Synthesizing Realistic Image-based Avatars by Body Sway Analysis

Nishiyama, Masashi; Miyauchi, Tsubasa; Yoshimura, Hideyuki; Iwai, Yoshio

doi:10.1145/2974804.2974807

Cited by 11 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Movements of whole body occur around a central position. An existing method [27] measures the movements using the body regions, under the assumption that all body parts move synchronously in the same direction. Although the method considers the temporal changes in movements, it ignores the spatial changes.…”

Section: Measuring Temporal and Spatial Changes In Local Movementsmentioning

confidence: 99%

See 1 more Smart Citation

Temporal and Spatial Analysis of Local Body Sway Movements for the Identification of People

Kamitani

Yoshimura

Nishiyama

et al. 2019

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

We propose a method for accurately identifying people using temporal and spatial changes in local movements measured from video sequences of body sway. Existing methods identify people using gait features that mainly represent the large swinging of the limbs. The use of gait features introduces a problem in that the identification performance decreases when people stop walking and maintain an upright posture. To extract informative features, our method measures small swings of the body, referred to as body sway. We extract the power spectral density as a feature from local body sway movements by dividing the body into regions. To evaluate the identification performance using our method, we collected three original video datasets of body sway sequences. The first dataset contained a large number of participants in an upright posture. The second dataset included variation over the long term. The third dataset represented body sway in different postures. The results on the datasets confirmed that our method using local movements measured from body sway can extract informative features for identification.

show abstract

Section: Measuring Temporal and Spatial Changes In Local Movementsmentioning

confidence: 99%

“…, T , we compute a mask image m t in which a pixel takes a value of 1 if it is within a body region and 0 otherwise. The original method [27] uses algorithm 1 to infer the reference time r, which represents the temporal center of swings, from the whole body region in the mask image.…”

Section: Measuring Temporal and Spatial Changes In Local Movementsmentioning

confidence: 99%

Temporal and Spatial Analysis of Local Body Sway Movements for the Identification of People

Kamitani

Yoshimura

Nishiyama

et al. 2019

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…There is a demand for a system that enables a human and machine to naturally interact through an avatar [1]- [5]. Such a system would have the ability to interact with users in various scenarios, for example, navigating in public spaces (e.g., airport, station, or city office) throughout 24 hours.…”

Section: Introductionmentioning

confidence: 99%

“…Such a system would have the ability to interact with users in various scenarios, for example, navigating in public spaces (e.g., airport, station, or city office) throughout 24 hours. We discuss an image-based avatar system [3]- [5] in which a video sequence acquired from a real person is used on a life-sized display. We consider that the image-based avatar waits for a user and starts to navigate toward the user in an information center.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, if the awareness state is not embedded in the image-based avatar, the approaching user will be confused because the timing of the response of the avatar is delayed. The existing methods for image-based avatars mainly focus on the action state [3], [4] and partly on the wait state [5]. However, these existing methods do not sufficiently consider how to address the awareness state and response state for the image-based avatar.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Embedding the Awareness State and Response State in an Image-Based Avatar to Start Natural User Interaction

Miyauchi

Ono

Yoshimura

et al. 2017

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

SUMMARYWe propose a method for embedding the awareness state and response state in an image-based avatar to smoothly and automatically start an interaction with a user. When both states are not embedded, the image-based avatar can become non-responsive or slow to respond. To consider the beginning of an interaction, we observed the behaviors between a user and receptionist in an information center. Our method replayed the behaviors of the receptionist at appropriate times in each state of the imagebased avatar. Experimental results demonstrate that, at the beginning of the interaction, our method for embedding the awareness state and response state increased subjective scores more than not embedding the states. key words: image-based avatar, beginning of interaction, awareness state, response state

show abstract

Investigation of Motion Video Enhancement for Image-Based Avatars on Small Displays

Miyauchi

Ganaha

Nishiyama

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Synthesizing Realistic Image-based Avatars by Body Sway Analysis

Cited by 11 publications

References 16 publications

Temporal and Spatial Analysis of Local Body Sway Movements for the Identification of People

Temporal and Spatial Analysis of Local Body Sway Movements for the Identification of People

Embedding the Awareness State and Response State in an Image-Based Avatar to Start Natural User Interaction

Investigation of Motion Video Enhancement for Image-Based Avatars on Small Displays

Contact Info

Product

Resources

About