New algorithm improves robot vision
December 7, 2005
Except in fanciful movies like 2003's The Matrix Revolutions, where fearsome squid-like robots maneuvered with incredible ease, most robots are too clumsy to move around obstacles at high speeds. This is true in large part because they have trouble judging in the images they "see" just how far ahead obstacles are. This week, however, Stanford computer scientists will unveil a machine vision algorithm that gives robots the ability to approximate distances from single still images.
"Many people have said that depth estimation from a single monocular image is impossible," says computer science Assistant Professor Andrew Ng, who will present a paper on his research at the Neural Information Processing Systems Conference in Vancouver Dec. 5-8. "I think this work shows that in practical problems, monocular depth estimation not only works well, but can also be very useful."
With substantial sensor arrays and considerable investment, robots are gaining the ability to navigate adequately. Stanley, the Stanford robot car that drove a desert course in the DARPA Grand Challenge this past October, used lasers and radar as well as a video camera to scan the road ahead. Using the work of Ng and his students, robots that are too small to carry many sensors or that must be built cheaply could navigate with just one video camera. In fact, using a simplified version of the algorithm, Ng has enabled a radio-controlled car to drive autonomously for several minutes through a cluttered, wooded area before crashing.
Inferring depth
To give robots depth perception, Ng and graduate students Ashutosh Saxena and Sung H. Chung designed software capable of learning to spot certain depth cues in still images. The cues include variations in texture (surfaces that appear detailed are more likely to be close), edges (lines that appear to be converging, such as the sides of a path, indicate increasing distance) and haze (objects that appear hazy are likely farther).
To analyze such cues as thoroughly as possible, the software breaks images into sections and analyzes them both individually and in relationship to neighboring sections. This allows the software to infer how objects in the image appear relative to each other. The software also looks for cues in the image at varying levels of magnification to ensure that it doesn't miss details or prevailing trends—literally missing the forest for the trees.
Using the Stanford algorithm, robots were able to judge distances in indoor and outdoor locations with an average error of about 35 percent—in other words, a tree that is actually 30 feet away would be perceived as being between 20 and 40 feet away. A robot moving at 20 miles per hour and judging distances from video frames 10 times a second has ample time to adjust its path even with this uncertainty. Ng points out that compared to traditional stereo vision algorithms—ones that use two cameras and triangulation to infer depth—the new software was able to reliably detect obstacles five to 10 times farther away.
"The difficulty of getting visual depth perception to work at large distances has been a major barrier to getting robots to move and to navigate at high speeds," Ng says. "I'd like to build an aircraft that can fly through a forest, flying under the tree canopy and dodging around trees." Of course, that brings to mind another movie image: that of the airborne chase scene through the forest on the Ewok planet in Return of the Jedi. Ng wants to take that idea out of the realm of fiction and make it a reality.
Source: Stanford University
-
Robots could improve everyday life, do chores
Sep 21, 2010 |
5 / 5 (3) |
0
-
Stanford researchers developing 3-D camera with 12,616 lenses
Mar 19, 2008 |
4.5 / 5 (78) |
7
-
Stanford site advances science of turning 2-D images into 3-D models
Jan 23, 2008 |
4.5 / 5 (22) |
4
-
Engineers Develop Undetectable Means Of Measuring Speed, Motion
Mar 30, 2005 |
3.7 / 5 (3) |
0
-
Robot reconnoiters uncharted terrain
Feb 01, 2012 |
5 / 5 (1) |
0
-
Engineers build first sub-10-nm carbon nanotube transistor
Feb 01, 2012 |
4.9 / 5 (30) |
30
-
Something old, something new: Evolution and the structural divergence of duplicate genes
Jan 31, 2012 |
4.6 / 5 (7) |
1
-
The hidden nanoworld of ice crystals: Revealing the dynamic behavior of quasi-liquid layers
Jan 30, 2012 |
5 / 5 (3) |
1
-
Stock market network reveals investor clustering
Jan 27, 2012 |
3.9 / 5 (23) |
8
-
Of microchemistry and molecules: Electronic microfluidic device synthesizes biocompatible probes
Jan 26, 2012 |
5 / 5 (1) |
0
More news stories
Sony's Hirai refuses to abandon dire TV business
Struggling Japanese entertainment giant Sony will not abandon its cash-bleeding television business, its incoming CEO says, but he acknowledges tough decisions lie ahead including over redundancies.
6 minutes ago |
not rated yet |
0
New error-correcting codes guarantee the fastest possible rate of data transmission
Error-correcting codes are one of the triumphs of the digital age. Theyre a way of encoding information so that it can be transmitted across a communication channel such as an optical fiber o ...
Technology / Computer Sciences
2 hours ago |
5 / 5 (2) |
2
|
Small modular reactor design could be a 'SUPERSTAR'
(PhysOrg.com) -- Though most of today's nuclear reactors are cooled by water, we've long known that there are alternatives; in fact, the world's first nuclear-powered electricity in 1951 came from a reactor ...
Technology / Energy & Green Tech
2 hours ago |
5 / 5 (4) |
7
|
Advanced power-grid model finds low-cost, low-carbon future in West
(PhysOrg.com) -- The least expensive way for the Western U.S. to reduce greenhouse gas emissions enough to help prevent the worst consequences of global warming is to replace coal with renewable and other ...
Technology / Energy & Green Tech
2 hours ago |
5 / 5 (1) |
3
|
Engineering images bring life to submerged city
(PhysOrg.com) -- Photo-realistic 3D mapping and digital reconstruction of an ancient underwater city in Greece have earned a team from the University of Sydney's Faculty of Engineering and Information Technologies ...
1 hour ago |
not rated yet |
1
The power of estrogen -- male snakes attract other males
A new study has shown that boosting the estrogen levels of male garter snakes causes them to secrete the same pheromones that females use to attract suitors, and turned the males into just about the sexiest ...
Could Venus be shifting gear?
(PhysOrg.com) -- ESAs Venus Express spacecraft has discovered that our cloud-covered neighbour spins a little slower than previously measured. Peering through the dense atmosphere in the infrared, the ...
Experts reveal how plants don't get sunburn
(PhysOrg.com) -- Experts at the University of Glasgow have discovered how plants survive the harmful rays of the sun.
Team isolates nerve cells involved in storing long term memory and gene proteins associated with them
(Medical Xpress) -- A research team in Taiwan has succeeded in isolating two nerve cells in fruit fly brains that are believed to be the major players in allowing for the formation of long term memories. Furthermore, ...
Fool's gold may prove an unlikely alternative to overexploited catalytic materials
Catalytic materials, which lower the energy barriers for chemical reactions, are used in everything from the commercial production of chemicals to catalytic converters in car engines. However, with current catalytic materials ...
SLAC, Stanford team focuses on high-energy electrons to treat cancer
Accelerator physicists at SLAC and cancer specialists from Stanford are working on a new technology that could dramatically reduce the time needed for cancer radiation treatments. The team ran an initial experiment ...