Method, device and equipment for segmenting ship and chaff in SAR (Synthetic Aperture Radar) image

Abstract

The invention provides a method, a device and equipment for segmenting ships and chaff in an SAR (Synthetic Aperture Radar) image. The method comprises the following steps: constructing a coherence matrix of each pixel according to complete polarization data of an SAR radar, decomposing the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering and volume scattering, and then generating a pseudo-color image based on the power ratio of each scattering mechanism; next, a foreground mask of the SAR image acts on the pseudo-color image to obtain a to-be-classified image; and finally, classifying pixels in the to-be-classified image based on a preset scattering feature difference, and marking the pixels as ship type pixels and chaff type pixels. According to the scheme, through the synergistic effect of polarization scattering mechanism decomposition and mask noise reduction, high-precision distinguishing of ship and chaff interference is achieved.

Description

Technical Field

[0001] One or more embodiments of this specification relate to the field of radar signal processing, and more particularly to a method, device, and apparatus for segmenting ships and chaff in SAR images. Background Art

[0002] Compared with other guidance technologies, the SAR seeker, which uses Synthetic Aperture Radar (SAR) technology as its core sensor, can effectively improve the detection accuracy and recognition probability of the target by the seeker, and has significant advantages in many aspects: all-weather and all-day imaging capabilities, long detection distance, and providing richer target features.

[0003] Chaff jamming is a very important jamming method against anti-ship missiles. Among them, centroid jamming is a jamming method released to counter the radar seeker in the tracking phase. Its purpose is to make the radar seeker track the target ship and the energy centroid of the chaff cloud. As the chaff cloud drifts with the wind and the target ship maneuvers, the tracking point of the radar seeker gradually falls on the chaff cloud and moves away from the target ship. Eventually, the target ship moves out of the radar seeker's tracking beam, thus avoiding attack. Figure 1 shown.

[0004] In the early stage of a ship releasing chaff for centroid jamming, the ship and the chaff are not completely separated in the SAR image. At this time, existing detection solutions are used. For example, constant false alarm rate (CFAR) detection will identify the chaff and the ship as the same target, and the missile will not be able to hit the ship during the attack. Therefore, it is necessary to identify and segment the detected area, which is of great significance for the accurate hit of anti-ship missiles. Summary of the Invention

[0005] In view of this, one or more embodiments of this specification provide a method, apparatus, device, and storage medium for segmenting ships and chaff in SAR images, so as to achieve accurate segmentation of ships and chaff.

[0006] To achieve the above objectives, one or more embodiments of this specification provide the following technical solutions:

[0007] According to a first aspect of one or more embodiments of this specification, a method for segmenting ships and chaff in a SAR image is proposed, comprising:

[0008] Obtain full polarization data of SAR radar;

[0009] constructing a coherence matrix for each pixel based on the full polarization data, and decomposing the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering;

[0010] Generate a pseudo-color image based on the power contribution of each scattering mechanism;

[0011] Acquiring a foreground mask in the SAR image corresponding to the full polarization data, and applying the foreground mask to the pseudo-color image to obtain an image to be classified;

[0012] Pixels in the image to be classified are classified based on preset scattering feature differences, marked as ship category pixels and chaff category pixels, and a segmentation result is obtained.

[0013] In some embodiments, the coherence matrix decomposition into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering comprises:

[0014] Making the coherence matrix equivalent to a weighted combination of plane scattering power, secondary scattering power, and volume scattering power;

[0015] The total power of the SAR image is equal to the sum of the plane scattering power, secondary scattering power, and volume scattering power, as well as the weight values corresponding to the three scattering powers, and each scattering power is solved.

[0016] In some embodiments, obtaining a foreground mask in the SAR image corresponding to the full polarimetric data includes:

[0017] Obtaining a total power map of the SAR image;

[0018] Setting a threshold according to a target feature, and binarizing the total power map using the threshold;

[0019] Isolated points in the binarization result are removed to obtain the foreground mask.

[0020] In some embodiments, setting a threshold value according to a target feature and binarizing the total power map using the threshold value includes: performing a constant false alarm rate test on the total power map to perform binarization;

[0021] The removing of isolated points in the binarization result to obtain the foreground mask includes:

[0022] The foreground mask is obtained by removing isolated points in the binarization result through a morphological opening operation.

[0023] In some embodiments, classifying pixels in the image to be classified based on preset scattering feature differences and marking them as ship-type pixels and chaff-type pixels includes:

[0024] A support vector machine is used to classify pixels in the image to be classified, wherein the support vector machine is trained using scattering mechanism power proportion values of multiple ships and multiple foil strips.

[0025] In some embodiments, the method further comprises:

[0026] Obtaining an image to be filtered according to the label value of each pixel in the segmentation result, wherein the label value of the background pixel is zero and the label value of the foreground pixel is non-zero;

[0027] For each non-zero pixel, a neighborhood window of fixed size is selected;

[0028] In the neighborhood window, the current pixel is updated using the largest non-zero label value in the connected neighborhood of the current non-zero pixel.

[0029] According to a second aspect of one or more embodiments of this specification, a device for segmenting ships and chaff in SAR images is provided, comprising:

[0030] An acquisition unit, used to acquire full polarization data of the SAR radar;

[0031] a decomposition unit, configured to construct a coherence matrix for each pixel based on the full polarization data, and decompose the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering;

[0032] a generating unit, configured to generate a pseudo-color image based on a power ratio of each scattering mechanism;

[0033] a mask unit, configured to obtain a foreground mask in the SAR image corresponding to the full polarization data, and apply the foreground mask to the pseudo-color image to obtain an image to be classified;

[0034] The segmentation unit is used to classify the pixels in the image to be classified based on the preset scattering feature difference, mark them as ship category pixels and chaff category pixels, and obtain a segmentation result.

[0035] In some embodiments, the decomposition unit is used to:

[0036] Making the coherence matrix equivalent to a weighted combination of plane scattering power, secondary scattering power, and volume scattering power;

[0037] The total power of the SAR image is equal to the sum of the plane scattering power, secondary scattering power, and volume scattering power, as well as the weight values corresponding to the three scattering powers, and each scattering power is solved.

[0038] In some embodiments, the mask unit is used to:

[0039] Obtaining a total power map of the SAR image;

[0040] Setting a threshold according to a target feature, and binarizing the total power map using the threshold;

[0041] Isolated points in the binarization result are removed to obtain the foreground mask.

[0042] In some embodiments, the mask unit, when used to set a threshold value according to a target feature and to binarize the total power map using the threshold value, is specifically used to: perform constant false alarm rate detection on the total power map to perform binarization;

[0043] The mask unit is used to remove isolated points in the binarization result to obtain the foreground mask, specifically:

[0044] The foreground mask is obtained by removing isolated points in the binarization result through a morphological opening operation.

[0045] In some embodiments, classifying pixels in the image to be classified based on preset scattering feature differences and marking them as ship-type pixels and chaff-type pixels includes:

[0046] A support vector machine is used to classify pixels in the image to be classified, wherein the support vector machine is trained using scattering mechanism power proportion values of multiple ships and multiple foil strips.

[0047] In some embodiments, the device further comprises a filtering unit for:

[0048] Obtaining an image to be filtered according to the label value of each pixel in the segmentation result, wherein the label value of the background pixel is zero and the label value of the foreground pixel is non-zero;

[0049] For each non-zero pixel, a neighborhood window of fixed size is selected;

[0050] In the neighborhood window, the current pixel is updated using the largest non-zero label value in the connected neighborhood of the current non-zero pixel.

[0051] According to a third aspect of one or more embodiments of this specification, an electronic device is provided, including:

[0052] processor;

[0053] a memory for storing processor-executable instructions;

[0054] The processor implements the steps of the method proposed in the above embodiment by running the executable instructions.

[0055] According to a fourth aspect of one or more embodiments of this specification, a computer-readable storage medium is proposed, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method proposed in the above embodiment are implemented.

[0056] According to a fifth aspect of one or more embodiments of this specification, a computer program product is proposed, comprising a computer program / instruction, which implements the steps of the method proposed in the above embodiment when executed by a processor.

[0057] The method for segmenting ships and chaff in SAR images proposed in this disclosed embodiment constructs a coherence matrix for each pixel based on the fully polarized data of the SAR radar and decomposes the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering. A pseudo-color image is then generated based on the power contribution of each scattering mechanism. Next, the pseudo-color image is applied to the foreground mask of the SAR image to obtain an image to be classified. Finally, the pixels in the image to be classified are classified based on the differences in preset scattering characteristics and labeled as either ship-class pixels or chaff-class pixels. This solution achieves high-precision differentiation between ship and chaff interference through the synergistic effect of polarization scattering mechanism decomposition and mask denoising. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a schematic diagram of chaff centroid interference.

[0059] Figure 2 This is a flowchart of a method for segmenting ships and chaff in SAR images provided by an exemplary embodiment.

[0060] Figure 3 This is an exemplary pseudo-color image obtained by full polarization detection of the ocean area.

[0061] Figure 4A is a diagram of the HH channel in an exemplary fully polarimetric SAR image.

[0062] Figure 4B is a diagram of the HV channels in an exemplary fully polarimetric SAR image.

[0063] Figure 4C is a diagram of the VV channel in an exemplary fully polarimetric SAR image.

[0064] Figure 5 is a span total power diagram of an exemplary fully polarimetric SAR image.

[0065] Figure 6 is an exemplary foreground mask.

[0066] Figure 7 This is the segmentation result of an exemplary ship and chaff.

[0067] Figure 8 is an exemplary window filtering schematic diagram.

[0068] Figure 9 is another exemplary window filtering schematic.

[0069] Figure 10 is a schematic diagram of an exemplary filtering result.

[0070] Figure 11 It is a block diagram of a device for segmenting ships and chaff in SAR images provided by an exemplary embodiment.

[0071] Figure 12 It is a structural diagram of a device provided by an exemplary embodiment. DETAILED DESCRIPTION

[0072] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments are not intended to represent all implementations consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of one or more embodiments of this specification, as detailed in the appended claims.

[0073] It should be noted that in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than those described in this specification. In addition, a single step described in this specification may be broken down into multiple steps for description in other embodiments, and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0074] Figure 2 FIG. 1 shows a flow chart of a method for segmenting ships and chaff in a SAR image provided by an embodiment of the present disclosure. Figure 2 As shown, the method includes:

[0075] Step 201: Acquire full polarization data of SAR radar.

[0076] Fully polarimetric SAR acquires the full polarimetric scattering information of a target by transmitting and receiving electromagnetic waves of different polarization modes. Its core data is the scattering matrix, which is expressed as:

[0077]

[0078] Among them, S HH Indicates that the radar transmits horizontally polarized (H) electromagnetic waves and receives horizontally polarized (H) components reflected by the target; S HV Indicates that the radar transmits horizontally polarized (H) electromagnetic waves, but receives vertically polarized (V) components reflected by the target; S VHIndicates that the radar transmits vertically polarized (V) electromagnetic waves and receives horizontally polarized (H) components reflected by the target; S VV It means that the radar transmits vertically polarized (V) electromagnetic waves and receives the vertically polarized (V) component reflected by the target. For radars where the transmitter and receiver are at the same location, the polarization scattering matrix satisfies the reciprocity condition: S HV =S VH , that is, the target responds the same to horizontal transmission-vertical reception (HV) and vertical transmission-horizontal reception (VH).

[0079] Step 201: construct a coherence matrix based on the full polarization data, and decompose the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering.

