SemanticLabel

public final enum SemanticLabel

Defines the labels the Scene Semantics API is able to detect and maps human-readable names to per-pixel semantic labels. See the Scene Semantics Developer Guide for more information.

Use Frame.acquireSemanticImage() to obtain an image containing these pixels and Frame.getSemanticLabelFraction(SemanticLabel) to query what percentage of the image contains these pixels.

Inherited Methods

Enum Values

BUILDING

public static final SemanticLabel BUILDING

Pixels of buildings, including houses, garages, etc. Includes all structures attached to the building, such as signs, solar panels, scaffolding, etc.

OBJECT

public static final SemanticLabel OBJECT

Pixels of general temporary and permanent objects and obstacles, including mailboxes, fire hydrants, poles, street lights, phone booths, bus stop enclosures, cones, parking meters, etc.

PERSON

public static final SemanticLabel PERSON

Pixels of humans and animals.

ROAD

public static final SemanticLabel ROAD

Pixels of drivable surfaces for vehicles, including paved, unpaved, dirt, driveways, etc.

SIDEWALK

public static final SemanticLabel SIDEWALK

Pixels of sidewalks for pedestrians and cyclists, including associated curbs.

SKY

public static final SemanticLabel SKY

Pixels of the open sky, including clouds. Thin electrical wires in front of the sky are included, but leaves/vegetation are not included.

STRUCTURE

public static final SemanticLabel STRUCTURE

Pixels of structures that are not buildings, including fences, guardrails, stand-alone walls, tunnels, bridges, mountains, etc.

TERRAIN

public static final SemanticLabel TERRAIN

Pixels of walkable vegetation areas, including grass, soil, sand, etc. In contrast, 'tree' specifies non-walkable vegetation, like trees and bushes.

TREE

public static final SemanticLabel TREE

Pixels of non-walkable vegetation, like trees and shrubs. In contrast, 'terrain' specifies walkable vegetation, like grass.

UNLABELED

public static final SemanticLabel UNLABELED

Pixels with no semantic label available in the API output.

VEHICLE

public static final SemanticLabel VEHICLE

Pixels of vehicles, including cars, vans, buses, trucks, motorcycles, bicycles, trains, etc.

WATER

public static final SemanticLabel WATER

Pixels of ground surfaces covered by water, including lakes, rivers, etc.