CN114419453A - Group target detection method based on electromagnetic scattering characteristics and topological configuration - Google Patents
Group target detection method based on electromagnetic scattering characteristics and topological configuration Download PDFInfo
- Publication number
- CN114419453A CN114419453A CN202210335606.5A CN202210335606A CN114419453A CN 114419453 A CN114419453 A CN 114419453A CN 202210335606 A CN202210335606 A CN 202210335606A CN 114419453 A CN114419453 A CN 114419453A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- group
- binary image
- clustering
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- G01S13/02—Systems using reflection of radio waves, e.g. primary radar systems; Analogous systems
- G01S13/04—Systems determining presence of a target
-
- 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
- G01S13/9004—SAR image acquisition techniques
-
- 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
- G01S13/9094—Theoretical aspects
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
- G01S7/41—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00 using analysis of echo signal for target characterisation; Target signature; Target cross-section
- G01S7/414—Discriminating targets with respect to background clutter
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
- G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
Abstract
The invention discloses a group target detection method based on electromagnetic scattering characteristics and topological configuration, which comprises the following steps: step 1, receiving a dual-polarization SAR image; step 2, obtaining a polarization enhancement image; step 3, obtaining a mean value filtering image; step 4, selecting a segmentation algorithm, and processing the mean value filtering image obtained in the step 3 by adopting the selected segmentation algorithm to obtain a first binary image; step 5, MRF segmentation is carried out on the mean value filtering image to obtain a second binary image; step 6, performing target pixel clustering on the first binary image obtained in the step 4 by adopting a preceding and following clustering method to obtain a plurality of single targets; step 7, obtaining a plurality of single targets corresponding to the second binary image; step 8, obtaining a plurality of target groups; and 9, selecting the target group with the maximum confidence value as the detected target group. The method can meet the requirements of practical application scenes on high precision and real-time detection of the group targets in the SAR image.
Description
Technical Field
The invention relates to the technical field of SAR image processing and target identification, in particular to a group target detection method based on electromagnetic scattering characteristics and topological configuration.
Background
The SAR has all-weather and all-weather capabilities, not only can acquire image characteristics such as the structure and the shape of a target, but also can acquire electromagnetic scattering characteristics such as the intensity and the amplitude of scattering points, and available information is richer. The SAR imaging is utilized to accurately identify the group targets with remarkable electromagnetic scattering characteristics, and the method has great significance for radar guidance and other applications.
Because the environment background in the practical application scene is complex, the typical scene comprises the gobi desert, the grassland, the forest land, the viaduct, the building group and the like, and the group target detection and identification difficulty is higher than that of single target detection and identification, the related research for group target detection and identification in China is less at present. Meanwhile, under the condition of limited computing resources such as an embedded system, the time efficiency of the detection and identification algorithm is a big difficulty restricting the radar imaging identification application, and how to design a high-precision and high-efficiency group target detection algorithm is a difficult problem to be solved urgently at present.
Disclosure of Invention
In order to solve the problems of low target detection efficiency and low precision in the existing group target detection and identification technology, the invention aims to provide a group target detection method based on electromagnetic scattering characteristics and topological configuration so as to improve the target detection precision and detection efficiency.
