Precise sowing and germination rate increasing system based on pine tree seeds

Abstract

The invention relates to the technical field of seeding analysis, in particular to a precise seeding and germination rate increasing system based on pine seeds, comprising: a seed detection module for detecting the quality of pine seeds, the seed detection module comprising a camera and a multispectral analyzer, detecting the appearance and internal quality of the seeds based on an image recognition technology and a multispectral analysis technology; the precise seeding module is used for grading the seeds according to a detection result of the seed detection module, grading comprises a preferential seeding object, a common seeding object and a non-preferential seeding object, and the precise seeding module comprises a controller, a seeder and a positioning unit. According to the method, the germination rate of the pine tree seeds is greatly increased, the utilization efficiency of the seeds is optimized, resource waste is avoided, and the overall sowing effect is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sowing analysis, and in particular to a precise sowing and germination rate improvement system based on pine seeds. Background Art

[0002] Pine is one of the most widely planted tree species in the world. It plays an important role in forestry, ecological restoration and the timber industry. However, the sowing and germination rate of pine seeds have always been key issues in forestry production. Traditional pine seed sowing methods mostly use mechanical sowing or manual broadcasting. Although this method is simple, it has problems such as uneven seed distribution, inaccurate sowing depth, and difficulty in adapting to different soil conditions, resulting in low germination rate and poor seedling survival rate. In addition, the quality of pine seeds themselves varies, and it is difficult to distinguish between high-quality seeds and low-quality seeds in appearance, which increases the risk of resource waste during the sowing process.

[0003] In the prior art, some methods attempt to improve the germination rate by improving sowing equipment or optimizing sowing conditions. For example, using an intelligent seeder combined with sensors to monitor soil conditions in real time to adjust the sowing depth and density; or using simple seed screening technology to remove obviously inferior seeds. However, these technologies have many limitations, such as: lack of accurate detection of seed quality, lack of environmental adaptability in sowing path planning, and insufficient real-time response of the sowing process to changes in soil conditions, resulting in limited effect on improving the overall germination rate.

[0004] In order to solve the above problems, the present invention proposes a precise sowing and germination rate improvement system based on pine seeds. Summary of the invention

[0005] The present invention provides a precise sowing and germination rate improvement system based on pine seeds.

[0006] The precision sowing and germination rate improvement system based on pine seeds includes:

[0007] A seed detection module is used to detect the quality of pine seeds. The seed detection module includes a high-resolution camera and a multi-spectral analyzer, and detects the appearance and internal quality of seeds based on image recognition technology and multi-spectral analysis technology;

[0008] A precision sowing module, which classifies seeds according to the detection results of the seed detection module, wherein the classification includes priority sowing objects, common sowing objects and non-priority sowing objects, and the precision sowing module includes a controller, a seeder and a positioning unit;

[0009] The positioning unit realizes the positioning and path planning of the seeder through satellite positioning and inertial navigation technology, and the path planning takes into account soil conditions and seed grading results to ensure that high-quality seeds are sown in the best position;

[0010] The controller instructs the seeder to sow along the planned path. For priority sowing objects, the sowing depth and sowing density are set to the optimal parameters (the optimal parameters are set according to the seed type and the optimal sowing parameters in the corresponding sowing instruction manual); for non-priority sowing objects, the seeder automatically adjusts the sowing depth and density to avoid wasting seed resources in unsuitable areas. High-quality seeds can be allocated to soil areas that are more suitable for their growth, while inferior or defective seeds can be avoided from being sown in key areas, thereby improving the overall efficiency of the entire sowing area. Path planning can also ensure that seeds are evenly distributed, avoiding resource waste and uneven growth.

[0011] Optionally, the seed detection module specifically includes:

[0012] Appearance quality detection submodule: using the high-resolution camera to collect surface images of pine seeds, analyzing them through image recognition technology, and detecting the surface defects, color consistency, and shape regularity quality parameters of the seeds;

[0013] Internal quality detection submodule: Use the multi-spectral analyzer to perform multi-band spectral scanning on pine seeds to obtain the internal composition and structure information of the seeds; use multi-spectral analysis technology to identify the internal moisture content of the seeds and perform internal structure detection, including whether there are internal cavities, immature areas or diseased areas.

[0014] Optionally, the seed detection module further includes a comprehensive quality assessment submodule, which combines the results of the appearance quality detection submodule and the internal quality detection submodule to comprehensively assess the overall quality of the pine seeds, and assesses the overall quality of the pine seeds through a comprehensive quality scoring function to obtain a comprehensive quality score Q, and the comprehensive quality scoring function is defined as:

[0015]

[0016] Among them, Q is the comprehensive quality score, which indicates the overall quality of the seeds. α1, α2, α3, α4, and α5 are the weight coefficients of various test indicators, which are set according to actual needs. D ,T C ,T S , is the threshold for surface defects, color consistency, shape regularity, and internal structure consistency, W ref is the reference moisture content value, set according to empirical data, W range It is the normal moisture content range, indicating the normal fluctuation range of seed moisture content.

[0017] Optionally, the controller receives and analyzes the comprehensive quality score Q output by the seed detection module, the comprehensive quality score Q including the surface defect judgment value D, the color consistency judgment value C v , shape regularity judgment value S, water content W, internal structure-consistency judgment value I s ;

[0018] The grading strategy for grading seeds according to the detection results of the seed detection module includes:

[0019] If Q>Q high , then the seed is marked as a priority seeding object, where Q high is the scoring threshold for high-quality seeds;

[0020] If Q≤Q low , then the seed is marked as a non-priority seeding object, or it is seeded in a non-critical area according to demand, where Q low The scoring threshold for low quality seeds.

[0021] Optionally, the path planning takes into account soil conditions and seed grading results, and the path planning is defined based on the path planning function P(x, y) as:

[0022] Among them, P(x,y) represents the target position (x,y) of the seeding path, N represents the number of seeds considered in the current path planning, and Q i represents the comprehensive quality score of the i-th seed, and F(x,y) represents the soil condition function, which is used to determine whether the current location is suitable for sowing.

[0023] Optionally, for non-priority sowing objects, the sowing device automatically adjusts the sowing depth and density, specifically including sowing depth adjustment and sowing density adjustment, and the final sowing depth D is obtained after the sowing depth adjustment. s The final sowing density ρ is obtained after the sowing density is adjusted. adj .

[0024] Optionally, the sowing depth adjustment is expressed as: D s =D ref +β·(Q target -Q), where D s is the final sowing depth, D ref is the reference sowing depth, β is the sowing depth adjustment coefficient, which is used to control the amplitude of depth adjustment. The larger the value, the more significant the adjustment. target is the target comprehensive quality score, which is used to compare the score Q of the current seed; when the actual quality score of the seed is lower than the target score targe, the depth

[0025] will increase or decrease to compensate for the lack of seeds and thus provide a more suitable growing environment;

[0026] The sowing density adjustment is expressed as: adj =ρ ref ·(1+δ·(Q target -Q)), where ρ adj is the final seeding density, ρ ref is the reference sowing density, δ is the sowing density adjustment coefficient, which is used to control the amplitude of density adjustment. The larger the value, the more significant the adjustment. target is the target comprehensive quality score, which is used to compare the score Q of the current seed; when the actual quality score of the seed is lower than the target score targe, the density

[0027] adj will be adjusted accordingly to optimize seed distribution and ensure rational use of resources.

[0028] Collect historical data, conduct regression analysis on the relationship between sowing depth, density, germination rate, and seed quality score, and derive the most appropriate β and δ values;

[0029] Or it can be obtained through experiments. In the actual sowing process, the sowing depth and density are adjusted, and the germination rate and growth effect under different parameter settings are recorded. Through multiple experiments, the β and δ values ​​that can best optimize the germination rate are found.

[0030] Optionally, the soil condition function F(x, y) includes a terrain suitability function F terrain (x, y) and soil suitability function F soil (x, y), then the path planning function P(x, y) is updated and defined as:

[0031]

[0032] Optionally, the surface defect detection uses a camera to collect the surface image of the pine seed, generates an image matrix I (x, y), where x and y are pixel coordinates of the image, and performs surface defect detection through image recognition technology to obtain a surface defect judgment value D, as follows:

[0033] Use Canny edge detection to extract the edge features E(x, y) of the seed surface, and define the judgment function D of the surface defect as: D = ∑ x，y |I(x,y)-E(x,y)|, where D is the surface defect judgment value, indicating the degree of surface defects of the seed, I(x,y) is the original image matrix, indicating the pixel value of the seed, E(x,y) is the image matrix after edge detection, x, y are the pixel coordinates of the image, and when D exceeds the preset threshold T D When the seeds are tested, it is determined that there are surface defects.

[0034] The color consistency detection is based on the color histogram equalization technology to calculate the color distribution C(c) of the image, where c is the color value, and obtain the color consistency judgment value based on the color consistency judgment function, which is defined as:

[0035] Among them, C v is the color consistency judgment value, indicating the uniformity of color distribution, C(c) is the frequency of color value c in the color histogram, is the mean of the color histogram, N is the number of color channels, if C v Exceeds the preset threshold T C , then the seeds are judged to have inconsistent colors;

[0036] The shape regularity detection calculates the shape regularity by Hu moment, and the seven invariant moments of Hu moment are H1, H2, ..., H7. The shape regularity judgment value is obtained based on the shape regularity judgment function, which is defined as:

[0037] Among them, S is the shape regularity judgment value, which indicates the regularity of the seed shape, and H i is the i-th invariant moment of the Hu moment, is the mean of the standard shape descriptors. If S exceeds the preset threshold T S , the seed shape is judged to be irregular.

[0038] Furthermore, the moisture content detection uses a multi-spectral analyzer to perform multi-band spectral scanning on pine seeds to obtain the reflectance spectrum data R(λ) of each band, where λ is the wavelength, and the spectral absorption value A is calculated based on the absorption characteristic band of water (970nm). water , define the water content W as: W = k·A water , where W is the moisture content, indicating the moisture content of the seeds, and k is the calibration coefficient, which is determined based on experimental data. If W is lower or higher than the preset normal range, the seed moisture content is judged to be abnormal.

[0039] The internal structure detection constructs an internal structure model through multi-spectral reflectance data R(λ) and calculates the internal structure consistency I s , expressed as:

[0040] Among them, I s is the internal structure consistency judgment value, indicating the uniformity of the internal structure of the seed, R j (λ1),R j (λ2) is the reflectance of the jth spectral sample at wavelengths λ1 and λ2, M is the number of spectral samples, λ1 and λ2 are two characteristic wavelengths, if I s Exceeding the threshold It is determined that there are abnormalities in the internal structure of the seeds, such as internal cavities, immature areas or diseased areas.

[0041] Beneficial effects of the present invention:

[0042] The present invention comprehensively evaluates the quality of pine seeds through a seed detection module, and combines a positioning unit to accurately plan a sowing path through satellite positioning and inertial navigation technology. It can dynamically adjust the sowing depth and density based on the comprehensive quality score Q of the seeds to ensure that high-quality seeds are sown in the best position and conditions, while ordinary or low-quality seeds are appropriately adjusted according to actual conditions. This combination can greatly improve the germination rate of pine seeds, optimize the utilization efficiency of seeds, avoid waste of resources, and significantly improve the overall sowing effect.

[0043] The present invention introduces a terrain suitability function and a soil condition suitability function to guide the planning of the sowing path. The positioning unit combines the terrain and soil conditions to ensure that the seeds are sown in the most suitable area, and adjusts the operation of the seeder through real-time data feedback. In particular, the adjustment of the sowing depth and density is achieved through specific calculations to ensure that the sowing conditions match the quality of the seeds. This data-driven path planning and sowing control method can adapt to different environmental conditions, ensure the best seed growth environment, and greatly improve the germination rate and growth quality of the seeds.

