A semi-automatic pipeline, ARS, uses a robot-moved camera and a one-time augmented-reality pen drawing to auto-label tens of thousands of frames, cutting annotation cost dramatically and training object detectors as well as manual labels.
IEEE Transactions on Automation Science and Engineering (99), 1–14 (2018)
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
-
Semi-Automatic Labeling for Deep Learning in Robotics
A semi-automatic pipeline, ARS, uses a robot-moved camera and a one-time augmented-reality pen drawing to auto-label tens of thousands of frames, cutting annotation cost dramatically and training object detectors as well as manual labels.