In order to achieve the purpose, the invention adopts the following technical scheme to solve the problem:
a group target detection method based on electromagnetic scattering characteristics and topological configuration specifically comprises the following steps:
step 1, receiving a dual-polarization SAR image;
step 2, carrying out polarization enhancement processing on the dual-polarization SAR image to obtain a polarization enhancement image;
step 3, carrying out mean value filtering processing on the polarization enhanced image to obtain a mean value filtering image;
step 4, selecting a segmentation algorithm, and processing the mean value filtering image obtained in the step 3 by using the selected segmentation algorithm to obtain a first binary image, wherein the method specifically comprises the following substeps:
step 41, calculating KS detection quantity of the mean filtering image by adopting various clutter models to obtain KS detection quantity;
step 42, when the minimum value of the KS inspection quantity is smaller than a threshold value T, selecting a clutter model corresponding to the minimum value of the KS inspection quantity as a distribution model of the CFAR algorithm, and executing step 43; when the KS check quantity minimum value is not less than the threshold value T, step 44 is executed;
step 43, performing segmentation processing on the mean filtering image by using a CFAR algorithm, calculating a target segmentation threshold according to a given false alarm probability in the processing process, and extracting a strong scattering target to obtain a first binary image;
step 44, performing segmentation processing on the mean value filtering image by adopting histogram segmentation, calculating a target segmentation threshold value according to a given false alarm probability in the processing process, and extracting a strong scattering target to obtain a first binary image;
step 5, processing the mean value filtering image obtained in the step 3 by adopting an MRF algorithm to obtain a second binary image;
step 6, performing target pixel clustering on the first binary image obtained in the step 4 by adopting a preceding and following clustering method to obtain a plurality of single targets;
step 7, clustering the second binary image by taking the position of the central pixel of the circumscribed rectangle of each single target obtained in the step 6 as an initial position for searching the second binary image to obtain a plurality of single targets corresponding to the second binary image; the clustering method is the same as the clustering method for the first binary image;
step 8, traversing a plurality of single targets corresponding to the second binary image obtained in the step 7, and searching a target group to obtain a plurality of target groups; counting to obtain the configuration parameters of each target group;
step 9, calculating the confidence degree corresponding to each configuration parameter of each target group obtained in the step 8, and multiplying the confidence degrees corresponding to all the configuration parameters to obtain the confidence degree corresponding to the target group; and selecting the target group with the maximum confidence value as the detected target group, and finishing the detection of the group target.
Further, the clutter models in step 41 include gaussian distribution, rayleigh distribution, log-normal distribution, exponential distribution and gamma distribution.
Further, the threshold T in step 42 is set to 0.15.
Further, the step 6 comprises the following sub-steps:
step 61, carrying out pixel search on the first binary image according to a certain row interval, and gathering the points with the pixel value of 1 connected in each row together to form a row point cluster;
step 62, clustering the row point clusters obtained in step 61 according to the column direction of the image, specifically: setting the spacing distance between two row point clusters as the minimum distance between the pixel positions of all points of one row point cluster and the pixel positions of all points of the other row point cluster, when the distance between the row point clusters is less than a certain spacing distance and the two row point clusters meet the merging condition, clustering the two row points together to be used as a block, traversing all the row point clusters along the column direction of the image to obtain a plurality of blocks, and using each block as a single target.
Further, the merging condition of the two row blob in step 62 is the following two conditions:
the area of the pixel of the single target is smaller than the actual area of the target to be detected:
wherein the content of the first and second substances,N 0 is the minimum value of the pixels contained in the object to be detected;Sarea of a pixel that is a single target;
is the resolution of the image;
the distance between two pixels within the region of the same single object satisfies the following relation:
wherein the target lengthLIn the range of 2m to 20m, target widthWIn the range of 2m to 10m,N 0 is 2.
Further, the configuration parameters of the target group in step 8 include target group average amplitude, target group area and target number.
Further, the method adopts a multi-core DSP platform to perform parallel processing.
Compared with the prior art, the method has the following technical effects:
1. high precision: the method has the advantages that the target-clutter ratio is improved by adopting a dual-polarization SAR image data source, the connectivity of a strong target is guaranteed through mean filtering, the statistical distribution and the spatial adjacency relation of the strong scattering target are considered by combining two segmentation algorithms of CFAR and MRF, the characteristic that a detection result is more consistent with a real target is guaranteed by the design of confidence degree sequencing of target group topological configuration parameters, and the accuracy of the detection result is effectively improved.
2. High efficiency: the optimized parallel design is carried out on the preprocessing, segmentation, clustering and other processing algorithms of the SAR image based on the multi-core DSP platform, the requirement of real-time detection of the SAR image target can be met, and the engineering implementation application is facilitated.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
The invention is further explained below with reference to the drawings and the detailed description.
Detailed Description
The important technical terms involved in the present invention are explained as follows:
1. dual-polarized SAR images: an HH (i.e., horizontal transmission, horizontal reception) polarization, an HV (i.e., horizontal transmission, vertical reception) polarization, and the like.
