Abstract
Synthetic aperture radar (SAR) ship detection is a heated and challenging problem. Traditional methods are based on hand-crafted feature extraction or limited shallow-learning features representation. Recently, with the excellent ability of feature representation, deep neural networks such as faster region based convolution neural network (FRCN) have shown great performance in object detection tasks. However, several challenges limit the applications of FRCN in SAR ship detection: (1) FRCN with a fixed receptive field cannot match the scale variability of multiscale SAR ship objects, and the performance degrade when the objects are small; (2) as a two-stage detector, FRCN performs an intensive computation and leads to low-speed detection; (3) when the background is complex, the imbalance of easy and hard examples will lead to a high false detection. To tackle the above issues, we design a multilayer fusion light-head detector (MFLHD) for SAR ship detection. Instead of using a single feature map, shallow high-resolution and deep semantic feature are combined to produce region proposal. In detection subnetwork, we propose a light-head detector with large-kernel separable convolution and position sensitive pooling to improve the detection speed. In addition, we adapt focal loss to loss function and training more hard examples to reduce the false alarm. Extensive experiments on SAR ship detection dataset (SSDD) show that the proposed method achieves superior performance in SAR ship detection both in accuracy and speed.
Highlights
Synthetic aperture radar (SAR) is a coherent imaging technology that provides high-resolution, all-day, and all-weather images [1,2]
Two experiments are designed to explore the effect of multilayer fusion and the influence of light-head design
The comparison with other methods indicates the outperformance of the proposed method
Summary
Synthetic aperture radar (SAR) is a coherent imaging technology that provides high-resolution, all-day, and all-weather images [1,2]. Methods based on CFAR require high contrast between the target and background clutter in the SAR image, and it is based on the assumption that the statistical distribution. Miao Kang et al [20] presented a small sized ships detection framework which fuses the deep semantic and shallow high-resolution features, taking the additional contextual features to provide complementary information for classification and help to rule out false alarms. The dominance of easy examples during training makes it difficult for the detector to detect hard examples, and leads to a high false detection To address these issues, inspired by [23], we propose a multilayer fusion light-head detector to detect multiscale objects. To realize multiscale SAR ship detection, the proposed method fuses the shallow high-resolution and deep semantic features to generate region proposal.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
