Fig. 1 | Scientific Data

Fig. 1

From: Helmets Labeling Crops: Kenya Crop Type Dataset Created via Helmet-Mounted Cameras and Deep Learning

Fig. 1

Illustration of crop type data generation pipeline. Steps: 1) Field agent with helmet-mounted GoPro drives along agricultural fields, 2) GoPro captures photo of adjacent field (red dotted line) and road coordinate (red point), 3) field coordinate (orange point) is calculated by moving road coordinate 20 meters into field and snapping to 10 meter grid, 4) GoPro photo is used to predict dominant crop.

Back to article page