CN114092748B - SAR (synthetic aperture radar) unintentional interference detection method, device, equipment and medium - Google Patents

SAR (synthetic aperture radar) unintentional interference detection method, device, equipment and medium Download PDF

Info

Publication number
CN114092748B
CN114092748B CN202111446821.4A CN202111446821A CN114092748B CN 114092748 B CN114092748 B CN 114092748B CN 202111446821 A CN202111446821 A CN 202111446821A CN 114092748 B CN114092748 B CN 114092748B
Authority
CN
China
Prior art keywords
sar
interference
image
browsing
detected
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
Application number
CN202111446821.4A
Other languages
Chinese (zh)
Other versions
CN114092748A (en
Inventor
申佳源
韩冰
潘宗序
丁赤飚
洪文
胡玉新
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aerospace Information Research Institute of CAS
Original Assignee
Aerospace Information Research Institute of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Aerospace Information Research Institute of CAS filed Critical Aerospace Information Research Institute of CAS
Priority to CN202111446821.4A priority Critical patent/CN114092748B/en
Publication of CN114092748A publication Critical patent/CN114092748A/en
Application granted granted Critical
Publication of CN114092748B publication Critical patent/CN114092748B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
    • G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
    • G01S13/9021—SAR image post-processing techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Abstract

The disclosure provides a method, a device, equipment and a medium for SAR unintentional interference detection. The method comprises the following steps: acquiring an SAR browsing image, wherein the SAR browsing image is a zoom preview image of an SAR product image generated by an SAR system; dividing the SAR browsing image into a plurality of images to be detected; sequentially inputting each image to be detected into a preset classification model to identify whether each image to be detected has unconscious interference or not; and when the image to be detected has the unintentional interference, determining the interference position of the unintentional interference in the SAR browsing image. According to the method, the problem is converted into the two classification problems of image processing, the browsing graph with small data volume is utilized, the deep neural network is trained to extract the characteristics of the interference elements on the image level, whether the SAR image has the unconscious interference or not is identified, and the rapid detection and accurate positioning of the interference are realized.

