CN109727279B - Automatic registration method of vector data and remote sensing image - Google Patents
Automatic registration method of vector data and remote sensing image Download PDFInfo
- Publication number
- CN109727279B CN109727279B CN201910083298.XA CN201910083298A CN109727279B CN 109727279 B CN109727279 B CN 109727279B CN 201910083298 A CN201910083298 A CN 201910083298A CN 109727279 B CN109727279 B CN 109727279B
- Authority
- CN
- China
- Prior art keywords
- matrix
- remote sensing
- edge
- vector data
- sensing image
- 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.)
- Active
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The open remote sensing data is processed by certain decryption according to the requirements of the security policy, and the user tries to make own vectorWhen the data is superposed with the remote sensing data, the two data are not matched. Aiming at the problem, the invention discloses an automatic registration method of vector data and a remote sensing image. The method comprises the following specific steps: 1) extracting a ternary matrix A by using a scanning line algorithm based on the vector data; 2) extracting a gray matrix G based on the remote sensing image, and obtaining an edge matrix E of the gray matrix G by using a Canny operator; 3) traversing on the three-valued matrix A by using the edge matrix E to generate a normalized edge registration factor matrix F' Edge (ii) a 4) Traversing on the three-value matrix A by using the gray matrix G to generate a normalized gray registration factor matrix F' Ash of (ii) a 5) Based on the characteristics of the registration factor, carrying out automatic registration on the vector data and the remote sensing image; 6) remote sensing image data within a specified range of the vector elements are extracted.
Description
Technical Field
The invention belongs to the field of GIS, and particularly relates to a method for carrying out automatic registration by utilizing consistency of pixel features of remote sensing images and element features of vector data.
Background
At present, a plurality of platforms provide open remote sensing data service, and good data background support is provided for a plurality of space browsing and retrieval applications. Especially, when the method is applied to land approval, environmental evaluation, road planning and the like, the remote sensing images within a certain vector element range are often required to be extracted and analyzed independently. However, since the relevant open data are all subjected to certain decryption processing according to the requirements of the security policy, when a user tries to overlay the own vector data and the remote sensing data, the two data are not matched. Therefore, an efficient and automatic method for correcting the geometric deviation between the self-contained vector data and the public remote sensing image data is urgently needed.
Because the vector data and the remote sensing image have different properties, certain rotation change, scale change and position change exist. At present, the mainstream method is to manually select a certain ground control point to obtain a transformation function between the two control points for calibration. The method has high requirement on operation precision, wastes time and labor, has the problems of incapability of downloading map data, inaccurate naked eye calibration, inconsistent zooming degree and the like, and is not suitable for being used as a conventional means for processing massive geographic information data. Nor can it be applied to high-precision and large-batch data processing and updating as a rigorous scientific method.
In recent years, many methods have been proposed by Chinese and foreign scholars for the problem of automatic registration between remote-sensing images and vector data. Joachim Hohle (2008) takes the old orthoimage and the existing vector map as references, obtains an image template of a road intersection through the orthoimage and the vector map, matches the new image to generate a new control point, and realizes automatic external orientation of the remote sensing image. Experiments show that the requirements of orthoscopic images and vector maps can be basically met; heiner Hild et al (2001) take registration of SPOT images and vector maps as research objects, determine approximate transformation relation between the SPOT images and the vector maps by using manually selected initial control points, and extract control points on polygonal boundaries to carry out aerial triangulation to realize registration of the images and the maps; zhang Xiaodong et al (2006) automatically registers remote sensing images and vector data based on polygonal features of planar ground objects; and the Liu Shi Qing (2012) screens and extracts proper remote sensing image linear features and measures similarity by using a Canny operator and edge tracking, so that automatic registration of the remote sensing image and vector data is realized.
The processing steps of the above method generally include: feature selection and extraction, vector data preprocessing, feature matching and vector grid registration realization. The research methods are only carried out aiming at a specific type of problem, most methods still need more manual interaction, no fully-automatic mature system exists, and the requirement for efficient large-scale image data processing is difficult to meet.
Disclosure of Invention
The invention mainly aims at the characteristics that the shape deformation and the angle deformation between self-contained vector data and public remote sensing image data are weak and the position deviation is large, and utilizes the consistency of the pixel characteristics and the vector element characteristics of the remote sensing image to carry out automatic registration so as to support the automatic cutting and extraction of the remote sensing image data in a certain element or element set range. On the basis of extracting the registration factor between the public remote sensing image data and the user own vector data, the remote sensing image within a certain element or element set range is accurately and quickly extracted by calculating the relative deviation between the public remote sensing image data and the user own vector data.
The invention provides an automatic registration method of vector data and remote sensing images, which comprises the following steps:
step 1, extracting a ternary matrix A by using a scanning line algorithm based on vector data;
step 2, extracting a gray matrix G based on the remote sensing image, and obtaining an edge matrix E of the gray matrix G by using a Canny operator;
step 3, traversing the three-value matrix A by using the edge matrix E to generate a normalized edge registration factor matrix F' Edge ；
Step 4, traversing the three-value matrix A by using the gray-scale matrix G to generate a normalized gray-scale registration factor matrix F' Ash of ；
Step 5, automatically registering the vector data and the remote sensing image based on the characteristics of the registration factor;
and 6, extracting the remote sensing image data in the specified range of the vector elements.
The step 1 specifically comprises the following steps:
1.1, extracting a minimum outsourcing rectangle of the vector data, and converting the minimum outsourcing rectangle into a binary grid matrix Y ═ { Y (i, j) | i ═ 0, ·, m-1 according to a formula (1); j is 0, a., n-1, wherein m is the height of the vector data outsourcing rectangle, and n is the width of the vector data outsourcing rectangle;
1.2, creating a boolean flag matrix F ═ { F (i, j) | i ═ 0. j ═ 0.., n-1} determines whether or not the vector element edge is present;
1.3 scanning the line L for each row t ＝{(t,j)|j＝0,...,n-1}(t∈[0,m-1]) Assigning the mark matrix F by using a formula (2);
1.4, respectively marking the boundary and the interior of the vector element according to the mark matrix F; creating a matrix a ═ { a (i, j) | i ═ 0. j is 0, the.. and n-1, the initial default value is 0, and assignment is performed according to a formula (3) to obtain an assigned ternary matrix A, wherein the edge point identifier of the vector data is 2, the internal point identifier is 1, and the background point identifier is 0;
the step 2 specifically comprises the following steps:
2.1, extracting a gray matrix based on the public remote sensing image: reading remote sensing image data to a matrix C (C (i, j) | i ═ 0., p-1; j-0., q-1} which is processed as a gray matrix G ═ { G (i, j) | i ═ 0., p-1; j ═ 0.., q-1 };
g(i,j)＝0.299*c r (i,j)+0.587*c g (i,j)+0.114*c b (i,j) (4)
Wherein, p is the height of the remote sensing image data, q is the width of the remote sensing image data, and the conditions (p > m) and (q > n) are satisfied; c. C r (i,j)、c g (i,j)、c b (i, j) respectively represents R, G, B values of the remote sensing image C at the point (i, j);
2.2, smoothing the gray matrix G by using a Gaussian filter;
a) calculating the user given size (2k +1) × (2k +1) and the variance σ using equation (5) 2 A lower gaussian convolution kernel G '═ { G' (x, y) | x ═ k, · k; y ═ k,.., k };
b) convolving the convolution kernel G' with the remote sensing image gray matrix G to obtain a smoothed image matrix S ═ { S (i, j) | i ═ 0., p-1; j ═ 0.., q-1 };
2.3, calculating the amplitude and the direction of the gradient; calculating the amplitude and the direction of the gradient of the smoothing matrix S by using the formulas (6), (7) and (8);
θ(i,j)＝arctan(P x (i,j)/P y (i,j)) (8)
wherein P is x ，P y Gradient operators, P, in the x, y directions of the image, respectively x (i,j)，P y (i, j) is the product of the gradient operator at point (i, j) and the smoothing matrix, arctan represents the tangent function, M (i, j) is the magnitude of the smoothing matrix S at (i, j), θ (i, j) is the direction of the smoothing matrix S at (i, j);
2.4, carrying out non-maximum suppression on the gradient amplitude: obtaining a gradient matrix Grad ═ { Grad (i, j) | i ═ 0.., p-1 after the non-maximum value is suppressed according to the formula (9); j ═ 0.., q-1 };
wherein M is Front side Representing the magnitude of the gradient, M, at a point preceding point (i, j) in the direction of the gradient Rear end Represents the gradient magnitude of a point subsequent to the point (i, j) in the gradient direction;
2.5, carrying out edge detection and connection according to a double-threshold method: establishing a high threshold delta Height of And a low threshold delta Is low in Points (i, j) satisfying the condition (10) can be determined as edge points, and the points are connected to obtain a final edge image matrix E ═ { E (i, j) | i ═ 0. j ═ 0.., q-1 };
g(i,j)＞δ height of or(g(i,j)＜δ Height of and g(i,j)＞δ Is low in and flag(i,j)＝true) (10)
The step 3 specifically comprises the following steps:
3.1, setting the point at the upper left corner of the remote sensing image as an origin, and obtaining a point pair set D { (D) of the relative displacement deviation between the point at the upper left corner and the origin of the remote sensing image when the user own vector data are at different positions by using the edge image matrix E and the ternary matrix A x ,d y )|0≤d x ≤p-m-1；0≤d y Q-n-1 ≦ q, any deviation (D) in the set D is calculated according to equation (11) x ,d y ) Corresponding result matrix T dxdy ＝{t(i,j)|i＝0,...,m-1；j＝0,...,n-1}；
3.2, calculating the sum f of elements in the result matrix T corresponding to the deviation according to the formula (12);
3.3 element corresponding to each element in the set D and the resulting matrix F formed Edge ＝{f Edge (x, y) | x ═ 0.., p-m-1; y is 0,., q-n-1, which is the edge registration factor matrix;
3.4, obtaining an edge registration factor matrix F Edge Normalizing according to a formula (13) to obtain a normalized edge registration factor matrix F' Edge ＝{f' Edge (d x ,d y )|d x ＝0,...,p-m-1；d y ＝0,...,q-n-1}；
Wherein f is Side max Representing the maximum value of the edge registration factor matrix, f While min Represents the minimum of the edge registration factor matrix.
The step 4 specifically comprises the following steps:
4.1 Using the grayscale image matrix G and the ternary matrix A, any deviation { (D) in the set D x ,d y ) A corresponding result matrix T '═ { T' (i, j) | i ═ 0., m-1 is calculated according to formula (14); j ═ 0.., n-1 };
4.2, calculating the variance f' of the non-zero value in the corresponding result matrix according to the formulas (15) and (16);
wherein R is the number of non-zero values in the result matrix T';
4.3 result matrix F consisting of variances corresponding to elements in set D Ash of ＝{f Ash of (x, y) | x ═ 0.., p-m-1; y is 0, the q-n-1 is a gray level registration factor matrix;
4.4, obtaining a gray level registration factor matrix F Ash of Normalizing according to the formula (17) to obtain a normalized gray level registration factor matrix F' Ash of ＝{f' Ash of (d x ,d y )|d x ＝0,...,p-m-1；d y ＝0,...,q-n-1}；
Wherein f is Ash max Representing gray scaleMaximum of the registration factor matrix, f Lime min Representing the minimum value of the gray scale registration factor matrix.
The step 5 specifically comprises the following steps:
5.1, according to the characteristic of the registration factor, if the edge registration factor of a deviation position is larger and the gray level registration factor is smaller, the vector data at the deviation position is matched with the remote sensing image more, and the comprehensive registration factor matrix F is created by using a formula (18) according to the principle Judgment ＝{f Judgment (i,j)|i＝0,...,p-m-1；j＝0,...,q-n-1}；
5.2 traversing the matrix F of the discrimination values Judgment Obtaining the deviation value (i) corresponding to the minimum value 0 ,j 0 ) And the vector data is the optimal deviation value of the registration of the vector data and the remote sensing image.
