Continuous Time-Varying Gesture Segmentation by Dynamic Time Warping of Compound Gesture Models
نویسندگان
چکیده
A novel method is introduced to simultaneously recognize and segment time-varying human gestures from continuous video streams. Motion is represented by a 3D spatio-temporal surface based upon the evolution of a contour over time. The temporal endpoints of a gesture are estimated by Dynamically Time Warping the input sequence against a set of Compound Gesture Models, which are composed of the concatenation of two gestures. The system has been implemented and tested on 8 different gestures performed by 5 subjects at a variety of time scales. The results demonstrate that the proposed method is very effective, achieving recognition rates of 88.1% for multiple scale and 93.3% for single scale tests.
منابع مشابه
Realtime Segmentation and Recognition of Gestures using Hierarchical Markov Models
In this work, we present a realtime system for continuous gesture segmentation and recognition. The model is an extension of the system called Gesture Follower developed at Ircam, which is an hybrid model between Dynamic Time Warping and Hidden Markov Models. This previous model allows for a realtime temporal alignment between a template and an input gesture. Our model extends it by proposing a...
متن کاملInertial Sensor-Based Touch and Shake Metaphor for Expressive Control of 3D Virtual Avatars
In this paper, we present an inertial sensor-based touch and shake metaphor for expressive control of a 3D virtual avatar in a virtual environment. An intuitive six degrees-of-freedom wireless inertial motion sensor is used as a gesture and motion control input device with a sensor fusion algorithm. The algorithm enables user hand motions to be tracked in 3D space via magnetic, angular rate, an...
متن کاملProbability-based Dynamic Time Warping and Bag-of-Visual-and-Depth-Words for Human Gesture Recognition in RGB-D
We present a methodology to address the problem of human gesture segmentation and recognition in video and depth image sequences. A Bag-ofVisual-and-Depth-Words (BoVDW) model is introduced as an extension of the Bag-of-Visual-Words (BoVW) model. State-of-the-art RGB and depth features, including a newly proposed depth descriptor, are analysed and combined in a late fusion form. The method is in...
متن کاملIntegrated Event Recognition from Multiple Sources
This paper proposes a system architecture for event recognition that integrates information from multiple sources (e.g., gesture and speech recognition from distributed sensors in the real world). The proposed system consists of multiple recognizers named Continuous State Machines (CSMs). Each CSM has a state transition rule in a continuous state space and classifies time-varying patterns from ...
متن کاملSilhouette-based gesture and action recognition via modeling trajectories on Riemannian shape manifolds
This paper addresses the problem of recognizing human gestures from videos using models that are built from the Riemannian geometry of shape spaces. We represent a human gesture as a temporal sequence of human poses, each characterized by a contour of the associated human silhouette. The shape of a contour is viewed as a point on the shape space of closed curves and, hence, each gesture is char...
متن کامل