| HOGDescriptorDetectROI Method |
evaluate specified ROI and return confidence value for each location
Namespace:
OpenCvSharp
Assembly:
OpenCvSharp (in OpenCvSharp.dll) Version: 1.0.0
Syntax public void DetectROI(
Mat img,
Point[] locations,
out Point[] foundLocations,
out double[] confidences,
double hitThreshold = 0,
Nullable<Size> winStride = null,
Nullable<Size> padding = null
)
Public Sub DetectROI (
img As Mat,
locations As Point(),
<OutAttribute> ByRef foundLocations As Point(),
<OutAttribute> ByRef confidences As Double(),
Optional hitThreshold As Double = 0,
Optional winStride As Nullable(Of Size) = Nothing,
Optional padding As Nullable(Of Size) = Nothing
)
public:
void DetectROI(
Mat^ img,
array<Point>^ locations,
[OutAttribute] array<Point>^% foundLocations,
[OutAttribute] array<double>^% confidences,
double hitThreshold = 0,
Nullable<Size> winStride = nullptr,
Nullable<Size> padding = nullptr
)
member DetectROI :
img : Mat *
locations : Point[] *
foundLocations : Point[] byref *
confidences : float[] byref *
?hitThreshold : float *
?winStride : Nullable<Size> *
?padding : Nullable<Size>
(* Defaults:
let _hitThreshold = defaultArg hitThreshold 0
let _winStride = defaultArg winStride null
let _padding = defaultArg padding null
*)
-> unit
Parameters
- img
- Type: OpenCvSharpMat
Matrix of the type CV_8U or CV_8UC3 containing an image where objects are detected. - locations
- Type: OpenCvSharpPoint
Vector of Point - foundLocations
- Type: OpenCvSharpPoint
Vector of Point where each Point is detected object's top-left point. - confidences
- Type: SystemDouble
confidences - hitThreshold (Optional)
- Type: SystemDouble
Threshold for the distance between features and SVM classifying plane. Usually
it is 0 and should be specified in the detector coefficients (as the last free coefficient). But if
the free coefficient is omitted (which is allowed), you can specify it manually here - winStride (Optional)
- Type: SystemNullableSize
winStride - padding (Optional)
- Type: SystemNullableSize
padding
See Also