Style transfer between different illumination, weather and seasonal conditions
The autonomous mobile robot is the key direction of robot research, while visual localization is the core of autonomous robot research. The bias caused by different illumination, weather, and seasonal conditions may undermine the robot perception and lead to imprecise localization results, while...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/155514 |
| _version_ | 1811678174399954944 |
|---|---|
| author | Zhu, Fangzheng |
| author2 | Wang Dan Wei |
| author_facet | Wang Dan Wei Zhu, Fangzheng |
| author_sort | Zhu, Fangzheng |
| collection | NTU |
| description | The autonomous mobile robot is the key direction of robot research, while visual
localization is the core of autonomous robot research. The bias caused by different
illumination, weather, and seasonal conditions may undermine the robot perception
and lead to imprecise localization results, while style transfer is an effective solution
to it. A recent class of style transfer models allows a realistic translation of images
between visual domains with comparatively little training data and without data
pairing.
In this work, I research methods for style transfer based on Generative Adversarial
Network (GAN) and apply them to image retrieval and visual localization. I implement
the ToDayGAN model, which can transfer the style of images between different
illumination, weather and seasonal conditions. After researching the state-of-the-art
visual localization methods on the effect of changing conditions, I apply the style
transfer model to implement hierarchical localization, and use SuperPoint to export the
dense local descriptors and NetVLAD to export global image-wide descriptors, finally,
the SolvePnPRansac pose estimation algorithm is used to obtain a more accurate 6-
DoF pose. This approach improves localization performance compared to the current
visual localization methods in a framework with several types of standard metrics,
which means applying style transfer methods to the task of visual localization is very
effective across the contrasting visual conditions. |
| first_indexed | 2024-10-01T02:49:04Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/155514 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:49:04Z |
| publishDate | 2022 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1555142023-07-04T17:02:56Z Style transfer between different illumination, weather and seasonal conditions Zhu, Fangzheng Wang Dan Wei School of Electrical and Electronic Engineering EDWWANG@ntu.edu.sg Engineering::Electrical and electronic engineering The autonomous mobile robot is the key direction of robot research, while visual localization is the core of autonomous robot research. The bias caused by different illumination, weather, and seasonal conditions may undermine the robot perception and lead to imprecise localization results, while style transfer is an effective solution to it. A recent class of style transfer models allows a realistic translation of images between visual domains with comparatively little training data and without data pairing. In this work, I research methods for style transfer based on Generative Adversarial Network (GAN) and apply them to image retrieval and visual localization. I implement the ToDayGAN model, which can transfer the style of images between different illumination, weather and seasonal conditions. After researching the state-of-the-art visual localization methods on the effect of changing conditions, I apply the style transfer model to implement hierarchical localization, and use SuperPoint to export the dense local descriptors and NetVLAD to export global image-wide descriptors, finally, the SolvePnPRansac pose estimation algorithm is used to obtain a more accurate 6- DoF pose. This approach improves localization performance compared to the current visual localization methods in a framework with several types of standard metrics, which means applying style transfer methods to the task of visual localization is very effective across the contrasting visual conditions. Master of Science (Computer Control and Automation) 2022-03-01T07:22:23Z 2022-03-01T07:22:23Z 2021 Thesis-Master by Coursework Zhu, F. (2021). Style transfer between different illumination, weather and seasonal conditions. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/155514 https://hdl.handle.net/10356/155514 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering Zhu, Fangzheng Style transfer between different illumination, weather and seasonal conditions |
| title | Style transfer between different illumination, weather and seasonal conditions |
| title_full | Style transfer between different illumination, weather and seasonal conditions |
| title_fullStr | Style transfer between different illumination, weather and seasonal conditions |
| title_full_unstemmed | Style transfer between different illumination, weather and seasonal conditions |
| title_short | Style transfer between different illumination, weather and seasonal conditions |
| title_sort | style transfer between different illumination weather and seasonal conditions |
| topic | Engineering::Electrical and electronic engineering |
| url | https://hdl.handle.net/10356/155514 |
| work_keys_str_mv | AT zhufangzheng styletransferbetweendifferentilluminationweatherandseasonalconditions |