CN119535399A - A method, device and medium for inversion of insect body axis ratio based on RCS characteristics - Google Patents
A method, device and medium for inversion of insect body axis ratio based on RCS characteristics Download PDFInfo
- Publication number
- CN119535399A CN119535399A CN202510108840.8A CN202510108840A CN119535399A CN 119535399 A CN119535399 A CN 119535399A CN 202510108840 A CN202510108840 A CN 202510108840A CN 119535399 A CN119535399 A CN 119535399A
- Authority
- CN
- China
- Prior art keywords
- insect
- axis ratio
- body axis
- rcs
- polarization
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/415—Identification of targets based on measurements of movement associated with the target
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Electromagnetism (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Catching Or Destruction (AREA)
Abstract
本申请提供了一种基于RCS特征的昆虫体轴比反演方法、设备及介质，属于昆虫雷达技术领域。该方法基于对预设昆虫共线极化方向图的分析结果，确定各方向图特征参数与昆虫体轴比的关联关系，以基于关联关系确定多个昆虫体轴比估计器；其中，关联关系至少包括与昆虫体长相关、与昆虫体宽相关；昆虫体轴比估计器用于表征昆虫极化特性与昆虫体轴比的量化关系；根据各昆虫体轴比估计器及预设XGBoost回归算法，构建预先训练的体轴比反演模型；其中，体轴比反演模型建立有各昆虫体轴比估计器与昆虫体轴比之间的映射关系；将体轴比反演模型部署至用户终端，以使用户终端基于输入的昆虫共线极化方向图及体轴比反演模型进行昆虫体轴比反演。
The present application provides an insect body axis ratio inversion method, device and medium based on RCS features, which belongs to the field of insect radar technology. The method is based on the analysis results of the preset insect colinear polarization pattern, determines the correlation between each pattern characteristic parameter and the insect body axis ratio, and determines multiple insect body axis ratio estimators based on the correlation relationship; wherein the correlation relationship at least includes correlation with the insect body length and correlation with the insect body width; the insect body axis ratio estimator is used to characterize the quantitative relationship between the insect polarization characteristics and the insect body axis ratio; according to each insect body axis ratio estimator and the preset XGBoost regression algorithm, a pre-trained body axis ratio inversion model is constructed; wherein the body axis ratio inversion model establishes a mapping relationship between each insect body axis ratio estimator and the insect body axis ratio; the body axis ratio inversion model is deployed to the user terminal, so that the user terminal performs insect body axis ratio inversion based on the input insect colinear polarization pattern and the body axis ratio inversion model.
Description
Technical Field
The application relates to the technical field of insect radars, in particular to an insect body axial ratio inversion method, equipment and medium based on RCS characteristics.
Background
The insect radar is a tool specially used for monitoring and researching the flying insects, and can realize all-weather and all-day monitoring on the premise of not interfering the flying behaviors of the insects, so that the insect radar is widely applied to insect research. The biological and behavioral characteristics of the insects, such as body length, body weight, wing vibration frequency, horizontal flying speed and direction, etc., can be estimated by insect echoes measured by the insect radar. Based on the parameters, the species identification and the track analysis can be carried out on the migratory insect, which has important significance for constructing an effective migratory insect air monitoring and interception prevention and control system.
The body-axis ratio (i.e., aspect ratio) of insects is an important morphological feature in species identification. The traditional method is to find Radar Cross-section (RCS) estimators related to specific morphological characteristics (such as weight and body length) of insects, and to construct mapping relations between the RCS estimators and the morphological characteristics, so that inversion of the characteristics is realized. However, no RCS estimator related to the body axis ratio has been found yet, and the conventional measuring method of the body axis ratio of the insect mainly relies on manual observation and physical measurement, which is not only inefficient, but also extremely difficult to measure for tiny insects or insects in complex environments, and accuracy is difficult to guarantee. The accurate and efficient inversion of the insect body axis ratio remains an unsolved problem.
Therefore, in order to further improve the accuracy of the identification of the species of the migratory insect, a technical scheme capable of inverting the accurate body-axis ratio of the migratory insect is needed.
Disclosure of Invention
The embodiment of the application provides an insect body axial ratio inversion method, equipment and medium based on RCS characteristics, which are used for solving the technical problem that the efficient and accurate inversion of the insect body axial ratio is difficult to realize at present.
In one aspect, the embodiment of the application provides an insect body axial ratio inversion method based on RCS characteristics, which comprises the following steps:
Determining association relations between characteristic parameters of each pattern and an insect body axis ratio based on analysis results of preset insect collinear polarization patterns, so as to determine a plurality of insect body axis ratio estimators based on the association relations, wherein the association relations at least comprise determining a quantitative relation between insect body length and insect body width in the insect body axis ratio based on a co-polarized radar scattering cross section RCS, wherein the quantitative relation is used for representing insect polarization characteristics and the insect body axis ratio;
Constructing a pre-trained body-axis ratio inversion model according to the insect body-axis ratio estimators and a preset XGBoost regression algorithm, wherein the body-axis ratio inversion model is provided with a mapping relation between the insect body-axis ratio estimators and the insect body-axis ratio;
And deploying the body-axis ratio inversion model to a user terminal so that the user terminal performs insect body-axis ratio inversion based on the input insect collinear polarization direction diagram and the body-axis ratio inversion model.
In one implementation of the present application, before determining the association relationship between the characteristic parameters of each pattern and the axial ratio of the insect body based on the analysis result of the preset insect collinear polarization patterns, the method further includes:
acquiring co-polarized radar cross sections RCS corresponding to pre-observed insects in different polarization directions, wherein the co-polarized RCS is obtained by observing the pre-observed insects through a polarized insect radar in a linear polarization mode;
determining the preset insect collinear polarization direction diagram according to the change of the co-polarization RCS in the polarization direction, wherein the preset insect collinear polarization direction diagram is expressed as:
Wherein, A co-linear polarization direction diagram of insects is shown,Is a pattern characteristic parameter irrelevant to the polarization direction; And Pattern feature parameters relating to the shape of the insect collinear polarization pattern; indicating the polarization direction, and the value interval is ;Indicating the direction of the insect body axis.
In one implementation mode of the application, based on an analysis result of a preset insect collinear polarization pattern, determining an association relation between characteristic parameters of each pattern and an insect body axis ratio specifically comprises:
Determining the collinear polarization pattern of the preset insects Items and itemsWhen the terms respectively obtain the maximum values, the included angle between the polarization direction and the insect body axis direction is formed;
According to the included angle side direction corresponding to each included angle and the preset insect length direction, respectively determining the body length direction and the body width direction corresponding to the polarization direction;
According to the described Items and saidThe item respectively corresponds to the length direction and the width direction of the body to establish theAnd saidAnd respectively associated relation with the insect body axial ratio.
In one implementation of the present application, determining a plurality of insect body axis ratio estimators based on the association relationship specifically includes:
according to the association relation, when the included angle is 0 or When it willAs a cuboid-length-direction RCS;
According to the association relation, when the included angle is Or (b)When it willAs a body width direction RCS;
according to the association relation, the ratio of the cuboid-length-direction RCS to the cuboid-width-direction RCS is calculated As an RCS body-axis ratio index;
The said The saidThe body length direction RCS, the body width direction RCS and the RCS body axis ratio index are respectively used as the insect body axis ratio estimator.
In one implementation manner of the application, a pre-trained body-axis ratio inversion model is constructed according to each insect body-axis ratio estimator and a preset XGBoost regression algorithm, and the method specifically comprises the following steps:
Constructing a plurality of multidimensional feature vector samples according to the insect body axis ratio estimators and the insect collinear polarization direction diagram samples, wherein the multidimensional feature vector samples comprise multidimensional feature vectors and insect body axis ratio labels, which are formed by the insect body axis ratio estimators corresponding to the insect collinear polarization direction diagram samples;
And inputting each multi-dimensional feature vector sample into the preset XGBoost regression algorithm to train the preset XGBoost regression algorithm until the training ending condition is met, and obtaining the body-axis ratio inversion model.
In one implementation manner of the present application, training the preset XGBoost regression algorithm until the training end condition is satisfied, to obtain the body-axis ratio inversion model, which specifically includes:
Iterative training is carried out on the preset XGBoost regression algorithm through each multi-dimensional feature vector sample in a preset training set;
Inputting each multi-dimensional feature vector sample in a preset test set into the preset XGBoost regression algorithm after iterative training so as to calculate corresponding average relative errors according to output results;
And under the condition that the average relative error is smaller than a preset threshold value, determining the preset XGBoost regression algorithm after iterative training as the body-axis ratio inversion model.
In one implementation of the present application, after the body-axis ratio inversion model is deployed to the user terminal, the method further includes:
acquiring the input insect body axial ratio estimators corresponding to the insect collinear polarization patterns, and constructing corresponding multidimensional feature vectors;
And sending the multidimensional feature vector to the user terminal so as to enable the user terminal to perform insect body axis ratio inversion.
In one implementation manner of the application, the user terminal performs insect body axis ratio inversion based on the input insect collinear polarization direction diagram and the body axis ratio inversion model, and specifically comprises the following steps:
the user terminal determines a plurality of corresponding insect body axial ratio estimators according to the input insect collinear polarization direction diagram, and constructs the multidimensional feature vector;
And the user terminal inputs the multidimensional feature vector into the pre-deployed body-axis ratio inversion model so as to invert the insect body-axis ratio.
On the other hand, the embodiment of the application also provides an insect body axial ratio inversion device based on RCS characteristics, which comprises:
and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform an insect body axis ratio inversion method based on RCS characteristics as described above.
In yet another aspect, embodiments of the present application further provide a non-volatile computer storage medium storing computer-executable instructions capable of performing an insect body axis ratio inversion method based on RCS features as described above.
Compared with the prior art, the application has the following remarkable effects:
(1) Through the scheme, the method and the device for determining the axial ratio of the insects deeply analyze the preset collinear polarization directional diagrams of the insects, determine the association relation between characteristic parameters of each directional diagram and the axial ratio of the insects, and further determine a plurality of axial ratio estimators of the insects. The estimators can accurately represent the quantitative relation between the insect polarization characteristic and the insect body axial ratio, and provide an accurate data basis for a subsequent construct axial ratio inversion model, so that the accuracy of the insect body axial ratio inversion is greatly improved. Compared with the traditional method, the body axis ratio inversion model constructed based on the preset XGBoost regression algorithm can rapidly process input insect polarization data, greatly improves the efficiency of inversion of the insect body axis ratio, and enables analysis of the body axis ratio of a large number of insect samples to be possible in a short time.
(2) And deploying the body-axis ratio inversion model to a user terminal, wherein the user can perform insect body-axis ratio inversion based on the model only by inputting an insect collinear polarization direction diagram at the terminal. The design gets rid of the dependence of the traditional measuring method on complex equipment and professional environments, so that insect researchers can conveniently analyze the axial ratio of the insect body in various scenes such as the field, the laboratory and the like, and the application convenience of the technology is remarkably enhanced. The application effectively solves the technical problem that the high-efficiency and accurate inversion of the axial ratio of the insect body is difficult to realize, and provides a more accurate, efficient and convenient research means for the research of the insect.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a schematic flow chart of an insect body axial ratio inversion method based on RCS characteristics in an embodiment of the application;
FIG. 2 is a schematic illustration of simulated collinear polarization directions in an inversion method of the axial ratio of an insect body based on RCS features in an embodiment of the application;
FIG. 3 is a schematic diagram showing a comparison between an estimated body axis ratio and a real body axis ratio in an inversion method of insect body axis ratios based on RCS characteristics according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of an insect body axial ratio inversion device based on RCS features in an embodiment of the application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the field of insect research, accurate acquisition of the insect body axis ratio is of great importance in the aspects of deep understanding of ecological habit, behavior pattern, evolution characteristics and the like of insects. The traditional insect body axial ratio measuring method mainly depends on manual observation and physical measurement, and the method is low in efficiency, and has extremely high measuring difficulty and difficult accuracy for tiny insects or insects in complex environments.
Based on the above, the embodiment of the application provides an insect body axial ratio inversion method, equipment and medium based on RCS characteristics, which are used for solving the technical problem that the efficient and accurate inversion of the insect body axial ratio is difficult to realize at present.
Various embodiments of the present application are described in detail below with reference to the attached drawing figures.
The embodiment of the application provides an insect body axial ratio inversion method based on RCS characteristics, which can comprise the following steps S101-S103 as shown in figure 1:
S101, the server determines association relations between characteristic parameters of each pattern and the insect body axis ratio based on analysis results of preset insect collinear polarization patterns, so as to determine a plurality of insect body axis ratio estimators based on the association relations.
