Not logged in.
Quick Search - Contribution
Contribution Details
Type | Conference or Workshop Paper |
Scope | Discipline-based scholarship |
Published in Proceedings | Yes |
Title | Learning-based Image Enhancement for Visual Odometry in Challenging HDR Environments |
Organization Unit | |
Authors |
|
Presentation Type | paper |
Item Subtype | Original Work |
Refereed | Yes |
Status | Published in final form |
Language |
|
Page Range | 1 - 8 |
Event Title | IEEE International Conference on Robotics and Automation (ICRA), 2018. |
Event Type | conference |
Event Location | Brisbane |
Event Start Date | May 21 - 2018 |
Event End Date | May 25 - 2018 |
Place of Publication | IEEE International Conference on Robotics and Automation (ICRA), 2018. |
Publisher | IEEE |
Abstract Text | One of the main open challenges in visual odometry (VO) is the robustness to difficult illumination conditions or high dynamic range (HDR) environments. The main difficulties in these situations come from both the limitations of the sensors and the inability to perform a successful tracking of interest points because of the bold assumptions in VO, such as brightness constancy. We address this problem from a deep learning perspective, for which we first fine-tune a deep neural network with the purpose of obtaining enhanced representations of the sequences for VO. Then, we demonstrate how the insertion of long short term memory allows us to obtain temporally consistent sequences, as the estimation depends on previous states. However, the use of very deep networks enlarges the computational burden of the VO framework; therefore, we also propose a convolutional neural network of reduced size capable of performing faster. Finally, we validate the enhanced representations by evaluating the sequences produced by the two architectures in several state-of-art VO algorithms, such as ORB-SLAM and DSO. |
Zusammenfassung | One of the main open challenges in visual odometry (VO) is the robustness to difficult illumination conditions or high dynamic range (HDR) environments. The main difficulties in these situations come from both the limitations of the sensors and the inability to perform a successful tracking of interest points because of the bold assumptions in VO, such as brightness constancy. We address this problem from a deep learning perspective, for which we first fine-tune a deep neural network with the purpose of obtaining enhanced representations of the sequences for VO. Then, we demonstrate how the insertion of long short term memory allows us to obtain temporally consistent sequences, as the estimation depends on previous states. However, the use of very deep networks enlarges the computational burden of the VO framework; therefore, we also propose a convolutional neural network of reduced size capable of performing faster. Finally, we validate the enhanced representations by evaluating the sequences produced by the two architectures in several state-of-art VO algorithms, such as ORB-SLAM and DSO. |
Official URL | http://rpg.ifi.uzh.ch/docs/ICRA18_Gomez.pdf |
Digital Object Identifier | 10.1109/ICRA.2018.8462876 |
Other Identification Number | merlin-id:16265 |
PDF File | Download from ZORA |
Export |
BibTeX
EP3 XML (ZORA) |