K
Keisuke Nakamura
Researcher at Honda
Publications - 153
Citations - 1631
Keisuke Nakamura is an academic researcher from Honda. The author has contributed to research in topics: Acoustic source localization & Signal. The author has an hindex of 18, co-authored 143 publications receiving 1324 citations. Previous affiliations of Keisuke Nakamura include Tokyo Institute of Technology & Centre national de la recherche scientifique.
Papers
More filters
Proceedings ArticleDOI
Model-based Region of Interest Segmentation for Remote Photoplethysmography
TL;DR: It is shown that this modification in how the spatial averaging of the ROI pixels is calculated can significantly increase the final performance of heart rate estimate.
Proceedings ArticleDOI
Remote Photoplethysmography measurement using constrained ICA
TL;DR: The constrained ICA (cICA) method is proposed where the knowledge about the periodicity of the blood flow signal along with the CHROM constraint is taken advantage and shows better performance compared to conventional ICA and other state of the art methods in terms of accuracy and robustness.
Patent
Acoustic processing device and acoustic processing method
TL;DR: In this article, a sound source localization part estimates the direction of sound sources from acoustic signals of a plurality of channels, which indicate the components of the sound sources, and a sound sources identification part determines the types of the different sound sources for the acoustic signals according to sound sources.
Proceedings ArticleDOI
Robust sound source mapping using three-layered selective audio rays for mobile robots
TL;DR: This paper investigates sound source mapping in a real environment using a mobile robot using a three-layered selective audio ray tracing mechanism, which integrates occupancy grids and sound source localization using a laser range finder and a microphone array.
Proceedings ArticleDOI
Robust Real-Time Hand Gestural Recognition for Non-Verbal Communication with Tabletop Robot Haru
TL;DR: A novel hand gestural understanding system is implemented by training a machine-learning architecture for real-time hand gesture recognition with the Leap Motion that is able to combine multiple gesture labels for recognition of consecutive gestures without clear movement boundaries.