CN112734788B - High-resolution SAR aircraft target contour extraction method, system, storage medium and equipment - Google Patents
High-resolution SAR aircraft target contour extraction method, system, storage medium and equipment Download PDFInfo
- Publication number
- CN112734788B CN112734788B CN202110020415.5A CN202110020415A CN112734788B CN 112734788 B CN112734788 B CN 112734788B CN 202110020415 A CN202110020415 A CN 202110020415A CN 112734788 B CN112734788 B CN 112734788B
- Authority
- CN
- China
- Prior art keywords
- image
- template
- contour
- aircraft
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 40
- 238000003860 storage Methods 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 51
- 238000001914 filtration Methods 0.000 claims abstract description 19
- 230000003287 optical effect Effects 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 abstract description 2
- 238000004088 simulation Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000002474 experimental method Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a high-resolution SAR aircraft target contour extraction method, a system, a storage medium and equipment, which are used for capturing an aircraft contour and generating a binary image to construct an aircraft target standard candidate template library; then extracting strong scattering points of SAR images to be matched, and filtering noise; then, the dimension of the binarization template is adjusted to be consistent with the dimension of the SAR image to be matched by adopting a bilinear interpolation method, the matching degree is calculated, and the template with the highest matching degree is taken as the best matching template of the aircraft target; and finally, extracting the contour of the optimal template, and returning to the SAR image to obtain the contour of the aircraft target to be detected, thereby completing contour extraction. The invention adopts the traditional image segmentation method, combines the high-resolution SAR image strong scattering point information and the public optical remote sensing information, and realizes the rapid and accurate extraction of the complete contour of the SAR aircraft target.
Description
Technical Field
The invention belongs to the technical field of remote sensing image processing, and particularly relates to a high-resolution SAR aircraft target contour extraction method, a system, a storage medium and equipment.
Background
The synthetic aperture radar (SAR, synthetic Aperture Radar) is an active earth observation system, can be installed on flight platforms of aircrafts, satellites, spacecraft and the like, realizes high-resolution microwave imaging by utilizing a synthetic aperture principle, has the characteristics of all-weather, high resolution, large breadth and the like, has certain surface penetration capacity, can obtain a large amount of useful information about detection regions after interpretation of SAR images, and has wide application in aspects of disaster monitoring, environment monitoring, military reconnaissance and the like. The radar has extremely strong discovery capability on targets such as planes, ships, tanks, vehicles and the like, so that the identification and classification of military targets based on SAR images becomes an important branch of SAR image interpretation. Currently, the three-stage identification procedure proposed by the lincoln laboratory of the university of ma is widely accepted:
(1) Detecting a target, namely detecting an interested part in the SAR image to obtain an ROI (region of interest);
(2) Target identification, namely screening the ROI obtained in the detection stage and removing false alarms formed by background ground objects;
(3) And classifying the targets, screening the screened targets again, and identifying the types, positions, postures, situations and the like of the targets.
The aircraft is taken as a main force army of modern war, is not only an important battlefield information reconnaissance object, but also an important battlefield detection object, and the military value of the aircraft is not ignored. Therefore, the fast and accurate identification of the aircraft target is an important means for obtaining favorable military information and capturing war initiative. And because the background environment is complex and other interference of other artificial targets, and the aircraft has complex outline and higher gesture sensitivity, the difficulty of recognition is higher, so that the difficulty of classification and recognition of the aircraft targets is higher. Therefore, research on the work of identifying aircraft targets in SAR images is being pursued.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a high-resolution SAR aircraft target contour extraction method, a storage medium and equipment, which fully utilize public information (corresponding to scene optical image information), make up the defect of SAR image target information deficiency, realize quick and accurate SAR aircraft target contour extraction, solve the problem that SAR image aircraft target contour is difficult to extract completely, and can be used for accurately extracting the contour containing a single aircraft target SAR image obtained through detection.
