CN106683102B

CN106683102B - SAR image segmentation method based on ridge ripple filter and convolutional coding structure learning model

Info

Publication number: CN106683102B
Application number: CN201611260197.8A
Authority: CN
Inventors: 刘芳; 李婷婷; 赵鹏; 焦李成; 郝红侠; 陈璞华; 马文萍; 马晶晶
Original assignee: Xidian University
Current assignee: Xidian University
Priority date: 2016-12-30
Filing date: 2016-12-30
Publication date: 2019-07-23
Anticipated expiration: 2036-12-30
Also published as: CN106683102A

Abstract

The SAR image segmentation method based on ridge ripple filter and convolutional coding structure model that the invention discloses a kind of.Mainly solve the problems, such as prior art segmentation SAR image inaccuracy.Implementation step are as follows: (1) SAR image sketch obtains sketch map；(2) according to the administrative division map of SAR image, the pixel subspace of SAR image is divided；(3) ridge ripple filter set is constructed；(4) convolutional coding structure learning model is constructed；(5) SAR image segmentation method based on ridge ripple filter and convolutional coding structure model, segmentation mixing aggregated structure atural object pixel subspace are used；(6) gather the pinpoint target segmentation of feature based on sketch line；(7) the line target segmentation of view-based access control model semantic rules；(8) homogenous region pixel subspace is split using based on multinomial logistic regression prior model；(9) combination and segmentation result.Present invention obtains the good segmentation effects of SAR image, can be used for the semantic segmentation of SAR image.

Description

SAR image segmentation method based on ridge ripple filter and convolutional coding structure learning model

Technical field

The invention belongs to technical field of image processing, further relate to one of target identification technology field and are based on ridge Synthetic aperture radar SAR (Synthetic Aperture Radar) image segmentation of wave filter and convolutional coding structure learning model Method.The present invention can have the mixing aggregated structure atural object pixel subspace of different characteristic to synthetic aperture radar SAR image It is accurately split, and can be used for the object detection and recognition of subsequent synthetic aperture radar SAR image.

Background technique

Synthetic aperture radar SAR is the impressive progress in remote sensing technology field, for obtaining the full resolution pricture of earth surface. Compared with other kinds of imaging technique, SAR has round-the-clock, round-the-clock, multiband, multipolarization, variable side view angle and height The advantages that resolution ratio, not only can in detail, accurately survey and draw landform, landforms, obtain the information of earth surface, can also be through ground Table and natural vegetation collect subsurface information, or even also can provide detailed ground under rugged environment with higher resolution ratio and survey Draw data and image.SAR technology has great importance for many fields such as military affairs, agricultural, geography.Image segmentation refers to The process in several mutually disjoint regions is divided an image into according to color, gray scale and Texture eigenvalue.Pass through computer pair It is the huge challenge faced at present that SAR image, which is interpreted, and SAR image segmentation is its steps necessary, it is into one Detection, the identification of step influence very big.

The common method of image segmentation has at present: the method based on edge detection, the method based on threshold value are based on region life Long and watershed method and the method based on cluster etc..Due to the unique imaging mechanism of SAR, containing there are many phases in SAR image Dry spot noise causes the conventional method of many optical imagerys all to cannot be directly used to the segmentation of SAR image.The tradition of SAR image Dividing method includes some methods based on cluster such as Kmeans, FCM and some other has supervision and semi-supervised side Method.They generally require manually experience and carry out feature extraction, however the quality for the feature extracted is for the segmentation knot of SAR image Fruit has key effect.For having supervision and semi-supervised method, label data is needed, the label data of SAR image is seldom, The cost for obtaining label data is very high.

Paper that the Zhong Weiyu and Shen Ting of Center for Earth Observation and Digital Earth Chinese Academy of Sciences are delivered at it " in conjunction with One kind is proposed in the SAR image of multiple features and SVM segmentation " (" computer application research ", 2013,30 (9): 2846-2851.) SAR image segmentation is carried out in conjunction with the texture characteristic extracting method of non-down sampling profile transformation (NSCT) and GLCM.This method is It realizes that gray level co-occurrence matrixes (GLCM) multiple dimensioned, multidirectional texture feature extraction, proposes a kind of combination non-down sampling profile Convert the texture characteristic extracting method of (NSCT) and GLCM.First with NSCT to synthetic aperture radar (SAR) SAR) image carry out it is multiple dimensioned, Multi-direction decomposition；Gray scale symbiosis amount is extracted using GLCM to obtained sub-band images again；Then to the gray scale symbiosis amount of extraction into Row correlation analysis removes redundancy feature amount, and it is constituted multiple features vector with gray feature；Finally, making full use of support Advantage of the vector machine (SVM) in terms of Small Sample Database library and generalization ability is completed the division of multiple features vector by SVM, is realized SAR image segmentation.But the shortcoming that this method still has is, does not introduce the high-level semantic knowledge of SAR image, only SAR image is divided in pixel scale, results in SAR image segmentation result inaccuracy, meanwhile, support vector machines is to have The method of supervision, needs category.

A kind of patent " specific objective contour images based on depth convolutional neural networks of the North China Electric Power University in its application It is disclosed in dividing method " (number of patent application CN201610109536.6, publication number CN105787482A) a kind of based on depth The image partition method of the specific objective profile of convolutional neural networks.It is big that training image is normalized to same pixel by this method It is small, obtained training image is input in a convolutional neural networks, by several layers of convolutional layer and full articulamentum, is being connected entirely The last layer of layer obtains image expression, and is compared to obtain prediction error with corresponding mark image.Using backpropagation Algorithm and stochastic gradient descent method reduce prediction error with the training neural network, obtain the segmentation of specific objective contour images Training pattern.Although this method has achieved the purpose that autonomous learning characteristics of image, still, the deficiency that this method still has Place is that input picture has been carried out normalized, just destroyed the original of image in this way by the method for the convenience handled Structural information.Meanwhile the method also marks image, is divided into training sample and test sample, to reach trained volume The purpose of product network.There is the processing mode of supervision to substantially increase the complexity of dividing method in this way.

Xian Electronics Science and Technology University " encodes the SAR image segmentation side with administrative division map based on depth in the patent of its application certainly Disclosed in method " (number of patent application 201410751944.2, publication number CN104392456 A) it is a kind of based on depth from coding and The SAR image segmentation method of administrative division map.The region that this method is divided according to the sketch map of synthetic aperture radar SAR image Figure, by administrative division map be mapped to original image assembled, homogeneous and structural region；Respectively to aggregation, the different depth in homogenous region Self-encoding encoder training, obtains the feature of aggregation and each point in homogenous region；Dictionary, each point are constructed to aggregation and homogenous region respectively The provincial characteristics for projecting to corresponding dictionary and converging out all subregion, respectively clusters the sub-district characteristic of field in two class regions； Structural region is split under the guidance of sketch line segment using super-pixel merging；Merge each region segmentation result and completes SAR figure As segmentation.Shortcoming existing for this method is that the input of the depth self-encoding encoder for automatically extracting characteristics of image used is one Dimensional vector, can destroy the spatial structure characteristic of image, it is thus impossible to extract the substantive characteristics of image, reduce SAR image segmentation Precision.

Liu Fang, Duan Yiping, Li Lingling, burnt Lee " are based on the semantic and adaptive neighbour of level vision in its paper delivered at equal The SAR image of the hidden model of domain multinomial is divided " (IEEE Trancactions on Geoscience and Remote Sensing, 2016,54 (7): 4287-4301.) in propose it is a kind of based on level vision semanteme and adaptive neighborhood multinomial The SAR image segmentation method of hidden model, this method go out SAR image according to the sketch model extraction of synthetic aperture radar SAR image Sketch map the administrative division map of SAR image is obtained using sketch line fields method, and administrative division map is mapped in SAR image, Synthetic aperture SAR image is finally divided into aggregation zone, homogenous region and structural region.Based on the division, to different characteristics Region use different dividing methods.For aggregation zone, it is extracted gray level co-occurrence matrixes feature, and uses local linear The method of constraint coding obtains the expression of each aggregation zone, and then is split using the method for hierarchical clustering.To structural area Domain devises vision semantic rules positioning boundary and line target by analysis side mode type and line model.In addition, boundary and line mesh Mark contains strong directional information, therefore devises the hidden model of multinomial based on geometry window and be split.To homogeneous Region, in order to find appropriate neighborhood go indicate center pixel, devise the hidden model of multinomial based on self-adapting window into Row segmentation.The segmenting structure in these three regions be integrated into together segmentation result to the end.The shortcoming of this method is, It is inaccurate to aggregation zone positioning, not reasonable, the region consistency of segmentation result is determined for the classification number of homogenous region It is poor, and pinpoint target is not handled in the segmentation result of structural region.

