MétaCan
Menu
Back to cohort
Record W1483971997 · doi:10.20381/ruor-19480

Stereo-Based Three-Dimensional Model Acquisition and Motion Detection

2010· dissertation· en· W1483971997 on OpenAlexfundno aff
Ting Yu

Bibliographic record

VenueuO Research (University of Ottawa) · 2010
Typedissertation
Languageen
FieldComputer Science
TopicAdvanced Vision and Imaging
Canadian institutionsnot available
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer visionComputer scienceArtificial intelligenceMotion (physics)Computer graphics (images)

Abstract

fetched live from OpenAlex

Deformable models have a long tradition in computer graphics and computer vision. This thesis looks at the capture of surface deformation based on stereo vision. In recent years, 3D reconstruction and motion detection has attracted great attention. In this thesis a framework for 3D reconstruction from mutli-view images followed by isometry-based motion detection is proposed. For 3D reconstruction, the thesis proposes a multi-view stereo algorithm based on well-known window-based matching combined with fusion of multiple matching results. To improve the matching result, some low-level image processing algorithms, camera calibration and background detection are utilized. For window-based matching, a new hybrid matching method is introduced by combining both, a measure of intensity difference and intensity distribution difference. Multiple MVS pointclouds from different reference views are fused with two new fusion strategies to generate a better final reconstruction. To characterize the performance of our matching method and fusion strategies, an evaluation based on the quality of reconstruction is given in the thesis. Based on 3D pointclouds of object surface obtained with stereo, the deformation of the surface is captured. To generate dense motion vectors over a deformed surface, a simple window-based 3D flow method is applied by using isometry of the observed surface as its primary matching constraint. The method uses feature points as anchoring references of the surface deformation. Given a set of matched features no other intensity information is used and hence the method can tolerate intensity changes over time. The approach is shown to work well on two example scenes which capture non-rigid isometric and general deformations. The thesis also presents experiments demonstrating the stability of the geodesic approximation employed in the isometry-based matching when the 3D pointclouds are sparse.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.021

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0060.005

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.033
GPT teacher head0.307
Teacher spread0.274 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2010
Admission routes1
Has abstractyes

Explore more

Same venueuO Research (University of Ottawa)Same topicAdvanced Vision and ImagingFrench-language works237,207