CN113192088A - Radar image fixed background mask method based on remote sensing image threshold segmentation - Google Patents
Radar image fixed background mask method based on remote sensing image threshold segmentation Download PDFInfo
- Publication number
- CN113192088A CN113192088A CN202110544732.7A CN202110544732A CN113192088A CN 113192088 A CN113192088 A CN 113192088A CN 202110544732 A CN202110544732 A CN 202110544732A CN 113192088 A CN113192088 A CN 113192088A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- image
- sensing image
- radar
- radar image
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Abstract
The invention provides a radar image fixed background mask method based on remote sensing image threshold segmentation. The method comprises the following steps: s101, aligning the remote sensing image with a radar image space; s102, cutting the remote sensing image after the space alignment; s103, carrying out sea-land segmentation on the cut remote sensing image, and extracting a coastline of the remote sensing image; and S104, overlapping and fusing the remote sensing image after sea and land segmentation and the radar image to realize a fixed background mask of the radar image. The radar image fixed background mask method solves the problems that the effect of the fixed background mask method in the prior art is not ideal and the manual participation degree is high.
Description
Technical Field
The invention relates to the technical field of radar image data processing, in particular to a radar image fixed background mask method based on remote sensing image threshold segmentation.
Background
The radar image mainly comprises parts such as a fixed land background, an ocean background, ship targets, clutter and the like, land and island areas in the image can be shielded through a fixed background mask, so that the radar image with a single background is obtained, subsequent ship target detection is only carried out aiming at the concerned sea surface area, and the efficiency and pertinence of target detection are improved.
There are two common approaches to the fixed background masking approach. Firstly, extracting a background image of a radar video image, and then subtracting the background image from an original radar image to obtain a foreground image containing a target. The key point of the method lies in the extraction of background images, and due to the difference between radar images and optical and infrared images, the background extraction methods such as a common multiframe averaging method, a statistical median method, a mixed Gaussian model method and the like cannot achieve ideal effects when applied to the background extraction of radar video images. And secondly, the idea of selecting a human-computer interaction region is to select a polygonal region in the original radar image in a human-computer interaction mode and then realize the fixation of a background mask through the binarization of the image. Although the method is flexible, the manual participation degree is high, fatigue is easy to generate to cause efficiency reduction, and the manually selected area has errors with the real land area, so that the fixed background cannot be completely replaced.
Disclosure of Invention
The invention aims to provide a radar image fixed background mask method based on remote sensing image threshold segmentation, which can solve the problems that the effect of the fixed background mask method in the prior art is not ideal and the manual participation degree is high.
In order to achieve the above purpose, the invention provides the following technical scheme:
a radar image fixed background mask method based on remote sensing image threshold segmentation specifically comprises the following steps:
s101, aligning the remote sensing image with a radar image space;
s102, cutting the remote sensing image after the space alignment;
s103, carrying out sea-land segmentation on the cut remote sensing image, and extracting a coastline of the remote sensing image;
and S104, overlapping and fusing the remote sensing image after sea and land segmentation and the radar image to realize a fixed background mask of the radar image.
On the basis of the technical scheme, the invention can be further improved as follows:
further, the step S101 specifically includes step S1011, selecting a remote sensing graph having the same area resolution as the radar image;
and S1012, determining the due north direction of the radar image, obtaining the longitude and latitude of the central point of the radar image, and performing primary positioning on the remote sensing image through the longitude and latitude of the central point.
Further, S101 specifically includes S1013, sampling the pixel points of the remote sensing image, and matching the pixel coordinates of the remote sensing image after sampling with the pixel coordinates of the radar image.
Further, the S102 specifically includes cutting the remote sensing image after the spatial alignment into an image with the same size as the radar image.
Further, the S103 specifically includes S1031, which converts the remote sensing image into a gray level image, and calculates a gray level average value of the remote sensing image.
Further, the S103 specifically includes S1032, obtaining a gray variance according to the gray mean, and obtaining a threshold of the remote sensing image according to the gray mean and the gray variance.
