Deep learning has greatly improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly ...

data/raw/violations.csv (298k rows) → src/etl.py (UTC→IST, explode violation JSON, H3-tag, validation-tier) → src/hotspots.py (H3 aggregation + DBSCAN cross-check) → src/scoring.py (Congestion Impact ...