CN107274401B - High-resolution SAR image ship detection method based on visual attention mechanism - Google Patents

High-resolution SAR image ship detection method based on visual attention mechanism Download PDF

Info

Publication number
CN107274401B
CN107274401B CN201710482797.7A CN201710482797A CN107274401B CN 107274401 B CN107274401 B CN 107274401B CN 201710482797 A CN201710482797 A CN 201710482797A CN 107274401 B CN107274401 B CN 107274401B
Authority
CN
China
Prior art keywords
probability
detection
target
image
region
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710482797.7A
Other languages
Chinese (zh)
Other versions
CN107274401A (en
Inventor
徐永力
熊伟
崔亚奇
姚力波
吕亚飞
刘恒燕
朱洪峰
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.)
Naval Aeronautical University
Original Assignee
Naval Aeronautical University
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 Naval Aeronautical University filed Critical Naval Aeronautical University
Priority to CN201710482797.7A priority Critical patent/CN107274401B/en
Publication of CN107274401A publication Critical patent/CN107274401A/en
Application granted granted Critical
Publication of CN107274401B publication Critical patent/CN107274401B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G06T2207/10044—Radar image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user
    • G06T2207/20104—Interactive definition of region of interest [ROI]

Abstract

The invention discloses a high-resolution SAR image ship detection method based on a visual attention mechanism, and belongs to the field of radar image target detection. Mainly aiming at the problem that the existing high-resolution SAR image target detection cannot meet the intelligent requirement and real-time requirement of detection, a frequency domain-based Fourier transform extracts a visual salient model from a frequency spectrum residual error part containing target information in an image; and then, carrying out significant map binarization processing and region-of-interest extraction on the significant map, analyzing and designing a local maximum posterior probability classifier from a classification angle to carry out target detection on the potential target region, and realizing the detection through parameter estimation and a decision criterion. The method can improve the real-time performance and accuracy of the high-resolution SAR image ship target detection, and effectively avoid the problem of higher false alarm in the detection.

Description

High-resolution SAR image ship detection method based on visual attention mechanism
Technical Field
The invention belongs to the field of synthetic aperture radar image target detection, relates to a detection method meeting the real-time detection requirement of a radar image target, and is suitable for high-resolution synthetic aperture radar images for detecting and monitoring ship targets under complex sea conditions including a large number of uneven sea clutter areas, spot noise and the like.
Background
Synthetic Aperture Radars (SAR) have the characteristics of all-time, all-weather, large range and the like, are important components of ocean monitoring and supervision, and among them, ship target detection increasingly becomes a research hotspot. The SAR image ship target detection is a precondition and a basis for classification and identification, and is an important aspect of SAR image application.
With the emission operation of new generation SAR sensors such as Radarsat-2, TerrasAR-X, high-resolution three-dimensional SAR and the like, the SAR gradually develops towards high resolution, large breadth and multi-polarization. However, as the size of the high-resolution SAR image gradually increases, the processing speed of the conventional point-by-point calculation based on the image is slow, and the contradiction between the SAR image information with large data volume and the limited computer processing capability is difficult to achieve the requirement of real-time processing. Secondly, when the traditional low-resolution SAR image detection method is applied to a high-resolution SAR image at the present stage, the detection accuracy is not high, the method still has defects in the aspect of improving false alarms caused by speckle noise and uneven sea clutter background to detection results, and the accurate and intelligent detection requirements of targets in the image are difficult to meet.
Disclosure of Invention
The invention provides a high-resolution SAR image ship detection method based on a visual attention mechanism, which aims to solve the problem of multiple false alarms in the existing SAR image target detection and meet the detection intelligentization requirement and the real-time requirement.
The invention relates to a high-resolution SAR image ship detection method based on a visual attention mechanism, which specifically comprises the following technical measures: the visual salient model is obtained by adopting a global salient region solving algorithm of a frequency spectrum residual method, and is realized based on the fast Fourier transform of a frequency domain, and a part which is different from the part with the same shape in the frequency spectrum of one image, namely a frequency spectrum residual part containing target information is extracted; and performing two steps of operations on the obtained saliency map according to the image properties of the saliency map, namely binarization processing of the saliency map and extraction of the region of interest. The step is realized by performing threshold segmentation processing on the saliency map twice, firstly segmenting the potential ship region in the visual saliency map through a first threshold, classifying pixels in the saliency map through two thresholds in the second threshold segmentation, and screening the classified part to accurately complete the approximate fitting of the gray level histograms of the subsequent target region and the background region; according to the theory of machine learning, analyzing the ship target detection problem in a classification angle, designing a local maximum posterior probability classifier to further detect the ship target in the significant region in the image, and converting the target detection problem into a binary hypothesis test problem of each pixel point of a potential target region; and performing parameter estimation and calculation on the conditional probability of the pixel points to be detected under the given category and the prior probability of the pixel points to be detected belonging to each category according to the judgment criterion of the classifier, and combining the classifier parameters obtained by estimation to realize secondary detection on the pixel points in the ship potential target area of the salient area.
The high-resolution SAR image ship detection method based on the visual attention mechanism can improve the real-time performance and accuracy of high-resolution SAR image ship target detection, and effectively avoids a higher false alarm problem in detection by processing images by using the visual attention theory and the machine learning theory for reference.
Drawings
FIG. 1 is a flow chart of a high resolution SAR image ship detection based on a visual attention mechanism;
fig. 2 is a schematic diagram of high-resolution SAR image ship detection based on a visual attention mechanism.
Detailed Description
The technical scheme of the high-resolution SAR image ship detection method based on the visual attention mechanism comprises the following steps:
step 1.1: the calculation model uses a salient region solving algorithm of a global search mode, is a visual salient region extraction method based on an image frequency domain, and is realized by adopting fast Fourier transform, under the normal condition, a part different from a part with the same shape in a frequency spectrum of an image is a frequency spectrum residual part containing target information, and the visual salient model extracts the residual part; assuming that i (x) is an image, the frequency spectrum FFT [ i (x) ] of the image can be decomposed into two parts, amplitude spectrum a (f) and phase spectrum p (f);
P(f)＝FFT[I(x)]/|{FFT[I(x)]}| (1)
R(f)＝BP(f)·P(f) (2)
S(f)＝FFT-1[R(f)](3)
wherein, FFT and FFT-1Representing the fast Fourier transform and the inverse transform of the image, P (f) is the phase spectrum of the original image, R (f) represents the residual error of the frequency spectrum, BP (f) is a band-pass filter, and the center frequency f is adopted in the model0Cut-off frequencyThe model for calculating the significance of the residual error of the frequency spectrum in the high-resolution SAR image ship detection method based on the visual attention mechanism mainly comprises two steps of operation, namely normalization processing of an original frequency spectrum and frequency domain band-pass filtering;
step 1.2: obtaining a visual saliency map by adopting a spectrum residual method in the previous step of operation, and carrying out two steps of operation on the obtained saliency map: firstly, binarization processing of a saliency map; secondly, extracting the region of interest. Two threshold segmentation steps are adopted, firstly, a salient region in a visual salient image is segmented, so that the salient region in the image screened out by a visual attention calculation model is a potential ship region. And the second threshold segmentation divides the pixels in the saliency map by setting two thresholds, so that the approximation of the gray level histograms of the subsequent target region and the background region is more accurately completed.
Step 2.1: the method comprises the following steps of analyzing a ship target detection problem from the idea of classification in machine learning, wherein the ship target detection is two classification problems, designing a local maximum posterior probability classifier to perform secondary detection on a potential ship target region after threshold segmentation of a visual salient region: converting the high-resolution SAR image ship target detection problem into a binary hypothesis test problem of a data vector x according to a Bayesian theory; the data samples are divided into two classes, sample class omegaiAre respectively omega1And ω0The class of samples labeled as targets is ω1The sample class marked as background is ω0(ii) a Let P (omega)i) Indicating that the input pixel belongs to ωiThe bayesian criterion of this binary hypothesis detection is:
Figure BDA0001329788510000031
Figure BDA0001329788510000032
wherein, P (ω)1| x) and P (ω)0| x) refers to the posterior summary of the detected pixel as the target and background, respectivelyRate, P (x | ω |)i) Is in a given category ωiConditional probability of, p (x) refers to the probability of acquiring a pixel;
according to the Bayes criterion and the maximum posterior probability estimation criterion, the classifier is defined as:
Figure BDA0001329788510000033
the conditions met when the target is present are:
Figure BDA0001329788510000034
conversely, the conditions met when the target is not present are:
Figure BDA0001329788510000035
the decision criterion of the local maximum a posteriori probability classifier is:
Figure BDA0001329788510000036
step 2.2: solving the conditional probability P (x | omega) of the pixel point to be detected under the given categoryi)：
For the parameter estimation of the local classifier, the first step needs to obtain the conditional probability P (x | ω)i) That is, two threshold values T are set as probability density functions of the target and the background1、T2Wherein T is2>T1(ii) a Carrying out threshold segmentation on the saliency map and carrying out approximate target and background region gray histogram fitting operation in the corresponding original image, wherein the process carries out modeling on both the background and the target:
a) the two thresholds are adopted to segment the saliency map, and the saliency map more than the threshold T in the corresponding saliency map in the image to be detected is extracted1Obtaining a gray level histogram from all partial pixels, and performing approximate gray level histogram fitting by using distribution models such as Gamma distribution, Weibull distribution, Log-Normal distribution and the like to obtain probability distribution of the ship target;
b) extracting the corresponding saliency map in the original image by the method of sub-step a) as above, wherein the saliency map is smaller than the threshold T2All pixels in the area are used as the approximation of a background area, and the gray level histogram fitting is carried out to be used as the approximation of background probability distribution;
c) solving a probability density function of the ship target and the clutter background according to the probability distribution obtained by histogram fitting to obtain the conditional probability P (x | omega) of the target and the background required to be solved in the classifieri)。
Step 2.3: solving prior probability P (omega) that pixel points to be detected belong to each categoryi)：
Obtaining omega of pixel point to be detected through a sliding windowiA priori probability of (a), a priori probability P (ω)i) Is defined as:
Figure BDA0001329788510000041
wherein x istRepresenting the gray value, x, of the current pixel to be detected1、x2,...,xNG is the maximum value of the gray level of the SAR image, a is an empirical parameter for adjusting the prior probability, a ∈ (0, 1)](ii) a In the operation, a sliding window is adopted to calculate the prior probability of a target potential region, and each parameter in the sliding window design needs to be determined according to the pixel area, the size and the distribution condition of the ship target in the SAR image;
step 2.4: and (3) combining the obtained prior probability and the conditional probability to realize secondary detection on the pixel points in the ship potential target area of the salient region, and performing ship target detection on all the pixel points in the salient region in the image by adopting a designed local maximum posterior probability classifier to obtain a final detection result.

