Trial data was collected and used to develop the annotation pipeline and test camera settings. The trial was performed between early-March and late-April (2022) in NC under indoor conditions. Details about the data and results follow.

Setup

• 7 batches of images

• 1 batch = 18-48 images

• sunflower and cereal rye(?) at early growth stages

Annotation Data Pipeline

The WIR is made up of five blob containers that store incoming data.

Uploads

Upload batches include images and metadata from a single location and capture period

Batch name example: NC_2022-03-22

Metadata is made up of:

1. Ground control point locations csv measured b

2. Specie map (csv)

Developed

AutoSfM

Developed images, gcps, and Structure from Motion are used to reconstruct the potting area and create a global coordinate reference system (CRS). The resulting CRS, along with camera location metadata, is used to convert local image coordinates into global potting area coordinates.

For example, an image 2000 pixels high and 4000 pixels wide has a local center point at (1000, 2000), half its height and half its width, recorded in pixels. A global CRS allows us to convert this local center point to location on the ground or in the real world.

Detection

Results