Semantic video analysis for surveillance systems

Kardaş, Karani
This thesis presents novel studies about semantic inference of video events. In this respect, a surveillance video analysis system, called SVAS is introduced for surveillance domain, in which semantic rules and the definition of event models can be learned or defined by the user for automatic detection and inference of complex video events. In the scope of SVAS, an event model method named Interval-Based Spatio-Temporal Model (IBSTM) is proposed. SVAS can learn action models and event models without any predefined threshold values and generates human readable and manageable IBSTM event models. The thesis proposes hybrid machine learning methods. A set of feature models named Threshold Model, which reflects the spatio-temporal motion analysis of an event, is kept as the first model. As the second model, Bag of Actions (BoA) model is used in order to reduce the search space in the detection phase. Markov Logic Network (MLN) model, which provides understandable and manageable logic predicates for users, is kept as the third model. SVAS has high performance event detection capability due to its interval-based hierarchical approach. It determines related candidate intervals for each main model of IBSTM and uses the related main model when needed rather than using all models as a whole. The main contribution of this study is to fill the semantic gap between humans and video computer systems such that, on one hand it decreases human intervention through its learning capabilities, but on the other hand it also enables human intervention when necessary through its manageable event model method. The study achieves all of them in the most efficient way through its machine learning methods. The proposed system is applied to different event datasets from CAVIAR, BEHAVE, CANTATA and our synthetic datasets. The experimental results show that our approach improves the event recognition performance and precision as compared to the current state-of-the-art approaches.


Configuration of Neural Networks for the Analysis of Seasonal Time Series
Taşkaya Temizel, Tuğba (2005-08-25)
Time series often exhibit periodical patterns that can be analysed by conventional statistical techniques. These techniques rely upon an appropriate choice of model parameters that are often difficult to determine. Whilst neural networks also require an appropriate parameter configuration, they offer a way in which non-linear patterns may be modelled. However, evidence from a limited number of experiments has been used to argue that periodical patterns cannot be modelled using such networks. In this paper, ...
Öztürel, İsmet Adnan; Bozşahin, Cem; Department of Cognitive Sciences (2022-8-29)
This thesis presents a novel approach to assigning types to expressive Discourse Representation Structure (DRS) meaning representations. In terms of linguistic analysis, our typing methodology couples together the representation of phenomena at the same level of analysis that was traditionally considered to belong to distinctive layers. In the thesis, we claim that the realisation of sub-lexical, lexical, sentence and discourse-level phenomena (such as tense, word sense, named entity class, thematic role, a...
Construction of security cultures: a content analysis of the representations of video-surveillance in urban space in Turkish print media
Erdem, Merve Tuğba; Mücen, Barış; Department of Sociology (2016)
This thesis provides an examination of the representations of MOBESE revealed in the print media. MOBESE portrayal is evaluated from an evaluative perspective seeking to know to what end do these representations given in the print media serve; furthermore; to amplify where MOBESE surveillance stand in the process of constructing security cultures. This research is conducted in terms of print media articles downsized to MOBESE-related items in four selected newspaper articles published between the years of 2...
Video Content Analysis Method for Audiovisual Quality Assessment
Konuk, Baris; Zerman, Emin; NUR YILMAZ, GÖKÇE; Akar, Gözde (2016-06-08)
In this study a novel, spatio-temporal characteristics based video content analysis method is presented. The proposed method has been evaluated on different video quality assessment databases, which include videos with different characteristics and distortion types. Test results obtained on different databases demonstrate the robustness and accuracy of the proposed content analysis method. Moreover, this analysis method is employed in order to examine the performance improvement in audiovisual quality asses...
Computatıonal aspects of discourse annotation
Aktaş, Berfin; Bozşahin, Hüseyin Cem; Department of Cognitive Sciences (2008)
In this thesis, we aim to analyze the computational aspects of discourse annotation. Discourse is not only a concatenation of sentences; in fact the totality of discourse is more than the sum total of the sentences that constitute it. The property that differentiates discourse from a set of arbitrary sentences is defined as coherence. Coherence is established by the relations between the parts of discourse. We have a lexicalized approach to discourse, therefore in this study, discourse relations are conside...
Citation Formats
K. Kardaş, “Semantic video analysis for surveillance systems,” Ph.D. - Doctoral Program, Middle East Technical University, 2018.