Multi-feature extraction of ships from SAR images

Gu, Dandan; Xu, Xiaojian

doi:10.1109/cisp.2013.6744037

Cited by 16 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One 1 × 1 convolution layer and three 3 × 3 empty convolution layers. The rate r is (6,12,18) when the output step size is 16, and is doubled when the output step size is 8.…”

Section: Semantic Segmentation Modelmentioning

confidence: 99%

“…Yan et al [5] improved the Canny edge detection algorithm using a two-dimensional wavelet Gaussian function to calculate the partial derivative of the structural filter gradient amplitude, and adopt maximum inhibition and threshold filters for edge detection and connection for ships. Gu et al [6] used a binary image gradient calculation for edge detection, and determined the minimum enclosing rectangle for ship contours. Zhu et al [7] demonstrated a ship recognition method that used a predicted shape template to determine ship contours using the Otsu method, with peak density detection and column scanning as well as a conventional area averaging algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online Estimation of Ship Dimensions by Combining Images with AIS Reports

Huang,

Hu,

et al. 2023

JMSE

View full text Add to dashboard Cite

Ship dimensions are an important component of static AIS information, and are a key factor in identifying the risks of ship collisions. We describe a method of extracting and correcting ship contour information using inland waterway surveillance video combined with AIS information that does not depend on ship dimension data. A lightweight object detection model was used to determine the ship’s position in an image. Dynamic AIS information was included to produce multigroup control points, solve the optimal homography matrix, and create a transformation model to map image coordinates onto water surface coordinates. A semantic segmentation DeepLabV3+ model was used to determine ship contours from the images, and the actual dimensions of the ship contours were calculated using homography matrix transformation. The mAP of the proposed object detection model and the MIoU of the semantic segmentation model were 86.73% and 91.07%, respectively. The calculation error of the ship length and width were 5.8% and 7.4%, respectively. These statistics indicate that the proposed method rapidly and accurately detected target ships in images, and that the model estimated ship dimensions within a reasonable range.

show abstract

“…One 1 × 1 convolution layer and three 3 × 3 empty convolution layers. The rate r is (6,12,18) when the output step size is 16, and is doubled when the output step size is 8.…”

Section: Semantic Segmentation Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Online Estimation of Ship Dimensions by Combining Images with AIS Reports

Huang,

Hu,

et al. 2023

JMSE

View full text Add to dashboard Cite

show abstract

“…The application of SAR ship data for the detection of ship targets on the water will be able to effectively enhance the early warning capability of sea defense, strengthen the detection and management of fisheries resources, as well as possess an extensive range of application prospects along with vital significance for national development 2,3 . At the current stage, there are four predominant methods for target detection based on SAR images: Target detection methods based on structural features [4][5][6] , grey-scale features [7][8][9] , texture features [10][11][12][13] , and deep learning [14][15][16][17] . In comparison, deep learning-based methods boast powerful feature extraction capabilities and are capable of automatically learning structured features to successfully achieve high-precision recognition of detection targets [18][19][20] .…”

Section: Introductionmentioning

confidence: 99%

Wavelet thresholding and F-NLM filtering based denoising algorithms applied to high resolution SAR ship detection

Tong

Liú

Peng

et al. 2023

Preprint

View full text Add to dashboard Cite

High resolution (HR) SAR ship images have distinctive features of multi-scale, multi-scene and densely arranged distribution of targets, while it is still challenging to have fast and accurate detection. To address the above problem, a SAR ship target detection framework using wavelet thresholding and Fast NLM (F-NLM) joint filtering is proposed. Firstly, wavelet thresholding and F-NLM are used to filter and de-noise the high-resolution SAR images to reduce background clutter noise, while enhancing the detection target detail features and edge information, solving the problem of high false alarm rate in multi-scale, inshore and offshore scenes of ships in SAR images of high resolutions.Then, the YOLOv5 detection network combined with the bi-directional feature fusion module (Bi-FPN) is selected to enable the model to better balance feature information. It can strengthen the aggregation of low and high semantic information and further improve the accuracy of the model. Experimental results show that the SAR ship detection framework has better robustness and target detection accuracy than other deep-learning based algorithms. Compared with SSDD and YOLOv5 network model, the Average Precision (AP) is improved by 1.33% and 2.25% respectively.

show abstract

“…Specifically, synthetic aperture radar (SAR) imaging possesses such capabilities and constitutes a cutting edge technology regarding Earth observation, since not only does it make it feasible to depict large portions of Earth's surface in high resolution images but it also provides information regarding the target scattering characteristics. Consequently, polarimetric SAR imaging constitutes an active research area with applications in land cover classification, maritime security, borderline security, search and rescue missions and automatic target recognition (ATR) [3] [4] [5] [6] [7].…”

Section: Introductionmentioning

confidence: 99%

Fully Polarimetric Land Cover Classification Based on Markov Chains

Κούκιου¹,

Anastassopoulos²

2021

ARS

View full text Add to dashboard Cite

A novel land cover classification procedure is presented utilizing the information content of fully polarimetric SAR images. The Cameron coherent target decomposition (CTD) is employed to characterize land cover pixel by pixel. Cameron's CTD is employed since it provides a complete set of elementary scattering mechanisms to describe the physical properties of the scatterer. The novelty of the proposed land classification approach lies on the fact that the features used for classification are not the types of the elementary scatterers themselves, but the way these types of scatterers alternate from pixel to pixel on the SAR image. Thus, transition matrices that represent local Markov models are used as classification features for land cover classification. The classification rule employs only the most important transitions for decision making. The Frobenius inner product is employed as similarity measure. Ten different types of land cover are used for testing the proposed method. In this aspect, the classification performance is significantly high.

show abstract

Multi-feature extraction of ships from SAR images

Cited by 16 publications

References 6 publications

Online Estimation of Ship Dimensions by Combining Images with AIS Reports

Online Estimation of Ship Dimensions by Combining Images with AIS Reports

Wavelet thresholding and F-NLM filtering based denoising algorithms applied to high resolution SAR ship detection

Fully Polarimetric Land Cover Classification Based on Markov Chains

Contact Info

Product

Resources

About