Purdue University Graduate School
Browse
Chu_thesis.pdf (2.06 MB)

VECTOR REPRESENTATION TO ENHANCE POSE ESTIMATION FROM RGB IMAGES

Download (2.06 MB)
thesis
posted on 2020-05-03, 14:51 authored by Zongcheng ChuZongcheng Chu
Head pose estimation is an essential task to be solved in computer vision. Existing research for pose estimation based on RGB images mainly uses either Euler angles or quaternions to predict pose. Nevertheless, both Euler angle- and quaternion-based approaches encounter the problem of discontinuity when describing three-dimensional rotations. This issue makes learning visual pattern more difficult for the convolutional neural network(CNN) which, in turn, compromises the estimation performance. To solve this problem, we introduce TriNet, a novel method based on three vectors converted from three Euler angles(roll, pitch, yaw). The orthogonality of the three vectors enables us to implement a complementary multi-loss function, which effectively reduces the prediction error. Our method achieves state-of-the-art performance on the AFLW2000, AFW and BIWI datasets. We also extend our work to general object pose estimation and show results in the experiment part.

History

Degree Type

  • Master of Science

Department

  • Computer Graphics Technology

Campus location

  • West Lafayette

Advisor/Supervisor/Committee Chair

Yingjie Chen

Additional Committee Member 2

Vetria Byrd

Additional Committee Member 3

Baijian Yang

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC