Bullfrog dynamic disease recognition system and method based on deep learning

Abstract

The invention relates to the technical field of bullfrog breeding, and particularly discloses a bullfrog dynamic disease recognition system and method based on deep learning, and the method comprises the steps: setting a monitoring region, setting a plurality of driving devices in the monitoring region, and driving bullfrogs in the monitoring region in a preset time period; acquiring first video information in a monitoring area in a preset time period and second video information in a feeding time period after the driving equipment is started, analyzing the first video information and the second video information, and performing disease early warning based on the jumping information and the moving information. According to the bullfrog disease early-warning method and system, diseases which can be reflected in appearance in common bullfrog diseases are judged through deep learning and recognition of pictures, and for diseases which cannot be reflected in appearance, disease early warning is carried out based on jumping information and moving information of bullfrogs in the driving and feeding processes, so that the bullfrog disease early-warning efficiency is improved. And a better bullfrog breeding management effect is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of bullfrog breeding, and in particular to a bullfrog dynamic disease recognition system and method based on deep learning. Background Art

[0002] Bullfrog farming has a long history, and disease prevention and control during the farming process has always been one of the research directions of the farming industry. At present, the method of identifying the appearance of bullfrogs to confirm diseases through deep learning of large models trained with pictures of sick bullfrogs has been applied to a certain extent.

[0003] The problem is that, on the one hand, some bullfrog diseases do not manifest themselves in appearance, making it difficult to use large models obtained through deep learning; on the other hand, the results obtained through image recognition have often already occurred, and bullfrog farming can only stop losses in a timely manner, making it difficult to provide early warnings.

[0004] In view of this, the purpose of the present invention is to provide a bullfrog dynamic disease identification system and method based on deep learning, which can provide a certain degree of early warning and identification of the dynamic state of bullfrogs and bullfrog diseases, thereby improving the efficiency of bullfrog breeding and management. Summary of the invention

[0005] The purpose of the present invention is to provide a bullfrog dynamic disease identification system and method based on deep learning to solve the following technical problems:

[0006] How to provide a certain degree of early warning and identification of bullfrog diseases based on the bullfrog's dynamic state.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] The bullfrog dynamic disease recognition method based on deep learning includes:

[0009] Setting up a monitoring area and installing a number of driving devices in the monitoring area to drive away bullfrogs in the monitoring area during a preset time period;

[0010] Acquire first video information in the monitoring area within a preset time period after the driving device is activated and second video information within a feeding time period, and analyze the first video information and the second video information to acquire a first valid image and a second valid image;

[0011] performing disease identification according to the first valid image;

[0012] The jump information and the movement information are acquired through the second effective image and a disease warning is performed based on the jump information and the movement information.

[0013] Through the above technical scheme: a method for disease identification and early warning based on image information during the driving and feeding of bullfrogs is provided. Specifically, for common diseases of bullfrogs that can be reflected in the appearance, judgment is made through deep learning and recognition of pictures. For diseases that cannot be reflected in the appearance, the jumping information and movement information of the bullfrogs during the driving and feeding process are used, and disease early warning is carried out based on the jumping information and movement information, so as to achieve better bullfrog breeding and management effects.

[0014] As a further technical solution of the present invention: the steps of acquiring the first effective image and identifying the disease according to the first effective image include:

[0015] Identify and mark complete bullfrog feature images from all video frames of the first video information and the second video information, and record the number of marks;

[0016] Selecting a number of video frames with the largest number of identical marks as first valid images;

[0017] A trained bullfrog disease recognition model is set, and the first valid image is input into the corresponding bullfrog disease recognition model, and the bullfrog disease recognition model performs disease recognition.

[0018] As a further technical solution of the present invention: the steps of obtaining the second effective image and obtaining the jump information through the second effective image include:

[0019] Acquire a video frame containing a bullfrog jumping action from all video frames of the first video information and the second video information;

[0020] taking three video frames including at least a bullfrog jumping starting point, a jumping end point and a jumping highest point as the second valid images;

[0021] The jumping curve of the current bullfrog is constructed based on the second valid image, and the number of jumping curves is recorded.

