Spelling suggestions: "subject:"eomputer disision."" "subject:"eomputer decisision.""
231 |
MEMS computer vision and robotic manipulation systemSukardi, Henry 14 August 2015 (has links)
MEMS technology is a growing field that requires more automative tools to lower the cost of production. Current industry standards of tele-operated 3D manipulated MEMS parts to create new devices are labor intensive and expensive process. Using computer vision as a main feedback tool to recognize parts on chip, it is possible to program a close loop system to instruct a computer to pick and assemble parts on the chip without the aid of a user. To make this process a viable means, new chip designs, robotic systems and computer vision algorithms working along side with motion controllers have to be developed. / Graduate / 0548 / 0544 / 0771 / hsukardi@uvic.ca
|
232 |
Image feature matching using pairwise spatial constraintsNg, Ee Sin January 2012 (has links)
No description available.
|
233 |
Pinball: High-Speed Real-Time Tracking and PlayingMetcalf, Adam Unknown Date
No description available.
|
234 |
The Development of a Relative Point and a Relative Plane SLAM algorithmsKraut, Jay 24 August 2011 (has links)
There are many different algorithms that have been shown to solve the simultaneous localization and mapping (SLAM) problem depending on the type of input data. Many of these algorithms use some form of cumulative current position as a state variable and only store landmarks in their globally mapped form, discarding past data. This thesis takes a different approach in not using current position as a cumulative state variable and storing and using past data. Landmarks are mapped relative to each other in their untransformed states and use either three points or one plane to maintain translation and rotation invariance. The Relative algorithms can use both current and past data for accuracy purposes. Using this approach, the SLAM problem is solved by data structures and algorithms rather than probabilistic modeling.
The Relative algorithms are shown to be good solutions to the simulated SLAM problems tested in this thesis. In particular the Relative Point algorithm is shown to have a worst case computation complexity of O(nslogns). ns is the average quantity of points observed in a given observation and is not related to the total quantity of points on the map. The Relative Point algorithm is able to identify points with movement that is not correlated to the viewpoint at a low cost, and has comparable accuracy to a 6D no odometry Extended Kalman Filter.
|
235 |
Optimum illumination for machine vision using optical scatter dataVolcy, Jerry 12 1900 (has links)
No description available.
|
236 |
Outdoor tracking using computer vision, xenon strobe illumination and retro-reflective landmarksSchreiber, Michael J. 08 1900 (has links)
No description available.
|
237 |
Towards 3D vision from range images : an optimisation framework and parallel distributed networksZiqing Li, S. January 1991 (has links)
No description available.
|
238 |
A new sensor for robot arm and tool calibrationSimon, D. G. January 1998 (has links)
No description available.
|
239 |
The Development of a Relative Point and a Relative Plane SLAM algorithmsKraut, Jay 24 August 2011 (has links)
There are many different algorithms that have been shown to solve the simultaneous localization and mapping (SLAM) problem depending on the type of input data. Many of these algorithms use some form of cumulative current position as a state variable and only store landmarks in their globally mapped form, discarding past data. This thesis takes a different approach in not using current position as a cumulative state variable and storing and using past data. Landmarks are mapped relative to each other in their untransformed states and use either three points or one plane to maintain translation and rotation invariance. The Relative algorithms can use both current and past data for accuracy purposes. Using this approach, the SLAM problem is solved by data structures and algorithms rather than probabilistic modeling.
The Relative algorithms are shown to be good solutions to the simulated SLAM problems tested in this thesis. In particular the Relative Point algorithm is shown to have a worst case computation complexity of O(nslogns). ns is the average quantity of points observed in a given observation and is not related to the total quantity of points on the map. The Relative Point algorithm is able to identify points with movement that is not correlated to the viewpoint at a low cost, and has comparable accuracy to a 6D no odometry Extended Kalman Filter.
|
240 |
Stereoscopic line-scan imaging using rotational motionPetty, Richard Stephen January 1997 (has links)
No description available.
|
Page generated in 0.1083 seconds