A Coarse-to-Fine Network for Ship Detection in Optical Remote Sensing Images

Yue Wu,Qiguang Miao,Wei Zhao,Xiaobo Chen,Maoguo Gong,Qiongqiong Guo,Wenping Ma,Zhuangfei Bai

doi:10.3390/rs12020246

Abstract

With the increasing resolution of optical remote sensing images, ship detection in optical remote sensing images has attracted a lot of research interests. The current ship detection methods usually adopt the coarse-to-fine detection strategy, which firstly extracts low-level and manual features, and then performs multi-step training. Inadequacies of this strategy are that it would produce complex calculation, false detection on land and difficulty in detecting the small size ship. Aiming at these problems, a sea-land separation algorithm that combines gradient information and gray information is applied to avoid false alarms on land, the feature pyramid network (FPN) is used to achieve small ship detection, and a multi-scale detection strategy is proposed to achieve ship detection with different degrees of refinement. Then the feature extraction structure is adopted to fuse different hierarchical features to improve the representation ability of features. Finally, we propose a new coarse-to-fine ship detection network (CF-SDN) that directly achieves an end-to-end mapping from image pixels to bounding boxes with confidences. A coarse-to-fine detection strategy is applied to improve the classification ability of the network. Experimental results on optical remote sensing image set indicate that the proposed method outperforms the other excellent detection algorithms and achieves good detection performance on images including some small-sized ships and dense ships near the port.

Highlights

Ship detection in optical remote sensing image is a challenging task and has a wide range of applications such as ship positioning, maritime traffic control and vessel salvage [1]
The sea-land separation algorithm [42] used in this paper considers the gradient information and the gray information of the optical remote sensing image comprehensively, combines some typical image morphology algorithms, and generates a binary image
We conduct multiple sets of experiments to evaluate the performance of our methods and compare it with three excellent detection methods

Summary

Introduction

Ship detection in optical remote sensing image is a challenging task and has a wide range of applications such as ship positioning, maritime traffic control and vessel salvage [1]. Schwegmann et al [6] used deep highway networks to avoid the vanishing gradient problem They developed their own three-class SAR dataset that allows for more meaningful analysis of ship discrimination performances. They used data from Sentinel-1 (Extra Wide Swath), Sentinel-3 and RADARSAT-2 (Scan-SAR Narrow) They used Deep Highway Networks 2, 20, 50, 100 with 5-fold cross-validation and obtained an accuracy of 96% outperforming classical techniques such as SVM, Decision Trees, and Adaboost. Carlos Bentes et al [7] used a custom CNN with TerraSAR-X Multi Look Ground Range Detected (MGD) images to detect ships and iceberg. They compared their results with SVM and PCA+SVM, and showed that the proposed model outperforms these classical techniques. The characteristics of optical remote sensing image such as the diversity of target size, high complexity of background and small targets makes ship detection difficult

Methods

Results

Conclusion