Stevens Institute of Technology

Amaury Gutiérrez

Damage Assesment

• Economic impact can be calculated
• Urban Resilience Planning

Croudsourcing 

Mexican communities are known to be resilient against natural dissasters 

We can manually annotate images using croudsourcing

Images taken from drones can be then automatically classified, to determine the level of damage in public infrastructure

Deep Learning 

Deep Learning algorithms are know to need a lot of training data to work

At least +5000 tagged images are needed

Deep Learning 

Best Case

The available information from public sources is enough

Students can help to manually tag the images

Worse Case

Images can be extracted from the web using a crawler

Image can be tagged using crowdsourcing or services like Amazon Turk

Scenarios

Manual Tagging

Automatic Damage Assesment

We would be able to categorise previously unseen images with an automatic pipeline.

References

Nazr-CNN: Object Detection and Fine-Grained Classification in Crowdsourced UAV Images N. Attari and F. Ofli and M. Awad and J. Lucas and S. Chawla Qatar Computing Reserach Institute Hamad bin Khalifa University {nattari, fofli, mawad, jlucas, schawla}@qf.org.qa

https://www.mapbox.com/blog/jakarta-flooding-map/