TY - GEN
T1 - Use of LSTM Regression and Rotation Classification to Improve Camera Pose Localization Estimation
AU - Xu, Meng
AU - Wang, Lingfeng
AU - Ren, Jian
AU - Poslad, Stefan
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/30
Y1 - 2020/10/30
N2 - More accurately estimating camera pose can be used to greatly improve localization in applications such as augmented reality, autonomous driving, and intelligent robots. Deep learning methods have achieved great progress to improve accuracy but still have limitations with respect to rotation, which results in angle regression errors. In this work, we combine a LSTM module with rotation classification loss to regress the camera pose. The algorithm uses a robust processing pipeline to supervise the pose estimation with dynamic, weighted, multi-losses in order to limit separate Euler angle (yaw, pitch, roll) losses, and common translation-quaternion losses. An empirical test on the 7Scenes benchmark dataset shows better results than when using common absolute pose regression methods.
AB - More accurately estimating camera pose can be used to greatly improve localization in applications such as augmented reality, autonomous driving, and intelligent robots. Deep learning methods have achieved great progress to improve accuracy but still have limitations with respect to rotation, which results in angle regression errors. In this work, we combine a LSTM module with rotation classification loss to regress the camera pose. The algorithm uses a robust processing pipeline to supervise the pose estimation with dynamic, weighted, multi-losses in order to limit separate Euler angle (yaw, pitch, roll) losses, and common translation-quaternion losses. An empirical test on the 7Scenes benchmark dataset shows better results than when using common absolute pose regression methods.
KW - Euler angles
KW - camera pose regression
KW - long term short term memory (LSTM)
KW - multi-loss
UR - https://www.scopus.com/pages/publications/85098103107
U2 - 10.1109/ASID50160.2020.9271762
DO - 10.1109/ASID50160.2020.9271762
M3 - 会议稿件
AN - SCOPUS:85098103107
T3 - Proceedings of the International Conference on Anti-Counterfeiting, Security and Identification, ASID
SP - 6
EP - 10
BT - Proceedings of 2020 IEEE 14th International Conference on Anti-Counterfeiting, Security, and Identification, ASID 2020
PB - IEEE Computer Society
T2 - 14th IEEE International Conference on Anti-Counterfeiting, Security, and Identification, ASID 2020
Y2 - 30 October 2020 through 1 November 2020
ER -