World Bank launches Open AI Challenge for Aerial Imagery of South Pacific

Disasters in the South Pacific are a reality. In the past 10 years, major Cyclones have seriously affected hundreds of islands across Fiji, Tonga, Vanuatu and Samoa to name a few; disrupting millions of lives and causing millions of dollars of damage. Many of the countries in the Pacific region are also exposed to other high risk disasters including earthquakes, tsunami, storm surge, volcanic eruptions, landslides and droughts, not to mention the growing threat of Climate Change.

What does all this have to do with Artificial Intelligence (AI)?

Aerial imagery is “Big Data” challenge. It can take hours and more often days to analyze aerial imagery following major disasters. This explains why the World Bank, WeRobotics and OpenAerialMap have just launched the Open AI Challenge focused on the use of artificial intelligence to automatically analyze aerial imagery in the South Pacific. More information on the challenge and how to participate and download the aerial imagery is available here

We'd be very grateful for your help in sharing this opportunity far and wide. 

Views: 987

Comment by Darrell Burkey on January 14, 2018 at 2:27am

Very interesting post. I'm wondering exactly what the expectations are of using AI in analyzing the aerial images? For example, AI might be able to count the number of buildings but is that type of knowledge helpful? Just counting things doesn't really tell you anything about the conditions of the item. Anyway, if you have any further info I would be very interested. Thanks.


Developer
Comment by John Arne Birkeland on January 14, 2018 at 2:33pm

As usual PR statements are dumbed down to a level where they contain no actual information. The AI mission criteria and data sets can be found here.

https://docs.google.com/document/d/16kKik2clGutKejU8uqZevNY6JALf4aV...

Quote from original link:

The following classifiers are required in order of priority:

  • Trees (counts and location of individual coconut trees)

    • Coconut trees
    • Banana trees
    • Papaya trees
    • Mango trees
  • Road type (size and surface type)
    • 2-way road vs. 1-lane road
    • Paved vs. dirt road

Being able to quantify the number of trees that serve as an important source of livelihood for local communities is essential. These trees and their locations can then be compared before and after major disasters to better understand just how much local agriculture and hence food security has been affected. This can directly inform and accelerate subsequent relief efforts. The focus on roads is also meant to help identify the impact of natural disasters on local transportation infrastructure and to inform how best to distribute aid across affected areas.

Comment by Darrell Burkey on January 14, 2018 at 11:27pm

Thanks for the additional info. Very interesting.

Comment

You need to be a member of DIY Drones to add comments!

Join DIY Drones

Groups

Season Two of the Trust Time Trial (T3) Contest 
A list of all T3 contests is here. The current round, the Vertical Horizontal one, is here

© 2018   Created by Chris Anderson.   Powered by

Badges  |  Report an Issue  |  Terms of Service