A Novel Variable Index and Excision CFAR Based Ship Detection Method on SAR Imagery

Ji, Kefeng; Xing, Xiangwei; Zou, Huanxin; Sun, Jixiang

doi:10.1155/2015/437083

Cited by 6 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[43]. And the CFAR-based methods include several advanced global algorithms based on the gamma or G0 clutter distribution [9][10][11][12][13][14][15][16][17][18]. It must be stated that all these methods are conducted on the same SSDD data set.…”

Section: The Effect Of Soft-nmsmentioning

confidence: 99%

“…The CFAR algorithms and their improved methods are widely used in ship detections [9][10][11][12][13][14][15][16][17][18]. We also make a more detailed comparison on the related CFAR-based methods in both inshore and offshore scenes [33].…”

Section: The Effect Of Soft-nmsmentioning

confidence: 99%

“…Traditional methods could be roughly divided into three categories including threshold methods [6], statistics methods [7], and transformation methods [8], they generally use a priori knowledge to extract features manually through a series of candidate regions. Among these traditional methods, the constant false alarm rate (CFAR) and its improved algorithms based on threshold are frequently-used in the SAR field [9]. As for CFAR detectors, an appropriate statistical model is selected to match the probability density function (PDF) of the ocean clutter, and then an adaptive threshold is calculated with a typical probability of false alarm (PFA).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

End‐to‐End Ship Detection in SAR Images for Complex Scenes Based on Deep CNNs

et al. 2021

View full text Add to dashboard Cite

Ship detection on synthetic aperture radar (SAR) imagery has many valuable applications for both civil and military fields and has received extraordinary attention in recent years. The traditional detection methods are insensitive to multiscale ships and usually time-consuming, results in low detection accuracy and limitation for real-time processing. To balance the accuracy and speed, an end-to-end ship detection method for complex inshore and offshore scenes based on deep convolutional neural networks (CNNs) is proposed in this paper. First, the SAR images are divided into different grids, and the anchor boxes are predefined based on the responsible grids for dense ship prediction. Then, Darknet-53 with residual units is adopted as a backbone to extract features, and a top-down pyramid structure is added for multiscale feature fusion with concatenation. By this means, abundant hierarchical features containing both spatial and semantic information are extracted. Meanwhile, the strategies such as soft non-maximum suppression (Soft-NMS), mix-up and mosaic data augmentation, multiscale training, and hybrid optimization are used for performance enhancement. Besides, the model is trained from scratch to avoid learning objective bias of pretraining. The proposed one-stage method adopts end-to-end inference by a single network, so the detection speed can be guaranteed due to the concise paradigm. Extensive experiments are performed on the public SAR ship detection dataset (SSDD), and the results show that the method can detect both inshore and offshore ships with higher accuracy than other mainstream methods, yielding the accuracy with an average of 95.52%, and the detection speed is quite fast with about 72 frames per second (FPS). The actual Sentinel-1 and Gaofen-3 data are utilized for verification, and the detection results also show the effectiveness and robustness of the method.

show abstract