Aerial Agricultural Dataset

Drone-captured agricultural imagery with crop health annotations for training agricultural robotics and precision farming AI.

Dataset at a Glance

30K+
Video clips
200+
Hours recorded
15+ crop types
Environments
6+
Annotation layers

Comparison with Public Datasets

How Claru's dataset compares to publicly available alternatives.

DatasetClipsHoursModalitiesEnvironmentsAnnotations
Agriculture-Vision94K imagesN/ARGB, NIRUS farms9 crop patterns
WeedMap~1K~5RGB, Multi-spectralSugar beetsWeed masks
Claru Aerial Ag30K+200+RGB, Thermal15+ cropsHealth, weeds, rows, growth, pests

Use Cases

Crop Health Monitoring

Identifying stressed, diseased, or nutrient-deficient crops from aerial views. Example models: PlantVillage, CropSight, Taranis.

Autonomous Spraying

Targeted herbicide and pesticide application using weed detection. Example models: Blue River See & Spray, Ecorobotix, Carbon Robotics.

Yield Prediction

Estimating crop yield from growth stage and health indicators. Example models: Descartes Labs, Indigo Agriculture, Gro Intelligence.

Key References

  1. [1]Chiu et al.. Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis.” CVPR 2020, 2020. Link
  2. [2]Sa et al.. WeedMap: A Large-Scale Semantic Weed Mapping Framework Using Aerial Multispectral Imaging.” Remote Sensing 2018, 2018. Link
  3. [3]Kamilaris & Prenafeta-Boldu. Deep Learning in Agriculture: A Survey.” Computers and Electronics in Agriculture 2018, 2018. Link

How Claru Delivers This Data

Claru operates drone collection campaigns across agricultural regions, capturing RGB and thermal imagery over diverse crop types and growth stages. Thermal data reveals irrigation stress invisible to RGB cameras.

Frequently Asked Questions

15+ crop types including corn, wheat, soybeans, cotton, vineyards, orchards, leafy greens, and specialty crops across different climate zones.

Currently RGB and thermal. Multispectral (NDVI) collection is available on request for specific projects.

Primary collection at 20-50m AGL for crop-level detail, with 100-200m flights for field-level coverage.

Request a Sample Pack

Get a curated sample of aerial agricultural data with full annotations to evaluate for your project.