WO2016101279A1 - Quick detecting method for synthetic aperture radar image of ship target - Google Patents
Quick detecting method for synthetic aperture radar image of ship target Download PDFInfo
- Publication number
- WO2016101279A1 WO2016101279A1 PCT/CN2014/095202 CN2014095202W WO2016101279A1 WO 2016101279 A1 WO2016101279 A1 WO 2016101279A1 CN 2014095202 W CN2014095202 W CN 2014095202W WO 2016101279 A1 WO2016101279 A1 WO 2016101279A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- sub
- threshold
- gpu
- images
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
Definitions
- the invention belongs to the technical field of image processing, and in particular relates to a rapid detection method for a ship target of a synthetic aperture radar image.
- Ship inspection is a routine task in the world's coastal countries. It has a wide range of applications in civil and military fields. It can carry out water transportation, illegal hunting, smuggling detection and management of specific sea areas and ports, and rescue ships for disasters.
- the sea area is vast, with an area of more than 3 million square kilometers. It is rich in marine resources. It is of great value and significance to carry out research on ship target detection.
- Synthetic Aperture Radar is a mature active microwave imaging radar. It has all-weather, all-day, and penetrating capability. It is compared with traditional visible and infrared sensors. The aspect has a unique advantage. With the development of technologies such as embedded technology, integrated circuit technology, and micro-machine manufacturing, SAR has gradually achieved miniaturization and miniaturization. At the same time, due to its low cost, flexibility and access to any designated place, UAVs can complement satellite remote sensing technology and rapidly develop in ocean observation applications. As the resolution of SAR continues to increase, the amount of data information provided by SAR images is also increasing. Quickly and accurately interpreting SAR images and obtaining useful information is an important issue in current SAR target detection. Fast analysis of SAR graphics, traditional serial algorithms have high requirements on system hardware, high-speed CPU, large-capacity memory and hard disk, and the performance improvement of system hardware is still very limited, it is difficult to meet the current slowdown of SAR images. Detect demand.
- the invention provides a rapid detection method for synthetic aperture radar image ship target, which can solve the above problems.
- a method for quickly detecting a target image of a synthetic aperture radar comprising the following steps:
- Target screening steps including:
- TBI1 ⁇ BI ⁇ TBI2 If TBI1 ⁇ BI ⁇ TBI2, it is a general uneven background clutter class
- TBI2 ⁇ BI it is a very uneven background clutter class
- the GPU sequentially processes the three types of sub-images according to their corresponding constant false alarm detection thresholds T1 to obtain a target area, and the three types of sub-images respectively use different processing algorithms to calculate a threshold T1. .
- the setting method of the boundary curve is:
- ⁇ 0 (x, y) is the level set function of the initial boundary curve C
- H( ⁇ ) is the Hai's function
- I(x, y) is the image in the narrow-band region, ⁇ , ⁇ , ⁇ 1 , ⁇ 2 Representing energy weights separately;
- the boundary curve is evolved n times in succession until all points on the image are traversed, and the boundary between land and sea is obtained.
- the boundary curve is initialized according to the solution short time interval equation
- F 1, where T(x, y, z) is a given point (x, y, z) to the boundary curve.
- the contraction time, F is the speed parameter.
- the set speed parameter F is 1, and the point where the distance boundary curve C is equal to or smaller than 1 forms a region to be inspected, and the boundary of the region to be inspected is the boundary curve. C.
- the Euler-Lagrangian method is used to solve the minimum value of the energy function of the boundary curve C,
- L(C) is the length of the closed curve C and S b (C) is the area of the inner area of the curve C.
- the calculation method of the background change index BI of the sub-image is:
- n is the number of pixels included in each sub-image.
- the calculation method of the gray threshold T is:
- the GPU sequentially processes the three types of sub-images separately:
- the GPU starts multi-threading and runs the kernel function: the CPU first loads the first type of threshold algorithm into the GPU, and as a multi-threaded kernel function, calculates a threshold, and uses the threshold as T1, which belongs to the first sub-image. A sub-image of a type is used for target detection, and the detection result is returned to the memory and copied to the memory. Secondly, the CPU loads the second type of threshold algorithm into the GPU, calculates the threshold, and uses the threshold as T1 as a multi-threaded kernel function.
- Target detection is performed on the sub-images belonging to the second category in all the sub-images, and the detection result is returned to the video memory and copied to the memory; again, the CPU loads the third-level threshold algorithm into the GPU as a multi-threaded kernel function, and calculates Threshold value, and using the threshold as T1, performing target detection on sub-images belonging to the second category in all sub-images, Return the test results to the video memory and copy them to memory.
- the first type of sub-images are uniform background clutter, and a threshold is calculated by using a Gaussian distribution statistical model
- the sub-image images of the second type are generally uneven background clutter, and the threshold is calculated by using a Weibull distribution statistical model
- the third type of sub-images are extremely uneven background clutter, and the G 0 distribution model is used to calculate the threshold.
- the advantages and positive effects of the present invention are: the method for quickly detecting the target image of the synthetic aperture radar of the present invention, firstly separating the land from the ocean region, filtering out the image of the land portion, and improving the detection efficiency; secondly, Perform preliminary statistics on the graph, set appropriate global thresholds, perform preliminary screening on SAR image targets, and segment the image into several sub-image blocks. Finally, use CUDA technology to perform constant false alarm detection on the three distributed graphs to detect effective Ship target.
- FIG. 1 is a flow chart showing an embodiment of a method for quickly detecting a synthetic aperture radar image object according to the present invention.
- Embodiment 1 provides a method for quickly detecting a target image of a synthetic aperture radar, including the following steps:
- S1 sea-land separation step, setting boundary curve, and separating sea and land by boundary curve, and obtaining ocean area image with effective data only in marine area;
- Step S1 separates the land and sea, removes the land area, reduces the influence of the land area on the target detection, and reduces the calculation amount, which is beneficial to improve the speed and accuracy of the target detection.
- target screening steps including:
- the ocean area image is divided into several sub-images by using the position of the candidate target area, and each candidate target area corresponds to one sub-image;
- step S2 is based on global threshold image segmentation, and the SAR image is segmented into several sub-images to form the basis for the identification of ship targets.
- TBI1 ⁇ BI ⁇ TBI2 it is a general heterogeneous clutter class
- the clutter statistical model in the background area is a key factor in determining the performance of the detection algorithm. Due to the relatively variable sea surface conditions, the statistical characteristics of clutter are very complicated. If the statistical model does not describe the clutter characteristics well, it will cause the performance of the constant false alarm detector to deteriorate.
- the existing constant false alarm target detection algorithm generally adopts global modeling, and uses the same background clutter distribution model for all regions, resulting in the use of the model in the unused area mismatch, making detection The performance is significantly reduced.
- the detection method of the present embodiment fully considers the advantages and disadvantages of each statistical model based on the in-depth analysis of the constant false alarm detection based on different statistical distribution models, and combines the constant false alarm detection algorithm according to the mean value of the SAR sub-image. And variance, the SAR sub-image is divided into three types: uniform background clutter, general uneven background clutter and extremely uneven background clutter. For these three different types, the constant false alarm detection algorithm suitable for this kind of characteristics is adopted to improve the detection accuracy.
- the GPU sequentially processes the three types of pixel units according to the threshold T1 to obtain a target area, and the three types of pixel units respectively use different processing algorithms to calculate the threshold T1.
- the Unified Computing Device Architecture (CUDA) technology is adopted, and the algorithm implementation based on three different distributions is optimized according to the characteristics of the GPU, and an efficient constant false alarm target detection algorithm is realized.
- the CPU implementation greatly shortens the data processing time and can meet the real-time requirements of SAR target detection.
- the setting method of the boundary curve is:
- ⁇ 0 (x, y) is the level set function of the initial boundary curve C
- H( ⁇ ) is the Hai's function
- I(x, y) is the image in the narrow-band region, ⁇ , ⁇ , ⁇ 1 , ⁇ 2 Representing energy weights separately;
- the boundary curve is evolved n times in succession until all points on the image are traversed, and the boundary between the land and the sea is obtained.
- the detection method of the present embodiment simplifies the initial evolution curve by using the initial boundary parameters under specific conditions on the basis of the advantages of the narrow-band solution in the analysis level set method and the Mumford-Shah model, thereby narrowing the solution and Mumford in the level set method.
- the -Shah model is effectively combined to quickly obtain the separation effect of the land and sea areas.
- the boundary curve is initialized according to the solution short time interval equation
- F 1, where T(x, y, z) is the contraction of the given point (x, y, z) to the boundary curve.
- Time, F is the speed parameter. Since the characteristics of F and the image are independent of each other, in the initial curve contour, the set speed parameter F is set to 1, and the point where the distance boundary curve C is equal to or smaller than 1 forms a to-be-detected area. The boundary of the area to be inspected is the boundary curve C.
- the Euler-Lagrangian method is used to solve the minimum value of the energy function of the boundary curve C,
- L(C) is the length of the closed curve C and S b (C) is the area of the inner area of the curve C.
- step S12 the solution of the partial differential equation can be obtained.
- the iteration formula is:
- the calculation method of the background change index BI of the sub-image is:
- m is the number of pixels included in each sub-image. Since the variance is a measure of the degree of background change, in the SAR image, because of the multiplicative noise, the variance can not accurately represent the degree of background change. Therefore, the detection method of this embodiment introduces each of the background change indices BI.
- the SAR sub-image has m pixels and calculates BI separately.
