Re:How Self-Driving Cars Work
by taneq on Monday December 26, 2016 @04:33AM
(#13257624)
I've been wondering why no self driving systems seem to use DTAM or similar methods. Realtime dense 3D reconstruction and camera localisation on commodity hardware seems perfect for the job.
[ Parent
| on HN ]
There is a big open research problem in the state of the art in visual SLAM (visual SLAM = SLAM from cameras), it doesn't work when the environment is moving (!!!).
Visual slam is still linear-algebra/geometric/keyframe based traditional computer vision (including variants that incorporate GPS/accelerometer info). I think the state of the art is stereo LSD-SLAM, but I could be wrong.
A great way to explain this to people would be to ask them if they've ever seen a panoramic photo glitch, and tell them that's what the car would be seeing most of the time (well, assuming anything is moving, like a car or a person or a piece of trash).