Regional attention-based single shot detector for SAR ship detection

Abstract

Automatic ship detection in SAR imagery has been playing a significant role in the field of marine monitoring but great challenges still exist in real-time application. Despite the exciting progresses made by deep-learning techniques, most detectors failed to yield locations of fairly high quality. Moreover, the ships with variant sizes and aspects are easily omitted especially for small objects under complicated background. To alleviate the above problem, the authors propose an elaborately designed single shot detection framework combined with attention mechanism, which roughly locates the regions of interest via an automatically learned attentional map. This lay the foundation of accurate positioning of extremely small objects since the background interference can be effectively suppressed. Furthermore, a multi-level feature fusion module integrated in top-down and bottom-up manner is adopted to adequately aggregate features from not only adjacent but also distant layers. This strengthens local details and merge strong semantic information, enabling the generation of higher qualified anchors for the efficient detection of multi-scale and multi-orientated objects. Experiments on SAR ship dataset have achieved a promising result, surpassing current state-of-the-art methods.

Keywords

• object detection
• feature extraction
• synthetic aperture radar
• learning (artificial intelligence)
• radar imaging
• ships
• radar detection
• marine radar
• neural nets
• multiorientated objects
• sar ship dataset
• regional attention-based single shot detector
• sar ship detection
• automatic ship detection
• sar imagery
• marine monitoring
• attention mechanism
• automatically learned attentional map
• background interference
• deep-learning techniques
• single shot detection
• extremely small objects
• multilevel feature fusion
• strong semantic information
• multiscale objects