Conjoint individual and group tracking framework with online learning

Download
index.pdf
2016
Yiğit, Ahmet
Show full item record
214
views
73
downloads
A group is a social unit which consists of people interacting with each other and sharing the similar characteristics. Because of social properties of group, group tracking re-quires taking into account not only visual properties but also social properties such as interaction of people with each other. Also, people groups are dynamic entities and they may grow and shrink with merge and split events. This dynamic nature makes it difficult to track groups using conventional trackers. Besides these difficulties, differ-ent types of groups require different strategies in order to perform tracking effectively. While it is possible to track individuals separately when group is sparse, group is con-sidered as a single entity when it is dense. To overcome and address these challenges, we propose a new tracking strategy, named the Conjoint Individual and Group Tracking (CIGT), based on particle filter and online learning from discriminative appearance model in this thesis. The CIGT proposes a multi observation model with in-group and out-group weights in order to track groups and to evaluate merge and split events. CIGT has two complementary phases: tracking and learning. In the tracking phase, the CIGT calculates multiple weights from observa-tions and models individuals and groups with merge and split events. Particle advection is used in the motion model of CIGT to facilitate tracking of dense groups. In the learn-ing phase, reliable tracklets are first created. Then discriminative appearance model, consisting of shape, color and texture features, is extracted and used in AdaBoost online learning. State estimate is performed for both individuals and groups by using the discriminative learning model.
Machine learning., Artificial intelligence., Computer algorithms., Social interaction., Social groups.
http://etd.lib.metu.edu.tr/upload/12619809/index.pdf
https://hdl.handle.net/11511/25517
Graduate School of Informatics, Thesis

Suggestions

Implementation of a Generic Framework on Crowd Simulation: A New Environment to Model Crowd Behavior and Design Video Games
Yücel, Furkan; Sürer, Elif (2020-12-01)
Crowd behavior is the collective act and gathering of a group of individuals to achieve a shared purpose. Swarm intelligence-based optimization algorithms are usually used to solve complex problems for crowd behavior. Crowd simulations are often used for the analyses that require precision in different domains such as complex structural analysis, image recognition, creating nature-inspired non-player character movements in video games, and more. In this study, a generic crowd simulation framework that can b...
Relatedness of identities and emotional closeness with parents across and within cultures
İmamoğlu, Emine Olcay; Karakitapoglu-Ayguen, Zahide (Wiley, 2007-09-01)
Differences in emotional- and identity-relatedness with parents were explored across two cultural groups ( 863 university students from the USA and Turkey, representing individualist and collectivist societies, respectively) in Study 1, and across two socioeconomic status (SES) groups ( 353 high school students from the upper and lower SES in Turkey) in Study 2. In both studies, within-cultural differences in emotional- and identity-relatedness with parents were also explored in terms of: (i) self-directed ...
Organizational structures and networks of four Islamıst/Islamic women's NGOs in Turkey : in the context of new social movement
Küçükoğlu, Lütfiye Sevinç; Rittersberger Tılıç, Helga İda; Department of Sociology (2004)
The main purpose of this study is to understand the organizational structures of Islamist/Islamic women̕s NGOs and explain the network mechanisms of them in the context of new social movements. This study is based on a social movement research; thus, both organizational structures and network mechanisms of Islamist/Islamic women̕s NGOs are explained and analyzed in terms of the features of new social movements, to answer the question of ءwhether Islamist/Islamic women̕s NGOs are potential and possible actor...
Contribution to the collaborative work in virtual organization - a case study
Weber, Gerhard Wilhelm; Özdamar, Linet; Pedamallu, Chandra Sekhar; Crespo, Fernando A. (Walter de Gruyter GmbH, 2012-10-1)
A virtual organization is a community of people who interact together socially on a technical platform. These kinds of communities are built on a common interest, a common problem or a common task of its members that is pursued on the basis of implicit and explicit codes of behavior. The six dimensions that are normally used to analyze virtual organizations are the use of technologies, sense of belonging, success factors, level of trust from members, virtual community management, and contents of the virtual...
Social comparison as a determinant of self-presentation
Demir, Sıla; Özkan, Türker; Department of Psychology (2017)
As social beings people usually try to project the best image of themselves on their interaction partners. On other occasions, they try to create the image that they think will be advantageous for them in a certain way. These self-presentational efforts may be conscious or automatic, and may be triggered by some situational determinants and be associated with some personality characteristics. Besides, social comparison tendencies may also be associated with self-presentation. People often compare themselves...
Citation Formats
A. Yiğit, “Conjoint individual and group tracking framework with online learning,” Ph.D. - Doctoral Program, Middle East Technical University, 2016.
METU IIS - Integrated Information Service open@metu.edu.tr