Zobrazeno 1 - 10
of 129
pro vyhledávání: '"Hiromitsu FUJII"'
Publikováno v:
ROBOMECH Journal, Vol 7, Iss 1, Pp 1-10 (2020)
Abstract In robot teleoperation, a lack of depth information often results in collisions between the robots and obstacles in its path or surroundings. To address this issue, free viewpoint images can greatly benefit the operators in terms of collisio
Externí odkaz:
https://doaj.org/article/628fcfe6ef8548cb9267ef3d2344a2ff
Autor:
Kenta KAWAMATA, Hiromitsu FUJII, Yuta HATAKEYAMA, Masato DOMAE, Takaaki MORIMOTO, Takeya IZUMIKAWA
Publikováno v:
Nihon Kikai Gakkai ronbunshu, Vol 87, Iss 898, Pp 20-00122-20-00122 (2021)
In Japan, “i-Construction” is promoted to improve the productivity of the construction industries by utilizing Information and Communication Technology (ICT). In particular, estimation of sediment volume at construction sites is highly demanded,
Externí odkaz:
https://doaj.org/article/a995006f29424770834abfa4a72589aa
Publikováno v:
IEEE Access, Vol 7, Pp 150306-150317 (2019)
In this paper, we propose the octave deep plane-sweeping network (OctDPSNet). OctDPSNet is a novel learning-based plane-sweeping stereo, which drastically reduces the required GPU memory and computation time while achieving a state-of-the-art depth e
Externí odkaz:
https://doaj.org/article/dc59c73ff01e45fe9307c41e1b75d451
Publikováno v:
ROBOMECH Journal, Vol 4, Iss 1, Pp 1-10 (2017)
Abstract In this paper we present an online unsupervised method based on clustering to find defects in concrete structures using hammering. First, the initial dataset of sound samples is roughly clustered using the k-means algorithm with the k-means+
Externí odkaz:
https://doaj.org/article/62d16334915542dc90f6107f7dab55a6
Autor:
Soichiro IWATAKI, Wei SUN, Hiromitsu FUJII, Masataka FUCHIDA, Alessandro MORO, Takashi NODA, Kazuki KURE, Koichi NAKAZAWA, Hiroshi YOSHINADA, Atsushi YAMASHITA, Hajime ASAMA
Publikováno v:
Nihon Kikai Gakkai ronbunshu, Vol 84, Iss 866, Pp 18-00196-18-00196 (2018)
This research proposes a new image visualization method of bulldozer and surrounding dangerous area to operator. Bulldozers are operated on uneven terrain which contains dangerous slope or obstacle. The objective of this research is to visualize the
Externí odkaz:
https://doaj.org/article/d7962a2e904a4f20bcbedd379a9fd05b
Autor:
Akira TAKEUCHI, Hiromitsu FUJII, Atsushi YAMASHITA, Masayuki TANAKA, Ryuho KATAOKA, Yoshizumi MIYOSHI, Masatoshi OKUTOMI, Hajime ASAMA
Publikováno v:
Nihon Kikai Gakkai ronbunshu, Vol 82, Iss 834, Pp 15-00428-15-00428 (2016)
Three-dimensional analysis of aurora is important for the research of solar wind and magnetic storms, because aurora reflects the relationship between solar wind and terrestrial magnetism. Therefore a method to reconstruct a three-dimensional shape o
Externí odkaz:
https://doaj.org/article/624e4014e7df4b41987f8ff258d96680
Publikováno v:
Nihon Kikai Gakkai ronbunshu, Vol 82, Iss 834, Pp 15-00426-15-00426 (2016)
The hammering test has been widely used for inspection of social infrastructures because of its accuracy and efficiency of operation. In order to automate and apply the method to actual inspection sites, it is important for the system to calibrate it
Externí odkaz:
https://doaj.org/article/96e94bdc9a6448e5b7e4a93478e93867
Autor:
Takaaki SATO, Hiromitsu FUJII, Alessandro Moro, Kazuya SUGIMOTO, Akira NOZUE, Yoichi MIMURA, Katsumi OBATA, Atsushi YAMASHITA, Hajime ASAMA
Publikováno v:
Nihon Kikai Gakkai ronbunshu, Vol 81, Iss 823, Pp 14-00031-14-00031 (2015)
This paper describes a development of bird's-eye view system for teleoperation. Emergent disaster recoveries are important when natural disaters occur. Unmanned construction is used to recover from natural disasters such as landslide and pyroclastic
Externí odkaz:
https://doaj.org/article/35cfe70297d54e1bb94dd96e62c9ec36
Publikováno v:
Journal of the Robotics Society of Japan. 40:449-452
Publikováno v:
IEEE/ASME Transactions on Mechatronics. 26:2826-2834
The automation of inspection methods for concrete structures is a pressing issue worldwide. Weakly supervised approaches, i.e., approaches based on supervision in other forms than traditional class labels, offer a unique mix of automation and human i