The ARtillery Crater Analysis and Detection Engine (ARCADE) is an experimental computer vision application built using MATLAB. ARCADE scans satellite imagery for signs of artillery bombardment, geocodes artillery blast craters, and calculates the inbound trajectory of projectiles to help journalists and human rights investigators determine their origins of fire.
[Rudiment is no longer active – this website is an archive]
Destroyed buildings and infrastructure, temporary settlements, terrain disturbances and other signs of conflict can be seen in freely available satellite imagery. The ARtillery Crater Analysis and Detection Engine (ARCADE) is experimental computer vision software developed by Rudiment and the Centre for Visual Computing at the University of Bradford. ARCADE examines satellite imagery for signs of artillery bombardment, calculates the location of artillery craters, the inbound trajectory of projectiles to aid identification of their possible origins of fire. An early version of the tool that demonstrates the core capabilities is available here.
Figure 1: Automating the detection of artillery craters near Amvrosiivka, Donetsk Oblast, Ukraine, Image date: 14 September 2014. Imagery via Google © 2015 DigitalGlobe.
Why create ARCADE?
What is ARCADE and how does it work?
Does ARCADE work and what’s next?
Can I use or hack or contribute to ARCADE?
Acknowledgements
The ‘eye in the sky’ has created new opportunities for investigative reporting, human rights monitoring, documentation and advocacy. For example, the examination of satellite imagery for information suggestive of human rights violations has been performed successfully by civil society groups like Amnesty International. More specifically, investigators have sought to locate specific features in the imagery – terrain disturbances consistent with military emplacements, damage to human settlements and blast craters caused by artillery fire. It is this last class of feature that the ARCADE project is concerned with.
In 2015, investigative reporters Bellingcat and MapInvestigation analysed thousands of artillery craters visible in Google satellite imagery, as part of their exposé of alleged cross-border shelling from the Russian Federation into eastern Ukraine in July 2014. This built upon an approach pioneered by the American Association for the Advancement of Science (AAAS), which used similar techniques to evidence alleged shelling by the Sri Lankan Army into a Civilian Safety Zone in northeastern Sri Lanka in May 2009.
Bellingcat shared with us the full research method they used in their investigations. It is a digital version of in-field artillery crater analysis techniques described in United States Army Field Manuals. Rather than taking measurements from the actual blast crater to geolocate it and determine the angle of incoming fire, it is possible to perform the core aspects of this analysis upon the blast craters visible in satellite imagery.
Using GIS tools like Google Earth or ArcGIS, analysts must discover and geocode the each blast crater, before performing a trajectory analysis on it. The trajectory readings collected from the imagery must then be collated, and averaged out in order to more accurately determine the direction from which the artillery fire originated.
With thousands of potential blast craters any analyst doing this work will quickly find the task gruelling, repetitive and time consuming – three factors which increase the likelihood of fatigue and error. As more locations containing blast craters are found, and updated satellite imagery becomes available, the analysis must be repeated. Over time, the process also becomes a significant data management challenge.
All this this suggests there is high value in exploring new technology and methodological options. However, most off-the-shelf desktop technologies do not have the object recognition capabilities central to this task. Nor is there a readily available pool of technologists with experience in this area. Rudiment started ARCADE to address the challenges and explore whether key parts of the US Army blast crater analysis process, as used by Bellingcat and AAAS, could be automated whilst retaining comparable levels of precision and accuracy.
For this exploration phase, we have set ourselves five constraints:
The remainder of this page describes the tool we have created, how it functions, whether it works and what’s next.
ARCADE is a standalone MATLAB application which can be run on a computer running Windows.
It works by applying computer vision techniques to images drawn from Google Maps. Look at the Google satellite image below, to the left – it’s of a football field sized area in eastern Ukraine. Per the information contained in the US Army Field Manuals, we can see the image contains shapes consistent with “low-angle fuze quick craters” made by artillery shells such as those fired by Multiple Launch Rocket Systems (MLRS). There are other types of crater, but we focussed on this one. The process used by Bellingcat to geolocate and obtain trajectory information involves using a GIS tool to place a marker over the centre of the shape, and then rotating an arrow-shaped template over the blast crater until it matches the shape in the imagery. This creates data that can be extracted into a spreadsheet for further analysis.
Figure 2: Manual process of geolocating and obtain trajectory data from suspected blast craters near Amvrosiivka, Donetsk Oblast, Ukraine. Image date 14 September 2014. Source: Google ©2015 DigitalGlobe
ARCADE will examine the same imagery and work through equivalent steps to obtain similar data:
Figure 3: Automated process of geolocating and obtain trajectory data from suspected blast craters near Amvrosiivka, Donetsk Oblast, Ukraine. Image date 14 September 2014. Source: Google ©2015 DigitalGlobe
In more detail, the process used by ARCADE looks like this:
Each of these steps uses a spread of techniques to assist the process of analysis. In turn:
Rudiment and the Centre for Visual Computing at the University of Bradford are currently writing a full technical article about ARCADE, which will be published in due course.
ARCADE is a successful prototype that will successfully identify a blast crater, detect its edges, extract its features and export data that can be taken and plotted on a map. However, there are – as ever – caveats to this.
We have tested ARCADE on over 70 crater fields from eastern Ukraine, and the results are mixed. For example, ARCADE’s analysis of the bombardment at Savur Mohyla in Donetsk Oblast correctly makes positive identifications of a very large number of craters.
Figure 5: Output by ARCADE on crater field at Savur Mohyla, Donetsk Oblast, Ukraine. Image date 14 September 2014. Imagery via Google © 2015 CNES / Astrium, Cnes Spot Image, DigitalGlobe
In the segmented view below the overlap between ARCADE’s results (the white shapes) and the craters that Rudiment identified by eye (the pink dots) can be more clearly seen.
Figure 5: Segmented output of analysis by ARCADE on crater field at Savur Mohyla, Donetsk Oblast, Ukraine. Image date 14 September 2014. Imagery via Google © 2015 CNES / Astrium, Cnes Spot Image, DigitalGlobe
ARCADE can clearly correctly identify blast craters (true positives) but the rate of incorrect identification (false positives) is very high. The challenge here is to improve the part of ARCADE which defines what a crater is and is not. Variations in the data used to train ARCADE produce different results – some better, some worse.
During the development process, we learned a great deal and encountered numerous other challenges which will need to be addressed for ARCADE to move forward:
Despite the limitations this release of ARCADE is an important first step. We think it gives an alluring glimpse into the potential of computer vision to assist with investigative work. We hope that you do too and use it to kickstart the debate about the future toolsets investigators will need, and the types of skills and partnerships that we will need to create them.
We hope so! If you live and breath computer vision and want a challenge, we know ARCADE could be just that.
ARCADE’s source code and a standalone application are available on Github, along with detailed installation and use guidance. ARCADE’s source and compiled application is licensed under the BSD simplified license. To adapt it you will access to a recent copy of MATLAB.
Should the tool prove useful we plan to move it to a free and open source toolset based around OpenCV. If you’d like to help us do that, get in touch.
ARCADE has been made possible through the skills and imagination of Professor Hassan Ugail, Ali M. Bukar and Shelina Jilani from the Centre for Visual Computing at the University of Bradford, and draws heavily on the investigative work of Eliot Higgins and the team at Bellingcat. Rudiment is also deeply grateful for support for our work as a Small Innovation Project from the Yorkshire Innovation Fund.
Our exhibit shows the ups and downs of using computer vision algorithms to help journalists and human rights investigators evidence war crimes
Read this blog post...Rudiment is a research and development organisation founded in 2015 by human rights defenders specialised in the use of modern digital technologies. We experiment with ways to acquire, analyse and present information that open new possibilities for people investigating human rights violations, war crimes and abuses of power. We draw on techniques of open source intelligence and civic hacking to create the sort of resources, tools and approaches which have revolutionised government, humanitarian work and investigative journalism.