The step 6 specifically comprises the following steps:
generating a result matrix R ═ { R (x, y) | x ═ 0., m-1 according to equation (19); y is 0,., n-1 }; the image corresponding to the matrix is a remote sensing image in a vector data element or element set range, and the rest part is a black background;
has the advantages that: compared with the prior art, the invention provides a method for solving and optimizing the deviation between the remote sensing image and the self-owned vector data by comprehensively utilizing the gray level registration factor matrix obtained by the remote sensing gray level image and the edge registration factor matrix obtained by combining the Canny operator and utilizing the characteristics of the gray level registration factor matrix and the edge registration factor matrix, and finally obtaining the remote sensing image in a certain vector element range. The method mainly has the following characteristics:
1) the characteristics that the position offset between the self-contained vector data and the remote sensing image is large and the shape and angle deformation can be ignored are fully utilized;
2) the consistency of the remote sensing image edge image and the vector elements and the correlation of the ground objects in a specific range are comprehensively utilized, and the automatic registration of the vector elements and the remote sensing image is realized.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of the deviation between the remote sensing image and the vector data;
FIG. 3 is remote sensing image data used in an embodiment;
FIG. 4 is vector data used by an embodiment;
FIG. 5 is a schematic diagram of the initial relative positions of the remote sensing image data and the vector data;
FIG. 6 is a schematic diagram of a three-valued matrix of vector data;
FIG. 7 is a remote sensing image gray scale image;
FIG. 8 is a remote sensing image edge image;
FIG. 9 is a partial diagram of the dot product of the three-valued matrix and the corresponding edge image when the deviation is (0, 0);
FIG. 10 is a schematic diagram of an edge registration factor matrix;
FIG. 11 is a schematic diagram of a portion of a dot product of a ternary matrix and a gray-scale image when the deviation is (0, 0);
FIG. 12 is a schematic diagram of a gray scale registration factor matrix;
FIG. 13 is a schematic diagram of a comprehensive registration factor matrix;
FIG. 14 is a schematic diagram of the relative positions of the remote sensing image and the vector data after registration;
fig. 15 is a result diagram of extracting a remote sensing image in a vector element range.
Detailed Description
The invention is further illustrated below with reference to the figures and examples.
In the embodiment, a remote sensing image base map of 2016 years in Jiangsu province published by Tian Ma-Jiangsu is used as remote sensing image data (fig. 3); the user's own vector data is part of the tin-free park element resources (fig. 4). The relative positions of which the two start are shown in figure 5. The size of the remote sensing map is 708 pixels 571, and the size of the user own vector data is 612 pixels 512.
Step 1, extracting a vector data ternary matrix;
1.1, extracting a minimum outsourcing rectangle of the vector data, and converting the minimum outsourcing rectangle into a binary grid matrix Y (Y (i, j) | i ═ 0, ·, m-1 according to a formula (1); j-0., n-1}, as shown in fig. 4, in the present embodiment, m-708, n-571;
1.2, creating a boolean flag matrix F ═ { F (i, j) | i ═ 0. j ═ 0.., n-1} determines whether or not the vector element edge is present;
1.3 scanning the line L for each row t ＝{(t,j)|j＝0,...,n-1}(t∈[0,m-1]) Assigning the mark matrix F by using a formula (2);
and 1.4, respectively marking the boundary and the interior of the vector element according to the mark matrix F. Creating a matrix a ═ { a (i, j) | i ═ 0. j is 0,.. and n-1, the initial value is 0, and assignment is performed according to a formula (3) to obtain a ternary matrix a, wherein the vector data edge point is identified as 2, the internal point is identified as 1, and the background point is identified as 0. In the present embodiment, the obtained three-value matrix is obtained by enlarging 255/2 times each value of the matrix as a pixel value of an image as necessary for display, as shown in fig. 6.
Step 2, extracting a gray matrix and an edge matrix based on the remote sensing image;
2.1, extracting a gray matrix based on the public remote sensing image, and reading remote sensing image data to a matrix C ═ { C (i, j) | i ═ 0.., p-1; j-0., q-1} which is processed as a gray matrix G ═ { G (i, j) | i ═ 0., p-1; j-0., q-1}, as shown in fig. 7, in the present embodiment, p-612 and q-512;
2.2, smoothing the gray matrix G by using a Gaussian filter;
a) given size (2k +1) × (2k +1) and variance σ are calculated using equation (5) 2 A lower gaussian convolution kernel G '═ { G' (x, y) | x ═ k, · k; y ═ k.., k }, where k is 1 and σ is taken in this example 2 ＝1；
b) Convolving the convolution kernel G' with the remote sensing image gray matrix G to obtain a smoothed image matrix S ═ { S (i, j) | i ═ 0., p-1; j ═ 0.., q-1 };
2.3, calculating the amplitude and the direction of the gradient, and calculating the amplitude and the direction of the gradient of the smoothing matrix S by using the formulas (6), (7) and (8);
and 2.4, carrying out non-maximum suppression on the gradient amplitude. Obtaining a gradient matrix Grad ═ { Grad (i, j) | i ═ 0.., p-1 after the non-maximum value is suppressed according to the formula (9); j ═ 0.., q-1 };
and 2.5, carrying out edge detection and connection according to a double-threshold method. Establishing a high threshold delta Height of 150 and a low threshold δ Is low in 50. The point (i, j) satisfying the condition (10) can be determined as an edge point. Connecting the points to obtain a final edge image matrix E ═ { E (i, j) | i ═ 0., p-1; j-0.., q-1}, as shown in fig. 8.
