著者
長松 隆 菅野 裕介 竹村 憲太郎
出版者
ヒューマンインタフェース学会
雑誌
ヒューマンインタフェース学会論文誌 (ISSN:13447262)
巻号頁・発行日
vol.23, no.1, pp.73-88, 2021 (Released:2021-02-25)
参考文献数
132

The need for personal calibration has been one of the most significant technical limitations in video-based eye tracking, and there have been many research attempts on calibration-free techniques. This paper reviews calibration-free eye tracking techniques from two perspectives: person-independent gaze estimation and implicit personal calibration. Person-independent gaze estimation is the technique to infer gaze directions without considering person-dependent parameters. The methods in this category include both model-based approaches to estimate the optical axis angle and appearance-based approaches to obtain generic gaze estimation functions. Implicit personal calibration refers to the technique to adjust person-dependent parameters for better estimation accuracy without relying on any explicit calibration instruction. The methods in this category utilize various cues such as bottom-up fixation prediction, environmental/anatomical constraints, and correlation in temporal patterns to predict gaze target locations. This review summarizes representative approaches in both categories and discusses future perspectives and potential application scenarios.
著者
荒木 天外 竹村 憲太郎 怡土 順一 松本 吉央 高松 淳 小笠原 司
出版者
一般社団法人 日本ロボット学会
雑誌
日本ロボット学会誌 (ISSN:02891824)
巻号頁・発行日
vol.28, no.1, pp.106-111, 2010 (Released:2012-01-25)
参考文献数
13
被引用文献数
2 2

In this research, a Universal map, which can be converted to individual maps for heterogeneous mobile robots, is proposed. A Universal map can be generated using our developed measurement robot, and it is composed of a textured 3D environment model. Therefore, every robot can use a Universal map as a common map, and it is utilized for various localization technologies such as view-based and LRF-based methods. In LRF-based localization, accurate localization is achieved using a specific map, which is generated from a Universal map. In a view-based approach, localization and navigation are achieved using rendered images. The use of a Universal map enables generation of these maps automatically. The effectiveness of this approach is confirmed through experiments.
著者
佐藤 志保理 山口 明彦 竹村 憲太郎 高松 淳 小笠原 司
出版者
一般社団法人日本機械学会
雑誌
ロボティクス・メカトロニクス講演会講演概要集
巻号頁・発行日
vol.2011, pp."1A1-O11(1)"-"1A1-O11(4)", 2011-05-26

In this paper, we study a method to translate the style of an input motion which is obtained by a motion capture system. For this aim, we model the difference of motions coming from the actor's attribute, such as gender and age. Especially, we focus on the difference coming from the gender, and model the difference of poses (joint angles) between males and females by using a Gaussian process regression. In training the model, we utilize Multifactor Gaussian Process Model to align the training set of motions in cyclic phase. In the experiments, we train the filter with walking motions of males and females, then we apply the filter to walking, running, and jumping motions of males. The results demonstrate that the filter successfully translates the motion into a womanish one.
著者
竹村 憲太郎 松本 吉央 小笠原 司
出版者
一般社団法人情報処理学会
雑誌
情報処理学会研究報告. HI,ヒューマンインタフェース研究会報告 (ISSN:09196072)
巻号頁・発行日
vol.110, pp.25-30, 2004-09-10

本研究は対面式会議等の状況において複数人の注視情報を利用し,注意の集中する位置(場の注意)の推定手法を提案する.本手法では複数人の視線情報(3次元ベクトル)から幾何学的に3次元空間中の交点を求め,場の注意を推定する.その結果,注意を物体や人単位ではなく,連続的な3次元座標として推定することが可能となる.本稿ではしりとりや対面式会議等の状況において,場の注意を推定し,その有効性を確認した.