
Segmented car mask visualized.
Usage Example
For segmentation, we highly recommend using the Structured Outputs API to get the segmentation masks in a structured and validated data format. The output masks will be in PNG format that can be retrieved as a pre-signed URL, per object instance.
FAQ
What different types of segmentation are supported?
What different types of segmentation are supported?
- Instance Segmentation: Segment individual objects with unique masks
- Semantic Segmentation: Classify pixels by category or class
- Panoptic Segmentation: Combine instance and semantic segmentation
What format do the segmentation masks come in?
What format do the segmentation masks come in?
The segmentation masks come in the format of a list of objects with their masks. The masks are in PNG format that can be retrieved as a pre-signed URL, per object instance.
What types of objects and categories can be segmented?
What types of objects and categories can be segmented?
Common Objects
- People: person, face, hand, foot
- Vehicles: car, truck, bus, motorcycle, bicycle
- Animals: dog, cat, bird, horse, cow, sheep
- Furniture: chair, table, bed, sofa, desk
- Electronics: laptop, phone, tv, keyboard, mouse
- Medical: organ, tissue, lesion, bone
- Nature: tree, grass, sky, water, mountain
- Indoor: wall, floor, ceiling, door, window
- Outdoor: road, sidewalk, building, sign, traffic_light
What mask formats are supported?
What mask formats are supported?
PNG Masks
- Binary or grayscale images where each pixel value represents a segment ID
- Compatible with most image editing software
- Small file size for simple segmentations