Ship Classification Based on Superstructure Scattering Features in SAR Images

Jiang, Mengshi; Yang, Xiu; Zeng, Dong; Fang, Shuai; Meng, Junmin

doi:10.1109/lgrs.2016.2514482

Cited by 64 publications

(24 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2018, 10, x FOR PEER REVIEW 5 of 22 scattering features, are mainly based on the image characteristic mentioned above, obtaining good performance in previous work [4][5][6][7][8][9]. However, interaction of strong scatters on board and electromagnetic reflection between hull and sea surface blur the imaging, making the effective information in SAR images unavailable, as shown in the third and fourth column of Figure 1.…”

Section: Mshog Featurementioning

confidence: 99%

“…MSHOG feature is compared to the features in previous work, including 2D comb feature (2DC) [7], selected features (SF) [10], superstructure scattering features (SS) [5], local RCS density features associated with geometric features (LRCSG) [31], and SAR-HOG feature with PCA dimensionality reduction (PSHOG). The parameters of these features are set up according to the original paper.…”

Section: Effectiveness Of Mshog Featurementioning

confidence: 99%

“…The parameters of these features are set up according to the original paper. Please refer to [5,7,10,31] for more details. We conduct experiments of each feature twenty times to reduce the disturbance of stochastic factors in single experiment and present the average performance of each feature.…”

Section: Effectiveness Of Mshog Featurementioning

confidence: 99%

“…Zhang et al [4] explored geometric features, focusing on width ratio of minimum enclosing rectangle (MER), and the ratio of ship and non-ship points on the principal axis. Jiang et al [5] and Xing et al [6] tried to present a deep understanding of ship properties from superstructure view. 2D comb feature was proposed by Leng et al [7] based on scattering distributions of ship target.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Ship Classification Based on MSHOG Feature and Task-Driven Dictionary Learning with Structured Incoherent Constraints in SAR Images

2018

View full text Add to dashboard Cite

Abstract:In this paper, we present a novel method for ship classification in synthetic aperture radar (SAR) images. The proposed method consists of feature extraction and classifier training. Inspired by SAR-HOG feature in automatic target recognition, we first design a novel feature named MSHOG by improving SAR-HOG, adapting it to ship classification, and employing manifold learning to achieve dimensionality reduction. Then, we train the classifier and dictionary jointly in task-driven dictionary learning (TDDL) framework. To further improve the performance of TDDL, we enforce structured incoherent constraints on it and develop an efficient algorithm for solving corresponding optimization problem. Extensive experiments performed on two datasets with TerraSAR-X images demonstrate that the proposed method, MSHOG feature and TDDL with structured incoherent constraints, outperforms other existing methods and achieves state-of-art performance.

show abstract

Section: Mshog Featurementioning

confidence: 99%

Section: Effectiveness Of Mshog Featurementioning

confidence: 99%

Section: Effectiveness Of Mshog Featurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ship Classification Based on MSHOG Feature and Task-Driven Dictionary Learning with Structured Incoherent Constraints in SAR Images

2018

View full text Add to dashboard Cite

show abstract

“…A number of SAR target classification methods have been proposed in the literature [1][2][3][4], based on radiometric and polarimetric features extracted from the image. In actual images, however, this is not always feasible, as polarimetry could not be available and artefacts due to strong reflectors, insufficient sampling rates or antenna sidelobes could be present.…”

Section: Introductionmentioning

confidence: 99%

Size and Heading of SAR-Detected Ships through the Inertia Tensor

Bedini

Righi

Salerno

2018

International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM)

View full text Add to dashboard Cite

We present a strategy to estimate the heading, the length overall and the beam overall of targets already detected as ships in a wide-swath SAR image acquired by a satellite platform. Such images are often affected by distortions due to marine clutter, spectral leakage, or antenna sidelobes. These can mask the target image, thus hampering the possibility of evaluating the size and the behaviour of the ship. Even in the presence of strong artefacts, we found that the principal inertia axes can help the estimation of the target heading and be included in an iterative procedure to erode the false target features, so to enable a more accurate evaluation of the overall measurements of the ship. Here we introduce our idea and present some results obtained from real SAR images.

show abstract

ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines

Espinosa-Leal

Majd

2023

Proceedings of ELM 2021

View full text Add to dashboard Cite

Ship Classification Based on Superstructure Scattering Features in SAR Images

Cited by 64 publications

References 13 publications

Ship Classification Based on MSHOG Feature and Task-Driven Dictionary Learning with Structured Incoherent Constraints in SAR Images

Ship Classification Based on MSHOG Feature and Task-Driven Dictionary Learning with Structured Incoherent Constraints in SAR Images

Size and Heading of SAR-Detected Ships through the Inertia Tensor

ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines

Contact Info

Product

Resources

About