Hand trajectory based gesture recognition using self-organizing feature maps and markov models

Karpouzis, Kostas; Pateritsas, Christos; Drosopoulos, Athanasios; Stafylopatis, Andreas; Kollias, Stefanos

doi:10.1109/icme.2008.4607632

Cited by 13 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ahmad and Lee [34] track gestures using shape and motion information. Caridakis et al [35] report classification of 30 hand gesture classes using spatial features (hand trajectory and hand motion direction) and temporal features (hand position in the trajectory), modeled through hidden Markov models. They report recognition rates between 85-93%.…”

Section: Introductionmentioning

confidence: 99%

Student mental state inference from unintentional body gestures using dynamic Bayesian networks

Abbasi

Dailey

Afzulpurkar

et al. 2009

J Multimodal User Interfaces

View full text Add to dashboard Cite

Applications that interact with humans would benefit from knowing the intentions or mental states of their users. However, mental state prediction is not only uncertain but also context dependent. In this paper, we present a dynamic Bayesian network model of the temporal evolution of students' mental states and causal associations between mental states and body gestures in context. Our approach is to convert sensory descriptions of student gestures into semantic descriptions of their mental states in a classroom lecture situation. At model learning time, we use expectation maximization (EM) to estimate model parameters from partly labeled training data, and at run time, we use the junction tree algorithm to infer mental states from body gesture evidence. A maximum a posteriori classifier evaluated with leave-one-out cross validation on labeled data from 11 stu-A.R. Abbasi

show abstract

Section: Introductionmentioning

confidence: 99%

Student mental state inference from unintentional body gestures using dynamic Bayesian networks

Abbasi

Dailey

Afzulpurkar

et al. 2009

J Multimodal User Interfaces

View full text Add to dashboard Cite

show abstract

“…Although there has been a significant amount of work on recognizing 3D gestures using traditional position and orientation tracking devices [3,10,16,17], the use of accelerometer and gyroscope-based devices for 3D gesture recognition has been sparse. Beedkar and Shah experimented with classifying four gestures using a Hidden Markov Model (HMM).…”

Section: Related Workmentioning

confidence: 99%

Breaking the status quo: Improving 3D gesture recognition with spatially convenient input devices

Hoffman

Varcholik

LaViola

2010

2010 IEEE Virtual Reality Conference (VR)

View full text Add to dashboard Cite

We present a systematic study on the recognition of 3D gestures using spatially convenient input devices. Specifically, we examine the linear acceleration-sensing Nintendo Wii Remote coupled with the angular velocity-sensing Nintendo Wii MotionPlus. For the study, we created a 3D gesture database, collecting data on 25 distinct gestures totalling 8500 gestures samples. Our experiment explores how the number of gestures and the amount of gestures samples used to train two commonly used machine learning algorithms, a linear and AdaBoost classifier, affect overall recognition accuracy. We examined these gesture recognition algorithms with user dependent and user independent training approaches and explored the affect of using the Wii Remote with and without the Wii MotionPlus attachment.Our results show that in the user dependent case, both the AdaBoost and linear classification algorithms can recognize up to 25 gestures at over 90% accuracy, with 15 training samples per gesture, and up to 20 gestures at over 90% accuracy, with only five training samples per gesture. In particular, all 25 gestures could be recognized at over 99% accuracy with the linear classifier using 15 training samples per gesture, with the Wii Remote coupled with the Wii MotionPlus. In addition, both algorithms can recognize up to nine gestures at over 90% accuracy using a user independent training database with 100 samples per gesture. The Wii MotionPlus attachment played a significant role in improving accuracy in both the user dependent and independent cases.

show abstract

“…9n contrast, our method will be able to provide a general framework for anomaly detection, independent of the number of dimensions of the input space and the kind of underlying sensors spanning the input space. A similar approach, which uses Feature Maps for spatialtemporal analysis, was introduced by [19] for hand gesture recognition. The Kohonen Map and the Levenstein distance are used to calculate the spatial similarity of the gestures.…”

Section: Related Workmentioning

confidence: 97%

“…Some further -non-robotic, but related -work based on spatialtemporal context using Kohonen-Feature Maps and external probabilistic temporal modeling are usually tailored to a very specific application system. The authors in [19] introduce a method for hand gesture recognition applying the Levenstein distance to find the spatial similarity of the gestures. The temporal aspect is modeled by two different Markov models considering the sequence of the map nodes and the discretized optical flow.…”

Section: Related Workmentioning

confidence: 99%

A Generic Framework for Behavior Recognition of Complex Activities in Robotics

Haeussermann

Zweigle

Levi

2013

2013 IEEE 25th International Conference on Tools With Artificial Intelligence

View full text Add to dashboard Cite

Considering the current state in service-robotics, an expert is still necessary to add new tasks and execution behaviors by textual and error-prone programming. Under the consideration that humans typically execute same activities almost identical (or at least similar) and further combine simple behaviors to more complex activities, we follow the constitutive assumption that all complex behaviors are composed of a limited set of atomic behaviors. This work introduces a generic framework for spatialtemporal analysis and classification of arbitrary atomic behaviors. Therefore, we propose the combination of Self-Organizing Maps (SOM) and Probabilistic Graphical Models (PGM) in order to exploit the advantages of both concepts. In this work, we describe the essential methods of the framework briefly, whereas the datadriven training of the spatial-temporal model and the reasoning process are described in detail. In order to demonstrate the potential and to emphasize the high level of generalization and flexibility in real-world environments, the framework is evaluated in an exemplary scenario.

show abstract

Hand trajectory based gesture recognition using self-organizing feature maps and markov models

Cited by 13 publications

References 17 publications

Student mental state inference from unintentional body gestures using dynamic Bayesian networks

Student mental state inference from unintentional body gestures using dynamic Bayesian networks

Breaking the status quo: Improving 3D gesture recognition with spatially convenient input devices

A Generic Framework for Behavior Recognition of Complex Activities in Robotics

Contact Info

Product

Resources

About