Intelligent training method for chicken flocks

Abstract

The invention provides an intelligent training method for chicken flocks, which comprises the following steps: controlling array sound pickups in a target breeding area to collect chicken flock timbre information in real time, analyzing the chicken flock timbre information to obtain abnormal timbre information, and determining the sound pickups receiving the abnormal timbre information as positioning sound pickups; determining an abnormal positioning area according to the pickup positioning strategy and the positioning pickup, calling historical video data collected by an area collection device corresponding to the abnormal positioning area based on the abnormal timbre information, and determining an abnormal individual according to the historical video data; controlling the mobile monitoring device to move to the abnormal positioning area, and controlling the mobile monitoring device to move to the position of the abnormal individual according to the real-time video data acquired by the area acquisition device; when it is determined that the mobile monitoring device is located at the position of the abnormal individual, the mobile monitoring device is controlled to lock and monitor the abnormal individual, and locked monitoring video data is obtained and sent to the management end.

Description

Technical Field

[0001] The invention relates to data processing technology, and in particular to an intelligent training method for chickens. Background Art

[0002] In modern farms, tens of thousands of chickens are raised in a vast area. This large-scale farming method improves production efficiency and economic benefits. However, as the number of chickens increases, the health problems of individual chickens become difficult to monitor. In particular, when a part of the flock exhibits abnormal behavior or health problems, it may have adverse effects on the entire flock.

[0003] Traditional farming monitoring methods mainly rely on manual inspections and video surveillance. However, these methods have obvious shortcomings. Manual inspections are time-consuming and labor-intensive, and are limited by the staff's energy and observation ability. It is difficult to monitor the entire farming area in real time. Although video surveillance can cover a larger area, it needs to process massive amounts of data, resulting in a slow speed in identifying abnormal individuals. In addition, as the chickens continue to move, abnormal conditions captured in the image data can easily be missed.

[0004] Therefore, how to quickly identify and locate abnormal individuals so that timely intervention measures can be taken has become an urgent problem that needs to be solved. Summary of the invention

[0005] The present invention provides an intelligent training method for chickens, which can quickly identify and locate abnormal individuals so as to take intervention measures in time.

[0006] A first aspect of the present invention provides an intelligent training method for chickens, comprising: Controlling the array microphones in the target breeding area to collect the timbre information of the chicken flock in real time, analyzing the timbre information of the chicken flock to obtain abnormal timbre information, and determining the microphone that receives the abnormal timbre information as the positioning microphone; According to the sound pickup positioning strategy and the positioning pickup, an abnormal positioning area is determined, and based on the abnormal timbre information, historical video data collected by a region collection device corresponding to the abnormal positioning area is retrieved, and abnormal individuals are determined according to the historical video data; Controlling the mobile monitoring device to move to the abnormal location area, and controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device; When it is determined that the mobile monitoring device is at the location of the abnormal individual, the mobile monitoring device is controlled to lock and monitor the abnormal individual, and the obtained locked monitoring video data is sent to the management end.

[0007] Optionally, in a possible implementation manner of the first aspect, determining the abnormal positioning area according to the sound pickup positioning strategy and the positioning pickup includes: Acquire the abnormal decibel value corresponding to the abnormal timbre information received by each of the positioning pickups, sort the positioning pickups in descending order based on the abnormal decibel value, and obtain a sound pickup selection sequence; Selecting the first positioning pickup in the sound picking sequence as the core pickup, determining the second positioning pickup in the sound picking sequence as the first auxiliary pickup, and selecting the third positioning pickup in the sound picking sequence as the second auxiliary pickup; An abnormality positioning area is determined based on the core pickup, the first auxiliary pickup, and the second auxiliary pickup.

[0008] Optionally, in a possible implementation manner of the first aspect, determining the abnormality positioning area according to the core microphone, the first auxiliary microphone, and the second auxiliary microphone includes: Connecting the core position of the core pickup and the first position of the first auxiliary pickup to obtain a core positioning line; Acquire the abnormal decibel value of the core pickup as the core decibel value, and determine the abnormal decibel value of the first auxiliary pickup as the first decibel value; Determine an initial core positioning point according to the core positioning line, the core decibel value and the first decibel value; Connecting the first position with the second position of the second auxiliary pickup to obtain an auxiliary positioning line; Acquire an abnormal decibel value of the second auxiliary pickup as a second decibel value, and determine an abnormal core positioning point according to the initial core positioning point, the auxiliary positioning line and the second decibel value; With the abnormal core positioning point as the center of the circle and based on the preset abnormal radius, an abnormal positioning area is generated.

[0009] Optionally, in a possible implementation manner of the first aspect, determining an initial core positioning point according to the core positioning line, the core decibel value and the first decibel value includes: A core decibel total value is obtained based on the sum of the core decibel value and the first decibel value, and a core point ratio is obtained based on the ratio of the first decibel value to the core decibel total value; Acquire the distance of the core positioning line as the core positioning line distance, obtain the core positioning distance based on the product of the core point ratio and the core positioning line distance, and determine the direction from the core position to the first position along the core positioning line as the core positioning direction; An initial core positioning point is determined along the core positioning line with the core position as a starting point based on the core positioning direction and the core positioning distance.

[0010] Optionally, in a possible implementation manner of the first aspect, determining the abnormal core positioning point according to the initial core positioning point, the auxiliary positioning line and the second decibel value includes: Determine the endpoint at the first position on the auxiliary positioning line as the first endpoint, and determine the endpoint at the second position on the auxiliary positioning line as the second endpoint; The first end point of the auxiliary positioning line is translated to the initial core positioning point of the core positioning line to obtain a core offset line; Obtaining an auxiliary decibel total value according to the sum of the second decibel value and the first decibel value, and obtaining an offset point ratio based on a ratio of the second decibel value to the auxiliary decibel total value; Acquire the distance of the auxiliary positioning line as the auxiliary positioning line distance, obtain the offset positioning distance based on the product of the offset point ratio and the auxiliary positioning line distance, and determine the direction from the first end point to the second end point along the core offset line as the offset positioning direction; Taking the initial core positioning point as a starting point along the core offset line, an abnormal core positioning point is determined based on an offset positioning direction and the offset positioning distance.

[0011] Optionally, in a possible implementation manner of the first aspect, the retrieving historical video data collected by a region collection device corresponding to the abnormal positioning region based on the abnormal timbre information, and determining the abnormal individual according to the historical video data includes: Acquire abnormal time information corresponding to the abnormal timbre information, and retrieve historical video data collected by a collection device corresponding to the abnormal positioning area based on the abnormal time information; Identifying an individual who performs a vocalization action in the historical video data as an execution individual, and obtaining the execution quantity of the execution individual; When it is determined that the execution quantity is equal to 1, the execution individual is regarded as an abnormal individual; When it is determined that the execution number is greater than 1, obtaining the identification video data collected by the regional collection device based on a preset statistical duration; Obtaining the number of abnormalities of each of the execution individuals in the identified video data and the abnormal area of ​​the observation area corresponding to each of the execution individuals; Obtaining a frequency coefficient according to the ratio of the abnormal frequency to the reference frequency, and obtaining a first discrimination value according to the product of the frequency coefficient and the frequency weight value; Obtaining the total area of ​​the observation area, obtaining an abnormal area ratio according to a ratio of the abnormal area to the total area, obtaining an abnormal area coefficient based on a ratio of the abnormal area ratio to a reference area ratio, and obtaining a second discrimination value according to a product of the abnormal area coefficient and a ratio weight value; The total discrimination value of each execution individual is obtained according to the sum of the first discrimination value and the second discrimination value, and when it is determined that the total discrimination value is greater than the preset discrimination value, the corresponding execution individual is regarded as an abnormal individual.

[0012] Optionally, in a possible implementation manner of the first aspect, controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device includes: Acquire the real-time video data collected by the area acquisition device, and identify abnormal pixel values ​​corresponding to abnormal individuals in the real-time video data; Based on the abnormal pixel value, the mobile monitoring device is controlled to move to the position of the abnormal individual.

[0013] Optionally, in a possible implementation manner of the first aspect, controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device includes: Acquire the real-time video data collected by the area acquisition device, acquire the center point of the picture corresponding to the real-time video data, and perform coordinate processing on the real-time video data with the center point of the picture as the coordinate origin; The coordinates of the abnormal individual are determined as abnormal positioning coordinates, and the mobile monitoring device is controlled to move to the position of the abnormal individual based on the abnormal positioning coordinates.

[0014] Optionally, in a possible implementation manner of the first aspect, controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device includes: Acquiring real-time video data collected by the regional collection device; The relative position relationship between the mobile monitoring device and the abnormal individual in the real-time video data is analyzed in real time, and the mobile monitoring device is controlled to move until the relative position relationship between the mobile monitoring device and the abnormal individual is a positive upper vertical position relationship, and then the movement is stopped.

[0015] Optionally, in a possible implementation of the first aspect, the method further includes: Acquire the number of sounds picked up by the positioning pickup in the sound picking sequence, and when it is determined that the number of sounds picked up is equal to 2, select the first positioning pickup in the sound picking sequence as the core pickup, and determine the second positioning pickup in the sound picking sequence as the first auxiliary pickup; Connecting the core position of the core pickup and the first position of the first auxiliary pickup to obtain a core positioning line; Acquire the abnormal decibel value of the core pickup as the core decibel value, and determine the abnormal decibel value of the first auxiliary pickup as the first decibel value; A core decibel total value is obtained based on the sum of the core decibel value and the first decibel value, and a core point ratio is obtained based on the ratio of the first decibel value to the core decibel total value; Acquire the distance of the core positioning line as the core positioning line distance, obtain the core positioning distance based on the product of the core point ratio and the core positioning line distance, and determine the direction from the core position to the first position along the core positioning line as the core positioning direction; Taking the core position as a starting point along the core positioning line, determining an abnormal core positioning point based on the core positioning direction and the core positioning distance; When it is determined that the number of picked-up sounds is equal to 1, the position of the positioning pickup is obtained as the abnormal core positioning point; With the abnormal core positioning point as the center of the circle and based on the preset abnormal radius, an abnormal positioning area is generated.

[0016] According to a third aspect of the present invention, there is provided an electronic device, comprising: a memory, a processor and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the first aspect of the present invention and various methods that may be involved in the first aspect.

[0017] According to a fourth aspect of the present invention, a storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the first aspect of the present invention and various methods that may be involved in the first aspect.

[0018] The beneficial effects of the present invention are as follows: 1. The present invention can quickly identify and locate abnormal individuals so that intervention measures can be taken in a timely manner. First, the present invention can innovatively combine sound monitoring and video data analysis, use array microphones to collect the timbre information of chickens in real time, accurately locate abnormal calls, and significantly reduce the scope of video data that needs to be processed through rapid identification and positioning of abnormal timbres, thereby improving the speed and accuracy of abnormal individual identification, which not only shortens the identification time of abnormal individuals, but also greatly reduces the data processing burden and improves the overall efficiency of farm management.

[0019] 2. The present invention can preliminarily screen the breeding area according to the abnormal decibel value and the corresponding position received by the positioning microphone, and obtain the abnormal positioning area, so as to reduce the data processing amount for identifying and analyzing the regional video, so as to retrieve the historical video data corresponding to the abnormal positioning area, so as to identify the abnormal individual and improve the efficiency of locating the abnormal individual. The present invention can adopt different technical schemes to determine the abnormal core positioning point according to the number of positioning microphones, and then obtain the abnormal positioning area, and improve the accuracy of determining the abnormal positioning area, wherein the present invention can obtain the abnormal decibel value and geographical location of the positioning microphone, determine the initial core positioning point and the abnormal core positioning point according to the value of the abnormal decibel value, so as to obtain the abnormal positioning area, and when the number of positioning microphones is 1, the position point of the corresponding positioning microphone can be used as the abnormal core positioning point, and at the same time, the abnormal core positioning point can be determined, and the intersection of the vertical line constructed by multiple positioning points can also be used to determine, so as to improve the accuracy of the abnormal positioning area, so as to facilitate improving the recognition efficiency of abnormal individuals.

[0020] 3. The present invention can dynamically monitor and track abnormal individuals. After confirming an abnormal individual, the mobile monitoring device can be directed to quickly go to the location of the abnormal individual, and the abnormal individual can be continuously monitored and located and tracked by the mobile monitoring device. The position of the mobile monitoring device can be controlled in real time, and the behavioral changes of the abnormal individual can be monitored in real time from a perspective directly above. The monitoring data can be transmitted to the management end in real time, which not only realizes the accurate positioning of the abnormal individual, but also provides detailed monitoring information for the management personnel, so as to facilitate the timely adoption of corresponding protection and treatment measures and improve management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flow chart of an intelligent training method for chickens provided by the present invention; Figure 2 A schematic diagram of an abnormal positioning area provided by the present invention; Figure 3 A schematic diagram of the hardware structure of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0023] like Figure 1 As shown, the present invention provides an intelligent training method for chickens, comprising: S1, controlling the array microphones in the target breeding area to collect the timbre information of the chicken flock in real time, analyzing the timbre information of the chicken flock to obtain abnormal timbre information, and determining the microphone that receives the abnormal timbre information as the positioning microphone.

[0024] It should be noted that in a breeding farm, due to the large number of farmed chickens, when a small number of farmed chickens become abnormal, it is easy to affect the rest of the farmed chickens. Therefore, it is necessary to monitor the farmed chickens so that abnormal sick chickens can be discovered in time, so that corresponding protective measures can be taken. The existing method is usually to monitor the breeding area and determine the abnormal sick chickens by viewing the monitoring images. This method has a large amount of data processing and a slow speed, and the position of the chickens will continue to change as they walk, resulting in a low efficiency in determining abnormal chickens. Therefore, the present invention can obtain abnormal tone information according to the pre-installed array microphone, thereby detecting abnormal sick chickens, and subsequently can quickly locate the area where the abnormal sick chickens are located according to the positioning microphone, so as to subsequently determine the abnormal sick chickens through image recognition, so as to reduce the amount of image processing, find abnormal sick chickens in time and implement protective measures, and improve the efficiency of chicken protection monitoring.

[0025] It can be understood that the target breeding area is the area of ​​the breeding farm where chicken flock monitoring is required, the array microphone is a microphone arranged and installed in an array, the chicken flock timbre information is the sound information of the chicken flock's crowing, the abnormal timbre information is the sound information of the chicken flock's timbre information that is different from the crowing of normal farmed chickens, and the positioning microphone is a microphone that collects the abnormal timbre information.

[0026] It is not difficult to understand that multiple microphones are arranged horizontally and vertically at a certain interval. When the corresponding farmed chickens are calling, the microphones that are closer can record their abnormal tone information. Therefore, the approximate regional location of the abnormal sick chickens can be preliminarily determined through the positioning microphone. Among them, all microphones that recognize abnormal tone information are positioning microphones, so that the collection image of the collection device in the corresponding area can be determined according to the position of the positioning microphone, and then the farmed chickens in the area can be observed and identified, which can greatly reduce the amount of image processing and improve positioning efficiency.

[0027] It is worth mentioning that when analyzing the timbre information of chicken flocks, spectrum analysis tools such as a spectrum analyzer can be used to help observe the spectral distribution of the sound and thus identify the timbre.

[0028] S2, determining the abnormal positioning area according to the sound pickup positioning strategy and the positioning pickup, retrieving the historical video data collected by the area collection device corresponding to the abnormal positioning area based on the abnormal timbre information, and determining the abnormal individual according to the historical video data.

[0029] It can be understood that after the microphone parses the corresponding abnormal tone information, the video data of the area acquisition device in the abnormal positioning area determined by the positioning microphone within the time period can be retrieved according to the crowing period of the farmed chickens corresponding to the abnormal tone information, so as to promptly identify the abnormal individuals through historical video data later.

[0030] Among them, the abnormal positioning area is the positioning area for determining abnormal sick chickens, the area acquisition device is a device for acquiring images of the area, such as a camera, the historical video data is the video data collected corresponding to the historical time period, and the abnormal individual is the abnormal farmed chicken. For example, through historical video data, it can be identified that there are farmed chickens with abnormal walking postures, severe hair loss areas on the body, or black combs, etc., which means that the farmed chickens may have abnormal symptoms, and the corresponding farmed chickens can be regarded as abnormal individuals.

[0031] In some embodiments, the specific implementation steps in step S2 (determining the abnormal positioning area according to the sound pickup positioning strategy and the positioning pickup) include: S201, obtaining the abnormal decibel value corresponding to the abnormal timbre information received by each of the positioning pickups, and sorting the positioning pickups in descending order based on the abnormal decibel values ​​to obtain a sound pickup selection sequence.

[0032] It should be noted that the distance between the farmed chickens and the pickup will affect the decibel value of the abnormal tone information received by the pickup. The closer the distance to the pickup, the higher the corresponding decibel value will be, and the farther the distance to the pickup, the lower the corresponding decibel value will be.

[0033] It can be understood that the abnormal decibel value is the sound decibel value of the positioning pickup corresponding to the abnormal timbre information. The abnormal call of a chicken may be received by multiple pickups to obtain sound information, but due to different distances, the corresponding abnormal decibel values ​​also have certain numerical differences. Therefore, the positioning pickups can be sorted according to the abnormal decibel value to obtain a pickup selection sequence.

[0034] The sound pickup selection sequence is a sequence of sound pickups arranged in descending order according to the size of abnormal decibel values.

[0035] For example, when there are 5 positioning pickups, namely pickup 1, pickup 2, pickup 3, pickup 4, and pickup 5, the corresponding abnormal decibel values ​​are 60 decibels, 10 decibels, 8 decibels, 30 decibels, and 5 decibels, respectively. Therefore, after arranging the positioning pickups in descending order according to the abnormal decibel values, the pickup selection sequence obtained is (pickup 1, pickup 4, pickup 2, pickup 3, pickup 5).

[0036] Through the above implementation, the present invention can obtain a sound picking sequence, so as to subsequently select a certain number of positioning pickups according to the sound picking sequence, so as to determine the abnormal positioning area.

[0037] S202, selecting the first positioning pickup in the sound picking sequence as the core pickup, determining the second positioning pickup in the sound picking sequence as the first auxiliary pickup, and selecting the third positioning pickup in the sound picking sequence as the second auxiliary pickup.

[0038] It can be understood that since the first positioning pickup in the sound picking sequence has the highest abnormal decibel value, the first positioning pickup can be used as the core pickup, and the second positioning pickup in the sound picking sequence can be used as the first auxiliary pickup, and the third positioning pickup in the sound picking sequence can be used as the second auxiliary pickup. Since the abnormal decibel values ​​of several positioning pickups arranged at the front row of the sound picking sequence are relatively high, three positioning pickups can be used to obtain the abnormal positioning area later.

[0039] Among them, the core pickup is the main pickup for determining the abnormal positioning area, that is, the first positioning pickup in the sound picking sequence, the first auxiliary pickup is the first pickup for assisting in determining the abnormal positioning area, that is, the second positioning pickup in the sound picking sequence, and the second auxiliary pickup is the second pickup for assisting in determining the abnormal positioning area, that is, the third positioning pickup in the sound picking sequence.

[0040] Through the above implementation, the present invention can obtain the core microphone, the first auxiliary microphone and the second auxiliary microphone, so as to subsequently determine the abnormal positioning area.

[0041] S203: Determine an abnormality location area according to the core microphone, the first auxiliary microphone, and the second auxiliary microphone.

[0042] It is understandable that the core pickup, the first auxiliary pickup and the second auxiliary pickup are obtained, and then the installation positions of the corresponding pickups can be retrieved, so that the abnormal positioning area where the abnormal individual may exist can be determined through multiple position points.

[0043] In some embodiments, the specific implementation steps in step S203 (determining the abnormal location area according to the core pickup, the first auxiliary pickup and the second auxiliary pickup) include: S2031, connecting the core position of the core pickup and the first position of the first auxiliary pickup to obtain a core positioning line.

[0044] It can be understood that the core position is the geographical location of the core pickup, the first position is the geographical location where the first auxiliary pickup is installed, and the core positioning line is the core line segment for determining the abnormal positioning area, that is, the connecting line between the core position and the first position.

[0045] Through the above implementation, the present invention can obtain a core positioning line, so as to subsequently determine an initial core positioning point according to the core positioning line, thereby facilitating subsequent determination of an abnormal positioning area.

[0046] S2032: Acquire the abnormal decibel value of the core sound pickup as the core decibel value, and determine the abnormal decibel value of the first auxiliary sound pickup as the first decibel value.

[0047] It can be understood that the core decibel value is the abnormal decibel value corresponding to the core pickup, for example, it may be 60 decibels, and the first decibel value is the abnormal decibel value corresponding to the first auxiliary pickup, for example, it may be 30 decibels.

[0048] Through the above implementation, the present invention can determine the core decibel value and the first decibel value, so as to subsequently determine the position of the initial core positioning point according to the difference in decibel values.

[0049] S2033: Determine an initial core positioning point according to the core positioning line, the core decibel value and the first decibel value.

[0050] It can be understood that the initial core positioning point is a positioning point of the abnormal positioning area that is initially determined, so that the abnormal core positioning point can be obtained based on the initial core positioning point, and then the abnormal positioning area can be determined.

[0051] In some embodiments, the specific implementation steps of step S2033 (determining the initial core positioning point according to the core positioning line, the core decibel value and the first decibel value) include: S20331, obtaining a core decibel total value based on the sum of the core decibel value and the first decibel value, and obtaining a core point ratio based on the ratio of the first decibel value to the core decibel total value.

[0052] It can be understood that the core decibel total value is the sum of the core decibel value and the first decibel value, and the core point ratio is the ratio corresponding to the initial core positioning point, that is, the ratio of the first decibel value to the core decibel total value.

[0053] It is not difficult to understand that by calculating the core point ratio, it is convenient to subsequently determine the distance between the initial core positioning point and the core position, and the smaller the core point ratio, the closer the distance between the initial core positioning point and the core position determined subsequently is.

[0054] S20332, obtaining the distance of the core positioning line as the core positioning line distance, obtaining the core positioning distance based on the product of the core point ratio and the core positioning line distance, and determining the direction along the core positioning line from the core position to the first position as the core positioning direction.

[0055] It can be understood that the core positioning line distance is the length of the core positioning line, the core positioning distance is the distance of the initial core positioning point, that is, the product of the core point ratio and the core positioning line distance, and the core positioning direction is the direction from the core position to the first position along the core positioning line.

[0056] Through the above implementation, the present invention can obtain the core positioning distance and the core positioning direction, so as to subsequently determine the initial core positioning point.

[0057] S20333: Determine an initial core positioning point along the core positioning line with the core position as the starting point based on the core positioning direction and the core positioning distance.

[0058] It can be understood that the core positioning distance is moved along the core positioning line with the core position as the starting point toward the core positioning direction, so that the corresponding position point can be used as the initial core positioning point.

[0059] Through the above implementation, the present invention can obtain the initial core positioning point, so as to subsequently determine the abnormal core positioning point according to the auxiliary microphone, and then obtain the abnormal positioning area, so as to facilitate the subsequent rapid identification of abnormal individuals and improve the identification efficiency.

[0060] S2034: Connect the first position and the second position of the second auxiliary pickup to obtain an auxiliary positioning line.

[0061] It can be understood that the second position is the geographical location of the second auxiliary microphone, and the auxiliary positioning line is a line segment for assisting in determining the abnormal positioning area, that is, a connecting line connecting the first position and the second position.

[0062] S2035, obtaining an abnormal decibel value of the second auxiliary pickup as a second decibel value, and determining an abnormal core positioning point according to the initial core positioning point, the auxiliary positioning line and the second decibel value.

[0063] It can be understood that the second decibel value is the abnormal decibel value of the second auxiliary microphone, and the abnormal core positioning point is the core position point of the abnormal positioning area.

[0064] Through the above implementation, the present invention can obtain the abnormal core positioning point, so as to subsequently determine the corresponding abnormal positioning area according to the abnormal core positioning point.

[0065] In some embodiments, the specific implementation steps of step S2035 (determining the abnormal core positioning point according to the initial core positioning point, the auxiliary positioning line and the second decibel value) include: S20351, determining the endpoint at the first position on the auxiliary positioning line as the first endpoint, and determining the endpoint at the second position on the auxiliary positioning line as the second endpoint.

[0066] It can be understood that the first endpoint is the endpoint where the first position on the auxiliary positioning line is located, and the second endpoint is the endpoint where the second position on the auxiliary positioning line is located.

[0067] It is not difficult to understand that the first endpoint and the second endpoint are determined based on the auxiliary positioning line so as to subsequently determine the core offset line.

[0068] S20352: Translate the first endpoint of the auxiliary positioning line to the initial core positioning point of the core positioning line to obtain a core offset line.

[0069] It should be noted that the core offset line is the positioning line after the auxiliary positioning line is moved. For example, Figure 2 As shown, the first endpoint of the auxiliary positioning line is translated to the initial core positioning point of the core positioning line to obtain the core offset line.

[0070] S20353: Obtain an auxiliary decibel total value based on the sum of the second decibel value and the first decibel value, and obtain an offset point ratio based on a ratio of the second decibel value to the auxiliary decibel total value.

[0071] It can be understood that the auxiliary decibel total value is the sum of the second decibel value and the first decibel value, and the offset point ratio is the ratio of the second decibel value to the auxiliary decibel total value.

[0072] Through the above implementation, the present invention can obtain the offset point ratio, so as to subsequently determine the abnormal core positioning point according to the offset point ratio.

[0073] S20354, obtaining the distance of the auxiliary positioning line as the auxiliary positioning line distance, obtaining the offset positioning distance based on the product of the offset point ratio and the auxiliary positioning line distance, and determining the direction from the first endpoint to the second endpoint along the core offset line as the offset positioning direction.

[0074] It can be understood that the auxiliary positioning line distance is the length of the auxiliary positioning line, the offset positioning distance is the product of the offset point ratio and the auxiliary positioning line distance, and the offset positioning direction is the direction from the first endpoint to the second endpoint along the core offset line.

[0075] Through the above implementation, the present invention can determine the offset positioning distance and the offset positioning direction, so as to subsequently obtain the abnormal core positioning point.

[0076] S20355: Taking the initial core positioning point as the starting point, determine the abnormal core positioning point along the core offset line based on the offset positioning direction and the offset positioning distance.

[0077] It is understandable that if Figure 2 As shown, starting from the initial core positioning point, the offset positioning distance is moved along the core offset line toward the offset positioning direction, and the corresponding position point is used as the abnormal core positioning point.

[0078] It is not difficult to understand that by using multiple positioning pickups to determine the abnormal core positioning point of the abnormal positioning area where the abnormal individual may be located, it is convenient for subsequent image processing of the determined abnormal positioning area, and farmed chickens with abnormal conditions can be quickly identified.

[0079] It is worth mentioning that when there are only two positioning pickups, the initial core positioning point can be used as the abnormal core point location to determine the abnormal positioning area.

[0080] S2036: Generate an abnormal positioning area based on a preset abnormal radius with the abnormal core positioning point as the center of the circle.

[0081] It can be understood that the preset abnormal radius is a preset radius distance, so that Figure 2 As shown, the abnormal core positioning point can be taken as the center of the circle, the radius is the preset abnormal radius, and the determined circular area is the abnormal positioning area, that is, the location area where the abnormal individual may exist. Then, the video data collected by the corresponding regional acquisition device can be retrieved according to the position of the abnormal positioning area for identification and analysis, so as to locate the abnormal individual and facilitate timely protection measures.

[0082] In some embodiments, the specific implementation steps of step S2 (retrieving the historical video data collected by the area collection device corresponding to the abnormal positioning area based on the abnormal timbre information, and determining the abnormal individual according to the historical video data) include: S204, obtaining abnormal time information corresponding to the abnormal timbre information, and retrieving historical video data collected by a region collection device corresponding to the abnormal positioning region based on the abnormal time information.

[0083] It can be understood that the abnormal time information is the collection time period corresponding to the abnormal sound information. For example, when analyzing the sound information of the chicken flock, it is determined that the collection time period corresponding to the abnormal sound information is 9:00-9:01. Then, according to the abnormal time information, the video between 9:00-9:01 collected by the area collection device corresponding to the determined abnormal positioning area can be retrieved, so as to subsequently identify the video and determine the farmed chickens with abnormal problems.

[0084] Among them, the historical video data is the video data corresponding to the historical time.

[0085] S205, identifying individuals who perform the vocalization action in the historical video data as execution individuals, and obtaining the execution quantity of the execution individuals.

[0086] It can be understood that the vocal action is the corresponding crowing action when the farmed chickens are crowing, the executing individuals are the farmed chickens with crowing actions, and the execution quantity is the number of executing individuals, that is, the number of farmed chickens that are crowing.

[0087] It is not difficult to understand that once the execution individuals and execution quantity are determined, the identification data and abnormal individuals can be determined based on the execution quantity.

[0088] S206: When it is determined that the execution quantity is equal to 1, the execution individual is regarded as an abnormal individual.

[0089] It is understandable that when it is determined that the execution quantity is equal to 1, it means that only one farmed chicken has called in the corresponding area and issued abnormal timbre information. Therefore, the corresponding execution individual can be regarded as an abnormal individual.

[0090] S207: When it is determined that the execution quantity is greater than 1, the identification video data collected by the area collection device is obtained based on a preset statistical duration.

[0091] It can be understood that when it is determined that the number of executions is greater than 1, it means that there are multiple farmed chickens in the abnormal positioning area that are at risk of abnormal problems. Therefore, based on the preset statistical time, the identification video data collected by the regional acquisition device can be obtained, so as to continuously monitor each execution individual for a preset statistical time, so as to subsequently improve the accuracy of determining abnormal individuals.

[0092] Among them, the preset statistical time length is the preset monitoring time length for statistically executing individual behaviors, for example, it can be 30 minutes, and the identification video data is the video data collected corresponding to the preset statistical time length, that is, the video data used to identify abnormal individuals.

[0093] S208, obtaining the number of abnormalities of each of the execution individuals in the identified video data, and the abnormal area of ​​the observation area corresponding to each of the execution individuals.

[0094] It should be noted that, when the identification video data collected within the preset statistical time length, the more times the corresponding execution individual exhibits abnormal behavior, it can be said that there is a problem with the farmed chicken. When the number of abnormal behaviors is less, such as only once or none, it can be said that the farmed chicken is not an abnormal sick chicken. Similarly, when it is identified that the corresponding execution individual has a large area of ​​hair loss on the chicken body, it can also be said that the farmed chicken has a lesion. Therefore, in order to improve the accuracy of determining abnormal individuals, the number of abnormalities and the abnormal area can be obtained by identifying the video data.

[0095] It can be understood that the number of abnormalities is the number of times the executing individual has an abnormal walking posture, the observation area is the area of ​​the executing individual for identification and observation, that is, the body area and comb area of ​​farmed chickens, and the abnormal area is the area where the abnormality occurs, for example, the area where the farmed chickens lose hair or the area where the comb turns black.

[0096] S209, obtaining a frequency coefficient according to the ratio of the abnormal frequency to the reference frequency, and obtaining a first identification value according to the product of the frequency coefficient and the frequency weight value.

[0097] It can be understood that the benchmark number of times is a benchmark value for judging the number of times coefficient, which can be preset manually, for example, the benchmark number of times can be 1, the number of times coefficient is the coefficient value calculated corresponding to the abnormal number of times, that is, the ratio of the abnormal number of times to the benchmark number of times, the number of times weight value is used to determine the weight ratio of the abnormal number of times in the calculation of abnormal individuals, and the first discrimination value is the first value for distinguishing abnormal individuals, that is, the product of the number of times coefficient and the number of times weight value.

[0098] S210, obtaining the total area of ​​the observation area, obtaining the abnormal area proportion based on the ratio of the abnormal area to the total area, obtaining the abnormal area coefficient based on the ratio of the abnormal area proportion to the reference area proportion, and obtaining the second discrimination value based on the product of the abnormal area coefficient and the proportion weight value.

[0099] It can be understood that the total area is the area size corresponding to the observation area, the abnormal area ratio is the area ratio of the abnormal area, that is, the ratio of the abnormal area to the total area, the baseline area ratio is the area ratio threshold for determining the abnormal individual, which can be pre-set, for example, it can be 1 / 10, the abnormal area coefficient is the number of calculations of the abnormal area in determining the abnormal individual, that is, the ratio of the abnormal area ratio to the baseline area ratio, the ratio weight value is the weight value corresponding to the area ratio, which can be artificially pre-set, and the second discrimination value is the judgment value corresponding to the abnormal area, that is, the product of the abnormal area coefficient and the ratio weight value.

[0100] S211, obtaining a total discrimination value of each execution individual according to the sum of the first discrimination value and the second discrimination value, and when it is determined that the total discrimination value is greater than a preset discrimination value, treating the corresponding execution individual as an abnormal individual.

[0101] It can be understood that when determining whether an executing individual is an abnormal individual, it is necessary to comprehensively consider the number of times abnormal behavior occurs and the area of ​​the abnormality in the corresponding observation area. Therefore, the calculated first discrimination value and the second discrimination value can be summed to obtain the total discrimination value. When the total discrimination value is greater than the preset discrimination value, it means that the corresponding abnormal value of the executing individual is high and exceeds the normal range. The corresponding executing individual can be regarded as an abnormal individual. On the contrary, when the total discrimination value is less than or equal to the preset discrimination value, it can be said that the corresponding executing individual has not reached the abnormal level, and it will not be regarded as an abnormal individual.

[0102] The total discrimination value is the total calculated value for judging abnormal individuals, that is, the sum of the first discrimination value and the second discrimination value, and the preset discrimination value is a preset reference value for distinguishing execution individuals, which can be preset manually.

[0103] S3, controlling the mobile monitoring device to move to the abnormal location area, and controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device.

[0104] It should be noted that since abnormal farmed chickens will also walk, the position of the abnormal individuals is constantly changing. In order to quickly provide the management end with a more accurate position of the abnormal individuals, the mobile monitoring device can be controlled to move to the abnormal positioning area, and the position of the abnormal individuals can be monitored in real time through the real-time video data collected by the regional acquisition device. However, the regional acquisition device has limitations in the monitoring range. Therefore, the mobile monitoring device can be moved to the position of the abnormal individual, and the position can be updated in real time to achieve positioning and tracking of the abnormal individuals, so as to facilitate the subsequent timely adoption of protective measures for the abnormal individuals, such as treatment or nursing measures.

[0105] It can be understood that the mobile monitoring device is a monitoring device that can be moved, such as a drone, and the real-time video data is the video data collected in real time by the regional collection device.

[0106] In some embodiments, the specific implementation steps of step S3 (controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device) include: S31, acquiring the real-time video data collected by the area collection device, and identifying abnormal pixel values ​​corresponding to abnormal individuals in the real-time video data.

[0107] It can be understood that since the pixel values ​​corresponding to abnormal individuals are different from the pixel values ​​of normal farmed chickens, for example, the black pixel values ​​corresponding to the combs, or the pixel values ​​corresponding to the exposed skin on the body, the real-time video data collected by the regional acquisition device can be obtained, thereby identifying the abnormal pixel values ​​corresponding to the abnormal individuals in the real-time video data, so as to subsequently control the mobile monitoring device to move to the position of the abnormal individual corresponding to the abnormal pixel values.

[0108] Among them, the abnormal pixel value is the pixel value corresponding to the abnormal individual.

[0109] S32, controlling the mobile monitoring device to move to the position of the abnormal individual based on the abnormal pixel value.

[0110] It can be understood that controlling the mobile monitoring device to move to the geographical location of the abnormal individual corresponding to the abnormal pixel value facilitates subsequent real-time positioning and tracking of the trajectory position of the abnormal individual.

[0111] In other embodiments, the specific implementation steps of the step (controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device) include: A1, obtaining the real-time video data collected by the area collection device, obtaining the center point of the picture corresponding to the real-time video data, and performing coordinate processing on the real-time video data with the center point of the picture as the coordinate origin.

[0112] It is understandable that another way to move the mobile monitoring device to the location of the abnormal individual is to obtain the center point of the screen corresponding to the real-time video data, and coordinate the video frames in the real-time video data with the center point of the screen as the coordinate origin, so as to subsequently determine the actual geographical location of the abnormal individual through the real-time video data, which will facilitate the control of the position movement of the mobile monitoring device.

[0113] The center point of the picture is the center point of the image of the video frame corresponding to the real-time video data, which can be obtained through the existing technology OpenCV.

[0114] A2, determining the coordinates of the abnormal individual as the abnormal positioning coordinates, and controlling the mobile monitoring device to move to the position of the abnormal individual based on the abnormal positioning coordinates.

[0115] It can be understood that the abnormal location coordinates are the position coordinates of the abnormal individual in the real-time video data.

[0116] It is not difficult to understand that the regional acquisition device has a fixed installation position. At the same time, the area range that the regional acquisition device can capture is also fixed. Therefore, the abnormal location coordinates obtained in the real-time video data can be converted into actual geographic coordinates. At the same time, the mobile monitoring device can be moved to the geographical location corresponding to the regional acquisition device in priority, and moved according to the actual geographic coordinates, so that the mobile monitoring device moves to the location of the abnormal individual.

[0117] In other embodiments, the specific implementation steps of the step (controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device) further include: B1, obtaining real-time video data collected by the regional collection device.

[0118] It is understandable that the real-time video data captured by the regional acquisition device is obtained first, so as to control the mobile monitoring device to move above the abnormal individual according to the real-time video data.

[0119] Among them, the real-time video data is the video data captured by the regional acquisition device in real time.

[0120] B2, analyzing the relative position relationship between the mobile monitoring device and the abnormal individual in the real-time video data in real time, and controlling the mobile monitoring device to move until the relative position relationship between the mobile monitoring device and the abnormal individual is a positive upper vertical position relationship, and then stopping the movement.

[0121] It can be understood that when the mobile monitoring device moves to the abnormal positioning area, the corresponding area acquisition device will capture real-time video data of the mobile monitoring device and the abnormal individual, and then the relative position of the mobile monitoring device and the identified abnormal individual can be determined, so that the relative position information can be transmitted in real time through real-time video data, and the mobile monitoring device can be controlled to move above the abnormal individual, that is, when the relative position relationship is a vertical position relationship, the movement is stopped.

[0122] Among them, the relative position relationship refers to the relative position between the mobile monitoring device and the abnormal individual, and the upper vertical position relationship refers to the vertical position between the mobile monitoring device and the abnormal individual.

[0123] S4, when it is determined that the mobile monitoring device is at the location of the abnormal individual, the mobile monitoring device is controlled to lock and monitor the abnormal individual, and the locked monitoring video data is obtained and sent to the management end.

