Automatic Ship Detection in Optical Remote Sensing Images Based on Anomaly Detection and SPP-PCANet

Nan Wang,Yonghua Wang,Bo Li,Qizhi Xu

doi:10.3390/rs11010047

Abstract

Automatic ship detection technology in optical remote sensing images has a wide range of applications in civilian and military fields. Among most important challenges encountered in ship detection, we focus on the following three selected ones: (a) ships with low contrast; (b) sea surface in complex situations; and (c) false alarm interference such as clouds and reefs. To overcome these challenges, this paper proposes coarse-to-fine ship detection strategies based on anomaly detection and spatial pyramid pooling pcanet (SPP-PCANet). The anomaly detection algorithm, based on the multivariate Gaussian distribution, regards a ship as an abnormal marine area, effectively extracting candidate regions of ships. Subsequently, we combine PCANet and spatial pyramid pooling to reduce the amount of false positives and improve the detection rate. Furthermore, the non-maximum suppression strategy is adopted to eliminate the overlapped frames on the same ship. To validate the effectiveness of the proposed method, GF-1 images and GF-2 images were utilized in the experiment, including the three scenarios mentioned above. Extensive experiments demonstrate that our method obtains superior performance in the case of complex sea background, and has a certain degree of robustness to external factors such as uneven illumination and low contrast on the GF-1 and GF-2 satellite image data.

Highlights

In recent decades, research on Synthetic Aperture Radar (SAR) images [1,2,3] has improved considerably, taking advantage of insensitivity in time and weather
The sample data of the optical remote sensing image were derived from the GF-1 and GF-2 satellites
The experiment validated the proposed method on the GF-1 images of 18,192 × 18,000 pixels and GF2 images of 29,200 × 27,620 pixels. These datasets contain a variety of scenarios, such as cloud interference, low contrast, complex sea conditions, port vessels and so on

Summary

Introduction

Research on Synthetic Aperture Radar (SAR) images [1,2,3] has improved considerably, taking advantage of insensitivity in time and weather. Compared with SAR images, optical images have more detailed information and more obvious geometric structures. This means that optical images can capture more details and complex structures of observation scenes, and can be further used for target recognition. In view of these advantages, ships in optical remote sensing images are often regarded as research targets. Ship detection of marine in optical remote sensing image has a paramount application value in military and civilian fields. Attention is paid to the location of passing ships within the target sea area to improve marine administration, playing an important

Methods

Results

Conclusion