Joseph Redmon: How computers learn to recognize objects instantly
Joseph Redmon works on the YOLO algorithm, which combines the simple face detection of your phone camera with a cloud-based AI -- in real time. Full bio
Double-click the English transcript below to play the video.
thought that getting a computer
between a cat and a dog
in the state of artificial intelligence.
greater than 99 percent accuracy.
put a label to that image --
thousands of other categories as well.
at the University of Washington,
computer vision models.
a prediction of dog or cat,
specific breed predictions.
of granularity we have now.
in image classification,
when we run our classifier
with a pretty similar prediction.
there is a malamute in the image,
we don't actually know that much
called object detection,
and try to find all of the objects,
when we run a detector on this image.
with our computer vision algorithms.
that there's a cat and a dog.
on top of computer vision,
or a robotic system,
of information that you want.
you can interact with the physical world.
on object detection,
to process a single image.
speed is so important in this domain,
to process an image.
it makes predictions,
by another factor of 10,
at five frames per second.
like this driving my car.
running in real time on my laptop.
as I move around the frame,
of changes in size,
on top of computer vision.
a thousand times faster.
object detection systems
on each of these regions,
detections in the image.
thousands of times over an image,
to produce detection.
to do all of detection for us.
and class probabilities simultaneously.
at an image thousands of times
the YOLO method of object detection.
we're not just limited to images;
that cat and dog,
and interact with each other.
like spoon and fork, bowl,
out into the audience
our threshold for detection a little bit,
out in the audience.
is happening in real time
object detection system,
already using this technology
like medicine, robotics.
of animals in Nairobi National Park
of this detection system.
free for anyone to use.
even more accessible and usable,
of model optimization,
running on a phone.
now we have a pretty powerful solution
and build something with it.
with access to this software,
will build with this technology.
ABOUT THE SPEAKERJoseph Redmon - Computer scientist
Joseph Redmon works on the YOLO algorithm, which combines the simple face detection of your phone camera with a cloud-based AI -- in real time.
Why you should listen
Computer scientist Joseph Redmon is working on the YOLO (You Only Look Once) algorithm, which has a simple goal: to deliver image recognition and object detection at a speed that would seem science-fictional only a few years ago. The algorithm looks like the simple face detection of a camera app but with the level complexity of systems like Google's Deep Mind Cloud Vision, using Convolutional Deep Neural Networks to crunch object detection in realtime. It's the kind of technology that will be embedded on all smartphones in the next few years.
Redmon is also internet-famous for his resume.
Joseph Redmon | Speaker | TED.com