Sample frames for this project are available under NDA. Write to bilal@wortel.ai and we will share the relevant before and after pairs.
Challenges
- Counting individual corn plants in dense field environments.
- Distinguishing corn plants from weeds and surrounding vegetation.
- Handling closely positioned and overlapping plants.
- Small corn plants were difficult to detect during early growth stages.
- Annotating partially visible plants accurately.
- Complex backgrounds contained soil, crop residue, and other vegetation.
- Different plant sizes and growth stages required consistent annotation.
- Ensuring no plants were missed or counted multiple times was critical for accurate stand count results.
Related work
Ground Cover Quadrat Segmentation
2,275 cover-crop plot images annotated in Labelbox: plot corners boxed, then every pixel classed as groundcover, weed, residue, crop or soil.
Almond Tree Detection
Bounding boxes around individual almond trees in top-down drone imagery, where shadows and neighbouring vegetation mimicked real trees.
Apple Detection
Bounding boxes around individual apples on tree branches, where dense leaves and occlusion hid much of each fruit.