A positioning method and system based on dual-view polarization fusion

Abstract

The application provides a positioning method and system based on dual-view polarization fusion, relates to the technical field of navigation positioning, and extracts feature parameters in a sky polarization image by collecting the sky polarization image; collects an environmental polarization image in an environmental scene, and constructs a polarization feature vector based on the environmental polarization image; combines the feature parameters in the sky polarization image and the polarization feature vector to identify positioning information of a camouflage target; that is, by constructing a polarization information perception framework of dual-view coordination of the sky polarization image and the environmental polarization image, the sky polarization features and the ground polarization texture are fused to improve stable identification and high-precision positioning under weak features and complex interference conditions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of navigation positioning, in particular to a positioning method and system based on dual-view polarization fusion. BACKGROUND

[0002] Intelligent unmanned systems continue to evolve, and the demand for "passive sensing + positioning" is increasingly urgent: once resources are limited, communication is interrupted or GPS signal disappears, the platform must rely on its own sensors to continue to work. However, the traditional scheme centered on vision, lidar or inertial navigation often has poor stability and insufficient robustness in strong light interference, sudden changes in light or severe occlusion. In recent years, polarization sensing has shown potential in image enhancement, target detection and navigation positioning by capturing target material and light changes, but the current mainstream polarization navigation is still limited to a single path of "sky polarization image → solar azimuth", and ground information is almost ignored; when the solar elevation angle is too low, buildings are blocked or multi-path reflection occurs, the positioning accuracy will decrease significantly. Therefore, there is an urgent need for a method that can improve the positioning accuracy of target objects. SUMMARY

[0003] To solve the above technical problems, the present application is proposed. Embodiments of the present application provide a positioning method and system based on dual-view polarization fusion.

[0004] According to one aspect of the present application, a positioning method based on dual-view polarization fusion is provided, comprising: collecting a sky polarization image and extracting feature parameters in the sky polarization image; collecting an environmental polarization image in an environmental scene and constructing a polarization feature vector based on the environmental polarization image; combining the feature parameters in the sky polarization image and the polarization feature vector to identify the positioning information of a camouflage target.

[0005] In an embodiment, the extraction of the feature parameters in the sky polarization image includes: based on the sky polarization image, the position of the sun is solved; based on the position of the sun, the geographical position of the observation point is calculated.

[0006] In an embodiment, the solving of the position of the sun based on the sky polarization image includes: extracting the polarization angle of each pixel point in the sky polarization image; based on the polarization angles of all pixel points, the azimuth and elevation angle of the sun are calculated.

[0007] In an embodiment, the extraction of the polarization angle of each pixel point in the sky polarization image includes: the calculation formula of the polarization angle is as follows: ; wherein (x, y) is the pixel point coordinate, S1 and S2 are Stokes polarization parameters respectively.

[0008] In an embodiment, the calculating the azimuth and altitude of the sun based on the polarization angles of all the pixels comprises: constructing a least square equation set based on the observation direction vectors and the polarization angles of the plurality of pixels, and solving a sun direction unit vector; wherein the least square equation set is:

[0009] ;

[0010] wherein, is the sun direction unit vector, P i is an observation direction vector of the i-th pixel, S x P i represents a vector product of S and P i , is a parameter of the Rayleigh scattering model, and f(S) is a least square function, is a parameter, and N is the number of pixels;

[0011] the azimuth and altitude of the sun are calculated based on the sun direction unit vector; wherein the calculation formulae of the azimuth and altitude of the sun are as follows:

[0012] ;

[0013] wherein, a s is the azimuth of the sun, h s is the altitude of the sun.

[0014] In an embodiment, the calculating the geographical position of the observation point based on the sun position comprises: calculating the geographical latitude and geographical longitude of the observation point based on the sun position; wherein the calculation formulae of the geographical latitude and the geographical longitude are as follows:

[0015] ;

[0016] wherein, is the geographical latitude, L is the geographical longitude, δ k is the declination angle, H k is the hour angle, is the observation time, is the local sidereal time.

[0017] In an embodiment, the constructing a polarization feature vector based on the environmental polarization image comprises: extracting joint feature information of each pixel in the environmental polarization image; wherein the joint feature information comprises the polarization degree, the polarization angle, the spatial gradient of the polarization degree, and the spatial gradient of the polarization angle of each pixel; calculating a score of each pixel based on the joint feature information; and identifying the camouflage target based on the score of the pixel.

[0018] In an embodiment, the calculating the score of each pixel based on the joint feature information comprises: the calculating formula of the score is as follows:

[0019] ; wherein, F(x, y) is a score value, f p (x, y) is a vector of joint feature information, is an edge response function, is a target morphology prior score, and a, b, and g are weighting coefficients.

[0020] In an embodiment, the identifying the camouflage target based on the score of the pixel comprises: if the score of the pixel is greater than a preset value, it is determined that the pixel is a pixel point of the camouflage target.

[0021] According to another aspect of the present application, a positioning system based on dual-view polarization fusion is provided, comprising: a sky polarization image acquisition module, configured to acquire a sky polarization image and extract a feature parameter in the sky polarization image; an environment polarization image acquisition module, configured to acquire an environment polarization image in an environment scene and construct a polarization feature vector based on the environment polarization image; and a camouflage target positioning and identification module, configured to combine the feature parameter in the sky polarization image and the polarization feature vector to identify positioning information of a camouflage target.

[0022] The positioning method and system based on dual-view polarization fusion provided by the present application, by acquiring a sky polarization image and extracting a feature parameter in the sky polarization image, acquiring an environment polarization image in an environment scene and constructing a polarization feature vector based on the environment polarization image, and combining the feature parameter in the sky polarization image and the polarization feature vector to identify positioning information of a camouflage target, that is, by constructing a polarization information perception framework of dual-view coordination of the sky polarization image and the environment polarization image, fusing the sky polarization feature in the upper view and the polarization texture in the lower view, the stable identification and high-precision positioning under the condition of weak features and complex interference can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0023] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings. The drawings provided in the specification and the contents of the specification serve as a further description of the embodiments of the present application, and together with the specification, explain the present application and do not limit the present application. In the drawings, the same reference numerals generally refer to the same components or steps throughout the specification.

[0024] Figure 1 FIG. 1 is a flowchart of a positioning method based on dual-view polarization fusion provided by an exemplary embodiment of the present application.

[0025] Figure 2FIG. 1 is a structural schematic diagram of a positioning system based on dual-view polarization fusion according to an example embodiment of the present application.

[0026] Figure 3 FIG. 2 is a structural diagram of an electronic device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0027] Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part but not all of the embodiments of the present application. It should be understood that the present application is not limited to the described example embodiments.

[0028] Figure 1 FIG. 3 is a flowchart of a positioning method based on dual-view polarization fusion according to an example embodiment of the present application. As shown in the figure, the positioning method based on dual-view polarization fusion includes the following steps: Figure 1

[0029] Step 110: Collect a sky polarization image and extract feature parameters in the sky polarization image.

[0030] The present application collects a sky polarization image and extracts feature parameters such as polarization angle and polarization degree in the sky polarization image to obtain sky polarization features, and calculates the sun position based on the feature parameters.

[0031] Step 120: Collect an environmental polarization image in an environmental scene and construct a polarization feature vector based on the environmental polarization image.

[0032] The present application collects an environmental polarization image in an environmental scene and constructs a polarization feature vector based on the environmental polarization image to obtain ground polarization texture.

[0033] Step 130: Identify the positioning information of a camouflage target by combining the feature parameters in the sky polarization image and the polarization feature vector.

[0034] After the feature parameters in the sky polarization image and the polarization feature vector of the environmental polarization image are collected, the present application combines the feature parameters and the polarization feature vector to comprehensively identify the positioning information of a camouflage target, so as to combine the sun direction, the camera posture and the imaging geometric parameters, perform cross-modal information matching, feature fusion and spatial position calculation, improve the target positioning accuracy, and realize camouflage target positioning and platform autonomous navigation and other tasks.

[0035] ​This application provides a positioning method based on dual-view polarization fusion. It acquires sky polarization images and extracts feature parameters from them; acquires environmental polarization images of the surrounding scene and constructs polarization feature vectors based on these images; and combines the feature parameters and polarization feature vectors from the sky polarization images to identify the positioning information of camouflaged targets. In other words, by constructing a dual-view polarization information perception framework that coordinates sky and environmental polarization images, it fuses the upward-looking sky polarization features with the downward-looking ground surface polarization texture to improve stable identification and high-precision positioning under conditions of weak features and complex interference.

[0036] In one embodiment, step 110 can be implemented as follows: the position of the sun is calculated based on the sky polarization image; the geographical location of the observation point is calculated based on the position of the sun.

