Semi-Supervised Single Image Depth Estimation Using Deep Neural Network

• Author / Creator

  Jahani Amiri, Ali

• There has been tremendous research progress in estimating the depth of a scene
  from a monocular camera image. Existing methods for single-image depth
  prediction are exclusively based on deep neural networks, and their training
  can be unsupervised using stereo image pairs, supervised using LiDAR point
  clouds, or semi-supervised using both stereo and LiDAR. In general, semi-
  supervised training is preferred as it does not suffer from the weaknesses of
  either supervised training, resulting from the difference in the camera’s and the
  LiDAR’s field of view, or unsupervised training, resulting from the poor depth
  accuracy that can be recovered from a stereo pair. In this thesis, we present
  our research in single-image depth prediction using semi-supervised training
  that outperforms the state-of-the-art. We achieve this through a loss function
  that explicitly exploits left-right consistency in a stereo reconstruction, which
  has not been adopted in previous semi-supervised training. Furthermore, we
  showed outputing inverse depth instead of disparity leads to better general-
  ization and it is essential in the training. In addition, we describe the correct
  use of ground truth depth derived from LiDAR that can significantly reduce
  prediction error. The performance of our depth prediction model is evaluated
  on popular KITTI dataset, and the importance of each aspect of our semi-
  supervised training approach is demonstrated through experimental results.

• Subjects / Keywords

  • Semi supervised learning
  • SLAM
  • Depth estimation
  • CNN
  • Deep Learning

• Graduation date

  Fall 2019

• Type of Item

  Thesis

• Degree

  Master of Science

• DOI

  https://doi.org/10.7939/r3-t0tf-6w23

• License

  Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.