Two-Stage Hidden Markov Model in Gesture Recognition for Human Robot Interaction

Abstract

Hidden Markov Model (HMM) is very rich in mathematical structure and hence can form the theoretical basis for use in a wide range of applications including gesture representation. Most research in this field, however, uses only HMM for recognizing simple gestures, while HMM can definitely be applied for whole gesture meaning recognition. This is very effectively applicable in HumanRobot Interaction (HRI). In this paper, we introduce an approach for HRI in which not only the human can naturally control the robot by hand gesture, but also the robot can recognize what kind of task it is executing. The main idea behind this method is the 2-stages Hidden Markov Model. The 1st HMM is to recognize the prime command-like gestures. Based on the sequence of prime gestures that are recognized from the 1st stage and which represent the whole action, the 2nd HMM plays a role in task recognition. Another contribution of this paper is that we use the output Mixed Gaussian distribution in HMM to improve the recognition rate. In the experiment, we also complete a comparison of the different number of hidden states and mixture components to obtain the optimal one, and compare to other methods to evaluate this performance.

Context aware 3D gesture recognition for games and virtual reality

“…This hierarchical approach, which breaks up the recognition process into actions and activities, helps to overcome the memory storage and computational power concerns of mobile devices. Other work on 3D gesture recognizers that incorporate HMMs include [Bilal et al 2011;Chen et al 2003;Kelly et al 2011;Just and Marcel 2009;Nguyen-Duc-Thanh et al 2012;Pylvninen 2005;Whitehead and Fox 2009;Zappi et al 2009]. …”

In situ spatial AR surgical planning using projector-Kinect system

“…In this HMM-based hand recognition method, the forward algorithm Baum-Welch [2] plays a significant role where it is used to do a full training of the initialized HMM parameters λ = (A, B, P). In order to improve accuracy of hand movement recognition, calculation of symbol output probability matrix is developed in the training procedure with a full-covariance Gaussian distribution [15] instead of the traditional Gaussian distribution:…”

Isolated Word Recognition for Dysarthric Patients

“…For convenience, the compact notation λ = (A, B, Π) is used to indicate the parameter set of the model. Every state of the HMM model could be reached from every other state of the model in a single step, and generally, the left-toright HMMs are used to model speech parameter sequences since they can appropriately model signals whose properties change successively [9].…”

“…A new method for statistical estimation of Mel-frequency cepstral coefficients (MFCCs) in noisy speech signals is proposed in [9]. The cepstral domain face high complexity of distortion models caused by the nonlinear interaction of speech and noise in this domain [10,11].…”