Treffer: Motion analysis and modeling for activity recognition and 3-D animation based on geometrical and video processing algorithms ; Ανάλυση κίνησης και μοντελοποίησης για αναγνώριση δραστηριότητας και 3-Δ συνθετική κίνηση βασισμένη σε γεωμετρικούς αλγορίθμους και μεθόδους επεξεργασίας βίντεο

The analysis of audiovisual data aims at extracting high level information, equivalent with the one(s) that can be extracted by a human. It is considered as a fundamental, unsolved (in its general form) problem. Even though the inverse problem, the audiovisual (sound and animation) synthesis, is judged easier than the previous, it remains an unsolved problem. The systematic research on these problems yields solutions that constitute the basis for a great number of continuously developing applications. In this thesis, we examine the two aforementioned fundamental problems. We propose algorithms and models of analysis and synthesis of articulated motion and undulatory (snake) locomotion, using data from video sequences. The goal of this research is the multilevel information extraction from video, like object tracking and activity recognition, and the 3–D animation synthesis in virtual environments based on the results of analysis. An important part of this thesis is dedicated to automatic human motion analysis from video and action/activity recognition. Moreover, we examine the problem of animal animation synthesis using parametric models and algorithms that are based on motion tracking data over appropriate video sequences. The problem of undulatory locomotion analysis led in the definition of a general geometrical problem, the curve EquiPartition (EP). In this thesis, we define, analyze and solve the EP problem. In the case of human motion analysis, we propose a general framework that focuses on automatic individual/multiple people motion-shape analysis and on suitable features extraction, which can be used on action/activity recognition problems under real, dynamical and unconstrained environments. In order to evaluate the robustness of the proposed scheme, we have applied it on various athletic videos from a single uncalibrated, possibly moving camera. The automatic analysis of these videos is a challenging problem due to the complex and fast motions of the athletes and to the unconstrained changes in the ...