CN115062770A - Navigation method based on generalized bionic polarized light navigation model and solution - Google Patents
Navigation method based on generalized bionic polarized light navigation model and solution Download PDFInfo
- Publication number
- CN115062770A CN115062770A CN202210934824.0A CN202210934824A CN115062770A CN 115062770 A CN115062770 A CN 115062770A CN 202210934824 A CN202210934824 A CN 202210934824A CN 115062770 A CN115062770 A CN 115062770A
- Authority
- CN
- China
- Prior art keywords
- orientation
- polarization
- polarized light
- generalized
- bionic
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application relates to a navigation method based on a generalized bionic polarized light navigation model and solution. The method comprises the following steps: establishing a generalized bionic polarized light navigation model by introducing a polarized orientation vector orthogonal residual error; and then, searching an orientation applicable area by using spectral atmospheric polarization information and adopting information such as area polarization information intensity, polarization mode distribution consistency and the like, learning a polarization orientation vector orthogonal residual error through a convolutional neural network to perform adaptive compensation to realize coarse orientation, finally performing fusion optimization according to the uniqueness of orientation under different wave bands, and feeding back, adjusting and searching the applicable area and a training network to obtain accurate navigation orientation precision. The method has the advantages of simple principle, suitability for different weathers and the like, and has wide application prospect for improving the robustness and all-weather adaptability of the bionic polarized light navigation under the complex weather.
Description
Technical Field
The application relates to the field of bionic navigation, in particular to a navigation method based on a generalized bionic polarized light navigation model and solving.
Background
Many living beings in nature perform navigation activities by sensitive atmospheric polarization modes, for example, desert ants can return to nests in an approximately straight line by utilizing polarization light orientation after foraging for hundreds of meters in deserts lacking olfactory sensation and enough visual characteristic information; the honey can also be navigated by using the sun as a compass, so that the honey can reach the flower source area, and some migratory birds and fishes can also be navigated by using atmospheric polarized light. As a novel navigation technology, polarized light orientation is developed by using an atmospheric polarization mode formed naturally by sensing biological visual organs for reference, and the method has the advantages of strong autonomy, bounded error, no accumulation along time, no interference, no deception and the like, and has great potential in solving the problem of all-weather unmanned aerial vehicle high-precision intelligent navigation under the condition that satellites cannot be used.
At present, a great deal of research results are obtained in the research of the polarized light orientation technology, for example, in sunny days, cloudy days and other days (rayleigh days) where rayleigh scattering is the main factor, the distribution of the atmospheric polarization mode is relatively stable, and autonomous navigation of some mobile robots, unmanned platforms and the like under the satellite-free condition can be realized, but in cloudy days, cloudy days and other complex days where atmospheric turbulence and cloud layers change, due to the existence of particles with different sizes such as haze, water drops and solid particles, rayleigh scattering, mie scattering and other multiple scattering occur, the distribution of the atmospheric polarization mode is unstable, and the polarized light orientation accuracy is reduced or even fails. For the polarized light orientation technology, in the aspects of all-weather adaptability and robustness, the polarized light orientation technology has a larger gap compared with the natural life, and especially under the complex weather conditions of atmospheric turbulence, cloud layer change and the like, the polarized light orientation technology still faces a lot of difficulties and challenges for truly applying to the autonomous navigation of all-weather unmanned aerial vehicles under the condition that satellites are unavailable. Therefore, it is necessary to construct a new bionic polarized light navigation model and solve the model, so as to improve the robustness and accuracy of the bionic polarized light navigation orientation in complex weather.
Disclosure of Invention
Therefore, it is necessary to provide a navigation method based on a generalized bionic polarized light navigation model and solution, which can improve the robustness and accuracy of the bionic polarized light navigation orientation in complex weather, in order to solve the above technical problems.
A navigation method based on a generalized biomimetic polarized light navigation model and solution, the method comprising:
establishing a generalized bionic polarized light navigation model; the generalized bionic polarized light navigation model comprises a polarized orientation vector orthogonal residual error;
acquiring multiband atmospheric polarization mode information, and inputting the multiband atmospheric polarization mode information into a solving model of the generalized bionic polarized light navigation model; the solving model comprises a searching module, an orientation module and a fusion module; the searching module is used for determining the directional applicable area of the atmospheric polarization mode in each waveband according to the multiband atmospheric polarization mode information and the information such as the regional polarization information intensity, the polarization mode distribution consistency and the like; the orientation module is used for learning corresponding polarization orientation vector orthogonal residual errors through a convolutional neural network respectively in an orientation applicable area of an atmospheric polarization mode in each wave band to perform self-adaptive compensation on the polarization vectors so as to obtain a polarization coarse orientation result under each wave band; the fusion module is used for constructing an optimization objective function based on the uniqueness of orientation according to the polarization coarse orientation result under different wave bands, and performing feedback optimization on the orientation applicable region and the convolutional neural network;
and solving the generalized bionic polarized light navigation model through the solving model, and further obtaining an accurate navigation orientation result through the generalized bionic polarized light navigation model.
