Layered detection and investigation method and device for in-situ soil living small animals

Abstract

The invention discloses an in-situ soil living small animal layered detection and investigation method and device, and the method comprises the steps: automatically collecting multi-mode hyperspectral imaging data of a layered soil sample through an in-situ soil living small animal layered instance segmentation device; carrying out pixel instance segmentation on the multi-modal hyperspectral imaging data by utilizing a soil animal 3D convolution instance segmentation deep network model, independently identifying the variety and instance individual quantity of small animals in each layer of soil, and further calculating the variety, instance individual quantity and density of the small animals in the in-situ integral soil sample; the longitudinal distribution condition of the small animals in the soil is determined. The invention breaks through the limitation of the traditional soil ecology research, avoids the low efficiency and large error of methods such as mechanical earth cutting, manual selection, insect trapping and the like, and provides a rapid and accurate soil animal detection technology. The technology provides reliable data support for soil ecology research and agricultural management, and is an advanced tool for soil health management and agricultural sustainable development.

Description

Technical Field

[0001] The invention belongs to the field of soil ecology investigation, and in particular relates to an in-situ soil living small animal stratification detection investigation method and device. Background Art

[0002] Soil fauna play a vital role in ecosystems by decomposing organic matter, promoting nutrient cycling, and improving soil structure. Their activities, such as burrowing and foraging, increase soil porosity and water retention, creating a heterogeneous environment that supports diverse microbial communities. These processes not only promote plant growth but also maintain soil health, so soil fauna are essential for sustainable ecosystems. Field soil fauna surveys are an important part of ecological research. However, traditional survey methods, such as direct observation and trap methods, usually require soil samples to be removed from their natural environment, which is not only time-consuming and labor-intensive, but also prone to inaccurate results due to human errors and subjective judgments. In addition, these methods often lack in-depth analysis of the soil hierarchical structure and are difficult to provide the distribution of living soil fauna in different soil depth layers. Although biomarker analysis can provide quantitative data, its complex chemical processing and analysis process not only increases costs but also prolongs the research cycle. Summary of the invention

[0003] In order to overcome the problems in the prior art, the present invention proposes a method and device for layered detection and investigation of live small animals in soil in situ. This method directly detects the in situ soil samples, avoids interference and contamination during the sample transfer process, and ensures the authenticity and reliability of the data. At the same time, the layered detection technology of the present invention can accurately identify the types, quantity and distribution of small soil animals in different soil layers, providing a new perspective for the study of soil ecological structure. Compared with traditional methods, the real-time recognition capability of the present invention significantly improves the detection efficiency, and the automated soil layered detection method simplifies the operation process and lowers the technical threshold. In addition, the detection method of the present invention does not require chemical treatment, reducing the impact on the environment and organisms. The present invention aims to achieve rapid, accurate, and layered detection of live small animals in soil through innovative technologies, reduce interference with the soil environment, improve detection efficiency, reduce costs, and provide more reliable data support for soil ecological research and agricultural management. This method provides a more advanced tool for soil ecological research and agricultural practice, promoting soil health management and sustainable agricultural development.

[0004] The technical scheme for achieving the purpose of the present invention is as follows:

[0005] A method and device for in-situ soil live small animal stratification detection and investigation, wherein naturally collected soil samples are placed in an in-situ soil live small animal stratification instance segmentation device, a gas anesthesia system controls the anesthetic gas to uniformly pass into a soil sample stratification detection box, after the small animals in the soil sample are anesthetized, an information processing unit in the in-situ soil live small animal stratification instance segmentation device controls a hyperspectral imaging module in combination with a broadband light source illumination module to collect the reflection spectrum of the small animals in the soil sample; the information processing unit controls the hyperspectral imaging module in combination with an ultraviolet light excitation module to detect the fluorescence spectrum of the small animals in the soil sample; the reflection spectrum and the fluorescence spectrum constitute multimodal hyperspectral imaging data, which are pixel-by-pixel segmented by a soil animal 3D convolution instance segmentation deep network model, and the pixel label category of the soil small animals is identified while segmenting the pixel regions of the soil small animals and the soil;

[0006] The in-situ soil living small animal stratified instance segmentation device adopts stratified detection, and the soil animal 3D convolutional instance segmentation deep network model independently identifies the types and number of individual instances of small animals in each layer of soil, and finally calculates the types, number of individual instances, distribution density of small animals in the in-situ overall soil sample, as well as the longitudinal distribution of small animals in the soil.

[0007] The in-situ soil living small animal stratification instance segmentation device includes an instrument light-shielding sealed cover, a broadband light source illumination module, a hyperspectral imaging module, a first electric displacement platform, an electric push arm module, a gas anesthesia system, a soil sample stratification detection box, a soil sample storage box, an ultraviolet light excitation module, an information processing unit, and a flippable transparent window module; the broadband light source illumination module, the hyperspectral imaging module, the first electric displacement platform, the electric push arm module, and the gas anesthesia system are respectively connected to the information processing unit.

[0008] The broadband light source illumination module comprises a first broadband light source, a second broadband light source, a first condensing lens, and a second condensing lens; the first broadband light source is connected to the second condensing lens; the second broadband light source is connected to the first condensing lens;

[0009] The hyperspectral imaging module comprises a first lens, a slit, a second lens, a spectrum conversion module, a third lens, a camera, and a second electric displacement platform; the first lens, the slit, the second lens, the spectrum conversion module, the third lens, and the camera are connected to the second electric displacement platform; the first electric displacement platform drives the hyperspectral imaging module to move;

[0010] The electric push arm module includes a first electric push arm, a second electric push arm, a third electric push arm, a fourth electric push arm, a fifth electric push arm, a sixth electric push arm, and a seventh electric push arm; the first electric push arm, the second electric push arm, the third electric push arm, the fourth electric push arm, the fifth electric push arm, the sixth electric push arm, and the seventh electric push arm are connected in sequence from top to bottom;

[0011] The ultraviolet light excitation module includes a first ultraviolet light source, a fourth lens, a first rotating motor, a first bandpass filter group, a second ultraviolet light source, a fifth lens, a second rotating motor, a second bandpass filter group, a third ultraviolet light source, a sixth lens, a third rotating motor, a third bandpass filter group, a fourth ultraviolet light source, a seventh lens, a fourth rotating motor, a fourth bandpass filter group, a fifth ultraviolet light source, an eighth lens, a fifth rotating motor, a fifth bandpass filter group, a sixth ultraviolet light source, a ninth lens, a sixth rotating motor, a sixth bandpass filter group, a seventh ultraviolet light source, a tenth lens, a seventh rotating motor, and a seventh bandpass filter group; A first ultraviolet light source, a fourth lens, a first rotating motor connected to a first bandpass filter group; a second ultraviolet light source, a fifth lens, a second rotating motor connected to a second bandpass filter group; a third ultraviolet light source, a sixth lens, a third rotating motor connected to a third bandpass filter group; a fourth ultraviolet light source, a seventh lens, a fourth rotating motor connected to a fourth bandpass filter group; a fifth ultraviolet light source, an eighth lens, a fifth rotating motor connected to a fifth bandpass filter group; a sixth ultraviolet light source, a ninth lens, a sixth rotating motor connected to a sixth bandpass filter group; a seventh ultraviolet light source, a tenth lens, a seventh rotating motor connected to a seventh bandpass filter group;

[0012] The flippable transparent window module comprises a first flippable transparent window, a second flippable transparent window, a third flippable transparent window, a fourth flippable transparent window, a fifth flippable transparent window, a sixth flippable transparent window, and a seventh flippable transparent window; the first flippable transparent window, the second flippable transparent window, the third flippable transparent window, the fourth flippable transparent window, the fifth flippable transparent window, the sixth flippable transparent window, and the seventh flippable transparent window are connected from top to bottom; the information processing unit comprises an industrial computer and a data connection line; the information processing unit is respectively connected to a broadband light source illumination module, a hyperspectral imaging module, an electric push arm module, a gas anesthesia system, an ultraviolet light excitation module, and a first electric displacement platform. The information processing unit is used to control the operating sequence of the broadband light source illumination module, the ultraviolet light excitation module, the hyperspectral imaging module, the electric push arm module, the gas anesthesia system and the first electric translation stage, so that the hyperspectral imaging module can orderly collect the multimodal hyperspectral data of all layered soil samples in the soil sample layered detection box, and perform instance segmentation of small animals in the multimodal hyperspectral data of the soil samples to calculate information such as the type of small animals in the soil samples, the number of individual instances and the distribution density.

[0013] The hierarchical detection method and the soil animal 3D convolutional instance segmentation deep network model calculate the types and number of individual instances of small animals on the soil surface based on the reflectance spectrum and fluorescence spectrum collected by the in-situ soil living small animal hierarchical instance segmentation device, and use the following method to estimate the types and number of individual instances of small animals in the deep soil:

[0014] The volume of the soil sample obtained from the soil in situ is (x, y, z), and the number of small animals of various types in the soil is S (S1, S2, S 3, …,S n ), where n is the number of small animal species in the soil;

[0015] In-situ soil living small animal stratification example segmentation device divides the soil sample into k layers in the longitudinal position; let the current soil sample stratification sequence be q, the volume of each layer of soil sample be (x, y, z / k), and the number of small animals of various types in the qth layer of soil sample be P q (P q 1,P q 2,P q 3, …,P q m ), where m is the total number of small animal species in the qth layer of soil samples;

[0016] The calibration method is as follows: according to the reflectance spectrum and fluorescence spectrum of the surface of the first layer of soil samples in the soil sample stratification detection box 10 collected by the in-situ soil living small animal stratification instance segmentation device, the multimodal hyperspectral imaging data is formed, and the types and instance individual numbers of small animals on the surface of the first layer of soil samples are identified through the soil animal 3D convolution instance segmentation deep network model, and the type number set T of small animals on the surface of the current soil sample is obtained. 1 (T 1 1,T 1 2,T 1 3, …,T 1 m ); By manually separating the small animals inside the soil samples, selecting and manually identifying, the total number of small animal species in the first layer of soil samples in the soil sample stratification detection box 10 is obtained. 1 (P 1 1,P 1 2,P 1 3, …,P 1 m ); Through machine learning P 1 (P 1 1,P 1 2,P 1 3, …,P1 m ) and T 1 (T 1 1,T 1 2,T 1 3, …,T 1 m ) is as follows:

[0017]

[0018] According to the above fitting relationship, the dataset T of small animals on the surface of the qth layer of soil samples is obtained by combining the in-situ soil living small animal layer instance segmentation device with the soil animal 3D convolutional instance segmentation deep network model. q (T q 1,T q 2,T q 3, …,T q m ), the total small animal species dataset P of the qth layer soil sample can be calculated q (P q 1,P q 2,P q 3, …,P q m );

[0019] Then, in the soil sample stratification detection box, the distribution density of soil small animals of type i in the qth layer of soil sample is:

[0020]

[0021] Then in the soil sample stratification detection box, the distribution density of soil small animals in the qth layer of soil sample is:

[0022]

[0023] The above steps are repeated in sequence until all the small animal species data sets of the stratified soil samples in the soil sample stratification detection box are detected;

[0024] The number of individuals of various types of soil small animals in the soil sample stratification detection box is:

[0025]

[0026] The total number of individuals of soil small animals in the soil sample stratification detection box is:

[0027]

[0028] The distribution density of various types of soil small animals in the soil sample stratification detection box is:

[0029]

[0030] The total distribution density of soil microfauna is:

[0031]

[0032] The soil animal 3D convolutional instance segmentation deep network model can extract the spatial and spectral features of the multimodal hyperspectral imaging data collected by the in-situ soil living small animal hierarchical instance segmentation device based on the 3D convolutional neural network, so as to perform instance segmentation of small animals in the soil. The species and individual information of the instance segmentation can be used to analyze the growth cycle, male and female individual information of the soil small animal individual, so as to establish a better soil small animal library. Even if the small animal is inside the soil, the soil small animal individuals actually collected are incomplete due to the occlusion of the soil. The soil animal 3D convolutional instance segmentation deep network model defined in the present invention can be used to perform instance segmentation on the incomplete soil small animals, which can not only segment and identify the species and instance individuals of the small animals, but also analyze whether the incomplete small animal parts are covered live small animals or dead bodies with broken limbs.

