Analysis of border ownership cues and improvement of depth prediction using border ownership

Download

index.pdf

Date

2014

Author

Akkuş, Mehmet Akif

Metadata

Show full item record

Item Usage Stats

110
views

67
downloads

Border Ownership is the problem of identifying which image regions own the image border. This information is essential and important for large variety of high-level vision problems such as object segmentation, object recognition, depth perception, motion perception etc. Current computational approaches to Border Ownership (BO) estimation either use artificial or limited number of real images. In this thesis, we propose a new comprehensive BO database, including 500 indoor and 500 outdoor images whose BO information is labeled by human participants. Using this dataset, BO estimation capability is investigated for several visual cues such as T-junction, L-junction, curvature, lower region and contrast both individually and combinatorially. Then using these cues, a basic computational model is proposed which estimates BO information based on the majority rule. Moreover, a new method, which merges a feature-based stereo algorithm and BO information, is proposed for more accurate depth prediction on homogeneous areas.

Subject Keywords

Image processing., Imaging systems, Image processing

URI

http://etd.lib.metu.edu.tr/upload/12618168/index.pdf
https://hdl.handle.net/11511/24179

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Analysis of methods for border ownership estimation Olgunsoylu, Sertaç; Kalkan, Sinan; Department of Computer Engineering (2015) Border Ownership (BO) signifies which side of an image border owns the border. This information is very important for many computer vision problems. There are various approaches for estimating BO in the literature. One approach is to use methods that rely on low-level local features; combinations of local visual cues such as convexity or junctions and using spectral features have been proven to be quite effective. Alternatively, global constraints or cues can be imposed on top of local cue predictions to ma...
Estimating border ownership using iterative vector voting and conditional random fields Özkan, Buğra; Kalkan, Sinan; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2014) Border ownership is the information that signifies which side of a border owns the border. Estimating this information has recently become very popular for perceptual organization as it allows rectification of ambigious visual information. It is applied on many computer vision problems such as object detection, depth perception and optical flow. In this thesis, two different approaches are followed to solve the border ownership problem. For the supervised approach, conditional random fields are used as it i...
Extraction of border ownership information by conditional random field model Koşullu rastgele alan modeli ile sinir sahipligi bilgisi çikarimi Özkan, Bugra; Kalkan, Sinan (2013-04-26) Border ownership is a kind of information used for determining the regions that own borders in an image. This information has recently become more valuable as it began to be used in many vision problems such as figure-ground segregation, depth perception and optical flow, however the quality and quantity of current literature are not sufficient yet. In this study, a Conditional Random Field model is developed for the enhancement of border ownership labelings, which are extracted with the help of some spatia...
A comprehensive database for border ownership Sinir Sahiplǐgi Için Kapsamli Bir Veri Taban Akkuş, Mehmet Akif; Topuz, Gaye; Özkan, Bǔgra; Kalkan, Sinan (2013-04-26) Border ownership is a problem of identifying which visual region the borders of a visual image belong. It has valuable and essential information for visual systems. Existing computational approaches either use artificial or limited type and number of images. In this study, we propose a new comprehensive database, which contains border ownership information from the edges and segments of 500 indoor and 500 outdoor images determined by hand-labeling of human participants and a couple of analyses carried on th...
A Learning-based method for person re-identification Oğul, Burçin Buket; Temizel, Alptekin; Department of Information Systems (2013) Matching pedestrian images captured from different cameras is called person re-identification problem. The problem is challenging due to the low resolution of images, differences in illumination, the positional variance and possible appearance of carried objects, such as a bag, at different viewpoints. In this thesis, we investigate the discriminative ability of different features extracted from image in a binary classification framework. We finally propose a learning based method to combine different featu...

Citation Formats

M. A. Akkuş, “Analysis of border ownership cues and improvement of depth prediction using border ownership,” M.S. - Master of Science, Middle East Technical University, 2014.