You are here

systematic evaluation of object detection and recognition approaches with context capabilities

Download pdf | Full Screen View

Date Issued:
2011
Summary:
Contemporary computer vision solutions to the problem of object detection aim at incorporating contextual information into the process. This thesis proposes a systematic evaluation of the usefulness of incorporating knowledge about the geometric context of a scene into a baseline object detection algorithm based on local features. This research extends publicly available MATLABRª implementations of leading algorithms in the field and integrates them in a coherent and extensible way. Experiments are presented to compare the performance and accuracy between baseline and context-based detectors, using images from the recently published SUN09 dataset. Experimental results demonstrate that adding contextual information about the geometry of the scene improves the detector performance over the baseline case in 50% of the tested cases.
Title: A systematic evaluation of object detection and recognition approaches with context capabilities.
132 views
19 downloads
Name(s): Giusti Urbina, Rafael J.
College of Engineering and Computer Science
Department of Computer and Electrical Engineering and Computer Science
Type of Resource: text
Genre: Electronic Thesis Or Dissertation
Date Issued: 2011
Publisher: Florida Atlantic University
Physical Form: electronic
Extent: xi,, 101 p. : ill. (some col.)
Language(s): English
Summary: Contemporary computer vision solutions to the problem of object detection aim at incorporating contextual information into the process. This thesis proposes a systematic evaluation of the usefulness of incorporating knowledge about the geometric context of a scene into a baseline object detection algorithm based on local features. This research extends publicly available MATLABRª implementations of leading algorithms in the field and integrates them in a coherent and extensible way. Experiments are presented to compare the performance and accuracy between baseline and context-based detectors, using images from the recently published SUN09 dataset. Experimental results demonstrate that adding contextual information about the geometry of the scene improves the detector performance over the baseline case in 50% of the tested cases.
Identifier: 754799744 (oclc), 3183127 (digitool), FADT3183127 (IID), fau:3707 (fedora)
Note(s): by Rafael J. Giusti Urbina.
Thesis (M.S.C.S.)--Florida Atlantic University, 2011.
Includes bibliography.
Electronic reproduction. Boca Raton, Fla., 2011. Mode of access: World Wide Web.
Subject(s): Imaging systems -- Mathematical models
Cognitive science
Optical pattern recognition
Computer vision
Logistic regression analysis
Persistent Link to This Record: http://purl.flvc.org/FAU/3183127
Use and Reproduction: http://rightsstatements.org/vocab/InC/1.0/
Host Institution: FAU