))
How AI Imaging Is Transforming Satellite Imagery
Manage episode 297999652 series 2954151
Indhold leveret af Damien Deighan and Philipp Diesinger, Damien Deighan, and Philipp Diesinger. Alt podcastindhold inklusive episoder, grafik og podcastbeskrivelser uploades og leveres direkte af Damien Deighan and Philipp Diesinger, Damien Deighan, and Philipp Diesinger eller deres podcastplatformspartner. Hvis du mener, at nogen bruger dit ophavsretligt beskyttede værk uden din tilladelse, kan du følge processen beskrevet her https://da.player.fm/legal.
In this episode we discuss the rapidly developing field of Satellite Imaging.
Our guests on this show are Heidi Hurst & Jerry He.
They are two remarkable industry Data Scientists with a strong academic pedigree and experience in the field of Satellite Image Processing. Heidi is based in Washington DC and Jerry is based in New York.
Join us as they discuss their journey into Satellite Imaging and share with us the latest developments in this fascinating and evolving area of Data Science.
Episode Summary
- Why is satellite image processing such an exciting field?
- What data sources is satellite image data based on?
- What are the challenges in using satellite image data?
- Sensors used in satellite imaging
- Methods used in satellite imaging - Image Processing, Deep Learning, CNN
- The Socio-economic applications
- Industry Applications for Satellite Imaging - Agriculture, Supply Chain monitoring, Sales Prediction, Insurance
- The Future of Satellite Imaging
RESOURCES:
Cool Visual - One Hour of active Satellites orbiting Earth:
DOTA - https://captain-whu.github.io/DOTA/ - Open dataset for object detection in overhead imagery
COwC - https://gdo152.llnl.gov/cowc/ - Cars Overhead with Context - specific detection dataset for car counting algorithms
xView - http://xviewdataset.org/ - dataset put together by the National Geospatial Intelligence Agency for an object detection challenge, including some particularly rare classes
25 episoder
Del
