HOGDescriptor class - cv library

Constructors

HOGDescriptor.empty(): factory
HOGDescriptor.fromFile(String filename): This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.
factory
HOGDescriptor.fromPointer(HOGDescriptorPtr ptr, [bool attach = true]): factory

Properties

hashCode → int: The hash code for this object.
no setterinherited
props → List<Object?>: no setterinherited
ptr ↔ Pointer<HOGDescriptor>: getter/setter pairinherited
ref → HOGDescriptor: no setteroverride
runtimeType → Type: A representation of the runtime type of the object.
no setterinherited

Methods

compute(Mat img, {(int, int) winStride = (0, 0), (int, int) padding = (0, 0)}) → (VecF32, VecPoint): Computes HOG descriptors of given image.
computeAsync(Mat img, {(int, int) winStride = (0, 0), (int, int) padding = (0, 0)}) → Future<(VecF32, VecPoint)>: Available on HOGDescriptor, provided by the HOGDescriptorAsync extension
computeGradient(InputArray img, InputOutputArray grad, InputOutputArray angleOfs, {(int, int) paddingTL = (0, 0), (int, int) paddingBR = (0, 0)}) → void: Computes gradients and quantized gradient orientations.
computeGradientAsync(InputArray img, InputOutputArray grad, InputOutputArray angleOfs, {(int, int) paddingTL = (0, 0), (int, int) paddingBR = (0, 0)}) → Future<void>: Available on HOGDescriptor, provided by the HOGDescriptorAsync extension
detect(InputArray img, {double hitThreshold = 0, (int, int) winStride = (0, 0), (int, int) padding = (0, 0)}) → (VecPoint, VecPoint): Performs object detection without a multi-scale window.
detect2(InputArray img, {double hitThreshold = 0, (int, int) winStride = (0, 0), (int, int) padding = (0, 0)}) → (VecPoint, VecF64, VecPoint): Performs object detection without a multi-scale window.
detect2Async(InputArray img, {double hitThreshold = 0, (int, int) winStride = (0, 0), (int, int) padding = (0, 0)}) → Future<(VecPoint, VecF64, VecPoint)>: Available on HOGDescriptor, provided by the HOGDescriptorAsync extension
detectAsync(InputArray img, {double hitThreshold = 0, (int, int) winStride = (0, 0), (int, int) padding = (0, 0)}) → Future<(VecPoint, VecPoint)>: Available on HOGDescriptor, provided by the HOGDescriptorAsync extension
detectMultiScale(InputArray image, {double hitThreshold = 0, int minNeighbors = 3, (int, int) winStride = (0, 0), (int, int) padding = (0, 0), double scale = 1.05, double groupThreshold = 2.0, bool useMeanshiftGrouping = false}) → VecRect: DetectMultiScale calls DetectMultiScale but allows setting parameters The detected objects are returned as a slice of image.Rectangle structs.
detectMultiScaleAsync(InputArray image, {double hitThreshold = 0, int minNeighbors = 3, (int, int) winStride = (0, 0), (int, int) padding = (0, 0), double scale = 1.05, double groupThreshold = 2.0, bool useMeanshiftGrouping = false}) → Future<VecRect>: Available on HOGDescriptor, provided by the HOGDescriptorAsync extension
dispose() → void
getDescriptorSize() → int
getWinSigma() → double: Returns winSigma value.
groupRectangles(VecRect rectList, VecF64 weights, int groupThreshold, double eps) → (VecRect, VecF64): Groups the object candidate rectangles.
groupRectanglesAsync(VecRect rectList, VecF64 weights, int groupThreshold, double eps) → Future<(VecRect, VecF64)>: Available on HOGDescriptor, provided by the HOGDescriptorAsync extension
load(String name) → bool
noSuchMethod(Invocation invocation) → dynamic: Invoked when a nonexistent method or property is accessed.
inherited
setSVMDetector(VecF32 det) → void: SetSVMDetector sets the data for the HOGDescriptor.
toString() → String: A string representation of this object.
inherited

Operators

operator ==(Object other) → bool: The equality operator.
inherited

Static Properties

finalizer → NativeFinalizer: final

Static Methods

getDaimlerPeopleDetector() → VecF32
getDefaultPeopleDetector() → VecF32: HOGDefaultPeopleDetector returns a new Mat with the HOG DefaultPeopleDetector.