A two-stage zoom-in detection framework with resampling and reweighting schemes improves detection performance on tiny pole parts in imbalanced aerial image datasets over baseline methods.
These results will provide useful insights for tackling prob- lems in performing fully automated distribution tower condition analysis
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
-
Deep inspection: an electrical distribution pole parts study via deep neural networks
A two-stage zoom-in detection framework with resampling and reweighting schemes improves detection performance on tiny pole parts in imbalanced aerial image datasets over baseline methods.