DG Launches SpaceNet, Opening Access to Hi-Res Satellite Imagery for Deep Learning Research

DigitalGlobe has recently launched SpaceNet, an online repository of satellite imagery and associated training data, for users to experiment with machine learning and deep learning algorithms. Spacenet has been launched as a collaboration between DigitalGlobe, CosmiQ Works, and NVIDIA, and is available as a public dataset on Amazon Web Services (AWS). As a first step, SpaceNet will contain DigitalGlobe’s high resolution multispectral imagery from their premier WorldView-2 satellite at its industry-leading full 8-band spectral resolution and over 200,000 curated building footbrints across Rio de Janeiro, Brazil. This is unprecedented: Never before has satellite imagery at such high resolution of 50 cm been released publicly with building annotations. The released dataset contains over 7000 images over Rio de Janeiro. The satellite imagery is being delivered in GeoTIFF format while the building footprints are in GeoJSON format.

spacenet

True color WV-2 high resolution imagery sample from the SpaceNet repository, along with corresponding building footprints. Source: NVIDIA

According to SpaceNet:

This dataset is being made public to advance the development of algorithms to automatically extract geometric features such as roads, building footprints, and points of interest using satellite imagery.

Scripts are already cropping up on GitHub for manipulating and using the satellite imagery data on SpaceNet: see code examples from Development Seed here and from CosmiQ Works here. NVIDIA has also released a detailed case study of analysis of SpaceNet data using their Deep Learning GPU Training System (DIGITS) platform, demonstrating the power and capability of GPU-based deep learning algorithms applied over high resolution satellite imagery. Application examples include detection of each building as a separate object and determining a bounding box around it, and semantic segmentation to partition the image into regions of pixels that can be given a common label, such as “building”, “forest”, “road”, or “water”.

SpaceNet plans a massive increase in both images and labeled features to be made available over the platform in the future. Incidentally, the name SpaceNet is inspired from ImageNet, a similar database of images created to help spur early advancements in computer vision.

To read more about the launch of SpaceNet, see coverage on GISCafeTechCrunch, MIT Technology Review, and Popular Science.

SpaceNet datasets can be accessed on AWS here.

 

Advertisements
This entry was posted in Uncategorized on by .

About WQ

I received my PhD (2013) in Remote Sensing, Earth and Space Science at the Dept. of Aerospace Engineering Sciences, University of Colorado, Boulder, USA, under a Fulbright fellowship. Currently, I'm an Assistant Professor in the Dept. of Space Science at Institute of Space Technology (IST), Islamabad, Pakistan, where I have been a founding member of the Geospatial Research & Education Lab (GREL). My general expertise is in Remote Sensing where I have worked with various remote sensing datasets through my career, while for my PhD thesis I specifically worked on Remote Sensing using SAR (Synthetic Aperture Radar) and Oceanography, working extensively on development of techniques to measure ocean surface currents from space-borne SAR intensity images and interferometric data. My research interests are: Remote sensing, Synthetic Aperture Radar (SAR) imagery and interferometric data processing & analysis, Visible/Infrared/High-resolution satellite image processing & analysis, Oceanography, Earth system study and modelling, LIDAR data processing and analysis, Scientific programming. I am a reviewer for IEEE Transactions on Geoscience & Remote Sensing, Forest Ecosystems, GIScience & Remote Sensing, Journal of African Earth Sciences, and Italian Journal of Agronomy. I am an alumnus of Pakistan National Physics Talent Contest (NPTC), an alumnus of the Lindau Nobel Laureate Meetings, a Fulbright alumnus, and the Pakistan National Point of Contact for Space Generation Advisory Council (SGAC). I was an invited speaker at the TEDxIslamabad event held in Nov., 2014. I've served as mentor in the NASA International Space App Challenge Islamabad events in April 2015 and April 2016.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s