← All projects

Remote Sensing · AgriTech

Satellite crop segmentation

Field-boundary and crop segmentation across 21 agricultural sites — delivered end-to-end, from raw scenes and dataset construction to trained models and clean handoff.

ROLECV Engineer SCOPE21 agricultural sites STATUSDelivered
Satellite scene segmented into land parcels with cloud and shadow masks and confidence scores

The challenge

No dataset existed

Labels and masks had to be built from raw imagery before any model could learn.

21 sites, one system

Soils, crops, and seasons vary — a single pipeline had to hold everywhere.

Clouds and shadows lie

Occlusions corrupt labels silently — they must be masked, not ignored.

The approach

01

Dataset construction

Built the training corpus across all 21 sites — scenes, labels, quality control.

02

Cloud & shadow masking

Segmented with per-region confidence so contaminated pixels never poison training.

03

Field & crop models

Trained segmentation for boundaries and crop classes across full site diversity.

04

Handoff-ready delivery

Packaged and documented for the client team to run and extend independently.

Outcomes

21 sites

One pipeline

A single segmentation system covering every site.

End-to-end

Dataset → handoff

From raw scenes to a delivered, documented model.

Cloud-aware

Honest labels

Occlusions masked with confidence scores.

Stack PyTorch Segmentation Satellite imagery Dataset construction Cloud / shadow masking Model handoff