[0033] In the described stratified detection, when the hyperspectral imaging module in the in-situ soil living small animal stratified instance segmentation device detects the instance segmented species of the first layer of soil small animals, the first electric push arm in the electric push arm module will push the first layer of soil through the first flip-able transparent window into the soil sample storage box; the first electric displacement platform in the hyperspectral imaging module drives the hyperspectral imaging module to move downward so that the surface image of the second layer of soil is clear; after the hyperspectral imaging module detects the instance segmented species of the second layer of soil small animals, the second electric push arm in the electric push arm module pushes the second layer of soil through the second flip-able transparent window into the soil sample storage box; and the cycle is repeated in sequence until all stratified soil samples in the soil sample stratified detection box are detected.

[0034] In the multimodal hyperspectral imaging detection, the broadband light source illumination module uses a wide spectrum band visible-near infrared band 400-1800nm ​​to detect soil small animals. After detecting the reflection spectrum of the soil sample. The information processing center controls to turn off the power of the broadband light source illumination module and turn on the power of the ultraviolet light excitation module; when detecting the first layer of soil samples in the soil sample stratification detection box, the ultraviolet light emitted by the first ultraviolet light source is collimated by the fourth lens and passes through the first bandpass filter group, and then irradiates the surface of the soil small animals from the side. The soil small animals are excited by the ultraviolet light to emit fluorescence and the fluorescence spectrum data is collected by the hyperspectral imaging module; the first rotating motor drives the first bandpass filter group to rotate to increase the switching of different bandpass filters to achieve different fluorescence band emission; when detecting the next layer of soil samples in the soil sample stratification detection box, the broadband light source illumination process is repeated and the second ultraviolet light source is switched to allow the ultraviolet light to irradiate the next layer of soil samples; the cycle is repeated until the multimodal hyperspectral imaging detection of all stratified soil samples in the soil sample stratification detection box is completed.

[0035] In the hyperspectral imaging module, the reflection or fluorescence image of the surface soil sample in the soil sample stratification detection box is imaged on the slit surface after passing through the first lens, and the light passing through the center of the slit is collimated into parallel light of different angles after passing through the second lens; the parallel light of different angles passes through the spectrum conversion module and then through the third lens to focus on the camera to form a spectrum image; the spectrum conversion module is composed of a prism-grating-prism module, or a tunable filter, and is used to separate the complex light into monochromatic light of different bands; the second electric displacement platform drives the hyperspectral imaging module to perform one-dimensional scanning, thereby realizing the reflection-fluorescence multimodal hyperspectral imaging detection of the surface soil sample in the soil sample stratification detection box.

[0036] Beneficial effects of the present invention:

[0037] The present invention discloses a method and device for layered detection and investigation of live small animals in soil in situ. A layered instance segmentation device for live small animals in soil in situ is used to perform layered multimodal hyperspectral imaging of live small animals in soil. Multimodal hyperspectral data is subjected to pixel instance segmentation by a soil animal 3D convolutional instance segmentation deep network model. According to the instance segmentation results, the species and instance individual number of small animals in each layer of soil are independently identified. Finally, the species, density and instance individual number of small animals in the in-situ overall soil sample are calculated.

[0038] The present invention overcomes the low efficiency, time-consuming and labor-intensive process of mechanically digging the soil, screening out impurities, and manually selecting small animals in the soil for empirical identification and classification in traditional soil ecology surveys, as well as the large statistical errors and low time efficiency caused by insect luring methods. A method and device for layered detection and investigation of living small animals in soil in situ is proposed. After collecting soil samples in situ, the distribution structure of soil animals is not changed, and the type, density, spatial distribution and other information of small animals in the in-situ soil samples can be quickly and accurately identified, which is of great significance to soil ecology surveys. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The present invention is a flowchart of an in-situ layered detection and investigation method for small living animals in soil.

[0040] Figure 2 It is an in-situ soil living small animal layer instance segmentation device;

[0041] Figure 2 In the invention, an instrument light-shielding sealed cover 1, a first wide-spectrum light source 2, a second wide-spectrum light source 3, a first condensing lens 4, a second condensing lens 5, a broadband light source illumination module 6, a hyperspectral imaging module 7, an electric push arm module 8, a gas anesthesia system 9, a soil sample stratification detection box 10, a soil sample storage box 11, a first electric displacement platform 12, a first lens 13, a slit 14, a second lens 15, a spectrum conversion module 16, a third lens 17, a camera 18, a second electric displacement platform 19, an ultraviolet light excitation module 20, a first ultraviolet light source 21, a fourth lens 22, a first rotating motor 23, a first bandpass filter group 24, a second ultraviolet light source 25, a fifth lens 26, a second rotating motor 27, a second bandpass filter group 28, a third ultraviolet light source 29, a sixth lens 30, a third rotating motor 31, a third bandpass filter group 32, a fourth ultraviolet light source 33, and a seventh lens 34 are provided. , a fourth rotating motor 35, a fourth bandpass filter group 36, a fifth ultraviolet light source 37, an eighth lens 38, a fifth rotating motor 39, a fifth bandpass filter group 40, a sixth ultraviolet light source 41, a ninth lens 42, a sixth rotating motor 43, a sixth bandpass filter group 44, a seventh ultraviolet light source 45, a tenth lens 46, a seventh rotating motor 47, a seventh bandpass filter group 48, a first electric push arm 49, a second electric push arm 50, a third electric push arm 51, a fourth electric push arm 52, a fifth electric push arm 53, a sixth electric push arm 54, a seventh electric push arm 55, a first flippable transparent window 56, a second flippable transparent window 57, a third flippable transparent window 58, a fourth flippable transparent window 59, a fifth flippable transparent window 60, a sixth flippable transparent window 61, a seventh flippable transparent window 62, an information processing unit 63, and a flippable transparent window module 64.