2. The CFAR algorithm: constant False-Alarm Rate algorithm, Constant False Alarm Rate detection algorithm.
3. The MRF algorithm: markov Random field image segmentation algorithm.
4. Multi-core DSP: a multi-core digital signal processor, typically TMS320C6678 (8 cores) from TI corporation.
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined purposes, the present invention is described in detail below with reference to the accompanying drawings.
The invention provides a group target detection method based on electromagnetic scattering characteristics and topological configuration, which comprises the following steps:
step 1, receiving a dual-polarization SAR image.
And 2, carrying out polarization enhancement processing on the dual-polarization SAR image to obtain a polarization enhanced image.
The polarization enhancement process calculation formula is as follows:
wherein the content of the first and second substances,S HH 、S HV an amplitude map of the HH polarization, HV polarization SAR image, respectively;
is an intermediate result;Eis to be expected;yis a polarization enhanced image.
Compared with single polarization data, the polarization enhancement image obtained in the step has a higher target-to-clutter ratio, and is more beneficial to detection.
And 3, carrying out mean filtering processing on the polarization enhanced image to obtain a mean filtered image.
The purpose of this step is to further suppress noise while better linking the split regions in the target, ensuring the integrity of the target after subsequent image segmentation.
And 4, selecting a segmentation algorithm, and processing the mean value filtering image obtained in the step 3 by adopting the selected segmentation algorithm to obtain a first binary image. The method specifically comprises the following substeps:
step 41, calculating KS detection quantity of the mean filtering image by adopting various clutter models to obtain KS detection quantity; specifically, the clutter model includes gaussian distribution, rayleigh distribution, log-normal distribution, exponential distribution, and gamma distribution.
42, when the minimum value of the KS inspection quantity is smaller than a threshold value T (KS), selecting a clutter model corresponding to the minimum value of the KS inspection quantity as a distribution model of the CFAR algorithm, and executing a step 43; when the KS check quantity minimum is not less than the threshold t (KS), step 44 is performed. The threshold T is selected according to the target and background conditions in practical application and is set to be 0.15 in the invention;
step 43, performing segmentation processing on the mean filtering image by using a CFAR algorithm, calculating a target segmentation threshold according to a given false alarm probability in the processing process, and extracting a strong scattering target to obtain a first binary image;
and 44, carrying out segmentation processing on the mean value filtering image by adopting histogram segmentation, calculating a target segmentation threshold value according to the given false alarm probability in the processing process, and extracting the strong scattering target to obtain a first binary image.
And 5, processing the mean value filtering image obtained in the step 3 by adopting an MRF algorithm to obtain a second binary image.
And 6, clustering target pixels of the first binary image obtained in the step 4 by adopting a preceding and subsequent clustering method to obtain a plurality of single targets. The specific operation is as follows:
step 61, performing pixel search on the first binary image according to a certain row interval (for example, searching one row every 3 rows instead of searching pixel by pixel), and gathering the points with the pixel value of 1 connected in each row together to form a row point group. During storage, the storage is carried out line by line according to the line starting position and the length of the line dot group.
And step 62, clustering the row dot clusters obtained in the step 61 according to the column direction of the image. The method comprises the following steps: setting the spacing distance between two row point clusters to be the minimum distance between the pixel positions of all points of one row point cluster and the pixel positions of all points of the other row point cluster, when the spacing distance between the row point clusters is smaller than a certain spacing distance (such as 3 pixel points) and the two row point clusters meet the merging condition, clustering the two row points together to be used as a block, traversing all the row point clusters along the column direction of the image to obtain a plurality of blocks, and using each block as a single target.
Specifically, in the process of the preceding and following clustering, the priori knowledge of the target to be detected is adopted for cluster termination and false alarm filtering, and the priori knowledge comprises the length L and the width W of the target to be detected and the resolution of an image
And the like. Meanwhile, the merging conditions of the two row dot clusters are as follows:
the area of the pixel of the single target (block) is smaller than the actual area of the target to be detected, namely the following relational expression is satisfied:
wherein the content of the first and second substances,N 0 is the minimum value of the pixels contained in the object to be detected;Sarea of a pixel that is a single target; l, W are the length and width of the object to be detected, respectively;
is the resolution of the image;
distance between two pixels within the area of the same single objectdSatisfies the following relation:
l, W represents the length and width of the target to be detected;
is the resolution of the image;
for example, according to statistics on target size information of a certain vehicle group, empirical parameters for summarizing target clusters are:dless than or equal to 3m, L ranging from 2m to 20m, W ranging from 2m to 10m, and the least number of target pixelsN 0 At 2, the target clustering parameters can be modified according to the true target type in practical application.
Step 7, clustering the second binary image by taking the position of the central pixel of the circumscribed rectangle of each single target obtained in the step 6 as an initial position for searching the second binary image to obtain a plurality of single targets corresponding to the second binary image; the method for clustering the second binary image is the same as the method for clustering the first binary image, and a preceding and following clustering method is also adopted.
Step 8, traversing a plurality of single targets corresponding to the second binary image obtained in the step 7, and searching a target group to obtain a plurality of target groups; and counting configuration parameters (including target group average amplitude, target group area and target number) of each target group.
Specifically, in the process of searching for a target group, the distance between targets in each group (i.e., the target search distance) and the total number of targets are guaranteed to be within a certain range. For example, when detecting a certain vehicle target group, according to empirical analysis, the parameters of the target group search can be generally set as: the target searching distance is 30m-100m, the total number of targets in the group is 3-50, and the target searching distance is adjusted according to the type of a real target in practical application.
Step 9, for each target group obtained in step 8, calculating a confidence coefficient corresponding to each configuration parameter (including the average amplitude of the target group, the area of the target group and the number of targets) of the target group, and performing multiplication on the confidence coefficients corresponding to all the configuration parameters to obtain a confidence coefficient corresponding to the target group; and selecting the target group with the maximum confidence value as the detected target group.
In this embodiment, the confidence coefficient is calculated as follows:
the values of T1, T2, T3 and T4 are obtained by conventional empirical statistics according to the types of different groups of targets and are used as prior input parameters for target detection; x is a configuration parameter and y is a confidence.
Preferably, the method of the present invention may use a multi-core DSP platform to perform parallel processing, for example, when processing an image, each computational core may process one line of data in a unit of line of the image.
Under the parallel processing mode based on the multi-core DSP platform, the processing processes of preprocessing, segmentation, clustering and the like of the SAR image are designed in parallel, processing acceleration is realized, the processing efficiency is effectively improved, the requirement of real-time detection of the SAR image target can be met, and engineering implementation and application are facilitated.
Claims (7)
1. A group target detection method based on electromagnetic scattering characteristics and topological configuration is characterized by comprising the following steps:
step 1, receiving a dual-polarization SAR image;
step 2, carrying out polarization enhancement processing on the dual-polarization SAR image to obtain a polarization enhancement image;
step 3, carrying out mean value filtering processing on the polarization enhanced image to obtain a mean value filtering image;
step 4, selecting a segmentation algorithm, and processing the mean value filtering image obtained in the step 3 by using the selected segmentation algorithm to obtain a first binary image, wherein the method specifically comprises the following substeps:
step 41, calculating KS detection quantity of the mean filtering image by adopting various clutter models to obtain KS detection quantity;
step 42, when the minimum value of the KS inspection quantity is smaller than a threshold value T, selecting a clutter model corresponding to the minimum value of the KS inspection quantity as a distribution model of the CFAR algorithm, and executing step 43; when the KS check quantity minimum value is not less than the threshold value T, step 44 is executed;
step 43, performing segmentation processing on the mean filtering image by using a CFAR algorithm, calculating a target segmentation threshold according to a given false alarm probability in the processing process, and extracting a strong scattering target to obtain a first binary image;
step 44, performing segmentation processing on the mean value filtering image by adopting histogram segmentation, calculating a target segmentation threshold value according to a given false alarm probability in the processing process, and extracting a strong scattering target to obtain a first binary image;
step 5, processing the mean value filtering image obtained in the step 3 by adopting an MRF algorithm to obtain a second binary image;
step 6, performing target pixel clustering on the first binary image obtained in the step 4 by adopting a preceding and following clustering method to obtain a plurality of single targets;
step 7, clustering the second binary image by taking the position of the central pixel of the circumscribed rectangle of each single target obtained in the step 6 as an initial position for searching the second binary image to obtain a plurality of single targets corresponding to the second binary image; the clustering method is the same as the clustering method for the first binary image;
step 8, traversing a plurality of single targets corresponding to the second binary image obtained in the step 7, and searching a target group to obtain a plurality of target groups; counting to obtain the configuration parameters of each target group;
step 9, calculating the confidence degree corresponding to each configuration parameter of each target group obtained in the step 8, and multiplying the confidence degrees corresponding to all the configuration parameters to obtain the confidence degree corresponding to the target group; and selecting the target group with the maximum confidence value as the detected target group, and finishing the detection of the group target.