Step 3, generating a normalized edge registration factor matrix;
3.1, setting the point at the upper left corner of the remote sensing image as an origin, and obtaining a point pair set D { (D) of the deviation of the relative displacement between the point at the upper left corner and the origin of the remote sensing image when the user own vector data is at different positions by using the edge image matrix E and the ternary matrix A x ,d y )|0≤d x ≤p-m-1；0≤d y Q-n-1 is less than or equal to. Calculating a result matrix T ═ { T (i, j) | i ═ 0,.., m-1 corresponding to the deviation (0,0) according to equation (11); j ═ 0., n-1}, some of the elements of which are shown in fig. 9;
3.2, according to the formula (12), calculating the corresponding matrix element sum f to 550;
3.3 result matrix F corresponding to set D Edge ＝{f Edge (x, y) | x ═ 0.., p-m-1; y is 0.
3.4, obtaining an edge registration factor matrix F Edge Normalizing according to a formula (13) to obtain a normalized edge registration factor matrix F' Edge ＝{f' Edge (d x ,d y )|d x ＝0,...,p-m-1；d y 0., q-n-1}, as shown in fig. 10.
Step 4, generating a normalized gray level registration factor matrix;
4.1, calculating a result matrix T '═ { T' (i, j) | i ═ 0, ·, m-1 corresponding to the deviation (0,0) according to the formula (14) by using the grayscale image matrix G and the ternary matrix a; j ═ 0., n-1}, some of the elements of which are shown in fig. 11;
4.2, calculating the variance f' of a nonzero value in the corresponding result matrix according to the formulas (15) and (16) to 1555;
4.3 the variance matrix F corresponding to the set D Ash of ＝{f Ash of (x, y) | x ═ 0.., p-m-1; y is 0, q-n-1, which is the gray scale registration factor matrix.
4.4, obtaining a gray level registration factor matrix F Ash of Normalizing according to the formula (17) to obtain a normalized gray level registration factor matrix F' Ash of ＝{f' Ash of (d x ,d y )|d x ＝0,...,p-m-1；d y Q-n-1, as shown in fig. 12.
Step 5, automatically registering vector data and the remote sensing image based on the characteristic of the registration factor matrix;
5.1, according to the characteristic of the registration factor, the larger the edge registration factor of a deviation position is, and the smaller the gray level registration factor is, the more matched the vector data at the deviation position is with the remote sensing image. Following this principle, a comprehensive registration factor matrix F is created using equation (18) Judgment ＝{f Judgment (d x ,d y )|d x ＝0,...,p-m-1；d y 0, as shown in fig. 13, q-n-1 };
5.2 traversing the matrix F of the discrimination values Judgment And obtaining deviation values (65,47) corresponding to the minimum values. This is the optimal deviation value of the registration of the vector data and the remote sensing image, and the registration result is shown in fig. 14.
And 6, extracting the remote sensing image data in the specified range of the vector elements.
Generating a resultant image matrix R ═ { R (x, y) | x ═ 0.., m-1 according to equation (19); y is 0,., n-1 }. The image corresponding to the matrix (fig. 15) is a remote sensing image corresponding to the vector data element, and the rest is a black background.
According to the embodiment, the method can automatically and accurately extract the remote sensing image data in a certain vector range. Compared with the existing registration method, the method mainly aims at automatic registration between user own vector data and public remote sensing image data, the registration mode using pixel characteristics is convenient and fast, the automation degree is high, and the registration processing requirement of large-batch elements can be met.
In the embodiment, the edge registration factor and the gray level registration factor are selected to perform registration in a manner of equal weight, so that the requirement of extracting the remote sensing image in the range is basically met. The weight setting of the registration factor is different for different kinds of vector data. If the vector data represents large and homogeneous natural ground objects such as forests, lakes and the like, the gray level registration factor should account for a larger proportion; whereas the edge registration factor should be a greater weight if it represents artificial features such as residential areas that are not homogenous but have sharp boundaries.
Claims (7)
1. An automatic registration method of vector data and remote sensing images is characterized in that: the method comprises the following steps:
step 1, extracting a ternary matrix A by using a scanning line algorithm based on vector data;
step 2, extracting a gray matrix G based on the remote sensing image, and obtaining an edge matrix E of the gray matrix G by using a Canny operator;
step 3, traversing the three-value matrix A by using the edge matrix E to generate a normalized edge registration factor matrix F' Edge ；
Step 4, traversing the three-value matrix A by using the gray-scale matrix G to generate a normalized gray-scale registration factor matrix F' Ash of ；
Step 5, automatically registering the vector data and the remote sensing image based on the characteristics of the registration factor;
And 6, extracting the remote sensing image data in the specified range of the vector elements.
2. The automatic registration method of vector data and remote sensing images according to claim 1, characterized in that: the step 1 specifically comprises:
1.1, extracting a minimum outsourcing rectangle of the vector data, and converting the minimum outsourcing rectangle into a binary grid matrix Y ═ { Y (i, j) | i ═ 0, ·, m-1 according to a formula (1); j is 0, a., n-1, wherein m is the height of the vector data outsourcing rectangle, and n is the width of the vector data outsourcing rectangle;
1.2, creating a boolean flag matrix F ═ { F (i, j) | i ═ 0. j ═ 0.., n-1} determines whether or not the vector element edge is present;
1.3 scanning the line L for each row t ＝{(t,j)|j＝0,...,n-1}(t∈[0,m-1]) Assigning the mark matrix F by using a formula (2);
1.4, respectively marking the boundary and the interior of the vector element according to the mark matrix F; creating a matrix a ═ { a (i, j) | i ═ 0. j is 0, the.. and n-1, the initial default value is 0, and assignment is performed according to a formula (3) to obtain an assigned ternary matrix A, wherein the edge point identifier of the vector data is 2, the internal point identifier is 1, and the background point identifier is 0;
3. the automatic registration method of vector data and remote sensing images according to claim 2, characterized in that: the step 2 specifically comprises:
2.1, extracting a gray matrix based on the public remote sensing image: reading remote sensing image data to a matrix C (C (i, j) | i ═ 0., p-1; j-0., q-1} which is processed as a gray matrix G ═ { G (i, j) | i ═ 0., p-1; j ═ 0.., q-1 };
g(i,j)＝0.299*c r (i,j)+0.587*c g (i,j)+0.114*c b (i,j) (4)
wherein, p is the height of the remote sensing image data, q is the width of the remote sensing image data, and the conditions (p > m) and (q > n) are satisfied; c. C r (i,j)、c g (i,j)、c b (i, j) respectively represents R, G, B values of the remote sensing image C at the point (i, j);
2.2, smoothing the gray matrix G by using a Gaussian filter;
a) calculating the user given size (2k +1) × (2k +1) and the variance σ using equation (5) 2 A lower gaussian convolution kernel G '═ { G' (x, y) | x ═ k, · k; y ═ k,.., k };
b) convolving the convolution kernel G' with the remote sensing image gray matrix G to obtain a smoothed image matrix S ═ { S (i, j) | i ═ 0., p-1; j ═ 0.., q-1 };
2.3, calculating the amplitude and the direction of the gradient; calculating the amplitude and the direction of the gradient of the smoothing matrix S by using the formulas (6), (7) and (8);
θ(i,j)＝arctan(P x (i,j)/P y (i,j)) (8)
wherein P is x ，P y Gradient operators, P, in the x, y directions of the image, respectively x (i,j)，P y (i, j) is the product of the gradient operator at point (i, j) and the smoothing matrix, arctan represents the tangent function, M (i, j) is the magnitude of the smoothing matrix S at (i, j), θ (i, j) is the direction of the smoothing matrix S at (i, j);
2.4, carrying out non-maximum suppression on the gradient amplitude: obtaining a gradient matrix Grad ═ { Grad (i, j) | i ═ 0.., p-1 after the non-maximum value is suppressed according to the formula (9); j ═ 0.., q-1 };
wherein M is Front side Representing the magnitude of the gradient, M, at a point preceding point (i, j) in the direction of the gradient Rear end Represents the gradient magnitude of a point subsequent to the point (i, j) in the gradient direction;
2.5, carrying out edge detection and connection according to a double-threshold method: establishing a high threshold delta Height of And a low threshold delta Is low in Points (i, j) satisfying the condition (10) can be determined as edge points, and the points are connected to obtain a final edge image matrix E ═ { E (i, j) | i ═ 0. j ═ 0.., q-1 };
g(i,j)＞δ height of or(g(i,j)＜δ Height of and g(i,j)＞δ Is low in and flag(i,j)＝true) (10)
4. The automatic registration method of vector data and remote sensing images according to claim 3, characterized in that: the step 3 specifically includes:
3.1, setting the point at the upper left corner of the remote sensing image as an origin, and obtaining a point pair set D { (D) of the relative displacement deviation between the point at the upper left corner and the origin of the remote sensing image when the user own vector data are at different positions by using the edge image matrix E and the ternary matrix A x ,d y )|0≤d x ≤p-m-1；0≤d y Q-n-1 ≦ q, any deviation (D) in the set D is calculated according to equation (11) x ,d y ) Corresponding result matrix 
3.2, calculating the sum f of elements in the result matrix T corresponding to the deviation according to the formula (12);
3.3 element corresponding to each element in the set D and the resulting matrix F formed Edge ＝{f Edge (x, y) | x ═ 0.., p-m-1; y is 0,., q-n-1, which is the edge registration factor matrix;
3.4, obtaining an edge registration factor matrix F Edge Normalizing according to a formula (13) to obtain a normalized edge registration factor matrix F' Edge ＝{f' Edge (d x ,d y )|d x ＝0,...,p-m-1；d y ＝0,...,q-n-1}；
Wherein f is Side max Representing the maximum value of the edge registration factor matrix, f While min Represents the minimum of the edge registration factor matrix.
5. The automatic registration method of vector data and remote sensing images according to claim 4, characterized in that: the step 4 specifically includes:
4.1 Using the grayscale image matrix G and the ternary matrix A, any deviation { (D) in the set D x ,d y ) A corresponding result matrix T '═ { T' (i, j) | i ═ 0., m-1 is calculated according to formula (14); j ═ 0.., n-1 };
4.2, calculating the variance f' of the non-zero value in the corresponding result matrix according to the formulas (15) and (16);
wherein R is the number of non-zero values in the result matrix T';
4.3 result matrix F consisting of variances corresponding to elements in set D Ash of ＝{f Ash of (x, y) | x ═ 0.., p-m-1; y is 0, the q-n-1 is a gray level registration factor matrix;
4.4, obtaining a gray level registration factor matrix F Ash of Normalizing according to the formula (17) to obtain a normalized gray level registration factor matrix F' Ash of ＝{f' Ash of (d x ,d y )|d x ＝0,...,p-m-1；d y ＝0,...,q-n-1}；
Wherein f is Ash max Representing the maximum value of the gray scale registration factor matrix, f Lime min Representing the minimum value of the gray scale registration factor matrix.
6. The automatic registration method of vector data and remote sensing images according to claim 5, characterized in that: the step 5 specifically includes:
5.1, according to the characteristic of the registration factor, if the edge registration factor of a deviation position is larger and the gray level registration factor is smaller, the vector data at the deviation position is matched with the remote sensing image more, and the comprehensive registration factor matrix F is created by using a formula (18) according to the principle Judgment ＝{f Judgment (i,j)|i＝0,...,p-m-1；j＝0,...,q-n-1}；
5.2 traversing the discriminating momentArray F Judgment Obtaining the deviation value (i) corresponding to the minimum value 0 ,j 0 ) And the vector data is the optimal deviation value of the registration of the vector data and the remote sensing image.
7. The automatic registration method of vector data and remote sensing images according to claim 6, characterized in that: the step 6 specifically includes:
generating a result matrix R ═ { R (x, y) | x ═ 0., m-1 according to equation (19); y is 0,., n-1 }; the image corresponding to the matrix is a remote sensing image in a vector data element or element set range, and the rest part is a black background;
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2018105622875 | 2018-06-04 | ||
| CN201810562287 | 2018-06-04 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109727279A CN109727279A (en) | 2019-05-07 |
| CN109727279B true CN109727279B (en) | 2022-07-29 |
Family
ID=66301207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910083298.XA Active CN109727279B (en) | 2018-06-04 | 2019-01-28 | Automatic registration method of vector data and remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109727279B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378316B (en) * | 2019-07-29 | 2023-06-27 | 苏州中科天启遥感科技有限公司 | Method and system for extracting ground object identification sample of remote sensing image |
| CN111696121A (en) * | 2020-06-05 | 2020-09-22 | 中国人民解放军火箭军工程设计研究院 | Planar water area extraction method and system |
| CN112950680B (en) * | 2021-02-20 | 2022-07-05 | 哈尔滨学院 | Satellite remote sensing image registration method |
| CN114897659B (en) * | 2022-05-09 | 2023-12-29 | 南京师范大学 | Vector geographic data zero watermark generation method and zero watermark information detection method |
| CN115830087B (en) * | 2022-12-09 | 2024-02-20 | 陕西航天技术应用研究院有限公司 | Batch rapid registration method for translational motion continuous frame image set |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040052409A1 (en) * | 2002-09-17 | 2004-03-18 | Ravi Bansal | Integrated image registration for cardiac magnetic resonance perfusion data |
| CN101957991A (en) * | 2010-09-17 | 2011-01-26 | 中国科学院上海技术物理研究所 | Remote sensing image registration method |
| CN102842137A (en) * | 2012-08-14 | 2012-12-26 | 中山大学 | Automatic registration method for multi-temporal empty spectrum remote sensing image based on space comprehensive mutual information |
| CN104167003A (en) * | 2014-08-29 | 2014-11-26 | 福州大学 | Method for fast registering remote-sensing image |
| CN105654423A (en) * | 2015-12-28 | 2016-06-08 | 西安电子科技大学 | Area-based remote sensing image registration method |
| CN107301661A (en) * | 2017-07-10 | 2017-10-27 | 中国科学院遥感与数字地球研究所 | High-resolution remote sensing image method for registering based on edge point feature |
-
2019
- 2019-01-28 CN CN201910083298.XA patent/CN109727279B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040052409A1 (en) * | 2002-09-17 | 2004-03-18 | Ravi Bansal | Integrated image registration for cardiac magnetic resonance perfusion data |
| CN101957991A (en) * | 2010-09-17 | 2011-01-26 | 中国科学院上海技术物理研究所 | Remote sensing image registration method |
| CN102842137A (en) * | 2012-08-14 | 2012-12-26 | 中山大学 | Automatic registration method for multi-temporal empty spectrum remote sensing image based on space comprehensive mutual information |
| CN104167003A (en) * | 2014-08-29 | 2014-11-26 | 福州大学 | Method for fast registering remote-sensing image |
| CN105654423A (en) * | 2015-12-28 | 2016-06-08 | 西安电子科技大学 | Area-based remote sensing image registration method |
| CN107301661A (en) * | 2017-07-10 | 2017-10-27 | 中国科学院遥感与数字地球研究所 | High-resolution remote sensing image method for registering based on edge point feature |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109727279A (en) | 2019-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109727279B (en) | Automatic registration method of vector data and remote sensing image | |
| CN107424142B (en) | Weld joint identification method based on image significance detection | |
| CN111179152B (en) | Road identification recognition method and device, medium and terminal | |
| Palenichka et al. | Automatic extraction of control points for the registration of optical satellite and LiDAR images | |
| CN104200461A (en) | Mutual information image selected block and sift (scale-invariant feature transform) characteristic based remote sensing image registration method | |
| CN107967482A (en) | Icon-based programming method and device | |
| CN104700071B (en) | A kind of extracting method of panorama sketch road profile | |
| CN109635733B (en) | Parking lot and vehicle target detection method based on visual saliency and queue correction | |
| CN107862319B (en) | Heterogeneous high-light optical image matching error eliminating method based on neighborhood voting | |
| CN113392856B (en) | Image forgery detection device and method | |
| JP6188052B2 (en) | Information system and server | |
| CN102903109A (en) | Integrated partition registering method of optical image and synthetic aperture radar (SAR) image | |
| Gonçalves et al. | CHAIR: Automatic image registration based on correlation and Hough transform | |
| CN109961065B (en) | Sea surface ship target detection method | |
| CN105809673A (en) | SURF (Speeded-Up Robust Features) algorithm and maximal similarity region merging based video foreground segmentation method | |
| Liu et al. | Object-oriented detection of building shadow in TripleSat-2 remote sensing imagery | |
| CN114387329A (en) | Building contour progressive regularization method based on high-resolution remote sensing image | |
| Hong et al. | The image registration technique for high resolution remote sensing image in hilly area | |
| Poornima et al. | A method to align images using image segmentation | |
| CN112669360B (en) | Multi-source image registration method based on non-closed multi-dimensional contour feature sequence | |
| CN114926635A (en) | Method for segmenting target in multi-focus image combined with deep learning method | |
| CN114299247A (en) | Rapid detection and problem troubleshooting method for road traffic sign lines | |
| CN107480648A (en) | A kind of method of natural scene text detection | |
| Zhou et al. | Road detection based on edge feature with GAC model in aerial image | |
| Deb et al. | Optical Recognition of Vehicle license plates |
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 |