Translation and scale-invariant gesture recognition in complex scenes

Stefan, Alexandra; Athitsos, Vassilis; Alon, Jonathan; Sclaroff, Stan

doi:10.1145/1389586.1389595

Cited by 28 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once body postures and their parts are represented, behavioral indicators are usually analyzed by studying their trajectories using both machine learning and pattern recognition approaches. Some methods in this context are based on dynamic programming techniques such as Dynamic Time Warping (DTW) [14] or statistical approaches such as Hidden Markov Models (HMM) and Conditional Random Fields (CRF) [15,16].…”

Section: Related Workmentioning

confidence: 99%

Multi-modal social signal analysis for predicting agreement in conversation settings

Ponce-López

Escalera

Baró

2013

Proceedings of the 15th ACM on International Conference on Multimodal Interaction

View full text Add to dashboard Cite

In this paper we present a non-invasive ambient intelligence framework for the analysis of non-verbal communication applied to conversational settings. In particular, we apply feature extraction techniques to multi-modal audio-RGB-depth data. We compute a set of behavioral indicators that define communicative cues coming from the fields of psychology and observational methodology. We test our methodology over data captured in victim-offender mediation scenarios. Using different state-of-the-art classification approaches, our system achieve upon 75% of recognition predicting agreement among the parts involved in the conversations, using as ground truth the experts opinions.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-modal social signal analysis for predicting agreement in conversation settings

Ponce-López

Escalera

Baró

2013

Proceedings of the 15th ACM on International Conference on Multimodal Interaction

View full text Add to dashboard Cite

show abstract

“…Unfortunately, their work does not present quantitative results. Stefan et al [23] used a nearest neighbor technique to classify dynamic gestures based on their feature vectors, with data acquired from video streams. A recognition rate of 96.3% was achieved, based on gestures representing digits from 0 to 9.…”

Section: Simple Pattern Recognition Techniquesmentioning

confidence: 99%

Comparative evaluation of static gesture recognition techniques based on nearest neighbor, neural networks and support vector machines

Savaris

Wangenheim

2010

J Braz Comput Soc

View full text Add to dashboard Cite

It is a common behavior for human beings to use gestures as a means of expression, as a complement to speaking, or as a self-contained communication mode. In the field of Human-Computer Interaction, this behavior can be adopted to build alternative interfaces, aiming to ease the relationship between the human element and the computational element. Currently, various gesture recognition techniques are described in the technical literature; however, the validation studies of these techniques are usually performed isolatedly, which complicates comparisons between them. To reduce this gap, this work presents a comparison between three well-established techniques for static gesture recognition, using Nearest Neighbor, Neural Networks, and Support Vector Machines as classifiers. These classifiers evaluate a common dataset, acquired from an instrumented glove, and generate results for precision and performance measurements. The results obtained show that the classifier implemented as a Support Vector Machine presented the best generalization, with the highest recognition rate. In terms of performance, all methods presented evaluation times fast enough to be used interactively. Finally, this work identifies and discusses a set of relevant criteria that must be observed for the training and evaluation steps, and its relation to the final results.

show abstract

“…In his inspirational thesis Mathias Kölsch [1] suggests a particular variation to the Viola and Jones algorithm [9] by adding the "four boxes same feature" to detect hand gestures. We have also adopted the approach developed by Alexandra et al [2] to make it scale invariant. This improves the operational range of the algorithm from 2m to 6m.…”

Section: The Viola and Jones Algorithmmentioning

confidence: 99%

“…This puts a particularly heavy constraint on the immunity of the system to translation to or away from the TV. Alexandra et al [2] in their paper have suggested a way to make the robust face detection algorithm developed by Viola and Jones (hats off to them), scale invariant. We adopt their approach and apply it to hand gesture recognition.…”

Section: Introductionmentioning

confidence: 99%

A Gesture Recognition Interface for a Set-Top Box

Srinivasan¹

2010

2010 First International Conference on Integrated Intelligent Computing

View full text Add to dashboard Cite

As the service providers are integrating internet and broadcast channels, the functionality of a set-top box has increased to much more than a simple multiplexer and decoder of television channels. The functionality offered by the 'remote control' is insufficient. Gesture recognition offers a useful solution to this problem as the functionality of such a system can be increased by a simple firmware upgrade over the network for the existing system. Also having a good seamless interface is a good selling point and the product will attract a lot of attention.Building such a system is challenging because its performance has to be real time and the cost of it should not be much more than the traditional remote control. In this paper we have developed such a system using a single CMOS sensor that is capable of recognizing hand gestures in the range of 0.5m-6m distance in a variety of backgrounds in order to keep its operational range as close as possible to the remote control. There is also no need for any calibration of the system before using it. We have benchmarked its performance on many of the popular embedded processors available in the market and the results are promising.

show abstract

Translation and scale-invariant gesture recognition in complex scenes

Cited by 28 publications

References 18 publications

Multi-modal social signal analysis for predicting agreement in conversation settings

Multi-modal social signal analysis for predicting agreement in conversation settings

Comparative evaluation of static gesture recognition techniques based on nearest neighbor, neural networks and support vector machines

A Gesture Recognition Interface for a Set-Top Box

Contact Info

Product

Resources

About