3D scene reconstruction using a single monocular image
Date of Publication
2012
Document Type
Bachelor's Thesis
Degree Name
Bachelor of Science in Computer Science
Subject Categories
Computer Sciences
College
College of Computer Studies
Department/Unit
Computer Science
Thesis Adviser
Miguel Angelo Cabral
Defense Panel Member
Nelson Marcos
Florante Salvador
Abstract/Summary
This is research on 3D scene reconstruction from a single monocular 2D image. It extends the study done by Saxena, Sun, and Ng (2008) called Make3D. Make3D constructs a 3D model from a single 2D image using monocular cues extracted from it. In this study, additional features not used by Make3D have been identified and used to produce a better 3D reconstruction. These features are the sky blob, saturation, and object blob. These features are extracted from the image and used in the improvement of the 3D model. Qualitative survey was used to evaluate the outputs of this study on unstructured images. Results of the survey reveal that this study has produced better results in some cases when compared against Make3D.
Abstract Format
html
Language
English
Format
Accession Number
TU18434
Shelf Location
Archives, The Learning Commons, 12F, Henry Sy Sr. Hall
Physical Description
viii, 69 leaves : illustrations (some colored) ; 28 cm.
Keywords
Pattern Recognition; Three-dimensional imaging
Recommended Citation
Ablay, F. P., Agustin, M. P., Cengca, M. M., & Tiam-Lee, T. Z. (2012). 3D scene reconstruction using a single monocular image. Retrieved from https://animorepository.dlsu.edu.ph/etd_bachelors/10651
Embargo Period
1-4-2022