Early Recognition and Prediction of Gestures

Mori, Akira; Uchida, Seiichi; Kurazume, Ryo; Taniguchi, Rin-ichiro; Hasegawa, Tsutomu; Sakoe, Hiroaki

doi:10.1109/icpr.2006.467

Cited by 59 publications

(40 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(8,9) show the simulation results of Cases 3 and 4. In the cases, each individual tries to trace Gaussian functions according to the information of only the locally best solutions, not the self best solution.…”

Section: B Preliminary Simulation Resultsmentioning

confidence: 99%

“…Visual systems have been discussed from various points of view [1][2][3][4][5][6][7][8][9][10]. Furthermore, various types of intelligent methods [11][12][13][14][15][16][17][18][19][20][21][22][23] have been applied for image processing in real world applications thanks to the development of cheap and small digital cameras and signal processing boards with low energy consumption.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary Robot Vision for People Tracking Based on Local Clustering

Sulistijono¹,

Kubota²

2008

TOCSJ

View full text Add to dashboard Cite

This paper discusses the role of evolutionary computation in visual perception for partner robots. The search of evolutionary computation has many analogies with human visual search. First of all, we discuss the analogies between the evolutionary search and human visual search. Next, we propose the concept of evolutionary robot vision, and a human tracking method based on the evolutionary robot vision. Finally, we show experimental results of the human tracking to discuss the effectiveness of our proposed method.

show abstract

Section: B Preliminary Simulation Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evolutionary Robot Vision for People Tracking Based on Local Clustering

Sulistijono¹,

Kubota²

2008

TOCSJ

View full text Add to dashboard Cite

show abstract

“…Mori et al [16] proposed a system for early recognition and anticipation, based on continuous dynamic programming.…”

Section: Related Workmentioning

confidence: 99%

Continuous Realtime Gesture Following and Recognition

Bevilacqua

Zamborlin

Sypniewski

et al. 2010

Lecture Notes in Computer Science

122

View full text Add to dashboard Cite

Abstract. We present a HMM based system for real-time gesture analysis. The system outputs continuously parameters relative to the gesture time progression and its likelihood. These parameters are computed by comparing the performed gesture with stored reference gestures. The method relies on a detailed modeling of multidimensional temporal curves. Compared to standard HMM systems, the learning procedure is simplified using prior knowledge allowing the system to use a single example for each class. Several applications have been developed using this system in the context of music education, music and dance performances and interactive installation. Typically, the estimation of the time progression allows for the synchronization of physical gestures to sound files by time stretching/compressing audio buffers or videos.

show abstract

“…These include Dynamic Time Warping, the $1 Recognizer (Wobbrock, Wilson, & Li, 2007) and $N Recognizer (Anthony & Wobbrock, 2010 Most recognition systems output however results in discrete time, typically upon gesture completion. There are some systems that continuously report estimation on gesture classes or characteristics (Mori et al, 2006;Bevilacqua et al, 2010), allowing for prediction and "early recognition" meaning that the ability to recognize before the end of the gesture execution.…”

Section: Gesture Recognitionmentioning

confidence: 99%

Designing natural gesture interaction for archaeological data in immersive environments

Albertini

Brogni

Olivito

et al. 2017

Virtual archaeol. rev.

View full text Add to dashboard Cite

Abstract:Archaeological data are heterogeneous, making it difficult to correlate and combine different types. Datasheets and pictures, stratigraphic data and 3D models, time and space mixed together: these are only a few of the categories a researcher has to deal with. New technologies may be able to help in this process and trying to solve research related problems needs innovative solutions. In this paper, we describe the whole process for the design and development of a prototype application that uses an Immersive Virtual Reality system to acces archaeological excavation 3D data through the Gesture Variation Follower (GVF) algorithm. This makes it possible to recognise which gesture is being performed and how it is performed. Archaeologists have participated actively in the design of the interface and the set of gestures used for triggering the different tasks. Interactive machine learning techniques have been used for the real time detection of the gestures. As a case study the agora of Segesta (Sicily, Italy) has been selected. Indeed, due to the complex architectural features and the still ongoing fieldwork activities, Segesta represents an ideal context where to test and develop a research approach integrating both traditional and more innovative tools and methods.Key words: cyber-archaeology, gesture recognition, virtual reality (VR) Resumen:Los datos arqueológicos son heterogéneos y difíciles de correlacionar entre diferentes tipos. Las fichas técnicas y las imágenes, los datos estratigráficos y los modelos 3D, el tiempo y el espacio mezclados entre sí: son solamente algunas de las categorías que el investigador tiene que tratar. Las nuevas tecnologías pueden ser capaces de ayudar en este proceso, llenando el vacío entre la historia y el futuro, y tratar de resolver las necesidades de investigación con soluciones innovadoras. En este trabajo se describe todo el proceso que conlleva el diseño y desarrollo de un prototipo de aplicación, que utiliza un sistema de realidad virtual inmersiva para acceder a datos 3D de la excavación arqueólogica a través del algoritmo Gesture Variation Follower (GVF), que permite reconocer lo que el gesto está realizando y cómo se realiza. Los arqueólogos han participado activamente en el diseño de la interfaz y el conjunto de gestos utilizados para la activación de las diferentes tareas. Se han utilizado avanzadas técnicas de aprendizaje automático para la detección en tiempo real de los gestos. Como caso de estudio se eligió el ágora de Segesta (Sicilia, Italia). De hecho, debido a las características arquitectónicas complejas y las actividades de trabajo de campo todavía en curso, Segesta representa un contexto ideal donde poner a prueba y desarrollar un enfoque de investigación integrando ambas herramientas tradicionales y los más innovadores métodos.Palabras clave: ciber-arqueología, reconocimiento de gestos, realidad virtual (RV)

show abstract

Early Recognition and Prediction of Gestures

Cited by 59 publications

References 3 publications

Evolutionary Robot Vision for People Tracking Based on Local Clustering

Evolutionary Robot Vision for People Tracking Based on Local Clustering

Continuous Realtime Gesture Following and Recognition

Designing natural gesture interaction for archaeological data in immersive environments

Contact Info

Product

Resources

About