AR-CP: Uncertainty-Aware Perception in Adverse Conditions with Conformal Prediction and Augmented Reality For Assisted Driving
| dc.contributor.author | Doula, Achref | |
| dc.contributor.author | Mühlhäuser, Max | |
| dc.contributor.author | Sanchez Guinea, Alejandro | |
| dc.date.accessioned | 2024-04-30T16:10:57Z | |
| dc.date.available | 2024-04-30T16:10:57Z | |
| dc.date.created | 2024-04-14 | |
| dc.date.issued | 2024-04-30 | |
| dc.description | Deep learning models play a crucial role in improving driver assistance systems and environmental perception. However, their tendency toward overconfident predictions poses risks to driver safety, particularly in adverse conditions. To address this, we propose AR-CP, an uncertainty-aware framework integrating conformal prediction and augmented reality (AR). AR-CP starts with a conformal prediction step, generating an uncertainty-aware prediction set. Then, AR simplifies and clarifies the visualization of the closest common parent class, reducing misinformation. We present a rigorous formulation and theoretical analysis, evaluating AR-CP on the ROAD dataset. Results demonstrate superior performance compared to existing methods, ensuring safer driving experiences with reduced mental load and heightened situation awareness, as validated by an immersive user study involving 15 participants. | de_DE |
| dc.description.version | 0.1 | de_DE |
| dc.identifier.uri | https://tudatalib.ulb.tu-darmstadt.de/handle/tudatalib/4219 | |
| dc.language.iso | en | de_DE |
| dc.rights.license | ODC-BY-1.0 (https://opendatacommons.org/licenses/by/1.0/) | |
| dc.subject | Uncertainty Quantification | de_DE |
| dc.subject | Deep Learning | de_DE |
| dc.subject | Augmented Reality | de_DE |
| dc.subject | Urban Scene Understanding | de_DE |
| dc.subject.classification | 4.43-04 | |
| dc.subject.classification | 4.43-05 | |
| dc.subject.ddc | 004 | |
| dc.title | AR-CP: Uncertainty-Aware Perception in Adverse Conditions with Conformal Prediction and Augmented Reality For Assisted Driving | de_DE |
| dc.type | Software | de_DE |
| dcterms.accessRights | openAccess | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| person.identifier.orcid | #PLACEHOLDER_PARENT_METADATA_VALUE# | |
| tuda.history.classification | Version=2016-2020;409-05 Interaktive und intelligente Systeme, Bild- und Sprachverarbeitung, Computergraphik und Visualisierung | |
| tuda.unit | TUDa |
Files
Original bundle
1 - 3 of 3
| Name | Description | Size | Format | |
|---|---|---|---|---|
| AR_CP_PlotsGeneration.ipynb | data processing and plot generation code | 75.62 KB | Unknown data format | |
| Example from study videos.zip | example videos from study | 43.94 MB | ZIP-Archivdateien | |
| CVPRW__AR_CP.pdf | Paper preprint | 2.63 MB | Adobe Portable Document Format |