ABSTRACT
In this paper, we present an improved end-to-end head pose estimation method in an unconstrained environment, which transforms the Head Pose Estimation(HPE) problem into a problem of directly predicting continuous 6D rotation matrix parameters belongs 3D Special Orthogonal Group(SO(3)). The method uses RepVGGplus-L2pse as the backbone, followed by one FC layer to output the results, model be trained on 300W-LP. The improved Root Mean Square Error of Geodesic Distance(RSME_GD) is used as the loss function to enhance the accuracy. The experiments on the two public face datasets AFLW-2000 and BIWI show that the results measured by Mean Absolute Error of Vectors (MAEV) are improved by 19.68% and 13.98% respectively compared with the original SOTA method.
- Zhu, X., Lei, Z., Liu, X., Shi, H. and Li, S. Z. Face alignment across large poses: A 3d solution. City, 2016.Google Scholar
- Zhu, X., Lei, Z., Yan, J., Yi, D. and Li, S. Z. High-fidelity pose and expression normalization for face recognition in the wild. City, 2015.Google Scholar
- Fanelli, G., Dantone, M., Gall, J., Fossati, A. and Van Gool, L. Random forests for real time 3d face analysis. International journal of computer vision, 101 (2013), 437-458.Google ScholarDigital Library
- Cao, Z. W., Chu, Z. C., Liu, D. F., Chen, Y. J. and Ieee A Vector-based Representation to Enhance Head Pose Estimation. Ieee Computer Soc, City, 2021.Google Scholar
- Tang, H., Dai, M., Du, X., Hung, J.-L. and Li, H. An EEG study on college students’ attention levels in a blended computer science class. Innovations in Education and Teaching International (2023), 1-13.Google Scholar
- Jahanmahin, R., Masoud, S., Rickli, J. and Djuric, A. Human-robot interactions in manufacturing: A survey of human behavior modeling. Robotics and Computer-Integrated Manufacturing, 78 (2022), 102404.Google ScholarDigital Library
- Lundgren, A. V. A., Santos, M. A. O. d., Bezerra, B. L. D. and Bastos-Filho, C. J. A. Systematic Review of Computer Vision Semantic Analysis in Socially Assistive Robotics. Ai, 3, 1 (2022), 229-249.Google Scholar
- Suzuki, R., Karim, A., Xia, T., Hedayati, H. and Marquardt, N. Augmented reality and robotics: A survey and taxonomy for ar-enhanced human-robot interaction and robotic interfaces. City, 2022.Google Scholar
- Oniki, K., Kikuchi, T. and Ozasa, Y. Training Data Generation Based on Observation Probability Density for Human Pose Refinement. Journal of Image and Graphics, 9, 2 (2021), 50-54.Google ScholarCross Ref
- Zhou, Y. and Gregson, J. Whenet: Real-time fine-grained estimation for wide range head pose. arXiv preprint arXiv:2005.10353 (2020).Google Scholar
- Yang, T. Y., Chen, Y. T., Lin, Y. Y. and Chuang, Y. Y. FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image. City, 2019.Google Scholar
- Zhang, H., Wang, M. M., Liu, Y., Yuan, Y. and Assoc Advancement Artificial, I. FDN: Feature Decoupling Network for Head Pose Estimation. Assoc Advancement Artificial Intelligence, City, 2020.Google Scholar
- Hsu, H.-W., Wu, T.-Y., Wan, S., Wong, W. H. and Lee, C.-Y. QuatNet: Quaternion-Based Head Pose Estimation With Multiregression Loss. IEEE Transactions on Multimedia, 21, 4 (2019), 1035-1046.Google Scholar
- Zhou, Y., Barnes, C., Lu, J., Yang, J. and Li, H. On the Continuity of Rotation Representations in Neural Networks. In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), [insert City of Publication],[insert 2019 of Publication].Google ScholarCross Ref
- Xiang, Y., Schmidt, T., Narayanan, V. and Fox, D. Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199 (2017).Google Scholar
- Hempel, T., Abdelrahman, A. A. and Al-Hamadi, A. 6d Rotation Representation For Unconstrained Head Pose Estimation. City, 2022.Google Scholar
- Wu, C. Y., Xu, Q. G., Neumann, U. and Soc, I. C. Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry. Ieee Computer Soc, City, 2021.Google ScholarCross Ref
- Ruiz, N., Chong, E. and Rehg, J. M. Fine-grained head pose estimation without keypoints. City, 2018.Google Scholar
- Ding, X. H., Zhang, X. Y., Ma, N. N., Han, J. G., Ding, G. G., Sun, J. and Ieee Comp, S. O. C. RepVGG: Making VGG-style ConvNets Great Again. Ieee Computer Soc, City, 2021.Google Scholar
- He, K., Zhang, X., Ren, S. and Sun, J. Deep Residual Learning for Image Recognition. City, 2016.Google Scholar
Index Terms
- Continuity Rotation Representation for Head Pose Estimation without Keypoints
Recommendations
Evaluation of head pose estimation for studio data
CLEAR'06: Proceedings of the 1st international evaluation conference on Classification of events, activities and relationshipsThis paper introduces our head pose estimation system that localizes nose-tip of the faces and estimate head poses in studio quality pictures. After the nose-tip in the training data are manually labeled, the appearance variation caused by head pose ...
Head Pose Estimation Based on Tensor Factorization
Neural Information ProcessingAbstractThis paper investigates head pose estimation problem which is considered as front-end preprocessing for improving multi-view human face recognition. We propose a computational model for perceiving head poses based on the Non-negative Multi-way ...
Combining Head Pose and Eye Location Information for Gaze Estimation
Head pose and eye location for gaze estimation have been separately studied in numerous works in the literature. Previous research shows that satisfactory accuracy in head pose and eye location estimation can be achieved in constrained settings. However,...
Comments