[0042] Figure 3This is an example segmentation effect diagram of soil small animals in the in-situ soil small animal layered instance segmentation device;

[0043] Figure 3 Among them, woodlice 70, woodlice 71, beetle 72, whip scorpion 73, ground centipede 74, stone centipede 75, millipede 76, cricket 77. DETAILED DESCRIPTION

[0044] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0045] A method for in-situ soil living small animal layered detection survey, the process is as follows Figure 1 As shown. A naturally collected soil sample with a volume of (x, y, z) is placed in the in-situ soil live small animal stratification instance segmentation device, and the gas anesthesia system controls the anesthetic gas to flow into the soil sample stratification detection box 10 at a uniform speed, waiting until the small animal is quiet and stable. The in-situ soil live small animal stratification instance segmentation device divides the soil sample into k layers in the longitudinal position; let the current soil sample stratification sequence number be q, and the first layer of soil sequence number q=1 on the surface; for the first layer of soil sample, the information processing unit 63 in the in-situ soil live small animal stratification instance segmentation device controls the hyperspectral imaging module 7 in combination with the broadband light source illumination module 6 to collect the reflection spectrum of the small animal in the soil sample; the information processing unit 63 controls the hyperspectral imaging module 7 in combination with the ultraviolet light excitation module 20 to detect the fluorescence spectrum of the small animal in the soil sample.

[0046] The reflectance spectrum and fluorescence spectrum constitute multimodal hyperspectral imaging data. The soil animal 3D convolutional instance segmentation deep network model is used to identify the types and number of small animals on the surface of the first layer of soil samples, and the number set of small animals on the surface of the current soil sample is obtained. 1 (T 1 1,T 1 2,T 1 3, …,T 1 m ); By manually separating the small animals inside the soil samples, selecting and manually identifying, the total number of small animal species in the first layer of soil samples in the soil sample stratification detection box 10 is obtained. 1 (P 1 1,P 1 2,P 1 3, …,P 1 m ), through machine learning P 1 (P 1 1,P 1 2,P 1 3, …,P 1 m) and T 1 (T 1 1,T 1 2,T 1 3, …,T 1 m ) is the fitting relationship.

[0047] The in-situ soil living small animal stratified instance segmentation device adopts stratified detection; after detecting the first layer of soil samples in the soil sample stratified detection box 10, the electric push arm module 8 pushes the soil layer in the soil sample stratified detection box into the soil sample storage box 11; the in-situ soil living small animal stratified instance segmentation device collects multimodal hyperspectral imaging data of the next layer qth layer of soil samples in the soil sample stratified detection box 10, identifies the types and instance individual numbers of small animals on the surface of the qth layer of soil samples through the soil animal 3D convolutional instance segmentation deep network model, and obtains the type number set T of small animals on the surface of the current soil sample q (T q 1,T q 2,T q 3, …,T q m ), and according to the fitting relationship established above, calculate the total number of small animal species set P in the qth layer q (P q 1,P q 2,P q 3, …,P q m ), where m is the total number of small animal species in the qth layer of soil samples.

[0048] The process is circulated successively until all the layered soils in the soil sample layered detection box 10 are detected. Finally, the types, distribution density, number of individual animals and the vertical distribution of the animals in the soil are calculated.

[0049] In-situ soil living small animal layer segmentation device Figure 2 shown.

[0050] The in-situ soil living small animal stratification instance segmentation device includes an instrument light-shielding sealed cover 1, a broadband light source illumination module 6, a hyperspectral imaging module 7, a first electric displacement platform 12, an electric push arm module 8, a gas anesthesia system 9, a soil sample stratification detection box 10, a soil sample storage box 11, an ultraviolet light excitation module 20, an information processing unit 63, and a flippable transparent window module 64; the broadband light source illumination module 6, the hyperspectral imaging module 7, the first electric displacement platform 12, the electric push arm module 8, the gas anesthesia system 9 and the information processing unit are connected via a data line.

[0051] The broadband light source illumination module 6 includes a first broadband light source 2, a second broadband light source 3, a first focusing lens 4, and a second focusing lens 5; the broadband light source illumination module 6 provides broadband illumination for the soil sample in the soil sample stratification detection box 10, so that the hyperspectral imaging module 7 collects the reflected hyperspectral data of the soil sample.

[0052] The hyperspectral imaging module 7 includes a first lens 13, a slit 14, a second lens 15, a spectrum conversion module 16, a third lens 17, a camera 18, and a second electric displacement platform 19; the first lens 13, the slit 14, the second lens 15, the spectrum conversion module 16, the third lens 17, and the camera 18 are connected to the second electric displacement platform 19; the first electric displacement platform 12 drives the hyperspectral imaging module to move.

[0053] The electric push arm module 8 includes a first electric push arm 49, a second electric push arm 50, a third electric push arm 51, a fourth electric push arm 52, a fifth electric push arm 53, a sixth electric push arm 54, and a seventh electric push arm 55; the first electric push arm 49, the second electric push arm 50, the third electric push arm 51, the fourth electric push arm 52, the fifth electric push arm 53, the sixth electric push arm 54 and the seventh electric push arm 55 are connected in sequence from top to bottom.

[0054] The ultraviolet light excitation module 20 includes a first ultraviolet light source 21, a fourth lens 22, a first rotating motor 23, a first bandpass filter group 24, a second ultraviolet light source 25, a fifth lens 26, a second rotating motor 27, a second bandpass filter group 28, a third ultraviolet light source 29, a sixth lens 30, a third rotating motor 31, a third bandpass filter group 32, a fourth ultraviolet light source 33, a seventh lens 34, a fourth rotating motor 35, a fourth bandpass filter group 36, a fifth ultraviolet light source 37, an eighth lens 38, a fifth rotating motor 39, a fifth bandpass filter group 40, a sixth ultraviolet light source 41, a ninth lens 42, a sixth rotating motor 43, a sixth bandpass filter group 44, a seventh ultraviolet light source 45, a tenth lens 46, a seventh rotating motor 47, and a seventh bandpass filter group 48; The first ultraviolet light source 21, the fourth lens 22, and the first rotating motor 23 are connected to the first bandpass filter group 24; the second ultraviolet light source 25, the fifth lens 26, and the second rotating motor 27 are connected to the second bandpass filter group 28; the third ultraviolet light source 29, the sixth lens 30, and the third rotating motor 31 are connected to the third bandpass filter group 32; the fourth ultraviolet light source 33, the seventh lens 34, and the fourth rotating motor 35 are connected to the fourth bandpass filter group 36; the fifth ultraviolet light source 37, the eighth lens 38, and the fifth rotating motor 39 are connected to the fifth bandpass filter group 40; the sixth ultraviolet light source 41, the ninth lens 42, and the sixth rotating motor 43 are connected to the sixth bandpass filter group 44; the seventh ultraviolet light source 45, the tenth lens 46, and the seventh rotating motor 47 are connected to the seventh bandpass filter group 48.

[0055] The flippable transparent window module 64 includes a first flippable transparent window 56, a second flippable transparent window 57, a third flippable transparent window 58, a fourth flippable transparent window 59, a fifth flippable transparent window 60, a sixth flippable transparent window 61, and a seventh flippable transparent window 62; the first flippable transparent window 56, the second flippable transparent window 57, the third flippable transparent window 58, the fourth flippable transparent window 59, the fifth flippable transparent window 60, the sixth flippable transparent window 61 and the seventh flippable transparent window 62 are connected from top to bottom.

[0056] The information processing unit 63 includes an industrial computer and a data connection line; the information processing unit 63 is respectively connected to the broadband light source illumination module 6, the hyperspectral imaging module 7, the electric push arm module 8, the gas anesthesia system 9, and the ultraviolet light excitation module 20. The information processing unit 63 is used to control the operation sequence of the broadband light source illumination module 6, the ultraviolet light excitation module 20, the hyperspectral imaging module 7, the electric push arm module 8, the gas anesthesia system 9 and the first electric translation stage 12, so that the hyperspectral imaging module 7 can collect multimodal hyperspectral data of all stratified soil samples in the soil sample stratification detection box 10 in an orderly manner. And the multimodal hyperspectral data of the soil sample is instance segmented for small animals to calculate the type of small animals in the soil sample, the number of instance individuals and the distribution density and other information.

[0057] The described hierarchical detection method and the soil animal 3D convolutional instance segmentation deep network model form multimodal hyperspectral imaging data based on the reflectance spectrum and fluorescence spectrum collected by the in-situ soil living small animal hierarchical instance segmentation device, calculate the types and number of individual instances of small animals on the soil surface, and use the following method to estimate the types and number of individual instances of small animals in the deep soil.

[0058] The volume of the soil sample obtained from the soil in situ is (x, y, z), and the number of small animals of various types in the soil is S (S1, S2, S 3, …,S n ), where n is the number of small animal species in the soil.

[0059] In-situ soil living small animal stratification example segmentation device divides the soil sample into k layers in the longitudinal position; let the current soil sample stratification sequence be q, the volume of each layer of soil sample be (x, y, z / k), and the number of small animals of various types in the qth layer of soil sample be P q (P q 1,P q 2,P q 3, …,P q m), where m is the total number of small animal species in the qth layer of soil samples.

[0060] The calibration method is as follows: according to the reflectance spectrum and fluorescence spectrum of the surface of the first layer of soil samples in the soil sample stratification detection box 10 collected by the in-situ soil living small animal stratification instance segmentation device, the multimodal hyperspectral imaging data is formed, and the types and instance individual numbers of small animals on the surface of the first layer of soil samples are identified through the soil animal 3D convolution instance segmentation deep network model, and the type number set T of small animals on the surface of the current soil sample is obtained. 1 (T 1 1,T 1 2,T 1 3, …,T 1 m ); By manually separating the small animals inside the soil samples, selecting and manually identifying, the total number of small animal species in the first layer of soil samples in the soil sample stratification detection box 10 is obtained. 1 (P 1 1,P 1 2,P 1 3, …,P 1 m ); Through machine learning P 1 (P 1 1,P 1 2,P 1 3, …,P 1 m ) and T 1 (T 1 1,T 1 2,T 1 3, …,T 1 m ) is as follows:

[0061]

[0062] According to the above fitting relationship, the dataset T of small animals on the surface of the qth layer of soil samples is obtained by combining the in-situ soil living small animal layer instance segmentation device with the soil animal 3D convolutional instance segmentation deep network model. q (T q 1,T q 2,T q 3, …,T q m ), the total small animal species dataset P of the qth layer soil sample can be calculated q (P q 1,P q 2,Pq 3, …,P q m ).

[0063] Then, in the soil sample layer detection box 10, the distribution density of soil small animals of type i in the qth layer of soil sample is:

[0064]

[0065] Then, in the soil sample stratification detection box 10, the distribution density of soil small animals in the qth layer of soil sample is:

[0066]

[0067] The above steps are cycled sequentially until all the small animal species data sets of the stratified soil samples in the soil sample stratification detection box 10 are detected.

[0068] The number of individuals of various types of soil small animals in the soil sample stratification detection box 10 is:

[0069]

[0070] The total number of soil microfauna in the soil sample stratification detection box 10 is:

[0071]

[0072] In the soil sample layered detection box 10, the distribution density of various types of soil small animals is:

[0073]

[0074] The total distribution density of soil microfauna is:

[0075]

[0076] The soil animal 3D convolutional instance segmentation deep network model can extract the spatial and spectral features of the multimodal hyperspectral imaging data collected by the in-situ soil live small animal hierarchical instance segmentation device based on the 3D convolutional neural network, so as to segment the instances of small animals in the soil. The species and individual information of the instance segmentation can be used to analyze the growth cycle, male and female individual information of the soil small animal individual, so as to establish a better soil small animal library. Even if the small animal is inside the soil, the soil small animal individuals actually collected are incomplete due to the occlusion of the soil. Through the soil animal 3D convolutional instance segmentation deep network model defined in the present invention, the incomplete soil small animals can be segmented, which can not only segment and identify the species and instance individuals of the small animals, but also analyze whether the incomplete small animal parts are covered live small animals or dead bodies with broken limbs.

[0077] In the described stratified detection, when the hyperspectral imaging module 7 in the in-situ soil live small animal stratified instance segmentation device detects the instance segmented species of the first layer of soil small animals, the first electric push arm 49 in the electric push arm module 8 will push the first layer of soil through the first flip-able transparent window into the soil sample storage box 11; the first electric displacement platform 12 in the hyperspectral imaging module 7 drives the hyperspectral imaging module 7 to move downward so that the surface image of the second layer of soil is clear; after the hyperspectral imaging module 7 detects the instance segmented species of the second layer of soil small animals, the second electric push arm 50 in the electric push arm module 8 pushes the second layer of soil through the second flip-able transparent window into the soil sample storage box 11; and the cycle is repeated in sequence until all stratified soil samples in the soil sample stratified detection box 10 are detected.

[0078] The multimodal hyperspectral imaging detection, the multimodal hyperspectral imaging detection, the broadband light source illumination module 6 uses a wide spectral band visible-near infrared band 400-1800nm ​​to detect soil small animals, after detecting the reflectance spectrum of the soil sample. The information processing center controls to turn off the power of the broadband light source illumination module 6 and turn on the power of the ultraviolet light excitation module 20; when detecting the first layer of soil samples in the soil sample stratification detection box 10, the ultraviolet light emitted by the first ultraviolet light source 21 is collimated by the fourth lens 22 and passes through the first bandpass filter group 24, and then irradiates the surface of the soil small animals from the side. The soil small animals are excited by the ultraviolet light to emit fluorescence, and the fluorescence spectrum data is collected by the hyperspectral imaging module 7; the first rotating motor 23 drives the first bandpass filter group 24 to rotate, so as to increase the switching of different bandpass filters and realize the emission of different fluorescence bands; when detecting the next layer of soil samples in the soil sample stratification detection box 10, the broadband light source illumination process is repeated and the second ultraviolet light source 25 is switched to allow the ultraviolet light to irradiate the next layer of soil samples; the cycle is repeated until the multimodal hyperspectral imaging detection of all stratified soil samples in the soil sample stratification detection box 10 is completed.

[0079] The reflection or fluorescence image of the surface soil sample in the soil sample stratification detection box 10 of the hyperspectral imaging module 7 is imaged on the slit surface after passing through the first lens 13, and the light passing through the center of the slit is collimated into parallel light of different angles after passing through the second lens 15; the parallel light of different angles passes through the spectrum conversion module and then through the third lens 17 to focus on the camera 18 to form a spectral image; the spectrum conversion module is composed of a prism-grating-prism module, or a tunable filter, which is used to separate the complex light into monochromatic light of different bands; the second electric displacement platform 19 drives the hyperspectral imaging module 7 to perform one-dimensional scanning, thereby realizing the reflection-fluorescence multimodal hyperspectral imaging detection of the surface soil sample in the soil sample stratification detection box.

[0080] Application Examples

[0081] Figure 3 This is an example segmentation effect diagram of soil small animals in the in-situ soil living small animal stratification instance segmentation device. Soil small animals in the in-situ soil sample, including woodlice 70, woodlice 71, beetle 72, whip scorpion 73, ground centipede 74, stone centipede 75, millipede 76, cricket 77 are all identified and classified.

[0082] Through the in-situ soil living small animal stratification instance segmentation device of the present invention, multimodal hyperspectral data collection is performed on the in-situ soil small animals. From the single-band reflection image, it can be seen that due to the complex scene covered by the soil, the small animals in the soil are mixed in the soil, and only a small part is exposed on the soil surface. It is extremely difficult to perform pixel area segmentation of the small animals by only exposing a small part of the insect body on the soil surface. The soil animal 3D convolution instance segmentation deep network model proposed in the present invention can perform accurate pixel area segmentation of the small animals in the soil for the collected multimodal hyperspectral data, directly identify the small animal species, density and longitudinal spatial distribution of soil small animals to which each pixel belongs, and provide more reliable data support for soil ecological research and agricultural management, and provide a more advanced tool for soil ecological research and agricultural practice to promote soil health management and sustainable agricultural development.

[0083] The embodiments described above can be further combined or replaced, and the embodiments are only descriptions of preferred embodiments of the present invention, and do not limit the concept and scope of the present invention. Without departing from the design concept of the present invention, various changes and improvements made by ordinary technicians in this field to the technical solution of the present invention belong to the protection scope of the present invention. The protection scope of the present invention is given by the attached claims and any equivalents thereof.