The association relation at least comprises the steps of determining the relationship with the length of the insect body in the insect body axial ratio and the relationship with the width of the insect body in the insect body axial ratio based on the co-polarized radar cross section RCS. The insect body axis ratio estimator is used for characterizing the quantitative relation between the polarization characteristic of the insect and the insect body axis ratio.
The server is an execution subject of the insect body axial ratio inversion method based on the RCS feature, and the execution subject is not limited to the server, but is not particularly limited thereto.
In the embodiment of the application, before determining the association relation between the characteristic parameters of each pattern and the insect body axis ratio based on the analysis result of the preset insect collinear polarization pattern, the method further comprises the following steps:
And acquiring co-polarized radar cross sections RCS corresponding to the pre-observed insects in different polarization directions. Wherein the co-polarized RCS is obtained by observing the pre-observed insects in a linear polarization mode by a polarized insect radar. And determining a preset insect collinear polarization direction diagram according to the change of the co-polarization RCS in the polarization direction. The preset insect collinear polarization direction diagram is expressed as follows:
Wherein, A co-linear polarization direction diagram of insects is shown,Is a pattern characteristic parameter independent of polarization direction.AndThe characteristic parameter of the pattern related to the shape of the collinear polarization pattern of the insects is a dimensionless parameter.Indicating the polarization direction, and the value interval is。Indicating the direction of the insect body axis.
That is, the application analyzes the relationship between the polarization characteristic and the insect body axis ratio in the collinear polarization direction diagram of the insects, and calculates the insect body axis ratio estimator. Specifically, when the polarized insect radar is adopted to observe in linear polarization, co-polarized RCS of different polarization directions of insects can be obtained. The present application, under the assumption of insect symmetry, represents the co-polarized RCS as described above。
In one embodiment of the present application, the determining, based on the analysis result of the preset co-linear polarization patterns of the insects, the association relationship between the characteristic parameters of each pattern and the axial ratio of the insects specifically includes:
Determining a co-linear polarization pattern of a predetermined insect Items and itemsAnd when the terms respectively obtain maximum values, the included angle between the polarization direction and the axial direction of the insect body is formed. And respectively determining the body length direction and the body width direction respectively corresponding to the polarization directions according to the included angle side direction corresponding to each included angle and the preset insect body length direction. According toItems and itemsThe corresponding relation between the items and the body length direction and the body width direction respectively is establishedAndRespectively with insect bodies association of axial ratios.
In other words, the present application is capable of calculating the polarization pattern of collinear,Items and itemsWhen the terms respectively obtain the maximum values, the included angle between the polarization direction and the insect body axis direction is formed.The period of the item isIts maximum value appears in,At this time, the polarization direction is aligned with the length direction of the preset insect body, i.eWhich is related to the elongation of the co-linear polarization pattern in the body length direction.Is of the period ofIts maximum value appears in,,,Due to the above-mentioned known,The direction of the length of the body is indicated,,Then the direction perpendicular to the body axis is indicated, which is the body width direction, i.eThe correlation with the co-linear polarization pattern along both the insect body length direction and the body width direction is more commonly interpreted as the cross correlation with the co-linear polarization pattern.
Fig. 2 is a normalized collinear polarization pattern of four simulated insects, the four insects all have a body length of 15 millimeters (mm), the preset insect body length direction is 0-180 °, and the insect body axis ratios are 2,3, 4, and 5, respectively, from (a) to (d) of fig. 2. In the case of the same body length, for insects with smaller body axes,The more the collinear polarization pattern is presented as a cross, the more the dominant effect, for insects with larger body axes,The more "long" the collinear polarization pattern is along the preset insect body length direction, based on which the application is as aboveAndCan reflect the axial ratio of the insect body.
In the embodiment of the application, a plurality of insect body axial ratio estimators are determined based on association relations, and the method specifically comprises the following steps:
According to the association relation, when the included angle is0 or When it willAs a cuboid-length-direction RCS. According to the association relation, when the included angle isOr (b)When it willAs a body width direction RCS. According to the association relation, the ratio of the length direction RCS to the width direction RCSAs an index of the body axis ratio of the RCS. Will be、The body length direction RCS, the body width direction RCS and the RCS body axis ratio index are respectively used as insect body axis ratio estimators.
