Noise sensitivity analysis of statistically consistent optimal structure from motion

F. C. Park, Byungsoo Park, Munsang Kim, Bhubaneswar Mishra

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a noise sensitivity analysis of the differential optimal structure from motion problem. Given optical flow measurements for a set of feature points, we formulate a least squares cost function based on a more reasonable additive isotropic model of measurement noise, normalized by depth, that also leads to statistically consistent estimates of the shape and motion parameters. A cyclic coordinate descent algorithm is developed, and its performance examined through experiments.

Original languageEnglish (US)
Title of host publication2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Pages3698-3703
Number of pages6
Volume4
StatePublished - 2004
Event2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Sendai, Japan
Duration: Sep 28 2004Oct 2 2004

Other

Other2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
CountryJapan
CitySendai
Period9/28/0410/2/04

Fingerprint

Optical flows
Flow measurement
Cost functions
Sensitivity analysis
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Park, F. C., Park, B., Kim, M., & Mishra, B. (2004). Noise sensitivity analysis of statistically consistent optimal structure from motion. In 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (Vol. 4, pp. 3698-3703). [SP1-L1]

Noise sensitivity analysis of statistically consistent optimal structure from motion. / Park, F. C.; Park, Byungsoo; Kim, Munsang; Mishra, Bhubaneswar.

2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vol. 4 2004. p. 3698-3703 SP1-L1.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Park, FC, Park, B, Kim, M & Mishra, B 2004, Noise sensitivity analysis of statistically consistent optimal structure from motion. in 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). vol. 4, SP1-L1, pp. 3698-3703, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sendai, Japan, 9/28/04.
Park FC, Park B, Kim M, Mishra B. Noise sensitivity analysis of statistically consistent optimal structure from motion. In 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vol. 4. 2004. p. 3698-3703. SP1-L1
Park, F. C. ; Park, Byungsoo ; Kim, Munsang ; Mishra, Bhubaneswar. / Noise sensitivity analysis of statistically consistent optimal structure from motion. 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Vol. 4 2004. pp. 3698-3703
@inproceedings{50b5d795573846e8a2aae5e7e5c0a4c0,
title = "Noise sensitivity analysis of statistically consistent optimal structure from motion",
abstract = "We present a noise sensitivity analysis of the differential optimal structure from motion problem. Given optical flow measurements for a set of feature points, we formulate a least squares cost function based on a more reasonable additive isotropic model of measurement noise, normalized by depth, that also leads to statistically consistent estimates of the shape and motion parameters. A cyclic coordinate descent algorithm is developed, and its performance examined through experiments.",
author = "Park, {F. C.} and Byungsoo Park and Munsang Kim and Bhubaneswar Mishra",
year = "2004",
language = "English (US)",
isbn = "0780384636",
volume = "4",
pages = "3698--3703",
booktitle = "2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

}

TY - GEN

T1 - Noise sensitivity analysis of statistically consistent optimal structure from motion

AU - Park, F. C.

AU - Park, Byungsoo

AU - Kim, Munsang

AU - Mishra, Bhubaneswar

PY - 2004

Y1 - 2004

N2 - We present a noise sensitivity analysis of the differential optimal structure from motion problem. Given optical flow measurements for a set of feature points, we formulate a least squares cost function based on a more reasonable additive isotropic model of measurement noise, normalized by depth, that also leads to statistically consistent estimates of the shape and motion parameters. A cyclic coordinate descent algorithm is developed, and its performance examined through experiments.

AB - We present a noise sensitivity analysis of the differential optimal structure from motion problem. Given optical flow measurements for a set of feature points, we formulate a least squares cost function based on a more reasonable additive isotropic model of measurement noise, normalized by depth, that also leads to statistically consistent estimates of the shape and motion parameters. A cyclic coordinate descent algorithm is developed, and its performance examined through experiments.

UR - http://www.scopus.com/inward/record.url?scp=14044255926&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=14044255926&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780384636

SN - 9780780384637

VL - 4

SP - 3698

EP - 3703

BT - 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

ER -