Latent Embedding Clustering for Occlusion Robust Head Pose Estimation

被引:0
|
作者
Celestino, Jose [1 ]
Marques, Manuel [1 ]
Nascimento, Jacinto C. [1 ]
机构
[1] Inst Super Tecn, Inst Syst & Robot, Lisbon, Portugal
关键词
D O I
10.1109/FG59268.2024.10582028
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Head pose estimation has become a crucial area of research in computer vision given its usefulness in a wide range of applications, including robotics, surveillance, or driver attention monitoring. One of the most difficult challenges in this field is managing head occlusions that frequently take place in real-world scenarios. In this paper, we propose a novel and efficient framework that is robust in real world head occlusion scenarios. In particular, we propose an unsupervised latent embedding clustering with regression and classification components for each pose angle. The model optimizes latent feature representations for occluded and non-occluded images through a clustering term while improving fine-grained angle predictions. Experimental evaluation on in-the-wild head pose benchmark datasets reveal competitive performance in comparison to state-of-the-art methodologies with the advantage of having a significant data reduction. We observe a substantial improvement in occluded head pose estimation. Also, an ablation study is conducted to ascertain the impact of the clustering term within our proposed framework.
引用
收藏
页数:9
相关论文
共 50 条
  • [1] Robust attentive behavior detection by non-linear head pose embedding and estimation
    Hu, Nan
    Huang, Weimin
    Ranganath, Surendra
    COMPUTER VISION - ECCV 2006, PT 3, PROCEEDINGS, 2006, 3953 : 356 - 367
  • [2] Fast and robust head detection with arbitrary pose and occlusion
    Zhang, Tao
    Yang, Zhijie
    Jia, Wenjing
    Wu, Qiang
    Yang, Jie
    He, Xiangjian
    MULTIMEDIA TOOLS AND APPLICATIONS, 2015, 74 (21) : 9365 - 9385
  • [3] Fast and robust head detection with arbitrary pose and occlusion
    Tao Zhang
    Zhijie Yang
    Wenjing Jia
    Qiang Wu
    Jie Yang
    Xiangjian He
    Multimedia Tools and Applications, 2015, 74 : 9365 - 9385
  • [4] Smooth Multi-Manifold Embedding for Robust Identity-Independent Head Pose Estimation
    Liu, Xiangyang
    Lu, Hongtao
    Luo, Heng
    COMPUTER ANALYSIS OF IMAGES AND PATTERNS, PROCEEDINGS, 2009, 5702 : 66 - 73
  • [5] Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions
    Drouard, Vincent
    Horaud, Radu
    Deleforge, Antoine
    Ba, Sileye
    Evangelidis, Georgios
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (03) : 1428 - 1440
  • [6] Robust head pose estimation using LGBP
    Ma, Bingpeng
    Zhang, Wenchao
    Shan, Shiguang
    Chen, Xilin
    Gao, Wen
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2006, : 512 - +
  • [7] Robust head pose estimation by machine learning
    Wang, C
    Brandstein, M
    2000 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, 2000, : 210 - 213
  • [8] Robust Face Recognition using Automatic Pose Clustering and Pose Estimation
    Beham, M. Parisa
    Roomi, S. Mohamed Mansoor
    Kapileshwaran, V.
    2013 FIFTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING (ICOAC), 2013, : 51 - 55
  • [9] Pose-Dependent Low-Rank Embedding for Head Pose Estimation
    Zhao, Handong
    Ding, Zhengming
    Fu, Yun
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 1422 - 1428
  • [10] Head pose estimation by non-linear embedding and mapping
    Hu, N
    Huang, WM
    Ranganath, S
    2005 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), VOLS 1-5, 2005, : 1669 - 1672