[0044] The present invention ensures that high-quality seeds obtain the best sowing conditions through intelligent decision-making driven by the comprehensive quality score Q, and makes intelligent adjustments to ordinary and low-quality seeds, flexibly responds to quality differences among different seeds, and optimizes sowing strategies. The intelligent sowing strategy based on the comprehensive quality score solves the problem of uneven germination rate caused by seed quality differences in traditional sowing methods, and improves the resource utilization efficiency and production benefits of the entire sowing area. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A schematic diagram of system function modules according to an embodiment of the present invention;

[0047] Figure 2 Schematic diagram of a seed detection module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0049] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0050] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0051] like Figure 1-Figure 2 As shown in the figure, the precise sowing and germination rate improvement system based on pine seeds includes:

[0052] The seed detection module is used to detect the quality of pine seeds. The seed detection module includes a high-resolution camera and a multi-spectral analyzer. It detects the appearance and internal quality of seeds based on image recognition technology and multi-spectral analysis technology.

[0053] A precision seeding module, which classifies seeds according to the detection results of the seed detection module, and the classification includes priority seeding objects, common seeding objects and non-priority seeding objects. The precision seeding module includes a controller, a seeding device and a positioning unit;

[0054] The positioning unit uses satellite positioning and inertial navigation technology to achieve positioning and path planning of the seeder. The path planning takes soil conditions and seed grading results into consideration to ensure that high-quality seeds are sown in the best position.

[0055] The controller instructs the seeder to sow along the planned path. For priority sowing objects, the sowing depth and density are set to the optimal parameters (the optimal parameters are set according to the seed type and the optimal sowing parameters in the corresponding sowing instruction manual); for non-priority sowing objects, the seeder automatically adjusts the sowing depth and density to avoid wasting seed resources in unsuitable areas. High-quality seeds can be allocated to soil areas that are more suitable for their growth, while inferior or defective seeds can be avoided from being sown in key areas, thereby improving the overall efficiency of the entire sowing area. Path planning can also ensure that seeds are evenly distributed, avoiding resource waste and uneven growth;

[0056] Satellite positioning data provides the absolute location information of the device, including latitude, longitude and altitude, through the Global Navigation Satellite System (GNSS);

[0057] Inertial navigation data uses the accelerometer and gyroscope to obtain the device's motion trajectory data and angular velocity, and is used to maintain position tracking when there is no satellite signal.

[0058] The positioning unit combines satellite positioning and inertial navigation technology to ensure the accuracy and continuity of path planning. Satellite positioning data provides absolute position information, while inertial navigation technology is used to calculate the current position by integrating velocity and acceleration when the satellite signal is unstable.

[0059] The seed detection module specifically includes:

[0060] Appearance quality inspection submodule: uses a high-resolution camera to collect surface images of pine seeds, analyzes them through image recognition technology, and detects quality parameters such as surface defects, color consistency, and shape regularity of the seeds;

[0061] Internal quality detection submodule: Use a multi-spectral analyzer to perform multi-band spectral scanning on pine seeds to obtain the internal composition and structure information of the seeds; through multi-spectral analysis technology, identify the internal moisture content of the seeds and perform internal structure detection, including whether there are internal cavities, immature areas or diseased areas.

[0062] The seed detection module also includes a comprehensive quality assessment submodule. The comprehensive quality assessment submodule combines the results of the appearance quality detection submodule and the internal quality detection submodule to comprehensively evaluate the overall quality of pine seeds. The overall quality of pine seeds is evaluated through a comprehensive quality scoring function to obtain a comprehensive quality score Q. The comprehensive quality scoring function is defined as:

[0063]

[0064] Among them, Q is the comprehensive quality score, which indicates the overall quality of the seeds. α1, α2, α3, α4, and α5 are the weight coefficients of various test indicators, which are set according to actual needs.D ,T C ,T S , is the threshold for surface defects, color consistency, shape regularity, and internal structure consistency, W ref is the reference moisture content value, set according to empirical data, W range It is the normal moisture content range, indicating the normal fluctuation range of seed moisture content.

[0065] The score will be used as input data for the precision seeding module to determine the seeding location and depth, ensuring that high-quality seeds are given priority for seeding.

[0066] The controller receives and analyzes the comprehensive quality score Q output by the seed detection module. The comprehensive quality score Q includes the surface defect judgment value D and the color consistency judgment value C. v , shape regularity judgment value S, water content W, internal structure-consistency judgment value I s ;

[0067] The classification strategies for classifying seeds according to the detection results of the seed detection module include:

[0068] If Q>Q high , then the seed is marked as a priority seeding object, where Q high is the scoring threshold for high-quality seeds;

[0069] If Q≤Q low , then the seed is marked as a non-priority seeding object, or it is seeded in a non-critical area according to demand, where Q low The scoring threshold for low quality seeds.

[0070] Path planning takes into account soil conditions and seed grading results. Path planning is based on the path planning function P(x,y) defined as:

[0071] Among them, P(x,y) represents the target position (x,y) of the seeding path, N represents the number of seeds considered in the current path planning, and Q i represents the comprehensive quality score of the i-th seed, and F(x,y) represents the soil condition function, which is used to determine whether the current location is suitable for sowing.

[0072] For non-priority sowing objects, the seeder automatically adjusts the sowing depth and density, including sowing depth adjustment and sowing density adjustment. After the sowing depth is adjusted, the final sowing depth D s , the final sowing density ρ is obtained after the sowing density is adjusted adj .

[0073] The sowing depth adjustment is expressed as: D s =Dref +β·(Q target -Q), where D s is the final sowing depth, D ref is the reference sowing depth, β is the sowing depth adjustment coefficient, which is used to control the amplitude of depth adjustment. The larger the value, the more significant the adjustment. target It is the target comprehensive quality score, which is used to compare the score Q of the current seed. When the actual quality score of the seed is lower than the target score targe, the depth will increase or decrease to compensate for the deficiency of the seed, thereby providing a more suitable growth environment.

[0074] The seeding density adjustment is expressed as: ρ adj =ρ ref ·(1+δ·(Q target -Q)), where ρ adj is the final seeding density, ρ ref is the reference sowing density, δ is the sowing density adjustment coefficient, which is used to control the amplitude of density adjustment. The larger the value, the more significant the adjustment. target is the target comprehensive quality score, which is used to compare the score Q of the current seed; when the actual quality score of the seed is lower than the target score targe, the density

[0075] adj will be adjusted accordingly to optimize seed distribution and ensure rational use of resources.

[0076] Collect historical data, conduct regression analysis on the relationship between sowing depth, density, germination rate, and seed quality score, and derive the most appropriate β and δ values;

[0077] Or it can be obtained through experiments. In the actual sowing process, the sowing depth and density are adjusted, and the germination rate and growth effect under different parameter settings are recorded. Through multiple experiments, the β and δ values ​​that can best optimize the germination rate are found.

[0078] The soil condition function F(x,y) includes the terrain suitability function F terrain (x, y) and soil suitability function F soil (x, y), then the path planning function P(x, y) is updated and defined as:

[0079]

[0080] 1. Terrain suitability function F terrain (x, y) is used to assess whether the terrain is suitable for sowing, based on slope suitability and elevation suitability;

[0081] Slope suitability f g (x,y): slope Too large will lead to soil loss or uneven seed distribution. The suitability function is as follows:

[0082]

[0083] where g max is the maximum suitable slope, g std is the standard deviation of slope.

[0084] Elevation suitability h (x,y): The change of elevation h(x,y) affects the difficulty of sowing operation and the survival rate of seeds. The suitability function is as follows:

[0085]

[0086] where h max is the optimal elevation range, h std is the elevation standard deviation.

[0087] 2. Soil suitability function F soil (x,y) based on soil moisture H s (x,y), pH(x,y) and temperature T s (x,y) evaluates the growth conditions of the seed at that location;

[0088] Humidity suitability

[0089]

[0090] Acidity suitability

[0091]

[0092] Temperature suitability

[0093]

[0094] Surface defect detection uses a camera to collect the surface image of pine seeds and generate an image matrix I (x, y), where x and y are the pixel coordinates of the image. Surface defect detection is performed through image recognition technology to obtain the surface defect judgment value D, as follows:

[0095] Use Canny edge detection to extract the edge features E(x, y) of the seed surface, and define the judgment function D of the surface defect as: D = ∑ x，y |I(x,y)-E(x,y)|, where D is the surface defect judgment value, indicating the degree of surface defects of the seed, I(x,y) is the original image matrix, indicating the pixel value of the seed, E(x,y) is the image matrix after edge detection, x, y are the pixel coordinates of the image, and when D exceeds the preset threshold T DWhen the seeds are tested, it is determined that there are surface defects.

