Abstract
Automatic ship detection in optical remote sensing images is of great significance due to its broad applications in maritime security and fishery control. Most ship detection algorithms utilize a single-band image to design low-level and hand-crafted features, which are easily influenced by interference like clouds and strong waves and not robust for large-scale variation of ships. In this paper, we propose a novel coarse-to-fine ship detection method based on discrete wavelet transform (DWT) and a deep residual dense network (DRDN) to address these problems. First, multi-spectral images are adopted for sea-land segmentation, and an enhanced DWT is employed to quickly extract ship candidate regions with missing alarms as low as possible. Second, panchromatic images with clear spatial details are used for ship classification. Specifically, we propose the local residual dense block (LRDB) to fully extract semantic feature via local residual connection and densely connected convolutional layers. DRDN mainly consists of four LRDBs and is designed to further remove false alarms. Furthermore, we exploit the multiclass classification strategy, which can overcome the large intra-class difference of targets and identify ships of different sizes. Extensive experiments demonstrate that the proposed method has high robustness in complex image backgrounds and achieves higher detection accuracy than other state-of-the-art methods.
Highlights
Automatic ship detection has attracted great research interest due to its broad applications in both the military and civil domain, such as national defense construction, maritime security, port surveillance, and sea traffic control [1]
Many previous studies on ship detection were mainly based on synthetic aperture radar (SAR) images [2,3,4,5,6,7,8,9,10,11,12], because they are less impacted by adverse weather conditions
Upon comprehensive consideration of the above factors, we propose a novel coarse-to-fine detection framework based on discrete wavelet transform (DWT) and a deep residual dense network (DRDN) to address these three aforementioned problems
Summary
Automatic ship detection has attracted great research interest due to its broad applications in both the military and civil domain, such as national defense construction, maritime security, port surveillance, and sea traffic control [1]. Nie et al [17] proposed an effective algorithm in which morphological, geometric, and texture features of candidate regions are extracted for target confirmation These hand-crafted features have achieved promising results, but they may lack generalization in complex weather conditions [24]. They proposed a coarse-to-fine detection strategy to improve the classification ability of the network These deep learning-based methods have shown desirable performance in response to the interference of clouds and waves; they might produce more false alarms on land and miss small ships [18,20], resulting in restrictions on further improvement of ship detection performance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have