Moving object detection and image inpainting in street-view imagery

Title

Moving object detection and image inpainting in street-view imagery

 Author

Uittenbogaard, Ries (TU Delft Mechanical, Maritime and Materials Engineering)

Contributor

Gavrila, Dariu (mentor)
Sebastian, Clint (mentor)
Vijverberg, Julien (mentor)

Degree granting institution

Delft University of Technology

 Date

2018-09-28

 Abstract

In this thesis, a pipeline is created consisting of two parts. In the first part, the moving objects (cars, cyclists, pedestrians) are detected in street-view imagery using image segmentation neural networks and a LIDAR-based moving object detection approach. In the second part, those moving objects are deleted from the image data and an image inpainting approach is used to inpaint the hole. This is a unique approach in which information from multiple views is used as an input for a Generative Adversarial Network (GAN).

 Subject

Image inpainting
Moving object detection
Image segmentation
Generative Adversarial Networks
LIDAR

 To reference this document use:

http://resolver.tudelft.nl/uuid:5528c3a3-8ff8-4c96-b181-a9bbae0e6d28

 Part of collection

Student theses

 Document type

master thesis

 Rights

© 2018 Ries Uittenbogaard
Files
PDF final_thesis_ries_uittenbogaard.pdf 212.36 MB
Close viewer