Claims (2)

1. A high-resolution SAR image ship detection method based on a visual attention mechanism is characterized by comprising the following steps:
step 1: designing a global search high-resolution SAR image salient region detection algorithm, obtaining a spectrum residual visual salient calculation model through spectrum normalization processing and frequency domain band-pass filtering, and quickly obtaining a visual interesting region;
step 2: combining a binary hypothesis testing thought in Bayes theory, designing a local maximum posterior probability classifier, and completing pixel two classification in a significant region through parameter estimation and decision criteria to realize target detection;
the step 2 specifically comprises the following substeps:
step 2.1: analyzing the ship target detection problem from the classification angle, designing a local maximum posterior probability classifier to further detect the ship target in the salient region in the image: converting a target detection problem into a binary hypothesis test problem of a data vector x according to a Bayesian theory; the data samples are divided into two classes, and the sample class is omega respectively1And ω0Let P (ω)i) Indicating that the input pixel belongs to ωiThe bayesian criterion of this binary hypothesis detection is:
Figure FDA0002477556970000011
Figure FDA0002477556970000012
wherein, P (ω)1| x) and P (ω)0| x) refers to the posterior probability of the detected pixel being the target and background, respectively, P (x | ω)i) Is in a given category ω0Conditional probability of, p (x) refers to the probability of acquiring a pixel;
according to the Bayesian criterion and the maximum posterior probability criterion, the classifier can be defined as:
Figure FDA0002477556970000013
the conditions met when the target is present are:
Figure FDA0002477556970000014
the decision criterion adopted by the maximum a posteriori probability classifier is as follows:
Figure FDA0002477556970000015
step 2.2: solving the conditional probability P (x | omega) of the pixel point to be detected under the given categoryi)：
Conditional probability P (x | ω |)i) Namely, setting two threshold values T as probability density functions of the target and the background1、T2Wherein T is2>T1；
a) The two thresholds are adopted to segment the saliency map, and the saliency map more than the threshold T in the corresponding saliency map in the image to be detected is extracted1Obtaining a gray level histogram of all partial pixels; fitting approximate gray level histogram of Gamma distribution, Weibull distribution and Log-Normal distribution to obtain probability distribution of the ship target;
b) extracting the corresponding saliency map in the original map smaller than the threshold T in the same way as the sub-step a) above2Performing gray level histogram fitting on all pixels in the region to serve as approximation of background probability distribution;
c) solving a probability density function of the ship target and the clutter background according to the probability distribution obtained by the histogram fitting;
step 2.3: solving prior probability P (omega) that pixel points to be detected belong to each categoryi)：
Obtaining omega of pixel point to be detected through a sliding windowiA priori probability of (a), a priori probability P (ω)i) Is defined as:
Figure FDA0002477556970000021
wherein x istRepresenting the gray value, x, of the current pixel to be detected1、x2,...,xNIs all pixel points belonging to the background area in the sliding window, G is the maximum value of the gray level of the SAR image, a is an empirical parameter for adjusting the prior probability, a ∈ (0, 1)](ii) a At this stepIn the method, a sliding window is adopted to calculate the prior probability of a target potential region, and each parameter in the sliding window design needs to be determined according to the pixel area, the size and the distribution condition of a ship target in an SAR image;
step 2.4: and (3) combining the obtained prior probability and conditional probability to realize secondary detection on the pixel points in the ship potential target area of the salient area, carrying out ship target detection on all the pixel points in the salient area in the image by adopting a designed local maximum posterior probability classifier in the detection, and obtaining a final detection result through a judgment criterion.
2. The visual attention mechanism-based high-resolution SAR image ship detection method according to claim 1, wherein the step 1 specifically comprises the following substeps:
step 1.1: the model uses a salient region calculation algorithm of global range search, the calculation model is based on frequency domain processing and is realized by adopting fast Fourier transform, and the part which is different from the part with the same shape in the frequency spectrum of one image, namely the frequency spectrum residual part containing target information is extracted; assuming that I (x) is an image, the frequency spectrum FFT [ I (x) ] of the image is decomposed into two parts of an amplitude spectrum A (f) and a phase spectrum P (f),
P(f)＝FFT[I(x)]/|{FFT[I(x)]}| (1)
R(f)＝BP(f)·P(f) (2)
S(f)＝FFT-1[R(f)](3)
wherein, FFT and FFT-1Representing the fast Fourier transform and the inverse transform of the image, P (f) is the phase spectrum of the original image, R (f) represents the residual of the frequency spectrum, BP (f) is a band-pass filter, and a center frequency f is adopted in the model0A Gaussian filter with cut-off frequency delta f, S (f) is a saliency map, and the spectrum residual saliency model mainly comprises two steps of operations: normalization processing of frequency spectrum and frequency domain band-pass filtering;
step 1.2: obtaining a visual saliency map by a previous step of spectrum residual error method, and carrying out two steps of operations on the obtained saliency map: firstly, extracting and segmenting a salient region in a visual salient image, and screening out a potential ship target region in the image according to a visual attention calculation model; the second threshold segmentation is realized by two thresholds, pixels in the saliency map are classified, and the gray histogram approximate fitting of a subsequent target region and a background region is completed more accurately.
CN201710482797.7A 2017-06-22 2017-06-22 High-resolution SAR image ship detection method based on visual attention mechanism Active CN107274401B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710482797.7A CN107274401B (en) 2017-06-22 2017-06-22 High-resolution SAR image ship detection method based on visual attention mechanism

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710482797.7A CN107274401B (en) 2017-06-22 2017-06-22 High-resolution SAR image ship detection method based on visual attention mechanism

Publications (2)

Publication Number Publication Date
CN107274401A CN107274401A (en) 2017-10-20
CN107274401B true CN107274401B (en) 2020-09-04

Family

ID=60069020

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710482797.7A Active CN107274401B (en) 2017-06-22 2017-06-22 High-resolution SAR image ship detection method based on visual attention mechanism

Country Status (1)

