TY - GEN
T1 - Camera Attitude Estimation by Neural Network Using Classification Network Method Instead of Numerical Regression
AU - Kawai, Hibiki
AU - Yoshiuchi, Wataru
AU - Hirakawa, Yasunori
AU - Shibuya, Takumi
AU - Matsuda, Takumi
AU - Kuroda, Yoji
N1 - Funding Information:
We have received generous support from new Energy and Industrial Technology Development Organization (NEDO) and Meiji University Research Cluster for Autonomous Robotic Systems for study. We would like thank it.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In this paper, we propose a method for estimating the camera pose using a classification neural network based on the idea of OCR. Some terrestrial robots can exhibit high maneuverability by freely tilting their upper bodies. When estimating the posture of such robots, posture estimation using IMU and gyroscopic sensors as in the case of drones is affected by the noise generated by the unevenness of the ground, making posture estimation difficult. Pose estimation using deep learning from camera images is one solution to these problems, and various studies have been conducted in the past. However, the accuracy of pose estimation using only inference by deep learning with camera images is extremely poor and is not practical. In order to solve this problem, this paper proposes a classification neural network based on the idea of OCR, which can ensure high inference accuracy in the pose estimation task.
AB - In this paper, we propose a method for estimating the camera pose using a classification neural network based on the idea of OCR. Some terrestrial robots can exhibit high maneuverability by freely tilting their upper bodies. When estimating the posture of such robots, posture estimation using IMU and gyroscopic sensors as in the case of drones is affected by the noise generated by the unevenness of the ground, making posture estimation difficult. Pose estimation using deep learning from camera images is one solution to these problems, and various studies have been conducted in the past. However, the accuracy of pose estimation using only inference by deep learning with camera images is extremely poor and is not practical. In order to solve this problem, this paper proposes a classification neural network based on the idea of OCR, which can ensure high inference accuracy in the pose estimation task.
UR - http://www.scopus.com/inward/record.url?scp=85126223589&partnerID=8YFLogxK
U2 - 10.1109/SII52469.2022.9708864
DO - 10.1109/SII52469.2022.9708864
M3 - Conference contribution
AN - SCOPUS:85126223589
T3 - 2022 IEEE/SICE International Symposium on System Integration, SII 2022
SP - 401
EP - 407
BT - 2022 IEEE/SICE International Symposium on System Integration, SII 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE/SICE International Symposium on System Integration, SII 2022
Y2 - 9 January 2022 through 12 January 2022
ER -