Multi-Scale Proposal Generation for Ship Detection in SAR Images

Abstract

The classic ship detection methods in synthetic aperture radar (SAR) images suffer from an extreme variance of ship scale. Generating a set of ship proposals before detection operation can effectively alleviate the multi-scale problem. In order to construct a scale-independent proposal generator for SAR images, we suggest four characteristics of ships in SAR images and the corresponding four procedures in this paper. Based on these characteristics and procedures, we put forward a framework to explore multi-scale ship proposals. The designed framework mainly contains two stages: hierarchical grouping and proposal scoring. Firstly, we extract edges, superpixels and strong scattering components from SAR images. The ship proposals are obtained at hierarchical grouping stage by combining the strong scattering components with superpixel grouping. Considering the difference of edge density and the completeness and tightness of contour, we obtain the scores to measure the confidence that a proposal contains a ship. Finally, the ranking proposals are obtained. Extensive experiments demonstrate the effectiveness of the four procedures. Our method achieves 0.70 the average best overlap (ABO) score, 0.59 the area under the curve (AUC) score and 0.85 best recall on a challenging dataset. In addition, the recall of our method on three scale subsets are all above 0.80. Experimental results demonstrate that our algorithm outperforms the approaches previously used for SAR images.

Depthwise Separable Convolution Neural Network for High-Speed SAR Ship Detection

“…SAR images in this dataset possess different satellite sensors, various polarization modes, multiple resolutions, different scenes, and abundant ship sizes, so it can verify the robustness of methods. Therefore, many scholars [10,21,35,[55][56][57][58][59][60][61][62][63] conducted research based on it for a better comparison.…”

Urban Features Identification from Dual-Pol SAR Images with Filter Properties

“…The filters are available for the reduction of speckle noise from the SAR images, and every filter has its characteristics and produced different results because of different algorithms they have it (Liu et al, 2016;Veci & March, 2015). Sometimes the result we want from the specific filter is not satisfying us due to different processing criteria.…”

“…For the reduction and removal of this granular effect from an image various low and high pass filtered are used. The speckle noise plays an important role in image processing (Liu et al, 2016). That's why the statistical properties of the speckle need to be analysed for the reduction of granular appearance.…”

FUSAR-Ship: building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognition

“…With a large volume of annotated training data, e.g., [19,20], a deep learning-based algorithm can achieve an unprecedented level of accuracy in the classical CV tasks such as object recognition and scene understanding. DL has also been applied to SAR ATR, e.g., [15,21]. Apparently, those DL algorithms heavily rely on the size and distribution of annotated training data.…”