camera.ui Node SDK

Appearance

@camera.ui/sdk / sensor / ModelSpec

Interface: ModelSpec ​

Defined in: sensor/spec.ts:52

Model spec for detectors with fixed output labels (face, classifier, license plate). Declares the input shape the backend should produce and the trigger labels that should activate this detector.

Extends ​

Properties ​

embeddingModel? ​

optional embeddingModel?: string

Defined in: sensor/spec.ts:58

Embedding model identifier. Required for face recognition and for CLIP: embeddings are stored and matched under this id.

input ​

input: VideoInputSpec

Defined in: sensor/spec.ts:54

Required input frame dimensions and pixel format.

models? ​

optional models?: LoadedModel[]

Defined in: sensor/spec.ts:44

Models this sensor has loaded, primary one first.

Inherited from ​

ModelRuntime.models

runtime? ​

optional runtime?: string

Defined in: sensor/spec.ts:42

Inference framework and version, e.g. 'openvino 2025.3.0'.

Inherited from ​

ModelRuntime.runtime

triggerLabels ​

triggerLabels: ("motion" | "audio" | "person" | "vehicle" | "animal")[]

Defined in: sensor/spec.ts:56

Labels emitted by an upstream object detector that activate this detector (e.g. ['person'] for face detection).