As can be seen from fig. 2, the larger the body-axis ratio is, the larger the difference between the RCS in the body-length direction and the RCS in the body-width direction is, and at this time, the application obtains the RCS in the body-length direction and the RCS in the body-width direction, and the ratio (RCS body-axis ratio index) of the two, respectively, according to the above-mentioned angle setting manner. To this end, the server obtains 5 collinear polarization pattern features related to the insect body axis ratio, namely:、、、、 they were used as insect body axis ratio estimators.
S102, the server constructs a pre-trained body-axis ratio inversion model according to the insect body-axis ratio estimators and a preset XGBoost regression algorithm.
The body-axis ratio inversion model establishes a mapping relation between each insect body-axis ratio estimator and the insect body-axis ratio.
In the embodiment of the application, a pre-trained body-axis ratio inversion model is constructed according to an insect body-axis ratio estimator and a regression algorithm of a preset limit gradient lifting algorithm (eXtreme Gradient Boosting, XGBoost), and the method specifically comprises the following steps:
And constructing a plurality of multidimensional feature vector samples according to the insect body axial ratio estimator and the insect collinear polarization pattern samples. The multi-dimensional characteristic vector sample comprises a multi-dimensional characteristic vector and an insect body axis ratio label, wherein the multi-dimensional characteristic vector is composed of insect body axis ratio estimators corresponding to all insect collinear polarization direction picture samples. And inputting each multidimensional feature vector sample into a preset XGBoost regression algorithm to train the preset XGBoost regression algorithm until the training ending condition is met, and obtaining the body-axis ratio inversion model.
That is, the application combines advanced XGBoost regression algorithm to realize the inversion of the insect body axis ratio based on the multiple insect body axis ratio estimators, and the application carries out the iterative training of XGBoost regression algorithm through a plurality of preset multidimensional feature vector samples. The multi-dimensional characteristic vector samples are obtained by extracting insect body axis ratio estimators from a plurality of insect collinear polarization pattern samples to form multi-dimensional characteristic vectors and marking insect body axis ratio labels for the multi-dimensional characteristic vectors by experts or other equipment. Multidimensional feature vectors such as]。
Training a preset XGBoost regression algorithm until a training ending condition is met, and obtaining a body-axis ratio inversion model, wherein the method specifically comprises the following steps of:
Iterative training is performed on a preset XGBoost regression algorithm through each multidimensional feature vector sample in a preset training set. And inputting each multidimensional feature vector sample in the preset test set into a preset XGBoost regression algorithm after iterative training so as to calculate corresponding average relative errors according to the output result. And under the condition that the average relative error is smaller than a preset threshold value, determining a preset XGBoost regression algorithm after iterative training as a body-axis ratio inversion model.
When the application carries out iterative training on the preset XGBoost regression algorithm, a plurality of multidimensional feature vector samples can contain 75% of training sets and 25% of testing sets. For example, with insects measured at the Ku band 16.2GHz, 75% of 159 insects measured in the darkroom were randomly selected as insects for generating the training set for training the body axis ratio inversion model, and the remaining 25% were used as test sets for evaluating the performance of the body axis ratio inversion model obtained by training.
The application adopts average relative Error (MEAN RELATIVE Error, MRE) as an evaluation index of the estimated Error of the body-axis ratio:
Wherein, The number of insects involved in the inversion is indicated,Representing the first to participate in inversionInversion of individual insects results in an insect body axis ratio,Representing the first to participate in inversionTrue insect body axis ratio of individual insects; The larger the characterization estimation error is. At the position of And when the body-axis ratio inversion model is smaller than a preset threshold value, obtaining the body-axis ratio inversion model. The preset threshold is specifically set by the user during actual use, which is not specifically limited by the present application.
In the embodiment of the application, the evaluation result of the inversion model based on the constructed body axial ratio is shown in table 1 (model evaluation result table), and the difference value between the MRE of the training set and the MRE of the test set can be used for judging whether the model is over-fitted or not. Table 1 shows that the MREs of the model training set and the test set are 9.31% and 10.57%, respectively, indicating that the model has good generalization. Fig. 3 is a schematic diagram of the comparison of the inversion insect body axis ratio (i.e., estimated body axis ratio) and the true body axis ratio of 159 insects, wherein the points represent insects and the lines represent the estimated value and true value contours. 159 insect data training and verification of the body-axis ratio inversion model based on the Ku wave band (16.2 GHz) of darkroom measurement are only exemplary, and model training samples can be specifically selected in the actual use process, for example, the model training samples are acquired through the Internet, and the application is not particularly limited to the model training samples.
