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
  • [21] Head Pose Estimation Based on Manifold Embedding and Distance Metric Learning
    Liu, Xiangyang
    Lu, Hongtao
    Zhang, Daqiang
    COMPUTER VISION - ACCV 2009, PT I, 2010, 5994 : 61 - 70
  • [22] Robust Head Pose Estimation using ContourletSD Transform and GLCM
    Meydanipour, Gelareh
    Faez, Karim
    2013 8TH IRANIAN CONFERENCE ON MACHINE VISION & IMAGE PROCESSING (MVIP 2013), 2013, : 375 - 380
  • [23] AUTOMATIC AND ROBUST HEAD POSE ESTIMATION BY BLOCK ENERGY MAP
    Li, Wei
    Huang, Yan
    Peng, Jingliang
    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 3357 - 3361
  • [24] Robust head pose estimation via supervised manifold learning
    Wang, Chao
    Song, Xubo
    NEURAL NETWORKS, 2014, 53 : 15 - 25
  • [25] Robust face model based approach to head pose estimation
    Fornalczyk, Krzysztof
    Wojciechowski, Adam
    PROCEEDINGS OF THE 2017 FEDERATED CONFERENCE ON COMPUTER SCIENCE AND INFORMATION SYSTEMS (FEDCSIS), 2017, : 1291 - 1295
  • [26] Robust Head Pose Estimation Using Supervised Manifold Learning
    BenAbdelkader, Chiraz
    COMPUTER VISION - ECCV 2010, PT VI, 2010, 6316 : 518 - 531
  • [27] Efficient and Robust Integration of Face Detection and Head Pose Estimation
    Jiang, Feijun
    Ekenel, Hazim Kemal
    Shi, Bertram E.
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 1578 - 1581
  • [28] ROBUST HEAD POSE ESTIMATION USING SUPERVISED MANIFOLD PROJECTION
    Wang, Chao
    Song, Xubo
    2012 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2012), 2012, : 161 - 164
  • [29] A robust algorithm for 3D head pose estimation
    Chen, Q
    Wu, HY
    Shioyama, S
    Shimada, T
    Chihara, K
    FOURTEENTH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1 AND 2, 1998, : 1356 - 1359
  • [30] Head Pose Estimation Based on Robust Convolutional Neural Network
    Bao, Jiao
    Ye, Mao
    CYBERNETICS AND INFORMATION TECHNOLOGIES, 2016, 16 (06) : 133 - 145