Claims

1. A method for in-situ soil living small animal layered detection survey, characterized by: A naturally collected soil sample is placed in an in-situ soil live small animal stratification instance segmentation device, and a gas anesthesia system controls the anesthetic gas to uniformly pass into the soil sample stratification detection box (10). After the small animals in the soil sample are anesthetized, the information processing unit (63) in the in-situ soil live small animal stratification instance segmentation device controls the hyperspectral imaging module (7) in combination with the broadband light source illumination module (6) to collect the reflection spectrum of the small animals in the soil sample; the information processing unit (63) controls the hyperspectral imaging module (7) in combination with the ultraviolet light excitation module (20) to detect the fluorescence spectrum of the small animals in the soil sample; the reflection spectrum and the fluorescence spectrum constitute multimodal hyperspectral imaging data, and the soil animal 3D convolution instance segmentation deep network model performs pixel instance segmentation on the data, and simultaneously segments the pixel regions of the soil small animals and the soil, identifies the pixel label category of the soil small animals; The in-situ soil living small animal stratified instance segmentation device adopts stratified detection, and the soil animal 3D convolutional instance segmentation deep network model independently identifies the types and number of individual instances of small animals in each layer of soil, and finally calculates the types, number of individual instances, distribution density of small animals in the in-situ overall soil sample, as well as the longitudinal distribution of small animals in the soil.

2. The layered detection and investigation method according to claim 1 is characterized in that: The in-situ soil living small animal stratification instance segmentation device comprises an instrument light-shielding sealed cover (1), a broadband light source illumination module (6), a hyperspectral imaging module (7), a first electric displacement platform (12), an electric push arm module (8), a gas anesthesia system (9), a soil sample stratification detection box (10), a soil sample storage box (11), an ultraviolet light excitation module (20), an information processing unit (63), and a flippable transparent window module (64); the broadband light source illumination module (6), the hyperspectral imaging module (7), the first electric displacement platform (12), the electric push arm module (8), and the gas anesthesia system (9) are respectively connected to the information processing unit.

3. The layered detection and investigation method according to claim 1 is characterized in that: The soil animal 3D convolutional instance segmentation deep network model calculates the types and number of individual instances of small animals on the soil surface based on the reflectance spectrum and fluorescence spectrum collected by the in-situ soil living small animal layered instance segmentation device, and estimates the types and number of individual instances of small animals in the deep soil layer using the following method: The volume of the soil sample taken from the soil in situ is (x, y, z), and the number of small animals of various types in the soil is S (S1, S2, S 3, …, S n ), where n is the number of small animal species in the soil; In-situ soil living small animal stratification example segmentation device divides the soil sample into k layers in the longitudinal position; let the current soil sample stratification sequence be q, the volume of each layer of soil sample be (x, y, z / k), and the number of small animals of various types in the qth layer of soil sample be P q (P q 1, P q 2, P q 3, …, P q m ), where m is the total number of small animal species in the qth layer of soil samples; The calibration method is as follows: based on the reflectance spectrum and fluorescence spectrum of the surface of the first layer of soil samples in the soil sample stratification detection box (10) collected by the in-situ soil living small animal stratification instance segmentation device, the multimodal hyperspectral imaging data is formed, and the types and instance individual numbers of small animals on the surface of the first layer of soil samples are identified through the soil animal 3D convolution instance segmentation deep network model, and the type number set T of small animals on the surface of the current soil sample is obtained. 1 (T 1 1, T 1 2, T 1 3, …, T 1 m ); By manually separating the small animals inside the soil sample, selecting and manually identifying, the total number of small animal species in the first layer of the soil sample in the soil sample stratification detection box (10) is obtained. 1 (P 1 1, P 1 2, P 1 3, …, P 1 m ); Through machine learning P 1 (P 1 1,P 1 2, P 1 3, …, P 1 m ) and T 1 (T 1 1, T 1 2, T 1 3, …, T 1 m ) is as follows: ； According to the above fitting relationship, the dataset T of small animals on the surface of the qth layer of soil samples is obtained by combining the in-situ soil living small animal layer instance segmentation device with the soil animal 3D convolutional instance segmentation deep network model. q (T q 1, T q 2,T q 3, …, T q m ), the total small animal species dataset P of the qth layer soil sample can be calculated q (P q 1, P q 2, P q 3, …, P q m ); Then, in the soil sample stratification detection box (10), the distribution density of soil small animals of type i in the qth layer of soil sample is: ； Then, in the soil sample stratification detection box (10), the distribution density of soil small animals in the qth layer of soil sample is: ； The above steps are repeated in sequence until all the small animal species data sets of the layered soil samples in the soil sample layered detection box (10) are detected; The number of individuals of various types of soil small animals in the soil sample stratification detection box (10) is: ； The total number of soil microfauna in the soil sample stratification detection box (10) is: ； The distribution density of various types of soil small animals in the soil sample layer detection box (10) is: ； The total distribution density of soil microfauna is: 。 4. The layered detection and investigation method according to claim 1 is characterized in that: The soil animal 3D convolutional instance segmentation deep network model is based on a 3D convolutional neural network to extract the spatial and spectral characteristics of the multimodal hyperspectral imaging data collected by the in-situ soil living small animal stratified instance segmentation device to perform instance segmentation of the soil small animals; the individual pixel information of the instance segmented species is used to analyze the growth cycle and male and female information of the individual soil small animals.

5. The layered detection and investigation method according to claim 1 is characterized in that: When the hyperspectral imaging module (7) in the in-situ soil living small animal stratification instance segmentation device detects the instance segmented species of the first layer of soil small animals, the first electric push arm (49) in the electric push arm module (8) pushes the first layer of soil through the first flippable transparent window into the soil sample storage box (11); the first electric displacement platform (12) in the hyperspectral imaging module (7) drives the hyperspectral imaging module (7) to move downward so that the second layer of soil surface is imaged clearly; when the hyperspectral imaging module (7) detects the instance segmented species of the second layer of soil small animals, the second electric push arm (50) in the electric push arm module (8) pushes the second layer of soil through the second flippable transparent window into the soil sample storage box (11); and the cycle is repeated until all the stratified soil samples in the soil sample stratification detection box (10) are detected.