2. The method of claim 1, wherein the clutter models in step 41 include gaussian distribution, rayleigh distribution, log-normal distribution, exponential distribution and gamma distribution.
3. The method according to claim 1, wherein the threshold T in step 42 is set to 0.15.
4. The method for group target detection based on electromagnetic scattering features and topological configurations according to claim 1, wherein the step 6 comprises the following sub-steps:
step 61, carrying out pixel search on the first binary image according to a certain row interval, and gathering the points with the pixel value of 1 connected in each row together to form a row point cluster;
step 62, clustering the row point clusters obtained in step 61 according to the column direction of the image, specifically: setting the spacing distance between two row point clusters to be the minimum distance between the pixel positions of all points of one row point cluster and the pixel positions of all points of the other row point cluster, when the spacing distance between the row point clusters is smaller than a certain spacing distance and the two row point clusters meet the merging condition, clustering the two row points together to be used as a block, traversing all the row point clusters along the column direction of the image to obtain a plurality of blocks, and using each block as a single target.
5. The method for group target detection based on electromagnetic scattering features and topological configurations according to claim 4, wherein the merging condition of the two row clusters in step 62 is two of the following:
the area of the pixel of the single target is smaller than the actual area of the target to be detected:
wherein the content of the first and second substances,N 0 is the minimum value of the pixels contained in the object to be detected;Sarea of a pixel that is a single target;
is the resolution of the image;
the distance between two pixels within the region of the same single object satisfies the following relation:
wherein the target lengthLIn the range of 2m to 20m, target widthWIn the range of 2m to 10m,N 0 is 2.
6. The method according to claim 1, wherein the configuration parameters of the target group in step 8 include target group average amplitude, target group area and target number.
7. The method for group target detection based on electromagnetic scattering features and topological configurations according to claim 1, wherein the method adopts a multi-core DSP platform for parallel processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210335606.5A CN114419453B (en) | 2022-04-01 | 2022-04-01 | Group target detection method based on electromagnetic scattering characteristics and topological configuration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210335606.5A CN114419453B (en) | 2022-04-01 | 2022-04-01 | Group target detection method based on electromagnetic scattering characteristics and topological configuration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114419453A true CN114419453A (en) | 2022-04-29 |
| CN114419453B CN114419453B (en) | 2022-07-01 |
Family
ID=81263611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210335606.5A Active CN114419453B (en) | 2022-04-01 | 2022-04-01 | Group target detection method based on electromagnetic scattering characteristics and topological configuration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114419453B (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11331857A (en) * | 1998-05-13 | 1999-11-30 | Mitsubishi Electric Corp | Image pickup device |
| CN102567963A (en) * | 2011-11-10 | 2012-07-11 | 西安电子科技大学 | Quantum multi-target clustering-based remote sensing image segmentation method |
| CN102880760A (en) * | 2012-10-11 | 2013-01-16 | 江苏科技大学 | Microwave circuit design method based on multiple target particle swarms and topological extension |
| CN103400156A (en) * | 2013-07-04 | 2013-11-20 | 西安电子科技大学 | CFAR (Constant False Alarm Rate) and sparse representation-based high-resolution SAR (Synthetic Aperture Radar) image ship detection method |
| CN103839261A (en) * | 2014-02-18 | 2014-06-04 | 西安电子科技大学 | SAR image segmentation method based on decomposition evolution multi-objective optimization and FCM |
| CN104376330A (en) * | 2014-11-19 | 2015-02-25 | 西安电子科技大学 | Polarization SAR image ship target detection method based on superpixel scattering mechanism |
| CN105160648A (en) * | 2014-11-26 | 2015-12-16 | 中国人民解放军第二炮兵工程大学 | Radar target and shadow segmentation method based on wavelet and constant false alarm rate |
| CN107145874A (en) * | 2017-05-13 | 2017-09-08 | 复旦大学 | Ship Target Detection and discrimination method in complex background SAR image |
| CN108734111A (en) * | 2018-04-26 | 2018-11-02 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | SAR image surface vessel recognition methods |
| CN108765491A (en) * | 2018-05-31 | 2018-11-06 | 成都信息工程大学 | A kind of SAR image Ship Target Detection method |
| CN112558066A (en) * | 2020-10-30 | 2021-03-26 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Dual-polarization SAR image system |
| CN112819775A (en) * | 2021-01-28 | 2021-05-18 | 中国空气动力研究与发展中心超高速空气动力研究所 | Segmentation and reinforcement method for damage detection image of aerospace composite material |
| CN113466797A (en) * | 2021-06-24 | 2021-10-01 | 电子科技大学 | Bistatic SAR space-time clutter suppression method based on clutter ridge matching sparse recovery |
| WO2021217795A1 (en) * | 2020-04-26 | 2021-11-04 | 南京慧尔视防务科技有限公司 | Traffic radar and target detection method therefor and apparatus thereof, and electronic device and storage medium |
| CN114139631A (en) * | 2021-12-03 | 2022-03-04 | 华北电力大学 | Multi-target training object-oriented selectable ash box confrontation sample generation method |
| CN114236464A (en) * | 2022-02-23 | 2022-03-25 | 中国人民解放军火箭军工程大学 | Coherent interference resisting method for polarization sensitive array self-adaptive polarization adjustment |
-
2022
- 2022-04-01 CN CN202210335606.5A patent/CN114419453B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11331857A (en) * | 1998-05-13 | 1999-11-30 | Mitsubishi Electric Corp | Image pickup device |
| CN102567963A (en) * | 2011-11-10 | 2012-07-11 | 西安电子科技大学 | Quantum multi-target clustering-based remote sensing image segmentation method |
| CN102880760A (en) * | 2012-10-11 | 2013-01-16 | 江苏科技大学 | Microwave circuit design method based on multiple target particle swarms and topological extension |
| CN103400156A (en) * | 2013-07-04 | 2013-11-20 | 西安电子科技大学 | CFAR (Constant False Alarm Rate) and sparse representation-based high-resolution SAR (Synthetic Aperture Radar) image ship detection method |
| CN103839261A (en) * | 2014-02-18 | 2014-06-04 | 西安电子科技大学 | SAR image segmentation method based on decomposition evolution multi-objective optimization and FCM |
| CN104376330A (en) * | 2014-11-19 | 2015-02-25 | 西安电子科技大学 | Polarization SAR image ship target detection method based on superpixel scattering mechanism |
| CN105160648A (en) * | 2014-11-26 | 2015-12-16 | 中国人民解放军第二炮兵工程大学 | Radar target and shadow segmentation method based on wavelet and constant false alarm rate |
| CN107145874A (en) * | 2017-05-13 | 2017-09-08 | 复旦大学 | Ship Target Detection and discrimination method in complex background SAR image |
| CN108734111A (en) * | 2018-04-26 | 2018-11-02 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | SAR image surface vessel recognition methods |
| CN108765491A (en) * | 2018-05-31 | 2018-11-06 | 成都信息工程大学 | A kind of SAR image Ship Target Detection method |
| WO2021217795A1 (en) * | 2020-04-26 | 2021-11-04 | 南京慧尔视防务科技有限公司 | Traffic radar and target detection method therefor and apparatus thereof, and electronic device and storage medium |
| CN112558066A (en) * | 2020-10-30 | 2021-03-26 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Dual-polarization SAR image system |
