DET is a lane detection dataset that consists of the raw event data, accumulated images over 30ms and corresponding lane labels. Contains 17,103 lane instances, each of which is labeled pixel by pixel manually.
Source: DET
Variants: DET
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Lane Detection | LDNet | LDNet: End-to-End Lane Marking Detection … | 2020-09-17 |
Recent papers with results on this dataset: