Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Iterative Dense Correspondence Correction Through Bundle Adjustment Feedback-Based Error Detection

Conference ·
OSTI ID:986066

A novel method to detect and correct inaccuracies in a set of unconstrained dense correspondences between two images is presented. Starting with a robust, general-purpose dense correspondence algorithm, an initial pose estimate and dense 3D scene reconstruction are obtained and bundle-adjusted. Reprojection errors are then computed for each correspondence pair, which is used as a metric to distinguish high and low-error correspondences. An affine neighborhood-based coarse-to-fine iterative search algorithm is then applied only on the high-error correspondences to correct their positions. Such an error detection and correction mechanism is novel for unconstrained dense correspondences, for example not obtained through epipolar geometry-based guided matching. Results indicate that correspondences in regions with issues such as occlusions, repetitive patterns and moving objects can be identified and corrected, such that a more accurate set of dense correspondences results from the feedback-based process, as proven by more accurate pose and structure estimates.

Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA
Sponsoring Organization:
USDOE
DOE Contract Number:
W-7405-ENG-48
OSTI ID:
986066
Report Number(s):
LLNL-CONF-420758
Country of Publication:
United States
Language:
English

Similar Records

Factorization of correspondence and camera error for unconstrained dense correspondence applications
Conference · Tue Sep 29 00:00:00 EDT 2009 · OSTI ID:970147

Error Detection, Factorization and Correction for Multi-View Scene Reconstruction from Aerial Imagery
Thesis/Dissertation · Wed Nov 09 23:00:00 EST 2011 · OSTI ID:1035591

Detecting Dominant Motions in Dense Crowds
Journal Article · Mon Dec 31 23:00:00 EST 2007 · IEEE Journal of Selected Topics in Signal Processing · OSTI ID:964347