CN103942803A - SAR (Synthetic Aperture Radar) image based automatic water area detection method - Google Patents

SAR (Synthetic Aperture Radar) image based automatic water area detection method Download PDF

Info

Publication number
CN103942803A
CN103942803A CN201410185121.8A CN201410185121A CN103942803A CN 103942803 A CN103942803 A CN 103942803A CN 201410185121 A CN201410185121 A CN 201410185121A CN 103942803 A CN103942803 A CN 103942803A
Authority
CN
China
Prior art keywords
image
threshold
sar image
sar
iteration
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
Application number
CN201410185121.8A
Other languages
Chinese (zh)
Other versions
CN103942803B (en
Inventor
陈禾
魏航
毕福昆
刘璐娇
杨小婷
于文月
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN201410185121.8A priority Critical patent/CN103942803B/en
Publication of CN103942803A publication Critical patent/CN103942803A/en
Application granted granted Critical
Publication of CN103942803B publication Critical patent/CN103942803B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention provides an SAR (Synthetic Aperture Radar) image based automatic water area detection method. The SAR image based automatic water area detection method comprises the following steps of a first step, performing de-noising processing on an SAR image; a second step, computing the gradient of an input image through an edge detection operator and obtaining a gradient image of the SAR image; a third step, improving the contrast ratio of the SAR image through a contrast ratio stretching conversion algorithm; a fourth step, achieving secondary self-adaption threshold segmentation through a double-peak iterative method and obtaining two binary image; a fifth step, performing post processing on the binary image obtained in the fourth step through morphology and obtaining a crude extracting target candidate area; a sixth step, removing false alarm, marking the target candidate area extracted from the fifth step, performing statistics of the area of every connecting dark spot, setting an area threshold value according to the resolution ratio of the SAR image, removing the dark spots with the area less than the preset area and marking extracted water areas in an original drawing.

