Ship Detection and Categorization

Download Product Sheet

Product Category

• Land use
• Land cover
• Natural Disaster
• Climate Change
• Coast Management 

• Marine
• Earth's Surface Motion

Financial Domains

• Investment management 
• Risk Analysis 
• Insurance management 
• Green finance

User requirements 

UN17: Need near real-time tracking of marine vessels to understand their routes and estimate fuel usage

Description

Ships detection and categorization using EO data involves the use of satellite imagery to identify and classify ships on water bodies. This technology employs advanced image processing and machine learning techniques to distinguish between different types of vessels, such as cargo ships, fishing boats, or naval vessels, and track their movements. For investment management, this capability is invaluable as it offers real-time insights into maritime traffic, trade routes, and shipping activities, enabling investors to make data-driven decisions related to shipping and logistics sectors.

Spatial Coverage Target

Water bodies extent

Data Throughput

Rapid tasking 

Data availability

• High
• High

• Low
• Low

PRODUCT SPECIFICATIONS

Main processing steps

The process starts by obtaining various training samples from optical and SAR VHR imagery (≤ 3 m) to be used for training of machine learning models for ship detection and categorization.  Then we apply the model for any type of ship over any type of water body to detect and categorize ships.

Input data sources

Optical:  VHR based on the availability like Pleiades 1A/1B & NEO, WorldView2&3, and SPOT6/7

Radar:  VHR images from different sources like ICEYE, Capella space, and TerraSAR-X

Supporting data:  AIS

Accessibility

Optical and SAR VHR imagery: commercially available on demand from EO service providers.

Spatial resolution

≤ 3 m

Frequency (Temporal resolution)

Daily

Latency

< 1 Day

Geographical scale coverage

Globally

Delivery/ output format

Data type: Raster

File format: GeoTIFF

Accuracies

Thematic accuracy: 80-90%

Spatial accuracy: 1.5-2 pixels of input data

Constraints and limitations

• Smaller vessels and low-profile ships may be challenging to detect or classify.
• Cloud presence but it can be overcome by using SAR imagery.
• Challenging to separate individual vessels over-crowded ports or regions with high maritime traffic.
• Cost of VHR imagery

User's level of knowledge and skills to extract information and perform further analysis on the EO products.

Skills: Essential

Knowledge: Essential