The invention adopts the following technical scheme:
the method for extracting the high-resolution SAR aircraft target contour comprises the steps of capturing the aircraft contour, generating a binary image and constructing an aircraft target standard candidate template library; then extracting strong scattering points of SAR images to be matched, and filtering noise; then, the dimension of the binarization template is adjusted to be consistent with the dimension of the SAR image to be matched by adopting a bilinear interpolation method, the matching degree is calculated, and the template with the highest matching degree is taken as the best matching template of the aircraft target; and finally, extracting the contour of the optimal template, and returning to the SAR image to obtain the contour of the aircraft target to be detected, thereby completing contour extraction.
Specifically, the construction of the aircraft target standard candidate template library is specifically as follows:
finding out corresponding regions from Google Earth websites according to longitude and latitude information provided in a target attribute file of an SAR airplane to be processed, extracting optical airplane images of corresponding categories, capturing an airplane outline through a Canny operator, generating a binary image after adjusting the outline by using photoshop, and carrying out rotation and translation processing on an airplane target in the binary image to realize construction of an airplane target standard candidate template library.
Specifically, the extraction of the target strong scattering points is specifically:
inputting a high-resolution SAR aircraft image to be processed, binarizing the image (0-1) by adopting an Otsu automatic threshold method, extracting target strong scattering points, and filtering part of noise.
Further, if the input image is f (i, j), the Otsu adaptive thresholding method specifically includes the following steps:
s201, calculating a gray level histogram of an input image;
s202, traversing all possible threshold sigma, classifying the pixel points of the input image, wherein if the gray value of the pixel point is larger than sigma, the pixel point is a foreground A, otherwise, the pixel point is a background B;
s203, calculating the number N of the pixel points of the area occupied by the foreground A and the background B A 、N B Proportion p A 、p B ；
S204, respectively calculating the average value u of the pixel values of the foreground A and background B areas A 、u B ；
S205, calculating an inter-class variance;
s206, selecting a threshold sigma for maximizing the inter-class variance value max For the best threshold, splitAn image is input.
Further, the inter-class variance is calculated as follows:
θ＝p A (u A -u) 2 +p B (u B -u) 2
where u represents the pixel mean of the whole image and θ is the resulting inter-class variance.
Specifically, the final matching degree y is calculated by using the spatial distribution characteristics of the high-resolution SAR aircraft target as follows:
wherein f (i, j) is the input image of the step, t (i, j) is a binary template, and both the values are m×n, and k represents the number of pixels with the pixel value not being 0 in the binary template.
Specifically, the Laplacian operator is adopted to extract the outline of the optimal template, as follows:
dx＝(f(i+1,j)-f(i,j))-(f(i,j)-f(i-1,j))
dy＝(f(i,j+1)-f(i,j))-(f(i,j)-f(i,j-1))
laplacian (i, j) =dx+dy, wherein f (i, j) is an optimal template, dx is a gradient value calculated in the horizontal direction of the image, dy is a gradient value calculated in the vertical direction of the image, and Laplacian (i, j) is a calculated contour.
Another technical solution of the present invention is a high resolution SAR aircraft target contour extraction system, comprising:
the construction module captures the outline of the aircraft and generates a binary image, and constructs an aircraft target standard candidate template library;
the filtering module is used for extracting strong scattering points of the image to be processed and filtering noise;
the matching module is used for adjusting the size of the binarized template to be consistent with the size of the aircraft target image to be matched by adopting a bilinear interpolation method, calculating the matching degree, and taking the template with the highest matching degree as the optimal matching template of the aircraft target;
and the extraction module is used for extracting the contour of the optimal template, returning the SAR image to obtain the contour of the aircraft target to be detected, and completing contour extraction.
Another aspect of the invention is a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the methods.
Another aspect of the present invention is a computing device, including:
one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods.
Compared with the prior art, the invention has at least the following beneficial effects:
according to the high-resolution SAR aircraft target contour extraction method, threshold segmentation and template matching are combined, so that full-automatic contour extraction of the high-resolution SAR image aircraft target is realized; the SAR aircraft target contour extraction is realized by adopting a traditional image processing method, so that the speed is high; the priori knowledge of SAR images is fully utilized, the extracted contour is attached to source data in aspects of azimuth, attitude and the like, and the accuracy is high.
