Pixels of general temporary and permanent objects and obstacles, including street signs, traffic signs, free-standing business signs, billboards, poles, mailboxes, fire hydrants, street lights, phone booths, bus stop enclosures, cones, parking meters, animals, etc.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-07-14 UTC."],[[["\u003cp\u003eThe Scene Semantics API allows developers to identify and interact with real-world objects in a scene by assigning semantic labels to pixels in an image.\u003c/p\u003e\n"],["\u003cp\u003eThese labels categorize objects like buildings, trees, roads, people, and vehicles, enhancing AR experiences.\u003c/p\u003e\n"],["\u003cp\u003eDevelopers can access an image with these semantic labels and analyze the proportion of each label in the image using dedicated functions.\u003c/p\u003e\n"],["\u003cp\u003eThis API provides valuable scene understanding capabilities for various AR applications, enabling interactions based on object types.\u003c/p\u003e\n"],["\u003cp\u003eRefer to the Scene Semantics Developer Guide for detailed information and implementation instructions.\u003c/p\u003e\n"]]],[],null,["# ArSemanticLabel\n===============\n\nScene Semantics API.\n\nSee the [Scene Semantics Developer Guide](https://developers.google.com/ar/develop/c/scene-semantics) for more information.\n\nSummary\n-------\n\n| ### Enumerations ||\n|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------|\n| [ArSemanticLabel](#arsemanticlabel)`{` ` `[AR_SEMANTIC_LABEL_UNLABELED](#ar_semantic_label_unlabeled)` = 0,` ` `[AR_SEMANTIC_LABEL_SKY](#ar_semantic_label_sky)` = 1,` ` `[AR_SEMANTIC_LABEL_BUILDING](#ar_semantic_label_building)` = 2,` ` `[AR_SEMANTIC_LABEL_TREE](#ar_semantic_label_tree)` = 3,` ` `[AR_SEMANTIC_LABEL_ROAD](#ar_semantic_label_road)` = 4,` ` `[AR_SEMANTIC_LABEL_SIDEWALK](#ar_semantic_label_sidewalk)` = 5,` ` `[AR_SEMANTIC_LABEL_TERRAIN](#ar_semantic_label_terrain)` = 6,` ` `[AR_SEMANTIC_LABEL_STRUCTURE](#ar_semantic_label_structure)` = 7,` ` `[AR_SEMANTIC_LABEL_OBJECT](#ar_semantic_label_object)` = 8,` ` `[AR_SEMANTIC_LABEL_VEHICLE](#ar_semantic_label_vehicle)` = 9,` ` `[AR_SEMANTIC_LABEL_PERSON](#ar_semantic_label_person)` = 10,` ` `[AR_SEMANTIC_LABEL_WATER](#ar_semantic_label_water)` = 11` `}` | enum Defines the labels the Scene Semantics API is able to detect and maps human-readable names to per-pixel semantic labels. |\n\nEnumerations\n------------\n\n### ArSemanticLabel\n\n```text\n ArSemanticLabel\n``` \nDefines the labels the Scene Semantics API is able to detect and maps human-readable names to per-pixel semantic labels.\n\nSee the [Scene Semantics Developer Guide](https://developers.google.com/ar/develop/c/scene-semantics) for more information.\n\nUse [ArFrame_acquireSemanticImage](/ar/reference/c/group/ar-frame#arframe_acquiresemanticimage) to obtain an image containing these pixels and [ArFrame_getSemanticLabelFraction](/ar/reference/c/group/ar-frame#arframe_getsemanticlabelfraction) to query what percentage of the image contains these pixels.\n\n| Properties ||\n|-----------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| AR_SEMANTIC_LABEL_BUILDING | Pixels of buildings, including houses, garages, etc. Includes all structures attached to the building, such as signs, solar panels, scaffolding, etc. |\n| AR_SEMANTIC_LABEL_OBJECT | Pixels of general temporary and permanent objects and obstacles, including street signs, traffic signs, free-standing business signs, billboards, poles, mailboxes, fire hydrants, street lights, phone booths, bus stop enclosures, cones, parking meters, animals, etc. |\n| AR_SEMANTIC_LABEL_PERSON | Pixels of humans, including pedestrians and bicycle/motorcycle riders. |\n| AR_SEMANTIC_LABEL_ROAD | Pixels of drivable surfaces for vehicles, including paved, unpaved, dirt, driveways, crosswalks, etc. |\n| AR_SEMANTIC_LABEL_SIDEWALK | Pixels of sidewalks for pedestrians and cyclists, including associated curbs. |\n| AR_SEMANTIC_LABEL_SKY | Pixels of the open sky, including clouds. Thin electrical wires in front of the sky are included, but leaves/vegetation are not included. |\n| AR_SEMANTIC_LABEL_STRUCTURE | Pixels of structures that are not buildings, including fences, guardrails, stand-alone walls, tunnels, bridges, etc. |\n| AR_SEMANTIC_LABEL_TERRAIN | Pixels of walkable vegetation areas, including grass, soil, sand, mountains, etc. In contrast, 'tree' specifies non-walkable vegetation, like trees and bushes. |\n| AR_SEMANTIC_LABEL_TREE | Pixels of non-walkable vegetation, like trees and shrubs. In contrast, 'terrain' specifies walkable vegetation, like grass. |\n| AR_SEMANTIC_LABEL_UNLABELED | Pixels with no semantic label available in the API output. |\n| AR_SEMANTIC_LABEL_VEHICLE | Pixels of vehicles, including cars, vans, buses, trucks, motorcycles, bicycles, trains, etc. |\n| AR_SEMANTIC_LABEL_WATER | Pixels of ground surfaces covered by water, including lakes, rivers, etc. |"]]