Ship Identification and Characterization in Sentinel-1 SAR Images with Multi-Task Deep Learning

Clément Dechesne,Guillaume Hajduch,Sébastien Lefèvre,Ronan Fablet,Rodolphe Vadaine

doi:10.3390/rs11242997

Abstract

The monitoring and surveillance of maritime activities are critical issues in both military and civilian fields, including among others fisheries’ monitoring, maritime traffic surveillance, coastal and at-sea safety operations, and tactical situations. In operational contexts, ship detection and identification is traditionally performed by a human observer who identifies all kinds of ships from a visual analysis of remotely sensed images. Such a task is very time consuming and cannot be conducted at a very large scale, while Sentinel-1 SAR data now provide a regular and worldwide coverage. Meanwhile, with the emergence of GPUs, deep learning methods are now established as state-of-the-art solutions for computer vision, replacing human intervention in many contexts. They have been shown to be adapted for ship detection, most often with very high resolution SAR or optical imagery. In this paper, we go one step further and investigate a deep neural network for the joint classification and characterization of ships from SAR Sentinel-1 data. We benefit from the synergies between AIS (Automatic Identification System) and Sentinel-1 data to build significant training datasets. We design a multi-task neural network architecture composed of one joint convolutional network connected to three task specific networks, namely for ship detection, classification, and length estimation. The experimental assessment shows that our network provides promising results, with accurate classification and length performance (classification overall accuracy: 97.25%, mean length error: 4.65 m ± 8.55 m).

Highlights

Deep learning is considered as one of the major breakthroughs related to big data and computer vision [1]
We propose a method based on deep learning for ship identification and characterization with the synergetic use of Sentinel-1 SAR images and Automatic Identification System (AIS) data
We evaluated the proposed framework with respect to other popular deep learning based solutions

Summary

Introduction

Deep learning is considered as one of the major breakthroughs related to big data and computer vision [1]. It has become very popular and successful in many fields including remote sensing [2]. When applied on visual data such as images, it is usually achieved by means of convolutional neural networks These networks consist of multiple layers (such as convolution, pooling, fully connected, and normalization layers) aiming to transform original data (raw input) into higher level semantic representation. It is simple through visual inspection to know what objects are in an image, where they are, and how they interact in a very fast and accurate way, allowing performing complex tasks. Fast and accurate algorithms for object detection are sought to allow computers to perform such tasks, at a much larger scale than humans can achieve

Objectives

Methods

Results

Discussion

Conclusion