Description

SAR (synthetic aperture radar) unintentional interference detection method, device, equipment and medium
Technical Field
The disclosure relates to the technical field of remote sensing image intelligent detection, in particular to a method, a device, equipment and a medium for detecting SAR unconsciousness interference.
Background
In the working process of transmitting a high-power electromagnetic wave detection target, an echo signal of a Synthetic Aperture Radar (SAR) inevitably dopes a same-frequency-band electromagnetic interference signal in the surrounding environment. The SAR interference is divided according to energy sources, and can be divided into two categories of passive interference and active interference. Active interference is interference generated by an external electromagnetic wave radiation source and can be divided into conscious interference and unconscious interference. The unintentional interference mainly refers to radio frequency interference caused when working frequencies of communication, televisions, ground radars and the like are within the frequency range of the SAR receiver. The unintentional interference usually does not completely spread over the whole image, but exists in the SAR image in the characteristics of scattered distribution and block aggregation, and forms multipoint and local shielding on the real image. The existence of the interference signal can influence the results of SAR image processing and information extraction, thereby reducing the application efficiency of SAR image products.
The conventional SAR interference detection method is usually tightly combined with an interference suppression method, and is mainly expanded from a parameterized angle of a time domain and a non-parameterized angle of a frequency domain. Common interference detection methods mainly include a notch method, a wavelet packet analysis method, a method based on eigenvalue decomposition and a time-frequency domain detection method based on a neural network. In the notch method, a change domain detection algorithm is used for detecting unconscious interference, when the number of interference frequency points is large, all interference points cannot be accurately detected, discontinuity of a change domain can be caused after subsequent inhibition, a subsequent imaging result is further influenced, and spatial position information of an echo signal imaging result is damaged in the process of converting to other domains, so that the detection result cannot reflect the position of the interference in an original image. The detection method based on wavelet packet analysis and characteristic decomposition needs to perform a series of decomposition operations on the SAR image to be detected, the algorithm complexity is high, time consumption is long when a large amount of data is processed, and similarly, the original spatial information cannot be maintained when the method decomposes the original echo signal, and the position of the interference cannot be accurately positioned. The time-frequency domain detection method based on the neural network needs to perform short-time Fourier transformation on original echo data to convert the original echo data into a time-frequency domain, and the two domains are mutually converted, so that the calculation amount is large, and the position of the interference cannot be specifically determined.
Disclosure of Invention
The present disclosure provides a method, apparatus, device and medium for detecting SAR unintentional interference, which at least solve the above technical problems.
One aspect of the present disclosure provides a method for detecting SAR unintentional interference, including: acquiring an SAR browsing image, wherein the SAR browsing image is a zoom preview image of an SAR product image generated by an SAR system; dividing the SAR browsing image into a plurality of images to be detected; sequentially inputting each image to be detected into a preset classification model so as to identify whether each image to be detected has unconscious interference or not; and when the image to be detected has unconscious interference, determining the interference position of the unconscious interference in the SAR browsing image.
Optionally, the dividing the SAR browse map into a plurality of images to be detected includes: acquiring a stripe boundary of the SAR browsing map, wherein the stripe boundary is a boundary between each stripe which is generated by the SAR system in a stripe mode and is adjacent in the distance direction; dividing the SAR browsing image into a plurality of strip images in the distance direction according to the strip boundary; and moving and scanning on a single strip image through a sliding window to obtain a plurality of images to be detected of the strip image, wherein the area of the sliding window moving upwards in distance is a sliding line, the sliding positions of the sliding window in the sliding line are not overlapped, and the sliding window moves along a pixel line by line in the azimuth direction.
Optionally, when there is unintentional interference in the image to be detected, determining an interference position of the unintentional interference in the SAR browse map includes: when at least one image to be detected in the sliding row has unconscious interference, marking the sliding behavior interference row; and acquiring the position of the interference row in the SAR browsing map to determine the interference position of the unintentional interference in the SAR browsing map.
Optionally, the obtaining the position of the interference row in the SAR browse map to determine the interference position of the unintentional interference in the SAR browse map includes: acquiring an interference starting row and an interference ending row in continuous interference rows; and determining the interference range of the interference position based on the positions of the interference starting line and the interference ending line.
Optionally, when there are multiple interference positions, comparing the scanning order of the interference start line and the interference end line of the sliding window at each interference position; and when the scanning sequence of the interference starting line is before the interference ending line, determining the interference position as a target position.
Optionally, the method further comprises: obtaining the scaling between the SAR browsing image and the SAR product image; and determining the actual interference position in the SAR product map according to the interference position in the SAR browsing map and the scaling.
Optionally, the acquiring a stripe boundary of the SAR browse map includes: acquiring size information of each strip image of the SAR product image in the distance direction; and determining each strip boundary of the SAR browsing image in the distance direction according to the size information and the scaling.
A second aspect of the present disclosure provides a SAR unintentional interference detection device, comprising: the SAR browsing image acquisition module is used for acquiring an SAR browsing image which is a zoom preview image of an SAR product image generated by an SAR system; the dividing module is used for dividing the SAR browsing image into a plurality of images to be detected; the identification module is used for sequentially inputting each image to be detected into a pre-trained classification model so as to identify whether each image to be detected has unconscious interference or not; and the positioning module is used for determining the interference position of the unintentional interference in the SAR browsing image when the unintentional interference exists in the image to be detected.
A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the SAR unintentional interference detection method described above.
A fourth aspect of the present disclosure provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described SAR unintentional interference detection method.
The at least one technical scheme adopted in the embodiment of the disclosure can achieve the following beneficial effects:
according to the method, interference detection is switched in from the angle of the whole image level, the problem is converted into the two classification problems of image processing according to the characteristics of scattered distribution and blocking aggregation of unconscious interference in the SAR image, a deep neural network is trained to extract the characteristics of interference elements on the image level, whether unconscious interference exists in the SAR image is identified, accurate positioning of the interference position is achieved by setting a sliding window and sliding rules of the sliding window, calculation of a large amount of original echo data is avoided, rapid detection is conducted on the image level, and a foundation is provided for subsequent operations such as interference suppression and image information extraction.
Drawings
For a more complete understanding of the present disclosure and the advantages thereof, reference is now made to the following descriptions taken in conjunction with the accompanying drawings, in which:
fig. 1 schematically illustrates a flowchart of a SAR unintentional interference detection method provided by an embodiment of the present disclosure;
fig. 2 schematically illustrates a browsing graph partitioning diagram of an SAR unintentional interference detection method according to an embodiment of the present disclosure;
fig. 3 schematically illustrates a block diagram of a SAR unintentional interference detection apparatus provided in an embodiment of the present disclosure;
fig. 4 schematically shows a block diagram of an electronic device provided in an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The words "a", "an" and "the" and the like as used herein are also intended to include the meanings of "a plurality" and "the" unless the context clearly dictates otherwise. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Some block diagrams and/or flow diagrams are shown in the figures. It will be understood that some blocks of the block diagrams and/or flowchart illustrations, or combinations thereof, 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, or other programmable data processing apparatus, such that the instructions, which execute via the processor, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks.
Accordingly, the techniques of this disclosure may be implemented in hardware and/or software (including firmware, microcode, etc.). In addition, the techniques of this disclosure may take the form of a computer program product on a computer-readable medium having instructions stored thereon for use by or in connection with an instruction execution system. In the context of this disclosure, a computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the instructions. For example, the computer readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. Specific examples of the computer readable medium include: magnetic storage devices, such as magnetic tape or Hard Disk Drives (HDDs); optical storage devices, such as compact disks (CD-ROMs); a memory, such as a Random Access Memory (RAM) or a flash memory; and/or wired/wireless communication links.
Fig. 1 schematically shows a flowchart of a SAR unintentional interference detection method provided by an embodiment of the present disclosure.
As shown in fig. 1, a method for detecting an SAR unintentional interference provided by the embodiment of the present disclosure includes steps S110 to S140.
In S110, an SAR browse map is obtained, where the SAR browse map is a scaled preview of an SAR product map generated by the SAR system.
In the embodiment of the disclosure, an SAR browse map is selected as an object of SAR image processing, for a high-resolution SAR, the echo data volume obtained by one-time imaging is usually different from several GB to several hundred GB, links such as data segmentation, auxiliary data extraction and verification, logic scenery segmentation and browse map generation, standard product production and the like are generally required in the production process of an SAR product map, and the size of the SAR browse map generated in the process for SAR image data management and product query browsing is only one tenth or even one hundredth of the size of the SAR product map. And the SAR browsing image is usually produced at the first time of acquiring the data before the SAR product image, so that the SAR browsing image is selected as an image processing object for the unintentional interference detection, the detection data volume and the detection time can be greatly reduced, and the detection speed of the unintentional interference is improved.
In S120, the SAR browse map is divided into a plurality of images to be detected.
In the embodiment of the disclosure, a stripe boundary of the SAR browsing map is obtained, wherein the stripe boundary is a boundary between each adjacent stripe in the distance direction generated by the SAR system in a stripe mode; dividing the SAR browsing image into a plurality of strip images in the distance direction according to the strip boundary; and moving and scanning on the single strip image through a sliding window to obtain a plurality of images to be detected of the strip image, wherein the area of the sliding window moving upwards in distance is a sliding line, the sliding positions of the sliding window in the sliding line are not overlapped, and the sliding window moves line by line along the pixel line in the azimuth direction. Where the range direction (or skew) is the direction of the line-of-sight distance of the SAR to the imaging target, and the azimuth direction is used to denote the dimension perpendicular to the range direction or parallel to the radar along the track axis.
Fig. 2 schematically illustrates a browsing graph partitioning diagram of an SAR unintentional interference detection method provided by the embodiment of the present disclosure.
As shown in fig. 2, in the stripe mode of the SAR system, the SAR system scans a plurality of stripes in an upward distance at the same time to obtain an image of an area in the upward distance to form an SAR product map, the scanned areas of different stripes are different, the actual image obtained by imaging of the SAR system is a complete image, and the SAR browsing map is divided according to the stripe boundaries, so that the data size of the image detected each time can be reduced, and the detection accuracy can be improved. And setting a sliding window on each strip, sliding the sliding window on the currently selected strip image to scan the area, cutting and caching. The size of the sliding window is set by a user, for example, the size of the sliding window in the distance direction can be set to be one third of the width of the strip in the distance direction, that is, the sliding window can select 3 images to be detected on the sliding line, the 3 images to be detected have no overlapping area, and the images to be detected are cut off and numbered according to the sliding sequence of the sliding window. And after all the areas of the sliding line are selected on the sliding line by the sliding window, moving the sliding window line by line along the pixel line, and scanning the next sliding line until all the areas of the SAR browsing image are scanned. The embodiment of the disclosure provides a position basis for the subsequent accurate positioning of the detected unintentional interference by setting the sliding window and setting the scanning rule of the sliding window.
In the embodiment of the present disclosure, acquiring a stripe boundary of an SAR browse map includes: acquiring size information of each strip image of the SAR product image in the distance direction; and determining each strip boundary of the SAR browsing image in the distance direction according to the size information and the scaling. The SAR browsing image is a thumbnail browsing image of an SAR product image finally generated by the SAR system, and is also a corresponding product descriptive (XML) file synchronously produced with the SAR product image, the XML file comprises size information of the product image in the direction and the distance direction and size information of the browsing image, the scaling between the SAR browsing image and the SAR product image can be obtained through the size information of the product image and the browsing image, and the width of each strip image in the SAR product image in the distance direction is also recorded in the XML file. For example, the SAR production map has three bands, the widths of the bands are WR1, WR2 and WR3 in the distance direction, the length of the to-be-processed browsing map in the distance direction is a, the scaling ratio between the browsing map and the production map is a/(WR1+ WR2+ WR3), the size of each band image in the SAR browsing map in the distance direction is WR1 a/(WR1+ WR2+ WR3), WR2 a/(WR1+ WR2+ WR3), WR3 a/(WR1+ WR2+ WR3), and the SAR browsing map is divided in the distance direction according to the size of the obtained band image.
In S130, each image to be detected is sequentially input into a preset classification model to identify whether there is unintentional interference in each image to be detected.
In the embodiment of the disclosure, a known browsing map with interference is prepared in advance, the known browsing map is cut into blocks, data expansion is performed through rotation, turning and the like to obtain a data set, after whether the data set is marked with interference or not, a training set and a test set are respectively obtained by extracting the marked data set, a ResNet network pre-trained on an ImageNet data set is called, the ResNet is iteratively trained by using the training set, and parameters of an output layer are finely adjusted to obtain a classification model suitable for the browsing map data set with unintentional interference. And (3) detecting the accuracy of the obtained classification model by using the test set, correcting the model and improving the detection accuracy of the classification model. It should be understood that RetNet in the present disclosure may also be replaced with LeNet, VGG-16, and other deep neural networks for classification. Through in the above-mentioned classification model trained with the image input that will wait to detect, classification model can discern whether every image that waits to detect has unconscious interference through extracting the image characteristic.
In S140, when the image to be detected has the unintentional interference, the interference position of the unintentional interference in the SAR browsing map is determined.
In the embodiment of the disclosure, when at least one image to be detected in the sliding row has unconscious interference, marking the sliding behavior interference row; and acquiring the position of the interference row in the SAR browsing map to determine the interference position of the unintentional interference in the SAR browsing map. For example, the size of the sliding window in the azimuth direction is h, the sliding window moves line by line h, each line is cut according to the sizes of WR1 × a/(WR1+ WR2+ WR3), WR2 × a/(WR1+ WR2+ WR3), WR3 × a/(WR1+ WR2+ WR3) to obtain the to-be-detected images, and the to-be-detected images are numbered in sequence, each number is i, the to-be-detected image mark value with interference is detected to be 1, the to-be-detected image mark value without interference is detected to be 0, if i% 3 is 0, it indicates that all the to-be-detected images of the sliding line are detected, and when the mark value of all the to-be-detected images of the sliding line is greater than or equal to 1, it indicates that interference exists in the sliding line, and determines the number of lines of the interference line in the browsing image. Otherwise, it is marked as a non-interfering row.
In the embodiment of the disclosure, an interference starting row and an interference ending row in consecutive interference rows are obtained; and determining the interference range of the interference position based on the positions of the interference starting line and the interference ending line. If the adjacent previous line of the interference line is a non-interference line, the interference line interferes with the initial line and is marked as line1(ii) a If the adjacent line of the interference line is a non-interference line, the interference line interferes with the termination line and is marked as line2；line1And line2The number of lines of the pixel line where the interference line is located is combined with the size of the sliding window to calculate and obtain an accurate interference position,
pixel behavior in the presence of interference: linestart＝1ine1+h-1；
Pixel behavior when interference disappears: lineend＝line2-1。
Since the interference position is located to provide information for subsequent interference suppression, a single distance pulse is required to be taken for interference suppression, and therefore, the pixel row in the SAR browsing image strip needs to be accurately located. The SAR unconscious interference detection method in the embodiment of the disclosure can be used for rapidly detecting and accurately positioning the interference position, thereby being beneficial to subsequently extracting accurate pulse for interference suppression.
In the embodiment of the present disclosure, the imaging time of each band may also be obtained, and the interference range of the interference position determined above is used to obtain the time range of interference generation and end.
In the embodiment of the disclosure, when there are a plurality of interference positions, comparing the scanning sequence of the interference start line and the interference end line of the sliding window at each interference position; and when the scanning sequence of the interference starting line is before the interference ending line, determining the interference position as the target position. Because the samples with little interference proportion or suspected interference in the training set are marked as interference when the classification model is trained, the classifier model obtained by training is biased to be stricter at the momentDuring actual progressive scanning, a plurality of interference start lines and interference stop lines may be calculated, the interference start lines and the interference stop lines are temporarily stored, screening is performed after scanning is finished, and if line existsstart＜lineendThe set of interference positions is reserved, and the fault-tolerant mechanism of 'first relaxation and then screening' can make the detection of the single-step classification model more strict, but the accuracy of the overall detection can be improved after the last screening is added.
The method for detecting the SAR unintentional interference provided in the embodiment of the present disclosure further includes: obtaining the scaling between the SAR browsing image and the SAR product image; and determining the actual interference position in the SAR product map according to the interference position and the scaling in the SAR browsing map. The actual interference position on the SAR product map can be obtained by obtaining the interference position and the scaling on the SAR browsing map, and because the data size of the browsing map is equivalent to one tenth or even one hundredth of the product map, the interference position on the SAR product map can be positioned by processing the browsing map with smaller data volume, thereby greatly reducing the data volume of image processing and improving the detection speed.
According to the method, interference detection is switched in from the angle of the whole image level, the problems are converted into two classification problems of image processing according to the characteristics of scattered distribution and blocking aggregation of unconscious interference in the image, a deep neural network is trained to extract the characteristics of interference elements on the image level so as to identify whether the SAR image has unconscious interference or not, the interference position is accurately positioned by setting a sliding window and a sliding rule thereof, the calculation of a large amount of original echo data is avoided, rapid detection is carried out on the image level, and a foundation is provided for subsequent operations such as interference suppression and image information extraction.
Fig. 3 schematically shows a block diagram of a SAR unintentional interference detection device according to an embodiment of the present disclosure.
As shown in fig. 3, a block diagram of a structure of an SAR unintentional interference detection apparatus according to an embodiment of the present disclosure includes: the system comprises an acquisition module 310, a dividing module 320, an identification module 330 and a positioning module 340.
