Human activity recognition by Gait Analysis

Kepenekci, Burcu
This thesis analyzes the human action recognition problem. Human actions are modeled as a time evolving temporal texture. Gabor filters, which are proved to be a robust 2D texture representation tool by detecting spatial points with high variation, is extended to 3D domain to capture motion texture features. A well known filtering algorithm and a recent unsupervised clustering algorithm, the Genetic Chromodynamics, are combined to select salient spatio-temporal features of the temporal texture and to segment the activity sequence into temporal texture primitives. Each activity sequence is represented as a composition of temporal texture primitives with its salient spatio-temporal features, which are also the symbols of our codebook. To overcome temporal variation between different performances of the same action, a Profile Hidden Markov Model is applied with Viterbi Path Counting (ensemble training). Not only parameters and structure but also codebook is learned during training.


Human activity classification using spatio-temporal feature relations
Akpınar, Kutalmış; Ulusoy, İlkay; Department of Electrical and Electronics Engineering (2012)
This thesis compares the state of the art methods and proposes solutions for human activity classification from video data. Human activity classification is finding the meaning of human activities, which are captured by the video. Classification of human activity is needed in order to improve surveillance video analysis and summarization, video data mining and robot intelligence. This thesis focuses on the classification of low level human activities which are used as an important information source to dete...
Human behavior understanding using video analysis
Gökçe, Celal Onur; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2016)
In this study we proposed a new hierarchical architecture for solution of human behavior understanding problem. A new dataset, namely football video game (FVG) dataset, is generated which involves activities more complex than any other dataset present in the literature. Football ball is detected using multilayer neural networks trained with gradient descent algorithm and enhanced using learning with queries method and it is tracked using growing window algorithm. After region of interest is extracted around...
An attempt to make a definition of existence and constructing a foundation for an axiomatic system of ontology
Çağatay, Hasan; Grünberg, Teo; Department of Philosophy (2007)
This thesis aims to make an analysis of the concepts of ‘existence’. It also constructs four new definitions based on the concept of ‘effect’ for different concepts of beings. By reasoning based on these definitions and some pre-suppositions, a foundation for an axiomatic system of ontology is tried to construct.
The analysis of alienation [Entfremdung] in being time from a Marxist perspective
Keskin, Eda; İnam, Ahmet; Department of Philosophy (2010)
In this thesis, the problem of human being’s alienation from its own Self, society, species-being, objects (products) and labour, which occurs in capitalist modernity through the formation of mass cultures, is analyzed in the conceptual context of Being and Time. In this respect, it is discussed that Heideggerian philosophy is not at odds with Marxism in contrast to Theodor W. Adorno’s arguments in The Jargon of Authenticity. Additionally, the claim of this study is that Heidegger’s ontologico-existential p...
New directions in the direction of time
Bağcı, Gökhan Barış; Grünberg, Teo; Department of Philosophy (2006)
This thesis analyzes the direction of time problem in the framework of philosophy of science. The radiation arrow, Newtonian arrow, thermodynamic arrow and quantum mechanical arrow have been studied in detail. The importance of the structure of space-time concerning direction of time is emphasized.
Citation Formats
B. Kepenekci, “Human activity recognition by Gait Analysis,” Ph.D. - Doctoral Program, Middle East Technical University, 2011.