Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

22

MVA
2000

favoriteEmaildiscussreport

160views Computer Vision» more MVA 2000»

Self-Calibration from Optical Flow and Its Reliability Evaluation

13 years 5 months ago

Self-Calibration from Optical Flow and Its Reliability Evaluation

Download www.mva-org.jp

An algorithm is presented for 3-D reconstruction from optical flow observed by an uncalibrated camera. We show that by incorporating a statistical model of image noise, we can not only compute a statistically optimal shape but also evaluateits reliability in quantitative terms. We show real-image experimentsand discuss the effect of the "gauge" on the uncertainty description.

Kenichi Kanatani

Real-time Traffic

3-d Reconstruction | MVA 2000 | MVA 2007 | Optical Flow | Uncalibrated Camera |

claim paper

Related Content

» 3D reconstruction from uncalibratedcamera optical flow and its reliability evaluation

» Fundamental matrix from optical flow optimal computation and reliability evaluation

» Toward robust estimation of specular flow

» Reliable Estimation of Dense Optical Flow Fields with Large Displacements

» Strict control dependence and its effect on dynamic information flow analyses

» LISA Learning Domain Specific IsaRelations from the Web

» GLOW A global router for lowpower thermalreliable interconnect synthesis using photonic wa...

» Genetic algorithms for designing multihop lightwave network topologies

» Evaluation of an Adaptive Composite Gaussian Model in Video Surveillance

Post Info
More Details (n/a)

Added	01 Nov 2010
Updated	01 Nov 2010
Type	Conference
Year	2000
Where	MVA
Authors	Kenichi Kanatani

Comments (0)