Yasushi Sumi

Dr. Yasushi Sumi

orcid

Research Focus & Metrics

Academic Career Length

31Years (1996-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2002 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YSYasushi Sumi
Yasushi Sumi
YKYoshihiro Kawai
Yoshihiro Kawai
TYTakashi Yoshimi
Takashi Yoshimi
FTFumiaki Tomita
Fumiaki Tomita

1 May 2012
Verified
Conference Paper
Closed access
HTHideyuki Tanaka
Hideyuki Tanaka
YSYasushi Sumi
Yasushi Sumi
YMYoshio Matsumoto
Yoshio Matsumoto
Visual marker is a useful assistive tool for service robots. Existing planar visual markers have poor accuracy and stability in pose estimation, especially in frontal direction. In this study, we developed a novel visual marker based on a new principle enabling accurate and stable pose estimation even by observation from frontal direction. The marker has moiré patterns which consist of lenticular lens and stripe pattern, which vary their appearance according to visual-line angle of observation. We can extract pose information from the pattern by a single camera. We developed a prototype of the marker and an algorithm for pose estimation, and then demonstrated its superiority to existing markers by some validation tests.

1 October 2012
Verified
Conference Paper
Closed access
HTHideyuki Tanaka
Hideyuki Tanaka
YSYasushi Sumi
Yasushi Sumi
YMYoshio Matsumoto
Yoshio Matsumoto
Visual markers are useful assistive tool for service robots. Existing planar visual markers have poor accuracy in pose estimation, especially in frontal direction. We solved this problem by a novel principle using a microlens array. The marker displays a changing moiré pattern according to the visual-line direction. We can extract the pose information from the pattern by image processing using a single camera. The developed marker and the processing algorithm enable high-accuracy pose estimation even by observation from frontal direction. We verified its superiority to the conventional method by some validation tests. The marker is an extension of a marker we previously developed, and is more easily fabricated.

1 February 1998 in Physical Review C
Verified
Journal Article
Open access
PDF file
IBI. G. Bearden
I. G. Bearden
HBH. Bøggild
H. Bøggild
JBJ. Boissevain
J. Boissevain
JDJ. Dodd
J. Dodd
SES. Esumi
S. Esumi
NXN. Xu
N. Xu
Experiment NA44 has measured proton and antiproton distributions at midrapidity in sulphur and proton collisions with nuclear targets at 200 and 450GeV/c per nucleon respectively. The inverse slopes of transverse mass distributions increase with system size for both protons and antiprotons but are slightly lower for antiprotons. This could happen if antiprotons are annihilated in the nuclear medium. The antiproton yield increases with system size and centrality and is largest at midrapidity. The proton yield also increases with system size and centrality, but decreases from backward rapidity to midrapidity. The stopping of protons at these energies lies between the full stopping and nuclear transparency scenarios. The data are in reasonable agreement with RQMD predictions except for the antiproton yields from sulphur-nucleus collisions.

11 November 2002
Verified
Conference Paper
Closed access
SLS. Lao
S. Lao
YSYasushi Sumi
Yasushi Sumi
MKM. Kawade
M. Kawade
FTF. Tomita
F. Tomita

1 May 2015
Verified
Conference Paper
Closed access
BKBong Keun Kim
Bong Keun Kim
HTHideyuki Tanaka
Hideyuki Tanaka
YSYasushi Sumi
Yasushi Sumi
In this paper, a robotic wheelchair using only a pan-tilt-zoom camera is proposed for developing a robotic system which enables a user to navigate in complex environment at low cost. For realizing the proposed system, a high accuracy visual marker, LentiBar which is capable of achieving a high level of precision in positioning and orienting a robotic wheelchair is utilized and its application to door crossing for a robotic wheelchair is presented. Since the visual marker is attached on the top of the target door through which the wheelchair is going to pass, the typical problems for achieving geometric features of the environment can be easily addressed. Door crossing navigation methods are also explained, which enable automatic and hybrid navigation of the robotic wheelchair. Finally, experimental results show the feasibility of the proposed navigation method and the robotic wheelchair system.