Sign in
Periphery (Camera)

Capture Boundingbox 2D

Retrieves 2D bounding box data for specified object classes from the scene. Use the set_semantic_label endpoint to assign labels to scene entities.

get/periphery/cameras/capture/bounding-box-2d

Query parameters

result_type'json' | 'rgb_png' | 'jpeg' required

Format which will be used to represent the captured data. 'json' carries the measurements; 'rgb_png' and 'jpeg' are renderings to look at, and jpeg is lossy.

Format which will be used to represent the captured data. 'json' carries the measurements; 'rgb_png' and 'jpeg' are renderings to look at, and jpeg is lossy.

object_classstring[]

Classes of objects to include in the 2D bounding box output. If not specified, returns all labeled instances.

Classes of objects to include in the 2D bounding box output. If not specified, returns all labeled instances.

camera_prim_pathstring nullable

Path of camera prim. Leave it out to capture through the active viewport camera.

Path of camera prim. Leave it out to capture through the active viewport camera.

widthinteger

Image width in px

Image width in px

heightinteger

Image height in px

Image height in px

Response

Successfully fetched 2D bounding box data

labelstring required

Class label for the detected object

bboxnumber[] required

Bounding box coordinates [x_min, y_min, x_max, y_max]

prim_pathstring required

Path to the USD prim of the detected object

semantic_idinteger required

Semantic ID of the detected object

Changes