Specifically, the obtaining module 310 is configured to obtain an SAR browse map, where the SAR browse map is a zoom preview of an SAR product map generated by an SAR system; a dividing module 320, configured to divide the SAR browse map into a plurality of images to be detected; the identification module 330 is configured to sequentially input each image to be detected into a pre-trained classification model to identify whether each image to be detected has unintentional interference; and the positioning module 340 is configured to determine an interference position of the unintentional interference in the SAR browse map when the image to be detected has the unintentional interference.
Preferably, in this embodiment of the present disclosure, the SAR unintentional interference detection apparatus further includes a comparison module and a target position determination module, where the comparison module is configured to compare the scanning order of the interference start line and the interference end line of the sliding window at each interference position when there are a plurality of interference positions, and the target position determination module is configured to determine that the interference position is the target position when the scanning order of the interference start line is before the interference end line. Interference positions obtained by the positioning module are further screened by the comparison module and the target position determination module, so that the accuracy of the SAR unconscious interference detection device in positioning the interference positions is improved.
It is understood that the obtaining module 310, the dividing module 320, the identifying module 330, the locating module 340, the comparing module and the target position determining module may be combined into one module to be implemented, or any one of the modules may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module. According to an embodiment of the present invention, at least one of the obtaining module, the dividing module, the identifying module, the locating module, the comparing module and the target position determining module may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or in a suitable combination of three implementations of software, hardware and firmware. Alternatively, at least one of the obtaining module, the dividing module, the identifying module, the locating module, the comparing module and the target position determining module may be at least partially implemented as a computer program module which, when executed by a computer, may perform the functions of the respective modules.
Fig. 4 schematically shows a block diagram of an electronic device provided in an embodiment of the present disclosure.
As shown in fig. 4, the electronic device described in this embodiment includes: the electronic device 400 includes a processor 410, a computer-readable storage medium 420. The electronic device 400 may perform the method described above with reference to fig. 1 to enable detection of a particular operation.
In particular, processor 410 may include, for example, a general purpose microprocessor, an instruction set processor and/or related chip set and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), and/or the like. The processor 410 may also include onboard memory for caching purposes. Processor 410 may be a single processing unit or a plurality of processing units for performing the different actions of the method flows described with reference to fig. 1 in accordance with embodiments of the present disclosure.
Computer-readable storage medium 420 may be, for example, any medium that can contain, store, communicate, propagate, or transport the instructions. For example, a readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. Specific examples of the readable storage medium include: magnetic storage devices, such as magnetic tape or Hard Disk Drives (HDDs); optical storage devices, such as compact disks (CD-ROMs); a memory, such as a Random Access Memory (RAM) or a flash memory; and/or wired/wireless communication links.
The computer-readable storage medium 420 may include a computer program 421, which computer program 421 may include code/computer-executable instructions that, when executed by the processor 410, cause the processor 410 to perform a method flow such as that described above in connection with fig. 1 and any variations thereof.
The computer program 421 may be configured with, for example, computer program code comprising computer program modules. For example, in an example embodiment, code in computer program 421 may include one or more program modules, including for example 421A, modules 421B, … …. It should be noted that the division and number of modules are not fixed, and those skilled in the art may use suitable program modules or program module combinations according to actual situations, which when executed by the processor 410, enable the processor 410 to perform the method flow described above in connection with fig. 1 and any variations thereof, for example.
According to an embodiment of the present invention, at least one of the obtaining module 310, the dividing module 320, the identifying module 330, the locating module 340, the comparing module and the target position determining module may be implemented as a computer program module as described with reference to fig. 4, which, when executed by the processor 410, may perform the respective operations described above.
The present disclosure also provides a computer-readable medium, which may be embodied in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer readable medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.
Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
While the disclosure has been shown and described with reference to certain exemplary embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the disclosure as defined by the appended claims and their equivalents. Accordingly, the scope of the present disclosure should not be limited to the above-described embodiments, but should be defined not only by the appended claims, but also by equivalents thereof.

Claims (9)

1. An SAR unintentional interference detection method is characterized by comprising the following steps:
acquiring an SAR browsing image, wherein the SAR browsing image is a zoom preview image of an SAR product image generated by an SAR system;
dividing the SAR browsing image into a plurality of images to be detected;
sequentially inputting each image to be detected into a preset classification model so as to identify whether each image to be detected has unconscious interference or not;
when the image to be detected has unconscious interference, determining the interference position of the unconscious interference in the SAR browsing image;
wherein the dividing the SAR browsing image into a plurality of images to be detected comprises:
acquiring a stripe boundary of the SAR browsing map, wherein the stripe boundary is a boundary between each stripe which is generated by the SAR system in a stripe mode and is adjacent in the distance direction;
dividing the SAR browsing image into a plurality of strip images in the distance direction according to the strip boundary;
and moving and scanning on a single strip image through a sliding window to obtain a plurality of images to be detected of the strip image, wherein the area of the sliding window moving upwards in distance is a sliding line, the sliding positions of the sliding window in the sliding line are not overlapped, and the sliding window moves line by line along a pixel line in the azimuth direction.
2. The SAR unintentional disturbance detection method according to claim 1, wherein when unintentional disturbance exists in the image to be detected, the determining of the disturbance position of the unintentional disturbance in the SAR browsing image comprises:
when at least one image to be detected in the sliding row has unconscious interference, marking the sliding behavior interference row;
and acquiring the position of the interference row in the SAR browsing map to determine the interference position of the unintentional interference in the SAR browsing map.
3. The SAR unintentional interference detection method according to claim 2, wherein the obtaining of the position of the interference row in the SAR browsing map to determine the interference position of the unintentional interference in the SAR browsing map comprises:
acquiring an interference starting row and an interference ending row in continuous interference rows;
and determining the interference range of the interference position based on the positions of the interference starting line and the interference ending line.
4. The SAR unintentional interference detection method according to claim 3,
when the interference position is multiple, comparing the scanning sequence of the interference starting line and the interference ending line of the sliding window at each interference position;
and when the scanning sequence of the interference starting line is before the interference ending line, determining the interference position as a target position.
5. The SAR unintentional interference detection method according to claim 1, characterized in that it further comprises:
obtaining the scaling between the SAR browsing image and the SAR product image;
and determining the actual interference position in the SAR product map according to the interference position in the SAR browsing map and the scaling.
6. The SAR unintentional interference detection method according to claim 5, wherein the obtaining the band boundary of the SAR browsing map comprises:
acquiring size information of each strip image of the SAR product image in the distance direction;
and determining each strip boundary of the SAR browsing image in the distance direction according to the size information and the scaling.
7. An SAR unintentional interference detection device, comprising:
the SAR browsing image acquisition module is used for acquiring an SAR browsing image which is a zoom preview image of an SAR product image generated by an SAR system;
the dividing module is used for dividing the SAR browsing image into a plurality of images to be detected;
the identification module is used for sequentially inputting each image to be detected into a pre-trained classification model so as to identify whether each image to be detected has unconscious interference or not;
the positioning module is used for determining the interference position of the unconscious interference in the SAR browsing image when the unconscious interference exists in the image to be detected;
wherein the dividing the SAR browsing map into a plurality of images to be detected comprises:
acquiring a stripe boundary of the SAR browsing map, wherein the stripe boundary is a boundary between each stripe which is generated by the SAR system in a stripe mode and is adjacent in the distance direction;
dividing the SAR browsing image into a plurality of strip images in the distance direction according to the strip boundary;
and moving and scanning on a single strip image through a sliding window to obtain a plurality of images to be detected of the strip image, wherein the area of the sliding window moving upwards in distance is a sliding line, the sliding positions of the sliding window in the sliding line are not overlapped, and the sliding window moves along a pixel line by line in the azimuth direction.
8. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-6.
9. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 6.
CN202111446821.4A 2021-11-30 2021-11-30 SAR (synthetic aperture radar) unintentional interference detection method, device, equipment and medium Active CN114092748B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111446821.4A CN114092748B (en) 2021-11-30 2021-11-30 SAR (synthetic aperture radar) unintentional interference detection method, device, equipment and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111446821.4A CN114092748B (en) 2021-11-30 2021-11-30 SAR (synthetic aperture radar) unintentional interference detection method, device, equipment and medium

