Making the Flow Glow -- Robot Perception under Severe Lighting Conditions using Normalizing Flow Gradients
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909423412183040 |
|---|---|
| author | Lind, Simon Kristoffersson Triebel, Rudolph Krüger, Volker |
| author_facet | Lind, Simon Kristoffersson Triebel, Rudolph Krüger, Volker |
| contents | Modern robotic perception is highly dependent on neural networks. It is well known that neural network-based perception can be unreliable in real-world deployment, especially in difficult imaging conditions. Out-of-distribution detection is commonly proposed as a solution for ensuring reliability in real-world deployment. Previous work has shown that normalizing flow models can be used for out-of-distribution detection to improve reliability of robotic perception tasks. Specifically, camera parameters can be optimized with respect to the likelihood output from a normalizing flow, which allows a perception system to adapt to difficult vision scenarios. With this work we propose to use the absolute gradient values from a normalizing flow, which allows the perception system to optimize local regions rather than the whole image. By setting up a table top picking experiment with exceptionally difficult lighting conditions, we show that our method achieves a 60% higher success rate for an object detection task compared to previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07565 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Making the Flow Glow -- Robot Perception under Severe Lighting Conditions using Normalizing Flow Gradients Lind, Simon Kristoffersson Triebel, Rudolph Krüger, Volker Computer Vision and Pattern Recognition Modern robotic perception is highly dependent on neural networks. It is well known that neural network-based perception can be unreliable in real-world deployment, especially in difficult imaging conditions. Out-of-distribution detection is commonly proposed as a solution for ensuring reliability in real-world deployment. Previous work has shown that normalizing flow models can be used for out-of-distribution detection to improve reliability of robotic perception tasks. Specifically, camera parameters can be optimized with respect to the likelihood output from a normalizing flow, which allows a perception system to adapt to difficult vision scenarios. With this work we propose to use the absolute gradient values from a normalizing flow, which allows the perception system to optimize local regions rather than the whole image. By setting up a table top picking experiment with exceptionally difficult lighting conditions, we show that our method achieves a 60% higher success rate for an object detection task compared to previous methods. |
| title | Making the Flow Glow -- Robot Perception under Severe Lighting Conditions using Normalizing Flow Gradients |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.07565 |