Fujitsu announces 3D image recognition chip for robots
By Donald Melanson 
posted Sep 12th 2007 12:11PM
posted Sep 12th 2007 12:11PM
Fujitsu looks to be doing its part to keep robots well aware of their surroundings, today announcing a new 3D image recognition chip that promises an array of benefits, although it sadly doesn't have a robot to go along with it. Still, the company doesn't seem to think it'll have much trouble finding suitable bots for it, with its small size and low power consumption making it ideal for small, household robots in addition to those of the larger, more terrifying variety. Apparently, the entire system works in real time, and is said to be five times more efficient in recognizing images than similar system. While the chip has yet to find its way into an actual robot, that'll apparently happen before too long, with Fujitsu promising to put that final touch on the experiment before year's end.
[Via Impress]
[Via Impress]
Can anyone else see the start of robot armys, lets just hope they do a better job at spotting the real enemy than humans.
"Humans detected...activate countermeasures..."
I, for one, welcome our 3D image recognising chip equipped robot overlords.
hehe cant resist saying that..
anyway this may find some use in digital cameras apart from robots... i guess
You say "3D image recognition chip for robots", I say Terminators targeting system made a reality. Thanks alot assholes.
ED-209: "Please put down your iWeapon. You have 20 seconds to comply."
Who wants to bet that this chip can't recognize you if you so much as wrinkle your clothes?
Or is this for the government to track all of us? Government tracking based on 3-d recognition...I'm gaining 50 lbs and then losing 25 then losing another 45 to constantly change my body shape so I can't be tracked
But won't they get confused if they run into Number Six?
why are those people covered with blue and red catapillers
So now they'll know what you look like before they kill you? Excellent....
This isn't so much a 3D Recognition chip as it is a 3D Preprocessor chip. All it's doing it generating left-right (and probably right-left) difference maps and then edge detecting in that data to tag objects in the field of view. There's no actual recognition of what's been found in the result, so the chip wouldn't know whether it's seeing a vase, a human or a shark with lasers. This isn't really anything new, since there's been a few FPGA-based solutions doing this in hardware for years, usually with Firewire cameras. Probably just a bad translation of the original Japanese release.