[0124] It can be understood that when it is determined that the mobile monitoring device is at the location of an abnormal individual, the mobile monitoring device can be controlled to locate, track and monitor the abnormal individual so as to obtain locked monitoring video data and send it to the management end, so that the management personnel can determine the location of the abnormal individual in real time and take timely measures.

[0125] Among them, the locked monitoring video data is the video data obtained by tracking and monitoring abnormal individuals, and the management terminal is the information terminal of the person who manages the chicken flock, which can be a mobile phone, computer, etc.

[0126] It should be noted that when the farmed chickens are closer to the pickups at a certain position, the number of pickups that can record abnormal timbre information will be smaller. Therefore, when it is determined that the number of pickups is equal to 2, the abnormal positioning area can be determined by the corresponding 2 positioning pickups. Therefore, in some embodiments, it also includes: C1, obtaining the number of pickups of the positioning pickup in the pickup selection sequence, and when determining that the number of pickups is equal to 2, selecting the first positioning pickup in the pickup selection sequence as the core pickup, and determining the second positioning pickup in the pickup selection sequence as the first auxiliary pickup.

[0127] It can be understood that the number of pickups is the number of positioning pickups in the pickup selection sequence, the core pickup is the first positioning pickup in the pickup selection sequence, and the first auxiliary pickup is the second positioning pickup in the pickup selection sequence.

[0128] C2, connecting the core position of the core pickup and the first position of the first auxiliary pickup to obtain a core positioning line.

[0129] It can be understood that the core position is the geographical position corresponding to the core pickup, the first position is the geographical position of the first auxiliary pickup, and the core positioning line is the connecting line between the core position and the first position.

[0130] Through the above implementation, the present invention can obtain a core positioning line, so as to subsequently determine the abnormal positioning area according to the core positioning line.

[0131] C3, obtaining the abnormal decibel value of the core pickup as the core decibel value, and determining the abnormal decibel value of the first auxiliary pickup as the first decibel value.

[0132] It can be understood that the core decibel value is the abnormal decibel value corresponding to the core pickup, for example, it may be 60 decibels, and the first decibel value is the abnormal decibel value corresponding to the first auxiliary pickup, for example, it may be 30 decibels.

[0133] Through the above implementation, the present invention can determine the core decibel value and the first decibel value, so as to subsequently determine the position of the initial core positioning point according to the difference in decibel values.

[0134] C4, obtaining a core decibel total value based on the sum of the core decibel value and the first decibel value, and obtaining a core point ratio based on the ratio of the first decibel value to the core decibel total value.

[0135] It can be understood that the core decibel total value is the sum of the core decibel value and the first decibel value, and the core point ratio is the ratio corresponding to the initial core positioning point, that is, the ratio of the first decibel value to the core decibel total value.

[0136] It is not difficult to understand that by calculating the core point ratio, it is convenient to subsequently determine the distance between the initial core positioning point and the core position, and the smaller the core point ratio, the closer the distance between the initial core positioning point and the core position determined subsequently is.

[0137] C5, obtaining the distance of the core positioning line as the core positioning line distance, obtaining the core positioning distance based on the product of the core point ratio and the core positioning line distance, and determining the direction along the core positioning line from the core position to the first position as the core positioning direction.

[0138] It can be understood that the core positioning line distance is the length of the core positioning line, the core positioning distance is the distance of the initial core positioning point, that is, the product of the core point ratio and the core positioning line distance, and the core positioning direction is the direction from the core position to the first position along the core positioning line.

[0139] Through the above implementation, the present invention can obtain the core positioning distance and the core positioning direction, so as to subsequently determine the initial core positioning point.

[0140] C6, along the core positioning line with the core position as the starting point, determine the abnormal core positioning point based on the core positioning direction and the core positioning distance.

[0141] It can be understood that the core positioning distance is moved along the core positioning line with the core position as the starting point toward the core positioning direction, so that the corresponding position point can be used as the abnormal core positioning point.

[0142] Through the above implementation, the present invention can obtain the abnormal core positioning point, so as to subsequently obtain the abnormal positioning area according to the abnormal core positioning point, thereby quickly identifying the abnormal individual and improving the recognition efficiency.

[0143] C7, when it is determined that the number of picked-up sounds is equal to 1, the position of the positioning pickup is obtained as the abnormal core positioning point.

[0144] It can be understood that when it is determined that the number of picked-up sounds is equal to 1, it can be explained that the abnormal individual is only closest to the positioning microphone, and the position of the positioning microphone can be used as the abnormal core positioning point, so as to quickly determine the corresponding abnormal positioning area, reduce the amount of data processing, and improve the recognition efficiency of abnormal individuals.

[0145] C8, taking the abnormal core positioning point as the center of the circle and based on a preset abnormal radius, generating an abnormal positioning area.

[0146] It can be understood that the preset abnormal radius is a pre-set radius distance, so that the abnormal core positioning point can be used as the center of the circle, and the radius is the preset abnormal radius. The determined circular area is the abnormal positioning area, that is, the location area where the abnormal individual may exist. Then, the video data collected by the corresponding area acquisition device can be retrieved according to the position of the abnormal positioning area for identification and analysis, thereby locating the abnormal individual and facilitating timely protection measures.

[0147] In some other embodiments, the specific implementation of the step (determining the abnormal location area according to the core pickup, the first auxiliary pickup and the second auxiliary pickup) includes: D1, connecting the core position of the core pickup and the first position of the first auxiliary pickup to obtain a first positioning line.

[0148] It can be understood that the core position is the geographical location where the core pickup is located, the first position is the geographical location where the first auxiliary pickup is installed, and the first positioning line is the positioning line segment for determining the abnormal positioning area, that is, the connecting line between the core position and the first position.

[0149] Through the above implementation, the present invention can obtain a first positioning line, so as to subsequently determine a first core positioning point according to the first positioning line, thereby facilitating subsequent determination of an abnormal positioning area.

[0150] D2, obtaining the abnormal decibel value of the core pickup as the core decibel value, determining the abnormal decibel value of the first auxiliary pickup as the first decibel value, and obtaining the abnormal decibel value of the second auxiliary pickup as the second decibel value.

[0151] It can be understood that the core decibel value is the abnormal decibel value corresponding to the core pickup, for example, it can be 60 decibels, the first decibel value is the abnormal decibel value corresponding to the first auxiliary pickup, for example, it can be 30 decibels, and the second decibel value is the abnormal decibel value of the second auxiliary pickup, for example, it can be 10 decibels.

[0152] D3, obtaining a first decibel total value based on the sum of the core decibel value and the first decibel value, and obtaining a first point ratio based on the ratio of the first decibel value to the first decibel total value.

[0153] It can be understood that the first decibel total value is the sum of the core decibel value and the first decibel value, and the first point ratio is the ratio value corresponding to the first core positioning point, that is, the ratio of the first decibel value to the first decibel total value.

[0154] It is not difficult to understand that by calculating the first point ratio, it is convenient to subsequently determine the distance between the first core positioning point and the core position, and the smaller the first point ratio, the closer the distance between the subsequently determined first core positioning point and the core position.

[0155] D4, obtaining the distance of the first positioning line as the first positioning line distance, obtaining the first positioning distance based on the product of the first point ratio and the first positioning line distance, and determining the direction from the core position to the first position along the first positioning line as the first positioning direction.

[0156] It can be understood that the first positioning line distance is the length distance of the first positioning line, the first positioning distance is the distance for positioning the first core positioning point, that is, the product of the first point ratio and the first positioning line distance, and the first positioning direction is the direction from the core position to the first position along the first positioning line.

[0157] Through the above implementation, the present invention can obtain the first positioning distance and the first positioning direction, so as to subsequently determine the first core positioning point.

[0158] D5, determining a first core positioning point along the first positioning line with the core position as a starting point based on a first positioning direction and the first positioning distance.

[0159] It can be understood that the first positioning distance is moved toward the first positioning direction with the core position as the starting point along the first positioning line, so that the corresponding position point can be used as the first core positioning point.

[0160] Through the above implementation, the present invention can obtain the first core positioning point, so as to subsequently determine the second core positioning point according to the auxiliary microphone, and then obtain the abnormal positioning area, so as to facilitate the subsequent rapid identification of abnormal individuals and improve the identification efficiency.

[0161] D6, connecting the core position of the core pickup and the second position of the second auxiliary pickup to obtain a second positioning line.

[0162] It can be understood that the second position is the geographical location of the second auxiliary pickup, and the second positioning line is a second line segment for assisting in determining the abnormal positioning area, that is, a connecting line connecting the core position and the second position.

[0163] D7, obtaining a second decibel total value based on the sum of the core decibel value and the second decibel value, and obtaining a second point ratio based on the ratio of the second decibel value to the second decibel total value.

[0164] It can be understood that the second decibel total value is the sum of the core decibel value and the second decibel value, and the second point ratio is the position distance ratio for determining the second core positioning point, that is, the ratio of the second decibel value to the second decibel total value.

[0165] Through the above implementation, the present invention can obtain the second point ratio, so as to subsequently determine the corresponding second core positioning point according to the second point ratio.

[0166] D8, obtaining the distance of the second positioning line as the second positioning line distance, obtaining the second positioning distance based on the product of the second point ratio and the second positioning line distance, and determining the direction along the second positioning line from the core position to the second position as the second positioning direction.

[0167] It can be understood that the second positioning line distance is the length distance of the second positioning line, the second positioning distance is the length distance for determining the second core positioning point, that is, the product of the second point ratio and the second positioning line distance, and the second positioning direction is the direction along the second position positioning line from the core position to the second position.

[0168] Through the above implementation, the present invention can determine the second positioning distance and the second positioning direction, so as to subsequently obtain the second core positioning point.

[0169] D9, determining a second core positioning point along the second positioning line with the core position as the starting point based on the second positioning direction and the second positioning distance.

[0170] It can be understood that the second positioning line is moved along the second positioning line with the core position as the starting point toward the second positioning direction by the second positioning distance, so that the corresponding position point can be used as the second core positioning point.

[0171] Through the above implementation, the present invention can obtain the second core positioning point, so as to subsequently determine the third core positioning point according to the auxiliary microphone, and then determine the abnormal positioning area, so as to facilitate the subsequent rapid identification of abnormal individuals and improve the identification efficiency.

[0172] D10, connecting the first position and the second position of the second auxiliary pickup to obtain a third positioning line.

[0173] It can be understood that the second position is the geographical location where the second auxiliary pickup is installed, and the third positioning line is a third line segment for determining the abnormal positioning area, that is, a connecting line between the first position and the second position.

[0174] Through the above implementation, the present invention can obtain the third positioning line, so as to subsequently determine the third core positioning point according to the third positioning line, thereby facilitating the subsequent determination of the abnormal positioning area.

[0175] D11, obtaining a third decibel total value based on the sum of the first decibel value and the second decibel value, and obtaining a third point ratio based on the ratio of the second decibel value to the third decibel total value.

[0176] It can be understood that the third decibel total value is the sum of the first decibel value and the second decibel value, and the third point ratio is the ratio value corresponding to the third core positioning point, that is, the ratio of the first decibel value and the second decibel total value.

[0177] It is not difficult to understand that by calculating the third point ratio, it is convenient to subsequently determine the distance between the third core positioning point and the first position, and the smaller the third point ratio, the closer the distance between the subsequently determined third core positioning point and the second position.

[0178] D12, obtaining the distance of the third positioning line as the third positioning line distance, obtaining the third positioning distance based on the product of the third point ratio and the third positioning line distance, and determining the direction from the first position to the second position along the third positioning line as the third positioning direction.

[0179] It can be understood that the third positioning line distance is the length distance of the third positioning line, the third position distance is the distance for positioning the third positioning point, that is, the product of the third point ratio and the third positioning line distance, and the third positioning direction is the direction from the first position to the second position along the third positioning line.

[0180] Through the above implementation, the present invention can obtain the third positioning distance and the third positioning direction, so as to subsequently determine the third core positioning point.

[0181] D13, determining a third core positioning point along the third positioning line with the first position as a starting point based on a third positioning direction and the third positioning distance.

[0182] It can be understood that the third positioning line is moved along the third positioning line with the first position as the starting point and toward the third positioning direction by a third positioning distance, so that the corresponding position point can be used as the third core positioning point.

[0183] Through the above implementation, the present invention can obtain the third core positioning point, so as to subsequently determine the abnormal core positioning point by combining the first core positioning point and the second core positioning point, and then obtain the abnormal positioning area, so as to facilitate the subsequent rapid identification of abnormal individuals and improve the recognition efficiency.

[0184] D14, constructing a first perpendicular line at the first positioning line based on the first core positioning point, constructing a second perpendicular line at the second positioning line based on the second core positioning point, and constructing a third perpendicular line at the third positioning line based on the third core positioning point.

[0185] It should be noted that vertical lines can be constructed on the positioning lines where the core positioning points are located, so that the points where the three vertical lines intersect can be used as abnormal core points, which means that the microphones corresponding to the three positions can all record abnormal sounds. Then, the abnormal core positioning points are determined by the three vertical lines, and then the abnormal positioning area is obtained, which makes the accuracy of the abnormal positioning area higher, thereby facilitating improving the efficiency of finding abnormal individuals.

[0186] It can be understood that the first vertical line is a vertical line passing through the first core positioning point and perpendicular to the first positioning line, the second vertical line is a vertical line passing through the second core positioning point and perpendicular to the second positioning line, and the third vertical line is a vertical line passing through the third core positioning point and perpendicular to the third positioning line.

[0187] D15: If the first perpendicular line, the second perpendicular line and the third perpendicular line have one intersection point, the intersection point is used as the abnormal core positioning point.

[0188] It can be understood that when the three vertical lines intersect at the same position point, the corresponding intersection point can be used as the abnormal core positioning point, so that the corresponding abnormal positioning area can be determined later according to the abnormal core positioning point.

[0189] D16: If the first vertical line, the second vertical line and the third vertical line have three intersection points, obtain the center point of the area corresponding to the three intersection points as the abnormal core positioning point.

[0190] It should be noted that the three constructed vertical lines may not intersect at the same position, that is, when the first vertical line, the second vertical line and the third vertical line have three intersection points, the center point of the area surrounded by the three intersection points can be obtained in sequence as the abnormal core positioning point, so as to subsequently determine the abnormal positioning area based on the abnormal core positioning point.

[0191] See also Figure 3 , is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention, the electronic device 30 includes: a processor 31, a memory 32 and a computer program; wherein The memory 32 is used to store the computer program, which may also be a flash memory. The computer program is, for example, an application program, a functional module, etc. for implementing the above method.

[0192] The processor 31 is used to execute the computer program stored in the memory to implement each step performed by the device in the above method. For details, please refer to the relevant description in the above method embodiment.

[0193] Optionally, the memory 32 may be independent or integrated with the processor 31 .

[0194] When the memory 32 is a device independent of the processor 31, the device may further include: The bus 33 is used to connect the memory 32 and the processor 31 .

[0195] The present invention also provides a readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the methods provided by the various embodiments described above.

[0196] Among them, the readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application-specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). In addition, the ASIC can be located in a user device. Of course, the processor and the readable storage medium can also exist in a communication device as discrete components. The readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0197] The present invention also provides a program product, which includes an execution instruction, which is stored in a readable storage medium. At least one processor of a device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the device implements the methods provided in the above various embodiments.

