Precision, recall, and F1 score are classification metrics used to evaluate the performance of AI and machine learning models in pavement and infrastructure defect detection. Precision measures the fraction of detected defects that are correct; recall measures the fraction of actual defects that are found; F1 is their harmonic mean.
TarmacView's AI models are rigorously evaluated using precision, recall, and F1 metrics across pavement distress classes to ensure reliable detection performance.
Object detection locates and classifies objects in images using bounding boxes — for infrastructure inspection, this includes potholes, patches, signs, FOD, and...
AI-based crack detection uses computer vision — convolutional neural networks, vision transformers, and semantic segmentation models — to automatically identify...
Patch condition is a standard inspection item in airport and highway pavement condition surveys. Well-performing patches indicate good maintenance practices; fa...