[0037] Specifically, this application obtains sky polarization images within the sky field of view, acquires polarization information through pixel-level Stokes parameter calculation, inverts the sun's direction based on the Rayleigh scattering model and least squares optimization, constructs a regional polarization angle continuous distribution model, and selects low-disturbance areas for attitude angle inversion and accuracy compensation to deduce the geographical location of the observation point.

[0038] In one embodiment, step 110 can be implemented by: extracting the polarization angle of each pixel in the sky polarization image; and calculating the azimuth and altitude angles of the sun based on the polarization angles of all pixels.

[0039] This application extracts the polarization angle and degree of polarization of each pixel in a sky polarization image, and calculates the azimuth and altitude angles of the sun based on the polarization angle of the pixel.

[0040] In one embodiment, step 110 can be implemented as follows: the formula for calculating the polarization angle is as follows: Where (x,y) are the pixel coordinates, and S1 and S2 are the Stokes polarization parameters, respectively.

[0041] Specifically, this application uses the above formula to calculate the polarization angle of a pixel, and this application can also use the following formula to calculate the degree of polarization of a pixel:

[0042] ;

[0043] in, S is the degree of polarization, and S0 is the Stokes polarization parameter.

[0044] In one embodiment, step 110 can be implemented as follows: A system of least squares equations is constructed based on the observation direction vectors and polarization angles of multiple pixels to solve for the unit vector of the solar direction; wherein the system of least squares equations is:

[0045] ;

[0046] wherein, is a unit vector of the sun direction, P i is an observation direction vector of the i th pixel point, S x P i represents a vector product of S and P i is a parameter of the Rayleigh scattering model, f(S) is a least square function, is a parameter, and N is the number of the pixel points; based on the unit vector of the sun direction, the azimuth angle and the elevation angle of the sun are calculated; wherein, the calculation formula of the azimuth angle and the elevation angle of the sun is as follows:

[0047] ;

[0048] wherein, a s is the azimuth angle of the sun, h s is the elevation angle of the sun.

[0049] The present application constructs a least square equation set based on the observation direction vector and the polarization angle of a plurality of pixel points, obtains the unit vector of the sun direction by solving the least square equation set, and calculates the azimuth angle and the elevation angle of the sun based on the unit vector of the sun direction.

[0050] In an embodiment, the specific implementation manner of the above step 110 can be: based on the sun position, the geographic latitude and the geographic longitude of the observation point are calculated; wherein, the calculation formula of the geographic latitude and the geographic longitude is as follows:

[0051] ;

[0052] wherein, is the geographic latitude, L is the geographic longitude, δ k is the declination angle, H k is the hour angle, is the observation time, is the local sidereal time.

[0053] The present application combines the observation time with the sun declination angle δ k , and calculates the geographic latitude and the geographic longitude of the observation point based on the above formula, specifically, a constraint equation set among the sun elevation angle h s , the geographic latitude λ, the declination angle δ k and the hour angle H k is constructed:

[0054] ;

[0055] ​Solving the above three formulas to calculate:

[0056] .

[0057] In an embodiment, the specific implementation of the above step 120 can be: extracting the joint feature information of each pixel in the environmental polarization image; wherein the joint feature information includes the polarization degree, the polarization angle, the spatial gradient of the polarization degree, and the spatial gradient of the polarization angle of each pixel; calculating the score of each pixel based on the joint feature information; wherein, based on the score of the pixel, the camouflage target is identified.

[0058] The present application uses GPU to accelerate the calculation of polarization angle, polarization degree and its gradient field by collecting the environmental polarization image in the environmental field of view, constructs the polarization response feature vector, and assigns scores to suspicious areas, and realizes the classification and significant enhancement of typical camouflage / non-camouflage materials through pre-training of the polarization material response library based on cosine similarity matching.

[0059] In an embodiment, the specific implementation of the above step 120 can be: the calculation formula of the score is as follows:

[0060] ; wherein, F(x, y) is the score value, f p (x, y) is the vector of joint feature information, is the edge response function, is the target morphology prior score, and alpha, beta and gamma are weighting coefficients.

[0061] Wherein, the vector of joint feature information is:

[0062] ;

[0063] Wherein, and are the spatial gradients of the polarization degree and the polarization angle, respectively.

[0064] In an embodiment, the specific implementation of the above step 120 can be: if the score of the pixel is greater than a preset value, the pixel is determined to be a pixel point of the camouflage target.