Summary of the invention

It is an object of the invention to be directed to the deficiency of above-mentioned prior art, propose a kind of based on ridge ripple filter and convolution knot The SAR image segmentation method of structure learning model is desirably to obtain the knot that can characterize SAR image mixing aggregated structure atural object subspace Structure feature, preferably to be divided to spatially disconnected multiple mixing aggregated structure atural objects subspace.

To achieve the above object, the specific steps of the present invention are as follows:

(1) SAR image sketch:

(1a) obtains its sketch model according to the characteristic distributions of SAR image to the synthetic aperture radar SAR image of input；

(1b) utilizes SAR image sketch model, carries out sketch processing to the synthetic aperture radar SAR image of input, obtains The corresponding sketch map of synthetic aperture radar SAR image that must be inputted；

(2) pixel subspace is divided:

(2a) uses sketch line fields method, carries out compartmentalization processing to the sketch map of synthetic aperture radar SAR image, Obtain include aggregation zone, synthetic aperture radar SAR image without sketch line region and structural region administrative division map；

(2b) will include aggregation zone, the administrative division map without sketch line region and structural region, be mapped to the synthesis hole of input In diameter radar SAR image, mixing aggregated structure atural object pixel subspace, the homogeneous area in synthetic aperture radar SAR image are obtained Domain pixel subspace and structure-pixel subspace；

(3) ridge ripple filter set is constructed:

It is corresponding that (3a) extracts mixing aggregated structure atural object pixel subspace from the administrative division map of synthetic aperture radar SAR image Aggregation zone, [0⁰, 180⁰] 10 are divided into in section⁰18 sections i.e. 18 directions are divided into, count each area respectively The item number of sketch line segment in the interior aggregation zone；

(3b) arranges sketch line segment all in the aggregation zone according to the number of the line segment item number in each interval Sequence obtains the collating sequence in direction, using the degree in 6 directions preceding in the collating sequence in direction as ridge ripple filter in Directioin parameter；

(3c) according to the following formula, the ridge ripple function of 9 × 9 ridge ripple filter is calculated according to parameter a, θ and b:

Y=a × (y₁×cosθ+y₂×sinθ-b)

Wherein, Y indicates that the ridge ripple function of ridge ripple filter, a indicate the scale parameter of ridge ripple filter, the value range of a For [0,3], the discrete interval of a is 0.2, y₁Indicate the abscissa positions of ridge ripple filter pixel, y₁Value range be [0, 8], y₁Discrete interval be 1, cos indicate cosine operation, θ indicate ridge ripple filter directioin parameter, y₂Indicate ridge ripple filter The ordinate position of pixel, y₂Value range be [0,8], y₂Discrete interval be 1, sin indicate sinusoidal operation；B indicates ridge The displacement parameter of wave filter, when directioin parameter θ is [0⁰,90⁰) when, b is divided into the section [0,9 × (sin θ+cos θ)] with 0.2 carries out discretization, when directioin parameter θ is [90⁰,180⁰) when, b is divided into 0.2 in [9 × cos θ, 9 × sin θ] section with Carry out discretization；

(3d) according to the following formula, calculates each ridge ripple wave filter:

Wherein, c (Y) indicates that the ridge ripple filter using ridge ripple function Y as parameter, K indicate ridge ripple filter frobenius The inverse of norm, exp are indicated using natural constant e as the index operation at bottom；

Each the ridge ripple filter bank being calculated is become ridge ripple filter set by (3e)；

(4) convolutional coding structure learning model is constructed:

(4a) is not connected to each of the mixing aggregated structure atural object pixel subspace in synthetic aperture radar SAR image mutually Region, by 31 × 31 window carry out every a sliding window sample, the corresponding multiple images block in each region is obtained, by multiple images Block is sequentially inputted in convolutional coding structure learning model, obtains the input layer of convolutional coding structure learning model；

(4b) uses ridge ripple filter, carries out convolution operation to the image block in the input layer of convolutional coding structure learning model, Obtain the convolutional layer of convolutional coding structure learning model；

(4c) according to the following formula, calculates data fidelity term:

Wherein, E (c) indicates data fidelity term, and c indicates the ridge ripple filter in convolutional coding structure learning model convolutional layer, ∑ Indicating sum operation, N indicates each of to be learnt the total number for the image block that mutually disconnected region includes, | | | |_FIt indicates The operation of frobenius norm is done,Indicate the square operation of frobenius norm, x_iIndicate convolutional coding structure study mould to be constructed I-th of the image block inputted in type,It indicates to extract x_iIntermediate size is the characteristic image block of n × n, M_iIndicate volume to be constructed The sum of the corresponding ridge ripple filter of i-th of image block inputted in product Structure learning model, * indicate convolution operation,It indicates Corresponding j-th of ridge ripple filter of i-th of the image block inputted in convolutional coding structure learning model to be constructed；

(4d) according to the following formula, calculates structure fidelity term:

Wherein, G (c) indicates structure fidelity term, and R () indicates to ask the operation of all sketch line total lengths in sketch map, SM () indicates to extract the operation with the one-to-one sketch segment of input picture block；

(4e) according to the following formula, calculating target function:

Wherein, L (c) indicates objective function,It indicates in objective function L (c) value minimum, seeks ridge ripple filter The operation of c；

(4f) exports the ridge ripple filter obtained by objective function guidance learning, obtains the output layer of convolutional coding structure model；

(5) training convolutional Structure learning model:

(5a) sets 0.1 for structural failure threshold value；

Step (4a) sampling is obtained image block and is sequentially inputted in convolutional coding structure learning model by (5b)；

(5c) randomly selects six filters, directioin parameter is by statistics in step (3b) from ridge ripple filter set 6 directions obtain, displacement parameter and scale parameter random initializtion, the filter that these initial six filters are formed Set is as selected ridge ripple filter set；

(5d) carries out each ridge ripple filter in image block currently entered and selected ridge ripple filter set Convolution operation obtains characteristic pattern corresponding with each ridge ripple filter；

(5e) utilizes the structure fidelity term formula in step (4d), the structure fidelity term of calculating input image block；

(5f) judges whether the structure fidelity term of current input image block is less than structural failure threshold value, if so, executing step Suddenly (5i) is otherwise executed step (5g)；

(5g) utilizes scale parameter more new formula and displacement parameter more new formula, updates step (4c) data fidelity term respectively The scale parameter and displacement parameter of formula median ridge wave filter obtain updated ridge ripple filter；

(5h) using updated ridge ripple filter set as selected ridge ripple filter set, return step (5d), Training is re-started to input picture block；

(5i) saves the ridge ripple filter that study obtains in the ridge ripple filter set succeeded in school to the input picture block, The study to the input picture block feature is completed, and exports the ridge ripple filter set that the input picture block succeeds in school；

(5j) judges whether all image blocks pass through the study that convolutional coding structure learning model completes feature, if so, terminating Otherwise program inputs next image block and executes step (5c)；

(6) segmentation SAR image mixes aggregated structure atural object pixel subspace:

The ridge ripple filter sets that disconnected regional learning obtains all mutually are spliced into code book by (6a)；

All ridge ripple filters in the ridge ripple filter set that (6b) obtains mutual disconnected regional learning, to code book It is projected, obtains structural eigenvector；

(6c) carries out maximum pond to the structural eigenvector in each mutually disconnected region, obtains all spies in each region Levy the structural eigenvector on code book；

(6d) propagates AP clustering algorithm using neighbour, clusters to structural eigenvector, obtains and structural eigenvector The segmentation result of corresponding mixing aggregated structure atural object pixel subspace；

(7) segmenting structure pixel subspace:

(7a) uses vision semantic rules, divides line target；

The feature of gathering of (7b) based on sketch line divides pinpoint target；

The result that (7c) divides line target and pinpoint target merges, and obtains the segmentation knot of structure-pixel subspace Fruit；

(8) divide homogenous region pixel subspace:

Using the homogenous region dividing method based on multinomial logistic regression prior model, to homogenous region pixel subspace It is split, obtains the segmentation result of homogenous region pixel subspace；

(9) combination and segmentation result:

The segmentation result of aggregated structure pixel subspace, homogenous region pixel subspace and structure-pixel subspace will be mixed Merge, obtains the final segmentation result of synthetic aperture radar SAR image.