- the calculation method of the gray threshold T is:
- the total gray level of the image of the ocean area is divided into L levels, the total number of pixels of the image of the ocean area is n, and the number of pixels of the kth gray level is n k , and the normalized square of the kth gray level is obtained.
- the GPU sequentially processes the three types of pixel units separately:
- the GPU starts multi-threading and runs the kernel function: the CPU first loads the threshold algorithm of the first type into the GPU, and uses the kernel function of the multi-thread to calculate the threshold, and uses the threshold as the T1, and belongs to the first in all the sub-images.
- the sub-image of the class performs target detection, and returns the detection result to the video memory and copies it to the memory.
- the CPU loads the second type threshold algorithm into the GPU, calculates the threshold, and uses the threshold as T1 as a multi-threaded kernel function.
- the sub-images of the first type are uniform clutter types, and a threshold is calculated by using a Gaussian distribution statistical model;
- the sub-image images of the second type are generally non-uniform clutter, and the threshold is calculated by using a Weibull distribution statistical model;
- the sub-images of the third type are extremely heterogeneous clutter types, and the threshold is calculated using a G 0 distribution model.
- the constant false alarm detection algorithm based on Gaussian distribution is used to solve the mean ⁇ m of the mixed Gaussian model according to the EM algorithm:
- the ⁇ m is taken into the following formula to calculate the detection threshold:
- T I B(-lnP fa ) 1/C
- n is the equivalent visual number
- ⁇ is the shape parameter
- ⁇ is the scale parameter
- ⁇ ( ⁇ ) is the digamma function.
Abstract
A quick detecting method for synthetic aperture radar image of ship target, comprising the following steps: (1) a step of separating land and sea; (2) a step of target screening; (3) setting a background cluster statistical model; (4) GPU processes three types of images respectively according to corresponding constant false alarm rate detection threshold T1 thereto at a GPU platform, and acquires a target area, and the three types of images respectively adapts different processing algorithms to calculate the threshold T1. The method firstly separates the land and sea area, and filters images of the land part, and improves a detection efficiency; secondly, performs a preliminary statistics on shapes, and sets a suitable overall threshold, and preliminary screens the SAR image target, and splits images to several sub-image blocks; finally utilizes CUDA technology to perform a constant false alarm rate detection on the three types of distributed shapes and detects the effective ship target. The present invention can accurately and rapidly accomplish detection of the ship target.
Description
本发明属于图像处理技术领域,具体地说,是涉及一种合成孔径雷达图像舰船目标快速检测方法。The invention belongs to the technical field of image processing, and in particular relates to a rapid detection method for a ship target of a synthetic aperture radar image.
舰船检测是世界各临海国家的常规任务,在民用、军事等领域拥有广泛的应用,可以对特定海域和港口进行水运交通,非法捕猎、走私的检测和管理,对遇难船只进行救助等,我国海域广阔,面积约为300多万平方公里,海洋资源丰富,开展舰船目标检测研究具有重要的价值和意义。Ship inspection is a routine task in the world's coastal countries. It has a wide range of applications in civil and military fields. It can carry out water transportation, illegal hunting, smuggling detection and management of specific sea areas and ports, and rescue ships for disasters. The sea area is vast, with an area of more than 3 million square kilometers. It is rich in marine resources. It is of great value and significance to carry out research on ship target detection.
合成孔径雷达(Synthetic Aperture Radar,SAR)是一种成熟的主动式微波成像雷达,因其具有全天候、全天时、穿透能力强的特点,与传统的可见光、红外等传感器相比在目标检测方面具有得天独厚的优势。随着嵌入式技术、集成电路技术以及微机械制造等技术的发展,SAR逐步实现了小型化、微型化。与此同时,无人机由于其低成本、机动灵活度强、可到达任意指定的地方等诸多特点,可与卫星遥感技术相互补充,在海洋观测应用方面得到迅速发展。随着SAR的分辨率不断提升,SAR图像提供的数据信息量也越来越大,快速、准确地对SAR图像进行解译,获取有用信息是当前SAR目标检测的一个重要问题。快速对SAR图形进行分析,传统的串行算法对系统硬件要求较高,需要高速的CPU、大容量内存和硬盘,而系统硬件的性能提升还是很有限的,很难满足目前对SAR图像的减速检测需求。Synthetic Aperture Radar (SAR) is a mature active microwave imaging radar. It has all-weather, all-day, and penetrating capability. It is compared with traditional visible and infrared sensors. The aspect has a unique advantage. With the development of technologies such as embedded technology, integrated circuit technology, and micro-machine manufacturing, SAR has gradually achieved miniaturization and miniaturization. At the same time, due to its low cost, flexibility and access to any designated place, UAVs can complement satellite remote sensing technology and rapidly develop in ocean observation applications. As the resolution of SAR continues to increase, the amount of data information provided by SAR images is also increasing. Quickly and accurately interpreting SAR images and obtaining useful information is an important issue in current SAR target detection. Fast analysis of SAR graphics, traditional serial algorithms have high requirements on system hardware, high-speed CPU, large-capacity memory and hard disk, and the performance improvement of system hardware is still very limited, it is difficult to meet the current slowdown of SAR images. Detect demand.
实用新型内容Utility model content
本发明为了解决现有的合成孔径雷达目标检测方法对硬件要求高,运算速度慢的技术问题,提出了一种合成孔径雷达图像舰船目标快速检测方法,可以解决上述问题。
In order to solve the technical problem that the existing synthetic aperture radar target detection method has high hardware requirements and slow operation speed, the invention provides a rapid detection method for synthetic aperture radar image ship target, which can solve the above problems.
为了解决上述技术问题,本发明采用以下技术方案予以实现:In order to solve the above technical problem, the present invention is implemented by the following technical solutions:
一种合成孔径雷达图像目标快速检测方法,包括以下步骤:A method for quickly detecting a target image of a synthetic aperture radar, comprising the following steps:
(1)、海陆分离步骤,演化边界曲线,并以边界曲线为界进行海陆分离,得到具有有效目标的海洋区域图像;(1) The sea-land separation step, evolving the boundary curve, and separating the sea and land with the boundary curve as the boundary, and obtaining the image of the marine area with effective targets;
(2)、目标筛选步骤,包括:(2) Target screening steps, including:
(21)、设置灰度阈值T,将海洋区域图像中灰度值大于T的像素的索引值赋值为该像素的灰度值,否则赋值为0,并将所得到的所有索引值建立一索引矩阵;(21), setting the gray threshold T, assigning the index value of the pixel whose gray value is greater than T in the image of the ocean area to the gray value of the pixel, otherwise assigning a value of 0, and establishing an index for all the obtained index values. matrix;
(22)、将所述索引矩阵中非0的区域设定为候选目标区域;(22) setting a non-zero region in the index matrix as a candidate target region;
(23)、以所述候选目标区域的位置为界,将海洋区域图像分隔成若干子图像,每一个候选目标区域对应一个子图像;(23) dividing the image of the marine area into a plurality of sub-images by using the position of the candidate target area, and each candidate target area corresponds to one sub-image;
(3)、设置背景杂波统计模型,包括:(3) Set the background clutter statistical model, including:
(31)、分别计算各子图像的背景变化指数BI;(31), respectively calculating the background change index BI of each sub-image;
(32)、设定阈值TBI1和TBI2,其中TBI1<TBI2,根据背景变化指数BI将子图像划分为三类:(32) Setting thresholds TBI1 and TBI2, where TBI1 < TBI2, the sub-images are divided into three categories according to the background change index BI:
如果BI≤TBI1,为均匀背景杂波类;If BI≤TBI1, it is a uniform background clutter class;
如果TBI1<BI≤TBI2,为一般不均匀背景杂波类;If TBI1 < BI ≤ TBI2, it is a general uneven background clutter class;
如果TBI2<BI,为极不均匀背景杂波类;If TBI2<BI, it is a very uneven background clutter class;
(4)、在GPU平台下,GPU依次对所述三类子图像根据其对应恒虚警检测阈值T1分别进行处理,获得目标区域,所述三类子图像分别采用不同的处理算法计算阈值T1。(4) Under the GPU platform, the GPU sequentially processes the three types of sub-images according to their corresponding constant false alarm detection thresholds T1 to obtain a target area, and the three types of sub-images respectively use different processing algorithms to calculate a threshold T1. .
进一步的,所述步骤(1)中,所述边界曲线的设置方法为:Further, in the step (1), the setting method of the boundary curve is:
(11)、初始化边界曲线C,定义边界曲线C内区域的水平集函数Φ,设置窄带半径,以边界曲线C上的点为中心,窄带半径为半径,获得窄带区域;(11) Initialize the boundary curve C, define the horizontal set function Φ of the region in the boundary curve C, set the narrow band radius, take the point on the boundary curve C as the center, and the narrow band radius as the radius to obtain the narrow band region;
(12)、计算边界曲线C的能量函数的最小值,采用海氏函数和狄利克冲击函数,得到偏微分方程的解为:
(12) Calculate the minimum value of the energy function of the boundary curve C, and use the Hai's function and the Dirich impact function to obtain the solution of the partial differential equation as:
其中,Φ0(x,y)为初始化边界曲线C的水平集函数;H(Φ)为海氏函数,I(x,y)为窄带区域内的图像,μ,ν,λ1,λ2分别表示能量权重;Where Φ 0 (x, y) is the level set function of the initial boundary curve C; H(Φ) is the Hai's function, I(x, y) is the image in the narrow-band region, μ, ν, λ 1 , λ 2 Representing energy weights separately;
(13)、将窄带区域内所有点代入初始化边界曲线C的水平集函数Φ0(x,y)=0,演化成新的边界曲线,并计新的边界曲线的水平集函数为Φ1;(13) Substituting all the points in the narrowband region into the level set function Φ 0 (x, y) = 0 of the initialization boundary curve C, and evolving into a new boundary curve, and calculating the level set function of the new boundary curve as Φ 1 ;
(14)、连续n次演化边界曲线,直到遍历完图像上所有点,获取陆地和海域的分界线
(14), the boundary curve is evolved n times in succession until all points on the image are traversed, and the boundary between land and sea is obtained.
(15)、以陆地和海域的分界线为界进行海陆分离,剔除陆地数据,得到具有有效目标的海洋区域图像。(15), with the boundary between land and sea Separation of land and sea for the boundary, eliminating land data, and obtaining images of marine areas with effective targets.
进一步的,所述步骤(11)中,根据解短时距方程|▽T|F=1初始化边界曲线,其中T(x,y,z)为给定点(x,y,z)到边界曲线的收缩时间,F为速度参数,在初始曲线轮廓时,设定速度参数F为1,将距离边界曲线C等于或小于1的点形成待检区域,所述待检区域的边界即为边界曲线C。Further, in the step (11), the boundary curve is initialized according to the solution short time interval equation |▽T|F=1, where T(x, y, z) is a given point (x, y, z) to the boundary curve. The contraction time, F is the speed parameter. In the initial curve contour, the set speed parameter F is 1, and the point where the distance boundary curve C is equal to or smaller than 1 forms a region to be inspected, and the boundary of the region to be inspected is the boundary curve. C.
进一步的,所述步骤(12)中采用欧拉-拉格朗日方法求解边界曲线C的能量函数的最小值,
Further, in the step (12), the Euler-Lagrangian method is used to solve the minimum value of the energy function of the boundary curve C,
其中L(C)为闭合曲线C的长度,Sb(C)为曲线C内部区域面积。Where L(C) is the length of the closed curve C and S b (C) is the area of the inner area of the curve C.
进一步的,所述步骤(12)中,由偏微分方程的解可得到的迭代公式为:Further, in the step (12), the solution of the partial differential equation can be obtained The iteration formula is:
其中,among them,
水平集函数在(x,y)的曲率,为前向差分运算。The set of functions of the level set function at (x, y), For forward differential operation.
进一步的,所述步骤(31)中,子图像的背景变化指数BI的计算方法为:Further, in the step (31), the calculation method of the background change index BI of the sub-image is:
其中,m为每个子图像所包括的像素数。Where m is the number of pixels included in each sub-image.
进一步的,所述步骤(21)中,所述灰度阈值T的计算方法为:Further, in the step (21), the calculation method of the gray threshold T is:
(211)、将海洋区域图像的总灰度划分为L级,海洋区域图像的总像素个数为n,第k级灰度的像素个数为nk,则第k级灰度的归一化直方图为:p(k)=nk/n(k=0,1,2……,L-1);(211), dividing the total gray level of the image of the ocean area into L levels, the total number of pixels of the image of the ocean area is n, and the number of pixels of the k-th gray level is n k , then the normalization of the k-th gray level The histogram is: p(k)=n k /n(k=0,1,2...,L-1);
进一步的,所述步骤(4)中,在GPU平台下,GPU依次对所述三类子图像分别进行处理的方法为:Further, in the step (4), under the GPU platform, the GPU sequentially processes the three types of sub-images separately:
(41)初始化GPU:由CPU启动CUDA,设置GPU相关参数,分配数据内存空间,并初始化输入子图像;(41) Initialize the GPU: start CUDA by the CPU, set GPU related parameters, allocate data memory space, and initialize the input sub-image;
(42)将子图像读入GPU显存:在CUDA框架下,分配显存,并将子图像从内存读入到GPU显存中;(42) Reading the sub-image into the GPU memory: in the CUDA framework, allocating the memory and reading the sub-image from the memory into the GPU memory;
(43)GPU开启多线程,运行内核函数:CPU首先将第一类的阈值算法载入GPU,作为多线程的内核函数,计算出阈值,并以该阈值作为T1,对所有子图像中属于第一类的子图像进行目标检测,将检测结果返回显存并拷贝到内存;其次,CPU将第二类的阈值算法载入GPU,计算出阈值,并以该阈值作为T1,作为多线程的内核函数,对所有子图像中属于第二类的子图像进行目标检测,将检测结果返回显存并拷贝到内存;再次,CPU将第三类的阈值算法载入GPU,作为多线程的内核函数,计算出阈值,并以该阈值作为T1,对所有子图像中属于第二类的子图像进行目标检测,
将检测结果返回显存并拷贝到内存。(43) The GPU starts multi-threading and runs the kernel function: the CPU first loads the first type of threshold algorithm into the GPU, and as a multi-threaded kernel function, calculates a threshold, and uses the threshold as T1, which belongs to the first sub-image. A sub-image of a type is used for target detection, and the detection result is returned to the memory and copied to the memory. Secondly, the CPU loads the second type of threshold algorithm into the GPU, calculates the threshold, and uses the threshold as T1 as a multi-threaded kernel function. Target detection is performed on the sub-images belonging to the second category in all the sub-images, and the detection result is returned to the video memory and copied to the memory; again, the CPU loads the third-level threshold algorithm into the GPU as a multi-threaded kernel function, and calculates Threshold value, and using the threshold as T1, performing target detection on sub-images belonging to the second category in all sub-images,
Return the test results to the video memory and copy them to memory.
(44)释放GPU资源:当程序执行完毕后,释放GPU显存,回收GPU资源,退出程序。(44) Release GPU resources: When the program is executed, release the GPU memory, recycle the GPU resources, and exit the program.
进一步的,所述第一类的子图像为均匀背景杂波类,采用高斯分布统计模型计算阈值;Further, the first type of sub-images are uniform background clutter, and a threshold is calculated by using a Gaussian distribution statistical model;
所述第二类的子图像像为一般不均匀背景杂波类,采用韦布尔分布统计模型计算阈值;The sub-image images of the second type are generally uneven background clutter, and the threshold is calculated by using a Weibull distribution statistical model;
所述第三类的子图像为极不均匀背景杂波类,采用G0分布模型计算阈值。The third type of sub-images are extremely uneven background clutter, and the G 0 distribution model is used to calculate the threshold.
与现有技术相比,本发明的优点和积极效果是:本发明的合成孔径雷达图像目标快速检测方法,首先进行陆地与海洋区域的分离,滤除陆地部分的图像,提高检测效率;其次,对图形进行初步统计,设置合适的全局阈值,对SAR图像目标做初步筛选,将图像分割成若干子图像块;最后利用CUDA技术,对三种分布的图形进行恒虚警检测,检测出有效的舰船目标。Compared with the prior art, the advantages and positive effects of the present invention are: the method for quickly detecting the target image of the synthetic aperture radar of the present invention, firstly separating the land from the ocean region, filtering out the image of the land portion, and improving the detection efficiency; secondly, Perform preliminary statistics on the graph, set appropriate global thresholds, perform preliminary screening on SAR image targets, and segment the image into several sub-image blocks. Finally, use CUDA technology to perform constant false alarm detection on the three distributed graphs to detect effective Ship target.
结合附图阅读本发明实施方式的详细描述后,本发明的其他特点和优点将变得更加清楚。Other features and advantages of the present invention will become more apparent from the detailed description of the embodiments.
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。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 embodiments or the description of the prior art will be briefly described below. Obviously, the drawings in the following description are only It is a certain embodiment of the present invention, and other drawings can be obtained from those skilled in the art without any creative work.
图1是本发明所提出的合成孔径雷达图像目标快速检测方法的一种实施例流程方框图。1 is a flow chart showing an embodiment of a method for quickly detecting a synthetic aperture radar image object according to the present invention.
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
The technical solutions in the embodiments of the present invention are clearly and completely described in the following with reference to the accompanying drawings in the embodiments of the present invention. It is obvious that the described embodiments are only a part of the embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.
实施例一,本实施例提出了一种合成孔径雷达图像目标快速检测方法,包括以下步骤:Embodiment 1 This embodiment provides a method for quickly detecting a target image of a synthetic aperture radar, including the following steps:
S1、海陆分离步骤,设置边界曲线,并以边界曲线为界进行海陆分离,得到仅海洋区域具有有效数据的海洋区域图像;S1, sea-land separation step, setting boundary curve, and separating sea and land by boundary curve, and obtaining ocean area image with effective data only in marine area;
一般陆地具有较强的散射,在SAR图像中表现为亮的区域,对舰船目标检测有较大影响。步骤S1通过将海陆分离,将除陆地区域剔除,减少陆地区域对目标检测的影响,同时减少计算量,有利于提高目标检测的速度和精度。Generally, land has strong scattering, and it is a bright region in SAR images, which has a great influence on ship target detection. Step S1 separates the land and sea, removes the land area, reduces the influence of the land area on the target detection, and reduces the calculation amount, which is beneficial to improve the speed and accuracy of the target detection.
S2、目标筛选步骤,包括:S2, target screening steps, including:
S21、设置灰度阈值T,将海洋区域图像中灰度值大于T的像素的索引值赋值为该像素的灰度值,否则赋值为0,并将所得到的所有索引值建立一索引矩阵;S21, setting a gray threshold T, assigning an index value of a pixel whose gray value is greater than T in the image of the ocean area to a gray value of the pixel, and otherwise assigning a value of 0, and establishing an index matrix for all the obtained index values;
S22、将所述索引矩阵中非0的区域设定为候选目标区域;S22. Set a non-zero region in the index matrix as a candidate target region.
S23、以所述候选目标区域的位置为界,将海洋区域图像分隔成若干子图像,每一个候选目标区域对应一个子图像;S23. The ocean area image is divided into several sub-images by using the position of the candidate target area, and each candidate target area corresponds to one sub-image;
由于图像分割是SAR图像解译应用的基础和前提,步骤S2基于全局阈值的图像分割,并将SAR图像分割成若干子图像,为舰船目标的识别做基础。Since image segmentation is the basis and premise of SAR image interpretation application, step S2 is based on global threshold image segmentation, and the SAR image is segmented into several sub-images to form the basis for the identification of ship targets.
S3、设置背景杂波统计模型,包括:S3. Set a background clutter statistical model, including:
S31、分别计算各子图像的背景变化指数BI;S31, respectively calculating a background change index BI of each sub-image;
S32、设定阈值TBI1和TBI2,其中TBI1<TBI2,根据背景变化指数BI将子图像划分为三类:S32. Set thresholds TBI1 and TBI2, where TBI1<TBI2, and divide the sub-image into three categories according to the background change index BI:
如果BI≤TBI1,为均匀杂波类;If BI≤TBI1, it is a uniform clutter class;
如果TBI1<BI≤TBI2,为一般不均匀杂波类;If TBI1 < BI ≤ TBI2, it is a general heterogeneous clutter class;
如果TBI2<BI,为极不均匀杂波类;If TBI2 < BI, it is a very uneven clutter class;
由于背景区的杂波统计模型是决定检测算法性能的关键因素。由于海面情况比较多变,导致杂波统计特性十分复杂。若统计模型不能很好地描述杂波特性,将会导致恒虚警检测器性能恶化。现有恒虚警目标检测算法一般采用全局建模,对所有区域使用同种背景杂波分布模型,导致使用的模型在不使用区域失配严重,使检测
性能明显下降。本实施例的检测方法,为提高检测性能,在深入分析基于不同统计分布模型的恒虚警检测基础上,充分考虑各个统计模型的优缺点,结合恒虚警检测算法,根据SAR子图像的均值和方差,将SAR子图像分为均匀背景杂波、一般不均匀背景杂波和极不均匀背景杂波三类。针对这三种不同类型,分别采用适合该类特性的恒虚警检测算法,提高检测精度。The clutter statistical model in the background area is a key factor in determining the performance of the detection algorithm. Due to the relatively variable sea surface conditions, the statistical characteristics of clutter are very complicated. If the statistical model does not describe the clutter characteristics well, it will cause the performance of the constant false alarm detector to deteriorate. The existing constant false alarm target detection algorithm generally adopts global modeling, and uses the same background clutter distribution model for all regions, resulting in the use of the model in the unused area mismatch, making detection
The performance is significantly reduced. In order to improve the detection performance, the detection method of the present embodiment fully considers the advantages and disadvantages of each statistical model based on the in-depth analysis of the constant false alarm detection based on different statistical distribution models, and combines the constant false alarm detection algorithm according to the mean value of the SAR sub-image. And variance, the SAR sub-image is divided into three types: uniform background clutter, general uneven background clutter and extremely uneven background clutter. For these three different types, the constant false alarm detection algorithm suitable for this kind of characteristics is adopted to improve the detection accuracy.
S4、在GPU平台下,GPU依次对所述三类像素单元根据阈值T1分别进行处理,获得目标区域,所述三类像素单元分别采用不同的处理算法计算阈值T1。S4. Under the GPU platform, the GPU sequentially processes the three types of pixel units according to the threshold T1 to obtain a target area, and the three types of pixel units respectively use different processing algorithms to calculate the threshold T1.
在基于图形处理器(GPU)构架下,采用统一计算设备构架(CUDA)技术,并根据GPU的特点对基于三种不同分布的算法实现进行优化,实现高效的恒虚警目标检测算法,相比CPU实现大大缩短了数据处理时间,能够满足SAR目标检测的实时性要求的需求。In the graphics processor (GPU) architecture, the Unified Computing Device Architecture (CUDA) technology is adopted, and the algorithm implementation based on three different distributions is optimized according to the characteristics of the GPU, and an efficient constant false alarm target detection algorithm is realized. The CPU implementation greatly shortens the data processing time and can meet the real-time requirements of SAR target detection.
作为一个优选的实施例,所述步骤S1中,所述边界曲线的设置方法为:As a preferred embodiment, in the step S1, the setting method of the boundary curve is:
S11、初始化边界曲线C,定义边界曲线C内区域的水平集函数Φ,设置窄带半径,以边界曲线C上的点为中心,窄带半径为半径,获得窄带区域;S11, initializing the boundary curve C, defining a horizontal set function Φ of the region in the boundary curve C, setting a narrow band radius, centering on a point on the boundary curve C, and taking a narrow band radius as a radius to obtain a narrow band region;
S12、计算边界曲线C的能量函数的最小值,采用海氏函数和狄利克冲击函数,得到偏微分方程的解为:S12. Calculate the minimum value of the energy function of the boundary curve C, and use the Hai's function and the Dirich impact function to obtain the solution of the partial differential equation as:
其中,Φ0(x,y)为初始化边界曲线C的水平集函数;H(Φ)为海氏函数,I(x,y)为窄带区域内的图像,μ,ν,λ1,λ2分别表示能量权重;Where Φ 0 (x, y) is the level set function of the initial boundary curve C; H(Φ) is the Hai's function, I(x, y) is the image in the narrow-band region, μ, ν, λ 1 , λ 2 Representing energy weights separately;
S13、将窄带区域内所有点代入初始化边界曲线C的水平集函数Φ0(x,y)=0,演化成新的边界曲线,并计新的边界曲线的水平集函数为Φ1;
S13. Substituting all points in the narrowband region into the level set function Φ 0 (x, y)=0 of the initialization boundary curve C, and evolving into a new boundary curve, and calculating a level set function of the new boundary curve is Φ 1 ;
S14、连续n次演化边界曲线,直到遍历完图像上所有点,获取陆地和海域的分界线
S14. The boundary curve is evolved n times in succession until all points on the image are traversed, and the boundary between the land and the sea is obtained.
S15、以陆地和海域的分界线为界进行海陆分离,剔除陆地数据,得到仅海洋区域具有有效数据的海洋区域图像。S15, the boundary between land and sea For sea and land separation for the boundary, the land data is eliminated, and the ocean area image with valid data only in the ocean area is obtained.
本实施例的检测方法在分析水平集方法中的窄带解法优点和Mumford-Shah模型的基础之上,通过特定条件下初始边界参数,简化初始演化曲线,从而将水平集方法中的窄带解法和Mumford-Shah模型有效地结合起来,快速得到陆海区域分离效果。The detection method of the present embodiment simplifies the initial evolution curve by using the initial boundary parameters under specific conditions on the basis of the advantages of the narrow-band solution in the analysis level set method and the Mumford-Shah model, thereby narrowing the solution and Mumford in the level set method. The -Shah model is effectively combined to quickly obtain the separation effect of the land and sea areas.
进一步的,所述步骤S11中,根据解短时距方程|▽T|F=1初始化边界曲线,其中T(x,y,z)为给定点(x,y,z)到边界曲线的收缩时间,F为速度参数,由于F与图像的特性是相互独立的,在初始曲线轮廓时,设定速度参数F为1,将距离边界曲线C等于或小于1的点形成待检区域,所述待检区域的边界即为边界曲线C。Further, in the step S11, the boundary curve is initialized according to the solution short time interval equation |▽T|F=1, where T(x, y, z) is the contraction of the given point (x, y, z) to the boundary curve. Time, F is the speed parameter. Since the characteristics of F and the image are independent of each other, in the initial curve contour, the set speed parameter F is set to 1, and the point where the distance boundary curve C is equal to or smaller than 1 forms a to-be-detected area. The boundary of the area to be inspected is the boundary curve C.
所述步骤S12中采用欧拉-拉格朗日方法求解边界曲线C的能量函数的最小值,
In the step S12, the Euler-Lagrangian method is used to solve the minimum value of the energy function of the boundary curve C,
其中L(C)为闭合曲线C的长度,Sb(C)为曲线C内部区域面积。Where L(C) is the length of the closed curve C and S b (C) is the area of the inner area of the curve C.
进一步的,所述步骤S12中,由偏微分方程的解可得到的迭代公式为:Further, in the step S12, the solution of the partial differential equation can be obtained. The iteration formula is:
其中,among them,
水平集函数在(x,y)的曲率,为前向差分运算。
The set of functions of the level set function at (x, y), For forward differential operation.
进一步的,所述步骤S31中,子图像的背景变化指数BI的计算方法为:Further, in the step S31, the calculation method of the background change index BI of the sub-image is:
其中,m为每个子图像所包括的像素数。由于方差是衡量背景变化程度的度量,但在SAR图像中,由于存在乘性噪声,单以方差不能准确表示背景变化程度,因此,本实施例的检测方法通过引入背景变化指数BI,设每个SAR子图像有m个像素数,分别计算BI。Where m is the number of pixels included in each sub-image. Since the variance is a measure of the degree of background change, in the SAR image, because of the multiplicative noise, the variance can not accurately represent the degree of background change. Therefore, the detection method of this embodiment introduces each of the background change indices BI. The SAR sub-image has m pixels and calculates BI separately.
所述步骤S21中,所述灰度阈值T的计算方法为:In the step S21, the calculation method of the gray threshold T is:
S211、将海洋区域图像的总灰度划分为L级,海洋区域图像的总像素个数为n,第k级灰度的像素个数为nk,则第k级灰度的归一化直方图为:p(k)=nk/n(k=0,1,2……,L-1);S211. The total gray level of the image of the ocean area is divided into L levels, the total number of pixels of the image of the ocean area is n, and the number of pixels of the kth gray level is n k , and the normalized square of the kth gray level is obtained. The picture is: p(k)=n k /n(k=0,1,2...,L-1);
所述步骤S4中,在GPU平台下,GPU依次对所述三类像素单元分别进行处理的方法为:In the step S4, under the GPU platform, the GPU sequentially processes the three types of pixel units separately:
S41、初始化GPU:由CPU启动CUDA,设置GPU相关参数,分配数据内存空间,并初始化输入子图像;S41. Initializing the GPU: starting CUDA by the CPU, setting GPU related parameters, allocating data memory space, and initializing the input sub-image;
S42、将子图像读入GPU显存:在CUDA框架下,分配显存,并将子图像从内存读入到GPU显存中;S42, reading the sub-image into the GPU memory: in the CUDA framework, allocating the memory, and reading the sub-image from the memory into the GPU memory;
S43、GPU开启多线程,运行内核函数:CPU首先将第一类的阈值算法载入GPU,作为多线程的内核函数,计算出阈值,并以该阈值作为T1,对所有子图像中属于第一类的子图像进行目标检测,将检测结果返回显存并拷贝到内存;其次,CPU将第二类的阈值算法载入GPU,计算出阈值,并以该阈值作为T1,作为多线程的内核函数,对所有子图像中属于第二类的子图像进行目标检测,将检测结果返回显存并拷贝到内存;再次,CPU将第三类的阈值算法载入GPU,作为多线程的内核函数,计算出阈值,并以该阈值作为T1,对所有子图像中属于第二类的子图像进行目标检测,将检测结果返回显存并拷贝到内存。S43. The GPU starts multi-threading and runs the kernel function: the CPU first loads the threshold algorithm of the first type into the GPU, and uses the kernel function of the multi-thread to calculate the threshold, and uses the threshold as the T1, and belongs to the first in all the sub-images. The sub-image of the class performs target detection, and returns the detection result to the video memory and copies it to the memory. Secondly, the CPU loads the second type threshold algorithm into the GPU, calculates the threshold, and uses the threshold as T1 as a multi-threaded kernel function. Perform target detection on the sub-images belonging to the second category in all sub-images, return the detection results to the video memory and copy them to the memory; again, the CPU loads the third-level threshold algorithm into the GPU as a multi-threaded kernel function to calculate the threshold. And using the threshold as T1, performing target detection on the sub-images belonging to the second category in all the sub-images, returning the detection result to the video memory and copying it to the memory.
S44、释放GPU资源:当程序执行完毕后,释放GPU显存,回收GPU资源,退出程序。
S44. Release the GPU resource: when the program is executed, release the GPU memory, recycle the GPU resource, and exit the program.
在本实施例中,所述第一类的子图像为均匀杂波类,采用高斯分布统计模型计算阈值;In this embodiment, the sub-images of the first type are uniform clutter types, and a threshold is calculated by using a Gaussian distribution statistical model;
所述第二类的子图像像为一般不均匀杂波类,采用韦布尔分布统计模型计算阈值;The sub-image images of the second type are generally non-uniform clutter, and the threshold is calculated by using a Weibull distribution statistical model;
所述第三类的子图像为极不均匀杂波类,采用G0分布模型计算阈值。The sub-images of the third type are extremely heterogeneous clutter types, and the threshold is calculated using a G 0 distribution model.
具体的,针对均匀杂波背景SAR图像,采用基于高斯分布的恒虚警检测算法,根据EM算法,求解混合高斯模型的均值μm:Specifically, for the uniform clutter background SAR image, the constant false alarm detection algorithm based on Gaussian distribution is used to solve the mean μ m of the mixed Gaussian model according to the EM algorithm:
将μm带入如下公式计算检测阈值:The μ m is taken into the following formula to calculate the detection threshold:
针对一般不均匀杂波背景SAR图像,采用基于韦布尔分布的恒虚警检测算法,假设相互独立的N个参考单元的联合概率密度为For the general inhomogeneous clutter background SAR image, the constant false alarm detection algorithm based on Weibull distribution is used, and the joint probability density of N independent reference units is assumed to be
其中B为尺度参数,C为形状参数。f(x)取对数后,对尺度参数和形状参数分别求导,可得到:Where B is the scale parameter and C is the shape parameter. After f(x) takes the logarithm, the scale parameter and the shape parameter are separately derived to obtain:
将B、C带入虚警概率公式,从而得到检测阈值:Bring B and C into the false alarm probability formula to get the detection threshold:
TI=B(-lnPfa)1/C
T I = B(-lnP fa ) 1/C
针对极不均匀杂波背景SAR图像,采用G0分布的恒虚警检测算法,利用SKS估计方法,对G0分布的参数进行估计,表达式为:Clutter for SAR images is uneven, CFAR detection algorithm using G 0 distribution, using SKS estimation method, the distribution of the parameter estimates by G 0, the expression is:
其中,n为等效视数,α为形状参数,γ为尺度参数,Ψ(·)为digamma函数,为样本对数累计量。由上述表达式可以计算出n,α,γ,得到概率密度表达式。Where n is the equivalent visual number, α is the shape parameter, γ is the scale parameter, and Ψ(·) is the digamma function. The cumulative amount of the sample logarithm. From the above expression, n, α, γ can be calculated to obtain a probability density expression.
给定虚警率Pfa,可由公式求解检测阈值TI。对于G0分布,上述积分公式无法得到解析表达式。为此,本发明采用如下方法求解:Given the false alarm rate P fa , can be formulated Solve the detection threshold T I . For the G 0 distribution, the above integral formula cannot obtain an analytical expression. To this end, the present invention solves by the following method:
(a)令初始化最小值m=min(I),最大值n=max(I),循环变量n=0,最大循环次数N,以及精度ξ;(a) order Initialize the minimum value m=min(I), the maximum value n=max(I), the loop variable n=0, the maximum number of loops N, and the precision ξ;
(b)若|F(ζ)-(1-Pfa)|≤ξ,则执行(d);否则,执行(c);(b) If |F(ζ)-(1-P fa )|≤ξ, execute (d); otherwise, execute (c);
(c)如果n<N,执行(d),否则,当F(ζ)<1-Pfa时,m=ζ;当F(ζ)>1-Pfa时,n=ζ;然后执行(b);(c) If n < N, perform (d), otherwise, when F (ζ) < 1-P fa , m = ζ; when F (ζ) > 1-P fa , n = ζ; then execute ( b);
(d)TI=ζ,退出循环。(d) T I = ζ, exit the loop.
当然,上述说明并非是对本发明的限制,本发明也并不仅限于上述举例,本技术领域的普通技术人员在本发明的实质范围内所做出的变化、改型、添加或替换,也应属于本发明的保护范围。
The above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and variations, modifications, additions or substitutions made by those skilled in the art within the scope of the present invention are also The scope of protection of the present invention.
Claims (9)
- 一种合成孔径雷达图像目标快速检测方法,其特征在于,包括以下步骤:A method for rapidly detecting a target image of a synthetic aperture radar, characterized in that it comprises the following steps:(1)、海陆分离步骤,演化边界曲线,并以边界曲线为界进行海陆分离,得到具有有效目标的海洋区域图像;(1) The sea-land separation step, evolving the boundary curve, and separating the sea and land with the boundary curve as the boundary, and obtaining the image of the marine area with effective targets;(2)、目标筛选步骤,包括:(2) Target screening steps, including:(21)、设置灰度阈值T,将所述海洋区域图像中灰度值大于T的像素的索引值赋值为该像素的灰度值,否则赋值为0,并将所得到的所有索引值建立一索引矩阵;(21) setting a gray threshold T, assigning an index value of a pixel whose gray value is greater than T in the image of the ocean area to a gray value of the pixel, otherwise assigning a value of 0, and establishing all index values obtained An index matrix;(22)、将所述索引矩阵中非0的区域设定为候选目标区域;(22) setting a non-zero region in the index matrix as a candidate target region;(23)、以所述候选目标区域的位置为界,将所述海洋区域图像分隔成若干子图像,每一个候选目标区域对应一个子图像;(23) dividing the image of the ocean area into a plurality of sub-images by using a position of the candidate target area, each candidate target area corresponding to one sub-image;(3)、设置背景杂波统计模型,包括:(3) Set the background clutter statistical model, including:(31)、分别计算各子图像的背景变化指数BI;(31), respectively calculating the background change index BI of each sub-image;(32)、设定阈值TBI1和TBI2,其中TBI1<TBI2,根据背景变化指数BI将子图像划分为三类:(32) Setting thresholds TBI1 and TBI2, where TBI1 < TBI2, the sub-images are divided into three categories according to the background change index BI:如果BI≤TBI1,为均匀背景杂波类;If BI≤TBI1, it is a uniform background clutter class;如果TBI1<BI≤TBI2,为一般不均匀背景杂波类;If TBI1 < BI ≤ TBI2, it is a general uneven background clutter class;如果TBI2<BI,为极不均匀背景杂波类;If TBI2<BI, it is a very uneven background clutter class;(4)、在GPU平台下,GPU依次对所述三类子图像根据其对应恒虚警检测阈值T1分别进行处理,获得目标区域,所述三类像素单元分别采用不同的处理算法计算阈值T1。(4) Under the GPU platform, the GPU sequentially processes the three types of sub-images according to their corresponding constant false alarm detection thresholds T1 to obtain a target area, and the three types of pixel units respectively use different processing algorithms to calculate a threshold T1. .
- 根据权利要求1所述的合成孔径雷达图像目标快速检测方法,其特征在于,所述步骤(1)中,所述边界曲线的设置方法为:The method for rapidly detecting a synthetic aperture radar image object according to claim 1, wherein in the step (1), the setting method of the boundary curve is:(11)、初始化边界曲线C,定义边界曲线C内区域的水平集函数Φ,设置窄带半径,以边界曲线C上的点为中心,窄带半径为半径,获得窄带区域; (11) Initialize the boundary curve C, define the horizontal set function Φ of the region in the boundary curve C, set the narrow band radius, take the point on the boundary curve C as the center, and the narrow band radius as the radius to obtain the narrow band region;(12)、计算边界曲线C的能量函数的最小值,采用海氏函数和狄利克冲击函数,得到偏微分方程的解为:(12) Calculate the minimum value of the energy function of the boundary curve C, and use the Hai's function and the Dirich impact function to obtain the solution of the partial differential equation as:其中,Φ0(x,y)为初始化边界曲线C的水平集函数;c1和c2分别表示边界曲线内外两个区域的灰度平均值,H(z)为海氏函数,I(x,y)为窄带区域内的图像,μ,ν,λ1,λ2分别表示能量权重;Where Φ 0 (x, y) is the level set function of the initialization boundary curve C; c 1 and c 2 respectively represent the gray average values of the two regions inside and outside the boundary curve, H(z) is the Hai's function, I(x , y) is an image in a narrow band region, and μ, ν, λ 1 , λ 2 respectively represent energy weights;(13)、将窄带区域内所有点代入初始化边界曲线C的水平集函数Φ0(x,y)=0,演化成新的边界曲线,并计新的边界曲线的水平集函数为Φ1;(13) Substituting all the points in the narrowband region into the level set function Φ 0 (x, y) = 0 of the initialization boundary curve C, and evolving into a new boundary curve, and calculating the level set function of the new boundary curve as Φ 1 ;(14)、连续n次演化边界曲线,直到遍历完图像上所有点,获取陆地和海域的分界线 (14), the boundary curve is evolved n times in succession until all points on the image are traversed, and the boundary between land and sea is obtained.
- 根据权利要求2所述的合成孔径雷达图像目标快速检测方法,其特征在于,所述步骤(11)中,根据解短时距方程|▽T|F=1初始化边界曲线,其中T(x,y,z)为给定点(x,y,z)到边界曲线的收缩时间,F为速度参数,在初始曲线轮廓时,设定速度参数F为1,将距离边界曲线C等于或小于1的点形成待检区域,所述待检区域的边界即为边界曲线C。The method for rapidly detecting a synthetic aperture radar image object according to claim 2, wherein in the step (11), the boundary curve is initialized according to the solution short time interval equation |▽T|F=1, wherein T(x, y, z) is the contraction time of the given point (x, y, z) to the boundary curve, F is the speed parameter, in the initial curve contour, the set speed parameter F is 1, and the distance boundary curve C is equal to or less than 1. The dots form a region to be inspected, and the boundary of the region to be inspected is the boundary curve C.
- 根据权利要求3所述的合成孔径雷达图像目标快速检测方法,其特征在于,所述步骤(12)中采用欧拉-拉格朗日方法求解边界曲线C的能量函数的最小值: The method for rapidly detecting a synthetic aperture radar image object according to claim 3, wherein in the step (12), the Euler-Lagrangian method is used to solve the minimum value of the energy function of the boundary curve C:其中L(C)为闭合曲线C的长度,Sb(C)为曲线C内部区域面积。Where L(C) is the length of the closed curve C and S b (C) is the area of the inner area of the curve C.
- 根据权利要求4所述的合成孔径雷达图像目标快速检测方法,其特征在于,所述步骤(12)中,由偏微分方程的解可得到的迭代公式为:The method for rapidly detecting a synthetic aperture radar image object according to claim 4, wherein in the step (12), the solution of the partial differential equation is obtained The iteration formula is:其中,among them,
- 根据权利要求1所述的合成孔径雷达图像目标快速检测方法,其特征在于,所述步骤(31)中,子图像的背景变化指数BI的计算方法为:The method for rapidly detecting a synthetic aperture radar image object according to claim 1, wherein in the step (31), the calculation method of the background change index BI of the sub-image is:其中,m为每个子图像所包括的像素数。Where m is the number of pixels included in each sub-image.
- 根据权利要求1-6任一项所述的合成孔径雷达图像目标快速检测方法,其特征在于,所述步骤(21)中,所述灰度阈值T的计算方法为:The method for quickly detecting a synthetic aperture radar image object according to any one of claims 1 to 6, wherein in the step (21), the calculation method of the grayscale threshold T is:(211)、将海洋区域图像的总灰度划分为L级,海洋区域图像的总像素个数为n,第k级灰度的像素个数为nk,则第k级灰度的归一化直方图为:p(k)=nk/n(k=0,1,2……,L-1);(211), dividing the total gray level of the image of the ocean area into L levels, the total number of pixels of the image of the ocean area is n, and the number of pixels of the k-th gray level is n k , then the normalization of the k-th gray level The histogram is: p(k)=n k /n(k=0,1,2...,L-1);
- 根据权利要求1-6任一项所述的合成孔径雷达图像目标快速检测方法,其特征在于,所述步骤(4)中,在GPU平台下,GPU依次对所述三类子图像分别进行处理的方法为: The method for quickly detecting a synthetic aperture radar image object according to any one of claims 1 to 6, wherein in the step (4), under the GPU platform, the GPU sequentially processes the three types of sub-images separately. The method is:(41)初始化GPU:由CPU启动CUDA,设置GPU相关参数,分配数据内存空间,并初始化输入子图像;(41) Initialize the GPU: start CUDA by the CPU, set GPU related parameters, allocate data memory space, and initialize the input sub-image;(42)将子图像读入GPU显存:在CUDA框架下,分配显存,并将子图像从内存读入到GPU显存中;(42) Reading the sub-image into the GPU memory: in the CUDA framework, allocating the memory and reading the sub-image from the memory into the GPU memory;(43)GPU开启多线程,运行内核函数:CPU首先将第一类的阈值算法载入GPU,作为多线程的内核函数,计算出阈值,并以该阈值作为T1,对所有子图像中属于第一类的子图像进行目标检测,将检测结果返回显存并拷贝到内存;其次,CPU将第二类的阈值算法载入GPU,计算出阈值,并以该阈值作为T1,作为多线程的内核函数,对所有子图像中属于第二类的子图像进行目标检测,将检测结果返回显存并拷贝到内存;再次,CPU将第三类的阈值算法载入GPU,作为多线程的内核函数,计算出阈值,并以该阈值作为T1,对所有子图像中属于第二类的子图像进行目标检测,将检测结果返回显存并拷贝到内存。(43) The GPU starts multi-threading and runs the kernel function: the CPU first loads the first type of threshold algorithm into the GPU, and as a multi-threaded kernel function, calculates a threshold, and uses the threshold as T1, which belongs to the first sub-image. A sub-image of a type is used for target detection, and the detection result is returned to the memory and copied to the memory. Secondly, the CPU loads the second type of threshold algorithm into the GPU, calculates the threshold, and uses the threshold as T1 as a multi-threaded kernel function. Target detection is performed on the sub-images belonging to the second category in all the sub-images, and the detection result is returned to the video memory and copied to the memory; again, the CPU loads the third-level threshold algorithm into the GPU as a multi-threaded kernel function, and calculates The threshold value is used as the T1, and the sub-images belonging to the second category in all the sub-images are subjected to target detection, and the detection result is returned to the video memory and copied to the memory.(44)释放GPU资源:当程序执行完毕后,释放GPU显存,回收GPU资源,退出程序。(44) Release GPU resources: When the program is executed, release the GPU memory, recycle the GPU resources, and exit the program.
