TY - GEN
T1 - HueCode2
T2 - 18th IEEE International Conference on Automation Science and Engineering, CASE 2022
AU - Yokota, Yoshiki
AU - Fujikura, Daiki
AU - Okada, Yoshito
AU - Ohno, Kazunori
AU - Tadakuma, Kenjiro
AU - Tadokoro, Satoshi
N1 - Funding Information:
ACKNOWLEDGMENT This research was conducted under the contract "R&D for the realization of high-precision radio wave emulator in cyberspace" (JPJ000254) with the Ministry of Internal Affairs and Communications of Japan.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - We studied HueCode, i.e., a metamarker with multiple fiducial markers overlaid in different colored layers. HueCode consists of relative pose markers (e.g., AR markers) and additional information markers (e.g., QR codes) through overlaying within the area of a single marker. Robots can simultaneously recognize the relative pose as well as additional information required for movement and recognition from a single HueCode. However, conventional coloring schemes and recognition methods deal with degradation of the recognition performance by illumination. Thus, we propose HueCode2 to solve this problem. The new coloring scheme allows the use of any color that is easy to distinguish. The new recognition method uses support vector machines trained under various illumination conditions to identify colors. The experimental results show that these methods improve recognition rates over conventional HueCode under various illumination conditions including indoor and outdoor environment.
AB - We studied HueCode, i.e., a metamarker with multiple fiducial markers overlaid in different colored layers. HueCode consists of relative pose markers (e.g., AR markers) and additional information markers (e.g., QR codes) through overlaying within the area of a single marker. Robots can simultaneously recognize the relative pose as well as additional information required for movement and recognition from a single HueCode. However, conventional coloring schemes and recognition methods deal with degradation of the recognition performance by illumination. Thus, we propose HueCode2 to solve this problem. The new coloring scheme allows the use of any color that is easy to distinguish. The new recognition method uses support vector machines trained under various illumination conditions to identify colors. The experimental results show that these methods improve recognition rates over conventional HueCode under various illumination conditions including indoor and outdoor environment.
UR - http://www.scopus.com/inward/record.url?scp=85141672038&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85141672038&partnerID=8YFLogxK
U2 - 10.1109/CASE49997.2022.9926583
DO - 10.1109/CASE49997.2022.9926583
M3 - Conference contribution
AN - SCOPUS:85141672038
T3 - IEEE International Conference on Automation Science and Engineering
SP - 583
EP - 588
BT - 2022 IEEE 18th International Conference on Automation Science and Engineering, CASE 2022
PB - IEEE Computer Society
Y2 - 20 August 2022 through 24 August 2022
ER -