Gesture Semantics Reconstruction Based on Motion Capturing and Complex Event Processing: a Circular Shape Example
نویسندگان
چکیده
A fundamental problem in manual based gesture semantics reconstruction is the specification of preferred semantic concepts for gesture trajectories. This issue is complicated by problems human raters have annotating fast-paced three dimensional trajectories. Based on a detailed example of a gesticulated circular trajectory, we present a data-driven approach that covers parts of the semantic reconstruction by making use of motion capturing (mocap) technology. In our FA3ME framework we use a complex event processing approach to analyse and annotate multi-modal events. This framework provides grounds for a detailed description of how to get at the semantic concept of circularity observed in the data.
منابع مشابه
3D Hand Motion Evaluation Using HMM
Gesture and motion recognition are needed for a variety of applications. The use of human hand motions as a natural interface tool has motivated researchers to conduct research in the modeling, analysis and recognition of various hand movements. In particular, human-computer intelligent interaction has been a focus of research in vision-based gesture recognition. In this work, we introduce a 3-...
متن کاملParsing 3D motion trajectory for gesture recognition
Motion trajectories have been widely used for gesture recognition. An effective representation of 3D motion trajectory is important for capturing and recognizing complex motion patterns. In this paper, we propose a view invariant hierarchical parsing method for free form 3D motion trajectory representation. The raw motion trajectory is first parsed into four types of trajectory primitives based...
متن کاملDesign and Realization of an Experimental Optical Stop-motion Capture System
Title: Design and Realization of an Experimental Optical Stop-Motion Capture System Author: Sven Bambach Reviewers: Prof. Dr. Stefan M. Grünvogel (Computer Animation and Computer Science) Prof. Dr. Dietmar Kunz (Digital Image Processing and Mathematics) Abstract: Motion capturing plays an important role in computer animation and combines many different fields of research in media engineering, s...
متن کاملEMG-based wrist gesture recognition using a convolutional neural network
Background: Deep learning has revolutionized artificial intelligence and has transformed many fields. It allows processing high-dimensional data (such as signals or images) without the need for feature engineering. The aim of this research is to develop a deep learning-based system to decode motor intent from electromyogram (EMG) signals. Methods: A myoelectric system based on convolutional ne...
متن کاملDerivation of Equation of Motion for the Pillow-Shape Seismic Base Isolation System
Rolling-based seismic isolation systems, in which rollers of circular or non-circular section are used, are less expensive and easier to manufacture. However, this type of isolation suffers from either lack of restoring or re-centering capability, or weakness against uplift forces. To resolve the first shortcoming the use of elliptical as well as pillow-shape rolling parts has been suggested, a...
متن کامل