Dimensions overall score 5.0

GitHub Code Pulse

No public code linked for this paper yet.

• In-air 3D SONAR sensors can classify road surface materials (asphalt, concrete, element roads) with F1 scores approaching 90%.result 90%
• In-air 3D SONAR sensors achieve around 75% F1 score for road damage detection and classification.result 90%
• SONAR sensing is robust to harsh sensing conditions (heavy rain, smoke, fog) where camera and LiDAR sensors tend to fail.technical 85%
• SONAR sensing enables opportunistic sensing applications where vehicles performing other tasks can monitor road conditions.market 80%
• The study uses a newly collected dataset containing SONAR recordings, camera images, and labels for road materials and damages.method 95%
• The damage detection task determines if damage exists and what type, without localizing the damage.method 90%
• Further research is needed to reach desired accuracy for SONAR-based road damage detection.limitation 90%
• The methodology treats both material classification and damage detection as multilabel classification problems.method 85%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card