A transformer that selects one pose from an array of poses.
Members (9)
get · iOS 16.0+
debugDescription
TypeScript
get debugDescription(): string
Swift declaration
var debugDescription: String { get }
A textual representation of this instance, suitable for debugging.
Calling this property directly is discouraged. Instead, convert an
instance of any type to a string by using the `String(reflecting:)`
initializer. This initializer works with any type, and uses the custom
`debugDescription` property for types that conform to
`CustomDebugStringConvertible`:
struct Point: CustomDebugStringConvertible {
let x: Int, y: Int
var debugDescription: String {
return "(\(x), \(y))"
}
}
let p = Point(x: 21, y: 30)
let s = String(reflecting: p)
print(s)
// Prints "(21, 30)"
The conversion of `p` to a string in the assignment to `s` uses the
`Point` type's `debugDescription` property.
get · iOS 16.0+
confidenceThreshold
TypeScript
get confidenceThreshold(): number
Swift declaration
var confidenceThreshold: Float
A threshold confidence between 0 to 1 for the joints to be considered valid in pose selection. The default value is 0.2.
set · iOS 16.0+
confidenceThreshold
TypeScript
set confidenceThreshold(value: number)
Swift declaration
var confidenceThreshold: Float
A threshold confidence between 0 to 1 for the joints to be considered valid in pose selection. The default value is 0.2.
Select a pose if multiple poses are detected on the same frame.
- Parameters:
- input: An array of poses.
- eventHandler: An event handler.
- Returns: A selected pose based on the strategy.
Creates a pose selector.
- Parameters:
- strategy: The strategy used to choose a pose if multiple poses are detected on the same frame. Default strategy is to select a pose with maximum bounding box area.
- confidenceThreshold: A threshold confidence between 0 to 1 for the joints to be considered valid in pose selection. The default value is 0.2.
Creates a pose selector.
- Parameters:
- strategy: The strategy used to choose a pose if multiple poses are detected on the same frame. Default strategy is to select a pose with maximum bounding box area.
