Intelligent pasture detection system based on pasture growth environment

Abstract

The invention relates to the technical field of forage grass sampling detection, in particular to an intelligent forage grass detection system based on a forage grass growth environment, which is provided with a feature acquisition module, a growth area screening module, a growth environment analysis module and a detection regulation and control module. A growth characteristic area is screened through a growth area screening module, a growth environment trend category of a slope inclined plane is determined through a growth environment analysis module according to a slope inclination vector and a wind direction characterization vector, and a sampling path for nutritional ingredient detection is determined through a detection regulation and control module; and determining the sampling density for detecting the nutritional ingredients in the turbulence active region. According to the invention, the microtopography can be quickly identified according to the actual environment of the pasture growth area, the arrangement mode of the nutrient sample collection point positions can be adaptively adjusted, and the reliability of the pasture growth environment and the nutrient detection data can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of forage sampling and detection, and in particular to an intelligent forage detection system based on a forage growth environment. Background Art

[0002] Forage is an essential material foundation for the development of animal husbandry. High-quality forage plays a key role in improving livestock production performance, product quality, and ensuring the sustainable development of animal husbandry. With the scale and intensive development of animal husbandry, the demand for forage yield and quality is becoming increasingly stringent. Accurately understanding the forage growing environment and nutrient composition is crucial for the scientific management of forage cultivation and utilization. However, traditional forage growing environment and nutrient composition testing often relies on manual sampling and laboratory analysis. Manual sampling is labor-intensive and time-consuming, making it difficult to obtain timely and comprehensive data, especially in large pastures. Furthermore, forage growing areas have diverse topography and extensive microtopography, such as windward and leeward slopes. These topographical differences can lead to significant variations in environmental conditions such as light, temperature, wind speed, and humidity. Using a single data collection method makes it difficult to obtain representative samples, resulting in biased nutrient composition data that fails to truly reflect the actual nutritional status of forage. Therefore, adjusting the layout of nutrient sample collection points based on the actual environmental adaptability of the forage growing area to improve the reliability of forage growing environment and nutrient composition testing data is an urgent technical issue to be addressed.

[0003] For example, Chinese patent application publication number: CN118393098A, the invention discloses a method and system for remote monitoring of water quality in a marine ranch, the method comprising: extracting a number of water samples to be tested from the marine ranch to be evaluated; using a water quality detector to perform substance analysis on each water sample to be tested, and obtaining information about the substance to be tested corresponding to each water sample to be tested; after obtaining environmental information of the marine ranch to be evaluated, calling a preset neural network to perform predictive processing using information about each substance to be tested and environmental information to obtain predicted information; extracting the content of each substance from the predicted information to obtain a predicted capacity value, and determining the water quality of the marine ranch to be evaluated based on the size of the predicted capacity value, and conducting comprehensive monitoring based on substances at different depths in the marine ranch and their substance content, thereby broadening the scope of monitoring, reducing monitoring deviations, and improving monitoring accuracy.

[0004] The following problems also exist in the prior art:

[0005] Existing technologies do not take into account the diversity of topography in forage-growing areas. Microtopography fluctuations are widespread, and these fluctuations will create different growth environments for forage. It is difficult to obtain comprehensive data information using a unified sample collection method. Existing technologies cannot quickly identify microtopography based on the actual environment of the forage-growing area, and cannot adaptively adjust the layout of nutrient sample collection points based on the microtopography, affecting the reliability of the forage-growing environment and nutrient detection data. Summary of the Invention

[0006] To this end, the present invention provides an intelligent grass detection system based on the grass growth environment to overcome the problem that the existing technology cannot quickly identify the micro-topography according to the actual environment of the grass growth area, cannot adaptively adjust the layout of the nutrient sample collection points according to the micro-topography, and affects the reliability of the grass growth environment and nutrient detection data.

[0007] To achieve the above objectives, the present invention provides an intelligent forage detection system based on the forage growth environment, comprising:

[0008] a feature acquisition module comprising a terrain acquisition unit for acquiring point cloud data of a plurality of preset collection points within the grass growing area, and an environment acquisition unit for determining a plurality of wind direction vectors within the grass growing area;

[0009] a growth area screening module, connected to the feature acquisition module, for dividing the forage growth area into a plurality of growth areas, determining terrain parameters based on point cloud data within the growth areas, and screening growth feature areas based on comparison of the terrain parameters;

[0010] a growth environment analysis module, connected to the feature acquisition module and the growth area screening module, respectively, for determining, based on the point cloud data, a plurality of slope aspect inclined surfaces within the growth feature area and slope aspect inclination vectors corresponding to the slope aspect inclined surfaces, and determining, within a preset monitoring period, a growth environment trend category of the slope aspect inclined surfaces based on the slope aspect inclination vectors and a wind direction characterization vector;

[0011] A detection and control module is respectively connected to the feature acquisition module, the growth area screening module and the growth environment analysis module, and is used to determine the sampling path for nutrient component detection according to the growth environment trend category, or to determine the sampling density for nutrient component detection in turbulent active areas.

[0012] Furthermore, the growth area screening module is used to determine terrain parameters, wherein:

[0013] The growth area screening module is used to obtain the three-dimensional rectangular coordinates of a plurality of preset collection points in the forage growth area, and determine the coordinate values ​​of the three-dimensional rectangular coordinates perpendicular to the plane where the forage growth area is located as the terrain parameters;

[0014] The three-dimensional rectangular coordinates are coordinates in a three-dimensional rectangular coordinate system established with the plane where the grass growth area is located as the X-axis and Y-axis plane.

[0015] Furthermore, the growth region screening module is used to screen growth feature regions, wherein:

[0016] The growth region screening module determines that the growth region is screened as a growth characteristic region based on that the terrain parameters of the growth region meet the characteristic growth determination condition;

[0017] The characteristic growth determination condition is that the terrain parameter variance exceeds a preset terrain parameter variance threshold.

[0018] Furthermore, the growth environment analysis module is used to determine the wind direction characterization vector, wherein:

[0019] The growth environment analysis module is used to obtain wind direction vectors at several moments in the growth feature area, and determine a vector obtained by adding the wind direction vectors at several moments as a wind direction characterization vector.

[0020] Furthermore, the growth environment analysis module is used to determine the growth environment trend category of the slope, wherein:

[0021] The growth environment analysis module determines that the growth environment trend category of the slope inclined surface in the growth feature area is the first growth environment trend category based on the slope inclination vector and the wind direction characterization vector of the slope inclined surface in the growth feature area meeting the first trend determination condition;

[0022] The growth environment analysis module determines that the growth environment trend category of the slope inclined surface in the growth feature area is the second growth environment trend category based on the slope inclination vector and the wind direction characterization vector of the slope inclined surface in the growth feature area not meeting the first trend judgment condition.

[0023] Furthermore, the first trend determination condition is that the horizontal component of the slope inclination vector is in the opposite direction to the horizontal component of the wind direction characterization vector.

[0024] Furthermore, the detection and control module selects a sampling path for nutrient component detection based on the wind direction characterization vector based on the growth environment trend category being the first growth environment trend category;

[0025] The detection and control module selects a sampling density for nutrient component detection in a turbulence active area based on terrain parameters and wind direction vectors based on the fact that the growth environment trend category is the second growth environment trend category.

[0026] Furthermore, the detection and control module is used to determine the sampling path for nutrient component detection, wherein:

[0027] The sampling path is arranged on the slope inclined surface in parallel with the wind direction characterization vector, the interval distance between adjacent sampling paths is negatively correlated with the wind direction deviation coefficient of the growth feature area, and the interval distance between adjacent sampling points on each sampling path is negatively correlated with the vector size of the wind direction characterization vector.

[0028] Furthermore, the sampling density for nutrient component detection in the turbulent active area is determined, where

[0029] The detection and control module divides the growth feature region into a plurality of growth feature sub-regions;

[0030] Used to calculate the difference between the maximum value and the minimum value of the terrain parameter in the growth feature sub-area;

[0031] To determine the wind direction deviation coefficient of each growth characteristic sub-region;

[0032] The growth characteristic sub-regions whose topographic parameters and wind direction deviation coefficients meet the turbulence active judgment conditions are screened as turbulence active regions;

[0033] The turbulence activity determination condition is that the difference exceeds a preset difference threshold, and the wind direction deviation coefficient exceeds a preset wind direction deviation threshold, and the sampling density of the turbulence active area is positively correlated with the difference and positively correlated with the wind direction deviation coefficient.

[0034] Furthermore, the detection and control module is used to determine the wind direction deviation coefficient, wherein:

[0035] The detection and control module obtains wind direction vectors at several moments in a preset monitoring period, calculates the vector angle between any wind direction vector and the remaining wind direction vectors, and determines the vector angle variance as the wind direction deviation coefficient.

[0036] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention sets a feature acquisition module, a growth area screening module, a growth environment analysis module, and a detection and control module. The feature acquisition module is used to acquire point cloud data and several wind direction vectors. The growth area screening module is used to determine terrain parameters based on the point cloud data in the growth area to screen the growth feature area. The growth environment analysis module is used to determine the growth environment trend category of the slope inclination surface according to the slope inclination vector and the wind direction characterization vector within a preset monitoring period. The detection and control module is used to select the nutrient component detection method according to the growth environment trend category. Furthermore, the micro-topography can be quickly identified according to the actual environment of the forage growth area, and the layout of the nutrient component sample collection points can be adaptively adjusted, thereby improving the reliability of the forage growth environment and nutrient component detection data.

[0037] In particular, the present invention uses a growth area screening module to screen growth characteristic areas according to the comparison of terrain parameters. It can be understood that due to the different terrain parameters of different growth characteristic areas, their environmental factors such as light, moisture, and soil fertility are also different. These factors will affect the nutritional content of forage. Accurately screening out these areas and performing data collection and analysis separately can more accurately reflect the actual growth conditions and nutritional levels of forage in different areas, reduce the detection data error caused by terrain differences, and different terrain parameters will lead to differences in forage growth environment, thereby affecting the growth characteristics and nutritional content of forage. Screening growth characteristic areas can clarify the characteristics of forage growth areas under different terrain conditions, so that the detection system can perform detailed detection and analysis on specific areas more targeted, avoid indiscriminate detection of the entire growth area, and improve detection efficiency and resource utilization efficiency. The present invention uses a growth area screening module to screen growth characteristic areas according to the comparison of terrain parameters, thereby realizing rapid identification of micro-topography according to the actual environment of the forage growth area, and improving the reliability of forage growth environment and nutritional content detection data.

[0038] In particular, the present invention obtains the comparison between the slope inclination vector and the wind direction characterization vector within a preset monitoring period through the growth environment analysis module. It can be understood that by continuously performing analysis within the preset monitoring period, the changing trend of the growth environment of the slope inclination surface can be dynamically grasped. Grass growth is significantly affected by the environment, and the wind direction will change with the season or weather. By analyzing the relationship between the slope inclination vector and the wind direction characterization vector within the preset monitoring period, changes in the growth environment trend category can be discovered in a timely manner, thereby better evaluating the adaptability of grass to environmental changes. For example, when the seasons change, the change in wind direction may cause the area originally on the leeward slope to become the windward slope. The growth environment analysis module can capture this change in time and provide information for judging whether the grass can adapt to the new environment. The present invention obtains the comparison between the slope inclination vector and the wind direction characterization vector within the preset monitoring period through the growth environment analysis module, thereby realizing the rapid identification of micro-topography according to the actual environment of the grass growth area, and improving the reliability of the grass growth environment and nutrient component detection data.

[0039] In particular, the present invention determines the growth environment trend category of the slope inclined surface according to the comparison of the slope inclination vector and the wind direction characterization vector through the growth environment analysis module. It can be understood that different slope and wind direction combinations will form different growth environments. By comparing the slope inclination vector and the wind direction characterization vector, it is possible to accurately judge whether the slope inclined surface is in a windward state or a leeward state, and then determine its growth environment trend category. When the slope inclined surface is in a windward state, it will face strong winds, large water evaporation and different lighting conditions, while the leeward slope inclined surface may be relatively warm and humid. This precise assessment helps to gain an in-depth understanding of the microenvironment of grass growth and provides a basis for accurately grasping the grass growth conditions. The present invention determines the growth environment trend category of the slope inclined surface according to the comparison of the slope inclination vector and the wind direction characterization vector through the growth environment analysis module, thereby realizing the rapid identification of microtopography according to the actual environment of the grass growth area, and improving the reliability of grass growth environment and nutrient component detection data.

[0040] In particular, the present invention determines the sampling path for nutrient component detection according to the wind direction characterization vector in the first growth environment trend category. It can be understood that the first growth environment trend category, that is, the slope inclined surface is the windward slope, and the wind direction of the windward slope has a significant impact on the growth of forage. Setting the sampling path in a direction parallel to the wind direction characterization vector can enable the collected samples to better reflect the changing pattern of the nutrient components of forage under the influence of wind. The wind will bring different climatic conditions, such as temperature, humidity and light. Setting the sampling path along the wind direction can cover the impact of the gradient changes of these environmental factors on the slope inclined surface on the nutrient components of forage, so that the collected samples are more representative and can more accurately reflect the changes in the nutrient components of the windward slope. The overall nutritional status of slope pasture, determining the sampling path for nutrient detection based on the wind direction characterization vector can more effectively utilize detection resources. On the windward slope, the sampling path is set according to the wind direction, and sampling can be carried out in a targeted manner to avoid repeated sampling or insufficient sampling, thereby rationally allocating detection resources, improving resource utilization efficiency, and reducing detection costs. The present invention determines the sampling path for nutrient detection based on the wind direction characterization vector in the first growth environment trend category, thereby realizing rapid identification of microtopography according to the actual environment of the pasture growth area, adaptively adjusting the layout of the nutrient sample collection points, and improving the reliability of the pasture growth environment and nutrient detection data.

[0041] In particular, the present invention determines the sampling density for nutrient component detection in turbulence-active areas in the second growth environment trend category according to terrain parameters and wind direction vectors. It can be understood that the second growth environment trend category, i.e., the slope is a leeward slope. Since the wind direction consistency of the leeward slope is not high, terrain fluctuations and frequent changes in wind direction will lead to small local airflows in the area. The more drastic the changes in terrain parameters and wind direction vectors, the more likely such areas are to have complex airflows such as eddies and backflows, resulting in high-frequency, small-scale mutations in temperature, humidity, wind speed, vegetation stress indicators, etc. within a few meters. Traditional uniform sampling is prone to missing key variations due to excessive spacing. By encrypting sampling in turbulence-active areas, accurate Capturing strong spatial heterogeneity characteristics, the more drastic the changes in terrain parameters and wind direction vectors in turbulence-active areas, the higher the sampling density, and the more stable the changes in terrain parameters and wind direction vectors in turbulence-active areas, the lower the sampling density. This can optimize resource allocation, reduce redundant investment, and better reflect the true distribution of nutritional status of leeward slope pasture. In the second growth environment trend category, the present invention determines the sampling density for nutrient component detection in turbulence-active areas based on terrain parameters and wind direction vectors. Furthermore, it achieves rapid identification of microtopography based on the actual environment of the pasture growth area, adaptively adjusts the layout of nutrient component sample collection points, and improves the reliability of pasture growth environment and nutrient component detection data. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a functional block diagram of an intelligent forage detection system based on forage growth environment according to an embodiment of the present invention;

[0043] Figure 2 A logic flow chart of a growth region screening module screening growth feature regions according to an embodiment of the present invention;

[0044] Figure 3 A logic flow chart of the growth environment analysis module of an embodiment of the present invention for determining the growth environment trend category of a sloped surface;

[0045] Figure 4 A logic flow chart for selecting and adjusting the sampling path of a growth feature area or the sampling density of a turbulence active area by a detection and control module in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0047] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0048] It should be noted that, in the description of the present invention, terms such as "upper", "lower", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0049] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted" and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; or internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0050] See also Figure 1 As shown in FIG, it is a functional block diagram of a grass intelligent detection system based on a grass growth environment according to an embodiment of the present invention. The grass intelligent detection system based on a grass growth environment according to the present invention includes:

[0051] a feature acquisition module comprising a terrain acquisition unit for acquiring point cloud data of a plurality of preset collection points within the grass growing area, and an environment acquisition unit for determining a plurality of wind direction vectors within the grass growing area;

[0052] Specifically, the setting of preset collection points in the grass growing area can be set by technical personnel in this field according to the accuracy requirements of the grass growing environment and nutrient component detection. The higher the accuracy requirement, the more preset collection points are set. Preferably, when the size of the grass growing area is 500m×500m, a collection point can be set every 20m×20m, and the number of preset collection points set in the grass growing area can be 625.

[0053] Specifically, the embodiment of the present invention does not limit the specific structure of the terrain acquisition unit. Preferably, it can be a lidar device, which can accurately obtain the three-dimensional position information of the terrain by emitting a laser beam and measuring the time it takes for it to be reflected back, and then generate point cloud data of several preset collection points in the grass growth area. It will not be repeated here.

[0054] Specifically, the embodiment of the present invention does not limit the specific structure of the environment acquisition unit. Preferably, it can be an ultrasonic anemometer, which transmits and receives ultrasonic signals and uses the relationship between the propagation speed of ultrasonic waves in the air and the wind speed and wind direction to accurately measure the wind speed and wind direction information, thereby obtaining the wind direction vector in the grass growth area. It will not be repeated here.

[0055] a growth area screening module, connected to the feature acquisition module, for dividing the forage growth area into a plurality of growth areas, determining terrain parameters based on point cloud data within the growth areas, and screening growth feature areas based on comparison of the terrain parameters;

[0056] Specifically, the embodiment of the present invention does not limit the specific structure of the growth area screening module. Preferably, it can be a microprocessor for dividing growth areas, determining terrain parameters, and screening growth feature areas, which will not be repeated here.

[0057] Specifically, the division size of the growth area can be set by technical personnel in this field according to the accuracy requirements of the forage growth environment and nutrient component detection. The higher the accuracy requirement, the smaller the division size of the growth area. Preferably, the division size of the growth area can be a rectangular area of ​​100m×100m.

[0058] a growth environment analysis module, connected to the feature acquisition module and the growth area screening module, respectively, for determining, based on the point cloud data, a plurality of slope aspect inclined surfaces within the growth feature area and slope aspect inclination vectors corresponding to the slope aspect inclined surfaces, and determining, within a preset monitoring period, a growth environment trend category of the slope aspect inclined surfaces based on the slope aspect inclination vectors and a wind direction characterization vector;

[0059] Specifically, the point cloud data can be fitted to the ground using the least squares method to separate ground points from non-ground points. The point cloud data can be divided into different clusters based on the spatial distribution density of the point cloud using a clustering algorithm. Each cluster corresponds to a slope inclination surface. The normal vectors of all points on the slope inclination surface are subjected to principal component analysis to obtain the slope inclination vector. The slope inclination vector is the normal vector of the slope inclination surface, which will not be described in detail here.

[0060] Specifically, the preset monitoring period can be set by technical personnel in this field according to the accuracy requirements of the forage growth environment and nutrient component detection. The higher the accuracy requirement, the longer the preset monitoring period. The value range of the preset monitoring period can be [2, 4], and the interval unit is h. Preferably, the preset monitoring period can be 3h.

[0061] Specifically, the embodiment of the present invention does not limit the specific structure of the growth environment analysis module. Preferably, it can be a processor used in a computer to determine several slope inclination surfaces and slope inclination vectors corresponding to the slope inclination surfaces in the growth feature area, as well as to determine the growth environment trend category of the slope inclination surfaces. No further details will be given here.

[0062] A detection and control module is respectively connected to the feature acquisition module, the growth area screening module and the growth environment analysis module, and is used to determine the sampling path for nutrient component detection according to the growth environment trend category, or to determine the sampling density for nutrient component detection in turbulent active areas.

[0063] Specifically, the embodiment of the present invention does not limit the specific structure of the detection and control module. Preferably, it can be a field programmable logic component, which is used to select and adjust the sampling path for nutrient detection according to the growth environment trend category, or determine the sampling density for nutrient detection in turbulence-active areas, determine the sampling path for nutrient detection, screen turbulence-active areas, and determine the sampling density. No further details will be given here.

[0064] Specifically, the diversity of topography and microtopography in the forage growing area leads to huge changes in environmental conditions such as light, temperature, wind speed, and humidity, resulting in significant spatial heterogeneity in the nutritional components of forage. These components include crude protein and crude fat that directly affect the nutritional supply of livestock, crude fiber that affects digestibility, moisture content that reflects metabolic activity and palatability, as well as mineral elements driven by soil nutrients, soluble sugars and vitamins related to stress resistance and taste. The traditional unified sampling method is prone to key data deviations because it is not adapted to the heterogeneity of terrain. Adaptive adjustment of sampling points can cover different terrains in a targeted manner to reduce spatial sampling deviations, so that the samples can more comprehensively and accurately reflect the forage growth environment and nutritional components, thereby effectively improving the representativeness and accuracy of the test data.

[0065] Specifically, the growth region screening module is used to determine terrain parameters, wherein:

[0066] The growth area screening module is used to obtain the three-dimensional rectangular coordinates of a plurality of preset collection points in the forage growth area, and determine the coordinate values ​​of the three-dimensional rectangular coordinates perpendicular to the plane where the forage growth area is located as the terrain parameters;

[0067] The three-dimensional rectangular coordinates are coordinates in a three-dimensional rectangular coordinate system established with the plane where the grass growth area is located as the X-axis and Y-axis plane.

[0068] See also Figure 2 As shown, it is a logic flow chart of the growth region screening module screening growth feature regions according to an embodiment of the present invention. The growth region screening module is used to screen growth feature regions, wherein:

[0069] The growth region screening module determines that the growth region is screened as a growth characteristic region based on that the terrain parameters of the growth region meet the characteristic growth determination condition;

[0070] The growth area screening module determines not to screen the growth area based on the terrain parameters of the growth area not meeting the characteristic growth determination condition;

[0071] The characteristic growth determination condition is that the terrain parameter variance exceeds a preset terrain parameter variance threshold.

[0072] Specifically, the preset terrain parameter variance threshold is the product of the average terrain parameter of the growth area within the forage growth area and the terrain fluctuation factor. The terrain fluctuation factor can be set by technical personnel in this field based on the detection accuracy requirements of the forage growth environment and nutrient components. The higher the accuracy requirement, the smaller the terrain fluctuation factor. The value range of the terrain fluctuation factor can be [0.2, 0.4]. Preferably, the terrain fluctuation factor can be 0.3.

[0073] Specifically, the embodiment of the present invention uses a growth area screening module to screen growth characteristic areas based on the comparison of terrain parameters. It can be understood that due to the different terrain parameters of different growth characteristic areas, their environmental factors such as light, moisture, and soil fertility are also different. These factors will affect the nutritional content of forage. Accurately screening these areas and performing data collection and analysis separately can more accurately reflect the actual growth conditions and nutritional levels of forage in different areas, reduce the detection data error caused by terrain differences, and different terrain parameters will lead to differences in forage growth environment, thereby affecting the growth characteristics and nutritional content of forage. Screening growth characteristic areas can clarify the characteristics of forage growth areas under different terrain conditions, so that the detection system can perform detailed detection and analysis of specific areas more targeted, avoid indiscriminate detection of the entire growth area, and improve detection efficiency and resource utilization efficiency. The embodiment of the present invention uses a growth area screening module to screen growth characteristic areas based on the comparison of terrain parameters, thereby realizing rapid identification of micro-topography according to the actual environment of the forage growth area, and improving the reliability of forage growth environment and nutritional content detection data.

[0074] Specifically, it is understandable that even in the forage planting areas of relatively flat grasslands or plains, there will be some micro-topography differences within a short distance, such as small mounds, shallow depressions, gentle slopes, etc. These micro-topography are formed due to natural geological effects, water erosion or accumulation and other factors. For example, in areas with strong winds, wind accumulation may form some sand dunes or sand ridges, while small water accumulation areas or wetlands may be formed in low-lying areas. Some local terrain undulations may only have a height difference of tens of centimeters to several meters, but it is enough to affect the growth conditions of forage. For example, the small earth slopes formed are affected differently by wind, and this difference will lead to different growth conditions of forage. Topographic parameters can characterize the topographic characteristics of the forage growth area. Through point cloud data, the areas with fluctuating terrain in the region are screened as growth characteristic areas. Then, the micro-topography can be quickly identified according to the actual environment of the forage growth area, thereby improving the reliability of the forage growth environment and nutrient detection data.

[0075] Specifically, the growth environment analysis module is used to determine the wind direction characterization vector, wherein:

[0076] The growth environment analysis module is used to obtain wind direction vectors at several moments in the growth feature area, and determine a vector obtained by adding the wind direction vectors at several moments as a wind direction characterization vector.

[0077] Specifically, the component vectors can be determined using trigonometric function relationships. The modulus can be multiplied by the cosine value of the corresponding angle to obtain the size of the component vector in each coordinate axis direction. Alternatively, the component vector can be indirectly solved by combining the vector modulus. Alternatively, the component vector can be directly determined using an algorithm based on trigonometric functions. This will not be repeated here.

[0078] Specifically, the wind direction vector in the growth feature area can be obtained at several moments within a preset monitoring period. The preset monitoring period and the interval between several moments can be determined by technical personnel in this field based on the historical data of the actual wind direction of the pasture. The value range of the preset monitoring period can be [2, 4], and the interval unit is h. The value range of the interval length can be [20, 40], and the interval unit is min. Preferably, the preset monitoring period can be 2.5h, and the interval length can be 30min. During this monitoring period, the wind direction of the pasture changes relatively slowly, and the phenomenon of the wind direction being opposite in a short period of time will not occur.

[0079] Specifically, the embodiment of the present invention obtains the comparison between the slope inclination vector and the wind direction characterization vector within a preset monitoring period through the growth environment analysis module. It can be understood that by continuously performing analysis within the preset monitoring period, the changing trend of the growth environment of the slope inclination surface can be dynamically grasped. Grass growth is significantly affected by the environment, and the wind direction will change with the season or weather. By analyzing the relationship between the slope inclination vector and the wind direction characterization vector within the preset monitoring period, changes in the growth environment trend category can be discovered in a timely manner, thereby better evaluating the adaptability of grass to environmental changes. For example, when the seasons change, the change in wind direction may cause the area originally on the leeward slope to become the windward slope. The growth environment analysis module can capture this change in time and provide information for judging whether the grass can adapt to the new environment. The embodiment of the present invention obtains the comparison between the slope inclination vector and the wind direction characterization vector within the preset monitoring period through the growth environment analysis module, thereby realizing the rapid identification of micro-topography according to the actual environment of the grass growth area, and improving the reliability of the grass growth environment and nutrient component detection data.

[0080] See also Figure 3 As shown, it is a logic flow chart of the growth environment analysis module of an embodiment of the present invention for determining the growth environment trend category of a slope-to-inclined surface. The growth environment analysis module is used to determine the growth environment trend category of the slope-to-inclined surface, wherein:

[0081] The growth environment analysis module determines that the growth environment trend category of the slope inclined surface in the growth feature area is the first growth environment trend category based on the slope inclination vector and the wind direction characterization vector of the slope inclined surface in the growth feature area meeting the first trend determination condition;

[0082] The growth environment analysis module determines that the growth environment trend category of the slope inclined surface in the growth feature area is the second growth environment trend category based on the slope inclination vector and the wind direction characterization vector of the slope inclined surface in the growth feature area not meeting the first trend judgment condition.

[0083] Specifically, the embodiment of the present invention determines the growth environment trend category of the slope inclined surface based on the comparison of the slope inclination vector and the wind direction characterization vector through the growth environment analysis module. It can be understood that different slope and wind direction combinations will form different growth environments. By comparing the slope inclination vector and the wind direction characterization vector, it is possible to accurately determine whether the slope inclined surface is in a windward state or a leeward state, and then determine its growth environment trend category. When the slope inclined surface is in a windward state, it will face strong winds, large water evaporation and different lighting conditions, while the leeward slope inclined surface may be relatively warm and humid. This precise assessment helps to gain an in-depth understanding of the microenvironment of grass growth and provides a basis for accurately grasping the grass growth conditions. The embodiment of the present invention determines the growth environment trend category of the slope inclined surface based on the comparison of the slope inclination vector and the wind direction characterization vector through the growth environment analysis module, thereby realizing the rapid identification of microtopography according to the actual environment of the grass growth area, and improving the reliability of grass growth environment and nutrient component detection data.

[0084] Specifically, the first trend determination condition is that the horizontal component of the slope inclination vector is in the opposite direction to the horizontal component of the wind direction characterization vector.

[0085] See also Figure 4 As shown, it is a logic flow chart of the detection and control module selecting and adjusting the sampling path of the growth feature area or adjusting the sampling density of the turbulence active area according to an embodiment of the present invention. The detection and control module selects a sampling path for determining nutrient component detection based on the wind direction characterization vector based on the growth environment trend category being the first growth environment trend category;

[0086] The detection and control module selects a sampling density for nutrient component detection in a turbulence active area based on terrain parameters and wind direction vectors based on the fact that the growth environment trend category is the second growth environment trend category.

[0087] Specifically, the detection and control module is used to determine the sampling path for nutrient component detection, wherein:

[0088] The sampling path is arranged on the slope inclined surface in parallel with the wind direction characterization vector, the interval distance between adjacent sampling paths is negatively correlated with the wind direction deviation coefficient of the growth feature area, and the interval distance between adjacent sampling points on each sampling path is negatively correlated with the vector size of the wind direction characterization vector.

[0089] Specifically, the interval distance between adjacent sampling paths is the path interval factor / wind direction deviation coefficient. The path interval factor can be set by those skilled in the art based on the average value of historical data. The value range of the path interval factor can be [24, 32]. Preferably, the path interval factor can be 25. For example, when the wind direction deviation coefficient is 0.8, the interval distance between adjacent sampling paths is the path interval factor / wind direction deviation coefficient = 31.25m. When the wind direction deviation coefficient is 1.5, the interval distance between adjacent sampling paths is the path interval factor / wind direction deviation coefficient = 16.67m.

[0090] Specifically, the interval distance between adjacent sampling points is the sampling point interval factor × the vector size reference value of the wind direction characterization vector / the vector size of the wind direction characterization vector. The vector size reference value of the wind direction characterization vector is the average value of the vector size of the wind direction characterization vector in the same period in the historical data. The sampling point interval factor can be set by a person skilled in the art based on the average value of the historical data. The value range of the sampling point interval factor can be [24, 32]. Preferably, the sampling point interval factor can be 25. For example, when the vector size reference value of the wind direction characterization vector is 10 m / s and the vector size of the wind direction characterization vector is 12 m / s, the interval distance between adjacent sampling points on the sampling path is the sampling point interval factor × the vector size reference value of the wind direction characterization vector / the vector size of the wind direction characterization vector = 20.8 m. When the vector size of the wind direction characterization vector is 8 m / s, the interval distance between adjacent sampling points on the sampling path is the sampling point interval factor × the vector size reference value of the wind direction characterization vector / the vector size of the wind direction characterization vector = 31.25 m.

[0091] Specifically, in the embodiment of the present invention, in the first growth environment trend category, the sampling path for nutrient component detection is determined according to the wind direction characterization vector. It can be understood that the first growth environment trend category, that is, the slope inclined surface is the windward slope, and the wind direction of the windward slope has a significant impact on the growth of forage. Setting the sampling path in a direction parallel to the wind direction characterization vector can enable the collected samples to better reflect the changing pattern of the nutrient components of forage under the influence of wind. The wind will bring different climatic conditions, such as temperature, humidity and light. Setting the sampling path along the wind direction can cover the impact of the gradient changes of these environmental factors on the slope inclined surface on the nutrient components of forage, so that the collected samples are more representative and can more accurately reflect the windward slope. The overall nutritional status of windward slope pasture, determining the sampling path for nutrient detection based on the wind direction characterization vector can more effectively utilize detection resources. On the windward slope, the sampling path is set according to the wind direction, and sampling can be carried out in a targeted manner to avoid repeated sampling or insufficient sampling, thereby rationally allocating detection resources, improving resource utilization efficiency, and reducing detection costs. In the embodiment of the present invention, in the first growth environment trend category, the sampling path for nutrient detection is determined based on the wind direction characterization vector, thereby realizing rapid identification of microtopography according to the actual environment of the pasture growth area, adaptively adjusting the layout of the nutrient sample collection points, and improving the reliability of pasture growth environment and nutrient detection data.

[0092] Specifically, it can be understood that, on the one hand, the soil moisture and nutrient distribution on the windward slope will be affected by the wind speed. Arranging sampling points along the wind direction gradient can better reflect the changes in these environmental factors, thereby improving the accuracy of the nutrient analysis of forage. On the other hand, arranging sampling points along the wind direction gradient can better monitor the stability and change pattern of wind direction. Stable wind direction and wind speed are helpful to predict the microenvironment for forage growth. The vegetation growth conditions at different locations will also vary due to different wind speed and humidity conditions. Arranging sampling points along the wind direction gradient can ensure the integrity of the data and cover the forage growth conditions under different terrains and environmental conditions, thereby improving the representativeness and reliability of the data. In the first growth environment trend category, the embodiment of the present invention determines the sampling path for nutrient detection according to the wind direction characterization vector, thereby realizing the rapid identification of microtopography according to the actual environment of the forage growth area, adaptively adjusting the layout of the nutrient sample collection points, and improving the reliability of the forage growth environment and nutrient detection data.

[0093] Specifically, the sampling density for nutrient content detection in turbulent active areas was determined, where

[0094] The detection and control module divides the growth feature region into a plurality of growth feature sub-regions;

[0095] The detection and control module is used to calculate the difference between the maximum value and the minimum value of the terrain parameter in the growth feature sub-area;

[0096] The detection and control module is used to determine the wind direction deviation coefficient of each growth feature sub-region;

[0097] The detection and control module is used to select the growth feature sub-regions whose terrain parameters and wind direction deviation coefficients meet the turbulence active judgment conditions as turbulence active regions;

[0098] If the topographic parameters and wind direction deviation coefficient of the growth feature sub-region do not meet the turbulence active judgment conditions, the growth feature sub-region will not be screened;

[0099] The turbulence activity determination condition is that the difference exceeds a preset difference threshold, and the wind direction deviation coefficient exceeds a preset wind direction deviation threshold, and the sampling density of the turbulence active area is positively correlated with the difference and positively correlated with the wind direction deviation coefficient.

[0100] Specifically, the divided area of ​​the growth feature sub-region is the product of the area of ​​the growth feature region and the sub-region division factor. The sub-region division factor can be set by technical personnel in this field according to the detection accuracy requirements of the forage growth environment and nutrient components. The higher the accuracy requirement, the smaller the sub-region division factor. The value range of the sub-region division factor can be [0.03, 0.05]. Preferably, the sub-region division factor can be 0.04, and the growth feature sub-region includes at least two collection points.

[0101] Specifically, the preset difference threshold is the product of the average value of the terrain parameters in the growth characteristic area and the value factor. The value factor can be set by technical personnel in this field based on the detection accuracy requirements of the forage growth environment and nutritional components. The higher the accuracy requirement, the smaller the value factor. The value range of the value factor can be [0.1, 0.3]. Preferably, the value factor can be 0.2.

[0102] Specifically, the preset wind direction offset threshold can be set by technical personnel in this field based on the detection accuracy requirements of the forage growth environment and nutrient components. The higher the accuracy requirement, the smaller the preset wind direction offset threshold. The value range of the wind direction offset threshold can be [1.5, 2]. Preferably, the wind direction offset threshold can be 1.6.

[0103] Specifically, the sampling density is the sampling terrain weight coefficient × difference / difference reference value + sampling wind direction weight coefficient × wind direction offset coefficient / wind direction offset coefficient reference value, the difference reference value is the difference average value of the terrain parameters in the historical data, and the wind direction offset coefficient reference value is the average value of the wind direction offset coefficient in the same period in the historical data. The sampling terrain weight coefficient and the sampling wind direction weight coefficient can be selected by those skilled in the art according to the degree of influence of the difference and wind direction offset coefficient in the historical data on the calculation results. The difference + wind direction offset coefficient = 1. Preferably, the difference can be set to 0.5 and the wind direction offset coefficient to 0.5. For example, when the difference reference value is 2m and the wind direction offset coefficient reference value is 1.5, the difference is 3m and the wind direction offset coefficient is 1.6, the sampling density = sampling terrain weight coefficient × difference / difference reference value + sampling wind direction weight coefficient × wind direction offset coefficient / wind direction offset coefficient reference value = 1.28 / m 2 When the difference is 4m and the wind direction offset coefficient is 1.8, the sampling density = sampling terrain weight coefficient × difference / difference reference value + sampling wind direction weight coefficient × wind direction offset coefficient / wind direction offset coefficient reference value = 1.6 / m 2 .

[0104] Specifically, in the embodiment of the present invention, in the second growth environment trend category, the sampling density for nutrient component detection in the turbulence active area is determined according to the terrain parameters and the wind direction vector. It can be understood that the second growth environment trend category, that is, the slope is the leeward slope. Since the wind direction consistency of the leeward slope is not high, the terrain fluctuations and the frequent changes in wind direction will cause local small airflows in the area. The more drastic the changes in terrain parameters and wind direction vectors, the more likely such areas are to have complex airflows such as eddies and backflows, resulting in high-frequency and small-scale mutations in temperature, humidity, wind speed, vegetation stress indicators, etc. within a few meters. Traditional uniform sampling is prone to missing key variations due to excessive spacing. By encrypting sampling in turbulence active areas, accurate sampling can be achieved. The strong spatial heterogeneity characteristics are accurately captured. The more drastic the changes in the terrain parameters and wind direction vectors in the turbulence-active area, the higher the sampling density. The more stable the changes in the terrain parameters and wind direction vectors in the turbulence-active area, the lower the sampling density. This can optimize resource allocation, reduce redundant investment, and better reflect the true distribution of the nutritional status of pasture on the leeward slope. In the second growth environment trend category, the embodiment of the present invention determines the sampling density for nutrient component detection in the turbulence-active area based on the terrain parameters and wind direction vector. Furthermore, it realizes the rapid identification of micro-topography according to the actual environment of the pasture growth area, adaptively adjusts the layout of the nutrient component sample collection points, and improves the reliability of the pasture growth environment and nutrient component detection data.

[0105] Specifically, the detection and control module is used to determine the wind direction deviation coefficient, wherein:

[0106] The detection and control module obtains wind direction vectors at several moments in a preset monitoring period, calculates the vector angle between any wind direction vector and the remaining wind direction vectors, and determines the vector angle variance as the wind direction deviation coefficient.

[0107] Specifically, the wind direction vectors at several moments, that is, several moments within a preset monitoring period, and the interval length between adjacent moments can be set by technical personnel in this field according to the detection accuracy requirements of the forage growth environment and nutrient components. The higher the accuracy requirement, the shorter the interval length. The value range of the interval length can be [20, 40], and the interval unit is min. Preferably, the interval length can be 30 minutes.

[0108] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0109] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A grass intelligent detection system based on grass growth environment, characterized in that: include: a feature acquisition module comprising a terrain acquisition unit for acquiring point cloud data of a plurality of preset collection points within the grass growing area, and an environment acquisition unit for determining a plurality of wind direction vectors within the grass growing area; a growth area screening module, connected to the feature acquisition module, for dividing the forage growth area into a plurality of growth areas, determining terrain parameters based on point cloud data within the growth areas, and screening growth feature areas based on comparison of the terrain parameters; a growth environment analysis module, connected to the feature acquisition module and the growth area screening module, respectively, for determining, based on the point cloud data, a plurality of slope aspect inclined surfaces within the growth feature area and slope aspect inclination vectors corresponding to the slope aspect inclined surfaces, and determining, within a preset monitoring period, a growth environment trend category of the slope aspect inclined surfaces based on the slope aspect inclination vectors and a wind direction characterization vector; A detection and control module is respectively connected to the feature acquisition module, the growth area screening module and the growth environment analysis module, and is used to determine the sampling path for nutrient component detection according to the growth environment trend category, or to determine the sampling density for nutrient component detection in turbulent active areas.

2. The intelligent grass detection system based on grass growth environment according to claim 1 is characterized in that: The growth area screening module is used to determine terrain parameters, wherein: The growth area screening module is used to obtain the three-dimensional rectangular coordinates of a plurality of preset collection points in the forage growth area, and determine the coordinate values ​​of the three-dimensional rectangular coordinates perpendicular to the plane where the forage growth area is located as the terrain parameters; The three-dimensional rectangular coordinates are coordinates in a three-dimensional rectangular coordinate system established with the plane where the grass growth area is located as the X-axis and Y-axis plane.

3. The intelligent grass detection system based on grass growth environment according to claim 2 is characterized in that: The growth region screening module is used to screen growth feature regions, wherein: The growth region screening module determines that the growth region is screened as a growth characteristic region based on that the terrain parameters of the growth region meet the characteristic growth determination condition; The characteristic growth determination condition is that the terrain parameter variance exceeds a preset terrain parameter variance threshold.

4. The intelligent grass detection system based on grass growth environment according to claim 3 is characterized in that: The growth environment analysis module is used to determine the wind direction characterization vector, wherein: The growth environment analysis module is used to obtain wind direction vectors at several moments in the growth feature area, and determine a vector obtained by adding the wind direction vectors at several moments as a wind direction characterization vector.

5. The intelligent forage detection system based on forage growth environment according to claim 4 is characterized in that: The growth environment analysis module is used to determine the growth environment trend category of the slope, wherein: The growth environment analysis module determines that the growth environment trend category of the slope inclined surface in the growth feature area is the first growth environment trend category based on the slope inclination vector and the wind direction characterization vector of the slope inclined surface in the growth feature area meeting the first trend determination condition; The growth environment analysis module determines that the growth environment trend category of the slope inclined surface in the growth feature area is the second growth environment trend category based on the slope inclination vector and the wind direction characterization vector of the slope inclined surface in the growth feature area not meeting the first trend judgment condition.

6. The intelligent forage detection system based on forage growth environment according to claim 5, characterized in that: The first trend determination condition is that the horizontal component of the slope inclination vector is in the opposite direction to the horizontal component of the wind direction characterization vector.

7. The intelligent forage detection system based on forage growth environment according to claim 5, characterized in that: The detection and control module selects a sampling path for nutrient component detection based on the wind direction characterization vector based on the growth environment trend category being the first growth environment trend category; The detection and control module selects a sampling density for nutrient component detection in a turbulence active area based on terrain parameters and wind direction vectors based on the fact that the growth environment trend category is the second growth environment trend category.

8. The intelligent forage detection system based on forage growth environment according to claim 7, characterized in that: The detection and control module is used to determine the sampling path for nutrient component detection, wherein: The sampling path is arranged on the slope inclined surface in parallel with the wind direction characterization vector, the interval distance between adjacent sampling paths is negatively correlated with the wind direction deviation coefficient of the growth feature area, and the interval distance between adjacent sampling points on each sampling path is negatively correlated with the vector size of the wind direction characterization vector.

9. The intelligent forage detection system based on forage growth environment according to claim 7, characterized in that: Determine the sampling density for nutrient content testing in areas with active turbulence, where The detection and control module divides the growth feature region into a plurality of growth feature sub-regions; Used to calculate the difference between the maximum value and the minimum value of the terrain parameter in the growth feature sub-area; To determine the wind direction deviation coefficient of each growth characteristic sub-region; The growth characteristic sub-regions whose topographic parameters and wind direction deviation coefficients meet the turbulence active judgment conditions are screened as turbulence active regions; The turbulence activity determination condition is that the difference exceeds a preset difference threshold, and the wind direction deviation coefficient exceeds a preset wind direction deviation threshold, and the sampling density of the turbulence active area is positively correlated with the difference and positively correlated with the wind direction deviation coefficient.

10. The intelligent forage detection system based on forage growth environment according to claim 8 or 9, characterized in that: The detection and control module is used to determine the wind direction deviation coefficient, wherein: The detection and control module obtains wind direction vectors at several moments in a preset monitoring period, calculates the vector angle between any wind direction vector and the remaining wind direction vectors, and determines the vector angle variance as the wind direction deviation coefficient.

Images