[0198] In the embodiments of the above-mentioned devices, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0199] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent training method for chickens, characterized in that: include: Controlling the array microphones in the target breeding area to collect the timbre information of the chicken flock in real time, analyzing the timbre information of the chicken flock to obtain abnormal timbre information, and determining the microphone that receives the abnormal timbre information as the positioning microphone; According to the sound pickup positioning strategy and the positioning pickup, an abnormal positioning area is determined, and based on the abnormal timbre information, historical video data collected by a region collection device corresponding to the abnormal positioning area is retrieved, and abnormal individuals are determined according to the historical video data; Controlling the mobile monitoring device to move to the abnormal location area, and controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device; When it is determined that the mobile monitoring device is at the location of the abnormal individual, the mobile monitoring device is controlled to lock and monitor the abnormal individual, and the obtained locked monitoring video data is sent to the management end.

2. The method according to claim 1, characterized in that The determining of the abnormal positioning area according to the sound pickup positioning strategy and the positioning pickup includes: Acquire the abnormal decibel value corresponding to the abnormal timbre information received by each of the positioning pickups, sort the positioning pickups in descending order based on the abnormal decibel value, and obtain a sound pickup selection sequence; Selecting the first positioning pickup in the sound picking sequence as the core pickup, determining the second positioning pickup in the sound picking sequence as the first auxiliary pickup, and selecting the third positioning pickup in the sound picking sequence as the second auxiliary pickup; An abnormality positioning area is determined based on the core pickup, the first auxiliary pickup, and the second auxiliary pickup.

3. The method according to claim 2, characterized in that The determining of the abnormal location area according to the core pickup, the first auxiliary pickup and the second auxiliary pickup comprises: Connecting the core position of the core pickup and the first position of the first auxiliary pickup to obtain a core positioning line; Acquire the abnormal decibel value of the core pickup as the core decibel value, and determine the abnormal decibel value of the first auxiliary pickup as the first decibel value; Determine an initial core positioning point according to the core positioning line, the core decibel value and the first decibel value; Connecting the first position with the second position of the second auxiliary pickup to obtain an auxiliary positioning line; Acquire an abnormal decibel value of the second auxiliary pickup as a second decibel value, and determine an abnormal core positioning point according to the initial core positioning point, the auxiliary positioning line and the second decibel value; With the abnormal core positioning point as the center of the circle and based on the preset abnormal radius, an abnormal positioning area is generated.

4. The method according to claim 3, characterized in that The step of determining an initial core positioning point according to the core positioning line, the core decibel value and the first decibel value includes: A core decibel total value is obtained based on the sum of the core decibel value and the first decibel value, and a core point ratio is obtained based on the ratio of the first decibel value to the core decibel total value; Acquire the distance of the core positioning line as the core positioning line distance, obtain the core positioning distance based on the product of the core point ratio and the core positioning line distance, and determine the direction from the core position to the first position along the core positioning line as the core positioning direction; An initial core positioning point is determined along the core positioning line with the core position as a starting point based on the core positioning direction and the core positioning distance.

5. The method according to claim 3, characterized in that: The step of determining the abnormal core positioning point according to the initial core positioning point, the auxiliary positioning line and the second decibel value includes: Determine the endpoint at the first position on the auxiliary positioning line as the first endpoint, and determine the endpoint at the second position on the auxiliary positioning line as the second endpoint; The first end point of the auxiliary positioning line is translated to the initial core positioning point of the core positioning line to obtain a core offset line; Obtaining an auxiliary decibel total value according to the sum of the second decibel value and the first decibel value, and obtaining an offset point ratio based on a ratio of the second decibel value to the auxiliary decibel total value; Acquire the distance of the auxiliary positioning line as the auxiliary positioning line distance, obtain the offset positioning distance based on the product of the offset point ratio and the auxiliary positioning line distance, and determine the direction from the first end point to the second end point along the core offset line as the offset positioning direction; Taking the initial core positioning point as a starting point along the core offset line, an abnormal core positioning point is determined based on an offset positioning direction and the offset positioning distance.

6. The method according to claim 5, characterized in that The method of retrieving the historical video data collected by the area collection device corresponding to the abnormal positioning area based on the abnormal timbre information, and determining the abnormal individual according to the historical video data, includes: Acquire abnormal time information corresponding to the abnormal timbre information, and retrieve historical video data collected by a collection device corresponding to the abnormal positioning area based on the abnormal time information; Identifying an individual who performs a vocalization action in the historical video data as an execution individual, and obtaining the execution quantity of the execution individual; When it is determined that the execution quantity is equal to 1, the execution individual is regarded as an abnormal individual; When it is determined that the execution number is greater than 1, obtaining the identification video data collected by the regional collection device based on a preset statistical duration; Obtaining the number of abnormalities of each of the execution individuals in the identified video data and the abnormal area of ​​the observation area corresponding to each of the execution individuals; Obtaining a frequency coefficient according to the ratio of the abnormal frequency to the reference frequency, and obtaining a first discrimination value according to the product of the frequency coefficient and the frequency weight value; Obtaining the total area of ​​the observation area, obtaining an abnormal area ratio according to a ratio of the abnormal area to the total area, obtaining an abnormal area coefficient based on a ratio of the abnormal area ratio to a reference area ratio, and obtaining a second discrimination value according to a product of the abnormal area coefficient and a ratio weight value; The total discrimination value of each execution individual is obtained according to the sum of the first discrimination value and the second discrimination value, and when it is determined that the total discrimination value is greater than the preset discrimination value, the corresponding execution individual is regarded as an abnormal individual.

7. The method according to claim 6, characterized in that The step of controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device comprises: Acquire the real-time video data collected by the area acquisition device, and identify abnormal pixel values ​​corresponding to abnormal individuals in the real-time video data; Based on the abnormal pixel value, the mobile monitoring device is controlled to move to the position of the abnormal individual.

8. The method according to claim 6, characterized in that The step of controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device comprises: Acquire the real-time video data collected by the area acquisition device, acquire the center point of the picture corresponding to the real-time video data, and perform coordinate processing on the real-time video data with the center point of the picture as the coordinate origin; The coordinates of the abnormal individual are determined as abnormal positioning coordinates, and the mobile monitoring device is controlled to move to the position of the abnormal individual based on the abnormal positioning coordinates.

9. The method according to claim 6, characterized in that The step of controlling the mobile monitoring device to move to the location of the abnormal individual according to the real-time video data collected by the area collection device comprises: Acquiring real-time video data collected by the regional collection device; The relative position relationship between the mobile monitoring device and the abnormal individual in the real-time video data is analyzed in real time, and the mobile monitoring device is controlled to move until the relative position relationship between the mobile monitoring device and the abnormal individual is a positive upper vertical position relationship, and then the movement is stopped.

10. The method according to claim 2, characterized in that Also includes: Acquire the number of sounds picked up by the positioning pickup in the sound picking sequence, and when it is determined that the number of sounds picked up is equal to 2, select the first positioning pickup in the sound picking sequence as the core pickup, and determine the second positioning pickup in the sound picking sequence as the first auxiliary pickup; Connecting the core position of the core pickup and the first position of the first auxiliary pickup to obtain a core positioning line; Acquire the abnormal decibel value of the core pickup as the core decibel value, and determine the abnormal decibel value of the first auxiliary pickup as the first decibel value; A core decibel total value is obtained based on the sum of the core decibel value and the first decibel value, and a core point ratio is obtained based on the ratio of the first decibel value to the core decibel total value; Acquire the distance of the core positioning line as the core positioning line distance, obtain the core positioning distance based on the product of the core point ratio and the core positioning line distance, and determine the direction from the core position to the first position along the core positioning line as the core positioning direction; Taking the core position as a starting point along the core positioning line, determining an abnormal core positioning point based on the core positioning direction and the core positioning distance; When it is determined that the number of picked-up sounds is equal to 1, the position of the positioning pickup is obtained as the abnormal core positioning point; With the abnormal core positioning point as the center of the circle and based on the preset abnormal radius, an abnormal positioning area is generated.

Images