Category: Ship detection in satellite imagery

Ship detection in satellite imagery

Skip to Main Content. A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. Use of this web site signifies your agreement to the terms and conditions. Personal Sign In. For IEEE to continue sending you helpful information on our products and services, please consent to our updated Privacy Policy.

Email Address. Sign In. Access provided by: anon Sign Out. A novel algorithm for ship detection in SAR imagery based on the wavelet transform Abstract: Carrying out an effective control of fishing activities is essential to guarantee a sustainable exploitation of sea resources.

Nevertheless, as the regulated areas are extended, they are difficult and time consuming to monitor by means of traditional reconnaissance methods such as planes and patrol vessels. On the contrary, satellite-based synthetic aperture radar SAR provides a powerful surveillance capability allowing the observation of broad expanses, independently from weather effects and from the day and night cycle.

Unfortunately, the automatic interpretation of SAR images is often complicated, even though undetected targets are sometimes visible by eye.

ship detection in satellite imagery

Attending to these particular circumstances, a novel approach for ship detection is proposed based on the analysis of SAR images by means of the discrete wavelet transform. The exposed method takes advantage of the difference of statistical behavior among the ships and the surrounding sea, interpreting the information through the wavelet coefficients in order to provide a more reliable detection.

The analysis of the detection performance over both simulated and real images confirms the robustness of the proposed algorithm. Article :. Date of Publication: 18 April DOI: Need Help?Based on unique access to leading-edge optical and SAR satellite imagery, we provide detailed information over vast and remote ocean areas. OceanFinder is a unique and innovative interface that allows customers to directly order satellite-based maritime detection and identification reports to monitor ships and activity at sea.

Vessel detection reports VDR include near real-time information regarding vessel positions, size and relevant context information. A simple pay-per-use concept ensures that users have full control over their budget, while a subscription service is also available.

This service conveniently packages the following steps:. Reliable service capability through combined use of optical and radar sensors:. Request an OceanFinder Account. Thematic Services. Monitoring Services for Maritime.

OceanFinder - Locate, Identify and Track Ocean Assets OceanFinder is a unique and innovative interface that allows customers to directly order satellite-based maritime detection and identification reports to monitor ships and activity at sea.

Ship Detection from Satellite Image

Play video. Enhanced AIS data correlation to identify the precise location of a non-responding vessel in near real-time. Fully-automated detection and classification of vessels. Route prediction and projected location of vessels coming soon. Satellite sensor activation with the relevant priority to ensure a successful mission. Report delivery, including AIS signal correlation to pinpoint non collaborative vessels.

It can be activated: In routine mode, for background intelligence, as a one-off or on a regular basis. For scheduled or spontaneous operations and emergency delivery can be activated to support urgent event responses.

Monitoring Services for Maritime

TerraSAR-X for near real-time detection of small to large vessels, independent of cloud cover and lighting conditions, a semi-automated detection capability allows for rapid delivery. Your advantages with OceanFinder:.

ship detection in satellite imagery

Did You Find Your Solution? Airbus is there to support your business. We are ready to deliver.The shipping industry is developing towards intelligence rapidly. This method promotes the regressive convolutional neural network from four aspects. First, the feature extraction layer is lightweighted by referring to YOLOv2.

Second, a new feature pyramid network layer is designed by improving its structure in YOLOv3. Last, the activation function is verified and optimized. Then, the detecting experiment on 7 types of ships shows that the proposed method has advantage compared with the YOLO series networks and other intelligent methods. On the testing-set, the final mAP is 0. Thus, this method provides a highly accurate and real-time ship detection method for the intelligent port management and visual processing of the USV.

In the age of artificial intelligence, the shipping industry is developing towards intelligence rapidly. An accurate and rapid detection method is of great significance to not only the port management, but also the safe operation of the USV.

The traditional methods of ship detection and classification are as the following two: 1 the method based on the structure and shape characteristics of ships. InFefilatyev et al.

InChen et al. The accuracy of this method reached Also inLi et al. InZhang et al. The three main steps, including the horizon detection, background modeling, and background subtraction, are all based on the discrete cosine transform [ 5 ]. The method based on threshold. It is usually very practical to detect ships directly with the threshold method. InEldhuset proposed a method based on the local threshold, which takes the ship out of the background and uses filtering window method in detection [ 6 ].Skip to Main Content.

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. Use of this web site signifies your agreement to the terms and conditions. Personal Sign In. For IEEE to continue sending you helpful information on our products and services, please consent to our updated Privacy Policy. Email Address. Sign In. Access provided by: anon Sign Out. This letter proposes a detection algorithm based on saliency segmentation and the local binary pattern LBP descriptor combined with ship structure.

First, we present a novel saliency segmentation framework with flexible integration of multiple visual cues to extract candidate regions from different sea surfaces. Then, simple shape analysis is adopted to eliminate obviously false targets. Finally, a structure-LBP feature that characterizes the inherent topology structure of ships is applied to discriminate true ship targets.

ship detection in satellite imagery

Experimental results on numerous panchromatic satellite images validate that our proposed scheme outperforms other state-of-the-art methods in terms of both detection time and detection accuracy.

Article :. Date of Publication: 13 March DOI: Need Help?Home Satellite imagery case studies Satellite imagery can help on maritime surveillance. Ship detection is a vital aspect of maritime surveillance as it allows the monitoring of maritime traffic, illegal fishing and sea border activities.

This is typically done through the use of an Automated Identification System AISwhich uses VHF radio frequencies to wirelessly broadcast the ships location, destination and identity to nearby receiver devices on other ships and land-based systems.

Ship Detection

AIS are very effective at monitoring ships which are legally required to install a VHF transponder, but fail to detect those which are not, and those which disconnect their transponder. This is where satellite imagery can help. Unlike optical imagery, the wavelengths which the instruments use are not affected by the time of day or meteorological conditions, enabling imagery to be obtained day or night, with cloudy, or clear skies. The below SAR satellite imagery can also provide us some important details such as ship dimensions, orientation and location.

But on its own, SAR satellite imagery has its limitations and it is acknowledged that when combined with AIS data, they form a powerful tool for maritime surveillance. We tried to match each ship location with a corresponding AIS signal to try and obtain more information on each ship see image below. Above : The vessel on the left would have remained unidentified using SAR data alone, but AIS helped us understand more about this ship.

The vessel on the right would have been undetected if one relied purely upon AIS data. There are two reasons for this: this ship may simply not have an AIS transponder or may have turned it off. The latter could be a cause for alarm as this would normally indicate possible illegal activities.

Thus, SAR helps to monitor those ships which may not want to be monitored. This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More. Necessary Always Enabled.Ship detection using SAR relies either on the detection of the ship itself or detection of the ship wake.

C band imagery in HH polarization is preferred for detecting the ship because the ship-sea contrast is usually higher for HH polarizations due to the increased scatter at VV by the surface capillary waves. This results in lower background clutter at HH polarization. Conversely VV is preferred for wake detection as the lower backscatter at HH decreases rapidly with increasing incidence angle, resulting in ship wakes rarely being seen in HH polarized images.

Multi-polarization and polarimetric data are expected to allow the user to exploit various polarization combinations to optimize ship detection applications. For example for ship surveillance a VV and VH combination would be optimal as the VH channel provides point target information against a very dark clutter background. At the same time the VV polarization will provide adequate ocean surface backscatter to allow for wake analyses. Since the interaction mechanism between ship and sea is double bounce scattering it is expected that RR, or right-right circular polarization will also be a good polarization for ship signature enhancement.

Polarimetric data are expected to improve ship target detection and possibly classification. However it will only be suitable for ship tracking or perhaps surveillance in certain regions limited in size and strategically or commercially important for ship traffic, due to limited swath coverage. Polarimetric decomposition and classification by scattering mechanism is an exciting application of polarimetric data for ship detection.

This is clearly illustrated in HH and Polarization entropy images that show the enhanced ship-sea contrast in Figure Figure Ship-sea contrast as a function of incidence angle for all linear polarization, RR polarization and polarization entropy van der Sanden and Ross, [61]. Date Modified: Thank you for your interest. Please send us your details and we will be in touch with you shortly. Diversity of satellite images conditions and scales makes object detection one step harder.

Given the exponential growth of images, and in particular optical, infrared and SAR satellite images, business opportunities are growing faster than the number of data scientists that know how to handle them.

Code available on github. With the increase of satellites in orbit, daily pictures of most of the world are now widely available. The competition is fierce, and seems to yield very fast innovation, with companies such as Capella Space now pitching hourly updates by launching constellations of small satellites of only a few kg. Those satellites increasingly cover beyond the optical visible spectrum, notably Synthetic Aperture Radar SAR which offer the benefit to work independently of clouds or daylight.

Along with the growth of other image sources, the ability to interpret image data is a key to untapped commercial opportunities.

The monitoring of human activity is increasing for the purpose of fishing, drilling, exploration, cargo and passenger transport, tourism, for both governmental and commercial purposes, particularly at sea. This is a very approximate method, as both weights and data are changing as the learning rate increase. However, this is computationally cheaper than running multiple simulations in parallel, so hopefully a reasonable stop-gap solution to pick a safe learning rate.

Note that most of the weights are in the dense layer, despite limiting the image size to x pixels. More recent architectures have moved away from this design, and are now fully convolutional, avoiding this concentration of weights on a single layer, which, all things being equal, tends to overfit and yield lower performance. By showing this simple neural network our training set about 2.

A naive approach given the class imbalance would be Examples of misclassification below. We can see that some cases are hard to resolve to the human eye while there still seems to be a minority of easy wins. Also interesting that a fraction of labels seem wrong: another reason to avoid overfitting.

Further improvements could involve more capacity for our model as it may underfit slightly currently, as well as exploit higher resolution images. An issue with this architecture is that input image size is fixed. That can be solved through.

In the second part of this post, we explore the former architecture, along with a deeper network. Explanation in part 2 of this post. The Vortexa analyst team delve deep into the impacts of the covid pandemic on global jet fuel and gasoline flows. Watch on-demand now! Login Request a demo.

ship detection in satellite imagery

Home Company Insight Contact Demo. Request demo Thank you for your interest.

Request demo

Subscribe and keep up to date with our latest news, or read our insights here. Simple generator to grab image on the fly, label it, resize and normalise it, and perform basic data augmentation. X-axis is the number of pseudo-epoch, i.


Author: Dosho

thoughts on “Ship detection in satellite imagery

Leave a Reply

Your email address will not be published. Required fields are marked *