Country Link
CN (1) CN107274401B (en)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108446584B (en) * 2018-01-30 2021-11-19 中国航天电子技术研究院 Automatic detection method for unmanned aerial vehicle reconnaissance video image target
CN108599884B (en) * 2018-03-19 2020-11-03 重庆大学 Signal detection method for noise enhancement minimizing error probability
CN108694714A (en) * 2018-05-14 2018-10-23 浙江大学 Ship seakeeping system in a kind of adaptive colony intelligence optimization SAR Radar Seas
CN109165660B (en) * 2018-06-20 2021-11-09 扬州大学 Significant object detection method based on convolutional neural network
CN110084210B (en) * 2019-04-30 2022-03-29 电子科技大学 SAR image multi-scale ship detection method based on attention pyramid network
CN110853050B (en) * 2019-10-21 2023-05-26 中国电子科技集团公司第二十九研究所 SAR image river segmentation method, device and medium
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
CN111046871B (en) * 2019-12-11 2023-07-11 厦门大学 Region of interest extraction method and system
CN111666854B (en) * 2020-05-29 2022-08-30 武汉大学 High-resolution SAR image vehicle target detection method fusing statistical significance
CN111767856B (en) * 2020-06-29 2023-11-10 烟台哈尔滨工程大学研究院 Infrared small target detection algorithm based on gray value statistical distribution model
CN112836571A (en) * 2020-12-18 2021-05-25 华中科技大学 Ship target detection and identification method, system and terminal in remote sensing SAR image
CN112862748B (en) * 2020-12-25 2023-05-30 重庆大学 Multi-dimensional domain feature combined SAR ship intelligent detection method
CN113111758B (en) * 2021-04-06 2024-01-12 中山大学 SAR image ship target recognition method based on impulse neural network
CN113203991B (en) * 2021-04-29 2022-05-31 电子科技大学 Anti-deception jamming method of multi-base SAR (synthetic aperture radar) in multi-jammer environment

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7848566B2 (en) * 2004-10-22 2010-12-07 Carnegie Mellon University Object recognizer and detector for two-dimensional images using bayesian network based classifier
CN102122352B (en) * 2011-03-01 2012-10-24 西安电子科技大学 Characteristic value distribution statistical property-based polarized SAR image classification method
US20150235073A1 (en) * 2014-01-28 2015-08-20 The Trustees Of The Stevens Institute Of Technology Flexible part-based representation for real-world face recognition apparatus and methods
CN105354541B (en) * 2015-10-23 2018-07-17 西安电子科技大学 The SAR image object detection method of view-based access control model attention model and constant false alarm rate
CN105427314B (en) * 2015-11-23 2018-06-26 西安电子科技大学 SAR image object detection method based on Bayes's conspicuousness

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
SAR IMAGE SHIP DETECTION BASED ON VISUAL ATTENTION MODEL;Biao Hou等;《IEEE》;20140127;第2003-2006页 *

Also Published As

Publication number Publication date
CN107274401A (en) 2017-10-20

Similar Documents

Publication Publication Date Title
CN107274401B (en) High-resolution SAR image ship detection method based on visual attention mechanism
CN107229918B (en) SAR image target detection method based on full convolution neural network
CN107808383B (en) Rapid detection method for SAR image target under strong sea clutter
CN106780485B (en) SAR image change detection method based on super-pixel segmentation and feature learning
CN108280460B (en) SAR vehicle target identification method based on improved convolutional neural network
Asokan et al. Machine learning based image processing techniques for satellite image analysis-a survey
Wang et al. A fast CFAR algorithm based on density-censoring operation for ship detection in SAR images
Xia et al. A novel sea-land segmentation algorithm based on local binary patterns for ship detection
CN108171119B (en) SAR image change detection method based on residual error network
CN107742113A (en) One kind is based on the posterior SAR image complex target detection method of destination number
CN110889843A (en) SAR image ship target detection method based on maximum stable extremal region
KR20220014805A (en) Generating training data usable for examination of a semiconductor specimen
CN108226890B (en) Airport foreign matter radar detection method based on time direction statistics
Li et al. Automatic infrared ship target segmentation based on structure tensor and maximum histogram entropy
Chang et al. Locating waterfowl farms from satellite images with parallel residual u-net architecture
Li et al. Ship target detection and recognition method on sea surface based on multi-level hybrid network
Ranjani et al. Fast threshold selection algorithm for segmentation of synthetic aperture radar images
CN107729903A (en) SAR image object detection method based on area probability statistics and significance analysis
CN109271902B (en) Infrared weak and small target detection method based on time domain empirical mode decomposition under complex background
CN107704864A (en) Well-marked target detection method based on image object Semantic detection
Wang et al. Vehicle recognition based on saliency detection and color histogram
Wang et al. An automatic bridge detection technique for high resolution SAR images
Li et al. Saliency detection using a background probability model
Li et al. Ship detection based on surface fitting modeling for large range background of ocean images
Wu et al. Fast cloud image segmentation with superpixel analysis based convolutional networks

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20200807

Address after: 264001 Research and Academic Department, 188 Erma Road, Zhifu District, Yantai City, Shandong Province

Applicant after: NAVAL AERONAUTICAL University

Address before: 264001 Yantai City, Zhifu Province, No. two road, No. 188, Department of research,

Applicant before: NAVAL AERONAUTICAL AND ASTRONAUTICAL University PLA

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant