[isaaccorley]

Adds ChesapeakeRSC v2, an RGB U-Net with a ResNet-18 encoder trained on 0.6 m NAIP imagery, for extracting road centerlines including roads under tree canopy.

Inference resamples imagery to approximately 0.6 m, blends overlapping 512 × 512 predictions with Hann weights, and traces probability ridges into WGS84 GeoJSON LineStrings. Includes CPU ONNX inference, fine-tuning, Docker images, STAC metadata, and tests.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 96.37%. Comparing base (07ff0da) to head (cc13d31).
⚠️ Report is 1 commits behind head on develop.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop      #81   +/-   ##
========================================
  Coverage    96.37%   96.37%           
========================================
  Files           35       35           
  Lines         3504     3504           
========================================
  Hits          3377     3377           
  Misses         127      127           

Flag	Coverage Δ
fair	96.37% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.