images

Preprocessed full resolution images. Used in various stages of pipeline. Are not modified or altered. Output product of Preprocessing stage which includes raw image conversion, color card calibration, and other color corrections.

{state}_{unix time}.jpg

masks

Benchbot binary masks used to ignore blue benchbot area within preprocessed images that can cause errors in AutoSfM processing. Output of Preprocessing stage. Important input for AutoSfM.

{state}_{unix time}.jpg

metadata

various metadata including camera, species, and localization information. Output of remap stage, main input segmentation-vegetation stage that provides bounding box and species information. Cutout ID are added during segment-vegetation

{state}_{unix time}.json

plant-detection

YoloV5 “plant” detections. Created during localize-plants Results are compiled into a single detection csv file. Plant-detections are temporary and will not likely be included in final data upload. Final plant detections are located in metadata

{state}_{unix time}.csv

batch metadata

Metadata associated with the entire batch. Includes list of all images along with basic batch information. Created during segment-vegetation.

{batch id}.json

metamasks/semantic_masks

Semantic labels output from segment-vegetation. Color labels are located in Image and Cutout metadata jsons.

{state}_{unix time}.png

metamasks/instance_masks

Instance labels output from segment-vegetation. Unique color labels are located in cutout metadata.

{state}_{unix time}.png

cutout

Plant cutout with black background.

{state}_{unix time}_{cutout #}.png

cropout

Crop of detection results with original color background.

{state}_{unix time}_{cutout #}.jpg

cutout metadata

Cutout properties and origin information.

{state}_{unix time}_{cutout #}.json

cutout mask

Binary mask of cutout.

{state}_{unix time}_{cutout #}_mask.png

cutout batch csv

cutout metadata compiled into a single csv file. One per batch. Excludes contours.

{batch id}.csv