Tilting at windmills

Data augmentation for deep pose estimation does not help with occlusions

Master thesis (2020)

Authors

R.J. Pytel Electrical Engineering, Mathematics and Computer Science

Contributors

J.C. van Gemert Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
O.S. Kayhan Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
M.J.T. Reinders Pattern Recognition and Bioinformatics - EEMCS (supervisor 2)
C.C.S. Liem (supervisor 2)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2020 Rafal Pytel
More Info
expand_more

Published Date

31-08-2020

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Occlusion degrades the performance of human pose estimation. In this paper, we introduce targeted keypoint and body part occlusion attacks. The effects of the attacks are systematically analyzed on the best-performing methods. In addition, we propose occlusion specific data augmentation techniques against keypoint and part attacks. Our extensive experiments show that human pose estimation methods are not robust to occlusion and data augmentation does not solve the occlusion problems.