National Technical University of Athens (NTUA)
Τεχνικές για αξιόπιστα συστήματα παρακολούθησης
Abstract
dc:descriptionCamera based supervision is a critical part of event detection and analysis applications. However, visual tracking still remains one of the biggest challenges in the area of computer vision, although it has been extensively discussed during in the previous years. In this thesis, object flow is introduced, for estimating both the displacement and the direction of an object-of-interest. Compared to the detection and tracking techniques, the proposed approach obtains the object displacement directly, while ignoring other irrelevant movements in the scene. Hence, object flow has the ability to continuously focus on a specific object and calculate its motion field. A robust tracking approach based on object flow and an observation model that utilizes a generative prior are adopted to tackle the pitfalls that derive from the appearance changes of the object-of-interest. In addition, an on-line sample verification mechanism is proposed. The efficiency of the proposed technique is demonstrated on various sequences, such as a complex industrial environment. The experimental results show that the proposed technique is sound, yielding improved performance in comparison with other tracking approaches.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2012
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Lalos, Constantinos
- Λάλος, Κωνσταντίνος
Subjects
dc:subject × 10- Όραση υπολογιστών
- Μέθοδοι μηχανών μάθησης
- Βάσεις πολυμεσικών δεδομένων
- Computer vision
- Machine learning
- Multimedia databases
- Επιστήμες Μηχανικού και Τεχνολογία
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Engineering and Technology
- Electrical Engineering, Electronic Engineering, Information Engineering
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/36071