Marine litter is a huge problem with lots of statistics that boggle the mind. Most people will also have heard of the North Pacific Gyre, or rather, the Great Pacific Garbage Patch. It occupies a relatively stationary area that is twice the size of Texas. What we are trying to do with The Plastic Drive is raise awareness about the problem and record data on beach litter in a scientifically useful way such that it can be fed into the relevant models (current understanding of how litter moves around at sea is still rather crude).
To help put some method into the madness we are supported by Kayleigh Wyles from Plymouth Marine Laboratory and, from Imperial College, Michael Lange (HPC), Erik Van Sebille (Ocean Circulation), and Stefan Leutenegger (Dyson lab).
To increase coverage and efficiency we figured we could use drones to map beaches & strandlines and process the imagery with some of the fancy deep nets that are all the rage these days. Hence a plan was formed and a UK version of the drive planned late summer. To test the basic data collection workflow we bought a second hand Canon SX260 on eBay, installed CHDK, strapped it to a quad and started doing some flights. Data is processed with DroneDeploy. Every area we fly we also survey manually and that way build up some data and experience as to the kind of things you find and would want to detect from the imagery. We know the camera is not great but its cheap and good enough for a baseline.
We've only just started with two outings so far, a third one planned. But as we are trying to raise awareness and get people involved I thought it useful to post here in case anybody has done similar things or wants to help out.
Full writeup can be found at: https://dirkgorissen.com/2016/07/12/marine-litter-mapping/ and you can follow progress @ThePlasticDrive.
Comments
@Hein, thanks!
@Thomas, to answer your questions:
1) Currently we are mapping what we are picking. So that means just a couple 100m which can be flown in a few minutes. Picking takes much (!) longer. Eventually much larger stretches can be just flown and the imagery analysed offline.
2) Not settled on something final but this looks like the best so far http://www.marinedebris.engr.uga.edu/
3) Currently just a handful of us doing this in spare time though you will find local groups cleaning up beaches all over the world. As always with these things they depend on people willing to contribute time and resources. I would love this to be a long term sustainable thing though its still too early days to say where it will go. That is a much harder problem :)
That's a very clever application!
There are a few components of what your doing that I'm interested in, would you be able to describe these parts a bit more?
- I assume you're doing the garbage detection manually. How long does it take to 'map' the two initial projects? Have you considered or found a way to auto map the garbage content?
- What service are you using to input the information for a day, or user observations? Is it Google Forms or some other service provider? I know of some apps that operate online and offline, but they are rather expensive and not accessible to anyone.
- How do you expect this initiative to carry on? Through community volunteers, already existing community organizations, commercially...?