Further, the S103 specifically includes S1033, setting pixels larger than the threshold to 1 and pixels smaller than the threshold to 0 according to the threshold, and performing threshold segmentation on the remote sensing image;
s1034, a coastline of the remote sensing image is provided, and sea and land segmentation is carried out on the remote sensing image.
Further, S103 specifically includes S1035 of processing the segmented remote sensing image by a morphological method, and expanding, corroding, and filling fine cavities in the remote sensing image to realize area communication of the remote sensing image.
Further, the step S103 specifically includes a step S1036 of performing edge detection on the remote sensing image after the threshold segmentation and the area connectivity, and extracting a coastline of the remote sensing image.
Further, the step S104 specifically includes, step S1041, separating land and sea of the radar image by a mask, and shielding land areas and islands of the radar image.
The invention has the following advantages:
according to the radar image fixed background mask method based on remote sensing image threshold segmentation, the characteristics that optical remote sensing images are good in performance, high in resolution, relatively obvious in sea-land boundary and convenient to separate sea and land are utilized, the remote sensing images are subjected to sea-land segmentation, and lands, islands and sea areas in a radar observation area are indirectly determined, so that the fixed background mask of the radar images is realized; the method solves the problems that the method for fixing the background mask in the prior art is not ideal in effect and high in manual participation.
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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart of a method for fixing a background mask of a radar image based on threshold segmentation of a remote sensing image according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an embodiment of S101;
FIG. 3 is a flowchart illustrating an embodiment of S103;
fig. 4 is a detailed flowchart of S104 in the embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. 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.
As shown in fig. 1, a method for fixing a background mask of a radar image based on threshold segmentation of a remote sensing image specifically includes:
s101, aligning the remote sensing image with a radar image space;
in the step, the remote sensing image is aligned with the radar image space;
firstly, a multispectral remote sensing image with the same area resolution as the sea radar image is selected. And then, determining the due north direction of the radar image, measuring the longitude and latitude of the central point of the radar image, and realizing the initial positioning of the remote sensing image by utilizing the longitude and latitude. And finally, sampling pixel points of the remote sensing image after positioning, and matching pixel coordinates of the radar image and the sampled remote sensing image, thereby realizing the spatial alignment of the remote sensing image and the radar image.
S102, cutting the remote sensing image after the space alignment;
in the step, the remote sensing image after spatial alignment is cut;
the coverage area of the remote sensing image is far larger than that of the radar image. In order to facilitate subsequent processing and improve the operation efficiency, the remote sensing image after spatial alignment is cut to be the same as the radar image in size.
S103, extracting a coastline of the remote sensing image;
in the step, sea and land segmentation is carried out on the cut remote sensing image, and a coastline of the remote sensing image is extracted;
firstly, converting the remote sensing image into a gray level image, calculating the gray level mean value mu of the whole image, and setting the size of the remote sensing image as mxn and the gray level value at the position (x, y) as f (x, y), then the gray level mean value of the whole image is
The variance of the gray scale of the whole image is,
T＝k1μ+k2σ (3)
the threshold T is estimated using equation (3), where k1，k2Setting the pixels larger than the threshold value T as 1 and setting the pixels smaller than the threshold value T as 0 for setting parameters, and finishing the threshold segmentation of the remote sensing image, namely:
the land area of the segmented image has discontinuous discontinuities, and the sea area has small targets. In order to connect adjacent land areas and eliminate small targets, the land areas are treated by a morphological method, expanded and then corroded, and fine cavities are filled to realize area communication. By regional connectivity, adjacent lands can be connected, voids filled, and land edges smoothed without changing shape and without significantly changing area.
In order to facilitate the fixing of a background mask of the radar image, edge detection is carried out on the remote sensing image after threshold segmentation and communication, and a coastline is extracted.
S104, overlapping and fusing the remote sensing image and the radar image after sea and land segmentation;
in the step, the remote sensing image and the radar image after sea and land segmentation are superposed and fused to realize a fixed background mask of the radar image.
Through the mask, sea-land separation of the radar image is realized, land areas and sea islands are shielded, the visual field is locked to the sea area concerned by people, and the background of the radar image is simplified. The method can effectively reduce the false alarm rate of the detection of the marine moving target, improve the detection performance and efficiency and establish a good foundation for the detection and tracking of the subsequent moving target.
The radar image mainly comprises a fixed land background, an ocean background, a ship target, clutter and the like. Land and island regions in the image can be masked out by fixing the background mask. Therefore, a radar image with a single background is obtained, subsequent ship target detection is only carried out aiming at the concerned sea surface area, and the target detection efficiency and pertinence are improved.
The invention provides a radar image fixed background mask method based on remote sensing image threshold segmentation. Through the mask, sea-land separation of the radar image is realized, land areas and sea islands are shielded, the visual field is locked to the sea area concerned by people, and the background of the radar image is simplified. The method can effectively reduce the false alarm rate of the detection of the marine moving target, improve the detection performance and efficiency and establish a good foundation for the detection and tracking of the subsequent moving target.
On the basis of the technical scheme, the invention can be further improved as follows:
as shown in fig. 2, S101 specifically includes S1011, selecting a remote sensing image;
in the step, selecting a remote sensing graph with the same area resolution as the radar image;
s1012, carrying out primary positioning on the remote sensing image;
in the step, the due north direction of the radar image is determined, the longitude and latitude of the central point of the radar image are obtained, and the remote sensing image is preliminarily positioned through the longitude and latitude of the central point.
Further, the S101 specifically includes, S1013, matching pixel coordinates of the remote sensing image and the radar image;
in the step, sampling is carried out on pixel points of the remote sensing image, and pixel coordinates of the remote sensing image and pixel coordinates of the radar image after sampling are matched.
Further, the S102 specifically includes cutting the remote sensing image after the spatial alignment into an image with the same size as the radar image.
As shown in fig. 3, S103 specifically includes S1031, and the mean grayscale value of the remote sensing image is calculated.
In the step, the remote sensing image is converted into a gray level image, and the gray level mean value of the remote sensing image is calculated.
Further, the S103 specifically includes S1032, obtaining a threshold of the remote sensing image;
in the step, a gray variance is obtained according to the gray mean value, and a threshold value of the remote sensing image is obtained through the gray mean value and the gray variance.
Further, the S103 specifically includes S1033, and performs threshold segmentation on the remote sensing image;
in the step, setting pixels larger than the threshold value as 1 and pixels smaller than the threshold value as 0 according to the threshold value, and carrying out threshold segmentation on the remote sensing image;
s1034, sea and land segmentation is carried out on the remote sensing image;
in this step, a coastline of the remote sensing image is proposed, and sea and land segmentation is performed on the remote sensing image.
Further, the S103 specifically includes S1035 of connecting the remote sensing images in areas;
in the step, the remote sensing image after being segmented is processed by a morphological method, and the remote sensing image is expanded, corroded and filled with tiny holes, so that the remote sensing image is communicated in the region.
Further, the step S103 specifically includes a step S1036 of providing a coastline of the remote sensing image;
in the step, the remote sensing image after threshold segmentation and region communication is subjected to edge detection, and a coastline of the remote sensing image is extracted.
As shown in fig. 4, the S104 further includes, in step S1041, separating land and sea of the radar image through a mask;
in the step, the land and the sea of the radar image are separated through a mask, and the land area and the sea island of the radar image are shielded.
The radar image fixed background mask method based on remote sensing image threshold segmentation has the following use process:
when in use, the remote sensing image is aligned with the radar image space; cutting the remote sensing image after the space alignment; carrying out sea-land segmentation on the cut remote sensing image, and extracting a coastline of the remote sensing image; and superposing and fusing the remote sensing image after sea and land segmentation and the radar image to realize a fixed background mask of the radar image.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of this document and is not intended to limit this document. Various modifications and changes may occur to those skilled in the art from this document. Any modifications, equivalents, improvements, etc. which come within the spirit and principle of the disclosure are intended to be included within the scope of the claims of this document.
Claims (10)
1. A radar image fixed background mask method based on remote sensing image threshold segmentation is characterized by specifically comprising the following steps:
s101, aligning the remote sensing image with a radar image space;
s102, cutting the remote sensing image after the space alignment;
s103, carrying out sea-land segmentation on the cut remote sensing image, and extracting a coastline of the remote sensing image;
and S104, overlapping and fusing the remote sensing image after sea and land segmentation and the radar image to realize a fixed background mask of the radar image.