6. The layered detection and investigation method according to claim 1 is characterized in that: In the multimodal hyperspectral imaging detection, the broadband light source illumination module (6) uses a wide spectrum band visible-near infrared band of 400-1800 nm to detect soil small animals. After detecting the reflection spectrum of the soil sample, the information processing center controls to turn off the power of the broadband light source illumination module (6) and turn on the power of the ultraviolet light excitation module (20). When detecting the first layer of soil samples in the soil sample stratification detection box (10), the ultraviolet light emitted by the first ultraviolet light source (21) is collimated by the fourth lens (22) and passes through the first bandpass filter group (24), and then irradiates the surface of the soil small animals from the side. The soil small animals are excited by the ultraviolet light to emit fluorescence and are then detected by the hyperspectral imaging module. (7) collecting fluorescence spectrum data; the first rotating motor (23) drives the first bandpass filter group (24) to rotate to increase the switching of different bandpass filters to achieve different fluorescence band emission; when detecting the next layer of soil samples in the soil sample stratification detection box (10), repeating the broadband light source illumination process and switching the second ultraviolet light source (25) to allow ultraviolet light to irradiate the next layer of soil samples; and repeating the cycle in sequence until the multimodal hyperspectral imaging detection of all stratified soil samples in the soil sample stratification detection box (10) is completed.

7. The layered detection and investigation method according to claim 1 is characterized in that: The hyperspectral imaging module (7) is characterized in that the reflection or fluorescence image of the surface soil sample in the soil sample stratification detection box (10) is imaged on the slit surface after passing through the first lens (13), and the light passing through the center of the slit is collimated into parallel light of different angles after passing through the second lens (15); the parallel light of different angles passes through the spectrum conversion module and then through the third lens (17) to be focused on the camera (18) to form a spectrum image; the spectrum conversion module is composed of a prism-grating-prism module, or a tunable filter, and is used to separate the complex light into monochromatic light of different wavelength bands; the second electric displacement platform (19) drives the hyperspectral imaging module (7) to perform one-dimensional scanning, thereby realizing the reflection-fluorescence multi-modal hyperspectral imaging detection of the surface soil sample in the soil sample stratification detection box.

8. An in-situ soil living small animal layer instance segmentation device, characterized by: Applied to the layered detection and investigation method according to claim 1; The broadband light source illumination module (6) comprises a first broadband light source (2), a second broadband light source (3), a first condensing lens (4), and a second condensing lens (5); the first broadband light source (2) is connected to the second condensing lens (5); the second broadband light source (3) is connected to the first condensing lens; The hyperspectral imaging module (7) comprises a first lens (13), a slit (14), a second lens (15), a spectrum conversion module (16), a third lens (17), a camera (18), and a second electric displacement platform (19); the first lens (13), the slit (14), the second lens (15), the spectrum conversion module (16), the third lens (17), and the camera (18) are connected to the second electric displacement platform (19); and the first electric displacement platform (12) drives the hyperspectral imaging module to move; The electric push arm module (8) comprises a first electric push arm (49), a second electric push arm (50), a third electric push arm (51), a fourth electric push arm (52), a fifth electric push arm (53), a sixth electric push arm (54), and a seventh electric push arm (55); the first electric push arm (49), the second electric push arm (50), the third electric push arm (51), the fourth electric push arm (52), the fifth electric push arm (53), the sixth electric push arm (54), and the seventh electric push arm (55) are connected in sequence from top to bottom; The ultraviolet light excitation module (20) comprises a first ultraviolet light source (21), a fourth lens (22), a first rotating motor (23), a first bandpass filter group (24), a second ultraviolet light source (25), a fifth lens (26), a second rotating motor (27), a second bandpass filter group (28), a third ultraviolet light source (29), a sixth lens (30), a third rotating motor (31), a third bandpass filter group (32), a fourth ultraviolet light source (33), a seventh lens (34), a fourth rotating motor (35), a fourth bandpass filter group (36), a fifth ultraviolet light source (37), an eighth lens (38), a fifth rotating motor (39), a fifth bandpass filter group (40), a sixth ultraviolet light source (41), a ninth lens (42), a sixth rotating motor (43), a sixth bandpass filter group (44), a seventh ultraviolet light source (45), a tenth lens (46), a seventh rotating motor (47), and a seventh bandpass filter group (48). The first ultraviolet light source (21), the fourth lens (22), the first rotating motor (23) are connected to the first bandpass filter group (24); the second ultraviolet light source (25), the fifth lens (26), the second rotating motor (27) are connected to the second bandpass filter group (28); the third ultraviolet light source (29), the sixth lens (30), the third rotating motor (31) are connected to the third bandpass filter group (32); the fourth ultraviolet light source (33), the seventh lens (34), the fourth The rotating motor (35) is connected to the fourth bandpass filter group (36); the fifth ultraviolet light source (37), the eighth lens (38), and the fifth rotating motor (39) are connected to the fifth bandpass filter group (40); the sixth ultraviolet light source (41), the ninth lens (42), and the sixth rotating motor (43) are connected to the sixth bandpass filter group (44); and the seventh ultraviolet light source (45), the tenth lens (46), and the seventh rotating motor (47) are connected to the seventh bandpass filter group (48); The flippable transparent window module (64) comprises a first flippable transparent window (56), a second flippable transparent window (57), a third flippable transparent window (58), a fourth flippable transparent window (59), a fifth flippable transparent window (60), a sixth flippable transparent window (61), and a seventh flippable transparent window (62); the first flippable transparent window (56), the second flippable transparent window (57), the third flippable transparent window (58), the fourth flippable transparent window (59), the fifth flippable transparent window (60), the sixth flippable transparent window (61), and the seventh flippable transparent window (62) are connected from top to bottom; The information processing unit (63) comprises an industrial computer and a data connection line; the information processing unit is respectively connected to the broadband light source illumination module (6), the hyperspectral imaging module (7), the electric push arm module (8), the gas anesthesia system (9), the ultraviolet light excitation module (20) and the first electric displacement stage (12).

Images