Geo AI

GeoAI is where geospatial technology, imagery and artificial intelligence converge. Orbica has developed algorithms that can detect and classify features with a high degree of accuracy and speed, revolutionising traditional methods. Building outlines, trees, roads and waterbodies are just the beginning: our algorithms can be trained to detect and classify any feature on the earth’s surface. The possibilities are endless.

  • Geo AI Case Study 1

Cs Geoai Randd Earth Observation Bw

It’s amazing to have 24/7 imagery of the earth, right?

Cs Geoai Randd Google Earth

Yip, it’s great! The problem is that it’s impossible to get real-time, useful information from that imagery using current geospatial practices.

Cs Geo Ai Randd Venn2

So, we wondered, what would happen if we combined geospatial technology and artificial intelligence to automate feature extraction and classification?

Cs Geo Ai Randd Process Extract Features2

Our inquisitive minds set to work and we did it! This is how it works…

Cs Geoai Randd Rivers Gif

And this is what we can do with water bodies...

Cs Geoai Randd Building Outlines Gif

Building outlines...

Cs Geoai Randd Roads Gif

And roads.

Cs Geoai Randd The Future

And there’s much more. Welcome to the future of GeoAI.

Nzsea Awards

Did we mention that we won the Technical Excellence category at the 2018 NZSEA awards with GeoAI? Just thought we'd drop it in there...

  • Geo AI Case Study 1

  • Project:

    Automated feature extraction and classification

  • Client:

    Research and development

  • Objective:

    To automate traditional extraction and classification of features such as waterbodies, roads, forestry, gravel and building outlines using an artificial intelligence deep learning algorithm.

  • Achievement:

    Orbica’s algorithm extracts and classifies – with a high degree of accuracy and speed – building outlines, roads, forestry and surface water types from 3-band imagery from any source – it doesn’t require multi-spectral. It can adapt to any other natural or man-made feature and has fantastic applications for environmental management, Civil Defence disaster management, change reporting and compliance. Using satellite or drone imagery – rather than traditional aerial imagery - significantly reduces carbon emissions.

  • GeoAI Case Study 2

Cs Tk Video Still
Play

Orbica automates build progress reporting for thyssenkrupp in Germany.

  • GeoAI Case Study 2

  • Project:

    Build progress reporting using GeoAI

  • Client:

    thyssenkrupp Industrial Solutions

  • Objective:

    To automate traditional/manual build progress reporting processes using Orbica’s deep learning feature detection and classification algorithm.

  • Achievement:

    Orbica won the Thyssenkrupp Industrial Solutions Drone Analytics Challenge and People’s Choice award at Beyond Conventions, Germany, in February 2018 for its proposal to automate build progress reporting using GeoAI.Orbica proposed to use drone-collected imagery to build 3D point-cloud models that would then be processed through our feature extraction and classification deep learning algorithm. Results would then be compared to previous results to determine progress.Orbica is currently progressing this solution with Thyssenkrupp.