基于黎曼优化的遮挡头部姿态估计算法

doi:10.11896/jsjkx.250300109

摘要/Abstract

摘要： 人体头部姿态估计是深度学习领域的重要任务,尤其在车载辅助驾驶系统中,它作为检测疲劳驾驶的关键手段,具有广泛的应用前景。然而,在实际应用中,面部遮挡常常导致关键特征点丢失,严重降低模型精度。针对这一难题,本文提出了6DRepLKNet-RGO算法。该算法在6DRepNet的基础上,通过结构重参数化设计,优化了网络结构,增强了特征提取能力。同时,结合黎曼流形梯度优化策略,优化了三维姿态表示方式的学习过程,减少了训练误差。为了进一步提高模型对遮挡情况下的姿态估计精度,增加了随机擦除的数据增强方法。实验表明,6DRepLKNet-RGO在BIWI和AFLW2000等公开数据集上,相较于 6DRepNet减少了5%以上的误差,并在MAE指标上超越了其他先进模型,验证了其有效性。

关键词: 头部姿态估计, 结构重参数化, 数据增强, 梯度优化, 深度学习

Abstract: Human head pose estimation is an important task in the field of deep learning,especially in vehicle-mounted assisted driving systems.As a key means of detecting fatigue driving,it has broad application prospects.However,in practical applications,facial occlusion often results in the loss of key feature points,seriously reducing model accuracy.In response to this problem,this paper proposes the 6DRepLKNet-RGO algorithm.Based on 6DRepNet,this algorithm optimizes the network structure and enhances feature extraction capabilities through structural re-parameterization design.At the same time,combined with the Riemannian manifold gradient optimization strategy,the learning process of the three-dimensional pose representation is optimized and the training error is reduced.In order to further improve the model's pose estimation accuracy under occlusion,a data enhancement method of random erasure is added.Experiments show that 6DRepLKNet-RGO reduces errors by more than 5% compared to 6DRepNet on public data sets such as BIWI and AFLW2000,and surpasses other advanced models in terms of the MAE metric,verifying its effectiveness.

Key words: Head pose estimation, Structural re-parameterization, Data augmentation, Gradient optimization, Deep learning

中图分类号:

TP312

王宝会, 谭英洁, 陈继轩. 基于黎曼优化的遮挡头部姿态估计算法[J]. 计算机科学, 2026, 53(6A): 250300109-9. https://doi.org/10.11896/jsjkx.250300109

WANG Baohui, TAN Yingjie , CHEN Jixuan. Occlusion Head Pose Estimation Algorithm Based on Riemann Optimization[J]. Computer Science, 2026, 53(6A): 250300109-9. https://doi.org/10.11896/jsjkx.250300109

参考文献

[1] LI D H,LIU Q,YUAN W,et al.Relationship between fatigued driving and traffic accidents[J].Journal of Traffic and Transportation Engineering,2010(4):104-109.
[2] SHERRAH J,GONG S.Face distributions in similarity space under varying head pose[J].Image and Vision Computing,2001,19(12):807-819.
[3] TORKI M,ELGAMMAL A.Regression from local features for viewpoint and pose estimation[C]//2011 International Conference on Computer Vision.IEEE,2011:2603-2610.
[4] DROUARD V,HORAUD R,DELEFORGE A,et al.Robusthead-pose estimation based on partially-latent mixture of linear regressions[J].IEEE Transactions on Image Processing,2017,26(3):1428-1440.
[5] LU J,TAN Y.Ordinary preserving manifold analysis for human age and head pose estimation[J].IEEE Transactions on Human-Machine Systems,2013,43(2):249-258.
[6] NIKOLAIDIS A,PITAS I.Facial feature extraction and posedetermination[J].Pattern Recogition,2000,33(11):1783-1791.
[7] NARAYANAN A,KAIMAL R M,BIJLANI K.Estimation of driver head yaw angle using a geometric model[J].IEEE Transactions on Intelligent Transportation Systems,2016,17(12):3446-3460.
[8] XIAO J,MORIYAMA T,KAASADE T,et al.Robust full-motion recovery of head by dynamic templates and re-registration techniques[J].International Journal of Imaging Systems and Technology,2003,13(1):85-94.
[9] ZHAO G,CHEN L,SONG J,et al.Large head movement tracking using sift-based registration[C]//15th ACM International Conference on Multimedia.ACM,2007:807-810.
[10] EL ABOUDI N,BENHLIMA L.Review on wrapper feature selection approaches[C]//Proceedings of the 2016 International Conference on Engineering & MIS(ICEMIS).IEEE,2016:1-5.
[11] VALLE R,BUENAPOSADA J M,BAUMELA L.Multi-taskhead pose estimation in-the-wild[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,43(8):2874-2881.
[12] HEMPEL T,ABDELRAHMAN A A,AL-HAMADI A.6d rotation representation for unconstrained head pose estimation[C]//IEEE International Conference on Image Processing(ICIP 2022).IEEE,2022:2496-2500.
[13] THAI C,TRAN V,BUI M,et al.An Effective Deep Network for Head Pose Estimation without Keypoints[C]//IEEE International Conference on Image Processing(ICIP).Bordeaux:IEEE,2022:2591-2595.
[14] WANG J,JIN Y C,GUO P,et al.A Survey of Camera Pose Estimation Methods Based on Deep Learning[J].Computer Engineering and Applications,2023,59(7):1-14.
[15] KAZEMI V,SULLIVAN J.One millisecond face alignment with an ensemble of regression trees[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2014:1867-1874.
[16] BULAT A,TZIMIROPOULOS G.How far are we from solving the 2d & 3d face alignment problem?(and a dataset of 30,000 3d facial landmarks) [C]//Proceedings of the IEEE International Conference on Computer Vision.2017:1021-1030.
[17] XIA J,PEI D,WANG Q Z,et al.Face recognition based on local adaptive ternary derivative pattern coupled with Gabor feature[J].Laser & Optoelectronics Progress,2016,53(11):111004.
[18] RUIZ N,CHONG E,REHG J M.Fine-grained head pose estimation without keypoints[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.2018:2074-2083.
[19] YANG T Y,CHEN Y T,LIN Y Y,et al.FSA-Net:Learning fine-grained structure aggregation for head pose estimation from a single image[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:1087-1096.
[20] ZHOU Y,GREGSON J.WHENet:Real-time fine-grained estimation for wide range head pose[J].arXiv:2005.10353,2020.
[21] DAI H H,TAN S X,ZHANG W.A Survey of Head Pose Estimation Methods[J].Modern Computer,2021(7):130-134.
[22] DING X,ZHANG X,MA N,et al.RepVGG:Making vgg-style convnets great again[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:13733-13742.
[23] VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[J].Advances in Neural Information Processing Systems,2017,30.
[24] DING X,ZHANG X,HAN J,et al.Scaling up your kernels to 31x31:Revisiting large kernel design in cnns[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:11963-11975.
[25] HU M,FENG J,HUA J,et al.Online convolutional re-parameterization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:568-577.
[26] DING X,CHEN H,ZHANG X,et al.Re-parameterizing youroptimizers rather than architectures[J].arXiv:2205.15242,2022.
[27] CHEN J,YIN Y,BIRDAL T,et al.Projective manifold gradient layer for deep rotation regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:6646-6655.
[28] ZHONG Z,ZHENG L,KANG G,et al.Random erasing dataaugmentation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:13001-13008.
[29] ZHOU Y,BARNES C,LU J,et al.On the continuity of rotation representations in neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:5745-5753.
[30] ZHU X,LEI Z,LIU X,et al.Face alignment across large poses:A 3d solution[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition.2016:146-155.
[31] ZHU X,LEI Z,YAN J,et al.High-fidelity pose and expression normalization for face recognition in the wild[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition.2015:787-796.
[32] FANELLI G,DANTONE M,GALL J,et al.Random forests for real time 3d face analysis[J].International Journal of Computer Vision,2013,101:437-458.
[33] ALBIERO V,CHEN X,YIN X,et al.img2pose:Face alignment and detection via 6dof,face pose estimation[C]//Proceedings of the IEEE/CVFConference on Computer Vision and Pattern Recognition.2021:7617-7627.
[34] AGHLI N,RIBEIRO E.A Data-Driven Approach to Improve 3D Head-Pose Estimation[C]//Advances in Visual Computing:16th International Symposium(ISVC 2021)..Springer International Publishing,2021:546-558.
[35] ZHANG C,LIU H,DENG Y,et al.Tokenhpe:Learning orientation tokens for efficient head pose estimation via transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:8897-8906.
[36] GAO Q,DING B R,DONG C L,et al.Head Pose Estimation Algorithm for Real-Time Applications[J].Journal of Shenyang University(Natural Science Edition),2025,37(1):25-33,93,99.
[37] WANG Y,LIU H,FENG Y,et al.HeadDiff:Exploring Rotation Uncertainty With Diffusion Models for Head Pose Estimation[J].IEEE Transactions on Image Processing,2024(33):1868-1882.
[38] ZHANG J,LI X,LI J,et al.Rethinking Mobile Block for Efficient Attention-based Models [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2023:1389-1400.
[39] DING X,CHEN H,ZHANG X,et al.Repmlpnet:Hierarchical vision mlp with re-parameterized locality[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:578-587.
[40] MEHTA S,RASTEGARI M.Mobilevit:light-weight,general-purpose,and mobile-friendly vision transformer[J].arXiv:2110.02178,2021.
[41] HATAMIZADEH A,HEINRICH G,YIN H,et al.FasterViT:Fast Vision Transformers with Hierarchical Attention[J].ar-Xiv:2306.06189,2023.
[42] VASU P K A,GABRIEL J,ZHU J,et al.FastViT:A Fast Hybrid Vision Transformer using Structural Reparameterization[J].arXiv:2303.14189,2023.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed