CN113447928B - False alarm rate reduction target identification method and system based on synthetic aperture radar - Google Patents
False alarm rate reduction target identification method and system based on synthetic aperture radar Download PDFInfo
- Publication number
- CN113447928B CN113447928B CN202111000879.6A CN202111000879A CN113447928B CN 113447928 B CN113447928 B CN 113447928B CN 202111000879 A CN202111000879 A CN 202111000879A CN 113447928 B CN113447928 B CN 113447928B
- Authority
- CN
- China
- Prior art keywords
- target
- suspected
- targets
- group
- centroid
- 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
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
- G01S13/88—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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Abstract
The invention discloses a false alarm rate reduction target identification method and a system based on a synthetic aperture radar, after finishing the second stage of target identification, the target obtained by the target identification is not directly identified, but all suspected targets obtained by the target identification are firstly clustered to obtain suspected groups, then the suspected groups are further screened by taking the number of the targets in the groups as the constraint condition, then the suspected groups meeting the constraint condition are calculated in a target circular domain, and finally the targets in the target circular domain are identified by target fine-grained model information, so that a large number of false alarm targets with strong scattering such as clutter interference, angular back interference and the like can be filtered, the workload is reduced for target identification, the processing efficiency is improved, the accuracy of the target identification is also improved, the traditional SAR image target identification method is solved, the target identification processing pressure is high, the technical problems of low recognition efficiency and low recognition accuracy rate.
Description
Technical Field
The invention relates to the technical field of radars, in particular to a false alarm rate reduction target identification method and system based on a synthetic aperture radar.
Background
Synthetic Aperture Radar (SAR) is an active microwave imaging sensor, which realizes high-resolution microwave imaging by using the Synthetic Aperture principle, and has higher resolution in both azimuth direction and distance direction. The SAR has all-weather and all-day working capability, and can flexibly select to acquire information such as position, distance, angle, Doppler and the like of a target object under different wave bands, different side viewing angles and different polarization combination states.
As shown in fig. 1, the conventional method for recognizing the target of the SAR image mainly includes three stages: the method comprises the steps of target detection, target identification and target classification/identification, wherein a first-stage target detection stage aims at extracting an interested target area from a complex image, a second-stage target identification stage further identifies false alarm information which does not contain a target in the interested target area, and finally, a third-stage target classification/identification stage classifies/identifies target fine-grained model information on the basis of extracting target slice information. However, after the target identification stage is completed, the number of the remaining targets is large, false alarm targets with isolated strong scattering such as clutter interference and angle back interference are easy to appear, and the targets directly enter the target classification/identification stage to classify/identify the fine-grained model information of the targets, so that the processing pressure of target identification is increased, the identification efficiency is reduced, and the accuracy of effective target identification is influenced.
Disclosure of Invention
The invention provides a false alarm rate reduction target identification method and system based on a synthetic aperture radar, which are used for solving the technical problems of high target identification processing pressure, low identification efficiency and low identification accuracy rate of the traditional SAR image target identification method.
In view of the above, the first aspect of the present invention provides a synthetic aperture radar-based false alarm rate reduction target identification, including:
obtaining all suspected targets obtained after SAR target detection and target identification, and extracting Doppler centroids of all the suspected targets;
presetting a Doppler centroid distance threshold, selecting the Doppler centroid of any one suspected target from all the suspected targets as a clustering center, and clustering all the suspected targets to obtain a plurality of suspected groups;
screening all suspected groups by taking the contained target number as a constraint condition, and reserving the suspected groups meeting the constraint condition;
extracting population information of a suspected population meeting constraint conditions, wherein the population information comprises the total number of targets in the suspected population and Doppler centroid distances among the targets;
calculating the group mass center and the group radius of each suspected group according to the group information to obtain a target circular domain;
and extracting the target in the target circular domain to identify the fine-grained model information of the target.
Optionally, the constraint is: the included target number is not less than the preset minimum value and not more than the preset maximum value.
Optionally, the calculation formula of the population centroid of the suspected population is:
wherein the content of the first and second substances,Xbeing the centroid of the populationxThe coordinates of the axes are set to be,Ybeing the centroid of the populationyThe coordinates of the axes are set to be,Nis the total target number of the suspected population,
is as followsiOf a single objectxThe coordinates of the axes are set to be,
is as followsiOf a single objectyAxis coordinates.
Optionally, the radius of the population of the suspected population is the maximum doppler centroid distance from the centroid of the population to each target within the suspected population.
Optionally, the method further comprises:
and extracting isolated targets which do not form a suspected group after clustering, and identifying the fine-grained model information of the isolated targets.
The invention provides a false alarm rate reduction target identification system based on a synthetic aperture radar, which comprises: the target centroid acquisition module is used for acquiring all suspected targets obtained after SAR target detection and target identification and extracting Doppler centroids of all the suspected targets;
the target clustering module is used for presetting a Doppler centroid distance threshold, selecting the Doppler centroid of any one suspected target from all the suspected targets as a clustering center, and clustering all the suspected targets to obtain a plurality of suspected groups;
the target screening module is used for screening all suspected groups by taking the number of the contained targets as a constraint condition and reserving the suspected groups meeting the constraint condition;
the group information extraction module is used for extracting group information of a suspected group meeting constraint conditions, wherein the group information comprises the total number of targets in the suspected group and Doppler centroid distances among the targets;
the target circular domain calculating module is used for calculating the group mass center and the group radius of each suspected group according to the group information to obtain a target circular domain;
and the target identification module is used for extracting the target in the target circular domain to identify the fine-grained model information of the target.
Optionally, the constraint is: the included target number is not less than the preset minimum value and not more than the preset maximum value.
Optionally, the calculation formula of the population centroid of the suspected population is:
wherein the content of the first and second substances,Xbeing the centroid of the populationxThe coordinates of the axes are set to be,Ybeing the centroid of the populationyThe coordinates of the axes are set to be,Nis the total target number of the suspected population,
is as followsiOf a single objectxThe coordinates of the axes are set to be,
is as followsiOf a single objectyAxis coordinates.
Optionally, the radius of the population of the suspected population is the maximum doppler centroid distance from the centroid of the population to each target within the suspected population.
Optionally, the object recognition module is further configured to:
and extracting isolated targets which do not form a suspected group after clustering, and identifying the fine-grained model information of the isolated targets.
According to the technical scheme, the embodiment of the invention has the following advantages:
the invention provides a synthetic aperture radar-based false alarm rate reduction target identification method, which does not directly identify targets obtained by target identification after finishing the second stage of target identification, but firstly clusters all suspected targets obtained by target identification to obtain suspected groups, then further screens the suspected groups by taking the number of the targets in the groups as a constraint condition, then calculates a target circular domain of the suspected groups meeting the constraint condition, and finally identifies the targets in the target circular domain by target fine-grained model information, and does not have the conditions of space clustering and number constraint for false alarm targets with isolated strong scattering such as clutter interference, angle inverse interference and the like, so that a large number of false alarm targets with isolated strong scattering such as clutter interference, angle inverse interference and the like can be filtered, the workload is reduced for target identification, and the processing efficiency is improved, meanwhile, the accuracy of target identification is improved, and the technical problems of high target identification processing pressure, low identification efficiency and low identification accuracy of the traditional SAR image target identification method are solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other related drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flow chart of a conventional SAR image target identification method;
fig. 2 is a schematic flowchart of a false alarm rate reduction target identification method based on a synthetic aperture radar according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a false alarm rate reduction target identification system based on a synthetic aperture radar according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For easy understanding, referring to fig. 2, an embodiment of a method for identifying a target with a reduced false alarm rate based on a synthetic aperture radar according to the present invention includes:
It should be noted that, the present invention obtains the target object after the target identification through the traditional target detection and target identification, the target detection and target identification are the prior art, the suspected target after the target identification can be obtained directly by using the prior art, and then the doppler centroid is estimated for the suspected target.
And 102, presetting a Doppler centroid distance threshold, selecting the Doppler centroid of any one suspected target from all the suspected targets as a clustering center, and clustering all the suspected targets to obtain a plurality of suspected groups.
It should be noted that each suspected target has a doppler centroid, so that a doppler centroid distance exists between the suspected target and the suspected target, a cluster center and a distance condition need to be determined for clustering the suspected targets, and the distance between every two targets of each suspected target is also different, so that a doppler centroid distance threshold can be preset according to prior experience information, the doppler centroid distances between the suspected target and other suspected targets are calculated by taking any one suspected target as a cluster center, when the doppler centroid distances between two suspected targets are smaller than the preset doppler centroid distance threshold, the two suspected targets are classified into one class, all the suspected targets are traversed, clustering is completed, each class corresponds to one suspected group, and a plurality of suspected groups can be obtained.
And 103, screening all suspected populations by taking the contained target number as a constraint condition, and reserving the suspected populations meeting the constraint condition.
It should be noted that if a region has too few targets, the region may be composed of isolated targets or clutter with strong scattering, and if a region has too many targets, it may be composed of artificial targets or clutter, such as a large building group, so that the number of targets contained in the suspected group needs to be within a certain range to be identified as a group target. Therefore, in the invention, the constraint conditions of the target number contained in the population need to be preset, all suspected populations are screened, only the suspected populations meeting the constraint conditions are reserved, and the suspected populations not meeting the constraint conditions are removed, so as to reduce the subsequent identification throughput. Similarly, the constraint condition of the population including the number of targets also needs to be preset according to prior empirical information, and the maximum value and the minimum value of the number of targets included in the population are specifically preset according to the prior information, so that the suspected population satisfying the screening condition in the range of the maximum value and the minimum value of the number of targets included is retained.
And 104, extracting the group information of the suspected group meeting the constraint condition, wherein the group information comprises the total number of targets in the suspected group and the Doppler centroid distance between the targets.
It should be noted that after the screening of the constraint condition of the number of targets of the suspected group is completed, the group information may be extracted for the remaining suspected group, which mainly includes the total number of targets in the suspected group and the doppler centroid distance between the targets.
And 105, calculating the group mass center and the group radius of each suspected group according to the group information to obtain a target circular domain.
It should be noted that after the total number of targets in each suspected group and the doppler centroid distance between the targets are obtained, the group centroid and the group radius of each suspected group can be calculated, so that a target circular domain with the group centroid as the center and the group radius as the radius can be obtained. The weighted centroid of the target in the group can be used as the group centroid, and the specific calculation mode is as follows:
wherein the content of the first and second substances,Xbeing the centroid of the populationxThe coordinates of the axes are set to be,Ybeing the centroid of the populationyThe coordinates of the axes are set to be,Nis the total target number of the suspected population,
is as followsiOf a single objectxThe coordinates of the axes are set to be,
is as followsiOf a single objectyAxis coordinates.
The population radius may employ the maximum distance of the target within the population to the centroid of the population.
And 106, extracting the target in the target circular domain to identify the fine-grained model information of the target.
It should be noted that the suspected target inside the target circular domain is an effective target, and the suspected target outside the target circular domain is a false alarm target, so that only the target within the target circular domain needs to be extracted for identifying the fine-grained model information of the target.
The invention provides a synthetic aperture radar-based false alarm rate reduction target identification method, which does not directly identify targets obtained by target identification after finishing the second stage of target identification, but firstly clusters all suspected targets obtained by target identification to obtain suspected groups, then further screens the suspected groups by taking the number of the targets in the groups as a constraint condition, then calculates a target circular domain of the suspected groups meeting the constraint condition, and finally identifies the targets in the target circular domain by target fine-grained model information, and does not have the conditions of space clustering and number constraint for false alarm targets with isolated strong scattering such as clutter interference, angle inverse interference and the like, so that a large number of false alarm targets with isolated strong scattering such as clutter interference, angle inverse interference and the like can be filtered, the workload is reduced for target identification, and the processing efficiency is improved, meanwhile, the accuracy of target identification is improved, and the technical problems of high target identification processing pressure, low identification efficiency and low identification accuracy of the traditional SAR image target identification method are solved.
In one embodiment, the method may further include:
and 107, extracting isolated targets which do not form a suspected group after clustering, and identifying fine-grained model information of the isolated targets.
It should be noted that, when clustering is performed in step 102, a small number of non-clustered isolated targets may exist, that is, suspected targets whose doppler centroid distance does not satisfy the preset doppler centroid distance threshold, and for these suspected targets, they may all be regarded as valid targets, and target fine-grained model information identification is directly performed.
For easy understanding, referring to fig. 3, an embodiment of a system for reducing false alarm rate target recognition based on synthetic aperture radar according to the present invention includes:
a target centroid obtaining module 301, configured to obtain all suspected targets obtained after SAR target detection and target identification, and extract doppler centroids of all suspected targets;
the target clustering module 302 is configured to preset a doppler centroid distance threshold, select a doppler centroid of any one suspected target from all suspected targets as a clustering center, and cluster all the suspected targets to obtain a plurality of suspected groups;
the target screening module 303 is configured to screen all suspected populations by using the number of included targets as a constraint condition, and retain suspected populations meeting the constraint condition;
a population information extraction module 304, configured to extract population information of a suspected population that meets a constraint condition, where the population information includes a total number of targets in the suspected population and a doppler centroid distance between the targets;
a target circular domain calculating module 305, configured to calculate a group centroid and a group radius of each suspected group according to the group information, so as to obtain a target circular domain;
and the target identification module 306 is configured to extract a target in the target circular domain to perform target fine-grained model information identification.
The constraint conditions are as follows: the included target number is not less than the preset minimum value and not more than the preset maximum value.
The calculation formula of the group centroid of the suspected group is as follows:
wherein the content of the first and second substances,Xbeing the centroid of the populationxThe coordinates of the axes are set to be,Ybeing the centroid of the populationyThe coordinates of the axes are set to be,Nis the total target number of the suspected population,
is as followsiOf a single objectxThe coordinates of the axes are set to be,
is as followsiOf a single objectyAxis coordinates.
The radius of the suspected group is the maximum Doppler centroid distance from the group centroid to each target in the suspected group.
The object recognition module is further configured to:
and extracting isolated targets which do not form a suspected group after clustering, and identifying the fine-grained model information of the isolated targets.
The false alarm rate reduction target identification system based on the synthetic aperture radar provided by the embodiment of the invention is used for executing the false alarm rate reduction target identification method based on the synthetic aperture radar in the foregoing embodiment, and a person skilled in the art can directly obtain the false alarm rate reduction target identification system based on the synthetic aperture radar provided by the embodiment of the invention on the basis of the false alarm rate reduction target identification method based on the synthetic aperture radar, and the working principle of the system is not described herein again.
The false alarm rate reduction target identification system based on the synthetic aperture radar provided by the embodiment of the invention does not directly identify the target obtained by target identification after the second stage of target identification is completed, but firstly clusters all suspected targets obtained by target identification to obtain suspected groups, then further screens the suspected groups by taking the number of the targets in the groups as a constraint condition, then calculates the target circular domain of the suspected groups meeting the constraint condition, and finally identifies the target fine-grained model information of the targets in the target circular domain, and does not have the conditions of space clustering and quantity constraint for the false alarm targets with isolated strong scattering such as clutter interference, angular back interference and the like, so that a large number of false alarm targets with isolated strong scattering such as clutter interference, angular back interference and the like can be filtered, and the workload is reduced for target identification, the processing efficiency is improved, the accuracy of target identification is improved, and the technical problems of high target identification processing pressure, low identification efficiency and low identification accuracy of the traditional SAR image target identification method are solved.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A false alarm rate reduction target identification method based on a synthetic aperture radar is characterized by comprising the following steps:
obtaining all suspected targets obtained after SAR target detection and target identification, and extracting Doppler centroids of all the suspected targets;
presetting a Doppler centroid distance threshold, selecting the Doppler centroid of any one suspected target from all the suspected targets as a clustering center, and clustering all the suspected targets to obtain a plurality of suspected groups;
screening all suspected groups by taking the contained target number as a constraint condition, and reserving the suspected groups meeting the constraint condition;
extracting population information of a suspected population meeting constraint conditions, wherein the population information comprises the total number of targets in the suspected population and Doppler centroid distances among the targets;
calculating the group mass center and the group radius of each suspected group according to the group information to obtain a target circular domain;
and extracting the target in the target circular domain to identify the fine-grained model information of the target.
2. The synthetic aperture radar-based false alarm rate reduction target identification method according to claim 1, wherein the constraint condition is: the included target number is not less than the preset minimum value and not more than the preset maximum value.
3. The synthetic aperture radar-based false alarm rate reduction target identification method according to claim 1, wherein the calculation formula of the group centroid of the suspected group is as follows:
wherein the content of the first and second substances,Xbeing the centroid of the populationxThe coordinates of the axes are set to be,Ybeing the centroid of the populationyThe coordinates of the axes are set to be,Nis the total target number of the suspected population,
is as followsiOf a single objectxThe coordinates of the axes are set to be,
is as followsiOf a single objectyAxis coordinates.
4. The synthetic aperture radar-based false alarm rate reduction target identification method according to claim 1, wherein the radius of the suspected group is a maximum doppler centroid distance from a group centroid to each target in the suspected group.
5. The synthetic aperture radar-based false alarm rate reduction target identification method of claim 1, further comprising:
and extracting isolated targets which do not form a suspected group after clustering, and identifying the fine-grained model information of the isolated targets.
6. A false alarm rate reduction target identification system based on a synthetic aperture radar, comprising:
the target centroid acquisition module is used for acquiring all suspected targets obtained after SAR target detection and target identification and extracting Doppler centroids of all the suspected targets;
the target clustering module is used for presetting a Doppler centroid distance threshold, selecting the Doppler centroid of any one suspected target from all the suspected targets as a clustering center, and clustering all the suspected targets to obtain a plurality of suspected groups;
the target screening module is used for screening all suspected groups by taking the number of the contained targets as a constraint condition and reserving the suspected groups meeting the constraint condition;
the group information extraction module is used for extracting group information of a suspected group meeting constraint conditions, wherein the group information comprises the total number of targets in the suspected group and Doppler centroid distances among the targets;
the target circular domain calculating module is used for calculating the group mass center and the group radius of each suspected group according to the group information to obtain a target circular domain;
and the target identification module is used for extracting the target in the target circular domain to identify the fine-grained model information of the target.
7. The synthetic aperture radar based false alarm rate reduction target recognition system of claim 6, wherein the constraint condition is: the included target number is not less than the preset minimum value and not more than the preset maximum value.
8. The synthetic aperture radar-based false alarm rate reduction target recognition system of claim 6, wherein the calculation formula of the group centroid of the suspected group is:
wherein the content of the first and second substances,Xbeing the centroid of the populationxThe coordinates of the axes are set to be,Ybeing the centroid of the populationyThe coordinates of the axes are set to be,Nis the total target number of the suspected population,
is as followsiOf a single objectxThe coordinates of the axes are set to be,
is as followsiOf a single objectyAxis coordinates.
9. The synthetic aperture radar-based false alarm rate reduction target recognition system of claim 6, wherein the radius of the suspected group is a maximum doppler centroid distance from a centroid of the group within the suspected group to each target.
10. The synthetic aperture radar-based false alarm rate reduction target recognition system of claim 6, wherein the target recognition module is further configured to:
and extracting isolated targets which do not form a suspected group after clustering, and identifying the fine-grained model information of the isolated targets.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111000879.6A CN113447928B (en) | 2021-08-30 | 2021-08-30 | False alarm rate reduction target identification method and system based on synthetic aperture radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111000879.6A CN113447928B (en) | 2021-08-30 | 2021-08-30 | False alarm rate reduction target identification method and system based on synthetic aperture radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113447928A CN113447928A (en) | 2021-09-28 |
| CN113447928B true CN113447928B (en) | 2022-01-21 |
Family
ID=77818923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111000879.6A Active CN113447928B (en) | 2021-08-30 | 2021-08-30 | False alarm rate reduction target identification method and system based on synthetic aperture radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113447928B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184829B (en) * | 2015-08-28 | 2017-12-12 | 华中科技大学 | A kind of tight quarters target detection and high-precision method for positioning mass center |
| CN113190646B (en) * | 2020-01-14 | 2024-05-07 | 北京达佳互联信息技术有限公司 | User name sample labeling method and device, electronic equipment and storage medium |
| CN111289998A (en) * | 2020-02-05 | 2020-06-16 | 北京汽车集团有限公司 | Obstacle detection method, obstacle detection device, storage medium, and vehicle |
| CN112101443B (en) * | 2020-09-09 | 2023-10-20 | 中国航空工业集团公司雷华电子技术研究所 | Small group track starting method based on measurement processing under multi-group target scene |
| CN112698301A (en) * | 2020-12-11 | 2021-04-23 | 中国科学院微电子研究所 | Laser radar target identification method, device and equipment based on distance intensity correlation |
-
2021
- 2021-08-30 CN CN202111000879.6A patent/CN113447928B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113447928A (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108510467B (en) | SAR image target identification method based on depth deformable convolution neural network | |
| CN105427314B (en) | SAR image object detection method based on Bayes's conspicuousness | |
| US8611604B2 (en) | Object detection device | |
| CN107563413B (en) | Unmanned aerial vehicle aerial image farmland block object accurate extraction method | |
| CN106339674B (en) | The Hyperspectral Image Classification method that model is cut with figure is kept based on edge | |
| CN108171193B (en) | Polarized SAR (synthetic aperture radar) ship target detection method based on super-pixel local information measurement | |
| CN110456320B (en) | Ultra-wideband radar identity recognition method based on free space gait time sequence characteristics | |
| CN108241871A (en) | Laser point cloud and visual fusion data classification method based on multiple features | |
| CN101930547A (en) | Method for automatically classifying remote sensing image based on object-oriented unsupervised classification | |
| CN102645679A (en) | Mesocyclone identification method based on Doppler radar echo images | |
| CN102842044A (en) | Method for detecting variation of remote-sensing image of high-resolution visible light | |
| CN103415871A (en) | Irradiation field recognition | |
| CN111222511B (en) | Infrared unmanned aerial vehicle target detection method and system | |
| CN112946630A (en) | Personnel counting and tracking method based on millimeter wave radar | |
| CN110412548B (en) | Radar multi-target recognition method based on high-resolution one-dimensional range profile | |
| CN111950498A (en) | Lane line detection method and device based on end-to-end instance segmentation | |
| CN113256990B (en) | Method and system for collecting road vehicle information by radar based on clustering algorithm | |
| CN113447928B (en) | False alarm rate reduction target identification method and system based on synthetic aperture radar | |
| Skidmore | Unsupervised training area selection in forests using a nonparametric distance measure and spatial information | |
| CN102800101A (en) | Satellite-borne infrared remote sensing image airport ROI rapid detection method | |
| CN107729903A (en) | SAR image object detection method based on area probability statistics and significance analysis | |
| CN102194224A (en) | Method for identifying tank group in optical remote sensing image | |
| Wang et al. | Multi-scale target detection in SAR image based on visual attention model | |
| CN113450373A (en) | Optical live image-based real-time discrimination method for characteristic events in carrier rocket flight process | |
| Shen et al. | Cropland extraction from very high spatial resolution satellite imagery by object-based classification using improved mean shift and one-class support vector machines |
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 |