Improving depth estimation in an automated privacy-preserving video processing system
Keywords
Loading...
Authors
Issue Date
2020-04-01
Language
en
Document type
Journal Title
Journal ISSN
Volume Title
Publisher
Title
ISSN
Volume
Issue
Startpage
Endpage
DOI
Abstract
This master thesis is written in collaboration with Info Support B.V. for
one of their clients, and explores the use of a conditional Generative Adversarial
Network for the estimation of depth from monocular rgb images. The
main research question stated is: Can a state-of-the-art neural network be
trained to accurately estimate relative depth in a crowded scene from monocular
recordings of a single uncalibrated camera? This question was answered
through three sub-questions, which addressed the addition of biological cues,
temporal information, and transfer learning from hyper-realistic video game
data. The model trained was improved through addition of biological cues,
temporal information and transfer learning, but was not accurate enough for
the intended application of depth estimation from monocular recordings in
a crowded scene.
Description
Citation
Faculty
Faculteit der Sociale Wetenschappen