Table 1 model evaluation results table
S103, the server deploys the body-axis ratio inversion model to the user terminal, so that the user terminal performs insect body-axis ratio inversion based on the input insect collinear polarization direction diagram and the body-axis ratio inversion model.
After the body-axis ratio inversion model is obtained, the body-axis ratio inversion model can be deployed at a user terminal, or can be directly deployed at a server, or an execution subject is the user terminal, and is directly deployed locally. The user terminal may be understood as a device such as a mobile phone or a computer of a user, which is not particularly limited in the present application.
In an embodiment of the present application, after the deploying the body axis ratio inversion model to the user terminal, the method further includes:
And acquiring an axial ratio estimator of each insect body corresponding to the input insect collinear polarization direction diagram, and constructing a corresponding multidimensional feature vector. And sending the multidimensional feature vector to the user terminal so that the user terminal performs inversion of the insect body axis ratio.
If the execution subject is not a user terminal, the execution subject is a server, and the server can accept the input insect collinear plan direction diagram from the user terminal or from other devices, and obtain the insect body axis ratio estimators according to the steps S101-S102, thereby obtaining the multidimensional feature vector.
In another embodiment of the present application, the user terminal performs inversion of the insect body axis ratio based on the inputted insect collinear polarization direction diagram and the body axis ratio inversion model, and specifically includes:
and the user terminal determines a plurality of corresponding insect body axis ratio estimators according to the input insect collinear polarization direction diagram, and constructs a multidimensional feature vector. The user terminal inputs the multidimensional feature vector into a pre-deployed body-axis ratio inversion model to perform insect body-axis ratio inversion.
That is, the steps S101 to S102 may be performed at a user terminal, where the user terminal performs multi-dimensional feature vector construction, so as to complete inversion of the axial ratio of the insect body.
Through the scheme, the method and the device for determining the axial ratio of the insects deeply analyze the preset collinear polarization directional diagrams of the insects, determine the association relation between characteristic parameters of each directional diagram and the axial ratio of the insects, and further determine a plurality of axial ratio estimators of the insects. The estimators can accurately represent the quantitative relation between the insect polarization characteristic and the insect body axial ratio, and provide an accurate data basis for a subsequent construct axial ratio inversion model, so that the accuracy of the insect body axial ratio inversion is greatly improved. Compared with the traditional method, the body axis ratio inversion model constructed based on the preset XGBoost regression algorithm can rapidly process input insect polarization data, greatly improves the efficiency of inversion of the insect body axis ratio, and enables analysis of the body axis ratio of a large number of insect samples to be possible in a short time.
And deploying the body-axis ratio inversion model to a user terminal, and enabling a user to perform insect body-axis ratio inversion based on the model only by inputting an insect collinear polarization direction diagram at the terminal. The design gets rid of the dependence of the traditional measuring method on complex equipment and professional environments, so that insect researchers can conveniently analyze the axial ratio of the insect body in various scenes such as the field, the laboratory and the like, and the application convenience of the technology is remarkably enhanced. The application effectively solves the technical problem that the high-efficiency and accurate inversion of the axial ratio of the insect body is difficult to realize, and provides a more accurate, efficient and convenient research means for the research of the insect.
Fig. 4 is a schematic structural diagram of an apparatus for inverting an axial ratio of an insect body based on RCS features according to an embodiment of the present application, where, as shown in fig. 4, the apparatus includes:
And a memory communicatively coupled to the at least one processor. Wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:
Based on the analysis result of the preset insect collinear polarization patterns, the association relation between the characteristic parameters of each pattern and the insect body axis ratio is determined, so that a plurality of insect body axis ratio estimators are determined based on the association relation. The association relation at least comprises the steps of determining the relationship with the length of the insect body in the insect body axial ratio and the relationship with the width of the insect body in the insect body axial ratio based on the co-polarized radar cross section RCS. The insect body axis ratio estimator is used for characterizing the quantitative relation between the polarization characteristic of the insect and the insect body axis ratio. And constructing a pre-trained body-axis ratio inversion model according to the body-axis ratio estimators of the insects and a preset XGBoost regression algorithm. The body-axis ratio inversion model establishes a mapping relation between each insect body-axis ratio estimator and the insect body-axis ratio. And deploying the body-axis ratio inversion model to the user terminal so that the user terminal performs insect body-axis ratio inversion based on the input insect collinear polarization direction diagram and the body-axis ratio inversion model.
