R-G-B, near-infrared, infrared, RADAR

Detecting tree height with UP42 and LiveEO

Challenge

  • Accessing high-resolution stereoscopic imagery for smaller areas of interest (AOIs) to detect height profiles of trees

  • Generating digital elevation models from stereoscopic imagery with resolution large enough to determine tree heights

  • Scaling the tree height detection to cover critical parts of railway systems across countries

Solution

  • Fast and simple access to high-resolution optical stereoscopic imagery from the Airbus Pleiades satellite for a large amount of small AOIs with price transparency through UP42

Results

  • UP42 enabled LiveEO to determine the height of trees surrounding railways track.

  • LiveEO were able to scale up their solution to cover the critical parts of the railway system across the whole of Germany

Background

LiveEO is an award-winning, Berlin-based startup committed to improving life on Earth using technology in space. Their clients rely on high-resolution satellite observations of the planet to solve their unique infrastructural challenges. LiveEO´s mission is to bring space data into the business world.

From railways and powerlines to oil and gas pipelines, LiveEO is committed to delivering quick and accurate answers tailored to their clients’ needs.

One such need involved mapping railway tracks across Germany and measuring the height of trees that line them, in order to assess the risk of trees falling on the tracks. The German railway system consists of 33000 kilometers of tracks - which need to be monitored. Between 2015 and 2017 alone there were over 830 train collisions with vegetation caused by storms. For example, storms Xavier and Herwart caused 13000 train cancellations and affected 2 million people. The damage for each of those storms was multiple million euros. Deutsche Bahn currently spends 125 million euro on vegetation management each year to reduce those damages. However, due to manual processes and the sheer size of the railway system, it is hard to reduce those damages.

Now, with the help of space technology and LiveEO, Deutsche Bahn is tackling the problem with a unique data set that helps managers as well as inspection teams.

Prior to working with us, LiveEO analyzed over 100000 kilometers of train infrastructure around the globe. They successfully mapped all the vegetation surrounding railway track systems in Germany using optical data from ESA’s Sentinel-2 satellite and commercial data sets. They also wrote a tree height detection algorithm that would process the data, allowing them to measure the height of trees surrounding the mapped rail tracks.

Challenge

Whilst the analysis already carried out by LiveEO was helpful in managing such complex monitoring problems — a more precise assessment of tree height was needed for infrastructure operators to distinguish between low-risk trees that are around 10 meters tall, and high-risk trees of around 5 meters tall.

However, the availability and resolution of radar data sources with the required wavelengths that LiveEO had access to was too low to accurately detect the height of trees.

This meant that while they were able to determine tree height profiles on test sites using historical data, it was not possible to determine the height of something as small as a single tree with recent data distributed over countries.

LiveEO wanted to use high-resolution optical stereoscopic satellite imagery to accurately measure the trees surrounding the tracks.

They faced the challenge that this kind of high-quality data is often difficult to access, usually requiring significant infrastructural efforts. That’s where we came in.

Solution

We provided LiveEO with optical images of the planet taken by Airbus’ Pleiades satellite.

The Pleiades satellite constellation is comprised of two very high-resolution optical Earth-imaging satellites that provide coverage of the planet with a repeat cycle of 26 days.

This high-resolution satellite data was in the form of stereoscopic images, allowing LiveEO to compare and derive height profiles of trees from it.

Results

We enabled LiveEO to easily access high-resolution stereoscopic optical imagery from Airbus’ Pleiades satellite. As a result, LiveEO can run its tree height detection algorithm, generate a digital surface model, and scale up their analysis to cover the whole of Germany and beyond.

LiveEO now provides its clients with accurate tree height measurements that have a real-world impact when analyzing risk near railway tracks. Being able to accurately detect tree height near railway lines improves safety, identifies high and low-risk trees and reduces the cost of tree clearing. Operators such as Deutsche Bahn can now save around 25 percent of their operational expenses by improving efficiency as a result of such analysis.

We continue to be an integral part of LiveEO’s mission to solve infrastructural problems on Earth, from space. Our role in powering data processing pipelines that can be relied on - leaves room for LiveEO to focus on drawing value from the UP42 platform and provide answers to their clients.

Ready to get started?

Create your first workflow with 10,000 free credits, no credit card required. Questions? Check out our frequently asked questions.