TY - GEN
T1 - Improvement of 3D Pose Estimation Abilities by Light-Emitting-3D Marker for AUV Docking
AU - Yamashita, Kohei
AU - Yi, Hsu Horng
AU - Yamada, Daiki
AU - Mukada, Naoki
AU - Lwin, Khin New
AU - Myint, Myo
AU - Toda, Yuichiro
AU - Matsuno, Takayuki
AU - Minami, Mamoru
N1 - Funding Information:
This work is supported by JSPS KAKENHI Grant Number 16K06183 and KOWA CORPORATION for the development of ROV.
PY - 2019/1/7
Y1 - 2019/1/7
N2 - Disturbances of turbidity and low illuminance are problems in real sea areas when recognizing objects with cameras. Therefore, the recognition target was made to emit light so that it can be recognized correctly even in that environment. However, a suitable light intensity of the target was not decided and it is obvious that recognition results was changed by light intensity of the target. This paper presents the analysis of recognition accuracy of the Real-time 3D estimation system by changing the current value of each color LED (red, green, blue) under turbid and low illuminance. Recognition experiments were conducted at the distance 600 [mm] between the ROV and 3D marker. The turbidity level was set constant value. The current value was changing from 0 [mA] to 16 [mA] for each LED individually. The best current for each LED was optimized by the fitness value and estimation value of position and orientation. The results showed that the recognition accuracy of the proposed system was improved by using optimized lighting intensity.
AB - Disturbances of turbidity and low illuminance are problems in real sea areas when recognizing objects with cameras. Therefore, the recognition target was made to emit light so that it can be recognized correctly even in that environment. However, a suitable light intensity of the target was not decided and it is obvious that recognition results was changed by light intensity of the target. This paper presents the analysis of recognition accuracy of the Real-time 3D estimation system by changing the current value of each color LED (red, green, blue) under turbid and low illuminance. Recognition experiments were conducted at the distance 600 [mm] between the ROV and 3D marker. The turbidity level was set constant value. The current value was changing from 0 [mA] to 16 [mA] for each LED individually. The best current for each LED was optimized by the fitness value and estimation value of position and orientation. The results showed that the recognition accuracy of the proposed system was improved by using optimized lighting intensity.
KW - Active/Lighting 3D marker
KW - LED's current value
KW - Pose Estimation
KW - Turbidity
UR - http://www.scopus.com/inward/record.url?scp=85061826643&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061826643&partnerID=8YFLogxK
U2 - 10.1109/OCEANS.2018.8604867
DO - 10.1109/OCEANS.2018.8604867
M3 - Conference contribution
AN - SCOPUS:85061826643
T3 - OCEANS 2018 MTS/IEEE Charleston, OCEAN 2018
BT - OCEANS 2018 MTS/IEEE Charleston, OCEAN 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - OCEANS 2018 MTS/IEEE Charleston, OCEANS 2018
Y2 - 22 October 2018 through 25 October 2018
ER -