University of Cambridge > Talks.cam > CEDSG-AI4ER > Using Deep Learning to Count Albatrosses from Space

Using Deep Learning to Count Albatrosses from Space

Add to your list(s) Download to your calendar using vCal

  • UserEllie Bowler, University of East Anglia, British Antarctic Survey
  • ClockTuesday 25 February 2020, 12:00-13:15
  • HouseBullard Lab, Seminar Room.

If you have a question about this talk, please contact Jonathan Rosser.

Chair: Emily Shuckburgh Abstract: In this project we aim to automate the detection of Wandering Albatrosses in super high resolution satellite imagery (DigitalGlobe’s WorldView-3), using state of the art deep learning approaches. We train a convolutional neural network to classify and detect potential albatrosses, achieving accuracy values of approximately 80% on the test set. By analysing the agreement between manually generated labels, we show that these results are in fact in line with human performance. We hope that the methods will streamline the analysis of WorldView-3 imagery, allowing more frequent monitoring of a species which is of high conservation concern.

This talk is part of the CEDSG-AI4ER series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity