TY - GEN
T1 - ACCURATE HEAD POSE ESTIMATION BASED ON MULTI-STAGE REGRESSION
AU - Liu, Yinchuan
AU - Gong, Yufei
AU - Lu, Zheng
AU - Zhang, Xuetao
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper proposes a method for head pose estimation from a single image. We employ a multi-stage regression strategy. To overcome the discontinuity of Euler angles and quaternions and avoid the additional constraints required to directly regress the rotation matrix, we apply a continuous 6D representation to the head pose estimation problem. Each stage of the network regresses two 1×3 vectors, which are then transformed into a 3 × 3 rotation matrix by this continuous 6D representation. To better perceive the difference in rotation angles, we adopt the Riemann distance to measure the closeness between the network-estimated rotation matrix and the ground truth rotation matrix corresponding to the head pose. Experiments show that our method achieves the state-of-the-art on BIWI dataset and performs favorably on AFLW2000 dataset.
AB - This paper proposes a method for head pose estimation from a single image. We employ a multi-stage regression strategy. To overcome the discontinuity of Euler angles and quaternions and avoid the additional constraints required to directly regress the rotation matrix, we apply a continuous 6D representation to the head pose estimation problem. Each stage of the network regresses two 1×3 vectors, which are then transformed into a 3 × 3 rotation matrix by this continuous 6D representation. To better perceive the difference in rotation angles, we adopt the Riemann distance to measure the closeness between the network-estimated rotation matrix and the ground truth rotation matrix corresponding to the head pose. Experiments show that our method achieves the state-of-the-art on BIWI dataset and performs favorably on AFLW2000 dataset.
KW - 6D rotation representation
KW - Head pose estimation
KW - Riemann distance
KW - multi-stage regression
UR - https://www.scopus.com/pages/publications/85146718079
U2 - 10.1109/ICIP46576.2022.9897420
DO - 10.1109/ICIP46576.2022.9897420
M3 - 会议稿件
AN - SCOPUS:85146718079
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1326
EP - 1330
BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PB - IEEE Computer Society
T2 - 29th IEEE International Conference on Image Processing, ICIP 2022
Y2 - 16 October 2022 through 19 October 2022
ER -