[0080] For each pixel in the full polarization data, the formula of the three-dimensional polarization coherence matrix is as follows:

[0081]

[0082] Where k is the polarization scattering vector, and the formula is as follows:

[0083]

[0084] Substituting k into formula (2), the S-form expression of the coherence matrix is obtained as follows:

[0085]

[0086] The coherence matrix (4) is incoherently decomposed into the sum of surface scattering, secondary scattering and volume scattering components:

[0087] T=P s T s +P d T d +P v T v (5)

[0088] Among them, P s 、P d 、P v Represents the power of plane scattering, secondary scattering, and volume scattering respectively, all of which are non-negative real numbers, and the sum of the three is equal to the total polarization power span. s 、T d 、T v Coherence matrix templates representing surface scattering, secondary scattering, and volume scattering, respectively, are pre-defined based on the physical scattering model and are used to decompose the scattering mechanism of the target into a weighted combination of the three types.

[0089] This power conservation characteristic can be expressed as:

[0090] Span=P s +P d +P v =T 11 +T 22 +T 33 (6)

[0091] Among them, T 11 represents the surface scattered power, T 22 represents the secondary scattering power, T 33 Represents the volume scattered power.

[0092] In some embodiments, the planar scattering component can be modeled using a first-order Bragg scattering model, and the corresponding T s It can be expressed as follows:

[0093]

[0094] The secondary scattering component can be modeled using the dihedral reflection model, and the corresponding T d It can be expressed as follows:

[0095]

[0096] In formulas (7) and (8), α and β are both complex numbers with absolute values less than 1. α can be determined by material properties (dielectric constant), geometric parameters (angle, height difference), and phase effects, and β can be determined by surface dielectric constant, incident angle, and Bragg scattering physical model, or by data decomposition and inversion.

[0097] Volume scattering corresponds to randomly oriented scatterers. These scatterers are randomly distributed in space, with random orientation angles (uniformly distributed from 0 to 2π), and there is no phase coherence between them (incoherent superposition). Therefore, the volume scattering model is an incoherent superposition of dipoles with uniform orientation angles between 0 and 2π. Since there are a large number of dipoles and the orientation angles are randomly distributed, the target is very chaotic. The corresponding T v It can be expressed as follows:

[0098]

[0099] Step 203: Generate a pseudo-color image based on the power proportion of each scattering mechanism.

[0100] By dividing the surface scattering P s , secondary scattering P d and volume scattering P v The power proportions of γ are mapped to the RGB color channels to obtain a pseudo-color image. This image can express the dominant areas of different scattering mechanisms.

[0101] Figure 3Shown is an exemplary pseudo-color image obtained through full-polarization detection of an ocean area, where the red channel represents secondary scattering, the green channel represents volume scattering, and the blue channel represents surface scattering. The values of each channel were normalized when synthesizing the pseudo-color image. It can be observed that sea surface scattering is primarily surface scattering; chaff scattering is primarily volume scattering (green areas), with some areas exhibiting strong surface scattering (sky blue areas); and ship targets exhibit all three scattering components simultaneously, with relatively high intensities. The composition of the ship scattering components is also related to their orientation relative to the radar beam. When the ship is perpendicular to the radar beam, strong secondary scattering is generated by the ship's edges. These significant differences provide a reliable basis for distinguishing between ships and chaff based on scattering mechanisms.

[0102] Step 204 : obtaining a foreground mask in the SAR image corresponding to the full polarization data, and applying the foreground mask to the pseudo-color image to obtain an image to be classified.

[0103] Figures 4A to 4C An exemplary fully polarimetric SAR image is shown, where Figure 4A is the image of the HH channel, Figure 4B is the image of the HV channel, Figure 4C This is the image of the VV channel (the VH channel image is omitted here because it is symmetrical with the HV channel). As can be seen from the figure, there is a ship in the plane, and the chaff interference released by it has not yet completely separated from the ship.

[0104] In some embodiments, the span total power map of the SAR image may be first obtained, where Span = |HH| 2 +|HV| 2 +|VH| 2 +|VV| 2 ,like Figure 5 As shown; Next, set a threshold according to the target feature, and use the threshold to Figure 2 In the binarization result, the area is marked as foreground (white) and the sea background is suppressed (black). Then, the foreground mask is obtained by removing the isolated points in the binarization result, as shown in Figure 6 As shown, white represents ship targets or chaff interference, and black represents the sea surface background.

[0105] In one example, the span graph can be binarized using the CFAR detection method, where the false alarm rate can be set to 10, for example. -4 ,Then the isolated points in the detection results are removed through morphological opening operation.

[0106] The foreground mask obtained in this way eliminates small isolated noise points and smoothes the edges of the detection area.

[0107] Step 205: Classify the pixels in the image to be classified based on the preset scattering feature differences and mark them as ship-type pixels and chaff-type pixels.

[0108] By applying the foreground mask to the pseudo-color image in step 204, the ocean background in the pseudo-color image is set to black, and the only parts to be distinguished are the ships and chaff. By using the preset scattering feature differences between the ship and the chaff, such as the secondary scattering power ratio, the volume scattering power ratio, the polarization ratio, etc., each pixel is determined to belong to the ship category or the chaff category, thereby achieving the segmentation of the ship and chaff in the SAR image. The segmentation result is shown in FIG. Figure 7 As shown, the red area represents the ship target, the green area represents the chaff interference, and the black area represents the sea surface background.

[0109] The method for segmenting ships and chaff in SAR images proposed in this disclosed embodiment constructs a coherence matrix for each pixel based on the fully polarized data of the SAR radar and decomposes the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering. A pseudo-color image is then generated based on the power contribution of each scattering mechanism. Next, the pseudo-color image is applied to the foreground mask of the SAR image to obtain an image to be classified. Finally, the pixels in the image to be classified are classified based on the differences in preset scattering characteristics and labeled as either ship-class pixels or chaff-class pixels. This solution achieves high-precision differentiation between ship and chaff interference through the synergistic effect of polarization scattering mechanism decomposition and mask denoising.

[0110] In some embodiments, a support vector machine (SVM) may be used to implement binary classification of the image to be classified.

[0111] For sample data in a p-dimensional feature space, SVM achieves classification by constructing a p-1-dimensional optimal classification hyperplane. When multiple hyperplanes exist that can linearly separate two classes of samples, the hyperplane that maximizes the distance between the points closest to the hyperplane in the two classes is selected as the decision boundary. This optimization objective is equivalent to finding the hyperplane parameters that maximize the geometric margin under constraints. The sample points closest to the hyperplane are called support vectors, which directly determine the final position of the classification boundary.

[0112] Assume that the l-dimensional training sample dataset {x i}, i=1,2,…,N, these samples are divided into two categories m1 and m2. Using the training samples, the hyperplane can be obtained:

[0113] g(x)=w T x+w0 (10)

[0114] Where w=[w1,w2,…,w l ] T is the weighted vector and w0 is the threshold.

[0115] We need to find a classification hyperplane that makes the distance between classes m1 and m2 and the hyperplane as large as possible. Since the distance between the sample data and the hyperplane is determined by the weighted vector, that is:

[0116] d=|g(x)| / ‖w‖ (11)

[0117] Therefore, to maximize d, we only need to minimize ‖w‖. Under the following constraints, the Lagrange multiplier method is used to minimize the risk function J(w).

[0118] y(w T x+w0)≥1

[0119] stJ(w)=1 / 2‖w‖ 2 (12)

[0120] Here, for class m1, y=1, and for class m2, y=-1.

[0121] Due to the small number of samples, the use of SVM for classification can maintain high generalization in small sample scenarios and stability under limited data. For example, after the embodiment of the present application performs three-component decomposition on 20 ships and 20 chaff strips, the SVM classifier is trained using the entire pixel set to achieve the segmentation of the ships and chaff strips. The segmentation results are shown in Figure 7 .

[0122] Since the segmentation results obtained above may contain some pixels that are identified as chaff in the ship area, and conversely, there may be some pixels that are identified as ships in the chaff area, the segmentation results can be filtered to further optimize the segmentation effect.

[0123] In some embodiments, filtering of the segmentation results may be achieved by the following method.

[0124] First, obtain the image to be filtered in which each pixel has a label value. Assume that the labels of the sea background, ship and foil are 0, 1, and 2, and the corresponding colors are black, red and green.

[0125] Next, for each non-zero pixel (i, j), a fixed-size neighborhood window (usually a 5x5 or 7x7 window) is selected, and within the neighborhood window, the most non-zero values are found from the connected neighborhood (surrounding pixels) of the current non-zero pixel to update the current pixel. Figure 8 For example, there are more red non-zero pixels with a value of 0 in the neighborhood, so the current pixel is updated to red; then Figure 9For example, some pixels in the neighborhood are not connected to the current pixel. Although there are more green non-zero pixels in the neighborhood, there are more red pixels in the connected neighborhood, so the current pixel is updated to red.

[0126] The result after filtering is Figure 10 As shown in the figure, the segmentation results are more uniform and concentrated. In this scheme, by analyzing the surrounding neighborhood of each pixel to consider its spatial context, it helps correct misclassifications, effectively removes isolated misclassified points, and smoothes the transitions between regions, resulting in a more uniform and concentrated segmentation result. The final output clearly distinguishes between the ship and the chaff, and misclassified pixels are largely eliminated, highlighting the effectiveness of the window filtering step in optimizing segmentation results.

[0127] Figure 11 FIG. 1 is a block diagram of a device for segmenting ships and chaff in a SAR image provided by an exemplary embodiment. Figure 11 As shown, the device includes:

[0128] An acquisition unit 1101 is configured to acquire full polarization data of a SAR radar;

[0129] a decomposition unit 1102 configured to construct a coherence matrix for each pixel based on the full polarization data, and decompose the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering;

[0130] A generating unit 1103 is configured to generate a pseudo-color image based on the power proportion of each scattering mechanism;

[0131] a mask unit 1104 configured to obtain a foreground mask in the SAR image corresponding to the full polarization data, and apply the foreground mask to the pseudo-color image to obtain an image to be classified;

[0132] The segmentation unit 1105 is configured to classify pixels in the image to be classified based on preset scattering feature differences, mark the pixels into ship category pixels and chaff category pixels, and obtain a segmentation result.

[0133] In some embodiments, the decomposition unit is used to:

[0134] Making the coherence matrix equivalent to a weighted combination of plane scattering power, secondary scattering power, and volume scattering power;

[0135] The total power of the SAR image is equal to the sum of the plane scattering power, secondary scattering power, and volume scattering power, as well as the weight values corresponding to the three scattering powers, and each scattering power is solved.

[0136] In some embodiments, the mask unit is used to:

[0137] Obtaining a total power map of the SAR image;

[0138] Setting a threshold according to a target feature, and binarizing the total power map using the threshold;

[0139] Isolated points in the binarization result are removed to obtain the foreground mask.

[0140] In some embodiments, the mask unit, when used to set a threshold value according to a target feature and to binarize the total power map using the threshold value, is specifically used to: perform constant false alarm rate detection on the total power map to perform binarization;

[0141] The mask unit is used to remove isolated points in the binarization result to obtain the foreground mask, specifically:

[0142] The foreground mask is obtained by removing isolated points in the binarization result through a morphological opening operation.

[0143] In some embodiments, classifying pixels in the image to be classified based on preset scattering feature differences and marking them as ship-type pixels and chaff-type pixels includes:

[0144] A support vector machine is used to classify pixels in the image to be classified, wherein the support vector machine is trained using scattering mechanism power proportion values of multiple ships and multiple foil strips.

[0145] In some embodiments, the device further comprises a filtering unit for:

[0146] Obtaining an image to be filtered according to the label value of each pixel in the segmentation result, wherein the label value of the background pixel is zero and the label value of the foreground pixel is non-zero;

[0147] For each non-zero pixel, a neighborhood window of fixed size is selected;

[0148] In the neighborhood window, the current pixel is updated using the largest non-zero label value in the connected neighborhood of the current non-zero pixel.

[0149] Figure 12 This is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 12At the hardware level, the device includes a processor 1202, an internal bus 1204, a network interface 1206, a memory 1208, and a non-volatile memory 1210. Of course, it may also include hardware required for other services. One or more embodiments of this specification can be implemented based on software, such as the processor 1202 reading the corresponding computer program from the non-volatile memory 1210 into the memory 1208 and then running it. Of course, in addition to software implementation, one or more embodiments of this specification do not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0150] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email transceiver, game console, tablet computer, wearable device, or any combination of these devices.

[0151] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0152] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0153] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0154] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0155] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0156] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "an," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0157] It should be understood that although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when..." or "when..." or "in response to determining."

[0158] The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of this specification shall be included in the scope of protection of one or more embodiments of this specification.

Claims

1. A method for segmenting ships and chaff in SAR images, characterized in that: include: Obtain full polarization data of SAR radar; constructing a coherence matrix for each pixel based on the full polarization data, and decomposing the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering; Generate a pseudo-color image based on the power contribution of each scattering mechanism; Acquiring a foreground mask in the SAR image corresponding to the full polarization data, and applying the foreground mask to the pseudo-color image to obtain an image to be classified; Pixels in the image to be classified are classified based on preset scattering feature differences, marked as ship category pixels and chaff category pixels, and a segmentation result is obtained.

2. The method according to claim 1, characterized in that The coherence matrix decomposition into the following scattering mechanisms: surface scattering, secondary scattering and volume scattering includes: Making the coherence matrix equivalent to a weighted combination of plane scattering power, secondary scattering power, and volume scattering power; The total power of the SAR image is equal to the sum of the plane scattering power, secondary scattering power, and volume scattering power, as well as the weight values corresponding to the three scattering powers, and each scattering power is solved.

3. The method according to claim 1, characterized in that The obtaining of a foreground mask in the SAR image corresponding to the full polarization data includes: Obtaining a total power map of the SAR image; Setting a threshold according to a target feature, and binarizing the total power map using the threshold; Isolated points in the binarization result are removed to obtain the foreground mask.

4. The method according to claim 3, characterized in that The step of setting a threshold value according to target characteristics and binarizing the total power graph using the threshold value comprises: performing constant false alarm rate detection on the total power graph to perform binarization; The removing of isolated points in the binarization result to obtain the foreground mask includes: The foreground mask is obtained by removing isolated points in the binarization result through a morphological opening operation.

5. The method according to claim 1, wherein The step of classifying pixels in the image to be classified into ship-type pixels and chaff-type pixels based on preset scattering feature differences includes: A support vector machine is used to classify pixels in the image to be classified, wherein the support vector machine is trained using scattering mechanism power proportion values of multiple ships and multiple foil strips.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining an image to be filtered according to the label value of each pixel in the segmentation result, wherein the label value of the background pixel is zero and the label value of the foreground pixel is non-zero; For each non-zero pixel, a neighborhood window of fixed size is selected; In the neighborhood window, the current pixel is updated using the largest non-zero label value in the connected neighborhood of the current non-zero pixel.

7. A device for segmenting ships and chaff in SAR images, characterized in that: include: An acquisition unit, used to acquire full polarization data of the SAR radar; a decomposition unit, configured to construct a coherence matrix for each pixel based on the full polarization data, and decompose the coherence matrix into the following scattering mechanisms: surface scattering, secondary scattering, and volume scattering; a generating unit, configured to generate a pseudo-color image based on a power ratio of each scattering mechanism; a mask unit, configured to obtain a foreground mask in the SAR image corresponding to the full polarization data, and apply the foreground mask to the pseudo-color image to obtain an image to be classified; The segmentation unit is used to classify the pixels in the image to be classified based on the preset scattering feature difference, mark them as ship category pixels and chaff category pixels, and obtain a segmentation result.

8. An electronic device comprising: processor; a memory for storing processor-executable instructions; The processor implements the method according to any one of claims 1 to 7 by running the executable instructions.

9. A computer-readable storage medium having computer instructions stored thereon, wherein when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

Images