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
- Detecting small objects such as coins and bolts in railway environments.
- Railway objects had to be distinguished from similar-looking background elements.
- Partially visible or occluded objects complicated box placement.
- Traffic signs appeared at different distances and orientations.
- Hectometer stones required careful identification among surrounding infrastructure.
- Cable poles and other tall objects needed accurate bounding box placement.
- Complex backgrounds containing tracks, gravel, vegetation and equipment made detection challenging.
- Keeping annotations accurate across multiple object categories required careful quality control.
Related work
Engineering Drawing Segmentation
Rooms, service runs and annotation blocks marked out on CAD floor plans so drawings can be parsed automatically.
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.