An image analysis request that tracks the movement of a previously identified object across multiple images or video frames.
Use this type of request to track the bounding boxes around objects previously identified in an image. Vision attempts to locate the same object from the input observation throughout the sequence. Each time the request runs, it produces a ``DetectedObjectObservation`` that holds the tracked object's updated bounding box.
- Parameters:
- detectedObject: The object to track
- revision: The specific algorithm or implementation revision that's used to perform the request.
- frameAnalysisSpacing: The duration between analysis operations. Increase this value to reduce the number of frames analyzed on slower devices. By default all frames will be analyzed.
get · iOS 18.0+
descriptor
TypeScript
get descriptor(): RequestDescriptor
Swift declaration
final var descriptor: RequestDescriptor { get }
An enum that identifies the request and request revision.
get · iOS 18.0+
inputObservation
TypeScript
get inputObservation(): (SDKHandle) & (SDKHandle)
Swift declaration
final let inputObservation: any BoundingBoxProviding & VisionObservation
The object which will be tracked.
get · iOS 18.0+
regionOfInterest
TypeScript
get regionOfInterest(): NormalizedRect
Swift declaration
final var regionOfInterest: NormalizedRect { get set }
The region of the image in which Vision will perform the request.
The rectangle is normalized to the dimensions of the processed image. Its origin is specified relative to the image's lower-left corner.
By default, the region of interest will be the full image.
set · iOS 18.0+
regionOfInterest
TypeScript
set regionOfInterest(value: NormalizedRect)
Swift declaration
final var regionOfInterest: NormalizedRect { get set }
The region of the image in which Vision will perform the request.
The rectangle is normalized to the dimensions of the processed image. Its origin is specified relative to the image's lower-left corner.
By default, the region of interest will be the full image.
final func setComputeDevice(_ computeDevice: MLComputeDevice?, for computeStage: ComputeStage)
Assigns a compute device for a compute stage.
If the parameter `computeDevice` is `nil`, the framework removes any explicit compute device assignment and allows the framework to select the device.
Configure any compute device for a given compute stage. When performing a request, the system makes a validity check. Use `supportedComputeStageDevices` to get valid compute devices for a request’s compute stages.
- Parameters:
- `computeDevice: `The compute device to assign to the compute stage.
- `computeStage: `The compute stage.
get · iOS 18.0+
supportedRevisions
TypeScript
static get supportedRevisions(): Array<TrackObjectRequest_Revision>
Swift declaration
static let supportedRevisions: [TrackObjectRequest.Revision]
The collection of currently-supported revisions for `TrackObjectRequest`.
get · iOS 18.0+
frameAnalysisSpacing
TypeScript
get frameAnalysisSpacing(): _CoreMedia_CMTime
Swift declaration
final let frameAnalysisSpacing: CMTime
The reciprocal of maximum rate at which buffers will be processed.
The request will not process buffers that fall within the `frameAnalysisSpacing` since the previously performed analysis.
The analysis is not done by wall time but by analysis of of the time stamps of the samplebuffers being processed.