- 根据权利要求8所述的合成孔径雷达图像目标快速检测方法,其特征在于,所述第一类的子图像为均匀背景杂波类,采用高斯分布统计模型计算阈值;The method for rapidly detecting a synthetic aperture radar image object according to claim 8, wherein the first type of sub-images are uniform background clutter, and a Gaussian distribution statistical model is used to calculate a threshold;所述第二类的子图像像为一般不均匀背景杂波类,采用韦布尔分布统计模型计算阈值;The sub-image images of the second type are generally uneven background clutter, and the threshold is calculated by using a Weibull distribution statistical model;所述第三类的子图像为极不均匀背景杂波类,采用G0分布模型计算阈值。 The third type of sub-images are extremely uneven background clutter, and the G 0 distribution model is used to calculate the threshold.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201480020648.3A CN106170819B (en) | 2014-12-26 | 2014-12-26 | A kind of diameter radar image Ship Target rapid detection method |
PCT/CN2014/095202 WO2016101279A1 (en) | 2014-12-26 | 2014-12-26 | Quick detecting method for synthetic aperture radar image of ship target |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2014/095202 WO2016101279A1 (en) | 2014-12-26 | 2014-12-26 | Quick detecting method for synthetic aperture radar image of ship target |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016101279A1 true WO2016101279A1 (en) | 2016-06-30 |
Family
ID=56149006
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2014/095202 WO2016101279A1 (en) | 2014-12-26 | 2014-12-26 | Quick detecting method for synthetic aperture radar image of ship target |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106170819B (en) |
WO (1) | WO2016101279A1 (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107301398A (en) * | 2017-06-23 | 2017-10-27 | 电子科技大学 | A kind of identification method of image target of synthetic aperture radar realized based on GPU |
CN109635730A (en) * | 2018-12-12 | 2019-04-16 | 中船(浙江)海洋科技有限公司 | SAR image Ship Detection based on abnormality detection and the double-deck Filtering system |
CN109801208A (en) * | 2019-01-24 | 2019-05-24 | 西安电子科技大学 | SAR image change detection based on the optimization of more GPU tasks |
CN109829361A (en) * | 2018-12-17 | 2019-05-31 | 深圳先进技术研究院 | The processing method of image and the robot, device of application this method |
CN109886218A (en) * | 2019-02-26 | 2019-06-14 | 西安电子科技大学 | SAR image Ship Target Detection method based on super-pixel statistics diversity |
CN110363779A (en) * | 2019-07-18 | 2019-10-22 | 东北大学 | A kind of Digital Image Segmentation and parallel method |
CN110378186A (en) * | 2019-03-22 | 2019-10-25 | 北京理工雷科电子信息技术有限公司 | The method that SAR remote sensing images Ship Target false-alarm is rejected |
CN110390667A (en) * | 2019-06-18 | 2019-10-29 | 平安科技(深圳)有限公司 | Lesion extracting method, device, equipment and storage medium based on eyeground OCT image |
CN110415254A (en) * | 2019-06-06 | 2019-11-05 | 西安电子科技大学 | A kind of level set image segmentation method based on Oscillatory Coupling network, computer |
CN110851187A (en) * | 2019-11-19 | 2020-02-28 | 北京百度网讯科技有限公司 | Video memory processing method, device, equipment and medium |
CN110889843A (en) * | 2019-11-29 | 2020-03-17 | 西安电子科技大学 | SAR image ship target detection method based on maximum stable extremal region |
CN111008585A (en) * | 2019-11-29 | 2020-04-14 | 西安电子科技大学 | Ship target detection method based on self-adaptive layered high-resolution SAR image |
CN111028256A (en) * | 2019-10-14 | 2020-04-17 | 杭州电子科技大学 | SAR image target detection method based on improved active contour model |
CN111127506A (en) * | 2019-11-19 | 2020-05-08 | 北京空间飞行器总体设计部 | Sequence image-based marine moving target comprehensive detection method |
CN111562976A (en) * | 2019-02-13 | 2020-08-21 | 同济大学 | GPU (graphics processing unit) acceleration method and system for radar imaging of electrically large-sized target |
CN111582198A (en) * | 2020-05-12 | 2020-08-25 | 中国电子科技集团公司第二十八研究所 | Automatic sea-land segmentation method for remote sensing image |
CN111709957A (en) * | 2020-06-22 | 2020-09-25 | 河南理工大学 | Medical image segmentation method based on two-dimensional maximum entropy threshold C-V model |
CN112560897A (en) * | 2020-11-24 | 2021-03-26 | 西安电子科技大学 | Radar ship classification capability evaluation method based on captain statistical model |
CN112698290A (en) * | 2020-12-10 | 2021-04-23 | 南京长峰航天电子科技有限公司 | Large-scene SAR echo simulation parallel processing method and system |
CN112907567A (en) * | 2021-03-19 | 2021-06-04 | 甘肃省地震局(中国地震局兰州地震研究所) | SAR image ordered artificial structure extraction method based on spatial reasoning method |
CN113673385A (en) * | 2021-08-06 | 2021-11-19 | 南京理工大学 | Sea surface ship detection method based on infrared image |
CN113807195A (en) * | 2021-08-24 | 2021-12-17 | 杭州电子科技大学 | Sea and land clutter classification method based on degree matrix distance discrimination |
US11262447B2 (en) * | 2017-02-24 | 2022-03-01 | Japan Aerospace Exploration Agency | Flying body and program |
CN114998720A (en) * | 2022-05-04 | 2022-09-02 | 西北工业大学 | Bridge target detection method based on Markov tree water area network construction |
CN115222758A (en) * | 2022-09-21 | 2022-10-21 | 北京九章星图科技有限公司 | Low-resolution wide-area sequence remote sensing image ship moving target real-time detection algorithm |
CN116299465A (en) * | 2023-05-18 | 2023-06-23 | 西安电子科技大学 | Bistatic SAR backward projection imaging method based on subspace time-frequency mapping |
CN116484954A (en) * | 2023-03-20 | 2023-07-25 | 中国人民解放军军事科学院战略评估咨询中心 | Artificial intelligence offshore voltaic model generation method, computer program and storage medium |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN109471101B (en) * | 2018-10-19 | 2021-05-04 | 湖北航天技术研究院总体设计所 | Missile-borne SAR image correction method |
CN113705505A (en) * | 2021-09-02 | 2021-11-26 | 浙江索思科技有限公司 | Marine fishery-oriented ship target detection method and system |
CN114463224B (en) * | 2022-04-14 | 2022-06-24 | 广东海洋大学 | Ocean target image restoration and identification method and system based on SAR technology |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000231571A (en) * | 1999-02-10 | 2000-08-22 | Mitsubishi Electric Corp | Isar image retrieving device |
WO2007133085A1 (en) * | 2006-05-15 | 2007-11-22 | Telefonaktiebolaget Lm Ericsson (Publ) | A method and system for automatic classification of objects |
JP4236767B2 (en) * | 1999-06-25 | 2009-03-11 | 三菱スペース・ソフトウエア株式会社 | Method for detecting movement information of moving object based on satellite SAR image |
CN102938150A (en) * | 2012-11-20 | 2013-02-20 | 西安电子科技大学 | Synthetic aperture radar (SAR) image ship detection method based on self-adaptation sea clutter statistics |
CN102968798A (en) * | 2012-12-12 | 2013-03-13 | 北京航空航天大学 | SAR (Synthetic Aperture Radar) image sea-land segmentation method based on wavelet transform and OTSU threshold |
CN104036239A (en) * | 2014-05-29 | 2014-09-10 | 西安电子科技大学 | Fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering |
CN104240257A (en) * | 2014-09-30 | 2014-12-24 | 中国人民解放军国防科学技术大学 | SAR (synthetic aperture radar) image naval ship target identification method based on change detection technology |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102968799B (en) * | 2012-12-12 | 2014-12-10 | 北京航空航天大学 | Integral image-based quick ACCA-CFAR SAR (Automatic Censored Cell Averaging-Constant False Alarm Rate Synthetic Aperture Radar) image target detection method |
-
2014
- 2014-12-26 WO PCT/CN2014/095202 patent/WO2016101279A1/en active Application Filing
- 2014-12-26 CN CN201480020648.3A patent/CN106170819B/en not_active Expired - Fee Related
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000231571A (en) * | 1999-02-10 | 2000-08-22 | Mitsubishi Electric Corp | Isar image retrieving device |
JP4236767B2 (en) * | 1999-06-25 | 2009-03-11 | 三菱スペース・ソフトウエア株式会社 | Method for detecting movement information of moving object based on satellite SAR image |
WO2007133085A1 (en) * | 2006-05-15 | 2007-11-22 | Telefonaktiebolaget Lm Ericsson (Publ) | A method and system for automatic classification of objects |
CN102938150A (en) * | 2012-11-20 | 2013-02-20 | 西安电子科技大学 | Synthetic aperture radar (SAR) image ship detection method based on self-adaptation sea clutter statistics |
CN102968798A (en) * | 2012-12-12 | 2013-03-13 | 北京航空航天大学 | SAR (Synthetic Aperture Radar) image sea-land segmentation method based on wavelet transform and OTSU threshold |
CN104036239A (en) * | 2014-05-29 | 2014-09-10 | 西安电子科技大学 | Fast high-resolution SAR (synthetic aperture radar) image ship detection method based on feature fusion and clustering |
CN104240257A (en) * | 2014-09-30 | 2014-12-24 | 中国人民解放军国防科学技术大学 | SAR (synthetic aperture radar) image naval ship target identification method based on change detection technology |
Non-Patent Citations (2)
Title |
---|
CHEN, DEYUAN ET AL.: "SAR Image Ehancement Using Multiscale Products for Targets Detection", JOURNAL OF REMOTE SENSING, vol. 11, no. 2, 31 March 2007 (2007-03-31), pages 185 - 192, ISSN: 1007-4619 * |
JIN, YAQIU: "Microwave Remote Sensing Technology for Monitoring Targets in Land-Oceanic Environment", REMOTE SENSING TECHNOLOGY AND APPLICATION, vol. 20, no. 1, 28 February 2005 (2005-02-28), ISSN: 1004-0323 * |
Cited By (45)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11262447B2 (en) * | 2017-02-24 | 2022-03-01 | Japan Aerospace Exploration Agency | Flying body and program |
CN107301398A (en) * | 2017-06-23 | 2017-10-27 | 电子科技大学 | A kind of identification method of image target of synthetic aperture radar realized based on GPU |
CN107301398B (en) * | 2017-06-23 | 2019-04-30 | 电子科技大学 | A kind of identification method of image target of synthetic aperture radar realized based on GPU |
CN109635730A (en) * | 2018-12-12 | 2019-04-16 | 中船(浙江)海洋科技有限公司 | SAR image Ship Detection based on abnormality detection and the double-deck Filtering system |
CN109829361A (en) * | 2018-12-17 | 2019-05-31 | 深圳先进技术研究院 | The processing method of image and the robot, device of application this method |
CN109829361B (en) * | 2018-12-17 | 2023-03-31 | 深圳先进技术研究院 | Image processing method, robot and device applying same |
CN109801208A (en) * | 2019-01-24 | 2019-05-24 | 西安电子科技大学 | SAR image change detection based on the optimization of more GPU tasks |
CN109801208B (en) * | 2019-01-24 | 2023-03-24 | 西安电子科技大学 | SAR image change detection method based on multi-GPU task optimization |
CN111562976B (en) * | 2019-02-13 | 2023-04-18 | 同济大学 | GPU (graphics processing unit) acceleration method and system for radar imaging of electrically large target |
CN111562976A (en) * | 2019-02-13 | 2020-08-21 | 同济大学 | GPU (graphics processing unit) acceleration method and system for radar imaging of electrically large-sized target |
CN109886218A (en) * | 2019-02-26 | 2019-06-14 | 西安电子科技大学 | SAR image Ship Target Detection method based on super-pixel statistics diversity |
CN109886218B (en) * | 2019-02-26 | 2022-12-23 | 西安电子科技大学 | SAR image ship target detection method based on superpixel statistic dissimilarity |
CN110378186A (en) * | 2019-03-22 | 2019-10-25 | 北京理工雷科电子信息技术有限公司 | The method that SAR remote sensing images Ship Target false-alarm is rejected |
CN110378186B (en) * | 2019-03-22 | 2021-09-24 | 北京理工雷科电子信息技术有限公司 | SAR remote sensing image ship target false alarm rejection method |
CN110415254A (en) * | 2019-06-06 | 2019-11-05 | 西安电子科技大学 | A kind of level set image segmentation method based on Oscillatory Coupling network, computer |
CN110415254B (en) * | 2019-06-06 | 2023-01-03 | 西安电子科技大学 | Level set image segmentation method based on oscillation coupling network and computer |
CN110390667B (en) * | 2019-06-18 | 2023-10-20 | 平安科技(深圳)有限公司 | Focus extraction method, device, equipment and storage medium based on fundus OCT image |
CN110390667A (en) * | 2019-06-18 | 2019-10-29 | 平安科技(深圳)有限公司 | Lesion extracting method, device, equipment and storage medium based on eyeground OCT image |
CN110363779A (en) * | 2019-07-18 | 2019-10-22 | 东北大学 | A kind of Digital Image Segmentation and parallel method |
CN110363779B (en) * | 2019-07-18 | 2022-11-25 | 东北大学 | Digital image segmentation and parallelization method |
CN111028256B (en) * | 2019-10-14 | 2023-04-07 | 杭州电子科技大学 | SAR image target detection method based on improved active contour model |
CN111028256A (en) * | 2019-10-14 | 2020-04-17 | 杭州电子科技大学 | SAR image target detection method based on improved active contour model |
CN111127506A (en) * | 2019-11-19 | 2020-05-08 | 北京空间飞行器总体设计部 | Sequence image-based marine moving target comprehensive detection method |
CN110851187A (en) * | 2019-11-19 | 2020-02-28 | 北京百度网讯科技有限公司 | Video memory processing method, device, equipment and medium |
CN110889843A (en) * | 2019-11-29 | 2020-03-17 | 西安电子科技大学 | SAR image ship target detection method based on maximum stable extremal region |
CN111008585B (en) * | 2019-11-29 | 2023-04-07 | 西安电子科技大学 | Ship target detection method based on self-adaptive layered high-resolution SAR image |
CN111008585A (en) * | 2019-11-29 | 2020-04-14 | 西安电子科技大学 | Ship target detection method based on self-adaptive layered high-resolution SAR image |
CN110889843B (en) * | 2019-11-29 | 2023-04-18 | 西安电子科技大学 | SAR image ship target detection method based on maximum stable extremal region |
CN111582198B (en) * | 2020-05-12 | 2022-10-04 | 中国电子科技集团公司第二十八研究所 | Automatic sea-land segmentation method for remote sensing image |
CN111582198A (en) * | 2020-05-12 | 2020-08-25 | 中国电子科技集团公司第二十八研究所 | Automatic sea-land segmentation method for remote sensing image |
CN111709957A (en) * | 2020-06-22 | 2020-09-25 | 河南理工大学 | Medical image segmentation method based on two-dimensional maximum entropy threshold C-V model |
CN112560897B (en) * | 2020-11-24 | 2024-02-09 | 西安电子科技大学 | Radar ship classification capability evaluation method based on captain statistical model |
CN112560897A (en) * | 2020-11-24 | 2021-03-26 | 西安电子科技大学 | Radar ship classification capability evaluation method based on captain statistical model |
CN112698290A (en) * | 2020-12-10 | 2021-04-23 | 南京长峰航天电子科技有限公司 | Large-scene SAR echo simulation parallel processing method and system |
CN112907567B (en) * | 2021-03-19 | 2022-05-27 | 甘肃省地震局(中国地震局兰州地震研究所) | SAR image ordered artificial structure extraction method based on spatial reasoning method |
CN112907567A (en) * | 2021-03-19 | 2021-06-04 | 甘肃省地震局(中国地震局兰州地震研究所) | SAR image ordered artificial structure extraction method based on spatial reasoning method |
CN113673385A (en) * | 2021-08-06 | 2021-11-19 | 南京理工大学 | Sea surface ship detection method based on infrared image |
CN113807195A (en) * | 2021-08-24 | 2021-12-17 | 杭州电子科技大学 | Sea and land clutter classification method based on degree matrix distance discrimination |
CN114998720A (en) * | 2022-05-04 | 2022-09-02 | 西北工业大学 | Bridge target detection method based on Markov tree water area network construction |
CN114998720B (en) * | 2022-05-04 | 2024-02-13 | 西北工业大学 | Bridge target detection method based on Markov tree water area network construction |
CN115222758B (en) * | 2022-09-21 | 2023-01-10 | 北京九章星图科技有限公司 | Real-time detection method for ship moving target of low-resolution wide-area sequence remote sensing image |
CN115222758A (en) * | 2022-09-21 | 2022-10-21 | 北京九章星图科技有限公司 | Low-resolution wide-area sequence remote sensing image ship moving target real-time detection algorithm |
CN116484954A (en) * | 2023-03-20 | 2023-07-25 | 中国人民解放军军事科学院战略评估咨询中心 | Artificial intelligence offshore voltaic model generation method, computer program and storage medium |
CN116484954B (en) * | 2023-03-20 | 2023-11-10 | 中国人民解放军军事科学院战略评估咨询中心 | Artificial intelligent offshore voltaic model generation method and storage medium |
CN116299465A (en) * | 2023-05-18 | 2023-06-23 | 西安电子科技大学 | Bistatic SAR backward projection imaging method based on subspace time-frequency mapping |
Also Published As
Publication number | Publication date |
---|---|
CN106170819B (en) | 2019-04-05 |
CN106170819A (en) | 2016-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2016101279A1 (en) | Quick detecting method for synthetic aperture radar image of ship target | |
Xia et al. | Infrared small target detection based on multiscale local contrast measure using local energy factor | |
Li et al. | An improved superpixel-level CFAR detection method for ship targets in high-resolution SAR images | |
CN108171193B (en) | Polarized SAR (synthetic aperture radar) ship target detection method based on super-pixel local information measurement | |
CN107808383B (en) | Rapid detection method for SAR image target under strong sea clutter | |
CN108805057B (en) | SAR image reservoir area detection method based on joint significance analysis | |
CN108229433B (en) | Method for detecting ship landing on shore based on straight-line segment detection and shape characteristics | |
CN111476159A (en) | Method and device for training and detecting detection model based on double-angle regression | |
CN110889843B (en) | SAR image ship target detection method based on maximum stable extremal region | |
CN113536963B (en) | SAR image airplane target detection method based on lightweight YOLO network | |
Fan et al. | A novel automatic dam crack detection algorithm based on local-global clustering | |
Hwang et al. | A practical algorithm for the retrieval of floe size distribution of Arctic sea ice from high-resolution satellite Synthetic Aperture Radar imagery | |
Chen et al. | Change detection algorithm for multi-temporal remote sensing images based on adaptive parameter estimation | |
Yu et al. | Automatic extraction of green tide from GF-3 SAR images based on feature selection and deep learning | |
Wang et al. | Revisiting SLIC: Fast superpixel segmentation of marine SAR images using density features | |
Li et al. | Outlier-robust superpixel-level CFAR detector with truncated clutter for single look complex SAR images | |
CN105046707B (en) | SAR image ship detection method based on n-order polynomial Function Fitting sea clutter | |
Su et al. | Ship detection based on RetinaNet-plus for high-resolution SAR imagery | |
CN112686222B (en) | Method and system for detecting ship target by satellite-borne visible light detector | |
CN115393577A (en) | Infrared marine small target anti-interference detection method | |
CN108805186A (en) | A kind of SAR image circle oil house detection method based on multidimensional notable feature cluster | |
Zhang et al. | FRS-Net: An efficient ship detection network for thin-cloud and FOG-covered high-resolution optical satellite imagery | |
Wang et al. | Sonar objective detection based on dilated separable densely connected CNNs and quantum-behaved PSO algorithm | |
Wang et al. | Context semantic perception based on superpixel segmentation for inshore ship detection in SAR image | |
Hu et al. | Ship detection in SAR images based on region growing and multi-scale saliency |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14908847 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14908847 Country of ref document: EP Kind code of ref document: A1 |