Abstract
Ship detection and classification in synthetic aperture radar (SAR) images play a vital role for wide applications. Due to the unique SAR imaging mechanism, ship detection and classification tasks have faced numerous challenges, such as land interference, image defocus, and noise. Many detectors and classifiers have been presented to handle these problems. However, the general deep learning-based detectors and classifiers lack the combination of SAR characteristics, which leads to poor performance. Compared with optical images, SAR images lack the texture information of ships, which brings great difficulties to the recognition task. To address the above issues, a novel deep learning-based ship detection and classification network combined with scattering characteristics is proposed in this article. First, to accurately locate ships in large-scale SAR images, this article designs a strong scattering point aware network (SPAN) by capturing the strong scattering points that existed in the ship area. SPAN recognizes the ship category according to their distribution characteristics. Second, to compensate for the feature loss caused by the down-sampling operation, this article designs a more suitable resolution recovery module to replace the bilinear interpolation method. Third, a region of interest automatic generation module is proposed to fully utilize the axis-align feature of oriented proposal boxes and the sufficient information of horizontal proposal boxes. Furthermore, the classification encoder module extracts the distribution feature of scattering points to classify SAR ships. Finally, the comprehensive experiments in the large-scale dataset for ship detection and classification in SAR images (LDSD) demonstrate the superior performance of the proposed method.
Highlights
B ENEFITTING from the all-time and all-weather superiority, synthetic aperture radar (SAR) is widely used in many fields, such as target discrimination [1], maritime surveillance [2], disaster prevention [3], change detection [4] and object detection [5], etc
The final part is the ship classification module, which uses the distribution characteristics of scattering points to classify ship based on ship region of interest (RoI)
We propose a novel and unified approach named scattering point aware network (SPAN) utilizing the SAR imaging mechanism for oriented ship detection and classification
Summary
B ENEFITTING from the all-time and all-weather superiority, synthetic aperture radar (SAR) is widely used in many fields, such as target discrimination [1], maritime surveillance [2], disaster prevention [3], change detection [4] and object detection [5], etc. Various traditional methods have been proposed in ship detection [6]–[8] and classification [9]–[12]. The separate detection and classification process lead to low efficiency of the algorithms, especially in large-scale SAR images. Traditional methods are usually based on prior knowledge to establish an approximate data distribution model of specific scene SAR images to recognize ships. The traditional algorithms have poor performance in the inshore ship detection and recognition. The supervised convolutional neural network (CNN) based methods are especially good at extracting complex and changeable features from massive data, which can accurately locate ship targets, and have strong generalization ability [13]. This article mainly studies ship detection and classification in large-scale SAR images based on deep-learning
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
