Re:Listening for illegal logging chainsaws using TensorFlow
by tony_cannistra on Saturday March 24, 2018 @03:59PM
(#16668564)
Planet does not image the ocean in its entirety due to the difficulty in geo-referencing (pre-user imagery processing pipelines use ground control points, usually just shiny objects with a known location, to locate the image on the earth, and this is hard in the ocean), but they do image focal regions for purposes similar to those you mention (vessel identification + tracking). I'd also imagine this choice has something to do with preserving satellite operational lifespan (can turn cameras off when not being used).
Re:Listening for illegal logging chainsaws using TensorFlow
by ada1981 on Saturday March 24, 2018 @08:36AM
(#16666302)
I can ask, but I assume so. The guy I spoke with was doing things like algorthmically measuring shadow angles on crude oil storage tank covers to determine supply stocks and then selling that data to commodities traders. They were able to get incredible detail along with really robust processing of huge datasets.
I'm asking because Sea Shepherd could not continue an anti-whaling campaign because they were technologically overmatched: http://www.themercury.com.au/news/politics/sea-shepherd-anno...