Furthermore, the disclosed optical information is fully utilized by constructing the aircraft target standard candidate template library, and the defect of target information deficiency of SAR images is overcome.
Furthermore, the high-resolution SAR airplane image to be processed is input, the image is binarized (0-1) by adopting an Otsu automatic threshold method, the target strong scattering points are extracted, the interference of noise is reduced, and the target is clearer.
Furthermore, the Otsu self-adaptive threshold segmentation method is used for extracting the strong scattering points, so that the speed is high and the effect is good.
Further, the inter-class variance of the background and the target is maximized, which is beneficial to dividing noise and strong scattering points.
Furthermore, the matching degree of the target and the template is measured by adopting a pixel-level matching degree calculation mode, and the obtained template is attached to source data in the aspects of direction, gesture and the like.
Furthermore, the Laplacian operator is adopted to extract the outline of the optimal template, the outline of the obtained optimal template is extracted as a final segmentation result, and the problem of discontinuous segmentation of the SAR image target is solved.
In summary, the invention adopts the traditional image segmentation method, combines the high-resolution SAR image strong scattering point information and the public optical remote sensing information, and realizes the rapid and accurate extraction of the complete contour of the SAR aircraft target.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a schematic flow chart of the present invention;
FIG. 2 is an optical remote sensing image aircraft template and its binarization template;
FIG. 3 is an example of a high score satellite No. 3 image SAR aircraft target image used in the simulation of the present invention;
FIG. 4 is a graph of simulation results of the present invention with respect to FIG. 3;
FIG. 5 is a graph of simulation results of the comparison algorithm Canny operator versus FIG. 3;
FIG. 6 is an example of a terraSAR-X satellite image plane target image used in the simulation of the present invention;
FIG. 7 is a graph of simulation results of the present invention with respect to FIG. 6;
FIG. 8 is a graph of simulation results of the comparison algorithm Canny operator versus FIG. 6;
FIG. 9 is a diagram of simulation results of contour extraction of a high-resolution No. 3 satellite image SAR aircraft target image by using different template libraries;
fig. 10 is a diagram of simulation results of the invention for extracting contours from terra sar-X satellite image aircraft target images using different template libraries.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
Various structural schematic diagrams according to the disclosed embodiments of the present invention are shown in the accompanying drawings. The figures are not drawn to scale, wherein certain details are exaggerated for clarity of presentation and may have been omitted. The shapes of the various regions, layers and their relative sizes, positional relationships shown in the drawings are merely exemplary, may in practice deviate due to manufacturing tolerances or technical limitations, and one skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions as actually required.
The invention provides a high-resolution SAR aircraft target contour extraction method, which comprises the steps of firstly capturing an aircraft contour, generating a binary image and constructing an aircraft target standard candidate template library; then extracting strong scattering points and filtering noise; then, the dimension of the binarization template is adjusted by adopting a bilinear interpolation method, and the template with the highest matching degree is taken as the best matching template of the aircraft target; and finally, extracting the contour of the optimal template, and returning to the SAR image to obtain the contour of the aircraft target to be detected. Compared with the existing SAR target segmentation method, the method has the advantages that the problem of discontinuous segmentation caused by incomplete SAR image target information is solved by fully utilizing the public information (corresponding scene optical image information), and the rapid and accurate SAR aircraft target contour extraction is realized.
Referring to fig. 1, the method for extracting the target contour of the high-resolution SAR aircraft of the present invention comprises the following steps:
s1, finding out a corresponding region from a Google earth website according to longitude and latitude information provided in a target attribute file of an SAR aircraft to be processed, extracting an optical aircraft image of a corresponding category, capturing an aircraft contour by a Canny operator, generating a binary image after adjusting the contour by using a photoshop, and carrying out rotation and translation processing on the binary image to realize construction of an aircraft target standard candidate template library;
in the experiment, n=3 aircraft templates are extracted from an optical remote sensing image, fig. 2 (a) is an aircraft template example, and (b) is a corresponding binarization template, aircraft targets in the obtained binarization template are rotated every 15 degrees according to the spatial distribution characteristics of the aircraft targets in the SAR image, and then the template library is expanded by translating distances of 10 pixels in four directions of 45 degrees, 135 degrees and 45 degrees, so that 345 templates are finally obtained.
S2, inputting a high-resolution SAR aircraft image to be processed (a single image contains a single aircraft target), binarizing the image (0-1) by adopting an Otsu automatic threshold method, extracting target strong scattering points, and filtering part of noise;
if the input image is f (i, j), the Otsu adaptive threshold segmentation method specifically comprises the following steps:
s201, calculating a gray level histogram of an input image;
s202, traversing all possible threshold sigma (each gray value) to classify the pixel points of the input image, wherein if the gray value of the pixel points is larger than sigma, the pixel points are foreground A, otherwise, the pixel points are background B;
s203, calculating the number and the proportion of the pixel points of the area occupied by the foreground A and the background B, wherein the formula is as follows:
wherein N is the total number of image pixels, N A 、N B The number of pixels of the foreground and the background is p A 、p B The proportion of the foreground and background pixels is respectively;
s204, respectively calculating the pixel value average value of the foreground A area and the background B area, wherein the formula is as follows:
s205, calculating an inter-class variance (ICV):
θ＝p A (u A -u) 2 +p B (u B -u) 2
where u represents the pixel mean of the whole image and θ is the resulting inter-class variance.
S206, selecting a threshold sigma for maximizing ICV value max The input image is segmented for an optimal threshold.
S3, according to the size of the binarized SAR image to be segmented, adjusting the size of the binarized template to be consistent with the size of the binarized template by adopting a bilinear interpolation method, calculating the matching degree of the binarized template and the binarized template by using a cross correlation coefficient, and taking the template with the highest matching degree as the optimal matching template of the aircraft target;
the matching degree calculation method used by the invention fully utilizes the spatial distribution characteristics of the high-resolution SAR aircraft target, and comprises the following steps:
wherein f (i, j) is the input image of the step, t (i, j) is a binary template, both the magnitudes are m×n, k represents the number of pixels with the pixel value not being 0 in the binary template, and y is the final obtained matching degree.
S4, extracting the outline of the optimal template by using a Laplacian operator, and returning to the SAR image to obtain the outline of the aircraft target to be detected.
The template airplane has clear targets and complete contours, so that the Laplacian operator is adopted for processing, has the characteristic of isotropy in all directions, can extract the edges in any direction, is a second derivative operator, and is specifically defined as follows:
dx＝(f(i+1,j)-f(i,j))-(f(i,j)-f(i-1,j))
dy＝(f(i,j+1)-f(i,j))-(f(i,j)-f(i,j-1))
Laplacian(i,j)＝dx+dy
wherein f (i, j) is an optimal template, dx is a gradient value calculated in the horizontal direction of the image, dy is a gradient value calculated in the vertical direction of the image, and Laplacian (i, j) is a calculated contour.
In still another embodiment of the present invention, a high-resolution SAR aircraft target contour extraction system is provided, which can be used to implement the high-resolution SAR aircraft target contour extraction method described above, and in particular, the high-resolution SAR aircraft target contour extraction system includes a construction module, a filtering module, a matching module, and an extraction module.
The construction module extracts corresponding category optical aircraft images from Google earth websites, captures aircraft contours and generates binary images, and constructs an aircraft target standard candidate template library;
the filtering module is used for extracting strong scattering points of the image to be processed and filtering noise;
the matching module is used for adjusting the size of the binarized template to be consistent with the size of the image to be processed by adopting a bilinear interpolation method, calculating the matching degree of the binarized template and the image to be processed, and taking the template with the highest matching degree as the optimal matching template of the aircraft target;
and the extraction module is used for extracting the contour of the optimal template, returning the SAR image to obtain the contour of the aircraft target to be detected, and completing contour extraction.
In yet another embodiment of the present invention, a terminal device is provided, the terminal device including a processor and a memory, the memory for storing a computer program, the computer program including program instructions, the processor for executing the program instructions stored by the computer storage medium. The processor may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., which are the computational core and control core of the terminal adapted to implement one or more instructions, in particular adapted to load and execute one or more instructions to implement a corresponding method flow or a corresponding function; the processor in the embodiment of the invention can be used for extracting the target contour of the high-resolution SAR aircraft, and comprises the following steps: extracting corresponding class optical aircraft images from Google Earth websites, capturing aircraft contours, generating binary images, and constructing an aircraft target standard candidate template library; then extracting strong scattering points of the image to be processed, and filtering noise; then, the dimension of the binarization template is adjusted to be consistent with the dimension of the image to be processed by adopting a bilinear interpolation method, the matching degree of the binarization template and the image to be processed is calculated, and the template with the highest matching degree is taken as the best matching template of the aircraft target; and finally, extracting the contour of the optimal template, and returning to the SAR image to obtain the contour of the aircraft target to be detected, thereby completing contour extraction.
In a further embodiment of the present invention, the present invention also provides a storage medium, in particular, a computer readable storage medium (Memory), which is a Memory device in a terminal device, for storing programs and data. It will be appreciated that the computer readable storage medium herein may include both a built-in storage medium in the terminal device and an extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. The computer readable storage medium herein may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.
One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the respective steps of the method for high resolution SAR aircraft target profile extraction in the above-described embodiments; one or more instructions in a computer-readable storage medium are loaded by a processor and perform the steps of: extracting corresponding class optical aircraft images from Google Earth websites, capturing aircraft contours, generating binary images, and constructing an aircraft target standard candidate template library; then extracting strong scattering points of the image to be processed, and filtering noise; then, the dimension of the binarization template is adjusted to be consistent with the dimension of the image to be processed by adopting a bilinear interpolation method, the matching degree of the binarization template and the image to be processed is calculated, and the template with the highest matching degree is taken as the best matching template of the aircraft target; and finally, extracting the contour of the optimal template, and returning to the SAR image to obtain the contour of the aircraft target to be detected, thereby completing contour extraction.
1. Experimental conditions and methods
Software platform: opencv-python
The experimental method comprises the following steps: binarizing the high-resolution SAR image to be processed by using an Otsu automatic threshold segmentation method, calculating the matching degree of the high-resolution SAR image and templates in a template library by using a cross-correlation method, selecting an optimal template, and extracting the contour of the template by using a Laplacian operator to obtain a final result.
2. Simulation results
The experiment adopts the high-resolution No. 3 satellite image plane target image shown in fig. 3 and the terra SAR-X satellite image plane target image shown in fig. 6 to verify the method provided by the invention. Fig. 4 is a high-score number 3 satellite image plane target contour extraction result, and fig. 7 is a terra sar-X satellite image plane target contour extraction result.
3. Analysis of experimental results
A. The experiment adopts a Canny operator as a comparison algorithm. In the experiment, a bilateral filtering algorithm is used for filtering part of noise, and then a Canny operator is used for extracting the outline of the obtained result, the obtained result is shown in fig. 5 and 8, wherein fig. 5 is a high-resolution number 3 satellite image SAR aircraft target result, and fig. 8 is a terraSAR-X satellite image aircraft target result.
Referring to fig. 3 and 6, the aircraft target is often represented as a discrete scattering point distribution in the SAR image, and the strong scattering points are generally located at the positions where strong scattering structures exist, such as a nose, a tail wing, an engine, etc., so that the aircraft target has weak integrity and strong gesture sensitivity and is easily interfered by other surrounding ground objects, therefore, most of the edges of the strong scattering points extracted by the Canny operator cannot be used for extracting the complete aircraft contour.
B. In the method provided by the invention, the advantages and disadvantages of the template library play a decisive role in the accuracy of the finally obtained profile, so that the template library is formed by expanding aircraft templates with different numbers.
The experiment is carried out by respectively selecting n=3, 10 and 30 templates for expansion, finally obtaining template libraries with 345, 1150 and 3450 template numbers, respectively carrying out simulation experiments on a high-resolution No. 3 satellite image SAR aircraft target and a terraSAR-X satellite image aircraft target by using the three template libraries, wherein the experimental results are shown in fig. 9 (high-resolution No. 3 satellite image aircraft target contour extraction result) and fig. 10 (terraSAR-X satellite image aircraft target contour extraction result), wherein the two (a) are high-resolution No. 3 satellite image and terraSAR-X satellite image aircraft target source data, (b) and (c) and (d) are simulation results obtained by adopting the n=3 template libraries, the n=10 template libraries and the n=30 template libraries. As can be seen from the figure, when n=10 and n=30, part of templates in the template library will interfere with the results, while the template library of n=3 has higher universality, and different aircraft targets can obtain better contour results.
In summary, the method, the system, the storage medium and the equipment for extracting the high-resolution SAR aircraft target contour fully utilize the public optical remote sensing image (Google Earth) to make up the defect of smaller SAR image information quantity, and provide the method for extracting the high-resolution SAR aircraft target contour based on the heterogeneous template matching based on the defect, wherein the method can extract a complete contour for the SAR aircraft target with a discrete structure and has considerable speed.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above is only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited by this, and any modification made on the basis of the technical scheme according to the technical idea of the present invention falls within the protection scope of the claims of the present invention.
Claims (6)
1. The high-resolution SAR aircraft target contour extraction method is characterized by comprising the steps of capturing an aircraft contour, generating a binary image and constructing an aircraft target standard candidate template library; then extracting strong scattering points of SAR images to be matched, and filtering noise; then, the dimension of the binarization template is adjusted to be consistent with the dimension of the SAR image to be matched by adopting a bilinear interpolation method, the matching degree is calculated, and the template with the highest matching degree is taken as the best matching template of the aircraft target; finally, extracting the contour of the optimal template, returning to the SAR image to obtain the contour of the aircraft target to be detected, and finishing contour extraction;
the extraction of the target strong scattering points comprises the following steps:
inputting a to-be-processed high-resolution SAR aircraft image, binarizing the image (0-1) by adopting an Otsu automatic threshold method, extracting target strong scattering points, and filtering part of noise at the same time, wherein if the input image is f (i, j), the specific flow of the Otsu self-adaptive threshold segmentation method is as follows:
calculating a gray histogram of the input image; traversing all possible threshold sigma to classify the pixel points of the input image, wherein if the gray value of the pixel points is larger than sigma, the pixel points are foreground A, otherwise, the pixel points are background B; calculating the number N of pixel points in the area occupied by the foreground A and the background B A 、N B Proportion p A 、p B The method comprises the steps of carrying out a first treatment on the surface of the Respectively calculating the average value u of the pixel values of the foreground A and background B areas A 、u B The method comprises the steps of carrying out a first treatment on the surface of the Calculating an inter-class variance; selecting a threshold sigma that maximizes the value of the inter-class variance max Dividing the input image for an optimal threshold;
the final matching degree y is calculated by utilizing the spatial distribution characteristics of the high-resolution SAR aircraft target as follows:
wherein f (i, j) is the input image of the step, t (i, j) is a binary template, and both the values are m multiplied by n, and k represents the number of pixels with the pixel value not being 0 in the binary template;
the outline of the optimal template is extracted by using Laplacian operator, as follows:
dx＝(f(i+1，j)-f(i，j))-(f(i，j)-f(i-1，j))
dy＝(f(i，j+1)-f(i，j))-(f(i，j)-f(i，j-1))
laplacian (i, J) =dx+dy, wherein f (i, J) is an optimal template, dx is a gradient value calculated in the horizontal direction of the image, dy is a gradient value calculated in the vertical direction of the image, and Laplacian (i, J) is a calculated contour.
2. The method according to claim 1, wherein constructing the aircraft target standard candidate template library is specifically:
finding out corresponding regions from Google Earth websites according to longitude and latitude information provided in a target attribute file of an SAR airplane to be processed, extracting optical airplane images of corresponding categories, capturing an airplane outline through a Canny operator, generating a binary image after adjusting the outline by using photoshop, and carrying out rotation and translation processing on an airplane target in the binary image to realize construction of an airplane target standard candidate template library.
3. The method of claim 1, wherein the inter-class variance is calculated as follows:
θ＝p A (u A -u) 2 +p B (u B -u) 2
where u represents the pixel mean of the whole image and θ is the resulting inter-class variance.
4. A high resolution SAR aircraft target contour extraction system, comprising:
the construction module captures the outline of the aircraft and generates a binary image, and constructs an aircraft target standard candidate template library;
the filtering module is used for extracting the strong scattering points of the image to be processed and filtering noise, and extracting the strong scattering points of the target specifically comprises the following steps:
inputting a to-be-processed high-resolution SAR aircraft image, binarizing the image (0-1) by adopting an Otsu automatic threshold method, extracting target strong scattering points, and filtering part of noise at the same time, wherein if the input image is f (i, j), the specific flow of the Otsu self-adaptive threshold segmentation method is as follows:
calculating a gray histogram of the input image; traversing all possible threshold sigma to classify the pixel points of the input image, wherein if the gray value of the pixel points is larger than sigma, the pixel points are foreground A, otherwise, the pixel points are background B; calculating the number N of pixel points in the area occupied by the foreground A and the background B A 、N B Proportion p A 、p B The method comprises the steps of carrying out a first treatment on the surface of the Respectively calculating the average value u of the pixel values of the foreground A and background B areas A 、u B The method comprises the steps of carrying out a first treatment on the surface of the Calculating an inter-class variance; selecting a threshold sigma that maximizes the value of the inter-class variance max Dividing the input image for an optimal threshold; the method comprises the steps of carrying out a first treatment on the surface of the
The matching module adjusts the dimension of the binarization template to be consistent with the dimension of the aircraft target image to be matched by adopting a bilinear interpolation method, calculates the matching degree, takes the template with the highest matching degree as the best matching template of the aircraft target, and calculates the final matching degree y by utilizing the spatial distribution characteristic of the high-resolution SAR aircraft target as follows:
wherein f (i, j) is the input image of the step, t (i, j) is a binary template, and both the values are m multiplied by n, and k represents the number of pixels with the pixel value not being 0 in the binary template;
the extraction module is used for extracting the contour of the optimal template, returning to the SAR image to obtain the contour of the aircraft target to be detected, completing contour extraction, and extracting the contour of the optimal template by using a Laplacian operator, wherein the contour extraction module comprises the following steps:
dx＝(f(i+1，j)-f(i，j))-(f(i，j)-f(i-1，j))
dy＝(f(i，j+1)-f(i，j))-(f(i，j)-f(i，j-1))
laplacian (i, j) =dx+dy, wherein f (i, j) is an optimal template, dx is a gradient value calculated in the horizontal direction of the image, dy is a gradient value calculated in the vertical direction of the image, and Laplacian (i, j) is a calculated contour.
5. A computer readable storage medium storing one or more programs, wherein the one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform any of the methods of claims 1-4.
