Accurate but fragile passive non-line-of-sight recognition
Non-line-of-sight imaging allows reconstruction and recognition of an obscured object, but external manipulation of the data can lead to inaccurate results. Here, the accuracy and robustness of passive non-line-of-sight recognition and its fragility to adversarial attacks are studied.
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | article |
| Language: | EN |
| Published: |
Nature Portfolio
2021
|
| Subjects: | |
| Online Access: | https://doaj.org/article/dd7253beb95c4d4ea71a2ec0584a47d7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Non-line-of-sight imaging allows reconstruction and recognition of an obscured object, but external manipulation of the data can lead to inaccurate results. Here, the accuracy and robustness of passive non-line-of-sight recognition and its fragility to adversarial attacks are studied. |
|---|