ADI3: Crowdsource Computer Vision Platform (16/21)

Company: Satellite Applications Catapult

Location: Harwell Oxford, Applied Digital Intelligence Team

The Satellite Applications Catapult is an independent innovation and technology company, created to foster growth across the economy through the exploitation of space. We help organisations make use of and benefit from satellite technologies, and bring together multi-disciplinary teams to generate ideas and solutions in an open innovation environment.

Based in Harwell, near Didcot, the Catapult was established in May 2013 by Innovate UK as one of a network of centres to accelerate the take-up of emerging technologies and drive economic growth. We are a not-for-profit research organisation which is registered as a private company limited by guarantee and controlled by its Board.

Background on the Project

Satellite image analysis can be a complex and time consuming process. In the last half decade automatic image identification algorithms have drastically improved they do not yet reach the quality of results that can be derived from human operators. To increase the reliability of the automatic image recognition the algorithm need to be able to access thousands of annotated images to train on. While there are large deposits of annotated images (e.g. cats and human faces) taken from conventional terrestrial photography there is still very limited similarly annotated catalogues consisting of satellite imagery.

On 3 April 2014 ESA launched Sentinel 1, their flagship Copernicus Synthetic Aperture Radar (SAR) mission. Sentinel 1 is capable of acquiring 1Tb of data a day. This is a vast amount of data. New automatic image recognition techniques offer the capability to derive large quantities of valuable information which can be ingested into multiple applications via API. Currently there is no publically available SAR catalogue consisting of thousands of annotated images in which to train a high accuracy automatic image recognition algorithm.

Recently there have been great success stories using the power of the public to annotate large amounts of data not possible through a single person or organisation. Examples include Zooniverse a crowd sourcing company which made its fame with its Galaxy Zoo application by allowing the public to classify thousands of astronomy images. Using similar crowd sourcing techniques, it is possible to create a diverse training dataset for automatic image recognition.

The Satellite Application Catapult is in a unique position where it has access to the Sentinel 1 platform via its cloud computing facility CEMS. This represents a large opportunity to create SAR dedicated crowed sourcing platform to train and validate image recognition algorithms.

Student Specification

The Catapult is looking for enthusiastic and skilled students to design and develop and web based crowed sourcing application utilising the Catapult’s Sentinel 1 data access. Applicants will need to be numerate, have computing skill, be able to critically evaluate problems, suggest solutions and show initiative in a supervised R&D project. You must be eligible to work in the UK

Minimum Requirements:

  • Experience or an interest in geographical web based software and applications or experience in crowd sourcing projects

Preferred Additional Requirements:

Target courses: Physics, Remote Sensing, Engineering, Physical Geography, Mathematics and other similar courses

The Nitty Gritty

8 weeks fixed term contract to be agreed with successful candidate but nominally with a start date around 27 June which is also the SPIN student induction day at Harwell. Salary is £1,500 per calendar month. (guide only)

Closing Date for Applications: 15 April

Applications will be through the online form attaching a CV, before the closing date. They will be checked for eligibility and forwarded to the employer.

Apply for this SpIN opportunity

Fill out my online form.

Cookies on Catapult explained

To comply with EU directives we now provide detailed information about the cookies we use. To find out more about cookies on this site, what they do and how to remove them, see our information about cookies. Click OK to continue using this site.