2. The radar image fixed background masking method based on remote sensing image threshold segmentation as claimed in claim 1, wherein said S101 specifically comprises S1011 of selecting a remote sensing image having the same area resolution as that of said radar image;
and S1012, determining the due north direction of the radar image, obtaining the longitude and latitude of the central point of the radar image, and performing primary positioning on the remote sensing image through the longitude and latitude of the central point.
3. The radar image fixing background masking method based on remote sensing image threshold segmentation as claimed in claim 2, wherein said S101 specifically comprises, S1013, sampling pixel points of the remote sensing image, and matching pixel coordinates of the remote sensing image after sampling with pixel coordinates of the radar image.
4. The radar image fixed background mask method based on remote sensing image threshold segmentation of claim 1, wherein the S102 specifically comprises the step of cutting the remote sensing image after spatial alignment into an image with the same size as the radar image.
5. The radar image fixed background masking method based on remote sensing image threshold segmentation as claimed in claim 1, wherein said S103 comprises S1031 specifically, converting said remote sensing image into a gray level image, and calculating a gray level mean value of said remote sensing image.
6. The radar image fixed background mask method based on remote sensing image threshold segmentation as claimed in claim 5, wherein said S103 comprises S1032 specifically, a gray variance is obtained according to said gray mean, and a threshold of said remote sensing image is obtained through said gray mean and said gray variance.
7. The radar image fixing background mask method based on remote sensing image threshold segmentation of claim 6, wherein the S103 specifically comprises S1033, and the remote sensing image is subjected to threshold segmentation by setting pixels larger than the threshold value to 1 and pixels smaller than the threshold value to 0 according to the threshold value;
s1034, a coastline of the remote sensing image is provided, and sea and land segmentation is carried out on the remote sensing image.
8. The radar image background mask method based on remote sensing image threshold segmentation of claim 7, wherein the step S103 further comprises a step S1035 of processing the segmented remote sensing image by a morphological method, and expanding, corroding and filling fine holes in the remote sensing image to realize the regional connectivity of the remote sensing image.
9. The radar image fixing background masking method based on remote sensing image threshold segmentation of claim 8, wherein the S103 further comprises S1036 of performing edge detection on the remote sensing image after threshold segmentation and region connectivity, and extracting a coastline of the remote sensing image.
10. The remote sensing image threshold segmentation-based radar image fixed background masking method according to claim 1, wherein the step S104 further comprises a step S1041 of separating land and sea of the radar image through a mask to shield land areas and islands of the radar image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110544732.7A CN113192088A (en) | 2021-05-19 | 2021-05-19 | Radar image fixed background mask method based on remote sensing image threshold segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110544732.7A CN113192088A (en) | 2021-05-19 | 2021-05-19 | Radar image fixed background mask method based on remote sensing image threshold segmentation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113192088A true CN113192088A (en) | 2021-07-30 |
Family
ID=76982309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110544732.7A Pending CN113192088A (en) | 2021-05-19 | 2021-05-19 | Radar image fixed background mask method based on remote sensing image threshold segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113192088A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520896A (en) * | 2009-03-30 | 2009-09-02 | 中国电子科技集团公司第十研究所 | Method for automatically detecting cloud interfering naval vessel target by optical remote sensing image |
| CN105513041A (en) * | 2015-10-28 | 2016-04-20 | 深圳大学 | Large-scale remote sensing image sea-land segmentation method and system |
| CN108229433A (en) * | 2018-02-01 | 2018-06-29 | 中国电子科技集团公司第十五研究所 | A kind of Inshore ship detection method based on line segment detection and shape feature |
| CN108662977A (en) * | 2018-03-14 | 2018-10-16 | 浙江大学山东工业技术研究院 | A kind of refractory brick geometric dimension measurement method |
| CN109977801A (en) * | 2019-03-08 | 2019-07-05 | 中国水利水电科学研究院 | A kind of quick Dynamic Extraction method and system of region water body of optical joint and radar |
| CN110568416A (en) * | 2019-09-17 | 2019-12-13 | 南京莱斯网信技术研究院有限公司 | radar effective detection area extraction method based on remote sensing image |
-
2021
- 2021-05-19 CN CN202110544732.7A patent/CN113192088A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101520896A (en) * | 2009-03-30 | 2009-09-02 | 中国电子科技集团公司第十研究所 | Method for automatically detecting cloud interfering naval vessel target by optical remote sensing image |
| CN105513041A (en) * | 2015-10-28 | 2016-04-20 | 深圳大学 | Large-scale remote sensing image sea-land segmentation method and system |
| CN108229433A (en) * | 2018-02-01 | 2018-06-29 | 中国电子科技集团公司第十五研究所 | A kind of Inshore ship detection method based on line segment detection and shape feature |
| CN108662977A (en) * | 2018-03-14 | 2018-10-16 | 浙江大学山东工业技术研究院 | A kind of refractory brick geometric dimension measurement method |
| CN109977801A (en) * | 2019-03-08 | 2019-07-05 | 中国水利水电科学研究院 | A kind of quick Dynamic Extraction method and system of region water body of optical joint and radar |
| CN110568416A (en) * | 2019-09-17 | 2019-12-13 | 南京莱斯网信技术研究院有限公司 | radar effective detection area extraction method based on remote sensing image |
Non-Patent Citations (2)
| Title |
|---|
| 丁星: "基于超像素的遥感图像海岸线检测与海岸带地物分类", 《中国优秀博硕士学位论文全文数据库(硕士) 基础科学辑》 * |
| 梁立 等: "基于遥感影像的海岸线提取方法综述", 《地球信息科学学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Modava et al. | Integration of spectral histogram and level set for coastline detection in SAR images | |
| CN111582089B (en) | Maritime target information fusion method based on satellite infrared and visible light images | |
| Sheng et al. | Coastline detection in synthetic aperture radar (SAR) images by integrating watershed transformation and controllable gradient vector flow (GVF) snake model | |
| US20160379053A1 (en) | Method and Apparatus for Identifying Object | |
| US9031285B2 (en) | Detection of floating objects in maritime video using a mobile camera | |
| CN111126335B (en) | SAR ship identification method and system combining significance and neural network | |
| CN113920448B (en) | Flood inundation information extraction method and device, electronic equipment and storage medium | |
| Osorio et al. | An algorithm for the measurement of shoreline and intertidal beach profiles using video imagery: PSDM | |
| CN106845347A (en) | Marine oil film recognizes extracting method and system | |
| Li et al. | Waterline mapping and change detection of Tangjiashan dammed lake after Wenchuan earthquake from multitemporal high-resolution airborne SAR imagery | |
| CN105184804A (en) | Sea surface small target detection method based on airborne infrared camera aerially-photographed image | |
| CN111274878B (en) | Satellite cloud image classification method and system | |
| CN112487912A (en) | Arbitrary-direction ship detection method based on improved YOLOv3 | |
| CN112633274A (en) | Sonar image target detection method and device and electronic equipment | |
| CN112669332B (en) | Method for judging sea-sky conditions and detecting infrared targets based on bidirectional local maxima and peak value local singularities | |
| CN115797374B (en) | Airport runway extraction method based on image processing | |
| CN113192088A (en) | Radar image fixed background mask method based on remote sensing image threshold segmentation | |
| Gao | Design and implementation of marine automatic target recognition system based on visible remote sensing images | |
| WO2008021949A2 (en) | Geospatial modeling system for separating foliage data from building data based upon loose and strict tolerance noise filtering operations and related methods | |
| CN108269268B (en) | Method for automatically extracting typhoon high-wind-speed cloud system area based on microwave scatterometer data | |
| Yu et al. | Automatic extraction of green tide using dual polarization Chinese GF-3 SAR images | |
| Shi et al. | A superpixel-based coastline extraction algorithm for single-polarized ENVISAT and ERS imagery | |
| Pamungkas et al. | 3D-building reconstruction approach using semi-global matching classified | |
| CN117557584B (en) | Water body extraction method and device, electronic equipment and storage medium | |
| CN114283128B (en) | Ocean mesoscale vortex edge detection method and system based on multi-parameter threshold |
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 |