Combining monocular depth and optical flow predictions from deep networks yields ego-vehicle speed estimates with RMSE below 1 m/s on KITTI after approximating one scale factor.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Speed estimation evaluation on the KITTI benchmark based on motion and monocular depth information
Combining monocular depth and optical flow predictions from deep networks yields ego-vehicle speed estimates with RMSE below 1 m/s on KITTI after approximating one scale factor.