Grassland livestock capacity monitoring system and method based on tower footing observation equipment

Abstract

The invention provides a grassland livestock capacity monitoring system and method based on tower footing observation equipment. The system comprises a high tower, photoelectric equipment and hyperspectral equipment, wherein the photoelectric equipment and the hyperspectral equipment are arranged on the high tower; the photoelectric equipment is used for monitoring a fixed grassland area in real time and carrying out identification and real-time quantity statistics on livestock animals in the monitored area; the hyperspectral equipment is used for carrying out data acquisition, processing and analysis on a monitoring area of the photoelectric equipment to obtain a vegetation index of the monitoring area; the theoretical livestock capacity in the current monitoring area is calculated according to the function relation between the vegetation index and the area livestock capacity; and the real-time monitoring alarm system is used for selectively sending out an alarm prompt according to the real-time monitoring condition. According to the invention, automatic monitoring of a fixed grassland area is realized, multiple technical means such as remote sensing monitoring, image recognition and hyperspectral data analysis are combined, a more accurate and real-time monitoring effect can be realized, grass and livestock balance is effectively maintained, and a sustainable development concept is embodied.

Description

Technical Field

[0001] The invention relates to the field of environmental technology, and in particular to a monitoring system and method for grassland livestock carrying capacity based on tower-based observation equipment. Background Art

[0002] my country has vast grassland resources, with the total grassland area accounting for about 40% of the country's total land area. Grasslands not only provide rich natural resources for animal husbandry, but also play a vital role in maintaining the balance of the ecosystem. However, with the growth of population and the development of animal husbandry, overgrazing has become an increasingly serious problem, leading to the degradation of grassland ecosystems, which in turn has caused a series of environmental problems such as sandstorms, soil erosion, and soil erosion. Therefore, it is of great significance to monitor and warn the carrying capacity of grassland grazing areas in real time.

[0003] For the monitoring of grassland carrying capacity, traditional manual monitoring methods require a lot of manpower and material resources, and have a long monitoring cycle and uncertainty, making it difficult to timely and accurately feedback changes in grassland status. In addition to traditional manual monitoring, related technologies also include monitoring methods based on satellite remote sensing, but due to the long satellite transit cycle, continuous monitoring cannot be achieved; and in the case of cloud cover, the accuracy and effectiveness of the data will be limited. Summary of the invention

[0004] The present invention provides a grassland livestock carrying capacity monitoring system and method based on tower-based observation equipment, which solves the problem of limited real-time and accuracy of grassland livestock carrying capacity monitoring methods in related technologies.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] In a first aspect, a grassland livestock carrying capacity monitoring system based on a tower-based observation device is provided, comprising:

[0007] A tower is set in the center of a fixed grassland area of ​​known area, the tower being a support frame at a set height from the ground, the height being lower than the cloud height;

[0008] Photoelectric equipment and hyperspectral equipment are arranged on the tower; the photoelectric equipment is used to monitor the fixed grassland area in real time, and identify and count the livestock in the monitoring area in real time; the hyperspectral equipment is used to collect data from the monitoring area of ​​the photoelectric equipment, and obtain the vegetation index of the monitoring area after processing and analysis; the theoretical livestock carrying capacity in the current monitoring area is calculated using the functional relationship between the vegetation index and the regional livestock carrying capacity;

[0009] The real-time monitoring alarm system is used to selectively issue alarm prompts based on the real-time monitoring situation.

[0010] In a first possible implementation manner of the first aspect, the optoelectronic device includes:

[0011] A data acquisition system, the data acquisition system comprising an infrared thermal imager, a visible light camera, and a laser lighting system, the data acquisition system being disposed on a turntable and used to acquire image data of the fixed grassland area;

[0012] A data transmission module, used for transmitting data collected by the data acquisition system;

[0013] A livestock animal identification module for identifying livestock animals based on predefined features;

[0014] The retrieval frame quantity counting module is used to generate a retrieval frame according to the identified livestock and animal, and to count the number of retrieval frames in the image.

[0015] Based on the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, the search box is used to mark the livestock animals appearing in the image, and each search box marks and only marks one livestock animal.

[0016] In a third possible implementation manner of the first aspect, the hyperspectral device includes a hyperspectral camera and a hyperspectral data analysis system, and a data collection area of ​​the hyperspectral camera is consistent with a monitoring area of ​​the optoelectronic device;

[0017] For the monitoring area within the set distance from the tower base, radiation correction is performed using the irradiance sensor correction method;

[0018] For the monitoring area outside the set distance range from the tower base, radiation correction is performed using the mobile multi-grayscale target correction method.

[0019] In a fourth possible implementation manner of the first aspect, the vegetation index includes a normalized vegetation index and an enhanced vegetation index;

[0020] The historical vegetation index and the corresponding stock carrying capacity data within a set time period of the monitoring area are obtained, regression analysis is performed, and a univariate linear regression model is established; the vegetation index is brought into the univariate linear regression model to obtain the theoretical stock carrying capacity.

[0021] Based on the fourth possible implementation of the first aspect, in a fifth possible implementation of the first aspect, the real-time monitoring and alarm system is used to compare the real-time statistical data of the number of livestock animals with the theoretical carrying capacity. If the real-time statistical data is greater than the theoretical carrying capacity, an alarm prompt is issued and real-time observation is continued.

[0022] In a second aspect, a method for monitoring grassland carrying capacity based on a tower-based observation device is provided, and monitoring is performed based on the monitoring system described in the first aspect, comprising:

[0023] Based on the photoelectric equipment installed on the high tower, a fixed grassland area of ​​known area is monitored in real time, and the livestock in the monitoring area are identified and counted in real time;

[0024] Based on the hyperspectral equipment installed on the tower, synchronously collect data of the fixed grassland area, and obtain the corresponding vegetation index after processing and analysis;

[0025] Obtain the historical vegetation index and corresponding livestock carrying capacity data within the set time period of the monitoring area, conduct regression analysis, and establish a univariate linear regression model;

[0026] Substituting the vegetation index into the univariate linear regression model to obtain the theoretical stocking capacity;

[0027] The real-time statistical data of the number of livestock animals is compared with the theoretical carrying capacity. If the real-time statistical data of the number of livestock animals is greater than the theoretical carrying capacity, an alarm is issued, otherwise the system maintains real-time observation.

[0028] In a first possible implementation manner of the second aspect, the real-time monitoring of a fixed grassland area of ​​a known area based on a photoelectric device installed on a high tower, and the identification and real-time counting of livestock animals in the monitoring area include:

[0029] Collecting image data of the fixed grassland area based on a data acquisition system; wherein the data acquisition system includes an infrared thermal imager, a visible light camera and a laser lighting system;

[0030] Based on the image data, identifying livestock animals according to predefined features;

[0031] A corresponding search frame is generated based on the identified livestock and the number of the search frames in the image is counted.

[0032] Based on the first possible implementation manner of the second aspect, in a second possible implementation manner of the second aspect, the search box is used to mark the livestock animal, and each search box marks and only marks one livestock animal.

[0033] Based on any possible implementation of the second aspect, in a third possible implementation of the second aspect, the hyperspectral device disposed on the high tower synchronously collects data on the fixed grassland area, and obtains a corresponding vegetation index after processing and analysis, including:

[0034] For the monitoring area within the set distance from the tower base, radiation correction is performed using the irradiance sensor correction method;

[0035] For the monitoring area outside the set distance range from the tower base, radiation correction is performed using the mobile multi-grayscale target correction method;

[0036] Extract terrain shadows, select corresponding band data, and calculate vegetation index for the effective area; wherein the vegetation index includes normalized vegetation index and enhanced vegetation index.

[0037] Beneficial effects:

[0038] Through real-time monitoring by optoelectronic equipment and hyperspectral equipment, the present application can instantly understand the number of livestock and the health status of vegetation in the grassland area; by utilizing the functional relationship between vegetation index and carrying capacity, the theoretical carrying capacity in the current monitoring area can be accurately calculated, and the dynamic assessment based on the health status of vegetation can more accurately reflect the actual carrying capacity of the grassland.

[0039] This application can realize automatic monitoring of fixed grassland areas through optoelectronic equipment and hyperspectral equipment on high towers, reducing the labor intensity and cost of manual inspections. It combines multiple advanced technologies such as remote sensing monitoring, image recognition, and hyperspectral data analysis. Through technical means, it can effectively remove other interference information such as the atmosphere, and achieve more accurate and real-time monitoring results. It effectively maintains the balance between grass and livestock, and embodies the concept of sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of the workflow of a grassland livestock carrying capacity monitoring system based on a tower-based observation device provided in an embodiment of the present application;

[0041] Figure 2 A schematic flow chart of a grassland livestock carrying capacity monitoring method based on tower-based observation equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose, the technical solutions in the embodiments of the present application are clearly described. Obviously, the described embodiments are 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 belong to the scope of protection of the present application.

[0043] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0044] The description of the method flow in the specification of the present application and the steps of the flowchart in the drawings of the present specification do not have to be strictly executed according to the step numbers, and the method steps can be executed in a different order. Moreover, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0045] In the following, in combination with the accompanying drawings and preferred embodiments, a grassland livestock carrying capacity monitoring system and method based on a tower-based observation device provided in an embodiment of the present application are described in detail as follows.

[0046] In view of the real-time and accuracy issues of the grassland carrying capacity monitoring method based on satellite remote sensing technology, the embodiment of the present application provides a grassland carrying capacity monitoring method based on tower-based observation equipment, which obtains real-time images and vegetation indexes of grassland grazing areas in real time through optoelectronic equipment and hyperspectral equipment installed on high towers, and uses remote sensing monitoring, image recognition, hyperspectral data analysis and other technologies to dynamically monitor, analyze and calculate the theoretical carrying capacity of the current grassland area, and warn grassland areas that exceed the theoretical carrying capacity. It effectively maintains the balance between grass and livestock, and embodies the concept of sustainable development.

[0047] See also Figure 1 The embodiment of the present application provides a grassland livestock carrying capacity monitoring system based on a tower-based observation device. The monitoring system of the embodiment of the present application includes:

[0048] A tower is set in the center of a fixed grassland area of ​​known area, the tower being a support frame at a set height from the ground, the height being lower than the cloud height;

[0049] Photoelectric equipment and hyperspectral equipment are installed on the high tower; the photoelectric equipment is used to monitor the fixed grassland area in real time, and identify and count the livestock in the monitoring area in real time; the hyperspectral equipment is used to collect data from the monitoring area of ​​the photoelectric equipment, and obtain the vegetation index of the monitoring area after processing and analysis; the theoretical livestock carrying capacity in the current monitoring area is calculated using the functional relationship between the vegetation index and the regional livestock carrying capacity;

[0050] The real-time monitoring alarm system is used to selectively issue alarm prompts based on the real-time monitoring situation. When working, if the real-time livestock carrying capacity monitored and counted by the photoelectric equipment is greater than the theoretical livestock carrying capacity calculated by the hyperspectral equipment, the real-time monitoring alarm system will issue an alarm prompt and continue to maintain real-time observation. If the real-time livestock carrying capacity is less than the theoretical livestock carrying capacity, the system will continue to maintain real-time observation of the monitoring area.

[0051] Specifically, the optoelectronic device includes a data acquisition system, which includes an infrared thermal imager, a visible light camera, and a laser lighting system. The data acquisition system is arranged on a turntable and is used to collect image data of the fixed grassland area; a data transmission module is used to transmit the data collected by the data acquisition system; a livestock animal identification module is used to identify livestock animals according to predefined features; and a search box number counting module is used to generate a search box according to the identified livestock animals and count the number of search boxes in the image. Among them, the search box is used to mark the livestock animals appearing in the image, and each search box marks and only marks one livestock animal.

[0052] Photoelectric devices conduct real-time quantity statistics to obtain the number of livestock in the current monitoring area. The search box can accurately point out the location of livestock in the image, helping the system to count more accurately. Through the search box, false positives and missed positives can be reduced, and the number of livestock in the current monitoring area can be quickly understood, improving the accuracy and efficiency of animal identification. At the same time, for operators, the search box makes the identification results more intuitive, making it easier for them to understand and track changes in animals.

[0053] In the specific implementation process, the front end of the optoelectronic equipment is composed of an infrared thermal imager, a visible light camera, a laser lighting system, a turntable, a single-chip microcomputer, and a data transmission module. The back end of the equipment is a device display and control software composed of a device control module, a livestock animal identification module, and a search frame quantity statistics module. When working, real-time image data is transmitted to the back-end livestock animal identification module. The livestock animal identification module compares and identifies the collected image data with the predefined livestock animal features, determines whether there are livestock animals in the collected image data and generates corresponding search frames. The search frame quantity statistics module counts the number of search frames in the image and obtains the livestock capacity in the current monitoring area. The equipment control module, single-chip microcomputer, etc. realize the overall operation of the optoelectronic equipment, including the working status, equipment movement, communication, interaction, etc. of components such as infrared thermal imagers, visible light cameras, and laser lighting.

[0054] The hyperspectral equipment includes a hyperspectral camera and a hyperspectral data analysis system. The data collection area of ​​the hyperspectral camera is consistent with the monitoring area of ​​the optoelectronic equipment. The data of the monitoring area obtained by the hyperspectral camera needs to be transmitted to the hyperspectral data analysis system for preprocessing, which includes geometric correction, atmospheric correction, etc. After preprocessing, the corresponding vegetation index of the grassland area is obtained.

[0055] Since the tower-based platform equipped with the hyperspectral camera is below the cloud layer, the imaging will be affected by the cloud layer and the surrounding aerosol conditions. Therefore, it is necessary to remove other interfering information such as the atmosphere from the image. This application eliminates these atmospheric influences through radiation correction to obtain accurate vegetation index.

[0056] Specifically, the present application adopts the irradiance sensor calibration method directly for the near tower and the mobile multi-grayscale target calibration method for the medium-long distance and large inclination distance according to different calibration distances. That is, for the monitoring area within the set distance range from the tower base, the irradiance sensor calibration method is used for radiation correction.

[0057] The irradiance sensor calibration method is mainly used for close-range monitoring, that is, when the monitoring area is close to the tower base, an irradiance sensor placed near the tower base is used to obtain the radiation intensity under standard lighting conditions.

[0058] The irradiance sensor can measure the intensity of solar radiation reaching the ground, so that the data obtained by the hyperspectral camera can be corrected to remove the influence of atmospheric effects and ensure the accuracy of the data.

[0059] For the monitoring area outside the set distance range from the tower base, radiation correction is performed using the mobile multi-grayscale target correction method.

[0060] The calibration factor is solved by combining the known reflectivity of multi-grayscale targets and obtaining the radiance of the target based on the three target images collected by the hyperspectral imager. The three sets of target reflectivity and radiance values ​​are substituted into the empirical formula to calculate the values ​​of A, B, and C. A, B, and C are the conversion coefficients between the target reflectivity and the radiance measured by the hyperspectral imager, representing the path radiance, the bottom atmospheric albedo, and additional parameters depending on the atmospheric and geometric conditions. The calibration factor is quickly solved through the simultaneous equations. Using the calculated A, B, and C calibration factors, the empirical formula is used again to perform radiation correction on the target scene.

[0061] After obtaining accurate vegetation index, regression analysis was performed based on the vegetation index and corresponding livestock carrying capacity data in each time period in the monitoring area over the past five years, and a univariate linear regression model was established to analyze the vegetation index obtained after real-time data collection.

[0062] Specifically, common vegetation indices include NDVI (Normalized Difference Vegetation Index) and EVI (Enhanced Vegetation Index), etc. These indices are based on ground reflectivity in different bands and can reflect the growth status and density of vegetation.

[0063] The theoretical carrying capacity calculation process includes:

[0064] Accurately extract terrain shadows, select corresponding band data, and calculate the vegetation index for the effective area; extract terrain shadow areas and accurately extract the shielding factor; calculate the normalized vegetation index and enhanced vegetation index; substitute the vegetation index into the univariate linear regression model to obtain the current theoretical carrying capacity.

[0065] See also Figure 2 , the embodiment of the present application provides a grassland livestock carrying capacity monitoring method based on tower-based observation equipment, such as Figure 2 As shown, the grassland carrying capacity monitoring method of the embodiment of the present application is monitored by the grassland carrying capacity monitoring system based on the tower-based observation device, including:

[0066] Step S1, based on the photoelectric equipment installed on the high tower, a fixed grassland area of ​​known area is monitored in real time, and the livestock animals in the monitoring area are identified and counted in real time.

[0067] Step S1 specifically includes the following steps:

[0068] Step S101, collecting image data of the fixed grassland area based on a data collection system; wherein the data collection system includes an infrared thermal imager, a visible light camera and a laser lighting system.

[0069] Step S102: identifying livestock animals according to predefined features based on the image data.

[0070] Step S103, generating corresponding search boxes based on the identified livestock animals, and counting the number of the search boxes in the image; wherein the search boxes are used to mark the livestock animals, and each search box marks and only marks one livestock animal.

[0071] Step S2, based on the hyperspectral equipment installed on the high tower, synchronously collect data of the fixed grassland area, and obtain the corresponding vegetation index after processing and analysis.

[0072] This step is performed simultaneously with step S1, and the data collection area is consistent with the optoelectronic device monitoring area. Specifically, in order to obtain accurate data, step S2 further includes the following steps:

[0073] Step S201: For a monitoring area within a set distance range from a tower base, radiation correction is performed using an irradiance sensor correction method.

[0074] The irradiance sensor calibration method is mainly used for close-range monitoring, that is, when the monitoring area is close to the tower base, an irradiance sensor placed near the tower base is used to obtain the radiation intensity under standard lighting conditions.

[0075] The irradiance sensor can measure the intensity of solar radiation reaching the ground, so that the data obtained by the hyperspectral camera can be corrected to remove the influence of atmospheric effects and ensure the accuracy of the data.

[0076] Step S202: For the monitoring area outside the set distance range from the tower base, radiation correction is performed using a mobile multi-grayscale target correction method.

[0077] The calibration factor is solved by combining the known reflectivity of the multi-grayscale target and the three target images collected by the hyperspectral imager to obtain the radiance of the target. The three sets of target reflectivity values ​​and radiance values ​​are substituted into the empirical formula to calculate the values ​​of A, B, and C; A, B, and C are the conversion coefficients between the target reflectivity and the radiance measured by the hyperspectral imager, representing the path radiance, the bottom atmospheric albedo, and additional parameters depending on the atmosphere and geometric conditions; the calibration factor is quickly solved through the simultaneous equations. Using the calculated A, B, and C calibration factors, the empirical formula is used again to perform radiation correction on the target scene.

[0078] Step S203, extracting terrain shadows, selecting corresponding band data, and calculating vegetation index for the effective area; wherein the vegetation index includes NDVI (normalized difference vegetation index) and EVI (enhanced vegetation index).

[0079] The purpose of extracting terrain shadows is to exclude these areas to ensure that the shadow areas are not included when calculating the vegetation index, and only the data of the valid area is retained for calculating the vegetation index. By extracting the terrain shadow area, the shielding factor is accurately extracted, and the normalized vegetation index and enhanced vegetation index are calculated.

[0080] Step S3, obtaining the historical vegetation index and the corresponding livestock carrying capacity data within a set time period in the monitoring area, performing regression analysis, and establishing a univariate linear regression model.

[0081] Using the functional relationship between vegetation index and regional carrying capacity, the theoretical carrying capacity in the current monitoring area can be calculated.

[0082] Step S4, bringing the vegetation index into a univariate linear regression model to obtain the theoretical stocking capacity.

[0083] Calculate the normalized vegetation index and enhanced vegetation index; substitute the vegetation index into the univariate linear regression model to obtain the current theoretical stocking capacity N max .

[0084] Step S5, comparing the real-time statistical data of the number of livestock animals with the theoretical carrying capacity, if the real-time statistical data of the number of livestock animals is greater than the theoretical carrying capacity, an alarm is issued, otherwise the system maintains real-time observation.

[0085] In the specific implementation, the real-time livestock carrying capacity Nnow The theoretical carrying capacity N obtained by analytical calculation max Input to the real-time monitoring alarm system, if N now >N max , an alarm will be issued. If N now <N max , we will continue to maintain real-time observation in the monitoring area.

[0086] If the real-time monitoring and alarm system finds that the real-time livestock carrying capacity N now This is greater than the theoretical livestock carrying capacity N in the area calculated by the hyperspectral equipment. max , an alarm will be issued. If it is less than, real-time observation will continue in the monitoring area.

[0087] Through real-time monitoring by optoelectronic equipment and hyperspectral equipment, the present application can instantly understand the number of livestock and the health status of vegetation in the grassland area; by utilizing the functional relationship between vegetation index and carrying capacity, the theoretical carrying capacity in the current monitoring area can be accurately calculated, and the dynamic assessment based on the health status of vegetation can more accurately reflect the actual carrying capacity of the grassland.

[0088] Hyperspectral equipment based on radiation correction can effectively remove other interference information such as the atmosphere, ensuring that accurate data can be obtained under different weather conditions.

[0089] Compared with traditional ground survey methods, which require a lot of manpower and material resources, have a long monitoring cycle, and are difficult to promptly feedback changes in grassland status; the satellite transit cycle is long, and continuous monitoring cannot be achieved, and in the case of cloud cover, the accuracy and effectiveness of the data are limited; this application uses optoelectronic equipment and hyperspectral equipment on high towers to achieve automated monitoring of fixed grassland areas, reducing the labor intensity and cost of manual inspections, and combining remote sensing monitoring, image recognition, hyperspectral data analysis and other advanced technologies. Through technical means, it can effectively remove other interference information such as the atmosphere, and achieve more accurate and real-time monitoring results.

[0090] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0091] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A grassland livestock carrying capacity monitoring system based on tower-based observation equipment, characterized in that: include: A tower is set in the center of a fixed grassland area of ​​known area, the tower being a support frame at a set height from the ground, the height being lower than the cloud height; Photoelectric equipment and hyperspectral equipment are arranged on the tower; the photoelectric equipment is used to monitor the fixed grassland area in real time, and identify and count the livestock in the monitoring area in real time; the hyperspectral equipment is used to collect data from the monitoring area of ​​the photoelectric equipment, and obtain the vegetation index of the monitoring area after processing and analysis; the theoretical livestock carrying capacity in the current monitoring area is calculated using the functional relationship between the vegetation index and the regional livestock carrying capacity; The real-time monitoring alarm system is used to selectively issue alarm prompts based on the real-time monitoring situation.

2. The monitoring system according to claim 1, characterized in that: The optoelectronic device comprises: A data acquisition system, the data acquisition system comprising an infrared thermal imager, a visible light camera, and a laser lighting system, the data acquisition system being disposed on a turntable and used to acquire image data of the fixed grassland area; A data transmission module, used for transmitting data collected by the data acquisition system; A livestock animal identification module for identifying livestock animals based on predefined features; The retrieval frame quantity counting module is used to generate a retrieval frame according to the identified livestock and animal, and to count the number of retrieval frames in the image.

3. The monitoring system according to claim 2, characterized in that: The search box is used to mark the livestock animals appearing in the image, and each search box marks and only marks one livestock animal.

4. The monitoring system according to claim 1, characterized in that: The hyperspectral device includes a hyperspectral camera and a hyperspectral data analysis system, and the data collection area of ​​the hyperspectral camera is consistent with the monitoring area of ​​the optoelectronic device; For the monitoring area within the set distance from the tower base, radiation correction is performed using the irradiance sensor correction method; For the monitoring area outside the set distance range from the tower base, radiation correction is performed using the mobile multi-grayscale target correction method.

5. The monitoring system according to claim 1, characterized in that: The vegetation index includes the normalized difference vegetation index and the enhanced vegetation index; The historical vegetation index and the corresponding stock carrying capacity data within a set time period of the monitoring area are obtained, regression analysis is performed, and a univariate linear regression model is established; the vegetation index is brought into the univariate linear regression model to obtain the theoretical stock carrying capacity.

6. The monitoring system according to claim 5, characterized in that: The real-time monitoring and alarm system is used to compare the real-time statistical data of the number of livestock animals with the theoretical carrying capacity. If the real-time statistical data of the number of livestock animals is greater than the theoretical carrying capacity, an alarm prompt is issued and real-time observation is continued.

7. A method for monitoring grassland carrying capacity based on tower-based observation equipment, characterized in that: Monitoring is performed based on the monitoring system according to any one of claims 1 to 6, including: Based on the photoelectric equipment installed on the high tower, a fixed grassland area of ​​known area is monitored in real time, and the livestock in the monitoring area are identified and counted in real time; Based on the hyperspectral equipment installed on the tower, synchronously collect data of the fixed grassland area, and obtain the corresponding vegetation index after processing and analysis; Obtain the historical vegetation index and corresponding livestock carrying capacity data within the set time period of the monitoring area, conduct regression analysis, and establish a univariate linear regression model; Substituting the vegetation index into the univariate linear regression model to obtain the theoretical stocking capacity; The real-time statistical data of the number of livestock animals is compared with the theoretical carrying capacity. If the real-time statistical data of the number of livestock animals is greater than the theoretical carrying capacity, an alarm is issued, otherwise the system maintains real-time observation.

8. The monitoring method according to claim 7, characterized in that: The photoelectric device installed on the tower is used to monitor a fixed grassland area of ​​known area in real time, and to identify and count the livestock in the monitoring area in real time, including: Collecting image data of the fixed grassland area based on a data acquisition system; wherein the data acquisition system includes an infrared thermal imager, a visible light camera and a laser lighting system; Based on the image data, identifying livestock animals according to predefined features; A corresponding search frame is generated based on the identified livestock and the number of the search frames in the image is counted.

9. The monitoring method according to claim 8, characterized in that: The search box is used to mark the livestock animal, and each search box marks and only marks one livestock animal.

10. The monitoring method according to any one of claims 7 to 8, characterized in that: The hyperspectral device installed on the tower synchronously collects data from the fixed grassland area, and obtains the corresponding vegetation index after processing and analysis, including: For the monitoring area within the set distance from the tower base, radiation correction is performed using the irradiance sensor correction method; For the monitoring area outside the set distance range from the tower base, radiation correction is performed using the mobile multi-grayscale target correction method; Extract terrain shadows, select corresponding band data, and calculate vegetation index for the effective area; wherein the vegetation index includes normalized vegetation index and enhanced vegetation index.

Images