6. A computing device, comprising:
one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020415.5A CN112734788B (en) | 2021-01-07 | 2021-01-07 | High-resolution SAR aircraft target contour extraction method, system, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110020415.5A CN112734788B (en) | 2021-01-07 | 2021-01-07 | High-resolution SAR aircraft target contour extraction method, system, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112734788A CN112734788A (en) | 2021-04-30 |
| CN112734788B true CN112734788B (en) | 2024-04-09 |
Family
ID=75589661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110020415.5A Active CN112734788B (en) | 2021-01-07 | 2021-01-07 | High-resolution SAR aircraft target contour extraction method, system, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734788B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723425B (en) * | 2021-07-16 | 2023-06-20 | 深圳大学 | Aircraft model identification method, device, storage medium and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052942A (en) * | 2017-12-28 | 2018-05-18 | 南京理工大学 | A kind of visual pattern recognition methods of aircraft flight attitude |
| CN110031843A (en) * | 2019-05-09 | 2019-07-19 | 中国科学院自动化研究所 | SAR image object localization method, system, device based on ROI region |
| CN110210418A (en) * | 2019-06-05 | 2019-09-06 | 西安电子科技大学 | A kind of SAR image Aircraft Targets detection method based on information exchange and transfer learning |
| CA3038176A1 (en) * | 2019-03-27 | 2020-09-27 | 4DM Inc. | Object motion mapping from single-pass electro-optical satellite imaging sensors |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10706551B2 (en) * | 2017-03-30 | 2020-07-07 | 4DM Inc. | Object motion mapping using panchromatic and multispectral imagery from single pass electro-optical satellite imaging sensors |
-
2021
- 2021-01-07 CN CN202110020415.5A patent/CN112734788B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052942A (en) * | 2017-12-28 | 2018-05-18 | 南京理工大学 | A kind of visual pattern recognition methods of aircraft flight attitude |
| CA3038176A1 (en) * | 2019-03-27 | 2020-09-27 | 4DM Inc. | Object motion mapping from single-pass electro-optical satellite imaging sensors |
| CN110031843A (en) * | 2019-05-09 | 2019-07-19 | 中国科学院自动化研究所 | SAR image object localization method, system, device based on ROI region |
| CN110210418A (en) * | 2019-06-05 | 2019-09-06 | 西安电子科技大学 | A kind of SAR image Aircraft Targets detection method based on information exchange and transfer learning |
Non-Patent Citations (1)
| Title |
|---|
| 申海洋 ; 李月娥 ; .基于边缘轮廓特征匹配的飞机目标识别.测试技术学报.2013,(第03期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112734788A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108510467B (en) | SAR image target identification method based on depth deformable convolution neural network | |
| Nie et al. | Inshore ship detection based on mask R-CNN | |
| Zhang et al. | S-CNN-based ship detection from high-resolution remote sensing images | |
| Unlu et al. | Using shape descriptors for UAV detection | |
| Siriborvornratanakul | An automatic road distress visual inspection system using an onboard in-car camera | |
| Wang et al. | Airport detection in remote sensing images: A method based on saliency map | |
| Haker et al. | Knowledge-based segmentation of SAR data with learned priors | |
| Li et al. | Road lane detection with gabor filters | |
| Sridevi et al. | A survey on monochrome image segmentation methods | |
| CN113536963A (en) | SAR image airplane target detection method based on lightweight YOLO network | |
| Shostko et al. | Optical-electronic system of automatic detection and higt-precise tracking of aerial objects in real-time. | |
| Long et al. | Object detection research of SAR image using improved faster region-based convolutional neural network | |
| Liu et al. | Vehicle detection from aerial color imagery and airborne LiDAR data | |
| CN112734788B (en) | High-resolution SAR aircraft target contour extraction method, system, storage medium and equipment | |
| Li et al. | Automatic infrared ship target segmentation based on structure tensor and maximum histogram entropy | |
| Albrecht et al. | Visual maritime attention using multiple low-level features and naive bayes classification | |
| Jiao et al. | A novel and fast corner detection method for sar imagery | |
| Cai et al. | Man-made object detection based on texture clustering and geometric structure feature extracting | |
| CN116805327A (en) | Infrared small target tracking method based on dynamic convolution kernel | |
| Li et al. | DAR-Net: dense attentional residual network for vehicle detection in aerial images | |
| Pelapur et al. | Vehicle detection and orientation estimation using the radon transform | |
| Wang et al. | An automatic bridge detection technique for high resolution SAR images | |
| Han et al. | Aircraft target detection in polsar image based on region segmentation and multi-feature decision | |
| Huang et al. | Passive ground camouflage target recognition based on gray feature and texture feature in SAR images | |
| KR101723028B1 (en) | Image processing system for integrated management of image information changing in real time |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |