Multi-task deep learning from Sentinel-1 SAR: ship detection, classification and length estimation

Clément Dechesne 1, 2 Sébastien Lefèvre 3 Rodolphe Vadaine 4 Guillaume Hajduch 4 Ronan Fablet 1, 2
1 Lab-STICC_IMTA_CID_TOMS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
3 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : The detection of inshore and offshore ships is an important issue in both military and civilian fields. It helps monitoring fisheries, managing maritime traffics, ensuring safety of coast and sea, etc. In operational contexts, ship detection is traditionally performed by a human observer who identifies all kind of ships from visual analysis on remote sensing images. Such a task is very time consuming and cannot be conducted at a very large scale, while Sentinel-1 SAR data now provides regular, worldwide coverage. Meanwhile, with the emergence of GPUs, deep learning methods are now established as a state-of-the-art solution for computer vision, replacing human intervention in many contexts. They have been shown to be adapted for ship detection and recognition, most often with very high resolution SAR or optical imagery. In this paper, we go one step further and propose a deep neu-ral network for the detection, classification and length estimation of ships from SAR Sentinel-1 data. We benefit from synergies between AIS (Automatic Identification System) and Sentinel-1 data to build significant training datasets. We then design a multi-task neural-network architecture composed of one joint convolutional network connected to 3 networks dedicated to the different tasks: ship detection, classification and length estimation. Experimental assessment showed our network provides satisfactory results, with accurate classification and length estimation.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal-imt-atlantique.archives-ouvertes.fr/hal-02285670
Contributor : Ronan Fablet <>
Submitted on : Wednesday, November 13, 2019 - 6:14:06 PM
Last modification on : Friday, November 15, 2019 - 4:33:44 PM

File

bids2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02285670, version 1

Citation

Clément Dechesne, Sébastien Lefèvre, Rodolphe Vadaine, Guillaume Hajduch, Ronan Fablet. Multi-task deep learning from Sentinel-1 SAR: ship detection, classification and length estimation. Big Data from Space, 2019, Munich, Germany. ⟨hal-02285670⟩

Share

Metrics

Record views

76

Files downloads

3