The embodiment of the application also provides a nonvolatile computer storage medium, which stores computer executable instructions, wherein the computer executable instructions are configured to:
Based on the analysis result of the preset insect collinear polarization patterns, the association relation between the characteristic parameters of each pattern and the insect body axis ratio is determined, so that a plurality of insect body axis ratio estimators are determined based on the association relation. The association relation at least comprises the steps of determining the relationship with the length of the insect body in the insect body axial ratio and the relationship with the width of the insect body in the insect body axial ratio based on the co-polarized radar cross section RCS. The insect body axis ratio estimator is used for characterizing the quantitative relation between the polarization characteristic of the insect and the insect body axis ratio. And constructing a pre-trained body-axis ratio inversion model according to the body-axis ratio estimators of the insects and a preset XGBoost regression algorithm. The body-axis ratio inversion model establishes a mapping relation between each insect body-axis ratio estimator and the insect body-axis ratio. And deploying the body-axis ratio inversion model to the user terminal so that the user terminal performs insect body-axis ratio inversion based on the input insect collinear polarization direction diagram and the body-axis ratio inversion model.
The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the apparatus and medium embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
The device, the medium and the method provided by the embodiment of the application are in one-to-one correspondence, so that the device and the medium also have similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the device and the medium are not repeated here because the beneficial technical effects of the method are described in detail above.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510108840.8A CN119535399B (en) | 2025-01-23 | 2025-01-23 | Insect body axis ratio inversion method, device and medium based on RCS characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510108840.8A CN119535399B (en) | 2025-01-23 | 2025-01-23 | Insect body axis ratio inversion method, device and medium based on RCS characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119535399A true CN119535399A (en) | 2025-02-28 |
| CN119535399B CN119535399B (en) | 2025-09-30 |
Family
ID=94711523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510108840.8A Active CN119535399B (en) | 2025-01-23 | 2025-01-23 | Insect body axis ratio inversion method, device and medium based on RCS characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119535399B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6653971B1 (en) * | 1999-05-14 | 2003-11-25 | David L. Guice | Airborne biota monitoring and control system |
| CN105759252A (en) * | 2016-03-24 | 2016-07-13 | 北京理工大学 | Insect dimension measurement method based on multi-frequency scattering modeling |
| CN115061107A (en) * | 2021-12-24 | 2022-09-16 | 北京理工大学 | A method for obtaining the average RCS scattering model of migratory insect swarms based on insect radar |
| CN115659118A (en) * | 2022-09-14 | 2023-01-31 | 北京理工大学 | A Feature Selection-Based Inversion Method for Biological Parameters of Insects |
| CN116736253A (en) * | 2023-06-14 | 2023-09-12 | 北京理工大学 | A method for retrieving insect radar body parameters based on minimum polarization RCS |
| CN118566898A (en) * | 2024-05-20 | 2024-08-30 | 北京理工大学 | A method for inverting insect radar weight based on multi-frequency difference estimator |
| CN118566897A (en) * | 2024-05-20 | 2024-08-30 | 北京理工大学 | A method for inverting insect radar body length based on multi-frequency difference estimator |
-
2025
- 2025-01-23 CN CN202510108840.8A patent/CN119535399B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6653971B1 (en) * | 1999-05-14 | 2003-11-25 | David L. Guice | Airborne biota monitoring and control system |
| CN105759252A (en) * | 2016-03-24 | 2016-07-13 | 北京理工大学 | Insect dimension measurement method based on multi-frequency scattering modeling |
| CN115061107A (en) * | 2021-12-24 | 2022-09-16 | 北京理工大学 | A method for obtaining the average RCS scattering model of migratory insect swarms based on insect radar |