The invention has the following advantages over the prior art:

First, the present invention is closed using the sketch map of synthetic aperture radar SAR image using sketch line fields method At the administrative division map of aperture radar SAR image, administrative division map is mapped to the synthetic aperture radar SAR image of input, obtains synthesis hole Mixing aggregated structure atural object pixel subspace, homogenous region pixel subspace and structure-pixel in diameter radar SAR image is empty Between, sampling and feature learning are carried out in the pixel subspace of mixing aggregated structure atural object, are not needed category, are overcome existing skill Input picture is denoted as training image when learning characteristics of image and marks the deficiency of image by art, is not required to so that the present invention has The advantages of indicating to input picture, and reducing convolutional coding structure learning model complexity, improves convolutional coding structure study The training speed of model, simultaneously as to input picture carry out mark be it is manually-operated, exist must error, and this hair It is bright not need to indicate, improve the accuracy of final segmentation result.

Second, the present invention is to each of the mixing aggregated structure atural object pixel subspace in synthetic aperture radar SAR image Mutual disconnected region sample every a sliding window by 31 × 31 window, obtains multiple images block, and obtained image block is defeated Enter into convolutional coding structure learning model, does not need that the synthetic aperture radar SAR image of input is normalized, overcome The prior art need that synthetic aperture radar SAR image is normalized before input and deficiency so that the present invention have There is prototype structure information that can directly using the image block obtained after sampling as input, without destroying input picture block Advantage.

Third, the present invention is to each of the mixing aggregated structure atural object pixel subspace in synthetic aperture radar SAR image Mutual disconnected region sample every a sliding window by 31 × 31 window, obtains multiple images block, and obtained image block is defeated Enter into convolutional coding structure learning model, overcomes the defeated of the depth self-encoding encoder for automatically extracting characteristics of image used in the prior art Enter for one-dimensional vector, the deficiency of the spatial structure characteristic of image can be destroyed, so that the present invention has the essence that can extract image The advantages of feature, the precision of promotion synthetic aperture radar SAR image segmentation.

Detailed description of the invention

Fig. 1 is flow chart of the present invention；

Fig. 2 is analogous diagram of the invention；

Fig. 3 is emulation experiment intermediate result figure of the present invention；

Fig. 4 is simulation result schematic diagram of the present invention；

Specific embodiment

The present invention will be further described below with reference to the accompanying drawings.

Referring to attached drawing 1, the specific steps of the present invention are as follows.

Step 1, SAR image sketch.

To the synthetic aperture radar SAR image of input, its sketch model is obtained according to the characteristic distributions of SAR image.

According to the following steps, using SAR image sketch model, sketch is carried out to the synthetic aperture radar SAR image of input Change processing, obtains the corresponding sketch map of synthetic aperture radar SAR image of input:

Step 1 arbitrarily chooses a number, the sum as template in [100,150] range；

Step 2 constructs a template on the side being made of pixel with different directions and scale, line, utilizes template Direction and dimensional information structural anisotropy's Gaussian function, by the Gaussian function, in calculation template each pixel plus Weight coefficient, the weighting coefficient of all pixels point in statistical mask, wherein scale number value is 3~5, and direction number value is 18；

Step 3 calculates pixel in synthetic aperture radar SAR image corresponding with template area coordinate according to the following formula Mean value:

Wherein, μ indicates the equal of all pixels point in corresponding with template area coordinate synthetic aperture radar SAR image Value, ∑ indicate sum operation, and g indicates the corresponding coordinate of any one pixel in the Ω region of template, and ∈ expression belongs to symbol Number, indicate weight coefficient of the pixel at coordinate g in the Ω region of template, w_gValue range be w_g∈ [0,1], A_gTable Show the value of the pixel with pixel in the Ω region of template at the coordinate g in corresponding synthetic aperture radar SAR image；

Step 4 calculates pixel in synthetic aperture radar SAR image corresponding with template area coordinate according to the following formula Variance yields:

Wherein, ν indicates the variance of all pixels point in synthetic aperture radar SAR image corresponding with template area coordinate Value；

Step 5 calculates the response that each pixel in synthetic aperture radar SAR image is directed to ratio operator according to the following formula Value:

Wherein, R indicates response of each pixel for ratio operator, min { } in synthetic aperture radar SAR image Indicate minimum Value Operations, a and b respectively indicate two different regions in template, μ_aIndicate all pixels point in a of template area Mean value, μ_bIndicate the mean value of all pixels point in the b of template area；

Step 6 calculates the response that each pixel in synthetic aperture radar SAR image is directed to correlation operator according to the following formula Value:

Wherein, C indicate synthetic aperture radar SAR image in each pixel be directed to correlation operator response,It indicates Square root functions, a and b respectively indicate two different zones, ν in template_aIndicate the variance of all pixels point in a of template area Value, ν_bIndicate the variance yields of all pixels point in the b of template area, μ_aIndicate the mean value of all pixels point in a of template area, μ_bTable Show the mean value of all pixels point in the b of template area；

Step 7 calculates the response that each pixel in synthetic aperture radar SAR image is directed to each template according to the following formula Value:

Wherein, F indicate synthetic aperture radar SAR image in each pixel be directed to each template response,It indicates Square root functions, R and C respectively indicate pixel in synthetic aperture radar SAR image and are directed to ratio operator and synthetic aperture radar Pixel is directed to the response of correlation operator in SAR image；

Step 8, judges whether constructed template is equal to the sum of selected template, if so, step 2 is executed, otherwise, Execute step 9；

Step 9, selection has the template of maximum response from each template, as synthetic aperture radar SAR image Template, and using the maximum response of the template as the intensity of pixel in synthetic aperture radar SAR image, by the side of the template The direction of pixel in as synthetic aperture radar SAR image, obtain synthetic aperture radar SAR image sideline response diagram and Gradient map；

Step 10 calculates the intensity value of synthetic aperture radar SAR image intensity map, obtains intensity map according to the following formula:

Wherein, I indicates that the intensity value of synthetic aperture radar SAR image intensity map, x indicate synthetic aperture radar SAR image Value in the response diagram of sideline, y indicate the value in synthetic aperture radar SAR image gradient map；

Step 11 detects intensity map using non-maxima suppression method, obtains suggestion sketch；

Step 12, choose suggest sketch in maximum intensity pixel, will suggest sketch in the maximum intensity The pixel of pixel connection connects to form suggestion line segment, obtains suggestion sketch map；

Step 13 calculates the code length gain for suggesting sketch line in sketch map according to the following formula:

Wherein, CLG indicates to suggest the code length gain of sketch line in sketch map, and ∑ indicates sum operation, and J indicates current The number of pixel, A in sketch line neighborhood_jIndicate the observation of j-th of pixel in current sketch line neighborhood, A_j,0It indicates In the case that current sketch line cannot indicate structural information, the estimated value of j-th of pixel, ln () table in the sketch line neighborhood Show the log operations using e the bottom of as, A_j,1Indicate the sketch line neighborhood in the case where current sketch line can indicate structural information In j-th of pixel estimated value；

Step 14 arbitrarily chooses a number, as threshold value T in [5,50] range；

Step 15 selects the suggestion sketch line of CLG > T in all suggestion sketch lines, is combined into synthetic aperture radar The sketch map of SAR image.

The synthetic aperture radar SAR image sketch model that the present invention uses is that Jie-Wu et al. in 2014 was published in IEEE Article " Local maximal on Transactions on Geoscience and Remote Sensing magazine homogenous region search for SAR speckle reduction with sketch-based Geometrical kernel function " proposed in model.

Step 2, pixel subspace is divided.

Using sketch line fields method, compartmentalization processing is carried out to the sketch map of synthetic aperture radar SAR image, is obtained The administrative division map of synthetic aperture radar SAR image including aggregation zone, without sketch line region and structural region.

According to the concentration class of sketch line segment in the sketch map of synthetic aperture radar SAR image, sketch line is divided into expression Assemble the aggregation sketch line of atural object and indicates boundary, line target, the boundary sketch line of isolated target, line target sketch line, isolates Target sketch line.

According to the statistics with histogram of sketch line segment concentration class, the sketch line segment conduct that concentration class is equal to optimal concentration class is chosen Seed line-segment sets { E_k, k=1,2 ..., m }, wherein E_kIndicate that any bar sketch line segment in seed line-segment sets, k indicate seed The label of any bar sketch line segment in line-segment sets, m indicate the total number of seed line segment, and { } indicates set operation.

As basic point with the unselected line segment for being added to seed line-segment sets sum, with this basic point recursive resolve line segment aggregate.

The round primitive that a radius is the optimal concentration class section upper bound is constructed, with the circle primitive in line segment aggregate Line segment is expanded, and is corroded to the line segment aggregate ecto-entad after expansion, is obtained as unit of sketch point in sketch map Aggregation zone.

To the sketch line for indicating boundary, line target and isolated target, centered on each sketch point of each sketch line The geometry window that size is 5 × 5 is constructed, structural region is obtained.

The part other than aggregation zone and structural region will be removed in sketch map as can not sketch region.

By in sketch map aggregation zone, structural region and can not sketch region merging technique, to obtain include aggregation zone, homogeneous The administrative division map of the synthetic aperture radar SAR image of region and structural region.

It will include aggregation zone, the administrative division map without sketch line region and structural region, be mapped to the synthetic aperture thunder of input Up in SAR image, mixing aggregated structure atural object pixel subspace in synthetic aperture radar SAR image, homogenous region picture are obtained Sub-prime space and structure-pixel subspace.

Step 3, ridge ripple filter set is constructed.

Step 1 extracts mixing aggregated structure atural object pixel subspace pair from the administrative division map of synthetic aperture radar SAR image The aggregation zone answered, [0⁰, 180⁰] 10 are divided into in section⁰18 sections i.e. 18 directions are divided into, statistics is each respectively In section in the aggregation zone sketch line segment item number.

Step 2, to sketch line segment all in the aggregation zone, according to how much progress of the line segment item number in each interval Sequence, obtain the collating sequence in direction, using the degree in 6 directions preceding in the collating sequence in direction as ridge ripple filter in Directioin parameter.

Step 3 calculates the ridge ripple function of 9 × 9 ridge ripple filter according to parameter a, θ and b according to the following formula:

Y=a × (y₁×cosθ+y₂×sinθ-b)

Wherein, Y indicates that the ridge ripple function of ridge ripple filter, a indicate the scale parameter of ridge ripple filter, the value range of a For [0,3], the discrete interval of a is 0.2, y₁Indicate the abscissa positions of ridge ripple filter pixel, y₁Value range be [0, 8], y₁Discrete interval be 1, cos indicate cosine operation, θ indicate ridge ripple filter directioin parameter, y₂Indicate ridge ripple filter The ordinate position of pixel, y₂Value range be [0,8], y₂Discrete interval be 1, sin indicate sinusoidal operation；B indicates ridge The displacement parameter of wave filter, when directioin parameter θ is [0⁰,90⁰) when, b is divided into the section [0,9 × (sin θ+cos θ)] with 0.2 carries out discretization, when directioin parameter θ is [90⁰,180⁰) when, b is divided into 0.2 in [9 × cos θ, 9 × sin θ] section with Carry out discretization.

Step 4 calculates each ridge ripple wave filter according to the following formula:

Wherein, c (Y) indicates that the ridge ripple filter using ridge ripple function Y as parameter, K indicate ridge ripple filter frobenius The inverse of norm, exp are indicated using natural constant e as the index operation at bottom.

Each the ridge ripple filter bank being calculated is become ridge ripple filter set by step 5.

Step 4, convolutional coding structure learning model is constructed.

Step 1 does not connect each of the mixing aggregated structure atural object pixel subspace in synthetic aperture radar SAR image mutually Logical region sample every a sliding window by 31 × 31 window, the corresponding multiple images block in each region is obtained, by multiple figures As block is sequentially inputted in convolutional coding structure learning model, the input layer of convolutional coding structure learning model is obtained.

Step 2 carries out convolution behaviour to the image block in the input layer of convolutional coding structure learning model using ridge ripple filter Make, obtains the convolutional layer of convolutional coding structure learning model.

Step 3 calculates data fidelity term according to the following formula.

Wherein, E (c) indicates data fidelity term, and c indicates the ridge ripple filter in convolutional coding structure learning model convolutional layer, ∑ Indicating sum operation, N indicates each of to be learnt the total number for the image block that mutually disconnected region includes, | | | |_FIt indicates The operation of frobenius norm is done,Indicate the square operation of frobenius norm, x_iIndicate convolutional coding structure study mould to be constructed I-th of the image block inputted in type,It indicates to extract x_iIntermediate size is the characteristic image block of n × n, M_iIndicate volume to be constructed The sum of the corresponding ridge ripple filter of i-th of image block inputted in product Structure learning model, * indicate convolution operation,It indicates Corresponding j-th of ridge ripple filter of i-th of the image block inputted in convolutional coding structure learning model to be constructed.

Step 4 calculates structure fidelity term according to the following formula:

Wherein, G (c) indicates structure fidelity term, and R () indicates to ask the operation of all sketch line total lengths in sketch map, SM () indicates to extract the operation with the one-to-one sketch segment of input picture block.

Step 5, according to the following formula, calculating target function:

Wherein, L (c) indicates objective function,It indicates in objective function L (c) value minimum, seeks ridge ripple filter The operation of c.

Step 6 exports the ridge ripple filter obtained by objective function guidance learning, obtains the output of convolutional coding structure model Layer.

Step 5, according to the following steps, training convolutional Structure learning model:

Step 1 sets 0.1 for structural failure threshold value；

Step 4 sampling is obtained image block and is sequentially inputted in convolutional coding structure learning model by step 2；

Step 3 randomly selects six filters, directioin parameter is by system in step (3b) from ridge ripple filter set 6 directions of meter obtain, displacement parameter and scale parameter random initializtion, the filtering that these initial six filters are formed Device set is as selected ridge ripple filter set；

Step 4, by each ridge ripple filter in image block currently entered and selected ridge ripple filter set into Row convolution operation, it is corresponding with each ridge ripple filter to obtain characteristic pattern；

Step 5 utilizes the structure fidelity term formula in step 4, the structure fidelity term of calculating input image block；

Step 6, judges whether the structure fidelity term of current input image block is less than structural failure threshold value, if so, executing Otherwise step 9 executes step 7；

Step 7 updates step 4 data fidelity term using scale parameter more new formula and displacement parameter more new formula respectively The scale parameter and displacement parameter of formula median ridge wave filter obtain updated ridge ripple filter；

The more new formula of scale parameter is as follows:

Wherein a indicates the scale parameter of ridge ripple filter, a^tThe scale acquired, a are walked for t^t-1It is acquired for t-1 step Scale, δ indicate coefficient, and value range is [0,1], and ∑ indicates to be added, x_iFor i-th piece 31 × 31 of SAR image sampling block,Table Show from x_iIn take the blocks of 23 × 23 sizes,Indicate the ridge ripple filter of i-th piece 31 × 31 of convolution of SAR image sampling block, γ =(a, b, θ), K (γ) indicate that the inverse of ridge ripple filter norm, e indicate that natural constant, Y indicate the ridge ripple letter of ridge ripple filter Number, y₁Indicate the abscissa positions of 9 × 9 ridge ripple filter pixel, y₂Indicate the vertical seat of 9 × 9 ridge ripple filter pixel Cursor position, θ indicate the directioin parameter of ridge ripple filter.

The more new formula of displacement parameter is as follows:

Wherein b^tIndicate the displacement parameter for the ridge ripple filter that the t times iteration acquires, b^t-1The displacement ginseng acquired for t-1 times Number, δ indicate coefficient, and value range is [0,1], and ∑ indicates to be added_,x_iFor i-th piece 31 × 31 of SAR image sampling block,It indicates From x_iIn take the blocks of 23 × 23 sizes,The ridge ripple filter of the SAR image sampling block of i-th piece 31 × 31 of convolution of expression, γ= (a, b, θ), K (γ) indicate that the inverse of ridge ripple filter norm, e indicate that natural constant, Y indicate the ridge ripple letter of ridge ripple filter Number, a^t-1For the scale parameter for the ridge ripple filter that t-1 step acquires.

Step 8, using updated ridge ripple filter set as selected ridge ripple filter set, return step the 4th Step, re-starts training to input picture block；

The ridge ripple filter that study obtains is saved the ridge ripple filter set succeeded in school to the input picture block by step 9 In, the study to the input picture block feature is completed, and export the ridge ripple filter set that the input picture block succeeds in school；

Step 9, judges whether all image blocks pass through the study that convolutional coding structure learning model completes feature, if so, knot Otherwise Shu Chengxu inputs next image block and executes step 3；

Step 6, segmentation SAR image mixes aggregated structure atural object pixel subspace:

The ridge ripple filter sets that disconnected regional learning obtains all mutually are spliced into code book by step 1.

Step 2, all ridge ripple filters in the ridge ripple filter set that mutual disconnected regional learning is obtained, to code This is projected, and structural eigenvector is obtained.

Step 3 carries out maximum pond to the structural eigenvector in each mutually disconnected region, obtains all of each region Structural eigenvector of the feature on code book.

Step 4, using neighbour propagate AP clustering algorithm, structural eigenvector is clustered, obtain with structure feature to Measure the segmentation result of corresponding mixing aggregated structure atural object pixel subspace.

Step 7, segmenting structure pixel subspace.

With vision semantic rules, divide line target.

If i-th sketch line l_iWith j-th strip sketch line l_jThe distance between be D_ij, l_iDirection be O_i, l_jDirection be O_j, I, j ∈ [1,2 ..., S], S are the total number of sketch line.

Width is greater than the line target of 3 pixels with two sketch line l_iAnd l_jIt indicates, l_iAnd l_jThe distance between D_ijIt is less than T₁And direction difference (O_i-O_j) less than 10 degree, wherein T₁=5.

If the s articles sketch line l_sGeometry window w_sThe average gray of interior each column is A_iIf the gray scale difference of adjacent column is AD_i=| A_i-A_i+1|, if z_s=[z_s1,z_s2,...,z_s9] be adjacent column gray scale difference AD_iLabel vector.

By width less than the line target of 3 pixels with single sketch line l_sIt indicates, l_sGeometry window w_sIt is interior, calculate phase The gray scale difference AD of adjacent column_iIf AD_i> T₂, then z_si=1；Otherwise z_si=0, z_sIn there are two element value be 1, remaining is 0, Middle T₂=34.

If L₁,L₂It is the set for indicating the sketch line of line target, if D_ij< T₁And | O_i-O_j| < 10, then l_i,l_j∈ L₁；If sum (z_s)=2, then l_s∈L₂, wherein sum () indicates the sum of parameter element.

In structure-pixel subspace, according to the set L of the sketch line of line target₁, by l_iAnd l_jBetween region as line mesh Mark.

In structure-pixel subspace, according to the set L of the sketch line of line target₂, l will be covered_sRegion as line target.

Feature of gathering based on sketch line divides pinpoint target.

Step 1 would not indicate all sketch wire tags of line target in the structural region of administrative division map as candidate sketch line Sketch line in set.

Step 2 randomly selects a sketch line from candidate sketch line set, with an endpoint of selected sketch line Centered on, construct the geometry window that size is 5 × 5.

Step 3 judges the endpoint that whether there is other sketch lines in geometry window, and if it exists, execute step 4；Otherwise, Execute step 6.

Step 4 judges whether to only exist an endpoint, if so, sketch line where the endpoint and current sketch line are carried out Connection；Otherwise, step 5 is executed.

Step 5 connects the sketch line where selected sketch line and each endpoint, wherein angle is chosen from all connecting lines The sketch line that maximum two sketch lines are completed as connection.

Step 6 judges the endpoint that whether there is other sketch lines in the geometry window of another endpoint of sketch line, if In the presence of execution step 4；Otherwise, step 7 is executed.

Step 7 chooses the sketch line comprising two and two or more sketch line segments to the sketch line for completing attended operation, The item number n comprising sketch line segment in selected sketch line is counted, wherein n >=2.

Step 8, judges whether the item number n of sketch line is equal to 2, if so, executing step 9；Otherwise, step 10 is executed.

Step 9, by the angle value on sketch line vertex [10⁰,140⁰] in the range of sketch line be used as have gather feature Sketch line.

Step 10 selects the angle value on the corresponding n-1 vertex of sketch line all [10⁰,140⁰] sketch line in range.

Step 11 is defined as follows two kinds of situations in selected sketch line:

Whether the first situation judges adjacent (i-1)-th, the two sketch line segments of i-th sketch line segment, i+1 item i-th The same side of straight line, 2≤i≤n-1, if all sketch line segments and adjacent segments on sketch line are all same where sketch line segment Side, then marking the sketch line is with the sketch line for gathering feature.

Whether second situation judges adjacent (i-1)-th, the two sketch line segments of i-th sketch line segment, i+1 item i-th The same side of straight line, 2≤i≤n-1, if having n-1 sketch line segment and adjacent segments same on sketch line where sketch line segment Side, and have a sketch line segment line segment adjacent thereto in non-the same side, also marking the sketch line is with the element for gathering feature Retouch line.

Step 12, an optional sketch line in there is the sketch line for gathering feature, by two ends of selected sketch line Point coordinate, determine the distance between two endpoints, if the end-point distances in [0,20] range, then using selected sketch line as table Show the sketch line of pinpoint target.

Step 13, judge it is untreated have gather the sketch line of feature and whether all selected, if so, executing step 12； Otherwise, step 14 is executed.

Step 14, with the method for super-pixel segmentation, to the sketch line for indicating pinpoint target in synthetic aperture radar SAR image The pixel of surrounding carries out super-pixel segmentation, by super-pixel of the gray value of super-pixel after segmentation in [0,45] or [180,255] As pinpoint target super-pixel.

Step 15 merges pinpoint target super-pixel, using the boundary of the pinpoint target super-pixel after merging as pinpoint target Boundary, obtain the segmentation result of pinpoint target.

The result divided to line target and pinpoint target merges, and obtains the segmentation result of structure-pixel subspace.

Step 8, divide homogenous region pixel subspace.

The segmentation of aggregated structure atural object pixel subspace, homogenous region pixel subspace and structure-pixel subspace will be mixed As a result it merges, obtains the final segmentation result of synthetic aperture radar SAR image.

Step 1 arbitrarily chooses a pixel, centered on selected pixel from the pixel subspace of homogenous region The square window for establishing 3 × 3 calculates the standard deviation sigma of the window₁。

The side length of square window is increased by 2, obtains new square window, calculate the standard deviation of new square window by step 2 σ₂。

Step 3, if standard deviation threshold method T₃=3, if | σ₁-σ₂| < T₃, then it is σ by standard deviation₂Square window as most Whole square window executes step 4；Otherwise, step 2 is executed.

Step 4 calculates the prior probability of center pixel in square window according to the following formula:

Wherein, p₁' indicate square window in center pixel prior probability, exp () indicate exponential function operation, η ' table Show that probabilistic model parameter, η ' value are 1, x_k′' indicate to belong to the number of pixels of kth ' class in square window, k' ∈ [1 ..., K'], K' indicates the classification number of segmentation, and K' value is 5, x '_i′Belong to the pixel of the i-th ' class in the square window that expression step 3 obtains Number.

The probability density of pixel grey scale is multiplied with the probability density of texture, obtains likelihood probability p' by step 6₂, wherein The probability density of gray scale is distributed to obtain by fading channel Nakagami, and the probability density of texture is distributed to obtain by t.

Step 7, by prior probability p₁' and likelihood probability p₂' be multiplied, obtain posterior probability p₁₂'。

Step 8 judges whether there are also untreated pixels in the pixel subspace of homogenous region, if so, executing step 1； Otherwise, step 9 is executed.

Step 9 obtains the segmentation result of homogenous region pixel subspace according to maximum posteriori criterion.

Step 9, combination and segmentation result.

Effect of the invention is further described below with reference to analogous diagram.

1. simulated conditions:

The hardware condition that the present invention emulates are as follows: Intellisense and image understanding laboratory graphics workstation；Present invention emulation Used synthetic aperture radar SAR image are as follows: the Piperiver that Ku wave band resolution ratio is 1 meter schemes.

2. emulation content:

Emulation experiment of the invention is split to the Piperiver figure in SAR image, as shown in Fig. 2 (a) Piperiver figure.The synthetic aperture radar SAR image that the figure is 1 meter from Ku wave band resolution ratio.

Using SAR image sketch step of the invention, to retouching of Piperiver pixel shown in Fig. 2 (a), obtain as Sketch map shown in Fig. 2 (b).

Sketch map compartmentalization shown in Fig. 2 (b) is obtained such as Fig. 2 using division pixel subspace step of the invention (c) administrative division map shown in.White space in Fig. 2 (c) indicates mixing aggregated structure semantic space, and others are homogeneous texture language Adopted space and structure semantics space.Administrative division map shown in Fig. 2 (c) is mapped to original SAR image shown in Fig. 2 (a), is obtained such as Fig. 2 (d) Shown in SAR image mix aggregated structure atural object pixel subspace figure.

Image Segmentation Methods Based on Features pinpoint target step is gathered based on sketch line using of the invention, extracts non-agglomerated area in Fig. 2 (b) The sketch line in domain obtains Fig. 3 (a), extracts the sketch line of the expression line target in Fig. 3 (a), obtains result shown in Fig. 3 (b). Black sketch line in Fig. 3 (b) is the sketch line for indicating line target.To the sketch line for not indicating line target in Fig. 3 (b), extract With the sketch line for gathering feature, obtain shown in Fig. 3 (c) as a result, wherein black sketch line indicates pinpoint target.Pairing pore-forming Diameter radar SAR image is sought indicating the super-pixel around doubtful pinpoint target sketch line, obtains result shown in Fig. 3 (d).It will Super-pixel of the gray value of super-pixel in [0,45] or [180,255] is as pinpoint target super-pixel after segmentation, and merges Pinpoint target super-pixel, using the boundary of the pinpoint target super-pixel after merging as the boundary of pinpoint target, obtained independent mesh It marks shown in segmentation result such as Fig. 3 (e).

Aggregated structure atural object pixel subspace step is mixed using segmentation SAR image of the invention, to shown in Fig. 2 (d) The mixing aggregated structure atural object pixel subspace figure of Piperiver figure is split, and obtains mixed land cover picture shown in Fig. 4 (a) Sub-prime space segmentation result figure, grey area indicate untreated ground object space, and the region of remaining same color indicates same A kind of atural object, the region of different colours indicate different atural object.

Using combination and segmentation result step of the invention, it is empty to merge mixing aggregated structure atural object pixel shown in Fig. 4 (a) Between segmentation result and homogenous region pixel subspace segmentation result and structure-pixel subspace segmentation result, obtain Fig. 4 (b), Fig. 4 (b) be Fig. 2 (a) Piperiver image final segmentation result, Fig. 4 (c) be based on level vision semanteme and adaptive neighborhood it is more Final segmentation result figure of the SAR image segmentation method of Xiang Shiyin model to Piperiver image.

3. simulated effect is analyzed:

Fig. 4 (b) is final segmentation result figure of the method for the present invention to Piperiver image, and Fig. 4 (c) is regarded based on level Feel semantic and the hidden model of adaptive neighborhood multinomial SAR image segmentation method to the final segmentation result of Piperiver image Figure, by the comparison of segmentation result figure, it could be assumed that, the method for the present invention is for mixing aggregated structure atural object pixel subspace Boundary determination is more accurate, and the segmentation for homogenous region pixel subspace, region consistency is obviously preferable, classification number more adduction Reason, and preferable dividing processing has been carried out to the pinpoint target in structure-pixel subspace.Use the method for the present invention pairing pore-forming Diameter radar SAR image is split, and is effectively divided SAR image, and improves the accuracy of SAR image segmentation.

Claims

1. a kind of SAR image segmentation method based on ridge ripple filter and convolutional coding structure learning model, includes the following steps:

(1) SAR image sketch:

(1b) utilizes SAR image sketch model, carries out sketch processing to the synthetic aperture radar SAR image of input, obtains defeated The corresponding sketch map of synthetic aperture radar SAR image entered；

(2) pixel subspace is divided:

(2a) uses sketch line fields method, carries out compartmentalization processing to the sketch map of synthetic aperture radar SAR image, obtains The administrative division map of synthetic aperture radar SAR image including aggregation zone, without sketch line region and structural region；

(2b) will include aggregation zone, the administrative division map without sketch line region and structural region, be mapped to the synthetic aperture thunder of input Up in SAR image, mixing aggregated structure atural object pixel subspace in synthetic aperture radar SAR image, homogenous region picture are obtained Sub-prime space and structure-pixel subspace；

(3) ridge ripple filter set is constructed:

It is corresponding poly- that (3a) extracts mixing aggregated structure atural object pixel subspace from the administrative division map of synthetic aperture radar SAR image Collect region, is divided into 10 ° in [0 °, 180 °] section with and is divided into 18 sections i.e. 18 directions, count each section respectively The item number of sketch line segment in the interior aggregation zone；

(3b) is ranked up sketch line segment all in the aggregation zone according to the number of the line segment item number in each interval, The collating sequence in direction is obtained, using the degree in 6 directions preceding in the collating sequence in direction as the side in ridge ripple filter To parameter；

Y=a × (y₁×cosθ+y₂×sinθ-b)

Wherein, Y indicates the ridge ripple function of ridge ripple filter, and a indicates the scale parameter of ridge ripple filter, the value range of a be [0, 3], the discrete interval of a is 0.2, y₁Indicate the abscissa positions of ridge ripple filter pixel, y₁Value range be [0,8], y₁ Discrete interval be 1, cos indicate cosine operation, θ indicate ridge ripple filter directioin parameter, y₂Indicate ridge ripple filter pixel The ordinate position of point, y₂Value range be [0,8], y₂Discrete interval be 1, sin indicate sinusoidal operation；B indicates ridge ripple filter The displacement parameter of wave device, when directioin parameter θ be [0 °, 90 °) when, b is divided into 0.2 in the section [0,9 × (sin θ+cos θ)] with Carry out discretization, when directioin parameter θ is [90 °, 180 °) when, b be divided into [9 × cos θ, 9 × sin θ] section 0.2 into Row discretization；

Wherein, c (Y) indicates that the ridge ripple filter using ridge ripple function Y as parameter, K indicate ridge ripple filter frobenius norm Inverse, exp indicate using natural constant e as the index operation at bottom；

(4) convolutional coding structure learning model is constructed:

(4a) is to the mutual disconnected area in each of mixing aggregated structure atural object pixel subspace in synthetic aperture radar SAR image Domain, by 31 × 31 window carry out every a sliding window sample, obtain the corresponding multiple images block in each region, by multiple images block according to It is secondary to be input in convolutional coding structure learning model, obtain the input layer of convolutional coding structure learning model；

(4b) uses ridge ripple filter, carries out convolution operation to the image block in the input layer of convolutional coding structure learning model, obtains The convolutional layer of convolutional coding structure learning model；

(4c) according to the following formula, calculates data fidelity term:

Wherein, E (c) indicates data fidelity term, and c indicates that the ridge ripple filter in convolutional coding structure learning model convolutional layer, ∑ indicate Sum operation, N indicate each of to be learnt the total number for the image block that mutually disconnected region includes, | | | |_FExpression is done The operation of frobenius norm,Indicate the square operation of frobenius norm, x_iIndicate convolutional coding structure learning model to be constructed I-th of image block of middle input,It indicates to extract x_iIntermediate size is the characteristic image block of n × n, M_iIndicate convolution to be constructed The sum of the corresponding ridge ripple filter of i-th of the image block inputted in Structure learning model, * indicate convolution operation,Indicate to Corresponding j-th of ridge ripple filter of i-th of image block inputted in construction convolutional coding structure learning model；

(4d) according to the following formula, calculates structure fidelity term:

Wherein, G (c) indicates structure fidelity term, and R () indicates to ask the operation of all sketch line total lengths in sketch map, SM () It indicates to extract the operation with the one-to-one sketch segment of input picture block；

(4e) according to the following formula, calculating target function:

Wherein, L (c) indicates objective function,It indicates in objective function L (c) value minimum, seeks the behaviour of ridge ripple filter c Make；

(5) training convolutional Structure learning model:

(5a) sets 0.1 for structural failure threshold value；

(5c) randomly selects six filters, directioin parameter is by middle 6 counted of step (3b) from ridge ripple filter set Direction obtains, displacement parameter and scale parameter random initializtion, the filter set that these initial six filters are formed As selected ridge ripple filter set；

Each ridge ripple filter in image block currently entered and selected ridge ripple filter set is carried out convolution by (5d) Operation, obtains characteristic pattern corresponding with each ridge ripple filter；

(5f) judges whether the structure fidelity term of current input image block is less than structural failure threshold value, if so, thening follow the steps (5i) is otherwise executed step (5g)；

(5g) utilizes scale parameter more new formula and displacement parameter more new formula, updates step (4c) data fidelity term formula respectively The scale parameter and displacement parameter of median ridge wave filter obtain updated ridge ripple filter；

(5h) is using updated ridge ripple filter set as selected ridge ripple filter set, return step (5d), to defeated Enter image block and re-starts training；

(5i) saves the ridge ripple filter that study obtains in the ridge ripple filter set succeeded in school to the input picture block, completes Study to the input picture block feature, and export the ridge ripple filter set that the input picture block succeeds in school；

(5j) judges whether all image blocks pass through the study that convolutional coding structure learning model completes feature, if so, terminate program, Otherwise, it inputs next image block and executes step (5c)；

All ridge ripple filters, carry out to code book in the ridge ripple filter set that (6b) obtains mutual disconnected regional learning Projection, obtains structural eigenvector；

(6c) carries out maximum pond to the structural eigenvector in each mutually disconnected region, and all features for obtaining each region exist Structural eigenvector on code book；

(6d) propagates AP clustering algorithm using neighbour, clusters, obtains opposite with structural eigenvector to structural eigenvector The segmentation result for the mixing aggregated structure atural object pixel subspace answered；

(7) segmenting structure pixel subspace:

(7a) uses vision semantic rules, divides line target；

The result that (7c) divides line target and pinpoint target merges, and obtains the segmentation result of structure-pixel subspace；

(8) divide homogenous region pixel subspace:

Using the homogenous region dividing method based on multinomial logistic regression prior model, homogenous region pixel subspace is carried out Segmentation, obtains the segmentation result of homogenous region pixel subspace；

(9) combination and segmentation result:

The segmentation result for mixing aggregated structure pixel subspace, homogenous region pixel subspace and structure-pixel subspace is closed And obtain the final segmentation result of synthetic aperture radar SAR image.

2. the SAR image segmentation method according to claim 1 based on ridge ripple filter and convolutional coding structure learning model, It is characterized in that, specific step is as follows for step (1) described sketch:

Step 1 constructs a template on the side being made of pixel with different directions and scale, line, utilizes the side of template To with dimensional information structural anisotropy's Gaussian function, count the weighting coefficient of every bit in the template, mesoscale number takes Value is 3~5, and direction number value is 18；

Step 2 calculates the mean value of pixel in synthetic aperture radar SAR image corresponding with template area position according to the following formula And variance yields:

Wherein, μ indicates the mean value of pixel in synthetic aperture radar SAR image corresponding with template area position, and ∑ expression is asked And operation, g indicate the position of a pixel in the Ω region of template, ∈ expression belongs to symbol, w_gIndicate template Ω Weight coefficient of the pixel at the position g, w in region_gValue range be w_g∈ [0,1], A_gIt indicates and the Ω region of template Pixel value of the middle pixel at the position g in corresponding synthetic aperture radar SAR image, ν indicate opposite with template area position The variance yields of pixel in the synthetic aperture radar SAR image answered；

Step 3 calculates the response of each pixel reduced value operator in synthetic aperture radar SAR image according to the following formula:

Wherein, R indicates the response of each pixel reduced value operator in synthetic aperture radar SAR image, and min { } expression is asked most Small Value Operations, a and b respectively indicate two different zones in template, μ_aAnd μ_bIt respectively indicates and template area a and template area b The mean value of pixel in the corresponding synthetic aperture radar SAR image in position；

Step 4, according to the following formula, response of each pixel to correlation operator in calculating synthetic aperture radar SAR image:

Wherein, C indicates that the response of correlation operator, a and b are respectively indicated each pixel in synthetic aperture radar SAR image Two different zones, v in template_aAnd v_bRespectively indicate synthetic aperture radar corresponding with template area a and the template area position b The variance yields of pixel, μ in SAR image_aAnd μ_bRespectively indicate synthetic aperture thunder corresponding with template area a and the template area position b Up to the mean value of pixel in SAR image,Indicate square root functions；

Step 5 merges the response and synthetic aperture of pixel reduced value operator in synthetic aperture radar SAR image according to the following formula Pixel is to the response of correlation operator in radar SAR image, calculates in synthetic aperture radar SAR image each pixel to each The response of template:

Wherein, F indicates that for each pixel to the response of each template, R and C respectively indicate conjunction in synthetic aperture radar SAR image At pixel in pixel reduced value operator in aperture radar SAR image and synthetic aperture radar SAR image to the sound of correlation operator It should be worth,Indicate square root functions；

Step 6, selection has the template of maximum response from the response of each template, schemes as synthetic aperture radar SAR The template of pixel as in, and using maximum response as the intensity of the pixel, the direction of the template with maximum response is made For the direction of the pixel, the sideline response diagram and directional diagram of synthetic aperture radar SAR image are obtained；

Step 7 is obtained using the selected template with maximum response of each pixel in synthetic aperture radar SAR image The gradient map of synthetic aperture radar SAR image；

Step 8 merges the response of sideline response diagram and the value of gradient map, intensity value is calculated, by intensity value according to the following formula Each pixel composition synthetic aperture radar SAR image intensity map:

Wherein, I indicates that intensity value, x indicate the value in the response diagram of synthetic aperture radar SAR image sideline, and y indicates synthetic aperture thunder Value up in SAR image gradient map；

Step 9 detects intensity map using non-maxima suppression method, obtains suggestion sketch；

Step 10 will suggest the pixel in sketch with the maximum intensity from pixel of the selection with maximum intensity in sketch is suggested The pixel of connection connects to form suggestion line segment, obtains suggestion sketch map；

Step 11 calculates the code length gain for suggesting sketch line in sketch map according to the following formula:

Wherein, CLG indicates to suggest the code length gain of sketch line in sketch map, and m indicates pixel in current sketch line neighborhood Number, ∑ indicate sum operation, and t indicates the number of pixel in current sketch line neighborhood, A_tIndicate t in current sketch line neighborhood The observation of a pixel, A_{T, 0}Indicate the t in sketch line neighborhood under the premise of current sketch line cannot indicate structural information The estimated value of a pixel, ln () are indicated using e as the log operations at bottom, A_{T, 1}It indicates to indicate that structure is believed in current sketch line Under the premise of breath, the estimated value of t-th of pixel in the sketch line neighborhood；

Step 12, the value range of given threshold T, T are 5~50, select the suggestion sketch line of CLG > T as in final sketch map Sketch line, obtain the corresponding sketch map of input synthetic aperture radar SAR image.

3. the SAR image segmentation method according to claim 1 based on ridge ripple filter and convolutional coding structure learning model, It is characterized in that, specific step is as follows for sketch line fields method described in step (2):

Sketch line is divided into table according to the concentration class of sketch line segment in the sketch map of synthetic aperture radar SAR image by step 1 Show the aggregation sketch line of aggregation atural object and indicates the sketch line of boundary, line target and isolated target；

Step 2 chooses the sketch line segment work that concentration class is equal to optimal concentration class according to the statistics with histogram of sketch line segment concentration class For seed line-segment sets { E_k, k=1,2 ..., m }, wherein E_kIndicate that any bar sketch line segment in seed line-segment sets, k indicate kind Sub-line section concentrates the label of any bar sketch line segment, and m indicates the total number of seed line segment, and { } indicates set operation；

Step 3, as basic point by the unselected line segment for being added to some seed line-segment sets sum, new with this basic point recursive resolve Line segment aggregate；

Step 4 constructs the round primitive that a radius is the optimal concentration class section upper bound, with the circle primitive in line segment aggregate Line segment expanded, the line segment aggregate ecto-entad after expansion is corroded, is obtained in sketch map with sketch point being single The aggregation zone of position；

Step 5, to the sketch line for indicating boundary, line target and isolated target, during each sketch point with each sketch line is The heart constructs the geometry window that size is 5 × 5, obtains structural region；

Step 6 will remove the part other than aggregation zone and structural region as can not sketch region in sketch map；

Step 7, by sketch map aggregation zone, structural region and can not sketch region, be respectively mapped to synthetic aperture radar In SAR image, mixing aggregated structure atural object pixel subspace, the structure-pixel subspace of synthetic aperture radar SAR image are obtained With homogenous region pixel subspace.

4. the SAR image segmentation method according to claim 1 based on ridge ripple filter and convolutional coding structure learning model, It is characterized in that, the more new formula of the scale parameter a of ridge ripple filter described in step (5g) is as follows:

Wherein a indicates the scale parameter of ridge ripple filter, a^tThe scale acquired, a are walked for t^t-1The scale acquired, δ are walked for t-1 Indicate coefficient, value range is [0,1], and ∑ indicates to be added, x_iFor i-th piece 31 × 31 of SAR image sampling block,It indicates from x_i In take the blocks of 23 × 23 sizes,The ridge ripple filter of the SAR image sampling block of i-th piece 31 × 31 of convolution of expression, γ=(a, b, θ), K (γ) indicates that the inverse of ridge ripple filter norm, e indicate that natural constant, Y indicate the ridge ripple function of ridge ripple filter, y₁Table Show the abscissa positions of 9 × 9 ridge ripple filter pixel, y₂Indicate the ordinate position of 9 × 9 ridge ripple filter pixel It sets, θ indicates the directioin parameter of ridge ripple filter.

5. the SAR image segmentation method according to claim 1 based on ridge ripple filter and convolutional coding structure learning model, It is characterized in that, the more new formula of displacement parameter b described in step (5g) is as follows:

Wherein b^tIndicate the displacement parameter for the ridge ripple filter that the t times iteration acquires, b^t-1The displacement parameter acquired for t-1 times, δ table Show coefficient, value range is [0,1], and ∑ indicates to be added, x_iFor i-th piece 31 × 31 of SAR image sampling block,It indicates from x_iIn The block of 23 × 23 sizes is taken,The ridge ripple filter of the SAR image sampling block of i-th piece 31 × 31 of convolution of expression, γ=(a, b, θ), K (γ) indicates that the inverse of ridge ripple filter norm, e indicate that natural constant, Y indicate the ridge ripple function of ridge ripple filter, a^t-1 For the scale parameter for the ridge ripple filter that t-1 step acquires.

6. the SAR image segmentation method according to claim 1 based on ridge ripple filter and convolutional coding structure learning model, It is characterized in that, vision semantic rules described in step (7a) are as follows:

If i-th sketch line l_iWith j-th strip sketch line l_jThe distance between be D_ij, l_iDirection be O_i, l_jDirection be O_j, i, j ∈ [1,2 ..., S], S are the total number of sketch line；

Width is greater than the line target of 3 pixels with two sketch line l_iAnd l_jIt indicates, l_iAnd l_jThe distance between D_ijLess than T₁And Direction difference (O_i-O_j) less than 10 degree, wherein T₁=5；

If the s articles sketch line l_sGeometry window w_sThe average gray of interior each column is A_iIf the gray scale difference of adjacent column is AD_i= |A_i-A_i+1|, if z_s=[z_s1,z_s2,...,z_s9] be adjacent column gray scale difference AD_iLabel vector；

By width less than the line target of 3 pixels with single sketch line l_sIt indicates, l_sGeometry window w_sIt is interior, calculate adjacent column Gray scale difference AD_iIf AD_i> T₂, then z_si=1；Otherwise z_si=0, z_sIn there are two element value be 1, remaining is 0, wherein T₂ =34；

If L₁,L₂It is the set for indicating the sketch line of line target, if D_ij< T₁And | O_i-O_j| < 10, then l_i,l_j∈L₁；If sum(z_s)=2, then l_s∈L₂, wherein sum () indicate to vector important summation operation.

7. the SAR image segmentation method according to claim 1 based on ridge ripple filter and convolutional coding structure learning model, It is characterized in that, specific step is as follows for segmentation line target described in step (7a):

Step 1, in structure-pixel subspace, according to the set L of the sketch line of line target₁, by l_iAnd l_jBetween region as line Target；

Step 2, in structure-pixel subspace, according to the set L of the sketch line of line target₂, l will be covered_sRegion as line mesh Mark.

8. the SAR image segmentation method according to claim 1 based on ridge ripple filter and convolutional coding structure learning model, It is characterized in that, specific step is as follows for segmentation pinpoint target described in step (7b):

Step 1 would not indicate all sketch wire tags of line target in the structural region of administrative division map as candidate sketch line set In sketch line；

Step 2 randomly selects a sketch line from candidate sketch line set, during an endpoint with selected sketch line is The heart, the geometry window that construction size is 5 × 5；

Step 3 judges the endpoint that whether there is other sketch lines in geometry window, and if it exists, execute step 4；Otherwise, it executes Step 6；

Step 4 judges whether to only exist an endpoint, if so, sketch line where the endpoint and current sketch line are attached； Otherwise, step 5 is executed；

Step 5 connects the sketch line where selected sketch line and each endpoint, and it is maximum that wherein angle is chosen from all connecting lines Two sketch lines as connection complete sketch line；

Step 6 judges the endpoint that whether there is other sketch lines in the geometry window of another endpoint of sketch line, if depositing Executing step 4；Otherwise, step 7 is executed；

Step 7 chooses the sketch line comprising two and two or more sketch line segments, statistics to the sketch line for completing attended operation It include the item number n of sketch line segment, wherein n >=2 in selected sketch line；

Step 8, judges whether the item number n of sketch line is equal to 2, if so, executing step 9；Otherwise, step 10 is executed；

Step 9, by sketch line of the angle value on sketch line vertex in the range of [10 °, 140 °] as have gather feature Sketch line；

Step 10 selects sketch line of the angle value on the corresponding n-1 vertex of sketch line all in [10 °, 140 °] range；

Step 11 is defined as follows two kinds of situations in selected sketch line:

Whether the first situation judges adjacent (i-1)-th, the two sketch line segments of i-th sketch line segment, i+1 item in i-th element The same side of straight line, 2≤i≤n-1, if all sketch line segments and adjacent segments on sketch line are all same where retouching line segment Side, then marking the sketch line is with the sketch line for gathering feature；

Whether second situation judges adjacent (i-1)-th, the two sketch line segments of i-th sketch line segment, i+1 item in i-th element The same side of straight line where line segment, 2≤i≤n-1 are retouched, if having n-1 sketch line segment and adjacent segments on sketch line in the same side, And have a sketch line segment line segment adjacent thereto in non-the same side, also marking the sketch line is with the sketch line for gathering feature；

Step 11, an optional sketch line in having the sketch line for gathering feature are sat by two endpoints of selected sketch line Mark, determines the distance between two endpoints, if the end-point distances are in [0,20] range, then only using selected sketch line as expression The sketch line of vertical target；

Step 12, judge it is untreated have gather the sketch line of feature and whether all selected, if so, executing step 11；Otherwise, Execute step 13；

Step 13, with the method for super-pixel segmentation, around the sketch line for indicating pinpoint target in synthetic aperture radar SAR image Pixel carry out super-pixel segmentation, by super-pixel conduct of the gray value of super-pixel after segmentation in [0,45] or [180,255] Pinpoint target super-pixel；

Step 14 merges pinpoint target super-pixel, using the boundary of the pinpoint target super-pixel after merging as the side of pinpoint target Boundary obtains the segmentation result of pinpoint target.

9. the SAR image segmentation method according to claim 1 based on ridge ripple filter and convolutional coding structure learning model, It is characterized in that, the specific steps of the homogenous region dividing method based on multinomial logistic regression prior model described in step (8) It is as follows:

Step 1 is arbitrarily chosen a pixel from the pixel subspace of homogenous region, is established centered on selected pixel 3 × 3 square window calculates the standard deviation sigma of the window₁；

The side length of square window is increased by 2, obtains new square window, calculate the standard deviation sigma of new square window by step 2₂；

Step 3, if standard deviation threshold method T₃=3, if | σ₁-σ₂| < T₃, then it is σ by standard deviation₂Square window as final Square window executes step 4；Otherwise, step 2 is executed；

Wherein, p '₁Indicate that the prior probability of center pixel in square window, η ' indicate that probabilistic model parameter, η ' value are 1, x_k′′ Indicate the number of pixels for belonging to kth ' class in square window, k' ∈ [1 ..., K'], K' indicate the classification number of segmentation, and K' value is 5, x '_i′Belong to the number of pixels of the i-th ' class in the square window that expression step 3 obtains；

The probability density of pixel grey scale is multiplied with the probability density of texture, obtains likelihood probability p ' by step 5₂, wherein gray scale Probability density is distributed to obtain by fading channel Nakagami, and the probability density of texture is distributed to obtain by t；

Step 6, by prior probability p₁' and likelihood probability p₂' be multiplied, obtain posterior probability p₁₂'；

Step 7 judges whether there are also untreated pixels in the pixel subspace of homogenous region, if so, executing step 1；Otherwise, Execute step 9；

Step 8 obtains the segmentation result of homogenous region pixel subspace according to maximum posteriori criterion.