Presentation 2019-01-29
[Poster Presentation] An Optimization of Drone Flight Plan based on Simulation for Precise Three-Dimensional Reconstruction
Tatsuya Kobayashi, Zhang Heming, Shin Kawai, Hajime Nobuhara,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the present three-dimensional reconstruction scheme using drone, various parameters such as the photographing position of the drones and the number of photos are based on the intuition and experience of the operator in many cases. There is room for optimizing reconstruction accuracy by adjusting them. In this study, we construct a scheme to automatically attempt and optimize combinations of various parameters within Drone's flight simulator, independent of operator's intuition and experience. By using Bayesian optimization, we solves the problem that many combinations can not be attempted because 3-dimensional reconstruction for combinations of parameters takes much calculation cost. In this study, we show the effectiveness of the proposed method by optimizing the number of images and the flight altitude using Bayesian optimization in the flight simulator of Drone. As a result, by using Bayesian optimization, the error of Three-dimensional reconstruction could be reduced by 0.49 times as compared with the case without Bayesian optimization.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Drone / Structure from Motion / 3D-reconstruction / Bayesian optimization
Paper # ASN2018-95
Date of Issue 2019-01-21 (ASN)

Conference Information
Committee ASN
Conference Date 2019/1/28(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyuukamura Ibusuki
Topics (in Japanese) (See Japanese page)
Topics (in English) Ambient intelligence, Sensor networks, Poster session, etc.
Chair Hiraku Okada(Nagoya Univ.)
Vice Chair Koji Yamamoto(Kyoto Univ.) / Jin Nakazawa(Keio Univ.) / Kazuya Monden(Hitachi)
Secretary Koji Yamamoto(NICT) / Jin Nakazawa(Sophia Univ.) / Kazuya Monden(Kanagawa Inst. of Tech.)
Assistant Masafumi Hashimoto(Osaka Univ.) / Tomoyuki Ota(Hiroshima City Univ.) / Tatsuya Kikuzuki(Fujitu Lab.) / Ryo Nakano(HITACHI) / Yoshifumi Hotta(Mitsubishi Electric)

Paper Information
Registration To Technical Committee on Ambient intelligence and Sensor Networks
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Poster Presentation] An Optimization of Drone Flight Plan based on Simulation for Precise Three-Dimensional Reconstruction
Sub Title (in English)
Keyword(1) Drone
Keyword(2) Structure from Motion
Keyword(3) 3D-reconstruction
Keyword(4) Bayesian optimization
1st Author's Name Tatsuya Kobayashi
1st Author's Affiliation University of Tsukuba(Univ. Tsukuba)
2nd Author's Name Zhang Heming
2nd Author's Affiliation University of Tsukuba(Univ. Tsukuba)
3rd Author's Name Shin Kawai
3rd Author's Affiliation University of Tsukuba(Univ. Tsukuba)
4th Author's Name Hajime Nobuhara
4th Author's Affiliation University of Tsukuba(Univ. Tsukuba)
Date 2019-01-29
Paper # ASN2018-95
Volume (vol) vol.118
Number (no) ASN-428
Page pp.pp.89-93(ASN),
#Pages 5
Date of Issue 2019-01-21 (ASN)