用cvGoodFeaturesToTrack()函数进行角点检测

1. 函数定义

public static void cvGoodFeaturesToTrack(
	IntPtr image,
	IntPtr eigImage,
	IntPtr tempImage,
	IntPtr corners,
	ref int cornerCount,
	double qualityLevel,
	double minDistance,
	IntPtr mask,
	int blockSize,
	int useHarris,
	double k
)

2. 函数参数解释

image

Type: System..::..IntPtr
The source 8-bit or floating-point 32-bit, single-channel image

eigImage

Type: System..::..IntPtr
Temporary floating-point 32-bit image of the same size as image

tempImage

Type: System..::..IntPtr
Another temporary image of the same size and same format as eig_image

corners

Type: System..::..IntPtr
Output parameter. Detected corners

cornerCount

Type: System..::..Int32
Output parameter. Number of detected corners

qualityLevel

Type: System..::..Double
Multiplier for the maxmin eigenvalue; specifies minimal accepted quality of image corners

minDistance

Type: System..::..Double
Limit, specifying minimum possible distance between returned corners; Euclidian distance is used

mask

Type: System..::..IntPtr
Region of interest. The function selects points either in the specified region or in the whole image if the mask is IntPtr.Zero

blockSize

Type: System..::..Int32
Size of the averaging block, passed to underlying cvCornerMinEigenVal or cvCornerHarris used by the function

useHarris

Type: System..::..Int32
If nonzero, Harris operator (cvCornerHarris) is used instead of default cvCornerMinEigenVal.

k

Type: System..::..Double
Free parameter of Harris detector; used only if useHarris != 0

3. 应用举例

            Image<Bgr, byte> img = (Image<Bgr, byte>)imageBox_Ori.Image;
            Image<Gray, byte> ImgGray = img.Convert<Gray, byte>();//将原始图像转换为灰度图像

            Image<Gray, Single> imageDest = new Image<Gray, float>(ImgGray.Size);
            Image<Gray, Single> imgTemp = new Image<Gray, float>(ImgGray.Size);
            int count = 700;
            corners = new PointF[count];
            double qualityLevel = 0.01;
            double minDistance = 20;
            int blockSize = 7;
            int useHarris = 0;//是否应用Harris检测角点
            double k = 0.04;//只有在useHarris != 0时起作用

            GCHandle hObject = GCHandle.Alloc(corners, GCHandleType.Pinned);//C#语言中没有指针的概念，对于没有Ptr属性的对象可用此方法获取对象的指针
            IntPtr pObject = hObject.AddrOfPinnedObject();
            CvInvoke.cvGoodFeaturesToTrack(ImgGray.Ptr, imageDest.Ptr, imgTemp.Ptr, pObject, ref count, qualityLevel, minDistance, IntPtr.Zero, blockSize, useHarris, k);
            if (hObject.IsAllocated)
            {
                hObject.Free();
            }
            #endregion

注意：C#语言中没有指针的概念，而cvGoodFeaturesToTrack函数的参数中有很多指针类型，所以此时需要想办法获取各对象的地址。对于一部分如Image,Matrix等类的对象，包含Ptr属性，可直接当作指针来用。而对于没有该属性的变量或对象如数组，则可以通过上述代码中的方法获得其地址。