Distributed Computing to help in search operations

[socaldmax]

Originally Posted by hellosailor

socal-
" I don't think it would be too hard to write some software that could pick out an object the size of a boat or life raft from a predominantly dark background."
The problem is way more complex than "white on black". Heck, WIRED ran a photo in 2013 or 2014...someone noticed a rather large construction area in China, and for months they were trying to figure out what it was. AFAIK no one ever did, and that's an image of a large ground site or facility. You couldn't tell if there were ditches or buildings--both look alike depending on the lighting angle. Irregular objects at sea, versus whitecaps and reflections? Granted the available images are getting better and better (higher resolution) and sometimes multi-spectral are available (rarely to civilians), but the folks who really have experience with this? Are still military photo analysis intelligence folks. And their first rule is, understandably, don't let anyone know what their capabilities are. So...you'd probably have to try someplace like the JPL, where they have had great image analysis programmers, who might be allowed to do pro bono work. Anyone can program--but really sharp programmers? Not so easy to find! And the USCG's budget for anything, is simply one more thing they don't have the funds to search for. [sic]

Take a look at the Airbus link from shaktisgurl. There are images in there showing docklines clearly visible in the photos, among other details.

I know that there were a number of satellites capable of detecting a sub periscope wake (very small, since it's only a 5" dia. tube traveling at 5 knots or less) back in the early 80's. We had to run a satellite vulnerability program that calculated the time periods where there would be no satellites overhead and we could safely come to persicope depth based on ephemeris data on all of them. There were days at a time when you only had 1 or 2 30 minute time periods where you weren't visible that day. This was back in '84-'89, so you can imagine how many more satellites there are now and how much higher resolution they are.

Pleiades 1A and 1B alone cover 1,000,000km2 per day each, with a resolution of 70cm and an 800km ground strip. Each one passes over the same path 12 hrs apart.

[Pie seas]

Individual knowledge is limited, collective knowledge and effort is compound. Go for it. There are thousands of little bit of help available if the software is available. Keep asking the right questions. Thank you.

[ShaktiGurl]

Worldview-3 from DG is 31cm (pan sharpened multispectral) and commercially available. It's quite nice to work with and probably my favorite imagery right now.

It is NOT the government agencies doing all the R&D for image processing. They actually use a lot of COTS and contract custom solutions out to companies such as DigitalGlobe, Esri, Erdas, BAE, Harris, Exelis and so on. Much of the same technology used at NGA is available commercially and used by commercial, federal and educational institutions all over the world.

The distributed/cloud based processing is the new focus of many agencies. But there are also several players in the field. I'm not a nay-sayer at all because I see it coming! I'm the tech support person assisting the users of these systems. At least the software end of it for our solution.

[socaldmax]

Originally Posted by Pirate1221

SOCAL---

Don't let the naysayers and "Debbie-Downers" on here discourage you. I think it sounds like an awesome project. Enough time, desire, and effort, I'm sure you can make it happen!! Wish I had the particular talents needed to help!!

Always here for encouragement, though!!

Thank you!

It looks like a number of companies already offer that type of maritime vessel search service, but I have no idea how expensive it is, probably very expensive. I have no doubt that there's some very bright programmer out there who is capable and willing to do something similar in the distributed computing arena, so the computing burden doesn't fall on one company.

The Folding@Home protein folding project headed up by Stanford (I mistakenly posted Berkeley earlier) is an amazing example of distributed computing. They actually wrote software that could auto detect your CPU type, your software version, and your graphics card make and model then it would install the customized version of the software capable of extracting the maximum power out of your CPU and GPU (my $300 graphics card was actually capable of rendering about 2.5x the work units of my Intel i7 water cooled CPU overclocked to 5GHz due to the parallel GPU design used.)

This was in addition to the server's ability to track all Work Units assigned to hundreds of thousands of volunteers and reassemble the data when returned, and reassign Work Units that had been assigned but never completed by people who dropped out, etc.

Lots of possible avenues, a number of ways to approach the problem.