[0022] As a further technical solution of the present invention: the step of obtaining movement information through the second effective image includes:

[0023] In the same scene, selecting a plurality of groups of reference images from the second valid image;

[0024] The frog swarm is partitioned along the direction of its movement in the reference image, and the partitioned Partitions and adjacent The partitions of are merged to obtain several target partitions;

[0025] The average moving speed of the frog group in the target partition is obtained based on the time interval and moving distance of the frog group in the target partition in a set of reference images.

[0026] As a further technical solution of the present invention: the steps of disease early warning based on jump information and movement information are as follows:

[0027] By formula:

[0028]

[0029] Obtain the activity coefficient Ac of the day, where α1 is the preset first weight coefficient, α2 is the preset second weight coefficient, Ju1 is the first jump coefficient, Ju2 is the second jump coefficient, n1 is the number of non-repeated jump curves occurring in all the first video information and the second video information obtained on the day, T is the breeding time, n0 is the preset jump curve number selection function set based on the breeding time, g is the normalization function, β1 is the preset first jump weight coefficient, β2 is the preset second jump weight coefficient, γ1 is the preset first movement weight coefficient, γ2 is the preset second movement weight coefficient, Mo1 is the first movement coefficient, Mo2 is the second movement coefficient, and σ is the correction amount selection function;

[0030] The activity coefficient is continuously counted and the judgment coefficient is obtained based on historical data, and early warning of bullfrog diseases is issued based on the judgment coefficient.

[0031] Through the above technical scheme: a step process for disease warning based on jumping information and movement information is provided. Specifically, the present invention obtains a first jumping coefficient and a second jumping coefficient related to jumping through a jumping curve and the number of jumps, and statistics the jumping conditions of bullfrogs in feeding and driving states. Some diseases of bullfrogs that are not reflected in the appearance will affect the appetite or athletic ability of bullfrogs, and most diseases in the breeding process are infectious diseases. Through the identification and estimation of the overall athletic ability, the disease status of bullfrogs can be warned, thereby avoiding breeding losses caused by the large-scale spread of diseases that are not reflected in the appearance.

[0032] As a further technical solution of the present invention: the process of obtaining the first jump coefficient, the second jump coefficient, the first movement coefficient, and the second movement coefficient is as follows:

[0033] By formula:

[0034]

[0035] Obtain the first jump coefficient Ju1, the second jump coefficient Ju2 and the first movement coefficient Mo1, the second movement coefficient Mo2, where f i is the function expression of the i-th jump curve in the preset time period, t i is the starting point corresponding to the time of the i-th jump curve, is the time corresponding to the end point of the i-th jump curve, is the preset first jump curve, fj is the functional expression of the jth jump curve in the feeding period, and Set the start and end time of the preset jump curve respectively, t j is the starting point corresponding to the time of the jth jump curve, is the time corresponding to the end point of the j-th jump curve, is the preset second jump curve, and They are respectively used to set the time start point and time end point for the preset jump curve, m1 is the total number of jump curves in the preset time period, m2 is the total number of jump curves in the feeding time period, i is a natural number ranging from 1 to m1, and j is a natural number ranging from 1 to m2.

[0036] As a further technical solution of the present invention: the process of obtaining the judgment coefficient includes:

[0037] By formula:

[0038]

[0039] Get the judgment coefficient Jg of the day, where Ac is the activity coefficient of the day, Ac k is the activity coefficient of the kth control day in the historical data, N is the total number of selected control days, and τ is the preset compensation function, which is used to obtain the compensation value according to the breeding time T.

[0040] As a further technical solution of the present invention: the process of early warning of bullfrog diseases based on the judgment coefficient includes:

[0041] Compare the judgment coefficient with the preset judgment interval [Jg1, Jg2]. If Jg>Jg2, it is judged that the frog group is abnormal and an early warning is required;

[0042] If Jg<Jg2, the frog population is considered normal and no warning is needed;

[0043] If Jg falls within the judgment interval, the second jump coefficient of the feeding time period is obtained, and the second jump coefficient is compared with multiple preset safety intervals. If the second jump coefficient falls within the safety interval, no warning is required, otherwise an alarm is issued.

[0044] Through the above technical scheme: a scheme for obtaining a judgment coefficient and issuing an early warning based on the judgment coefficient is provided. Specifically, the judgment coefficient of the present invention is obtained based on the activity coefficient of the day and historical data, and can reflect the change of the activity coefficient of the day compared with the control day, so as to issue an early warning. In addition, a judgment interval is set. When the judgment coefficient falls into the judgment interval, it means that the change of the activity coefficient of the day compared with the control day is not enough to determine whether an early warning is needed. At this time, the second jump coefficient obtained during the feeding time period of the day can be used to determine whether the data of the bullfrog in the feeding status is normal, and a secondary verification can be performed, thereby improving the comprehensiveness of the early warning.

[0045] The present invention also provides a bullfrog dynamic disease identification system based on deep learning, comprising:

[0046] Monitoring module, used for video monitoring of the monitoring area;

[0047] The driving module is used to drive away the frogs;

[0048] The judgment module is used to judge bullfrog diseases and whether an early warning is needed;

[0049] The early warning module remotely notifies the management personnel when an early warning is required.

[0050] (1) The present invention uses deep learning and recognition of images to judge common bullfrog diseases that can be manifested in appearance. For diseases that cannot be manifested in appearance, the present invention uses the jumping information and movement information of the bullfrog during the driving and feeding process to provide disease warnings based on the jumping information and movement information, thereby achieving better bullfrog breeding and management effects.

[0051] (2) The present invention obtains a first jumping coefficient and a second jumping coefficient related to jumping through a jumping curve and the number of jumps, and performs statistics on the jumping conditions of bullfrogs in feeding and driving states. Some diseases of bullfrogs that are not reflected in their appearance will affect the appetite or athletic ability of bullfrogs, and most diseases in the breeding process are infectious diseases. By identifying and estimating the overall athletic ability, the disease status of bullfrogs can be warned, thereby avoiding breeding losses caused by the large-scale spread of diseases that are not reflected in their appearance.

[0052] (3) The judgment coefficient of the present invention is obtained based on the activity coefficient of the day and historical data, and can reflect the change of the activity coefficient of the day compared with the control day, so as to issue an early warning. In addition, a judgment interval is set. When the judgment coefficient falls into the judgment interval, it means that the change of the activity coefficient of the day compared with the control day is not enough to determine whether an early warning is needed. At this time, the second jump coefficient obtained during the feeding time period of the day can be used to determine whether the bullfrog data in the feeding status is normal, and a second verification can be performed, thereby improving the comprehensiveness of the early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The present invention will be further described below in conjunction with the accompanying drawings.

[0054] Figure 1 It is a flow chart of the overall steps of the present invention;

[0055] Figure 2 is a flow chart of the first effective image acquisition step of the present invention;

[0056] Figure 3 It is a flow chart of the second effective image acquisition step of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1-Figure 3 As shown, in one embodiment, a method for dynamic disease identification of bullfrog based on deep learning is provided, including:

[0059] S100, setting a monitoring area and setting a number of driving devices in the monitoring area to drive the bullfrogs in the monitoring area in a preset time period. It should be noted that the bullfrogs in the same monitoring area need to be in the same growth cycle to maintain a similar growth state;

[0060] S200, obtaining first video information in the monitoring area within a preset time period after the driving device is started and second video information within a feeding time period, and analyzing the first video information and the second video information to obtain a first valid image and a second valid image;

[0061] S300, performing disease identification according to the first valid image;

[0062] S400, obtaining jump information and movement information through the second effective image and performing disease warning based on the jump information and movement information.

[0063] In this embodiment, a method for disease identification and early warning based on image information during the driving and feeding of bullfrogs is provided. Specifically, for common diseases of bullfrogs that can be manifested in appearance, judgment is made through deep learning and recognition of pictures. For diseases that cannot be manifested in appearance, the jumping information and movement information of the bullfrogs during the driving and feeding process are used, and disease early warning is performed based on the jumping information and movement information, so as to achieve better bullfrog breeding and management effects.

[0064] The steps of acquiring a first valid image and identifying a disease according to the first valid image include:

[0065] S310, identifying and marking complete bullfrog feature images from all video frames of the first video information and the second video information, and recording the number of marks, the feature images include head images, abdomen images and back images. It should be noted that, in order to reduce the waste of computing power, an attention mechanism can be set, and the focus target can be identified before identifying and marking the complete bullfrog feature image;

[0066] S320, selecting a number of video frames with the largest number of identical marks as first valid images;

[0067] S330. Set a trained bullfrog disease recognition model. The bullfrog disease recognition model is obtained by deep learning training through common case pictures of hemorrhagic disease, crooked head disease, rotten skin disease, bloating disease, flatulence disease and erythema disease, which may cause external physical changes in bullfrogs. Input the first valid image into the corresponding bullfrog disease recognition model, and the bullfrog disease recognition model performs disease recognition and outputs the recognition result. It should be noted that a minimum number of recognitions can be set. If the number of bullfrogs with diseases recognized in the first valid image is not higher than the minimum number, no warning will be issued, thereby avoiding false alarms caused by abnormalities of individual bullfrogs.

[0068] The steps of acquiring the second effective image and acquiring the jump information through the second effective image include:

[0069] S340, acquiring a video frame containing a bullfrog jumping action from all video frames of the first video information and the second video information;

[0070] S350, taking three video frames including at least a bullfrog jumping starting point, a jumping end point, and a jumping highest point as second valid images;

[0071] S360. Construct a jumping curve of the current bullfrog based on the second valid image, and record the number of jumping curves. The jumping information includes the jumping curve and the number of jumping curves. It is worth noting that in order to avoid repeated recording of jumping curves, a recognition vector can be constructed based on the appearance of the bullfrog. After obtaining the jumping curve, the current curve is matched with the recognition vector. In this way, the same bullfrog identified in the same jumping curve in subsequent pictures can be skipped to avoid repeated recording.

[0072] The step of acquiring movement information through the second effective image comprises:

[0073] S410, in the same scene, select several groups of reference images from the second valid images. The same scene means that the valid images are selected from the same preset time period or feeding time period. In addition, the reference images are timestamped. A group of reference images consists of two images. The time interval between the two images is known through the timestamp. Obviously, the shooting angles and positions of a group of reference photos are preferably the same. If they are different, coordinate conversion is required first.

[0074] S420, partitioning the frog group along the frog group movement direction in the reference image, and dividing the partitioned frog group into Partitions and adjacent The partitions of are merged to obtain several target partitions, the value range of a is between 20-50, and is set to 30 in this embodiment. The smaller the value of a is, the more bullfrogs can be included in a target partition, and the fewer the number of target partitions is. It is necessary to ensure that the number of target partitions is sufficient to provide enough data for analysis;

[0075] S430, obtaining an average moving speed of the frog group in the target partition based on the time interval and moving distance of the frog group in the target partition in a set of reference images.

[0076] The process of disease early warning based on jump information and movement information is as follows:

[0077] By formula:

[0078]

[0079] Obtain the activity coefficient Ac of the day, wherein α1 is a preset first weight coefficient, α2 is a preset second weight coefficient, Ju1 is a first jump coefficient, Ju2 is a second jump coefficient, n1 is the number of non-repetitive jump curves occurring in all first video information and second video information obtained on the day, T is the breeding time, n0 is a preset jump curve number selection function set based on the breeding time, g is a normalization function, and the value range is between 0 and 1, β1 is a preset first jump weight coefficient, β2 is a preset second jump weight coefficient, γ1 is a preset first movement weight coefficient, γ2 is a preset second movement weight coefficient, Mo1 is a first movement coefficient, Mo2 is a second movement coefficient, σ is a correction amount selection function, preferably a comparison table function, wherein α1, α2, β1, β2 and γ1, γ2 are all constants set based on empirical data;

[0080] The activity coefficient is continuously counted and the judgment coefficient is obtained based on historical data, and early warning of bullfrog diseases is issued based on the judgment coefficient.

[0081] In this embodiment, a step process for disease warning based on jumping information and movement information is provided. Specifically, the present invention obtains a first jumping coefficient and a second jumping coefficient related to jumping through a jumping curve and the number of jumps, and statistics the jumping conditions of bullfrogs in feeding and driving states. Some diseases of bullfrogs that are not reflected in the appearance will affect the appetite or athletic ability of the bullfrogs, and most diseases in the breeding process are infectious diseases. By identifying and estimating the overall athletic ability, the disease status of the bullfrog can be warned, thereby avoiding breeding losses caused by the large-scale spread of diseases that are not reflected in the appearance.

[0082] The process of obtaining the first jump coefficient, the second jump coefficient, the first movement coefficient, and the second movement coefficient is as follows:

[0083] By formula:

[0084]

[0085] Obtain the first jump coefficient Ju1, the second jump coefficient Ju2 and the first movement coefficient Mo1, the second movement coefficient Mo2, where f i is the function expression of the i-th jump curve in the preset time period. It should be noted that the construction of the function expression takes time as the x-axis and distance as the y-axis. The starting point of the jump curve, that is, the position of the take-off action, is set to zero. i is the starting point corresponding to the time of the i-th jump curve, is the time corresponding to the end point of the i-th jump curve, is the preset first jump curve, f j is the functional expression of the jth jump curve in the feeding period, and Set the start and end time of the preset jump curve respectively, t j is the starting point corresponding to the time of the jth jump curve, is the time corresponding to the end point of the j-th jump curve, is the preset second jump curve, and They are the starting time and the ending time for the preset jump curve, respectively. m1 is the total number of jump curves in the preset time period, m2 is the total number of jump curves in the feeding time period, i is a natural number ranging from 1 to m1, and j is a natural number ranging from 1 to m2.

[0086] The process of obtaining the judgment coefficient includes:

[0087] By formula:

[0088]

[0089] Get the judgment coefficient Jg of the day, where Ac is the activity coefficient of the day, Ac k is the activity coefficient of the kth control day in the historical data, N is the total number of selected control days, τ is the preset compensation function, which is set based on historical data and is used to obtain the compensation value according to the breeding time T. The control day data is the breeding data of the past days in the selected historical data, usually set to the previous N days. If there is abnormal data in the previous N days, it can be increased or maintained.

[0090] The process of early warning of bullfrog diseases based on the judgment coefficient includes:

[0091] Compare the judgment coefficient with the preset judgment interval [Jg1, Jg2]. If Jg>Jg2, it is judged that the frog group is abnormal and an early warning is required;

[0092] If Jg<Jg2, the frog population is considered normal and no warning is needed;

[0093] If Jg falls within the judgment interval, the second jump coefficient of the feeding time period is obtained, and the second jump coefficient is compared with multiple preset safety intervals. If the second jump coefficient falls within the safety interval, no warning is required, otherwise an alarm is issued to the management personnel.

[0094] In this embodiment, a solution for obtaining a judgment coefficient and issuing an early warning based on the judgment coefficient is provided. Specifically, the judgment coefficient of the present invention is obtained based on the activity coefficient of the day and historical data, and can reflect the change of the activity coefficient of the day compared with the control day, so as to issue an early warning. In addition, a judgment interval is set. When the judgment coefficient falls into the judgment interval, it means that the change of the activity coefficient of the day compared with the control day is not enough to determine whether an early warning is needed. At this time, the second jump coefficient obtained during the feeding time period of the day can be used to determine whether the bullfrog data in the feeding status is normal, and a secondary verification can be performed to improve the comprehensiveness of the early warning.

[0095] This embodiment also provides a bullfrog dynamic disease recognition system based on deep learning, including:

[0096] Monitoring module, used for video monitoring of the monitoring area;

[0097] The driving module is used to drive away the frogs. The specific implementation method of the driving device is not limited. In this embodiment, an automatically controlled enclosure striking module is used as the driving device, which has the advantages of coexistence of vibration and sound and easy control;

[0098] The judgment module is used to judge bullfrog diseases and whether an early warning is needed;

[0099] The early warning module remotely notifies management personnel when an early warning is deemed necessary.

[0100] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for dynamic disease identification of bullfrog based on deep learning, characterized in that: The steps include: Setting up a monitoring area and installing a number of driving devices in the monitoring area to drive away bullfrogs in the monitoring area during a preset time period; Acquire first video information in the monitoring area within a preset time period after the driving device is activated and second video information within a feeding time period, and analyze the first video information and the second video information to acquire a first valid image and a second valid image; performing disease identification according to the first valid image; The jump information and the movement information are acquired through the second effective image and a disease warning is performed based on the jump information and the movement information.

2. The method for dynamic disease identification of bullfrog based on deep learning according to claim 1, characterized in that: The steps of acquiring a first valid image and identifying a disease according to the first valid image include: Identify and mark complete bullfrog feature images from all video frames of the first video information and the second video information, and record the number of marks; Selecting a number of video frames with the largest number of identical marks as first valid images; A trained bullfrog disease recognition model is set, and the first valid image is input into the corresponding bullfrog disease recognition model, and the bullfrog disease recognition model performs disease recognition.

3. The method for dynamic disease identification of bullfrog based on deep learning according to claim 1, characterized in that: The steps of acquiring the second effective image and acquiring the jump information through the second effective image include: Acquire a video frame containing a bullfrog jumping action from all video frames of the first video information and the second video information; taking three video frames including at least a bullfrog jumping starting point, a jumping end point and a jumping highest point as the second valid images; The jumping curve of the current bullfrog is constructed based on the second valid image, and the number of jumping curves is recorded.

4. The method for dynamic disease identification of bullfrog based on deep learning according to claim 3 is characterized in that: The step of acquiring movement information through the second effective image comprises: In the same scene, selecting a plurality of groups of reference images from the second valid image; In the reference image, the frogs are partitioned along their movement direction and The average moving speed of the frog group in the target partition is obtained based on the time interval and moving distance of the frog group in the target partition in a set of reference images.

5. The method for dynamic disease identification of bullfrog based on deep learning according to claim 4 is characterized in that: The process of disease early warning based on jump information and movement information is as follows: By formula: Obtain the activity coefficient Ac of the day, where α1 is the preset first weight coefficient, α2 is the preset second weight coefficient, Ju1 is the first jump coefficient, Ju2 is the second jump coefficient, n1 is the number of non-repeated jump curves occurring in all the first video information and the second video information obtained on the day, T is the breeding time, n0 is the preset jump curve number selection function set based on the breeding time, g is the normalization function, β1 is the preset first jump weight coefficient, β2 is the preset second jump weight coefficient, γ1 is the preset first movement weight coefficient, γ2 is the preset second movement weight coefficient, Mo1 is the first movement coefficient, Mo2 is the second movement coefficient, and σ is the correction amount selection function; The activity coefficient is continuously counted and the judgment coefficient is obtained based on historical data, and early warning of bullfrog diseases is issued based on the judgment coefficient.

6. The method for dynamic disease identification of bullfrog based on deep learning according to claim 5 is characterized in that: The process of obtaining the first jump coefficient, the second jump coefficient, the first movement coefficient, and the second movement coefficient is as follows: By formula: Obtain the first jump coefficient Ju1, the second jump coefficient Ju2 and the first movement coefficient Mo1, the second movement coefficient Mo2, where f i is the function expression of the i-th jump curve in the preset time period, t i is the starting point corresponding to the time of the i-th jump curve, is the time corresponding to the end point of the i-th jump curve, is the preset first jump curve, f j is the functional expression of the jth jump curve in the feeding period, and Set the start and end time of the preset jump curve respectively, t j is the starting point corresponding to the time of the jth jump curve, is the time corresponding to the end point of the j-th jump curve, is the preset second jump curve, and They are respectively used to set the time start point and time end point for the preset jump curve, m1 is the total number of jump curves in the preset time period, m2 is the total number of jump curves in the feeding time period, i is a natural number ranging from 1 to m1, and j is a natural number ranging from 1 to m2.

7. The method for dynamic disease identification of bullfrog based on deep learning according to claim 6, characterized in that: The process of obtaining the judgment coefficient includes: By formula: Get the judgment coefficient Jg of the day, where Ac is the activity coefficient of the day, Ac k is the activity coefficient of the kth control day in the historical data, N is the total number of selected control days, and τ is the preset compensation function, which is used to obtain the compensation value according to the breeding time T.

8. The method for dynamic disease identification of bullfrog based on deep learning according to claim 7 is characterized in that: The process of early warning of bullfrog diseases based on the judgment coefficient includes: Compare the judgment coefficient with the preset judgment interval [Jg1, Jg2]. If Jg>Jg2, it is judged that the frog group is abnormal and an early warning is required; If Jg<Jg2, the frog population is considered normal and no warning is needed; If Jg falls within the judgment interval, the second jump coefficient of the feeding time period is obtained, and the second jump coefficient is compared with multiple preset safety intervals. If the second jump coefficient falls within the safety interval, no warning is required, otherwise an alarm is issued.

9. A bullfrog dynamic disease identification system based on deep learning, using a bullfrog dynamic disease identification method based on deep learning as claimed in any one of claims 1 to 8, characterized in that: include: Monitoring module, used for video monitoring of the monitoring area; The driving module is used to drive away the frog swarm; The judgment module is used to judge bullfrog diseases and whether an early warning is needed; The early warning module remotely notifies management personnel when an early warning is deemed necessary.

Images