[0065] The present application determines the target area by judging whether the score of each pixel is greater than a preset value, and specifically, the determination formula of the target area is as follows:

[0066] ;

[0067] Wherein, τ s is a preset value.

[0068] In an embodiment, the specific implementation of step 130 can be: according to the sun direction inversed from the sky polarization map and the platform attitude matrix information, combined with the target pixel position observed in the environment image, the back projection from the image plane to the geographic space can be realized. Specifically, the calculation formula of the target geographic position is as follows:

[0069] ;

[0070] wherein, is the pixel coordinate of the target point in the image, K is the camera intrinsic matrix, is the direction vector of the camera coordinate system C, represents the geographic position of the carrier platform, λ h represents the height inverse solution coefficient, R B→G represents the attitude conversion matrix of the carrier coordinate system B to the navigation geographic coordinate system G, R C→B is the extrinsic matrix of the camera coordinate system C to the carrier coordinate system B, X target is the target geographic position.

[0071] Optionally, in order to ensure the stability of system detection and positioning, a target tracking model of multi-frame polarization information fusion is established, and each frame of target state is defined as a state vector containing spatial position, motion speed and polarization characteristics, and the method is as follows:

[0072] ;

[0073] ;

[0074] wherein, is the target pixel position, is the motion speed, ρ and α are the polarization degree and polarization angle of the current frame, A is the state transition matrix, z t is the observation vector, H is the observation matrix, and are the system noise and observation noise respectively.

[0075] Optionally, the application can also introduce a polarization degree dynamic compensation model to cope with environmental changes, wherein the polarization degree dynamic compensation model is:

[0076] ;

[0077] ;

[0078] wherein, is the compensated polarization degree, is the time-dependent compensation factor, I0 is the standard light intensity constant, is the average light intensity of the current frame sky region.

[0079] Figure 2 is a structural schematic diagram of a positioning system based on dual-view polarization fusion provided by an exemplary embodiment of the present application. As shown in the figure, the positioning system based on dual-view polarization fusion 20 comprises a sky polarization image acquisition module 21 configured to acquire a sky polarization image and extract a feature parameter in the sky polarization image; an environment polarization image acquisition module 22 configured to acquire an environment polarization image in an environment scene and construct a polarization feature vector based on the environment polarization image; and a camouflage target positioning and recognition module 23 configured to combine the feature parameter in the sky polarization image and the polarization feature vector to recognize positioning information of a camouflage target. Figure 2

[0080] The positioning system based on dual-view polarization fusion provided by the present application acquires a sky polarization image through the sky polarization image acquisition module 21 and extracts a feature parameter in the sky polarization image; acquires an environment polarization image in an environment scene through the environment polarization image acquisition module 22 and constructs a polarization feature vector based on the environment polarization image; and combines the feature parameter in the sky polarization image and the polarization feature vector through the camouflage target positioning and recognition module 23 to recognize positioning information of a camouflage target; that is, by constructing a polarization information perception framework of dual-view coordination of sky polarization images and environment polarization images, the sky polarization features and the ground polarization textures are fused to improve stable recognition and high-precision positioning under weak features and complex interference conditions.

[0081] In an embodiment, the sky polarization image acquisition module 21 described above can be further configured to calculate a sun position based on the sky polarization image; and calculate a geographical position of an observation point based on the sun position.

[0082] In an embodiment, the sky polarization image acquisition module 21 described above can be further configured to extract a polarization angle of each pixel point in the sky polarization image; and calculate an azimuth angle and an elevation angle of the sun based on the polarization angles of all the pixel points.

[0083] In an embodiment, the sky polarization image acquisition module 21 described above can be further configured to calculate the polarization angle according to the following formula: ; wherein (x, y) is a pixel point coordinate, S1 and S2 are Stokes polarization parameters respectively.

[0084] In an embodiment, the sky polarization image acquisition module 21 described above can be further configured to construct a least square equation set based on the observation direction vector and the polarization angle of a plurality of pixel points to solve a sun direction unit vector; wherein the least square equation set is as follows:

[0085] ;

[0086] ; wherein, is the sun direction unit vector, P​i is the observation direction vector of the i-th pixel point, SxP i represents the vector product of S and P i is a parameter of the Rayleigh scattering model, and f(S) is a least squares function, is a parameter, and N is the number of pixel points; based on the unit vector of the sun direction, the azimuth and elevation angles of the sun are calculated; wherein the calculation formula of the azimuth and elevation angles of the sun is as follows:

[0087] ;

[0088] wherein a s is the azimuth of the sun, h s is the elevation angle of the sun.

[0089] In an embodiment, the sky polarization image acquisition module 21 can be further configured to: based on the sun position, the geographic latitude and the geographic longitude of the observation point are calculated; wherein the calculation formula of the geographic latitude and the geographic longitude is as follows:

[0090] ;

[0091] wherein, is the geographic latitude, L is the geographic longitude, δ k is the declination angle, H k is the hour angle, is the observation time, is the local sidereal time.

[0092] In an embodiment, the environment polarization image acquisition module 22 can be further configured to: extract the joint feature information of each pixel in the environment polarization image; wherein the joint feature information includes the polarization degree, the polarization angle, the spatial gradient of the polarization degree, and the spatial gradient of the polarization angle of each pixel; based on the joint feature information, the score of each pixel is calculated; wherein based on the score of the pixel, the camouflage target is identified.

[0093] In an embodiment, the environment polarization image acquisition module 22 can be further configured to: the calculation formula of the score is as follows:

[0094] ; wherein F(x, y) is the score value, f p (x, y) is the vector of the joint feature information, is the edge response function, is the target morphology prior score, and a, β, γ are weighting coefficients respectively.

[0095] ​In an embodiment, the environmental polarization image acquisition module 22 can be further configured to determine the pixel as a pixel point of the camouflage target if the score of the pixel is greater than a preset value.

[0096] In the following, an electronic device according to embodiments of the present application will be described with reference to Figure 3 The electronic device can be either one or both of the first device and the second device, or a stand-alone device independent of them, which can communicate with the first device and the second device to receive the acquired input signals therefrom.

[0097] Figure 3 Fig. 1 illustrates a block diagram of an electronic device according to embodiments of the present application.

[0098] As shown in Fig. 1, the electronic device 10 includes one or more processors 11 and a memory 12. Figure 3

[0099] The processor 11 can be a central processing unit (CPU) or other form of processing unit having data processing and / or instruction executing capabilities, and can control other components in the electronic device 10 to perform desired functions.

[0100] The memory 12 can include one or more computer program products, which can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read-only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, which can be run by the processor 11 to implement the methods according to the embodiments of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, and the like can also be stored in the computer-readable storage media.

[0101] In one example, the electronic device 10 can further include an input device 13 and an output device 14, which are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0102] When the electronic device is a stand-alone device, the input device 13 can be a communication network connector for receiving the acquired input signals from the first device and the second device.

[0103] In addition, the input device 13 can further include, for example, a keyboard, a mouse, and the like.

[0104] ​The output device 14 can output various information including the determined distance information, direction information, etc. to the outside. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0105] Of course, in order to simplify, Figure 3 Only some of the components of the electronic device 10 related to the present application are shown in the figure, and components such as buses, input / output interfaces, etc. are omitted. In addition, the electronic device 10 can include any other appropriate components according to the specific application.

[0106] In addition to the methods and devices described above, an embodiment of the present application can also be a computer program product including computer program instructions that, when executed by a processor, cause the processor to perform the steps of the methods according to various embodiments of the present application described in the above "Exemplary Methods" section of this specification.

[0107] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++, etc., and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server.

[0108] In addition, an embodiment of the present application can also be a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the steps of the methods according to various embodiments of the present application described in the above "Exemplary Methods" section of this specification.

[0109] The computer readable storage medium can be any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the above. More specific examples (a non-exhaustive list) of the computer readable storage medium include an electrical connection having one or more wires, a portable disc, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0110] The above describes the basic principles of the present application in combination with specific embodiments, but it needs to be pointed out that the advantages, benefits, effects and the like mentioned in the present application are only examples and are not limiting, and these advantages, benefits, effects and the like cannot be considered as necessary for each embodiment of the present application. In addition, the above specific details disclosed are only for the purpose of example and understanding, and are not limiting, and the above details do not limit the present application to be necessarily implemented with the above specific details.

[0111] The block diagrams of the devices, apparatuses, equipment, systems involved in the present application are only illustrative examples and are not intended to require or imply the connection, arrangement, configuration shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner. Words such as "include", "contain", "have" and the like are open-ended words, mean "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0112] It also needs to be pointed out that in the devices, equipment and methods of the present application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present application.

[0113] The above description of the disclosed aspects is provided so that any person skilled in the art can make or use the present application. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but is intended to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0114] The above description has been given for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A positioning method based on dual-view polarization fusion, characterized in that, The method comprises: collecting a sky polarization image and extracting a characteristic parameter in the sky polarization image; collecting an environmental polarization image in an environmental scene and constructing a polarization feature vector based on the environmental polarization image; combining the characteristic parameter in the sky polarization image and the polarization feature vector to identify positioning information of a camouflage target; the extraction of the characteristic parameter in the sky polarization image comprises: based on the sky polarization image, the sun position is solved; based on the sun position, the geographical position of the observation point is calculated; the construction of the polarization feature vector based on the environmental polarization image comprises: extracting joint feature information of each pixel in the environmental polarization image; wherein the joint feature information comprises the polarization degree, the polarization angle, the spatial gradient of the polarization degree and the spatial gradient of the polarization angle of each pixel; based on the joint feature information, the score of each pixel is calculated; wherein, based on the score of the pixel, the camouflage target is identified.

2. The dual-view polarization fusion based positioning method according to claim 1, wherein, the solving of the sun position based on the sky polarization image comprises: extracting the polarization angle of each pixel point in the sky polarization image; based on the polarization angle of all pixel points, the azimuth and elevation angle of the sun are calculated.

3. The dual-view polarization fusion based positioning method according to claim 2, wherein, the extraction of the polarization angle of each pixel point in the sky polarization image comprises: The calculation formula of the polarization angle is as follows: ; wherein (x,y) is the pixel point coordinate, S 1 , S 2 are the Stokes polarization parameters, respectively.

4. The dual-view polarization fusion based positioning method according to claim 3, characterized in that, the calculation of the azimuth and elevation angle of the sun based on the polarization angle of all pixel points comprises: based on the observation direction vector and the polarization angle of multiple pixel points, a least squares equation set is constructed to solve the sun direction unit vector; wherein the least squares equation set is: ； wherein is the unit vector in the direction of the sun, P i is the observation direction vector of the i th pixel point, S x P i denotes the vector product of S and P i , and is a parameter of the Rayleigh scattering model, f (S) is a least squares function, is a parameter, N is the number of pixel points; based on the sun direction unit vector, the azimuth and elevation angle of the sun are calculated; wherein the calculation formula of the azimuth and elevation angle of the sun is as follows: ； wherein a s is the azimuth angle of the sun, h s is the altitude angle of the sun.

5. The dual-view polarization fusion based positioning method according to claim 4, characterized in that, the calculation of the geographical position of the observation point based on the sun position comprises: based on the sun position, the geographical latitude and geographical longitude of the observation point are calculated; wherein the calculation formula of the geographical latitude and the geographical longitude is as follows: ； where is the geographic latitude, L is the geographic longitude, δ k is the declination angle, H k is the hour angle, and is the local sidereal time.

6. The dual-view polarization fusion based positioning method according to claim 1, wherein, the calculation of the score of each pixel based on the joint feature information comprises: the calculation formula of the score is as follows: ； wherein, F x y are score values, f p x y are vectors of joint feature information, is an edge response function, and α β、γ are weighting coefficients.​​​​​ 7. The dual-view polarization-fusion-based positioning method according to claim 6, wherein, the identification of the camouflage target based on the score of the pixel comprises: if the score of the pixel is greater than a preset value, it is determined that the pixel is a pixel point of the camouflage target.

8. A positioning system based on dual view polarization fusion, characterized in that, The method comprises: a sky polarization image collection module for collecting a sky polarization image and extracting a characteristic parameter in the sky polarization image; an environmental polarization image collection module for collecting an environmental polarization image in an environmental scene and constructing a polarization feature vector based on the environmental polarization image; a camouflage target positioning identification module for combining the characteristic parameter in the sky polarization image and the polarization feature vector to identify positioning information of a camouflage target; the sky polarization image collection module is configured to: based on the sky polarization image, the sun position is solved; based on the sun position, the geographical position of the observation point is calculated; the environmental polarization image collection module is configured to: extract joint feature information of each pixel in the environmental polarization image; wherein the joint feature information comprises the polarization degree, the polarization angle, the spatial gradient of the polarization degree and the spatial gradient of the polarization angle of each pixel; Based on the joint feature information, a score of each pixel is calculated; wherein Based on the score of the pixel, the camouflage target is identified.

Images