| CN115659118A (en) * | 2022-09-14 | 2023-01-31 | 北京理工大学 | A Feature Selection-Based Inversion Method for Biological Parameters of Insects |
| CN116736253A (en) * | 2023-06-14 | 2023-09-12 | 北京理工大学 | A method for retrieving insect radar body parameters based on minimum polarization RCS |
| CN118566898A (en) * | 2024-05-20 | 2024-08-30 | 北京理工大学 | A method for inverting insect radar weight based on multi-frequency difference estimator |
| CN118566897A (en) * | 2024-05-20 | 2024-08-30 | 北京理工大学 | A method for inverting insect radar body length based on multi-frequency difference estimator |
Non-Patent Citations (4)
| Title |
|---|
| JIANGTAO WANG ET AL.: "Radar-Based Identification of Insect Species With Ensemble Learning Algorithms Utilizing Multiple Electromagnetic Scattering Parameters", IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, vol. 62, 13 August 2024 (2024-08-13) * |
| 付晓伟: "昆虫雷达目标回波的种类辨识研究", 中国博士论文电子期刊, no. 01, 15 January 2019 (2019-01-15) * |
| 王江涛等: "基于最小极化RCS 的昆虫雷达目标体型参数反演", 信号处理, vol. 39, no. 9, 30 September 2023 (2023-09-30) * |
| 胡程;方琳琳;王锐;周超;李卫东;张帆;郎添娇;龙腾;: "昆虫雷达散射截面积特性分析", 电子与信息学报, no. 01, 31 January 2020 (2020-01-31) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119535399B (en) | 2025-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107144643B (en) | A kind of damnification recognition method of Lamb wave monitoring signals statistical parameter | |
| CN110261485B (en) | Method for measuring elastic modulus and Poisson's ratio of each part in material by ultrasonic wave | |
| CN104280455B (en) | Ultrasonic scattering coefficient optimal computation method for crack direction recognition | |
| CN106908786B (en) | A high-precision insect body axis orientation extraction method based on polarization scattering matrix estimation | |
| CN105606637B (en) | Utilize the method for moisture and fat content in low-field nuclear magnetic resonance technology for detection abalone | |
| CN107589412B (en) | An Insect Feature Parameter Inversion Method Based on Eigenvalues of Polarization Power Matrix | |
| CN108009378B (en) | Time-varying damage assessment method for guided wave HMM based on uniformly initialized GMM | |
| CN110007355A (en) | A convolutional autoencoder and method and device for detecting abnormality inside an object | |
| CN112927185B (en) | A true stress-true strain curve test calculation method based on digital image correlation method | |
| CN111168569B (en) | Grinding material removal amount prediction method, device, equipment and storage medium | |
| CN110763728A (en) | Fatigue damage assessment method based on metal surface infrared polarization thermal image characteristics | |
| CN106525753A (en) | Convenient and simple remote-sensing soil moisture monitoring method | |
| CN106908755A (en) | Wireless acoustic sensor network pushes the sound bearing method of estimation of contracting gas leakage | |
| CN104182768B (en) | The quality classification method of ISAR image | |
| CN117150386A (en) | Assessment method and device for measurement uncertainty of humidity sensor based on self-adaption | |
| CN119535399B (en) | Insect body axis ratio inversion method, device and medium based on RCS characteristics | |
| CN111964757B (en) | Transducer consistency evaluation method based on echo signal characteristic parameters | |
| CN110568074B (en) | Wind turbine blade crack positioning method based on non-contact multipoint vibration measurement and Hilbert conversion | |
| CN112818762A (en) | Large-size composite material and rapid nondestructive testing method for sandwich structure thereof | |
| CN103268491A (en) | Weld defect ultrasound phased array sector scanned image feature extraction method | |
| CN112285435A (en) | An Equivalent Simulation Method of High Power Magnetic Field Radiation Source | |
| CN114384152A (en) | Ultrasonic guided wave damage positioning method and system based on search point matching | |
| CN114547770A (en) | Fatigue crack evaluation method and terminal based on heteroscedastic guided wave-Gaussian process | |
| CN118711063A (en) | Plant growth parameter inversion method based on polarimetric SAR images and semi-supervised regression | |
| CN114047474B (en) | A method for estimating the target direction of uniform linear array based on generalized regression neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |