Dark space target detection method under deep space background

Abstract

The invention relates to a dark space target detection method under a deep space background. The method comprises the steps of uniform bright star extraction, bright star feature expression and matching, global inter-frame registration, local area dark star accurate matching, deformation field calculation, inter-frame alignment background suppression, dark target extraction and the like. A uniform bright star extraction strategy is adopted to reduce the influence of dark stars on bright star matching, and feature expression and angular distance constraint can ensure that bright star matching is correct and global inter-frame registration is effective during inter-frame large maneuver. A coarse-to-fine inter-frame registration strategy is adopted, dark star coordinate precision is updated during local alignment, deformation field precision is improved, background suppression noise interference is reduced, and robustness is higher for large-view-field and large-edge distortion. According to the method, the disharmonious target moving between local frames of the field of view can be identified at the first time, a potential faint target position of each frame is provided for inter-frame track association, and the faint target detection rate is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of space target monitoring and relates to a method for detecting dark and weak space targets under a deep space background. Background Art

[0002] With the development of large-field-of-view space cameras, the perception of space targets has been greatly improved. Not only are the detected magnitudes getting higher and higher, but the stable tracking capability of targets brought by the large field of view has also made a qualitative leap. The increase in the tracking arc has greatly improved the precision of precise orbit determination of space targets. However, due to the ultra-large field of view and complex stellar background interference, the detection of faint space targets faces great challenges, which are mainly reflected in the following aspects: the difference in angular velocity of space targets relative to the camera causes the diversity of target morphology during the exposure time, which is intertwined with the densely distributed strong and weak stars, and cannot be effectively distinguished from the morphology alone; the use of star catalogs to identify all stars at low magnitudes and then eliminate background interference will not be achieved quickly when the star is dense and high in magnitude, and it will be a great challenge to the completeness of the star catalog, and there will be star omissions; the traditional inter-frame differential background suppression method, due to the field distortion caused by the ultra-large field of view, is very likely to cause a large number of false alarms, causing some stars to be misdetected as space targets. Therefore, achieving inter-frame registration of star maps with large field of view and high magnitude is the key to extracting faint space targets.

[0003] According to the available public literature, there are mainly the following methods for inter-frame registration of serial star maps: methods based on regional statistics, such as grayscale correlation method, mutual information method, and Fourier-Mellin transform method based on frequency domain phase correlation. Grayscale correlation method and mutual information method require traversal search to determine the optimal registration parameters. The Fourier-Mellin method also requires multiple judgments in the frequency domain due to the periodicity of the rotation coefficients. The calculation is large and the accuracy is generally at the pixel level. Methods based on geometric features, such as star polygon matching method and grid method, usually require the construction of feature vectors. The combination of star pairs used to generate feature vectors in densely distributed stars is varied, which increases the difficulty of matching. In addition, the uniqueness of feature vectors is also greatly challenged, resulting in an increase in mismatches. The deep learning-based method constructs a training set by pairing adjacent frames and uses the network to learn the transformation parameters of the two. It can be a rigid transformation or a deformable transformation. However, deep learning requires a large number of training samples. When the training set is very different from the actual one, the registration result is not satisfactory and will cause many false alarms, especially for deep space images without texture. Deep learning does not show a strong advantage over traditional methods, but has strict requirements on the training set. Summary of the invention

[0004] The technical problem solved by the present invention is to overcome the above-mentioned shortcomings of the prior art and provide a method for detecting faint space targets under deep space background. The method obtains the deformation field between frames by coarse-to-fine frame matching, thereby suppressing the interference of stellar background, detecting faint targets that are not harmonious with local transformations for inter-frame trajectory association, and ensuring the detection rate of faint targets.

[0005] The technical solution of the present invention is: a method for detecting dark and weak space targets under deep space background, comprising:

[0006] Obtain star-gazing sequence images; perform large-scale median filtering on each frame of the star image to obtain the background light of the star image, and subtract the background light from each frame of the star image to obtain a star image with a clean background I i ;

[0007] Divide the star map into u×v different regions R evenly according to the image size uv , the variance of each area is taken as the noise variance σ, and 3σ is used as the threshold for binarization, and the connected domain and the peak value in the connected domain are obtained, and the connected domain with multiple peaks is deleted to obtain the single-peak connected domain; the sum of the DN values ​​of the single-peak connected domain is taken as the star point energy; the relatively dark one of the two close star points needs to be deleted to ensure that the distance between the two stars in the star map exceeds γ pixels, and the γ size is larger than the connected domain where the brightest star is located; all detected star points are sorted from large to small according to energy;

[0008] The stars with the top Y% of energy are regarded as bright stars. For each bright star s k , calculate the neighborhood feature expression vector composed of the m star points ranked top by energy in the ρ degree field of view neighborhood, that is, the m companion stars;

[0009] According to the neighborhood feature expression vectors of all bright stars in the star map of the i-th frame and the i+1-th frame, the corresponding possible matching point set is found according to the principle of shortest Euclidean distance and mutual matching of the neighborhood feature expression vector, that is, the initial matching point set {p}i of the i-th frame star map and the point set {p′}i of the i+1-th frame star map are obtained. +1 ;

[0010] Introduce angular distance constraint {p} i and {p′} i+1 Screen and get the correct matching point set M i，i+1 ;

[0011] The correct matching point set M i，i+1 The transformation relationship from the star image of the i-th frame to the star image of the i+1-th frame is calculated and represented by a 3x3 homography matrix model H;

[0012] The i-th frame star image I i After homography transformation and the i+1th star map I i+1 Align and get the transformed star map I i′;

[0013] After transformation, star map I i ′ and the star image I of the i+1th frame i+1 The aligned parts are evenly divided into U sub-areas {b k}, k = 1, ..., U and {c k}, k=1, ..., U, obtain U sub-regions to be matched, and find the star point set of each sub-region to be matched from the obtained energy-ranked star points;

[0014] Each matching area b k and c k The star point set {p} detected in k i and{q} k i+1 , confirm the matching point pairs through cross-correlation, and calculate the homography transformation model H of each area to be matched k , and adjust the positions of the matching point pairs confirmed by cross-correlation to obtain the precise matching point set of all the areas to be matched;

[0015] The point set S of the i-th frame i ′ and the previous homography transformation H are inversely transformed to obtain the point set of the star map of the i-th frame

[0016] All the exact matching point sets S i and S i+1 Calculate the star map I of the i-th frame i To the i+1th frame star map I i+1 The deformation field T;

[0017] Using the deformation field T, the star image I of the i-th frame i The pixel coordinates (x i ,y i ) are calculated to obtain the position of the star map in the i+1 frame (x i+1 ,y i+1 ), and use interpolation to obtain the transformed image I i ″;

[0018] Using conventional background suppression techniques to process I i "And I i+1 , suppress the same areas of the two, obtain the different areas, that is, the potential dark target areas, and then associate the potential dark target areas according to the trajectory association constraints through multiple frames to further confirm the dark target.

[0019] The Y=5, ρ is set to one tenth of the star map field of view, and m is greater than 10.

[0020] For each bright star s k, calculate the neighborhood feature expression vector composed of the m star points ranked top by energy in the ρ degree field of view neighborhood, that is, the m companion stars, including:

[0021] s k Establish the x-axis with the closest companion star, and calculate the distance between all companion stars and s k The distance between j}, j = 1, ..., m, and s k The line connecting the companion star and the x-axis forms an angle {θ j}, j = 1, ..., m;

[0022] With Δθ as the step length, a circle is divided into 360 / Δθ intervals, and the sum of the companion star distances in each interval is counted to obtain a histogram and normalize it as s k The neighborhood feature expression vector of .

[0023] The introduction of angular distance constraint {p} i and {p′} i+1 Screen and get the correct matching point set M i，i+1 ,include:

[0024] For {p} i Each point s k , in {p} i Find all the distances from this point in [τ min , τ max ] degrees, select the N star points with the highest energy ranking p 1,...N ; At the same time, we also found {p′} i+1 The corresponding point s′ in the initial match k and N star points p′ 1，...N ;

[0025] Assume k The initial confidence is 0; p1 and p2 and s k To form a triangle, find the angular distances between the three vertices. At the same time, p′1 and p′2 are k To form a triangle, we also need to find the angular distances between the three vertices. If their corresponding angular distances are all less than ∈ instantaneous field of view, then s k The confidence level increases by 1, and the ∈ is greater than the maximum distortion of the star map; similarly, p2 and p3 are related to s k Form a triangle to verify the angular distance until p N-1 and p N With s k Form a triangle to verify the angular distance and get the final s kIf the confidence is greater than 1, it means that at least one quadrilateral angle constraint is satisfied, and the point is considered to be the correct matching point M(s k , s′ k );

[0026] Check in sequence and finally get the correct matching point set M i，i+1 ={M(s k , s′ k )}.

[0027] The τ min Set to one tenth of the star map field of view; τ max Set it to one-third of the star map field of view, and N is greater than 10.

[0028] The correct matching point set M i，i+1 The transformation relationship from the star image of the i-th frame to the star image of the i+1-th frame is calculated, including:

[0029] The correct matching point set M of the star image of the i-th frame and the star image of the i+1-th frame i，i+1 The pixel coordinates are normalized respectively, and the mean value of the normalized pixel coordinate distribution is set to 0 and the variance is set to 1;

[0030] Use the RANSAC strategy to calculate the homography matrix H';

[0031] The homography matrix H' is denormalized to obtain the homography matrix transformation model H from the i-th frame star image calculated by the bright star to the i+1-th frame star image.

[0032] Each matching area b k and c k The star point set {p} detected in k i and{q} k i+1 , confirm the matching point pairs through cross-correlation, and calculate the homography transformation model H of each area to be matched k , and adjust the positions of the matching point pairs confirmed by cross-correlation to obtain the precise matching point set of all the areas to be matched, including:

[0033] From sub-area b k Get the a×a window area w centered at each star point p p i , from c k Get the neighboring a×a window area w centered at each point q q i ; Since it has been roughly aligned, w p i Can find its neighboring w q iPerform cross-correlation operation, then p and w with the largest correlation value q i The corresponding q is a pair of matching points; thus we get b k and c k The set of candidate matching points between ; a is a positive integer;

[0034] Use RANSAC to determine the homography transformation model H for the candidate matching point set k , and satisfy H k The partial candidate matching point set of the relationship is modified to obtain the coordinates of the precise matching point set;

[0035] The precise matching point set of all the areas to be matched Combined into the i-th frame I i The point set of ′ To the i+1th frame I i+1 Point set

[0036] The deformation field T(a0, ..., a9, b0, ..., b9, c0, ..., c9) satisfies the following relationship:

[0037]

[0038] Among them, (x i ,y i ) is S i The pixel coordinates of the elements in (x i+1 ,y i+1 ) is S i+1 The pixel coordinates of the elements in the deformation field are obtained by iterative method to obtain the deformation field model parameters a0, ..., a9, b0, ..., b9, c0, ..., c9; the initial value of the iteration a1 = h 11 , a2=h 12 , a0=h 13 , a4~a9 are all 0, c0=h 33 , c1=h 31 , c2=h 32 , c4~c9 are all 0, b0=h 23 , b1=h 21 , b2=h 22 , b4~b9 are all 0, among which h ij is the element in the i-th row and j-th column of the homography matrix H.

[0039] The beneficial effects of the present invention compared with the prior art are:

[0040] (1) The present invention adopts a uniform bright star screening mode and feature expression method, and introduces angular distance constraints to ensure accurate matching of bright stars between frames even in the case of large maneuvers between frames. The calculation is simple and fast.

[0041] (2) After the rough alignment of bright stars between frames, the present invention performs confirmation of the cross-correlation matching point set in the local area. Since the basic alignment has been completed, there is no need to adjust the time-consuming cross-correlation registration parameters. Confirmation is performed only through the maximum correlation value, which ensures the one-to-one correspondence between dark stars. The local transformation relationship is calculated and the precise coordinate position of the matching point set is updated, thereby improving the accuracy of the subsequent deformation field.

[0042] (3) The present invention adopts a deformation field calculation method from coarse to fine, which can not only effectively solve the large maneuvering between frames, but also adapt to the situation of large edge distortion of large field of view due to the fitting of local area deformation, so that potential dark and weak targets can be discovered in the first time. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 The present invention is a flow chart of a method for detecting dark and weak space targets under a deep space background. DETAILED DESCRIPTION

[0044] like Figure 1 As shown, a method for detecting a dark and weak space target under a deep space background comprises:

[0045] Step (1), obtaining a sequence of star-gazing images; performing a large-scale median filter on each frame of the star image to obtain the background light of the star image, and subtracting the background light from each frame of the star image to obtain a star image with a clean background I i .

[0046] Step (2): Divide the star map into u times v different regions R according to the image size uv , the variance calculated in each region is used as the noise variance σ, and 3σ is used as the threshold for binarization. The connected domain and the peak value in the connected domain are obtained, and the connected domain with multiple peaks is deleted to obtain the single-peak connected domain. The sum of the DN values ​​of the single-peak connected domain is calculated as the star point energy. For two close star points, the relatively dark one should be deleted to ensure that the distance between the two stars in the star map exceeds γ pixels. γ should be larger than the size of the connected domain where the brightest star is located, which can usually be selected between 30 and 100. All detected star points are sorted from large to small according to energy.

[0047] Step (3): The stars with the top 5% energy are regarded as bright stars. k , calculate the neighborhood feature expression vector composed of m star points (companion stars) ranked top by energy in the neighborhood of ρ degree field of view, ρ is set to one tenth of the star map field of view, m is generally greater than 10, usually 20. The whole process of step (three) is as follows:

[0048] 1)s k Establish the x-axis with the closest companion star, and calculate the distance between all companion stars and s k The distance betweenj}, j = 1, ..., m, and s k The line connecting the companion star and the x-axis forms an angle {θ j}, j = 1, ..., m.

[0049] 2) Taking Δθ as the step length, divide a circle into 360 / Δθ intervals, and count the sum of the companion star distances in each interval to obtain a histogram, recorded as D k , and normalized as s k The neighborhood feature expression vector of , Δθ is set to 10 degrees.

[0050] Step (iv), find the corresponding possible matching point set according to the shortest Euclidean distance and mutual matching principle of the neighborhood feature expression vectors of all bright stars in the star map of the i-th frame and the i+1-th frame, that is, obtain the initial matching point set {p} of the star map of the i-th frame i and the star map point set {p′} of the i+1th frame i+1 .

[0051] Step (V): Introduce angular distance constraint {p} i and {p′} i+1 Screening, the whole process of step (five) is as follows:

[0052] 1) For {p} i Each point s k , in {p} i Find all the distances from this point in [τ min , τ max ] degrees, select the N star points with the highest energy ranking p 1，...N ; At the same time, we also found {p′} i+1 The corresponding point s′ in the initial match k and N star points p′ 1，...N τ min Set to one tenth of the star map field of view, τ max Set it to one third of the star map field of view, N should be greater than 10, usually set to 15.

[0053] 2) Let s k The initial confidence is 0. k To form a triangle, find the angular distances between the three vertices. At the same time, p′1 and p′2 are k To form a triangle, we also need to find the angular distances between the three vertices. If their corresponding angular distances are all less than ∈ instantaneous field of view, then s k The confidence level of ∈ is increased by 1, and ∈ is slightly larger than the maximum distortion of the star map (in pixels); similarly, p2 and p3 can be kForm a triangle to verify the angular distance until p N-1 and p N With s k Form a triangle to verify the angular distance and get the final s k If the confidence is greater than 1, it means that at least one quadrilateral angle constraint is satisfied, and the point is considered to be the correct matching point M(s k , s′ k ).

[0054] 3) Check in sequence and finally get the correct matching point set M i，i+1 ={M(s k , s′ k )}.

[0055] Step (six): From the correct matching point set M i，i+1 , we can calculate the transformation relationship from the star image of the i-th frame to the star image of the i+1-th frame, and the transformation relationship adopts the 3x3 homography matrix model H. The specific process of the whole step (six) is:

[0056] 1) The correct matching point set M of the star image of the i-th frame and the star image of the i+1-th frame i，i+1 The pixel coordinates are normalized respectively, and the mean value of the normalized pixel coordinate distribution is set to 0 and the variance is set to 1;

[0057] 2) Use the RANSAC strategy to calculate the homography matrix H';

[0058] 3) Denormalize the homography matrix H' to obtain the homography matrix transformation model H from the i-th frame star image calculated from the bright star to the i+1-th frame star image.

[0059] Step (VII): the i-th frame star map I i After homography transformation and the i+1th star map I i+1 Align and get the transformed star map I i ′.

[0060] Step (eight), transform the star map I i ′ and the star image I of the i+1th frame i+1 The aligned parts are evenly divided into U sub-areas {b k}, k = 1, ..., U and {c k}, k=1, ..., U, obtain U sub-regions to be matched, and find the star point set of each sub-region to be matched from the energy-ranked star points obtained in step (ii).

[0061] Step (IX): for each matching area b k and c k The star point set {p} detected in k i and{q}k i+1 , confirm the matching point pairs through cross-correlation, and calculate the homography transformation model H of each area to be matched k , and adjust the positions of the matching point pairs confirmed by cross-correlation to obtain the precise matching point set of all the areas to be matched. The specific process of the overall step (IX) is:

[0062] 1) From sub-area b k Get the a×a window area w centered at each star point p p i , from c k Get the neighboring a×a window area w centered at each point q q i . Since the rough alignment has been done, w p i You can find its neighboring w q i Perform cross-correlation operation, then p and w with the largest correlation value q i The corresponding q is a pair of matching points. Thus, we can get b k and c k The set of candidate matching points between . a is usually set to 31.

[0063] 2) Use RANSAC to determine the homography transformation model H for the candidate matching point set k , and satisfy H k The partial candidate matching point set of the relationship is modified to obtain the coordinates of the precise matching point set.

[0064] 3) The precise matching point set of all the areas to be matched Combined into the i-th frame I i ′ To the i+1th frame I i+1 Point set

[0065] Step (10): From the point set S of the i-th frame i ′ and the previous homography transformation H are inversely transformed to obtain the point set of the star map of the i-th frame

[0066] Step (XI): S i and S i+1 Calculate the star map I of the i-th frame i To the i+1th frame star map I i+1 The deformation field T(a0, ..., a9, b0, ..., b9, c0, ..., c9) satisfies the following relationship:

[0067]

[0068] Among them, (x i ,y i ) is S i The pixel coordinates of the elements in (x i+1 ,y i+1 ) is S i+1 The pixel coordinates of the elements in the deformation field are obtained by iteration to obtain the deformation field model parameters a0, ..., a9, b0, ..., b9, c0, ..., c9. The initial value of the iteration is a1 = h 11 , a2=h 12 , a0=h 13 , a4~a9 are all 0, c0=h 33 , c1=h 31 , c2=h 32 , c4~c9 are all 0, b0=h 23 , b1=h 21 , b2=h 22 , b4~b9 are all 0, among which h ij is the element in the i-th row and j-th column of the homography matrix H.

[0069] Step (12): Based on the deformation field T, the star image I of the i-th frame is i The pixel coordinates (x i ,y i ) can calculate the position of the star map in the i+1 frame (x i+1 ,y i+1 ), the transformed image I can be obtained by interpolation i ″, compared to I i ′,I i ″The i+1 frame star image I can be well aligned locally i+1 .

[0070] Step (thirteen): using conventional background suppression technology to process I i "And I i+1 , the same areas of the two are suppressed, and the different areas, namely the potential dim target areas, are obtained. Then, the potential dim target areas are associated with each other according to the trajectory association constraints through multiple frames, so that the dim target can be further confirmed.

[0071] The above description is only the best specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for detecting dark and weak space targets under deep space background, characterized in that: include: Get stargazing sequence images; Perform a large-scale median filter on each frame of the star image to obtain the background light of the star image, and subtract the background light from each frame of the star image to obtain a star image with a clean background I i ; Divide the star map into u×v different regions R evenly according to the image size uv , the variance of each area is taken as the noise variance σ, and 3σ is used as the threshold for binarization, and the connected domain and the peak value in the connected domain are obtained, and the connected domain with multiple peaks is deleted to obtain the single-peak connected domain; the sum of the DN values ​​of the single-peak connected domain is taken as the star point energy; the relatively dark one of the two close star points needs to be deleted to ensure that the distance between the two stars in the star map exceeds γ pixels, and the γ size is larger than the connected domain where the brightest star is located; all detected star points are sorted from large to small according to energy; The stars with the top Y% of energy are regarded as bright stars. For each bright star s k , calculate the neighborhood feature expression vector composed of the m star points ranked top by energy in the ρ degree field of view neighborhood, that is, the m companion stars; Based on the neighborhood feature expression vectors of all bright stars in the star image of the i-th frame and the i+1-th frame, the corresponding possible matching point set is found according to the principle of shortest Euclidean distance and mutual matching of the neighborhood feature expression vectors, that is, the point set {p} of the i-th frame star image is obtained. i and the star map point set {p′} of the i+1th frame i+1 ; Introduction Angular distance constraint pair {p} i and {p′} i+1 Screen and get the correct matching point set M i，i+1 ; The correct matching point set M i，i+1 The transformation relationship from the star image of the i-th frame to the star image of the i+1-th frame is calculated and represented by a 3x3 homography matrix model H; The i-th frame star image I i After homography transformation and the i+1th star map I i+1 Align and get the transformed star map I i ′; After transformation, star map I i ′ and the star image I of the i+1th frame i+1 The aligned parts are evenly divided into U sub-areas {b k }, k = 1, ..., U and {c k }, k=1, ..., U, obtain U sub-regions to be matched, and find the star point set of each sub-region to be matched from the obtained energy-ranked star points; Each matching area b k and c k The star point set {p} detected in k i and{q} k i+1 , confirm the matching point pairs through cross-correlation, and calculate the homography transformation model H of each area to be matched k , and adjust the positions of the matching point pairs confirmed by cross-correlation to obtain the precise matching point set of all the areas to be matched; The point set S of the i-th frame i ′ and the previous homography transformation H are inversely transformed to obtain the point set of the star map of the i-th frame All the exact matching point sets S i and S i+1 Calculate the star map I of the i-th frame i To the i+1th frame star map I i+1 The deformation field T; Using the deformation field T, the star image I of the i-th frame i The pixel coordinates (x i ,y i ) are calculated to obtain the position of the star map in the i+1 frame (x i+1 ,y i+1 ), and use interpolation to obtain the transformed image I i ″; Using conventional background suppression techniques to process I i "And I i+1 , suppress the same areas of the two, and obtain the different areas, that is, the potential dark target areas. Then, through multiple frames, the potential dark target areas are associated according to the trajectory association constraints to further confirm the dark target.

2. The method for detecting dark and weak space targets under deep space background according to claim 1, characterized in that: The Y==5, ρ is set to one tenth of the star map field of view, and m is greater than 10.

3. The method for detecting dark and weak space targets under deep space background according to claim 1, characterized in that: For each bright star s k , calculate the neighborhood feature expression vector composed of the m star points ranked top by energy in the ρ degree field of view neighborhood, that is, the m companion stars, including: s k Establish the x-axis with the closest companion star, and calculate the distance between all companion stars and s k The distance between j }, j = 1, ..., m, and s k The line connecting the companion star and the x-axis forms an angle {θ j }, j = 1, ..., m; With Δθ as the step length, a circle is divided into 360 / Δθ intervals, and the sum of the companion star distances in each interval is counted to obtain a histogram and normalize it as s k The neighborhood feature expression vector of .

4. The method for detecting dark and weak space targets under deep space background according to claim 1, characterized in that: The introduction of angular distance constraint {p} i and {p′} i+1 Screen and get the correct matching point set M i，i+1 ,include: For {p} i Each point s k , in {p} i Find all the distances from this point in [T min , τ max ] degrees, select the N star points with the highest energy ranking p 1，...N ; At the same time, we also found {p′} i+1 The corresponding point s′ in the initial match k and N star points p′ 1，...N ; Assume k The initial confidence is 0; p1 and p2 and s k To form a triangle, find the angular distances between the three vertices. At the same time, p′1 and p′2 are k To form a triangle, we also need to find the angular distances between the three vertices. If their corresponding angular distances are all less than ∈ instantaneous field of view, then s k The confidence level increases by 1, and the ∈ is greater than the maximum distortion of the star map; similarly, p2 and p3 are related to s k Form a triangle to verify the angular distance until p N-1 and p N With s k Form a triangle to verify the angular distance and get the final s k If the confidence is greater than 1, it means that at least one quadrilateral angle constraint is satisfied, and the point is considered to be the correct matching point M(s k , s′ k ); Check in sequence and finally get the correct matching point set M i，i+1 ={M(s k , s′ k )}.

5. The method for detecting dark and weak space targets under deep space background according to claim 4, characterized in that: The T min Set to one tenth of the star map field of view; T max Set it to one-third of the star map field of view, and N is greater than 10.

6. The method for detecting dark and weak space targets under deep space background according to claim 4, characterized in that: The correct matching point set M i，i+1 The transformation relationship from the star image of the i-th frame to the star image of the i+1-th frame is calculated, including: The correct matching point set M of the star image of the i-th frame and the star image of the i+1-th frame i，i+1 The pixel coordinates are normalized respectively, and the mean value of the normalized pixel coordinate distribution is set to 0 and the variance is set to 1; Use the RANSAC strategy to calculate the homography matrix H'; The homography matrix H' is denormalized to obtain the homography matrix transformation model H from the i-th frame star image calculated by the bright star to the i+1-th frame star image.

7. The method for detecting dark and weak space targets under deep space background according to claim 6, characterized in that: Each matching area b k and c k The star point set {p} detected in k i and{q} k i+1 , confirm the matching point pairs through cross-correlation, and calculate the homography transformation model H of each area to be matched k , and adjust the positions of the matching point pairs confirmed by cross-correlation to obtain the precise matching point set of all the areas to be matched, including: From sub-area b k Get the a×a window area w centered at each star point p p i , from c k Get the neighboring a×a window area w centered at each point q q i ; Since it has been roughly aligned, w p i Can find its neighboring w q i Perform cross-correlation operation, then p and w with the largest correlation value q i The corresponding q is a pair of matching points; thus we get b k and c k The set of candidate matching points between ; a is a positive integer; Use RANSAC to determine the homography transformation model H for the candidate matching point set k , and satisfy H k The partial candidate matching point set of the relationship is modified to obtain the coordinates of the precise matching point set; The precise matching point set of all the areas to be matched Combined into the i-th frame I i ′ To the i+1th frame I i+1 Point set 8. The method for detecting dark and weak space targets under deep space background according to claim 7, characterized in that: The deformation field T(a0, ..., a9, b0, ..., b9, c0, ..., c9) satisfies the following relationship: Among them, (x i ,y i ) is S i The pixel coordinates of the elements in (x i+1 ,y i+1 ) is S i+1 The pixel coordinates of the elements in the deformation field are obtained by iterative method to obtain the deformation field model parameters a0, ..., a9, b0, ..., b9, c0, ..., c9; the initial value of the iteration a1 = h 11 , a2=h 12 , a0=h 13 , a4~a9 are all 0, c0=h 33 , c1=h 31 , c2=h 32 , c4~c9 are all 0, b0=h 23 , b1=h 21 , b2=h 22 , b4~b9 are all 0, among which h ij is the element in the i-th row and j-th column of the homography matrix H.

Images