← Annotation portfolio
AgricultureBounding Box

St. John's Wort Detection

Bounding boxes marking St. John's Wort in dense field imagery, telling the weed apart from visually similar crops and grass.

SAMPLE PENDING

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

  • Differentiating St. John's Wort from other weeds and surrounding vegetation.
  • Small plants were hard to identify in dense field environments.
  • Partially visible and overlapping plants complicated placement.
  • Growth stages and plant sizes varied across the dataset.
  • Complex backgrounds contained grass, crops, soil and other weeds.
  • Varying lighting conditions and shadows affected plant visibility.
  • Keeping bounding boxes tight and accurate around irregularly shaped plants required care.

Related work

Ground Cover Quadrat Segmentation - annotation sample

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.

SAMPLE PENDING

Almond Tree Detection

Bounding boxes around individual almond trees in top-down drone imagery, where shadows and neighbouring vegetation mimicked real trees.

SAMPLE PENDING

Apple Detection

Bounding boxes around individual apples on tree branches, where dense leaves and occlusion hid much of each fruit.