http://www.emgu.com
Assembly: Emgu.CV.GPU (in Emgu.CV.GPU.dll) Version: 2.3.0.1416 (2.3.0.1416)
Perfroms object detection with increasing detection window.
Namespace: Emgu.CV.GPUAssembly: Emgu.CV.GPU (in Emgu.CV.GPU.dll) Version: 2.3.0.1416 (2.3.0.1416)
Syntax
C# |
---|
public Rectangle[] DetectMultiScale( GpuImage<Bgra, byte> image, double hitThreshold, Size winStride, Size padding, double scale, int groupThreshold ) |
Visual Basic |
---|
Public Function DetectMultiScale ( _ image As GpuImage(Of Bgra, Byte), _ hitThreshold As Double, _ winStride As Size, _ padding As Size, _ scale As Double, _ groupThreshold As Integer _ ) As Rectangle() |
Visual C++ |
---|
public: array<Rectangle>^ DetectMultiScale( GpuImage<Bgra, unsigned char>^ image, double hitThreshold, Size winStride, Size padding, double scale, int groupThreshold ) |
Parameters
- image
- Type: Emgu.CV.GPU..::..GpuImage<(Of <(<'Bgra, Byte>)>)>
The GpuImage to search in
- hitThreshold
- Type: System..::..Double
The threshold for the distance between features and classifying plane.
- winStride
- Type: System.Drawing..::..Size
Window stride. Must be a multiple of block stride.
- padding
- Type: System.Drawing..::..Size
Mock parameter to keep CPU interface compatibility. Must be (0,0).
- scale
- Type: System..::..Double
Coefficient of the detection window increase.
- groupThreshold
- Type: System..::..Int32
After detection some objects could be covered by many rectangles. This coefficient regulates similarity threshold. 0 means don't perform grouping.