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
- Distinguishing thistle and johnsongrass from corn plants and other surrounding vegetation.
- Small or partially visible weeds were easy to miss.
- Weeds overlapped or hidden by corn leaves were difficult to annotate.
- Dense agricultural environments produced complex backgrounds.
- Keeping bounding boxes accurate around irregularly shaped plants.
- Growth stages, lighting conditions and image quality varied across the dataset.
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.