The abstract superclass for image analysis requests that track unique features across multiple images or video frames.
SDKs
Framework
Instantiate a tracking request subclass to perform object tracking across multiple frames of an image. After initialization, configure the degree of accuracy by setting tracking, and provide observations you would like to track by setting the input initial bounding box.
enum VNRequestAn enumeration of tracking priorities.
var inputThe observation object defining a region to track.
var trackingA value for specifying whether to prioritize speed or location accuracy.
var isA Boolean that indicates the last frame in a tracking sequence.
Detect and track faces from the selfie cam feed in real time.
Apply Vision algorithms to track objects or rectangles throughout a video.
class VNTrackAn image analysis request that tracks movement of a previously identified rectangular object across multiple images or video frames.
class VNTrackAn image analysis request that tracks movement of a previously identified arbitrary object across multiple images or video frames.
class VNDetectedAn image analysis result that provides the position and extent of a detected image feature.
class VNRecognizedA detected object observation with an array of classification labels that classify the recognized object.
Apply Vision algorithms to identify objects in real-time video.