Description

Waters automatic testing method based on SAR image
Technical field
The present invention relates to a kind of waters automatic testing method based on SAR image, belong to technical field of image processing.
Background technology
Because synthetic-aperture radar (SAR) has round-the-clock, the feature such as round-the-clock, be widely used in every field such as military affairs, agricultural, aviations.Wherein, waters detection is an importance of SAR image applications.
The water surface of general land is relatively evenly with level and smooth, and the electromagnetic wave that SAR is mapped to water surface is equivalent to occur mirror-reflection, so the backscattering coefficient of water body is less, waters presents single, the uniform black blackening of textural characteristics region in SAR image.And the body surfaces such as land, massif, building are inhomogeneous, can there is slow reflection on its surface in electromagnetic wave, so the backscattering coefficient of these objects is larger, is rendered as the region of the higher and coarse texture of brightness in SAR image.
Existing waters detection algorithm mainly comprises: extracting method based on textural characteristics, based on morphologic extracting method, the extracting method based on support vector machines, the extracting method based on region growing etc.Wherein, extracting method based on textural characteristics mainly contains the algorithm based on gray level co-occurrence matrixes, the algorithm based on conversion, the algorithm based on shape facility etc., this method is generally calculated more complicated, for example the algorithm based on gray level co-occurrence matrixes need to extract the gray level co-occurrence matrixes of each pixel, and computation process is very consuming time.
The method of extracting based on morphology is mainly to utilize burn into expansion and their combinatorial operation, can from image, extract for expressing and describe the useful picture content of region shape, as border, skeleton, convex hull etc., also can carry out pre-service or aftertreatment to image, as filtration, refinement, pruning etc., but size and the operation times of the structural element of this method are difficult to determine.
First method based on support vector machines needs to determine selects and calculates these textural characteristics for which kind of textural characteristics, then utilize SVM to train classification, finally obtain the target of extracting, but be difficult to determine optimum textural characteristics combination, and calculated amount is also very large.
Method based on region growing is to determine the rule of region growing according to target imaging characteristic and priori, but selects suitable growth rule not only to need through great many of experiments training, and is sometimes very difficult.
The common shortcoming of above-mentioned these methods is that operand is large, speed is slower, be difficult to meet the requirement of real-time, and need to utilize priori and a large amount of tests to train and determine some features or rule, sometimes these features or the definite of rule are very difficult.
Summary of the invention
The object of the invention is to overcome existing methods shortcoming, proposed a kind of waters automatic testing method based on SAR image.
Be somebody's turn to do the waters automatic testing method based on SAR image, comprise the following steps:
The first step, carries out denoising to SAR image: before extracting waters target, by wave filter, SAR image is carried out to filtering processing;
Second step, taking the image after the denoising of exporting in the first step as input picture, utilizes the gradient of edge detection operator calculating input image, obtains the gradient image of SAR image;
The 3rd step, taking the image after the denoising of exporting in the first step as input picture, utilize contrast stretching mapping algorithm to improve the contrast of SAR image, be set to a fixing gray-scale value for the pixel value that is less than predetermined gray level, be set to another fixing gray-scale value for the pixel value that is greater than predetermined gray level, the pixel value of the gray level within the scope of this converts according to linear function, and the contrast that realizes SAR image strengthens;
The 4th step, utilizes bimodal process of iteration to realize secondary adaptive threshold and cuts apart: the image that utilizes bimodal process of iteration respectively second step and the 3rd step to be obtained carries out secondary Threshold segmentation, obtains two width bianry images;
The 5th step: utilize the two width bianry images that morphology obtains the 4th step respectively to carry out aftertreatment, utilize corrosion and expansive working to carry out filtering, refinement to binary map, and merge two width bianry images after morphology processing;
The 6th step: false-alarm is rejected: the object candidate area of the thick extraction that mark the 5th step obtains, and add up the area of each connection blackening, according to the resolution of SAR image, an area threshold is set, the blackening that is less than preset area is rejected, finally in former figure, mark the waters of extraction.
Wherein utilize bimodal process of iteration to realize the concrete grammar that secondary adaptive threshold cuts apart as follows: first to select an initial threshold, the gray level of image is divided into two parts, then calculate respectively this two-part gray average, calculate again the average of these two averages as new threshold value, again repeat said process, until the new threshold value of calculating and the threshold value difference of last time within preset range time iteration finish, or iteration finishes while having completed all iterationses, the threshold value that last threshold value is cut apart as image.
Wherein ask the threshold value of Threshold segmentation for the first time: first gray level image is carried out to down-sampling, then select iterations, and calculate the gray average of down-sampled images as the initial value of iteration; The grey level histogram of statistics down-sampled images, utilizes above-mentioned iterations and initial value, calculates the threshold value of Threshold segmentation for the first time according to bimodal process of iteration; The image that finally utilizes this Threshold segmentation contrast to strengthen, obtains two width binary map, the candidate region that wherein blackening is waters.
Wherein ask the threshold value of Threshold segmentation for the second time: first, add up the grey level histogram of the down-sampling gray level image that in the binary map that Threshold segmentation obtains for the first time, blackening is corresponding, and calculate the gray average of this part as the initial value of Threshold segmentation; Then,, being less than in the threshold range of cutting apart for the first time, utilize bimodal process of iteration to ask for the threshold value of Threshold segmentation for the second time; The image that finally utilizes this Threshold segmentation contrast to strengthen, finally obtains two width binary map.
Benefit of the present invention:
1, the present invention utilizes edge detection operator and two kinds of complementary methods of contrast stretching conversion, realize figure image intensifying and extract object candidate area, not only can extract accurately large waters, and can extract thin river, the artificial waters of small size etc., make the object candidate area of extraction more complete, false dismissal probability is reduced to minimum.
2, the present invention realizes secondary self-adaptation and asks threshold value, and in the time asking threshold value for the second time, in the scope of threshold value for the first time, ask the threshold value of cutting apart for the second time in zero gray level, not only reduce calculated amount, and the threshold value of asking for is partial to low gray level, can be partitioned into accurately waters, reduce greatly false-alarm.
3, the present invention has overcome existing algorithm in the difficulty of selecting the aspects such as eigenwert, structural element size, and greatly reduces the complexity of operation time.
Brief description of the drawings
Fig. 1 is the basic flow sheet that the present invention is based on the waters automatic testing method of SAR image;
Fig. 2 is the pixel value schematic diagram in the window of 5*5 in the embodiment of the present invention;
Fig. 3 is the gradient operator schematic diagram of rim detection in the embodiment of the present invention.
Specific implementation method
As shown in Figure 1, the performing step that the present invention is based on the waters automatic testing method of SAR image mainly comprises: spatial mean value filtering, gradient conversion, contrast stretching conversion, twice adaptive threshold cut apart, morphology is processed and small size is rejected, and merges the blackening image extracting based on two kinds of conversion, and false-alarm is rejected.Specific implementation is as follows:
Step 1, selecting a size is the window that N*N slides, and according to spatial filtering principle, the SAR image of input is carried out to mean filter.In the time selecting N=5, the implementation procedure of mean filter is as follows.
Pixel average in calculating chart 2:
f ‾ = 1 5 × 5 Σ i = 1 5 Σ j = 1 5 f ij - - - ( 1 )
Utilize average the pixel value that replaces intermediary image vegetarian refreshments (3,3), utilizes the aforesaid operations of little sliding window to view picture figure, finally obtains mean filter image afterwards.。
Step 2, selects Sobel edge detection operator to carry out compute gradient image.
Sobel gradient conversion: utilize Sobel operator to calculate the Grad at pixel i place, then, with the original pixel value at Grad replacement pixels point i place, can obtain the gradient image that contrast is higher.
The gradient operator of Sobel rim detection as shown in Figure 3;
Utilize the horizontal gradient component of each pixel position of these two formwork calculation images gxwith VG (vertical gradient) component g y, then utilize the publish picture amplitude M (x, y) of gradient of each pixel position in picture of these two Partial derivative estimations, in order to simplify calculating, make M (x, y)=max (| g x|, | g y|), finally use M (x, y) value to replace the pixel value of template center, can obtain gradient image.
The formula of calculated level gradient component and VG (vertical gradient) component is as follows:
g x＝-f 11-2*f 12-f 13+f 31+2*f 32+f 33 (2)
g y＝-f 11-2*f 21-f 31+f 13+2*f 23+f 33 (3)
Wherein, f ijfor the image pixel value in Sobel template window.
Step 3, selects piecewise function to carry out contrast stretching conversion to image.
The function of comparative selection degree stretching conversion is:
G ( x , y ) = a ; f ( x , y ) < t 1 k * f ( x , y ) + b ; t 1 < f ( x , y ) < t 2 c ; f ( x , y ) > t 2 - - - ( 4
k = c - a t 2 - t 1 - - - ( 5 )
b＝c-k*t 2(6)
Wherein, f (x, y) represents the pixel value that in SAR image, pixel (x, y) is located, and G (x, y) is the gray-scale value after conversion.Because waters mainly concentrates on low gray level, for contrast is significantly improved, a is typically chosen in the pixel value in [0,5] scope, and c generally selects maximum gray-scale value, and k and b are definite according to the value of a, the c that select, in addition, and t 1a gray-scale value of low gray level, through sample experiment t 1get near the value 10, t 2be a gray-scale value of high grade grey level, be chosen near the value 100.
Step 4, utilize bimodal process of iteration respectively the image of the gradient image to Sobel conversion and contrast stretching conversion carry out twice adaptive threshold and cut apart.
A) first, the image after conversion being carried out to down-sampling: proportionally L:1 carries out down-sampling, is all to adopt a point every L point with vertical direction in the horizontal direction, reduces the size of image, thus the calculated amount of asking threshold value reducing.
B) then, utilize the bimodal process of iteration of self-adaptation Threshold segmentation for the first time: the statistics grey level histogram of down-sampled images and the gray average of image, within gray level is less than 255 scope, the initial threshold T taking the gray average of image as iteration, is divided into two parts R by image histogram 1and R 2, zoning R 1and R 2average μ 1and μ 2, calculate μ 1and μ 2average be new segmentation threshold T, repeat above-mentioned steps until T changes within the specific limits, or selection iterations M carries out iteration, generally select M>20, until iteration finishes.Finally obtain the threshold value of cutting apart for the first time, and utilize the threshold value of cutting apart for the first time to cut apart respectively gradient image and contrast stretching changing image, obtain two width bianry images.
C) secondly, in the tonal range that is less than segmentation threshold for the first time, the grey level histogram of the down-sampled images that blackening that statistics is cut apart is for the first time corresponding, and calculate this part gray average corresponding to blackening.
D) last, utilize self-adaptation bimodal process of iteration to carry out Threshold segmentation for the second time: the gray average calculating in utilizing c) is as the initial threshold T of iteration, within gray level is less than the scope of segmentation threshold for the first time, grey level histogram based on c) carries out iteration and obtains the threshold value of cutting apart for the second time, and utilize this Threshold segmentation gradient image and contrast stretching changing image, the bianry image of finally being cut apart.
Step 5, morphology is processed and small size is rejected: it is mainly to utilize once corrosion and expansive working that morphology is processed, blackening image is carried out to thinning processing, and reject some small size false-alarms, utilize " also " operation, merge the blackening image extracting based on gradient image and the blackening image that conversion is extracted based on contrast stretching, obtain the candidate region of waters target.
Step 6, false-alarm is rejected: mark waters object candidate area, then add up the area of each mark connected region, according to the resolution of SAR image, select a suitable area thresholding, rejecting is less than the connected region of area thresholding, after rejecting, obtains final waters testing result image through false-alarm.

Claims (4)

1. the waters automatic testing method based on SAR image, is characterized in that, comprises the following steps:
The first step, carries out denoising to SAR image: before extracting waters target, by wave filter, SAR image is carried out to filtering processing;
Second step, taking the image after the denoising of exporting in the first step as input picture, utilizes the gradient of edge detection operator calculating input image, obtains the gradient image of SAR image;
The 3rd step, taking the image after the denoising of exporting in the first step as input picture, utilize contrast stretching mapping algorithm to improve the contrast of SAR image, be set to a fixing gray-scale value for the pixel value that is less than predetermined gray level, be set to another fixing gray-scale value for the pixel value that is greater than predetermined gray level, the pixel value of the gray level within the scope of this converts according to linear function, and the contrast that realizes SAR image strengthens;
The 4th step, utilizes bimodal process of iteration to realize secondary adaptive threshold and cuts apart: the image that utilizes bimodal process of iteration respectively second step and the 3rd step to be obtained carries out secondary Threshold segmentation, obtains two width bianry images;
The 5th step: utilize the two width bianry images that morphology obtains the 4th step respectively to carry out aftertreatment, utilize corrosion and expansive working to carry out filtering, refinement to binary map, and merge two width bianry images after morphology processing;
The 6th step: false-alarm is rejected: the object candidate area of the thick extraction that mark the 5th step obtains, and add up the area of each connection blackening, according to the resolution of SAR image, an area threshold is set, the blackening that is less than preset area is rejected, finally in former figure, mark the waters of extraction.
2. the waters automatic testing method based on SAR image as claimed in claim 1, it is characterized in that, wherein utilize bimodal process of iteration to realize the concrete grammar that secondary adaptive threshold cuts apart as follows: first to select an initial threshold, the gray level of image is divided into two parts, then calculate respectively this two-part gray average, calculate again the average of these two averages as new threshold value, again repeat said process, until the new threshold value of calculating and the threshold value difference of last time within preset range time iteration finish, or while having completed all iterationses, iteration finishes, the threshold value that last threshold value is cut apart as image.
3. the waters automatic testing method based on SAR image as claimed in claim 2, it is characterized in that, wherein ask the threshold value of Threshold segmentation for the first time: first gray level image is carried out to down-sampling, then select iterations, and calculate the gray average of down-sampled images as the initial value of iteration; The grey level histogram of statistics down-sampled images, utilizes above-mentioned iterations and initial value, calculates the threshold value of Threshold segmentation for the first time according to bimodal process of iteration; The image that finally utilizes this Threshold segmentation contrast to strengthen, obtains two width binary map, the candidate region that wherein blackening is waters.
4. the waters automatic testing method based on SAR image as claimed in claim 2, it is characterized in that, wherein ask the threshold value of Threshold segmentation for the second time: first, add up the grey level histogram of the down-sampling gray level image that in the binary map that Threshold segmentation obtains for the first time, blackening is corresponding, and calculate the gray average of this part as the initial value of Threshold segmentation; Then,, being less than in the threshold range of cutting apart for the first time, utilize bimodal process of iteration to ask for the threshold value of Threshold segmentation for the second time; The image that finally utilizes this Threshold segmentation contrast to strengthen, finally obtains two width binary map.
CN201410185121.8A 2014-05-05 2014-05-05 SAR (Synthetic Aperture Radar) image based automatic water area detection method Active CN103942803B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410185121.8A CN103942803B (en) 2014-05-05 2014-05-05 SAR (Synthetic Aperture Radar) image based automatic water area detection method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410185121.8A CN103942803B (en) 2014-05-05 2014-05-05 SAR (Synthetic Aperture Radar) image based automatic water area detection method

Publications (2)

Publication Number Publication Date
CN103942803A true CN103942803A (en) 2014-07-23
CN103942803B CN103942803B (en) 2017-05-17

Family

ID=51190454

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410185121.8A Active CN103942803B (en) 2014-05-05 2014-05-05 SAR (Synthetic Aperture Radar) image based automatic water area detection method

Country Status (1)

Country Link
CN (1) CN103942803B (en)

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104835176A (en) * 2015-01-20 2015-08-12 广西机电职业技术学院 Threshold segmentation method of laser vision image
CN105069780A (en) * 2015-07-17 2015-11-18 北京理工大学 SAR image water area detection realization method based on SoPC
CN106097368A (en) * 2016-06-22 2016-11-09 国家林业局北京林业机械研究所 A kind of recognition methods in veneer crack
CN107292869A (en) * 2017-06-07 2017-10-24 西安电子科技大学 Image Speckle detection method based on anisotropic Gaussian core and gradient search
CN107369163A (en) * 2017-06-15 2017-11-21 西安微电子技术研究所 A kind of quick SAR image object detection method based on best entropy Double Thresholding Segmentation
CN107423734A (en) * 2016-05-23 2017-12-01 中国科学院计算技术研究所 A kind of SAR image targets in ocean quick determination method and device
CN107507200A (en) * 2017-08-31 2017-12-22 电子科技大学 A kind of a wide range of water area extraction method of SAR image high-precisions based on communication with detection and noise suppressed
CN107798681A (en) * 2016-09-02 2018-03-13 天津工业大学 Small object image Fast Threshold dividing method based on mathematical morphology
CN108765406A (en) * 2018-05-31 2018-11-06 电子科技大学 A kind of snow mountain detection method based on infrared remote sensing image
CN108876772A (en) * 2018-06-05 2018-11-23 南华大学 A kind of Lung Cancer Images diagnostic system and method based on big data
CN108960085A (en) * 2018-06-20 2018-12-07 中国电子科技集团公司第五十四研究所 A kind of diameter radar image Ship Target candidate region rapid extracting method
CN110569683A (en) * 2018-06-06 2019-12-13 伟诠电子股份有限公司 bar code detection method and bar code detection system
CN110648341A (en) * 2019-09-19 2020-01-03 福建师范大学 Target boundary detection method based on scale space and subgraph
CN110688923A (en) * 2019-09-19 2020-01-14 中国电子科技集团公司第二十九研究所 Sentinel 1A SAR data-based urban inland inundation risk area extraction method
CN111028197A (en) * 2019-11-01 2020-04-17 深圳先进技术研究院 Method and terminal for detecting metal corrosion
CN111046812A (en) * 2019-12-18 2020-04-21 四创科技有限公司 Water surface floater detection method based on twin network
CN111539242A (en) * 2018-11-15 2020-08-14 杭州芯影科技有限公司 Millimeter wave imaging image processing method
CN111914686A (en) * 2020-07-15 2020-11-10 云南电网有限责任公司带电作业分公司 SAR remote sensing image water area extraction method, device and system based on surrounding area association and pattern recognition
CN112101282A (en) * 2020-09-25 2020-12-18 北京瞰天科技有限公司 Aquatic target identification method and device, electronic equipment and storage medium
CN112183534A (en) * 2020-10-07 2021-01-05 西安电子科技大学 Moving target intelligent combined detection method based on video synthetic aperture radar
CN112329791A (en) * 2020-10-30 2021-02-05 中国电子科技集团公司第五十四研究所 Automatic extraction method for hyperspectral image water area
CN113177949A (en) * 2021-04-16 2021-07-27 中南大学 Large-size rock particle feature identification method and device
CN113362293A (en) * 2021-05-27 2021-09-07 西安理工大学 SAR image ship target rapid detection method based on significance
CN114511471A (en) * 2022-04-18 2022-05-17 广州骏天科技有限公司 Image optimization method and system based on gray level co-occurrence matrix
CN115019187A (en) * 2022-08-09 2022-09-06 中国科学院空天信息创新研究院 Detection method, device, equipment and medium for SAR image ship target
CN112101282B (en) * 2020-09-25 2024-04-26 北京瞰天科技有限公司 Water target identification method and device, electronic equipment and storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102175993A (en) * 2011-01-28 2011-09-07 华中科技大学 Radar scene matching feature reference map preparation method based on satellite SAR (synthetic aperture radar) images
US8134489B2 (en) * 2008-07-14 2012-03-13 The Boeing Company System and method for bistatic change detection for perimeter monitoring

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8134489B2 (en) * 2008-07-14 2012-03-13 The Boeing Company System and method for bistatic change detection for perimeter monitoring
CN102175993A (en) * 2011-01-28 2011-09-07 华中科技大学 Radar scene matching feature reference map preparation method based on satellite SAR (synthetic aperture radar) images

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
张怀利等: ""从SAR遥感图像中提取水域的一种双模式结合方法"", 《光学技术》 *
李琳琳: ""遥感图像分割中阈值的自动选取技术研究"", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 *

Cited By (42)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104835176B (en) * 2015-01-20 2018-02-27 广西机电职业技术学院 A kind of threshold segmentation method of laser vision image
CN104835176A (en) * 2015-01-20 2015-08-12 广西机电职业技术学院 Threshold segmentation method of laser vision image
CN105069780A (en) * 2015-07-17 2015-11-18 北京理工大学 SAR image water area detection realization method based on SoPC
CN105069780B (en) * 2015-07-17 2017-12-08 北京理工大学 A kind of SAR image waters detection implementation method based on SoPC
CN107423734A (en) * 2016-05-23 2017-12-01 中国科学院计算技术研究所 A kind of SAR image targets in ocean quick determination method and device
CN107423734B (en) * 2016-05-23 2020-01-21 中国科学院计算技术研究所 SAR image ocean target rapid detection method and device
CN106097368B (en) * 2016-06-22 2019-05-31 国家林业局北京林业机械研究所 A kind of recognition methods in veneer crack
CN106097368A (en) * 2016-06-22 2016-11-09 国家林业局北京林业机械研究所 A kind of recognition methods in veneer crack
CN107798681B (en) * 2016-09-02 2021-01-15 天津工业大学 Small target image fast threshold segmentation method based on mathematical morphology
CN107798681A (en) * 2016-09-02 2018-03-13 天津工业大学 Small object image Fast Threshold dividing method based on mathematical morphology
CN107292869A (en) * 2017-06-07 2017-10-24 西安电子科技大学 Image Speckle detection method based on anisotropic Gaussian core and gradient search
CN107292869B (en) * 2017-06-07 2020-04-07 西安电子科技大学 Image speckle detection method based on anisotropic Gaussian kernel and gradient search
CN107369163A (en) * 2017-06-15 2017-11-21 西安微电子技术研究所 A kind of quick SAR image object detection method based on best entropy Double Thresholding Segmentation
CN107507200B (en) * 2017-08-31 2021-03-30 电子科技大学 SAR image high-precision large-range water area extraction method based on connectivity detection and noise suppression
CN107507200A (en) * 2017-08-31 2017-12-22 电子科技大学 A kind of a wide range of water area extraction method of SAR image high-precisions based on communication with detection and noise suppressed
CN108765406A (en) * 2018-05-31 2018-11-06 电子科技大学 A kind of snow mountain detection method based on infrared remote sensing image
CN108876772A (en) * 2018-06-05 2018-11-23 南华大学 A kind of Lung Cancer Images diagnostic system and method based on big data
CN110569683B (en) * 2018-06-06 2023-06-09 伟诠电子股份有限公司 Bar code detection method and bar code detection system
CN110569683A (en) * 2018-06-06 2019-12-13 伟诠电子股份有限公司 bar code detection method and bar code detection system
CN108960085B (en) * 2018-06-20 2021-10-01 中国电子科技集团公司第五十四研究所 Method for rapidly extracting synthetic aperture radar image ship target candidate area
CN108960085A (en) * 2018-06-20 2018-12-07 中国电子科技集团公司第五十四研究所 A kind of diameter radar image Ship Target candidate region rapid extracting method
CN111539242A (en) * 2018-11-15 2020-08-14 杭州芯影科技有限公司 Millimeter wave imaging image processing method
CN110688923A (en) * 2019-09-19 2020-01-14 中国电子科技集团公司第二十九研究所 Sentinel 1A SAR data-based urban inland inundation risk area extraction method
CN110648341A (en) * 2019-09-19 2020-01-03 福建师范大学 Target boundary detection method based on scale space and subgraph
CN111028197A (en) * 2019-11-01 2020-04-17 深圳先进技术研究院 Method and terminal for detecting metal corrosion
CN111046812B (en) * 2019-12-18 2023-04-07 四创科技有限公司 Water surface floater detection method based on twin network
CN111046812A (en) * 2019-12-18 2020-04-21 四创科技有限公司 Water surface floater detection method based on twin network
CN111914686A (en) * 2020-07-15 2020-11-10 云南电网有限责任公司带电作业分公司 SAR remote sensing image water area extraction method, device and system based on surrounding area association and pattern recognition
CN111914686B (en) * 2020-07-15 2022-10-18 云南电网有限责任公司带电作业分公司 SAR remote sensing image water area extraction method, device and system based on surrounding area association and pattern recognition
CN112101282A (en) * 2020-09-25 2020-12-18 北京瞰天科技有限公司 Aquatic target identification method and device, electronic equipment and storage medium
CN112101282B (en) * 2020-09-25 2024-04-26 北京瞰天科技有限公司 Water target identification method and device, electronic equipment and storage medium
CN112183534A (en) * 2020-10-07 2021-01-05 西安电子科技大学 Moving target intelligent combined detection method based on video synthetic aperture radar
CN112183534B (en) * 2020-10-07 2023-05-23 西安电子科技大学 Moving target intelligent joint detection method based on video synthetic aperture radar
CN112329791A (en) * 2020-10-30 2021-02-05 中国电子科技集团公司第五十四研究所 Automatic extraction method for hyperspectral image water area
CN112329791B (en) * 2020-10-30 2022-12-27 中国电子科技集团公司第五十四研究所 Automatic extraction method for hyperspectral image water area
CN113177949A (en) * 2021-04-16 2021-07-27 中南大学 Large-size rock particle feature identification method and device
CN113177949B (en) * 2021-04-16 2023-09-01 中南大学 Large-size rock particle feature recognition method and device
CN113362293A (en) * 2021-05-27 2021-09-07 西安理工大学 SAR image ship target rapid detection method based on significance
CN114511471B (en) * 2022-04-18 2022-07-01 广州骏天科技有限公司 Image optimization method and system based on gray level co-occurrence matrix
CN114511471A (en) * 2022-04-18 2022-05-17 广州骏天科技有限公司 Image optimization method and system based on gray level co-occurrence matrix
CN115019187B (en) * 2022-08-09 2022-11-22 中国科学院空天信息创新研究院 Detection method, device, equipment and medium for SAR image ship target
CN115019187A (en) * 2022-08-09 2022-09-06 中国科学院空天信息创新研究院 Detection method, device, equipment and medium for SAR image ship target

Also Published As

Publication number Publication date
CN103942803B (en) 2017-05-17

Similar Documents

Publication Publication Date Title
CN103942803A (en) SAR (Synthetic Aperture Radar) image based automatic water area detection method
CN102324021B (en) Infrared dim-small target detection method based on shear wave conversion
CN107808383B (en) Rapid detection method for SAR image target under strong sea clutter
CN101714252A (en) Method for extracting road in SAR image
CN103778627B (en) A kind of marine site based on SAR image oil spilling detection method
CN105654091A (en) Detection method and apparatus for sea-surface target
CN105405138B (en) Waterborne target tracking based on conspicuousness detection
CN104021553B (en) A kind of sonar image object detection method based on pixel layering
CN103413303A (en) Infrared target segmentation method based on joint obviousness
Nair et al. Fuzzy logic-based automatic contrast enhancement of satellite images of ocean
CN103473755B (en) Based on the sparse denoising method of SAR image that change detects
CN102930273A (en) Auroral oval segmenting method based on brightness self-adaptive level set
CN102324099A (en) Step edge detection method oriented to humanoid robot
CN102999908A (en) Synthetic aperture radar (SAR) airport segmentation method based on improved visual attention model
CN107993219A (en) A kind of deck of boat detection method of surface flaw based on machine vision
CN114764801A (en) Weak and small ship target fusion detection method and device based on multi-vision significant features
Chen et al. Road damage detection and classification using mask R-CNN with DenseNet backbone
CN104574417B (en) A kind of image border gray scale Characteristic fluctuation tolerance and self-adapting detecting method
CN105354547A (en) Pedestrian detection method in combination of texture and color features
CN102750675A (en) Non-local means filtering method for speckle noise pollution image
CN104637060A (en) Image partition method based on neighbor-hood PCA (Principal Component Analysis)-Laplace
CN104036491A (en) SAR image segmentation method based on area division and self-adaptive polynomial implicit model
CN103177244A (en) Method for quickly detecting target organisms in underwater microscopic images
CN109544531A (en) A method of GPR image Damage Types are identified based on shape feature
CN109872358B (en) Marine oil film identification method for shipborne radar image based on active contour model

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant