A lightweight two-stream CNN trained on a new fisheye surround-view dataset detects moving vehicles and pedestrians, reaching about 40% moving-object IoU versus 10% when trained on rectilinear KITTI data.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
FisheyeMODNet: Moving Object detection on Surround-view Cameras for Autonomous Driving
A lightweight two-stream CNN trained on a new fisheye surround-view dataset detects moving vehicles and pedestrians, reaching about 40% moving-object IoU versus 10% when trained on rectilinear KITTI data.