3D Crisis Mapping in the Cloud.

"The holy grail? Combining crowdsourcing with machine learning for real-time feature detection of disaster damage
in 3D point clouds rendered in real-time via airborne UAVs surveying a disaster site." Dr Partick Meier

Durbar Square neighbourhood in downtown Kathmandu after the earthquake on 25th April 2015.

1. UAVs from our partner HAZON Solutions.

HAZON Solutions is the leading US developer of small UAV inspection service operations, capability development, training, safety and testing programs. They get the cameras into the sky and the imagery into our systems.

HAZON Soltions UAV in action

2. High resolution 3D point cloud generation.

Imagery from our UAV network is processed into 3D models. We're working across a variety of disciplines to make 3D imagery available through our platform within a short enough timeframe and with the necessary detail for disaster damage assessment.


3. Crowdsourced 3D annotation platform.

We're building the platform to crowdsource the annotation of 3D imagery. From UN officials to altruistic individuals around the world we're harnessing the crowd to do damage assessment in 3D. Disaster tourism that helps not hinders.

Oculus Rift 3D headset

4. Machine learning 3D damage assessment.

Our aim is to take features traced manually by humans as training data to develop machine learning classifiers that can automatically identify these features in future scenarios. This has already happened in 2D (Haiti rubble assessment), it's just a matter of time.

Machine learning of damage assessment patterns