| CN112819775A (en) * | 2021-01-28 | 2021-05-18 | 中国空气动力研究与发展中心超高速空气动力研究所 | Segmentation and reinforcement method for damage detection image of aerospace composite material |
| CN113466797A (en) * | 2021-06-24 | 2021-10-01 | 电子科技大学 | Bistatic SAR space-time clutter suppression method based on clutter ridge matching sparse recovery |
| CN114139631A (en) * | 2021-12-03 | 2022-03-04 | 华北电力大学 | Multi-target training object-oriented selectable ash box confrontation sample generation method |
| CN114236464A (en) * | 2022-02-23 | 2022-03-25 | 中国人民解放军火箭军工程大学 | Coherent interference resisting method for polarization sensitive array self-adaptive polarization adjustment |
Non-Patent Citations (4)
| Title |
|---|
| RUOCHEN WU: "Two-Parameter CFAR Ship Detection Algorithm Based on Rayleigh Distribution in SAR Images", 《D O I : 1 0.20944/PREPRINTS202112.0280.V1》 * |
| XUEJIAO CHEN 等: "A New Multi-objective Evolution Model for Community Detection in Multi-layer Networks", 《SPRINGER NATURE SWITZERLAND AG 2019》 * |
| 刘俊涛: "雷达杂波图CFAR算法研究及基于FPGA的实现", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
| 黄杰军: "双模融合舰船目标检测方法研究", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114419453B (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106170819B (en) | A kind of diameter radar image Ship Target rapid detection method | |
| CN109559324B (en) | Target contour detection method in linear array image | |
| CN109886218B (en) | SAR image ship target detection method based on superpixel statistic dissimilarity | |
| CN109344812A (en) | A kind of improved single photon point cloud data denoising method based on cluster | |
| CN111753682B (en) | Hoisting area dynamic monitoring method based on target detection algorithm | |
| CN102800104B (en) | Two-dimensional scattering center automatic correlation method based on ISAR (inverse synthetic aperture radar) image sequence | |
| CN111915583A (en) | Vehicle and pedestrian detection method based on vehicle-mounted thermal infrared imager in complex scene | |
| CN114972370A (en) | Remote sensing image self-adaptive segmentation method for neural network reasoning | |
| Zheng et al. | Building recognition of UAV remote sensing images by deep learning | |
| CN110866926A (en) | Infrared remote sensing image rapid and fine sea-land segmentation method | |
| Kou et al. | Infrared small target detection based on the improved density peak global search and human visual local contrast mechanism | |
| CN108983194B (en) | Target extraction and condensation method based on ground monitoring radar system | |
| CN114419453B (en) | Group target detection method based on electromagnetic scattering characteristics and topological configuration | |
| CN111783656A (en) | Self-adaptive infrared small target detection method based on statistical characteristic pre-segmentation | |
| CN108828549B (en) | Target extraction method based on airport scene surveillance radar system | |
| CN111767856A (en) | Infrared small target detection algorithm based on gray value statistical distribution model | |
| Raj et al. | A novel Ship detection method from SAR image with reduced false alarm | |
| Zhang et al. | Ship detection and recognition in optical remote sensing images based on scale enhancement rotating cascade R-CNN networks | |
| CN115436900A (en) | Target detection method, device, equipment and medium based on radar map | |
| Wang et al. | FPA-DNN: a forward propagation acceleration based deep neural network for ship detection | |
| CN115330841A (en) | Method, apparatus, device and medium for detecting projectile based on radar map | |
| CN114742849A (en) | Leveling instrument distance measuring method based on image enhancement | |
| CN110211124B (en) | Infrared imaging frozen lake detection method based on MobileNet V2 | |
| CN113406625A (en) | SAR image superpixel sliding window CFAR detection method | |
| CN113496159B (en) | Multi-scale convolution and dynamic weight cost function smoke target segmentation method |
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 |