RoadFormer, a hybrid convolutional-transformer network with a foreground-background training module, reports top-1 accuracies of 92.52% and 96.50% on the RSCD pavement datasets.
Road surface state recog- nition based on svm optimization and image segmen- tation processing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
RoadFormer : Local-Global Feature Fusion for Road Surface Classification in Autonomous Driving
RoadFormer, a hybrid convolutional-transformer network with a foreground-background training module, reports top-1 accuracies of 92.52% and 96.50% on the RSCD pavement datasets.