A yak intelligent breeding monitoring system and monitoring method

Abstract

The present application discloses a yak intelligent breeding monitoring system and monitoring method, which relates to the field of intelligent breeding. It includes an infrared temperature detection module, a data acquisition module, a data analysis module and an early warning module. When in use, the infrared temperature detection module is used to first obtain a first infrared temperature image and several second infrared temperature images of a target breeding area, and then a stock forage prediction model is generated for the target breeding area according to the first infrared temperature image and the second infrared image; finally, grazing early warning information is generated for the target breeding area according to the stock forage prediction model; the present application can generate a prediction model according to the stock forage in the target breeding area, thereby evaluating the animal husbandry capacity of the stock forage, scientifically determining whether the stock forage is compatible with the number of herds, and issuing an early warning message before the forage in the target breeding area is over-consumed, prompting the replacement of the target breeding area, thereby realizing the scientific rotation of different target breeding areas and realizing the rational use of the entire pasture.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent management of animal husbandry, and in particular to an intelligent yak breeding monitoring system and method. Background Art

[0002] Yaks are traditional large livestock in Tibetan areas with a long history of breeding. Traditional yak breeding methods mainly include free-range and captive breeding. However, the current situation of yaks is that they are strong in summer, fat in autumn, thin in winter, and die in spring. In addition, there is a lack of automatic and intelligent breeding technology, the ecological environment is severely damaged, diseases occur frequently, and the breeding efficiency is low.

[0003] In recent years, with the continuous development of science and technology, intensive breeding of yaks has gradually emerged. Through scientific management and technical means, intensive breeding can effectively improve the efficiency and benefits of yak breeding. The key points of intensive breeding mainly include scientific division and management of cattle herds, rational use of pastures, rational construction of sheds and pens, and disease prevention.

[0004] In terms of the rational use of pastures, the growth of pasture grass is affected by factors such as pastoral weather, yak food intake, yak trampling, etc. The above factors are highly random, and the existing breeding technology lacks corresponding monitoring methods, which leads to a lack of scientific basis for the use of pastures and the inability to use pastures rationally. Summary of the invention

[0005] The present application provides an intelligent yak breeding monitoring system and a monitoring method, aiming to solve the technical problem of unreasonable pasture utilization existing in the prior art.

[0006] In order to solve the above technical problems, the embodiment of the present application provides an intelligent yak breeding monitoring system, including:

[0007] The infrared temperature detection module is used to obtain a first infrared temperature image of a target breeding area at a first moment, and obtain a plurality of second infrared temperature images of the target breeding area at a second moment, wherein the first moment is a certain time before the target breeding area is activated, and the second moment is a certain time after the yaks return to the pens every evening after the target breeding area is activated;

[0008] A data acquisition module, used for acquiring the first infrared temperature image and each of the second infrared temperature images;

[0009] A data analysis module, configured to generate a forage stock prediction model for the target breeding area according to the first infrared temperature image and the second infrared image;

[0010] An early warning module is used to generate grazing early warning information for the target breeding area according to the existing forage prediction model.

[0011] Optionally, the monitoring system also includes a number of detection beacons, each of which is placed in a fully grass-covered area, a semi-grass-covered area and a bare soil area; the infrared temperature detection module includes a drone and an infrared thermal imager, and the infrared thermal imager is arranged on the drone.

[0012] Correspondingly, the present application also discloses a monitoring method based on the above-mentioned intelligent yak breeding monitoring system, comprising the following steps:

[0013] Dividing the pasture into a number of breeding areas, and selecting one of the breeding areas as a target breeding area;

[0014] Taking a first infrared temperature image of the target breeding area at a first moment, and taking a plurality of second infrared temperature images of the target breeding area at a second moment, wherein the first moment is a certain time before the target breeding area is activated, and the second moment is a certain time after the yaks return to the pens every evening after the target breeding area is activated;

[0015] Acquire the first infrared temperature image and each of the second infrared temperature images;

[0016] generating a forage stock prediction model for the target breeding area according to the first infrared temperature image and each of the second infrared images;

[0017] Grazing warning information is generated for the target breeding area according to the stock forage prediction model.

[0018] Optionally, dividing the pasture into a number of breeding areas, and selecting one of the breeding areas as a target breeding area, comprises the following steps;

[0019] Manually survey the forage stock in each area of ​​the pasture;

[0020] Get a three-dimensional topographic map of the ranch;

[0021] The pasture is divided into several breeding areas according to the forage stock and the three-dimensional topographic map of the pasture, and the total amount of forage in each breeding area does not exceed 5%;

[0022] One of the breeding areas is randomly selected as the target breeding area.

[0023] Optionally, acquiring a first infrared temperature image of the target breeding area at a first moment, and acquiring a plurality of second infrared temperature images of the target breeding area at a second moment, comprises the following steps:

[0024] Selecting a first identification area, a second identification area and a third identification area in the target breeding area, wherein the first identification area identifies a fully grass-covered area, the second identification area is a semi-grass-covered area, and the third identification area is a bare soil area;

[0025] Disposing detection beacons and guardrails for protecting the detection beacons in the first identification area, the second identification area, and the third identification area respectively;

[0026] Set data collection paths and flight parameters for target breeding areas;

[0027] At a first moment, controlling the drone to acquire a first infrared temperature image of the target breeding area according to the data acquisition path and flight parameters;

[0028] At the second moment, the UAV is controlled to acquire a second infrared temperature image of the target breeding area according to the data acquisition path and flight parameters.

[0029] Optionally, generating a forage stock prediction model for the target breeding area according to the first infrared temperature image and the second infrared image comprises the following steps:

[0030] Acquire a first infrared temperature image and each of the second infrared temperature images;

[0031] Identify a first identification area, a second identification area, and a third identification area on the first infrared temperature image and each of the second infrared temperature images according to the detection beacon;

[0032] Obtain a first standard temperature set {T1, T2, T3} of the first infrared temperature image and a second standard temperature set {T1', T2', T3'}1, {T1', T2', T3'}2, ... {T1', T2', T3'} of each second infrared temperature image n ; Wherein T1, T2, T3 represent the standard temperatures of the first identification area, the second identification area and the third identification area in the first infrared temperature image respectively; T1', T2', T3' represent the standard temperatures of the first identification area, the second identification area and the third identification area in the second infrared temperature image respectively, and n represents the number of the second standard temperature set determined according to the number of days the target breeding area is used;

[0033] The initial forage quantity Q0 of the target breeding area is calculated according to the first standard temperature set, and the stock forage quantities Q1, Q2, ..., Q3 of the target breeding area are calculated according to the second standard temperature sets. n ;

[0034] According to the initial forage amount Q0 and the stock forage amounts Q1, Q2, ..., Q n Fit and generate a model for predicting forage stock.

[0035] Optionally, calculating the initial forage amount Q0 of the target breeding area according to the first standard temperature set includes the following steps:

[0036] Get the first standard temperature set {T1, T2, T3};

[0037] Identifying a first temperature zone, a second temperature zone, and a third temperature zone on the first infrared temperature image, wherein the temperature of the first temperature zone is T1, the temperature of the second temperature zone is T2, and the temperature of the third temperature zone is T3;

[0038] generating contour curves for the first temperature zone, the second temperature zone, and the third temperature zone, respectively;

[0039] Calculate a first area S1 of the first temperature zone, a second area S2 of the second temperature zone, and a third area S3 of the third temperature zone;

[0040] The initial forage amount is calculated according to the initial forage amount calculation formula, wherein the initial forage amount calculation formula is Q0=aS1+bS2+cS3; wherein a, b and c represent calculation coefficients.

[0041] Optionally, calculating the first area S1 of the first temperature zone, the second area S2 of the second temperature zone, and the third area S3 of the third temperature zone comprises the following steps:

[0042] generating a segmentation network, wherein the segmentation network has a plurality of standard grids of unit area;

[0043] Segmenting the first infrared temperature image having the contour curve generated by the segmentation network to generate a plurality of calculation units;

[0044] Respectively calling each calculation unit to round or straighten the contour curve in each calculation unit;

[0045] Calculate the first partition area s of each calculation unit according to the rounded or straightened contour curve 1i 、The area of ​​the second partition s 2i and the third partition area s 3i , where i represents the number of the computing unit;

[0046] The first area S1 is calculated based on the areas of the first sub-areas; the second area S2 is calculated based on the areas of the second sub-areas; the third area S3 is calculated based on the areas of the third sub-areas, wherein , , , where m represents the number of computing units and i represents the number of computing units.

[0047] Optionally, according to the initial forage amount Q0 and the stock forage amounts Q1, Q2, ..., Q n The model for the prediction of stock forage is generated by fitting, which is characterized by:

[0048] Establishing a standard coordinate system, wherein the horizontal axis of the standard coordinate system represents the number of days the target breeding area is used, and the vertical axis represents the amount of forage;

[0049] Get the initial forage amount Q0 and the stock forage amounts Q1, Q2, ..., Q n ;

[0050] Combine the target breeding area with the number of days to generate the calculated coordinates (Q0, 0), (Q1, 1), (Q2, 2), ... (Q n , n);

[0051] Obtaining a calculation point in a standard coordinate system according to the calculation coordinates;

[0052] A fitting calculation is performed according to each of the calculation points to obtain a stock forage change curve, and the stock forage change curve is used as a stock forage prediction model.

[0053] Optionally, generating grazing warning information for the target breeding area according to the stock forage prediction model includes the following steps:

[0054] Setting warning thresholds;

[0055] Retrieve the forage stock prediction model;

[0056] Importing the warning threshold into the stock forage prediction model to calculate the remaining grazing days;

[0057] Generate grazing warning information based on the calculated remaining grazing days.

[0058] Compared with the prior art, this application has the following beneficial effects:

[0059] The present application includes an infrared temperature detection module, a data acquisition module, a data analysis module and an early warning module, and also discloses a corresponding monitoring method. First, a first infrared temperature image and several second infrared temperature images of a target breeding area are acquired through the infrared temperature detection module, and then a stock forage prediction model is generated for the target breeding area according to the first infrared temperature image and the second infrared image; finally, grazing early warning information is generated for the target breeding area according to the stock forage prediction model.

[0060] Compared with the prior art, firstly, the present application can generate a corresponding prediction model based on the stock of forage in the target breeding area after daily grazing, and thus evaluate the animal husbandry capacity of the stock of forage according to the prediction model, so as to scientifically determine whether the stock of forage is compatible with the number of herds, thereby issuing an early warning message before the forage in the target breeding area is over-consumed, prompting herders to change the target breeding area within the pasture, and then realizing the rotation of different target breeding areas within the entire pasture, so as to avoid excessive grazing of the pasture grass, causing pasture degradation or desertification, and realizing the rational use of the entire pasture.

[0061] Secondly, due to the grazing of yaks, the coverage of grass will gradually decrease, while the area of ​​bare soil and semi-covered areas will continue to increase. Due to the obstruction of grass and the influence of photosynthesis, the temperature changes in the full grass coverage area, semi-covered area and fully bare area are completely different, that is, the temperature of the fully bare area is most affected by the ambient temperature, followed by the semi-obstructed area of ​​grass, and the fully covered area is the least affected. Therefore, the temperatures of the above three areas will also be completely different. The above areas can be quickly and accurately distinguished through infrared temperature images, thereby improving the timeliness and accuracy of the prediction.

[0062] Finally, the basic parameters of the stock forage prediction model described in this application are the infrared temperature image before the target breeding area is activated and the infrared temperature image after the yaks return to the pen every evening after the target breeding area is activated. The above parameters respectively reflect the original state of the target breeding area and the state after the end of grazing every day. The changes in the above parameters truly reflect the actual changing state of the forage, so there is no need to consider the number of yaks and the total food intake, thereby reducing the difficulty of data collection as much as possible and providing the accuracy of the prediction model and grazing warning information. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the specific implementation of the present application or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0064] Figure 1 This is a structural diagram of an intelligent yak breeding monitoring system involved in this application;

[0065] Figure 2 This is a structural diagram of the control terminal described in Implementation Example 1 of this application;

[0066] Figure 3 This is a flow chart of the monitoring method described in Embodiment 2 of the present application;

[0067] Figure 4 This is the principle diagram of segmentation of the segmentation network;

[0068] Figure 5 for Figure 4 The calculation principle diagram of the calculation unit A in FIG.

[0069] Figure 6 This is the prediction principle diagram of the stock forage prediction model.

[0070] Figure numerals: 1-infrared temperature detection module, 2-data acquisition module, 3-data analysis module, 4-early warning module, 5-detection beacon, 6-control terminal, 101-drone, 102-infrared thermal imager.

[0071] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0073] The precise feeding method for livestock and poultry based on image recognition of the present application, when judging the food intake and weight of individual livestock and poultry, is not simply judged by setting a threshold, but analyzed and judged by a deep learning model, which can better adapt to the differences between different livestock and poultry individuals, thereby improving the accuracy of judgment. In addition, the precise feeding method for livestock and poultry based on image recognition described in the present application can monitor the feeding situation and weight changes of livestock and poultry in real time. If a problem is found, an alarm message can be sent to the feeder in time, so that measures can be taken in time to ensure the healthy growth of livestock and poultry. It can be seen that the present application greatly improves the breeding efficiency, reduces labor costs, and improves economic benefits through automated monitoring and intelligent judgment.

[0074] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components in a certain specific posture. If the specific posture changes, the directional indication will also change accordingly.

[0075] In this application, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0076] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing in the full text includes three parallel schemes. Taking "A and / or B" as an example, it includes scheme A, or scheme B, or a scheme that satisfies both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0077] Embodiment 1:

[0078] Reference Figure 1 and Figure 2 This embodiment discloses an intelligent yak breeding monitoring system, including an infrared temperature detection module 1, wherein the infrared temperature detection module 1 includes a drone 101 and an infrared thermal imager, wherein the infrared thermal imager is installed on the drone 101; the infrared thermal imager has a data storage card;

[0079] Further, the monitoring system also includes a control terminal 6, which is preferably a computer, and is provided with a data acquisition module 2, a data analysis module 3 and an early warning module 4, wherein the data acquisition module 2 includes a USB interface and a card reader adapted for a data storage card of the infrared thermal imager, and the data acquisition module 2 is used to acquire the first infrared temperature image and each of the second infrared temperature images;

[0080] The data analysis module 3 is used to generate a stock forage prediction model for the target breeding area according to the first infrared temperature image and the second infrared image; the warning module 4 is used to generate grazing warning information for the target breeding area according to the stock forage prediction model;

[0081] Furthermore, the monitoring system also includes a number of detection beacons 5. Before use, the herders need to select a grass-covered area, a grass-covered area, and a bare soil area in each breeding area of ​​the pasture according to actual observations, and at least one of the above areas is selected, and a detection beacon 5 is set in each area;

[0082] It should be noted that the detection beacon 5 can be a display board with special colors or other special marks. When installing, a guardrail needs to be set around the detection beacon 5 to prevent yaks from damaging the detection beacon 5.

[0083] Of course, the detection beacon 5 can also be a position coordinate. In the actual monitoring process, it can be marked in the three-dimensional topographic map of the pasture according to the above position coordinate.

[0084] Embodiment 2:

[0085] Reference Figures 3 to 6 This embodiment, as another optional embodiment of the present application, discloses a method for intelligent yak breeding monitoring, comprising the following steps:

[0086] S1. Divide the pasture into several breeding areas, and select one of the breeding areas as a target breeding area;

[0087] S11. Manually survey the forage stock in each area of ​​the pasture;

[0088] The amount of grass stock in different areas of the pasture was obtained by manual field survey, so as to determine the distribution and area of ​​grass in different areas, that is, to determine the distribution and area of ​​the full grass coverage area, the semi-grass coverage area and the bare soil area;

[0089] S12, obtaining a three-dimensional topographic map of the pasture;

[0090] S13. Divide the pasture into several breeding areas according to the forage stock and the three-dimensional topographic map of the pasture, where the total amount of forage in each breeding area does not exceed 5%;

[0091] The pasture is divided by combining the grass stock volume parameters collected on site and the three-dimensional topographic map, so as to reasonably allocate the distribution of the grass-covered area, the grass-semi-covered area and the bare soil area, that is, the total amount of grass in each breeding area is basically the same by adjusting the area of ​​different regions. Preferably, the deviation of the total amount of grass in each breeding area does not exceed 5%;

[0092] S14. Randomly select one of the breeding areas as a target breeding area.

[0093] S2, acquiring a first infrared temperature image of the target breeding area at a first moment, and acquiring a plurality of second infrared temperature images of the target breeding area at a second moment, wherein the first moment is a certain time before the target breeding area is activated, and the second moment is a certain time after the yaks return to the pens every evening after the target breeding area is activated;

[0094] S21, selecting a first marked area, a second marked area and a third marked area in the target breeding area, wherein the first marked area indicates a fully covered area with grass, the second marked area indicates a semi-covered area with grass, and the third marked area indicates a bare soil area;

[0095] After the target breeding area is determined, a first identification area, a second identification area and a third identification area are selected in the target breeding area, wherein the first identification area identifies a fully covered area with forage grass, the second identification area is located in a semi-covered area with forage grass, and the third identification area is located in a bare soil area;

[0096] It should be noted that at least one of the first identification area, the second identification area and the third identification area must be set, and the specific number is determined according to the terrain conditions and actual needs;

[0097] S22, respectively setting detection beacons and guardrails for protecting the detection beacons in the first identification area, the second identification area, and the third identification area;

[0098] After the first identification area, the second identification area and the third identification area are determined, detection beacons are respectively set in the first identification area, the second identification area and the third identification area, and then protection fences are set;

[0099] The protective fence can ensure that the detection beacon will not be damaged or moved by the migration of yaks, thus ensuring the accuracy of the detection;

[0100] The detection beacon may also be a virtual beacon, which is the three-dimensional coordinate of each identification area; the virtual coordinate is not only lower in cost;

[0101] By setting detection beacons, the temperature characteristics of typical grass-covered areas, grass-covered areas and bare soil areas can be directly, accurately and quickly obtained on the acquired infrared temperature images, thereby providing a standard for feature extraction in subsequent steps, which is conducive to improving the accuracy of prediction;

[0102] Secondly, by detecting beacons, the difficulty of identifying different areas can be effectively reduced, which is not only conducive to improving the accuracy of identification, but also facilitates computer automatic identification and improves prediction efficiency.

[0103] S23, setting a data collection path and flight parameters for the target breeding area;

[0104] The data collection path and flight parameters (such as flight altitude and flight speed) are designed according to the actual conditions of the target breeding area. The above data settings can ensure the safety of UAV flight on the one hand, and on the other hand, can ensure the consistency of various conditions in the process of UAV data collection as much as possible, thereby ensuring the accuracy and consistency between different infrared temperature images, that is, obtaining infrared temperature images based on the single variable control principle, and improving the reliability and accuracy of the prediction results.

[0105] S24, controlling the drone to acquire a first infrared temperature image of the target breeding area according to the data acquisition path and flight parameters at a first moment;

[0106] S25. At a second moment, control the UAV to obtain a second infrared temperature image of the target breeding area according to the data collection path and flight parameters.

[0107] It should be pointed out that the first moment is a certain time before the target breeding area is put into use, and the second moment is a certain time after the yaks return to the pens every evening after the target breeding area is put into use; the above moments are determined according to actual conditions. For example, according to the grazing habits of herders, they generally let the yaks out of the cowshed in the morning or early morning, and drive the yaks back to the cowshed in the evening every day. In this case, the first moment is set before grazing on the first day of the activation of the target breeding area, such as 7 o'clock in the morning, and the second moment is set at 7 o'clock in the evening every day.

[0108] S3, acquiring the first infrared temperature image and each of the second infrared temperature images;

[0109] At the first moment and the second moment, the UAV is controlled to fly along the data collection path and the flight parameters set in step S23, and when the UAV reaches the designated shooting area during the flight, the infrared thermal imager is controlled to shoot and obtain the corresponding infrared temperature image;

[0110] S4. generating a forage stock prediction model for the target breeding area according to the first infrared temperature image and each of the second infrared images;

[0111] S41, acquiring a first infrared temperature image and each of the second infrared temperature images;

[0112] S42, identifying a first identification area, a second identification area, and a third identification area on the first infrared temperature image and each of the second infrared temperature images according to the detection beacon;

[0113] First, a special appearance feature or other specific mark of the detection beacon is identified on the first infrared temperature image, thereby identifying the detection beacon, and then identifying the first identification area, the second identification area and the third identification area on the first infrared temperature image;

[0114] Using the same method, the first identification area, the second identification area and the third identification area are identified on each of the second infrared temperature images that have been acquired;

[0115] S43, obtaining a first standard temperature set {T1, T2, T3} of the first infrared temperature image and a second standard temperature set {T1', T2', T3'}1, {T1', T2', T3'}2, ... {T1', T2', T3'} of each second infrared temperature image n; Wherein T1, T2, T3 represent the standard temperatures of the first identification area, the second identification area and the third identification area in the first infrared temperature image respectively; T1', T2', T3' represent the standard temperatures of the first identification area, the second identification area and the third identification area in the second infrared temperature image respectively, and n represents the number of the second standard temperature set determined according to the number of days the target breeding area is used;

[0116] After the first identification area, the second identification area and the third identification area are identified on the first infrared temperature image, a first standard temperature set {T1, T2, T3} of the first infrared temperature image is automatically identified and obtained, wherein T1, T2, T3 represent the standard temperatures of the first identification area, the second identification area and the third identification area in the first infrared temperature image, respectively;

[0117] Then, the same method is used to obtain the second standard temperature set {T1', T2', T3'}1, {T1', T2', T3'}2, ... {T1', T2', T3'} of each second infrared temperature image. n ; T1', T2', T3' respectively represent the standard temperatures of the first identification area, the second identification area and the third identification area in the second infrared temperature image, and n represents the number of the second standard temperature set; that is, if three second infrared temperature images have been acquired, n=3;

[0118] S44, calculating the initial forage quantity Q0 of the target breeding area according to the first standard temperature set, and calculating several stock forage quantities Q1, Q2, ..., Q3 of the target breeding area according to each of the second standard temperature sets. n ;

[0119] S441, obtaining a first standard temperature set {T1, T2, T3};

[0120] S442, identifying a first temperature zone, a second temperature zone, and a third temperature zone on the first infrared temperature image, wherein the temperature of the first temperature zone is T1, the temperature of the second temperature zone is T2, and the temperature of the third temperature zone is T3;

[0121] Taking the acquired first standard temperature set {T1, T2, T3} as a reference, marking all areas with a temperature of T1 on the first infrared temperature image as first temperature zones;

[0122] The same method is used to identify the second temperature zone and the third temperature zone respectively;

[0123] It should be pointed out that in actual operation, considering the detection error, a corresponding identification interval can be set in the first standard temperature set {T1, T2, T3}, that is, the temperature in [T1-t, T1+t] can be identified as the first temperature zone, where t is the allowable error;

[0124] S443, generating contour curves for the first temperature zone, the second temperature zone, and the third temperature zone respectively;

[0125] When the first temperature zone, the second temperature zone and the third temperature zone, a contour curve is automatically generated at the junction of each area;

[0126] S444, calculating a first area S1 of the first temperature zone, a second area S2 of the second temperature zone, and a third area S3 of the third temperature zone;

[0127] S4441, generating a segmentation network, wherein the segmentation network has a plurality of standard grids of unit area;

[0128] The segmentation network is automatically generated by a computer, wherein the segmentation network is a grid, each square has a unit area, that is, the area of ​​each square is 1; the number of squares on the segmentation network is determined according to needs, and each square is a standard grid;

[0129] S4442, segmenting the first infrared temperature image having the contour curve by the segmentation network to generate a plurality of calculation units;

[0130] Reference Figure 4 , overlapping the segmentation network with the first infrared temperature image, wherein the area of ​​the segmentation network is larger than the area of ​​the first infrared temperature image, thereby ensuring that the segmentation network covers the entire first infrared temperature image;

[0131] After the overlap is completed, the first infrared temperature image with the contour curve generated can be segmented into a number of calculation units through the segmentation network, and each calculation unit is numbered after the segmentation;

[0132] Based on the principle of cutting a circle, the above cutting can cut the contour curve into a straight line as much as possible, thereby reducing the difficulty of calculation.

[0133] S4443, respectively call each calculation unit to round or straighten the contour curve in each calculation unit;

[0134] Reference Figure 5 , if there is a curve in the calculation unit, it will be converted into a straight line or a polyline segment, and if there is a complete ellipse or an approximate circle, it will be rounded into a circle;

[0135] The above technical measures can further correct the contour curve and further reduce the difficulty of calculation;

[0136] S4444. Calculate the first partition area s of each calculation unit according to the rounded or straightened contour curve. 1i 、The area of ​​the second partition s 2i and the third partition area s 3i , where i represents the number of the computing unit;

[0137] Call any computing unit, such as Figure 5 As shown in the figure, the rounded or straightened contour curve realizes the standard division of the calculation unit, and the area s of the first partition can be automatically calculated by the computer. 1i 、The area of ​​the second partition s 2i and the third partition area s 3i , where i represents the number of the calculation unit; the first partition represents the area of ​​the full grass coverage area in the calculation unit, the second partition represents the area of ​​the semi-grass coverage area, and the third partition represents the area of ​​the bare soil area;

[0138] Repeat the above steps to get the first partition area s of all calculation units. 1i 、The area of ​​the second partition s 2i and the third partition area s 3i ;

[0139] By dividing the above data, we can get the following data set {s 11 、s 12 ,...,s 1i ,...,s 1m}、{s 21 、s 22 ,...,s 2i ,...,s 2m}、{s 31 、s 32 ,...,s 3i ,...,s 3m};

[0140] It should be pointed out that the areas of the above-mentioned partitions can also be calculated by integral calculation.

[0141] S4445, calculating the first area S1 according to the areas of the first sub-areas; calculating the second area S2 according to the areas of the second sub-areas; calculating the third area S3 according to the areas of the third sub-areas, wherein , , , where m represents the number of computing units and i represents the number of computing units.

[0142] S445, calculating the initial forage amount according to the initial forage amount calculation formula, wherein the initial forage amount calculation formula is Q0=aS1+bS2+cS3; wherein a, b and c represent calculation coefficients;

[0143] The initial forage amount is calculated according to the calculation formula of the initial forage amount Q0=aS1+bS2+cS3, where a, b and c represent calculation coefficients. It should be noted that the above coefficients can be determined according to actual needs. Preferably, the value of a is 1, the value of b is 0.5, and the value of c is 0;

[0144] The initial forage amount can be obtained by substituting the first area, the second area and the third area obtained in step S4445 into the initial forage amount calculation formula.

[0145] S446, using the steps from S441 to S445, respectively calculate the stock forage quantities Q1, Q2, ..., Q n ;

[0146] The steps S441 to S445 are used to retrieve the second standard temperature sets {T1', T2', T3'}1, {T1', T2', T3'}2, ... {T1', T2', T3'} n The stock of forage Q1, Q2, ..., Q n ;

[0147] S45, based on the initial forage amount Q0 and the stock forage amounts Q1, Q2, ..., Q n Fit and generate a model for predicting forage stock.

[0148] S451, establishing a standard coordinate system, wherein the horizontal axis of the standard coordinate system represents the number of days the target breeding area is used, and the vertical axis represents the amount of forage;

[0149] S452, obtaining the initial forage quantity Q0 and the stock forage quantities Q1, Q2, ..., Q n ;

[0150] S453, combine the target breeding area with the number of days to generate the calculated coordinates (Q0, 0), (Q1, 1), (Q2, 2), ... (Q n , n);

[0151] It should be noted that since the second infrared temperature image is obtained after each grazing day, that is, one second infrared temperature image can be obtained in one grazing day, the number of days used in the target breeding area is exactly the same as the number of the second infrared temperature image;

[0152] Combined with the number of days used in the target breeding area and the amount of forage, the calculation coordinates (Q0, 0), (Q1, 1), (Q2, 2), ... (Q n , n);

[0153] S454, obtaining a calculation point in a standard coordinate system according to the calculation coordinates;

[0154] S455. Perform fitting calculation according to each of the calculation points to obtain a stock forage change curve, and use the stock forage change curve as a stock forage prediction model.

[0155] like Figure 6 As shown, after determining each of the calculation points, the stock forage change curve can be obtained by computer fitting calculation, and the stock forage change curve is used as a stock forage prediction model.

[0156] S5. generating grazing warning information for the target breeding area according to the stock forage prediction model;

[0157] S51, setting a warning threshold;

[0158] It should be pointed out that the warning threshold is generally the forage stock; its value is flexibly determined according to needs, such as the warning threshold is 0.2;

[0159] S52, retrieve the stock forage prediction model;

[0160] S53, importing the warning threshold into the stock forage prediction model to calculate the remaining animal husbandry days;

[0161] like Figure 6 As shown in the figure, the solid line represents the trend of pasture changes in the past few days, while the dotted line represents the trend of future pasture stock changes. The slope change of the pasture stock prediction model clearly reflects the trend of pasture changes. The pasture stock at a certain time point in the future can be predicted based on the above trend.

[0162] The warning threshold is the minimum warning value, which corresponds to a time point in the prediction model;

[0163] S54. Generate grazing warning information according to the calculated remaining grazing days.

[0164] Assuming that the warning threshold is 0.2, the corresponding time point is 10, which means that the warning value will be reached on the 10th day of grazing;

[0165] At this time, the actual number of days the target breeding area is used is 6 days, which means that the target breeding area can still be grazed for 4 days;

[0166] It should be noted that if the calculated result is not an integer, it will be rounded to avoid overgrazing; Figure 6 As shown, assuming that the corresponding time point is 10.4 and grazing has been done for 7 days, the remaining number of days for the target breeding area to be used after rounding is 3 days.

[0167] Different levels are divided according to the number of days of use of the remaining target breeding area, and grazing warning information is generated, as shown in Table 1:

[0168] Table 1

[0169] Remaining days of use of target breeding area 1 day 2-4 days 5-7 days 8 days and above Grazing warning information Stop grazing Reduce or stop grazing Controlling grazing Grazing allowed

[0170] According to the remaining days of use of the target breeding area and the above table, the grazing warning information can be output accordingly.

[0171] Compared with the prior art, firstly, the present application can generate a corresponding prediction model based on the stock of forage in the target breeding area after daily grazing, and thus evaluate the animal husbandry capacity of the stock of forage according to the prediction model, so as to scientifically determine whether the stock of forage is compatible with the number of herds, thereby issuing an early warning message before the forage in the target breeding area is over-consumed, prompting herders to change the target breeding area within the pasture, and then realizing the rotation of different target breeding areas within the entire pasture, so as to avoid excessive grazing of the pasture grass, causing pasture degradation or desertification, and realizing the rational use of the entire pasture.

[0172] Secondly, due to the grazing of yaks, the coverage of grass will gradually decrease, and the area of ​​bare soil and semi-covered areas will continue to increase. Due to the obstruction of grass and the influence of photosynthesis, the temperature changes in the full grass coverage area, semi-covered area and fully bare area are completely different, that is, the temperature of the fully bare area is most affected by the ambient temperature, followed by the semi-obstructed area of ​​grass, and the fully covered area is the least affected. Therefore, the temperatures of the above three areas will also be completely different. The above areas can be quickly and accurately distinguished through infrared temperature images, thereby improving the timeliness and accuracy of the prediction.

[0173] Finally, the basic parameters of the stock forage prediction model described in this application are the infrared temperature image before the target breeding area is activated and the infrared temperature image after the yaks return to the pen every evening after the target breeding area is activated. The above parameters respectively reflect the original state of the target breeding area and the state after the end of grazing every day. The changes in the above parameters truly reflect the actual changing state of the forage, so there is no need to consider the number of yaks and the total food intake, thereby reducing the difficulty of data collection as much as possible and providing the accuracy of the prediction model and grazing warning information.

[0174] The above descriptions are only optional embodiments of the present disclosure, and are not intended to limit the patent scope of the present disclosure. All equivalent structural transformations made using the contents of the present disclosure and the drawings under the inventive concept of the present disclosure, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present disclosure.

Claims

1. A method for intelligent yak breeding monitoring, characterized in that: The following steps are involved: Dividing the pasture into a number of breeding areas, and selecting one of the breeding areas as a target breeding area; Selecting a first identification area, a second identification area and a third identification area in the target breeding area, wherein the first identification area indicates a fully covered area with grass, the second identification area indicates a semi-covered area with grass, and the third identification area indicates a bare soil area; Disposing detection beacons and guardrails for protecting the detection beacons in the first identification area, the second identification area, and the third identification area respectively; Set data collection paths and flight parameters for target breeding areas; At a first moment, controlling the drone to acquire a first infrared temperature image of the target breeding area according to the data acquisition path and flight parameters; At a second moment, the UAV is controlled to obtain a second infrared temperature image of the target breeding area according to the data collection path and the flight parameters; wherein the first moment is a certain time before the target breeding area is activated, and the second moment is a certain time after the yaks return to the pens every evening after the target breeding area is activated; Acquire the first infrared temperature image and each of the second infrared temperature images; Identify a first identification area, a second identification area, and a third identification area on the first infrared temperature image and each of the second infrared temperature images according to the detection beacon; Obtain a first standard temperature set {T1, T2, T3} of the first infrared temperature image and a second standard temperature set {T1', T2', T3'}1, {T1', T2', T3'}2, ... {T1', T2', T3'} of each second infrared temperature image n ; Wherein T1, T2, T3 represent the standard temperatures of the first identification area, the second identification area and the third identification area in the first infrared temperature image respectively; T1', T2', T3' represent the standard temperatures of the first identification area, the second identification area and the third identification area in the second infrared temperature image respectively, and n represents the number of the second standard temperature set determined according to the number of days the target breeding area is used; Retrieve the first standard temperature set {T1, T2, T3}; Identifying a first temperature zone, a second temperature zone, and a third temperature zone on the first infrared temperature image, wherein the temperature of the first temperature zone is T1, the temperature of the second temperature zone is T2, and the temperature of the third temperature zone is T3; generating contour curves for the first temperature zone, the second temperature zone, and the third temperature zone, respectively; Calculate a first area S1 of the first temperature zone, a second area S2 of the second temperature zone, and a third area S3 of the third temperature zone; Calculate the initial forage amount according to the initial forage amount calculation formula, wherein the initial forage amount calculation formula is Q0=aS1+bS2+cS3; wherein a, b and c represent calculation coefficients; Respectively retrieve the second standard temperature sets {T1', T2', T3'}1, {T1', T2', T3'}2, ... {T1', T2', T3'} n , the same calculation method as the initial forage quantity is used to calculate several stock forage quantities Q1, Q2, ..., Q n ; According to the initial forage amount Q0 and the stock forage amounts Q1, Q2, ..., Q n Fit and generate a model for predicting forage stock; Grazing warning information is generated for the target breeding area according to the stock forage prediction model.

