Andrew Yee[_1_]
July 12th 07, 03:16 AM
Public Affairs
University of Toronto
Toronto, Canada
June 27, 2007
Computer program makes night sky searchable
Technology will assist amateurs, as well as professionals
By Sara Franca
Computer science PhD candidate Dustin Lang has embarked on his own Star Trek
as part of astronometry.net, a collaboration between computer scientists at
U of T and astronomers at New York University.
Under the tagline Making the Sky Searchable, Lang and fellow graduate
student Keir Mierle have put together a system that takes an image of the
night sky and figures out which stars the image contains. The goal of the
project, a concept originated by Lang's supervisor, Professor Sam Roweis, is
to apply cutting-edge machine learning and computer vision ideas to huge
astronomical data sets.
"We call it a blind astronometry solver," Lang explained. "It's a bit like
going utside on a dark night and trying to find the constellations, except
we're trying to recognize images that come from all kinds of cameras,
amateur telescopes, large ground-based telescopes and space telescopes such
as the Hubble Space Telescope.
"Some of the images we are trying to solve cover less than a millionth of
the area of the sky -- about 10 per cent of the size of the full moon."
When asked what he enjoys most about the project, Lang said, "Working with
astronomers is great. They deal with extremely small and extremely large
things, so they get to be really good at "order-of-magnitude" thinking: Is
this process going to take a minute, an hour or a week? Do we need 10, 100
or 1,000 computers to solve this problem?"
On the technical side, because the group is processing information about a
billion stars, Lang noted, "We have to ensure that everything we do is done
efficiently ... the project requires a lot of tricky technical engineering,
which I find fun." He added, "And, of course, I get to look at a lot of
beautiful pictures of the sky."
Astonometry.net has significant implications for both professional and
amateur astronomers, since, said Lang, "Amateur astronomers can take great
pictures but they rarely record where their telescopes are pointing -- we
can figure out exactly where the image came from and combine images into a
high-resolution picture of the sky that is always being updated.
Professional astronomers can use this data to look for transient events like
comets, supernovae -- things an amateur astronomer may have taken a picture
of without even knowing it."
What's more, Lang explained, "observatories around the world have large
archives of photographic plates, some going back to the early 1800s. These
collections are being scanned to make them available digitally; if
astronomers could easily tap into these images, they would have a much
longer history to look for changes over time."
This project is also helpful in correcting possible telescope errors; the
system can check to make sure information recorded by telescopes is correct
and recover images where the telescope information was wrong.
Current plans for the project include making the system more robust,
flexible and fast, creating a way of incorporating new images to make a map
of the sky that is updated and improved as people add new images to it.
There are groups interested in hooking the system up to new telescopes that
are being built and other astronomers hoping to use it in their own
research.
Lang is enthusiastic about these possibilities and is pleased that while the
project is "geared towards professional astronomers, we'll end up producing
a system that should be of interest to amateur astronomers -- and anyone who
has looked up at the sky and wondered ... ."
University of Toronto
Toronto, Canada
June 27, 2007
Computer program makes night sky searchable
Technology will assist amateurs, as well as professionals
By Sara Franca
Computer science PhD candidate Dustin Lang has embarked on his own Star Trek
as part of astronometry.net, a collaboration between computer scientists at
U of T and astronomers at New York University.
Under the tagline Making the Sky Searchable, Lang and fellow graduate
student Keir Mierle have put together a system that takes an image of the
night sky and figures out which stars the image contains. The goal of the
project, a concept originated by Lang's supervisor, Professor Sam Roweis, is
to apply cutting-edge machine learning and computer vision ideas to huge
astronomical data sets.
"We call it a blind astronometry solver," Lang explained. "It's a bit like
going utside on a dark night and trying to find the constellations, except
we're trying to recognize images that come from all kinds of cameras,
amateur telescopes, large ground-based telescopes and space telescopes such
as the Hubble Space Telescope.
"Some of the images we are trying to solve cover less than a millionth of
the area of the sky -- about 10 per cent of the size of the full moon."
When asked what he enjoys most about the project, Lang said, "Working with
astronomers is great. They deal with extremely small and extremely large
things, so they get to be really good at "order-of-magnitude" thinking: Is
this process going to take a minute, an hour or a week? Do we need 10, 100
or 1,000 computers to solve this problem?"
On the technical side, because the group is processing information about a
billion stars, Lang noted, "We have to ensure that everything we do is done
efficiently ... the project requires a lot of tricky technical engineering,
which I find fun." He added, "And, of course, I get to look at a lot of
beautiful pictures of the sky."
Astonometry.net has significant implications for both professional and
amateur astronomers, since, said Lang, "Amateur astronomers can take great
pictures but they rarely record where their telescopes are pointing -- we
can figure out exactly where the image came from and combine images into a
high-resolution picture of the sky that is always being updated.
Professional astronomers can use this data to look for transient events like
comets, supernovae -- things an amateur astronomer may have taken a picture
of without even knowing it."
What's more, Lang explained, "observatories around the world have large
archives of photographic plates, some going back to the early 1800s. These
collections are being scanned to make them available digitally; if
astronomers could easily tap into these images, they would have a much
longer history to look for changes over time."
This project is also helpful in correcting possible telescope errors; the
system can check to make sure information recorded by telescopes is correct
and recover images where the telescope information was wrong.
Current plans for the project include making the system more robust,
flexible and fast, creating a way of incorporating new images to make a map
of the sky that is updated and improved as people add new images to it.
There are groups interested in hooking the system up to new telescopes that
are being built and other astronomers hoping to use it in their own
research.
Lang is enthusiastic about these possibilities and is pleased that while the
project is "geared towards professional astronomers, we'll end up producing
a system that should be of interest to amateur astronomers -- and anyone who
has looked up at the sky and wondered ... ."