A novel ship-detection technique for Sentinel-1 SAR data

Iervolino, Pasquale; Guida, Raffaella; Whittaker, Philip

doi:10.1109/apsar.2015.7306324

Cited by 17 publications

(22 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ship detector employed to test the SAR images is based on the scattering models presented in [7] and on the detection procedure introduced in [5][6]. Here, the model parameters are introduced and the block diagram to implement the GLRT is shown in fig.…”

Section: Glrt Detectormentioning

confidence: 99%

“…In all the detectors already presented in literature, the ship model is never considered to reduce the complexity of the detector itself. However, to achieve better performance, the ship model has to be taken in account as already done in [5][6] where a likelihood function for a canonical ship target was derived and employed in a Generalized Likelihood Ratio Test (GLRT) algorithm. This paper is based on the same detector which is here used to test and compare two SAR images acquired over the same area by two different sensors operating at two different bands.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ship detection in SAR imagery: A comparison study

Iervolino

Guida

Lumsdon

et al. 2017

2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

Self Cite

View full text Add to dashboard Cite

This paper presents a ship-detection study with Synthetic Aperture Radar (SAR) images acquired at two different frequencies: X-and C-band. The detection procedure relies on a novel algorithm based on the likelihood functions of both canonical ship target and sea clutter. Spaceborne images were acquired over the same area in the Solent Channel in UK at approximately the same time on the 7 th June 2016. Here, datasets are compared in terms of probability of detection (PD), probability of false alarm (PFA) and Target-to-Clutter Ratio (TCR). Detection maps are validated with Automatic Identification System (AIS) data when available and preliminary results show a higher TCR for the X-band SAR image.

show abstract

Section: Glrt Detectormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Ship detection in SAR imagery: A comparison study

Iervolino

Guida

Lumsdon

et al. 2017

2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Current ship detection research is focused on using high resolution IW Sentinel-1 imagery [3], [4], [5], instead of EW imagery [5], [6]. IW high resolution imagery allows for precise monitoring of small areas such as ports and shoreline areas.…”

Section: Introductionmentioning

confidence: 99%

“…Ship detection in SAR intensity imagery is split into two steps after preprocessing, namely ship prescreening and ship discrimination [1], [6], [2]. Preprocessing concerns itself with the geocoding and removal of land (and sometimes SAR image errors such as ghosting) [2].…”

Section: Introductionmentioning

confidence: 99%

“…These steps are the part of the process which run through a SAR image and prescreen pixels to determine if they are reflective and then discriminate among reflective pixels to only highlight ships. In many research papers these two steps are used separately [1], [6] but some research has shown it can also be approximated using a finely tuned single prescreening step [5]. Almost exclusively in ship detection studies the prescreening step is configured to stringently remove as many false alarms as possible [5], [6] which reduces the responsibility of the ship discrimination step.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Synthetic Aperture Radar Ship Detection Using Haar-Like Features

Schwegmann

Kleynhans

Salmon

2017

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Abstract-The detection of ships at sea is a complex task made more so by adverse weather conditions, lack of night visibility and large areas of concern. Synthetic Aperture Radar imagery with large swaths can provide the needed coverage at a reduced resolution. The development of ship detection methods that can effectively detect ships despite the reduced image resolution is an important area of research. A novel ship detection method is introduced that makes use of a standard Constant False Alarm Rate prescreening step followed by a cascade classifier ship discriminator. Ships are identified using Haar-like features using AdaBoost training on the classifier with an accuracy of 89.38% and false alarm rate of 1.47 × 10 −8 across a large swath Sentinel-1 and RADARSAT-2 newly created SAR dataset.

show abstract

A coupled convolutional neural network for small and densely clustered ship detection in SAR images

Zhao

Guo

Zhang

et al. 2018

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Ship detection from synthetic aperture radar (SAR) imagery plays a significant role in global marine surveillance. However, a desirable performance is rarely achieved when detecting small and densely clustered ship targets, and this problem is difficult to solve. Recently, convolutional neural networks (CNNs) have shown strong detection power in computer vision and are flexible in complex background conditions, whereas traditional methods have limited ability. However, CNNs struggle to detect small targets and densely clustered ones that exist widely in many SAR images. To address this problem while preserving the good properties for complex background conditions, we develop a coupled CNN for small and densely clustered SAR ship detection. The proposed method mainly consists of two subnetworks: an exhaustive ship proposal network (ESPN) for ship-like region generation from multiple layers with multiple receptive fields, and an accurate ship discrimination network (ASDN) for false alarm elimination by referring to the context information of each proposal generated by ESPN. The motivation in ESPN is to generate as many ship proposals as possible, and in ASDN, the goal is to obtain the final results accurately. Experiments are evaluated on two data sets. One is collected from 60 wide-swath Sentinel-1 images and the other is from 20 GaoFen-3 (GF-3) images. Both data sets contain many ships that are small and densely clustered. The quantitative comparison results illustrate the clear improvements of the new method in terms of average precision (AP) and F 1 score by 0.4028 and 0.3045 for the Sentinel-1 data set compared with the multi-step constant false alarm rate (CFAR-MS) method. The values are verified as 0.2033 and 0.1522 for the GF-3 data set. In addition, the new method is demonstrated to be more efficient than CFAR-MS.

show abstract

A novel ship-detection technique for Sentinel-1 SAR data

Cited by 17 publications

References 11 publications

Ship detection in SAR imagery: A comparison study

Ship detection in SAR imagery: A comparison study

Synthetic Aperture Radar Ship Detection Using Haar-Like Features

A coupled convolutional neural network for small and densely clustered ship detection in SAR images

Contact Info

Product

Resources

About