1. Regional attention‐based single shot detector for SAR ship detection
- Author
-
Zhan Ronghui, Zhang Jun, and Chen Shiqi
- Subjects
Synthetic aperture radar ,010504 meteorology & atmospheric sciences ,Computer science ,Feature extraction ,Energy Engineering and Power Technology ,deep-learning techniques ,02 engineering and technology ,sar ship dataset ,strong semantic information ,01 natural sciences ,Radar imaging ,0202 electrical engineering, electronic engineering, information engineering ,radar detection ,Computer vision ,Semantic information ,automatic ship detection ,0105 earth and related environmental sciences ,automatically learned attentional map ,Artificial neural network ,business.industry ,feature extraction ,sar imagery ,Detector ,General Engineering ,Single shot ,object detection ,single shot detection ,multiorientated objects ,Object detection ,marine monitoring ,radar imaging ,neural nets ,lcsh:TA1-2040 ,marine radar ,background interference ,learning (artificial intelligence) ,sar ship detection ,020201 artificial intelligence & image processing ,Artificial intelligence ,multilevel feature fusion ,attention mechanism ,lcsh:Engineering (General). Civil engineering (General) ,business ,ships ,multiscale objects ,regional attention-based single shot detector ,Software ,synthetic aperture radar ,extremely small objects - 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.
- Published
- 2019