Ship Detection and Categorization

Download Product Sheet


Example of ship detection and categorization from SHIP MONITORING SUITE (SIMON) project (Source: GMV)

Product Category

  • Land use
  • Land cover
  • Natural Disaster
  • Climate Change
  • Coast Management 
  • Earth's Surface Motion

Financial Domains

  • 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

  • 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


 


Edit


P34: Ship detection and categorization

Download the product sheet gap analysis 

Maturity score

Mean: 2.7

STD: 0.47

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 in overcrowded ports or regions with high maritime traffic.

Relevant user needs

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

R&D gaps

·   High cost of VHR satellite imagery

·   For near-real time, Automatic Identification System (AIS) data is needed. EO is a complement to permit detecting unreported ships, but real-time tracking is not possible yet with the current technology

Potential improvements drivers

·  Price models

·  More investigation of fusing EO with AIS data

Utilisation level review

Utilisation score

Mean: 2.00

STD: 1.26

No utilisation

·  Unavailability of freely available sources of the EO product.

·  Unacceptable reliability and accuracy of the EO product.

·  Users’ lack of EO knowledge and skills to utilize the EO product.

·  Unawareness of the existence of this EO product.

Low utilisation

Medium utilisation

·  We would not state full technical and usability requirements are met. This remains viable depending on the financial offer and use case.

High utilisation

·  Only this product satisfies the technical and usability requirements.

Critical gaps related to relevant user needs

Utilisation gap

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

Edit
  • No labels

This page has no comments.