Publications (2)

Publication Number Publication Date
CN114092748A CN114092748A (en) 2022-02-25
CN114092748B true CN114092748B (en) 2022-06-14

Family

ID=80306179

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111446821.4A Active CN114092748B (en) 2021-11-30 2021-11-30 SAR (synthetic aperture radar) unintentional interference detection method, device, equipment and medium

Country Status (1)

Country Link
CN (1) CN114092748B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114966691B (en) * 2022-07-14 2022-10-18 成都戎星科技有限公司 Satellite SAR data recording quick-look and application system
CN116184407B (en) * 2023-02-22 2023-08-22 北京东方至远科技股份有限公司 Automatic marking method, device and equipment for SAR image radiation quality problem

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107369163A (en) * 2017-06-15 2017-11-21 西安微电子技术研究所 A kind of quick SAR image object detection method based on best entropy Double Thresholding Segmentation
CN110221256A (en) * 2019-06-21 2019-09-10 西安电子科技大学 SAR disturbance restraining method based on depth residual error network
CN113469088A (en) * 2021-07-08 2021-10-01 西安电子科技大学 SAR image ship target detection method and system in passive interference scene

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7830300B2 (en) * 2006-10-26 2010-11-09 Raytheon Company Radar imaging system and method using directional gradient magnitude second moment spatial variance detection
US20090091492A1 (en) * 2007-10-09 2009-04-09 The Mitre Corporation Detection and mitigation radio frequency memory (DRFM)-based interference in synthetic aperture radar (SAR) images
CN102693530B (en) * 2012-06-13 2014-11-12 西安电子科技大学 Synthetic aperture radar (SAR) image despeckle method based on target extraction and speckle reducing anisotropic diffusion (SRAD) algorithm
CN102759530B (en) * 2012-07-03 2016-05-04 湖南镭目科技有限公司 A kind of surface quality image on-line measuring device
CN104778717A (en) * 2015-05-05 2015-07-15 西安电子科技大学 SAR image change detection method based on oriented difference chart
CN112327259B (en) * 2020-10-30 2024-03-15 河南大学 Method and device for eliminating interference signals in SAR image
CN112859016A (en) * 2021-01-13 2021-05-28 上海无线电设备研究所 Waveform composite interference method for forwarding deception SAR interference

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107369163A (en) * 2017-06-15 2017-11-21 西安微电子技术研究所 A kind of quick SAR image object detection method based on best entropy Double Thresholding Segmentation
CN110221256A (en) * 2019-06-21 2019-09-10 西安电子科技大学 SAR disturbance restraining method based on depth residual error network
CN113469088A (en) * 2021-07-08 2021-10-01 西安电子科技大学 SAR image ship target detection method and system in passive interference scene

Also Published As

Publication number Publication date
CN114092748A (en) 2022-02-25

Similar Documents

Publication Publication Date Title
CN114092748B (en) SAR (synthetic aperture radar) unintentional interference detection method, device, equipment and medium
CN108596055B (en) Airport target detection method of high-resolution remote sensing image under complex background
US8744168B2 (en) Target analysis apparatus, method and computer-readable medium
CN105654098B (en) Hyperspectral remote sensing image classification method and system
US20130236115A1 (en) Method and System for Recovery of Missing Spectral Information in Wideband Signal
US20190340746A1 (en) Stationary object detecting method, apparatus and electronic device
CN104021394A (en) Insulator image recognition method based on Adaboost algorithm
CN105844279A (en) Depth learning and SIFT feature-based SAR image change detection method
Zhou et al. A sidelobe-aware small ship detection network for synthetic aperture radar imagery
CN110298227B (en) Vehicle detection method in unmanned aerial vehicle aerial image based on deep learning
CN102592280B (en) Hyperspectral image anomaly detection method using multi-window feature analysis
CN101794437B (en) Method for detecting abnormal target in hyperspectral remotely sensed image
CN104361351A (en) Synthetic aperture radar (SAR) image classification method on basis of range statistics similarity
Capobianco et al. Target detection with semisupervised kernel orthogonal subspace projection
CN115620212B (en) Behavior identification method and system based on monitoring video
CN110033481A (en) Method and apparatus for carrying out image procossing
CN111986162A (en) Hyperspectral abnormal point rapid detection method based on rough positioning and collaborative representation
CN111062321B (en) SAR detection method and system based on deep convolutional network
CN105354824A (en) Region extraction-based two-parameter constant false alarm detection method
CN113253269B (en) SAR self-focusing method based on image classification
Kopp et al. Tackling clutter in radar data-label generation and detection using pointnet++
CN106778822B (en) Image straight line detection method based on funnel transformation
Yang et al. SAR image target detection and recognition based on deep network
CN107729903A (en) SAR image object detection method based on area probability statistics and significance analysis
Chen et al. Infrared dim target detection method based on local feature contrast and energy concentration degree

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