paper
2021
Observations & remote sensing
Application study
CNN / U-Net Journal
2021-06-10
008
Jun 2021
Sheela Ramanna, Cenker Sengoz, Scott D. Kehler et al.
Applied Artificial Intelligence
EfficientNet classifies road surface conditions from street and highway camera images into five classes at 90.6% validation accuracy, complementing station-based road weather data.
Near Real-time Map Building with Multi-class Image Set Labeling and Classification of Road Conditions Using Convolutional Neural Networks
In one sentence. EfficientNet classifies road surface conditions from street and highway camera images into five classes at 90.6% validation accuracy, complementing station-based road weather data.
Labels
- Topic
- Observations & remote sensing
- Type
- Application study
- Method
- CNN / U-Net
- Domain
- Regional
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.1080/08839514.2021.1935590 OpenAlex:W3172032788
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.