AutoGraph: predicting lane graphs from traffic observations
Lane graph estimation is a long-standing problem in the context of autonomous driving. Previous works aimed at solving this problem by relying on large-scale, hand-Annotated lane graphs, introducing a data bottleneck for training models to solve this task. To overcome this limitation, we propose to...
| Main Authors: | , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
IEEE
2023
|
| _version_ | 1797111789377290240 |
|---|---|
| author | Zurn, J Posner, I Burgard, W |
| author_facet | Zurn, J Posner, I Burgard, W |
| author_sort | Zurn, J |
| collection | OXFORD |
| description | Lane graph estimation is a long-standing problem in the context of autonomous driving. Previous works aimed at solving this problem by relying on large-scale, hand-Annotated lane graphs, introducing a data bottleneck for training models to solve this task. To overcome this limitation, we propose to use the motion patterns of traffic participants as lane graph annotations. In our AutoGraph approach, we employ a pre-Trained object tracker to collect the tracklets of traffic participants such as vehicles and trucks. Based on the location of these tracklets, we predict the successor lane graph from an initial position using overhead RGB images only, not requiring any human supervision. In a subsequent stage, we show how the individual successor predictions can be aggregated into a consistent lane graph. We demonstrate the efficacy of our approach on the UrbanLaneGraph dataset and perform extensive quantitative and qualitative evaluations, indicating that AutoGraph is on par with models trained on hand-Annotated graph data. |
| first_indexed | 2024-03-07T08:15:18Z |
| format | Journal article |
| id | oxford-uuid:34b2f397-dc36-4cc2-9728-424980406065 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:15:18Z |
| publishDate | 2023 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:34b2f397-dc36-4cc2-9728-4249804060652023-12-20T14:05:56ZAutoGraph: predicting lane graphs from traffic observationsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:34b2f397-dc36-4cc2-9728-424980406065EnglishSymplectic ElementsIEEE2023Zurn, JPosner, IBurgard, WLane graph estimation is a long-standing problem in the context of autonomous driving. Previous works aimed at solving this problem by relying on large-scale, hand-Annotated lane graphs, introducing a data bottleneck for training models to solve this task. To overcome this limitation, we propose to use the motion patterns of traffic participants as lane graph annotations. In our AutoGraph approach, we employ a pre-Trained object tracker to collect the tracklets of traffic participants such as vehicles and trucks. Based on the location of these tracklets, we predict the successor lane graph from an initial position using overhead RGB images only, not requiring any human supervision. In a subsequent stage, we show how the individual successor predictions can be aggregated into a consistent lane graph. We demonstrate the efficacy of our approach on the UrbanLaneGraph dataset and perform extensive quantitative and qualitative evaluations, indicating that AutoGraph is on par with models trained on hand-Annotated graph data. |
| spellingShingle | Zurn, J Posner, I Burgard, W AutoGraph: predicting lane graphs from traffic observations |
| title | AutoGraph: predicting lane graphs from traffic observations |
| title_full | AutoGraph: predicting lane graphs from traffic observations |
| title_fullStr | AutoGraph: predicting lane graphs from traffic observations |
| title_full_unstemmed | AutoGraph: predicting lane graphs from traffic observations |
| title_short | AutoGraph: predicting lane graphs from traffic observations |
| title_sort | autograph predicting lane graphs from traffic observations |
| work_keys_str_mv | AT zurnj autographpredictinglanegraphsfromtrafficobservations AT posneri autographpredictinglanegraphsfromtrafficobservations AT burgardw autographpredictinglanegraphsfromtrafficobservations |