the shrimp group does not need to be marked.

[0070] The active deviation representation threshold value is selected in the interval [1.69, 1.74]

[0071] Specifically, based on the factors such as the decline of physiological functions and the decrease of environmental adaptability of the sick and weak shrimps, the shrimps appear to be separated from the shrimp group and form separate swimming tracks, the active distribution of the shrimp group in the swimming process in the culture pond is considered, the density of the shrimps in the swimming deviation of the separated shrimp group reflects the damage degree of the sick and weak shrimps to the whole shrimp group; compared with the normal shrimp group uniformly distributed in the upper layer or the flow area of the water body, the sick and weak shrimps usually gather in the deep places such as the bottom and corners of the culture pond, so the change amount of the swimming depth of the shrimp cluster can reflect the degree of physical exhaustion and the decrease of swimming ability of the sick and weak shrimps, and the swimming speed can directly reflect the activity level of the shrimp cluster.

[0072] Therefore, by combining the above features, the activity and health status of the whole shrimp group can be comprehensively captured, the active deviation characteristic value is used to represent the severity of the dispersion of the swimming track of the shrimp group, and the deviation degree of the swimming track of the dispersed shrimp cluster, data support is provided for subsequent marking of the shrimp group, and then the shrimp group is adaptively analyzed, on the basis of real-time and continuous monitoring of the shrimp group, the accuracy of the health monitoring of the shrimp group is improved, and by grading management of the shrimp cluster, the influence of the shrimp cluster that may have health problems on the whole shrimp group is reduced, and the health level of the whole shrimp group is ensured.

[0073] Specifically, in response to the marking result, the shrimp group is analyzed, including,

[0074] If any shrimp group is set with a high deviation degree label, the shrimp group is analyzed.

[0075] Specifically, the process of identifying the track swimming dispersion stage of the shrimp group includes,

[0076] The shrimp group image is called to identify the swimming track of the shrimp group.

[0077] If the swimming track meets the track dispersion condition, it is determined that the shrimp group enters the track swimming dispersion stage.

[0078] The track meets the track forming condition, which includes two or more swimming tracks appearing and maintaining for a predetermined time length.

[0079] It can be understood that due to the influence of shrimp species and breeding environment factors, the swimming speed of shrimps is different, for example, the normal swimming speed of South American white shrimp is 5cm / s-15cm / s, when the density of the shrimp group in the breeding environment is >300 tails / m³, the swimming speed of the South American white shrimp will decrease to 3cm / s-8cm / s due to limited activity, therefore, in order to intuitively observe the swimming deviation of the shrimp group, the predetermined time length maintained by the swimming track is selected within the interval [30s, 1min].

[0080] Specifically, the process of evaluating the health abnormality representation coefficient of the minimum shrimp cluster includes,

[0081] a ratio of the horizontal minimum distance threshold value to the horizontal minimum distance of the minimum shrimp cluster from the obstacle in the aquaculture pond as a first health abnormality feature;

[0082] a ratio of the stacking amount of the minimum shrimp cluster to the stacking amount threshold value as a second health abnormality feature;

[0083] a sum of the first health abnormality feature and the second health abnormality feature as the health abnormality representation coefficient.

[0084] In the embodiment, the purpose of setting the horizontal minimum distance threshold value and the stacking amount threshold value is to represent the severity of the disease deterioration of the weak shrimp. By obtaining historical shrimp group images in the aquaculture pond corresponding to a plurality of disease conditions, historical data of the horizontal minimum distance of the minimum shrimp cluster from the obstacle in the aquaculture pond and historical data of the stacking amount of the minimum shrimp cluster are extracted, the mean value of the horizontal minimum distance and the mean value of the stacking amount are solved, and based on the purpose of setting the two threshold values, the horizontal minimum distance threshold value is determined as the product of the mean value of the horizontal minimum distance and the distance deviation coefficient, and the stacking amount threshold value is determined as the product of the mean value of the stacking amount and the stacking deviation coefficient, wherein the distance deviation coefficient is selected in the interval [0.9, 0.95], and the stacking deviation coefficient is selected in the interval [1.1, 1.15];

[0085] wherein the stacking height of the minimum shrimp cluster accumulated together is the stacking amount.

[0086] Specifically, the present application differentiates the shrimp group with a high deviation degree label, focuses on analyzing the discrete swimming trajectory of the whole shrimp group, locks the high-risk weak area, realizes the dynamic positioning of the weak shrimp cluster and prioritizes the waste removal and other treatments. The weak shrimp is easily pushed to the vicinity of the obstacle, such as the corner of the pond, the sewage outlet, etc., because it cannot resist the water flow impact due to its physical exhaustion or nerve damage, which shortens the horizontal distance between the weak shrimp and the obstacle in the aquaculture pond, and also reflects the severity of the disease of the weak shrimp. The weak shrimp is usually accumulated together due to the decline in vitality or avoidance, forming multiple layers of stacking, which reflects the risk degree of cross-infection of the weak shrimp cluster and the deterioration degree of the local environment. Therefore, the present application evaluates the health abnormality representation coefficient by the horizontal minimum distance of the minimum shrimp cluster from the obstacle and the corresponding stacking amount to represent the disease deterioration degree of the minimum shrimp cluster, which provides data support for subsequent determination of whether to remove the waste of the minimum shrimp cluster. The present application improves the accuracy of health monitoring of the shrimp group on the basis of real-time and continuous monitoring of the shrimp group, and reduces the influence of the shrimp cluster with possible health problems on the whole shrimp group through hierarchical management of the shrimp cluster, thereby ensuring the health level of the whole shrimp group.

[0087] Specifically, please refer toFigure 3 As shown, it is a logical determination diagram for determining whether to clean up the minimum shrimp cluster, and determining whether to clean up the minimum shrimp cluster, comprising,

[0088] If the health abnormality characteristic coefficient of the minimum shrimp cluster is greater than or equal to the health abnormality characteristic coefficient threshold value, it is determined that the minimum shrimp cluster is cleaned up;

[0089] If the health abnormality characteristic coefficient of the minimum shrimp cluster is less than the health abnormality characteristic coefficient threshold value, it is determined that the minimum shrimp cluster does not need to be cleaned up.

[0090] The health abnormality characteristic coefficient threshold value is selected in the interval [2.18, 2.24].

[0091] Specifically, the process of determining the trajectory tendency value of each of the remaining shrimp cluster comprises,

[0092] Generating a plurality of vectors corresponding to the swimming trajectory of a plurality of remaining shrimp clusters;

[0093] Selecting a plurality of remaining target shrimp clusters whose vector directions remain unchanged within a predetermined time;

[0094] Determining the distance reduction amount of each of the remaining target shrimp clusters from the minimum shrimp cluster within the predetermined time;

[0095] The distance reduction amount is taken as the trajectory tendency value.

[0096] It can be understood that the new sick shrimp with disease has a short infection time, a slight disease, and a significant decrease in activity. The old sick shrimp with disease will avoid the old sick shrimp due to sensory signals, and then swim in other directions relative to the direction of the old sick shrimp. However, as the infection time increases, the disease becomes more serious, and the high-density farming or farming pool environment will force the new sick shrimp and the old sick shrimp to passively gather in the same area. Therefore, in this embodiment, the distance reduction between the remaining shrimp cluster maintaining single direction swimming and the minimum shrimp cluster is considered to reflect the trajectory convergence degree of the new sick shrimp and the old sick shrimp, and then the disease deterioration degree of the new sick shrimp is evaluated.

[0097] In this embodiment, the difference between the distance of the remaining target shrimp cluster from the minimum shrimp cluster at the beginning of the predetermined time and the distance of the remaining target shrimp cluster from the minimum shrimp cluster at the end of the predetermined time is taken as the distance reduction amount;

[0098] Since the swimming speed of the sick shrimp with disease will decrease accordingly, in order to make the collected data representative, the predetermined time is selected in the interval [7min, 10min].

[0099] Specifically, please refer toFigure 4 As shown, it is a logical determination diagram for determining whether to isolate the rest of the shrimp clusters, and determining whether to isolate the rest of the shrimp clusters, comprising,

[0100] If the trajectory trend value of any of the rest of the target shrimp clusters is not in the trajectory trend reference range, it is determined that the rest of the target shrimp clusters are isolated;

[0101] If the trajectory trend value of any of the rest of the target shrimp clusters is in the trajectory trend reference range, it is determined that the rest of the target shrimp clusters do not need to be isolated;

[0102] The trajectory trend reference range is pre-set.

[0103] In this embodiment, by obtaining a plurality of related shrimp group historical data of the disease, a plurality of distance reduction historical data of the rest of the target shrimp clusters from the minimum shrimp cluster are determined, the maximum value and the minimum value of the distance reduction historical data are determined, the maximum value is taken as the upper limit of the interval of the trajectory trend reference range, and the minimum value is taken as the lower limit of the interval of the trajectory trend reference range, wherein the trajectory trend reference range is a closed region.

[0104] Specifically, on the basis of locking the high-risk sick area, the present application also considers the health risk that the rest of the shrimp clusters may exist, identifies the abnormal approaching behavior of the rest of the shrimp clusters to the minimum shrimp cluster, analyzes and verifies the abnormal approaching behavior, excludes random wandering interference through the vector direction corresponding to the swimming trajectory of the rest of the shrimp clusters, accurately identifies the abnormal approaching behavior, and further quantifies the distance reduction between the rest of the shrimp clusters and the minimum shrimp cluster, that is, the initiative of the rest of the shrimp clusters to approach the minimum shrimp cluster, that is, the sick shrimp group, and the degree of attraction of other shrimp clusters due to the stress secretion of sick shrimp or the release of chemical signals by pathogens, so that the rest of the shrimp clusters may have a cross-infection risk. Therefore, the present application isolates the rest of the shrimp clusters in time based on the above considerations, and further improves the accuracy of the health monitoring of the shrimp group on the basis of real-time and continuous monitoring of the shrimp group, and reduces the influence of the shrimp cluster that may have health problems on the whole shrimp group, and ensures the health level of the whole shrimp group.

[0105] Specifically, it also includes setting a response prompt signal,

[0106] In response to the minimum shrimp cluster being cleared or the rest of the target shrimp clusters being isolated, a prompt signal is sent.

[0107] If the shrimp group living body health monitoring method based on the large model intelligent identification of the present application is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application or the part that essentially contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0108] So far, the technical solution of the present application has been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to related technical features without deviating from the principles of the present application, and the technical solutions after these changes or replacements will fall within the protection scope of the present application.

Claims

1. A method for intelligent identification and live health monitoring of shrimp populations based on a large model, characterized in that, include: Images of shrimp groups in the aquaculture pond are continuously acquired to extract the active distribution features of the shrimp groups, including the density of shrimp groups that move away and the change in the swimming depth of the corresponding shrimp groups. The active distribution characteristics are combined with the swimming speed of the shrimp cluster to analyze the active offset characterization value of the shrimp group, so as to mark the shrimp group; The shrimp population is analyzed in response to the labeling results. include, Identify the discrete phases of the shrimp population's trajectory swimming, and analyze several shrimp clusters in the discrete phases of the trajectory swimming, including obtaining each branch trajectory corresponding to the discrete phases of the trajectory swimming, extracting the swimming data of the smallest shrimp cluster in each branch trajectory, calling the shortest horizontal distance of the smallest shrimp cluster from the obstacle in the breeding pond and the stacking amount of the smallest shrimp cluster, to evaluate the health abnormality characterization coefficient of the smallest shrimp cluster, and to determine whether the smallest shrimp cluster should be removed. The swimming trajectories of several other shrimp clusters are obtained, the trajectory trend value of each other shrimp cluster is determined, and the trajectory trend reference range is matched to determine whether the other shrimp clusters should be isolated. The process of analyzing the activity shift characterization value of the shrimp group based on the active distribution characteristics and the swimming speed of the shrimp cluster includes: The sum of the ratio of the density of the shrimp clusters that have shifted to the shrimp cluster density threshold and the ratio of the change in the swimming depth of the corresponding shrimp cluster to the change in the swimming depth threshold is used as the first active shift feature. The ratio of the swimming speed threshold to the swimming speed of the shrimp cluster is used as the second active offset feature; The active offset feature is determined by weighted summation of the first active offset feature and the second active offset feature; The process of determining the trajectory directional values ​​of each of the remaining shrimp clusters includes, Generate several vectors corresponding to the swimming trajectories of the remaining shrimp clusters; Select several other target shrimp clusters whose vector directions remain unchanged within a predetermined time period; Determine the amount by which the distance between each of the remaining target shrimp clusters and the smallest shrimp cluster is shortened within the predetermined time period; The amount of distance reduction is used as the trajectory trend value.

2. The intelligent identification and live health monitoring method for shrimp groups based on a large model according to claim 1, characterized in that, Marking the shrimp population includes, If the active offset characterization value of the shrimp population is greater than or equal to the active offset characterization threshold, then a high offset label is set for the shrimp population.

3. The method for intelligent identification and live health monitoring of shrimp groups based on a large model according to claim 2, characterized in that, In response to the labeling results, the shrimp population is analyzed, including, If any shrimp population is labeled with a high degree of offset, then the shrimp population is analyzed.

4. The intelligent identification and live health monitoring method for shrimp groups based on a large model according to claim 1, characterized in that, The process of identifying the discrete stages of the shrimp group's trajectory swimming. include, Images of the shrimp swarm are retrieved to identify the swimming trajectories of the shrimp swarm; If the swimming trajectory meets the trajectory discrete condition, then the shrimp group is determined to have entered the trajectory swimming discrete stage; The trajectory meets the trajectory forming conditions, which include the occurrence of two or more swimming trajectories and their maintenance for a predetermined duration.

5. The intelligent identification and live health monitoring method for shrimp groups based on a large model according to claim 1, characterized in that, The process of evaluating the health abnormality characterization coefficient of the minimum shrimp cluster includes, The ratio of the horizontal shortest distance threshold to the horizontal shortest distance from the smallest shrimp cluster to the obstacle in the aquaculture pond is used as the first abnormal health feature. The ratio of the minimum shrimp cluster stack size to the stack size threshold is used as the second health anomaly feature. The sum of the first health abnormality feature and the second health abnormality feature is used as the health abnormality characterization coefficient.

6. The intelligent identification and live health monitoring method for shrimp groups based on a large model according to claim 5, characterized in that, Determine whether to remove the smallest shrimp cluster. include, If the health abnormality characterization coefficient of the smallest shrimp cluster is greater than or equal to the health abnormality characterization coefficient threshold, then the smallest shrimp cluster is determined to be discarded.

7. The intelligent identification and live health monitoring method for shrimp groups based on a large model according to claim 1, characterized in that, Determining whether to isolate the remaining shrimp clusters includes, If the trajectory trend value of any other target shrimp cluster is not within the trajectory trend reference range, then it is determined that the other target shrimp clusters should be isolated. The trajectory tendency reference range is preset.

8. The intelligent identification and live health monitoring method for shrimp groups based on a large model according to claim 1, characterized in that, This also includes setting response prompt signals. A warning signal is issued in response to the elimination of the smallest shrimp cluster or the isolation of the remaining target shrimp clusters.

Images