2. The intelligent yak breeding monitoring method according to claim 1 is characterized in that: The pasture is divided into several breeding areas, and one of the breeding areas is selected as a target breeding area. The steps include: Manually survey the forage stock in each area of ​​the pasture; Get a three-dimensional topographic map of the ranch; The pasture is divided into several breeding areas according to the forage stock and the three-dimensional topographic map of the pasture, and the total amount of forage in each breeding area does not exceed 5%; One of the breeding areas is randomly selected as the target breeding area.

3. The intelligent yak breeding monitoring method according to claim 2 is characterized in that: The calculating of the first area S1 of the first temperature zone, the second area S2 of the second temperature zone and the third area S3 of the third temperature zone comprises the following steps: generating a segmentation network, wherein the segmentation network has a plurality of standard grids of unit area; Segmenting the first infrared temperature image having the contour curve generated by the segmentation network to generate a plurality of calculation units; Respectively calling each calculation unit to round or straighten the contour curve in each calculation unit; Calculate the first partition area s of each calculation unit according to the rounded or straightened contour curve 1i 、The area of ​​the second partition s 2i and the third partition area s 3i , where i represents the number of the computing unit; The first area S1 is calculated based on the areas of the first sub-areas; the second area S2 is calculated based on the areas of the second sub-areas; the third area S3 is calculated based on the areas of the third sub-areas, wherein , , , where m represents the number of computing units and i represents the number of computing units.

4. The intelligent yak breeding monitoring method according to claim 1 is characterized in that: The stock forage prediction model is generated by fitting the initial forage amount Q0 and each stock forage amount Q1, Q2, ..., Qn, characterized in that: Establishing a standard coordinate system, wherein the horizontal axis of the standard coordinate system represents the number of days the target breeding area is used, and the vertical axis represents the amount of forage; Get the initial forage amount Q0 and the stock forage amounts Q1, Q2, ..., Q n ; Combine the target breeding area with the number of days to generate the calculated coordinates (Q0, 0), (Q1, 1), (Q2, 2), ... (Q n , n); Obtaining a calculation point in a standard coordinate system according to the calculation coordinates; A fitting calculation is performed according to each of the calculation points to obtain a stock forage change curve, and the stock forage change curve is used as a stock forage prediction model.

5. The intelligent yak breeding monitoring method according to claim 1 is characterized in that: The step of generating grazing warning information for the target breeding area according to the stock forage prediction model comprises the following steps: Setting warning thresholds; Retrieve the forage stock prediction model; Importing the warning threshold into the stock forage prediction model to calculate the remaining grazing days; Generate grazing warning information based on the calculated remaining grazing days.

6. An intelligent yak breeding monitoring system, characterized in that: The monitoring system is used to implement the monitoring method described in any one of claims 1 to 5; the monitoring system comprises an infrared temperature detection module (1), which is used to capture a first infrared temperature image of a target breeding area at a first moment, and capture a plurality of second infrared temperature images of the target breeding area at a second moment, wherein the first moment is a certain time before the target breeding area is activated, and the second moment is a certain time after the yaks return to the pens every evening after the target breeding area is activated; A data acquisition module (2), used for acquiring the first infrared temperature image and each of the second infrared temperature images; A data analysis module (3) is used to generate a forage stock prediction model for the target breeding area based on the first infrared temperature image and the second infrared image; An early warning module (4) is used to generate grazing early warning information for the target breeding area according to the existing forage prediction model.

7. The intelligent yak breeding monitoring system according to claim 6 is characterized in that: The breeding monitoring system further comprises a plurality of detection beacons (5), each of the detection beacons (5) being respectively arranged in a grass-fully covered area, a grass-half covered area and a bare soil area; the infrared temperature detection module (1) comprises a drone (101) and an infrared thermal imager, and the infrared thermal imager is arranged on the drone (101).

Images