In one embodiment, the method further comprises the following steps: the orthogonal residual error of the polarization orientation vector is a component which is not vertical to the sun vector in the polarization vector.
In one embodiment, the method further comprises the following steps: and the constraint information of the regional polarization information intensity is that the regional polarization information intensity is set to be greater than a preset threshold value.
In one embodiment, the method further comprises the following steps: the constraint information of the polarization mode distribution consistency is that the gradient value of the constraint polarization degree is close to 0.
In one embodiment, the method further comprises the following steps: establishing a generalized bionic polarized light navigation model; the generalized bionic polarized light navigation model comprises the following steps:
wherein the content of the first and second substances,
in order to measure the polarization vector of a point,
is a vector in the direction of the sun,
in order to observe the direction vector,
orthogonal residuals for polarization orientation vectors.
In one embodiment, the method further comprises the following steps: the fusion module is used for constructing an optimization objective function based on the uniqueness of orientation according to the polarization coarse orientation result under different wave bands, and performing feedback optimization on the orientation applicable region and the convolutional neural network; the optimization objective function is:
wherein the content of the first and second substances,
，
is an index of the band(s),
，
the total number of the wave bands is,
and
orientation results obtained for two different bands of polarization information.
The navigation method based on the generalized bionic polarized light navigation model and the solution establishes the generalized bionic polarized light navigation model by introducing the orthogonal residual error of the polarization orientation vector; and then searching an orientation applicable area according to information such as the area polarization information intensity, the polarization mode distribution consistency and the like by using the spectrum atmospheric polarization information, learning the orthogonal residual error of the polarization orientation vector through a convolutional neural network to perform self-adaptive compensation to realize coarse orientation, finally performing fusion optimization according to the uniqueness of orientation under different wave bands, and feeding back and adjusting the search applicable area and the training network to obtain accurate navigation orientation precision. Compared with the prior art, the invention has the following advantages:
1) the defect that the adaptability of the original bionic polarized light orientation model is poor under the condition of complex weather is overcome;
2) the orientation applicable region can be adaptively adjusted and the orthogonal residual error of the polarization orientation vector can be compensated through neural network learning and multispectral polarization orientation fusion, and therefore the robustness and the accuracy of the existing bionic polarization light navigation orientation result are improved.
Drawings
FIG. 1 is a flow diagram of a navigation method based on a generalized biomimetic polarized light navigation model and solution in one embodiment;
FIG. 2 is a flow chart of a navigation method based on a generalized bionic polarized light navigation model and solution in another embodiment;
FIG. 3 is a flow chart illustrating an orientation solution based on multispectral polarization in another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, there is provided a navigation method based on a generalized bionic polarized light navigation model and solution, including the following steps:
and 102, establishing a generalized bionic polarized light navigation model.
The generalized bionic polarized light navigation model provided by the invention comprises a polarized orientation vector orthogonal residual error.
Specifically, the generalized bionic polarized light navigation model is established as follows:
in the formula (I), the compound is shown in the specification,
in order to measure the polarization vector of a point,
is a vector in the direction of the sun,
to observe the directionThe vector of the vector is then calculated,
orthogonal residuals for polarization orientation vectors.
Under ideal Rayleigh scattering, the atmospheric polarization mode meets a certain narrow orthogonal constraint relation, namely that a polarized light vector (vibration E vector) of an observation point is vertical to a solar vector, while the invention aims at the situation that under actual non-Rayleigh scattering, because of the influence of weather, Rayleigh scattering, meter scattering and multiple scattering exist, and then the polarization vector can be divided into a part vertical to the solar vector and a part not vertical to the solar vector, namely a polarization orientation vector orthogonal residual error.
And 104, acquiring multiband atmospheric polarization mode information, and inputting the multiband atmospheric polarization mode information into a solving model of the generalized bionic polarized light navigation model.
The invention provides a method for solving a model by adopting multispectral polarized SOF (Searching) -Orientation (Orientation) -Fusion (Fusion)) to obtain a navigation Orientation result.
Correspondingly, the solution model comprises a searching module, an orientation module and a fusion module.
The searching module is used for determining the directional applicable area of the atmospheric polarization mode in each waveband according to the multiband atmospheric polarization mode information and the information such as the intensity of the regional polarization information and the distribution consistency of the polarization mode
(kA certain band).
Wherein the regional polarization information intensity should be larger than a certain threshold value, and the polarization mode distribution uniformity is that the gradient value of the polarization degree is close to 0.
In complex weather, due to the fact that particles with different scales exist, atmospheric polarization modes generated by different wave bands are different, each wave band can obtain different atmospheric polarization modes, corresponding directional application areas are different, corresponding atmospheric polarization vector orthogonal residuals are different, and the generalized polarized light navigation model provided by the invention is met.
The orientation module is used for parallel processing in an orientation applicable area of an atmospheric polarization mode in each wave band, and learning corresponding polarization orientation vector orthogonal residual errors through a convolutional neural network to perform self-adaptive compensation on polarization vectors to obtain a polarization coarse orientation result under each wave band.
And extracting orthogonal residual errors of the polarization orientation vectors through convolutional neural network learning, and adjusting the network learning process through rear-end fusion optimization feedback to realize adaptive estimation and compensation of the orientation errors.
The fusion module is used for performing difference operation on the polarization coarse orientation results corresponding to two different wave bands by adopting an algorithm of mutual difference fusion according to the polarization coarse orientation results under the different wave bands, constructing an optimized objective function based on the uniqueness of orientation, and performing feedback optimization on the orientation applicable region and the convolutional neural network. The optimization objective function is:
wherein the content of the first and second substances,
，
is an index of the band(s),
，
the total number of the wave bands is,
and
and obtaining orientation results for the polarization information of two different wave bands.
And 106, solving the generalized bionic polarized light navigation model through the solving model, and further obtaining an accurate navigation orientation result through the generalized bionic polarized light navigation model.
In the navigation method based on the generalized bionic polarized light navigation model and the solution, the generalized bionic polarized light navigation model is established by introducing the orthogonal residual error of the polarization orientation vector; and then, searching an orientation applicable area by using spectrum atmospheric polarization information and adopting information such as area polarization information intensity, polarization mode distribution consistency and the like, learning a polarization orientation vector orthogonal residual error through a convolutional neural network to perform adaptive compensation to realize coarse orientation, finally performing fusion optimization according to the uniqueness of orientation under different wave bands, and performing feedback adjustment to search the applicable area and train the network so as to obtain accurate navigation orientation precision. The method has the advantages of simple principle, suitability for different weathers and the like, and has wide application prospect for improving the robustness and all-weather adaptability of the bionic polarized light navigation under the complex weather.
In another embodiment, as shown in fig. 2, a navigation method based on a generalized bionic polarized light navigation model and solution is provided, which includes the following steps:
s1, establishing a generalized bionic polarized light navigation model;
s2, based on the polarization orientation suitable region search (search) according to the information of region polarization information intensity, polarization mode distribution consistency, etc.;
s3, carrying out polarization vector orthogonal residual error adaptive compensation based on the convolutional neural network so as to realize coarse Orientation (Orientation);
s4, multi-band polarization coarse orientation result optimization Fusion (Fusion);
and S5, feeding back and adjusting the search area and optimizing the training network to solve the model to obtain an accurate navigation orientation result.
FIG. 3 is a schematic diagram of an orientation solution process based on multispectral polarization. The input information is a multi-band atmospheric polarization mode, and each band comprises an atmospheric polarization degree distribution image and an atmospheric polarization angle distribution image. Determining orientation applicable regions P of polarization modes of s1 wave band, s2 wave band and s3 wave band respectively according to information of multi-band atmospheric polarization mode 1 、P 2 And P 3 And corresponding regionDomain P 1 Polarization information, region P 2 Polarization information and region P 3 Polarization information. Will be the region P 1 Polarization information, region P 2 Polarization information and region P 3 The polarization information is respectively input into a convolutional neural network for learning to obtain orthogonal residual errors of the polarization vectors, the polarization vectors are subjected to self-adaptive orientation error compensation, and course angles are respectively obtained through orientation model calculation
、
And
. To pair
、
And
two by two are subtracted and the absolute value is obtained
、
And
. By optimizing an objective function
And (5) feedback adjusting a search area and optimizing a training network, and updating the search area if the target function exceeds the directional expectation.
It should be understood that although the various steps in the flow charts of fig. 1-2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (6)
1. A navigation method based on a generalized bionic polarized light navigation model and solution, which is characterized by comprising the following steps:
establishing a generalized bionic polarized light navigation model; the generalized bionic polarized light navigation model comprises a polarized orientation vector orthogonal residual error;
acquiring multiband atmospheric polarization mode information, and inputting the multiband atmospheric polarization mode information into a solving model of the generalized bionic polarized light navigation model; the solving model comprises a searching module, an orientation module and a fusion module; the searching module is used for determining the directional applicable area of the atmospheric polarization mode in each waveband according to the multiband atmospheric polarization mode information and the constraint information of the area polarization information intensity and the polarization mode distribution consistency; the orientation module is used for learning corresponding polarization orientation vector orthogonal residual errors through a convolutional neural network respectively in an orientation applicable area of an atmospheric polarization mode in each wave band to perform self-adaptive compensation on the polarization vectors so as to obtain a polarization coarse orientation result under each wave band; the fusion module is used for constructing an optimization objective function based on the uniqueness of orientation according to the polarization coarse orientation result under different wave bands, and performing feedback optimization on the orientation applicable region and the convolutional neural network;
and solving the generalized bionic polarized light navigation model through the solving model, and further obtaining an accurate navigation orientation result through the generalized bionic polarized light navigation model.
2. The method of claim 1, wherein the polarization orientation vector quadrature residual is a component of the polarization vector that is not perpendicular to the sun vector.
3. The method according to claim 1, wherein the constraint information of the regional polarization information intensity is to set the regional polarization information intensity to be greater than a preset threshold.
4. The method of claim 1, wherein the constraint information of the uniformity of the polarization mode distribution is that the gradient value of the constrained polarization degree is close to 0.
5. The method of claim 1, wherein a generalized bionic polarized light navigation model is established; the generalized bionic polarized light navigation model comprises a polarized orientation vector orthogonal residual error, and comprises the following steps:
establishing a generalized bionic polarized light navigation model; the generalized bionic polarized light navigation model comprises the following steps:
wherein the content of the first and second substances,
in order to measure the polarization vector of a point,
is a vector in the direction of the sun,
in order to observe the direction vector,
orthogonal residuals for polarization orientation vectors.
6. The method of claim 1, wherein the fusion module is configured to construct an optimization objective function based on uniqueness of orientation according to polarization coarse orientation results in different wavelength bands, and perform feedback optimization on the orientation applicable region and the convolutional neural network, and includes:
the fusion module is used for constructing an optimization objective function based on the uniqueness of orientation according to the polarization coarse orientation result under different wave bands, and performing feedback optimization on the orientation applicable region and the convolutional neural network; the optimization objective function is:
wherein the content of the first and second substances,
，
is an index of the band(s),
，
the total number of the wave bands is,
and with
And obtaining orientation results for the polarization information of two different wave bands.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210934824.0A CN115062770B (en) | 2022-08-04 | 2022-08-04 | Navigation method based on generalized bionic polarized light navigation model and solution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210934824.0A CN115062770B (en) | 2022-08-04 | 2022-08-04 | Navigation method based on generalized bionic polarized light navigation model and solution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115062770A true CN115062770A (en) | 2022-09-16 |
| CN115062770B CN115062770B (en) | 2022-11-08 |
Family
ID=83207539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210934824.0A Active CN115062770B (en) | 2022-08-04 | 2022-08-04 | Navigation method based on generalized bionic polarized light navigation model and solution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115062770B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117928565A (en) * | 2024-03-19 | 2024-04-26 | 中北大学 | Polarization navigation orientation method under complex shielding environment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120175496A1 (en) * | 2009-09-22 | 2012-07-12 | Vorotec Ltd. | Apparatus and method for navigation |
| CN104880191A (en) * | 2015-06-02 | 2015-09-02 | 北京航空航天大学 | Polarization aided navigation method based on solar vectors |
| CN106643704A (en) * | 2017-01-16 | 2017-05-10 | 中国人民解放军国防科学技术大学 | Solar azimuth acquisition method based on atmospheric polarization modes |
| CN108225335A (en) * | 2018-01-23 | 2018-06-29 | 中国人民解放军国防科技大学 | Course angle solving method for multi-view polarized vision |
| CN111307140A (en) * | 2020-05-11 | 2020-06-19 | 中国人民解放军国防科技大学 | Atmospheric polarized light orientation method used under cloudy weather condition |
| CN111539413A (en) * | 2020-04-23 | 2020-08-14 | 南京理工大学 | Bionic polarized light course resolving system and method for soft edge support vector machine |
| CN111652276A (en) * | 2020-04-30 | 2020-09-11 | 南京理工大学 | All-weather portable multifunctional bionic positioning, attitude determining and viewing system and method |
| CN112053402A (en) * | 2020-07-30 | 2020-12-08 | 大连理工大学 | Method for obtaining course angle by using polarized geographic information database |
-
2022
- 2022-08-04 CN CN202210934824.0A patent/CN115062770B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120175496A1 (en) * | 2009-09-22 | 2012-07-12 | Vorotec Ltd. | Apparatus and method for navigation |
| CN104880191A (en) * | 2015-06-02 | 2015-09-02 | 北京航空航天大学 | Polarization aided navigation method based on solar vectors |
| CN106643704A (en) * | 2017-01-16 | 2017-05-10 | 中国人民解放军国防科学技术大学 | Solar azimuth acquisition method based on atmospheric polarization modes |
| CN108225335A (en) * | 2018-01-23 | 2018-06-29 | 中国人民解放军国防科技大学 | Course angle solving method for multi-view polarized vision |
| CN111539413A (en) * | 2020-04-23 | 2020-08-14 | 南京理工大学 | Bionic polarized light course resolving system and method for soft edge support vector machine |
| CN111652276A (en) * | 2020-04-30 | 2020-09-11 | 南京理工大学 | All-weather portable multifunctional bionic positioning, attitude determining and viewing system and method |
| CN111307140A (en) * | 2020-05-11 | 2020-06-19 | 中国人民解放军国防科技大学 | Atmospheric polarized light orientation method used under cloudy weather condition |
| CN112053402A (en) * | 2020-07-30 | 2020-12-08 | 大连理工大学 | Method for obtaining course angle by using polarized geographic information database |
Non-Patent Citations (2)
| Title |
|---|
| BIANBIAN LIU等: "Solar Position Acquisition Method for Polarized Light Navigation Based on ∞ Characteristic Model of Polarized Skylight Pattern", 《IEEE ACCESS》 * |
| 范颖等: "多云天气条件下的大气偏振光定向方法", 《航空学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117928565A (en) * | 2024-03-19 | 2024-04-26 | 中北大学 | Polarization navigation orientation method under complex shielding environment |
| CN117928565B (en) * | 2024-03-19 | 2024-05-31 | 中北大学 | Polarization navigation orientation method under complex shielding environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115062770B (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rajmohan et al. | Revamping land coverage analysis using aerial satellite image mapping | |
| CN102540166B (en) | Cross radiation calibration method based on optimization algorithm of hyper-spectral sensor | |
| Zhao et al. | Object-oriented vegetation classification method based on UAV and satellite image fusion | |
| CN114740180A (en) | Soil organic carbon estimation method and device based on multi-source remote sensing data | |
| CN113836779A (en) | CNN-based farmland surface soil moisture inversion method for Sentinel multi-source data | |
| CN115471437A (en) | Image fusion method based on convolutional neural network and remote sensing image fusion method | |
| CN115062770B (en) | Navigation method based on generalized bionic polarized light navigation model and solution | |
| CN114297938B (en) | Inversion method of optical shallow water depth based on neural network | |
| CN115308386B (en) | Soil salinity inversion method and system based on CYGNSS satellite data | |
| Veettil et al. | Remote sensing of plastic‐covered greenhouses and plastic‐mulched farmlands: Current trends and future perspectives | |
| Huertas-Tato et al. | Using a multi-view convolutional neural network to monitor solar irradiance | |
| Yin et al. | Synergistic estimation of soil salinity based on Sentinel-1 image texture and Sentinel-2 salinity spectral indices | |
| CN108229426B (en) | Remote sensing image change vector change detection method based on difference descriptor | |
| Zou et al. | Combining spectral and texture feature of UAV image with plant height to improve LAI estimation of winter wheat at jointing stage | |
| CN117035066A (en) | Ground surface temperature downscaling method coupling geographic weighting and random forest | |
| Wang et al. | Multispectral satellite-derived bathymetry based on sparse prior measured data | |
| CN115294562B (en) | Intelligent sensing method for operation environment of plant protection robot | |
| Qin et al. | An illumination estimation and compensation method for radiometric correction of UAV multispectral images | |
| CN113836731B (en) | Construction method and device of land surface stable target atmosphere top reflectivity model | |
| CN115855272A (en) | Method for generating near-real-time hourly all-weather surface temperature | |
| CN112364289B (en) | Method for extracting water body information through data fusion | |
| Pipitone et al. | Detection of a reservoir water level using shape similarity metrics | |
| He et al. | [Retracted] An Early Warning Intelligent Algorithm System for Forest Resource Management and Monitoring | |
| Di Paola et al. | Weather Forecast Downscaling for Applications in Smart Agriculture and Precision Farming using Artificial Neural Networks | |
| Wald | A conceptual approach to the fusion of earth observation data |
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 |