[0096] Color consistency detection is based on color histogram equalization technology. The color distribution C(c) of the image is calculated, where c is the color value. The color consistency judgment value is obtained based on the color consistency judgment function, which is defined as:

[0097] Among them, C v is the color consistency judgment value, indicating the uniformity of color distribution, C(c) is the frequency of color value c in the color histogram, is the mean of the color histogram, N is the number of color channels, if C v Exceeds the preset threshold T C , then the seeds are judged to have inconsistent colors;

[0098] Shape regularity detection calculates shape regularity through Hu moment. The seven invariant moments of Hu moment are H1, H2, …, H7. The shape regularity judgment value is obtained based on the shape regularity judgment function, which is defined as:

[0099] Among them, S is the shape regularity judgment value, which indicates the regularity of the seed shape, and H i is the i-th invariant moment of the Hu moment, is the mean of the standard shape descriptors. If S exceeds the preset threshold T S , the seed shape is judged to be irregular.

[0100] The moisture content is detected by using a multi-spectral analyzer to perform multi-band spectral scanning on pine seeds to obtain the reflectance spectrum data R(λ) of each band, where λ is the wavelength. Based on the absorption characteristic band of water (970nm), the spectral absorption value A is calculated. water , define the water content W as: W = k·A water , where W is the moisture content, indicating the moisture content of the seeds, and k is the calibration coefficient, which is determined based on experimental data. If W is lower or higher than the preset normal range, the seed moisture content is judged to be abnormal.

[0101] Internal structure detection uses multispectral reflectance data R(λ) to build an internal structure model and calculate the internal structure consistency I s , expressed as:

[0102] Among them, I s is the internal structure consistency judgment value, indicating the uniformity of the internal structure of the seed, R j (λ1),R j (λ2) is the reflectance of the jth spectral sample at wavelengths λ1 and λ2, M is the number of spectral samples, λ1 and λ2 are two characteristic wavelengths, if I sExceeding the threshold It is determined that there are abnormalities in the internal structure of the seeds, such as internal cavities, immature areas or diseased areas.

[0103] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0104] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A precise sowing and germination rate improvement system based on pine seeds, characterized in that: include: A seed detection module, used to detect the quality of pine seeds, the seed detection module includes a camera and a multi-spectral analyzer, and detects the appearance and internal quality of seeds based on image recognition technology and multi-spectral analysis technology; A precision sowing module, which classifies seeds according to the detection results of the seed detection module, wherein the classification includes priority sowing objects, common sowing objects and non-priority sowing objects, and the precision sowing module includes a controller, a seeder and a positioning unit; The positioning unit realizes the positioning and path planning of the seeder through satellite positioning and inertial navigation technology, and the path planning takes into account soil conditions and seed grading results to ensure that high-quality seeds are sown in the best position; The controller instructs the seeder to sow according to the planned path. For priority sowing objects, the sowing depth and sowing density are set to optimal parameters; for non-priority sowing objects, the seeder automatically adjusts the sowing depth and density.

2. The precise sowing and germination rate improvement system based on pine seeds according to claim 1 is characterized in that: The seed detection module specifically includes: Appearance quality detection submodule: using the camera to collect surface images of pine seeds, analyzing them through image recognition technology, and detecting the surface defects, color consistency, and shape regularity quality parameters of the seeds; Internal quality detection submodule: Use the multi-spectral analyzer to perform multi-band spectral scanning on pine seeds to obtain the internal composition and structure information of the seeds; use multi-spectral analysis technology to identify the internal moisture content of the seeds and perform internal structure detection.

3. The precise sowing and germination rate improvement system based on pine seeds according to claim 2 is characterized in that: The seed detection module also includes a comprehensive quality assessment submodule, which combines the results of the appearance quality detection submodule and the internal quality detection submodule to comprehensively assess the overall quality of the pine seeds, and assesses the overall quality of the pine seeds through a comprehensive quality scoring function to obtain a comprehensive quality score Q.

4. The precise sowing and germination rate improvement system based on pine seeds according to claim 3 is characterized in that: The controller receives and analyzes the comprehensive quality score Q output by the seed detection module, and the comprehensive quality score Q includes the surface defect judgment value D, the color consistency judgment value C v , shape regularity judgment value S, water content W, internal structure-consistency judgment value I s ; The grading strategy for grading seeds according to the detection results of the seed detection module includes: If Q>Q high , then the seed is marked as a priority seeding object, where Q high is the scoring threshold for high-quality seeds; If Q≤Q low , then the seed is marked as a non-priority seeding object, where Q low The scoring threshold for low quality seeds.

5. The precise sowing and germination rate improvement system based on pine seeds according to claim 4 is characterized in that: The path planning takes into account soil conditions and seed grading results. The path planning is based on the path planning function P(x, y) defined as: Among them, P(x,y) represents the target position (x,y) of the seeding path, N represents the number of seeds considered in the current path planning, and Q i represents the comprehensive quality score of the i-th seed, and F(x,y) represents the soil condition function, which is used to determine whether the current location is suitable for sowing.

6. The precise sowing and germination rate improvement system based on pine seeds according to claim 5 is characterized in that: For non-priority sowing objects, the sowing device automatically adjusts the sowing depth and density, specifically including sowing depth adjustment and sowing density adjustment. After the sowing depth adjustment, the final sowing depth D s The final sowing density ρ is obtained after the sowing density is adjusted. adj .

7. The precise sowing and germination rate improvement system based on pine seeds according to claim 6 is characterized in that: The sowing depth adjustment is expressed as: D s =D ref +β·(Q target -Q), where D s is the final sowing depth, D ref is the reference sowing depth, β is the sowing depth adjustment coefficient, which is used to control the amplitude of depth adjustment, Q target The target comprehensive quality score is used to compare the score Q of the current seed; The sowing density adjustment is expressed as: adj =ρ ref ·(1+δ·(Q target -Q)), where ρ adj is the final seeding density, ρ ref is the reference sowing density, δ is the sowing density adjustment coefficient, which is used to control the amplitude of density adjustment, Q target It is the target comprehensive quality score, which is used to compare the score Q of the current seed.

8. The precise sowing and germination rate improvement system based on pine seeds according to claim 5 is characterized in that: The soil condition function F(x, y) includes the terrain suitability function F terrain (x, y) and soil suitability function F soil (x, y), then the path planning function P(x, y) is updated and defined as:

9. The precise sowing and germination rate improvement system based on pine seeds according to claim 2, characterized in that: The surface defect detection uses a camera to collect the surface image of the pine seed, generates an image matrix I (x, y), where x and y are the pixel coordinates of the image, and performs surface defect detection through image recognition technology to obtain a surface defect judgment value D; The color consistency detection is based on the color histogram equalization technology, calculates the color distribution C(c) of the image, where c is the color value, and obtains the color consistency judgment value based on the color consistency judgment function; The shape regularity detection calculates shape regularity through Hu moment, and the seven invariant moments of Hu moment are H1, H2, ..., H7 respectively, and the shape regularity determination value is obtained based on the shape regularity determination function.

10. The precise sowing and germination rate improvement system based on pine seeds according to claim 2, characterized in that: The moisture content detection uses a multi-spectral analyzer to perform multi-band spectral scanning on pine seeds to obtain the reflection spectrum data R(λ) of each band, where λ is the wavelength, and the spectral absorption value A is calculated based on the absorption characteristic band of water. water , define the water content W as: W = k·A water , where W is the moisture content, indicating the moisture content of the seeds, and k is the calibration coefficient. If W is lower or higher than the preset normal range, the seed moisture content is judged to be abnormal; The internal structure detection constructs an internal structure model through multi-spectral reflectance data R(λ) and calculates the internal structure consistency I s , expressed as: Among them, I s is the internal structure consistency judgment value, indicating the uniformity of the internal structure of the seed, R j (λ1),R j (λ2) is the reflectance of the jth spectral sample at wavelengths λ1 and λ2, M is the number of spectral samples, λ1 and λ2 are two characteristic wavelengths, if I s Exceeding the threshold It is determined that there is an abnormality in the internal structure of the seed.

Images