/// <summary>
/// 取得一个样本的特征
/// </summary>
/// <param name="bmpSource">源图像，需24位或32位真彩位图</param>
/// <param name="template">基础分类器模板</param>
/// <param name="sampletype">样本类型，1表示正样本，－1表示负样本</param>
/// <returns>返回一个样本的特征</returns>
public static SampleFeature GetSampleFeature(Bitmap bmpSource, BaseClassifierTemplate template, int sampletype)
{
SampleFeature sf = null;
Bitmap bmp = bmpSource;
if (bmp != null && (bmp.PixelFormat == PixelFormat.Format24bppRgb || bmp.PixelFormat ==
PixelFormat.Format32bppRgb || bmp.PixelFormat == PixelFormat.Format32bppArgb))
{
// 将图像调整至模板大小
if (bmp.Width != template.BmpWidth || bmp.Height != template.BmpHeight)
{
bmp = ImgOper.ResizeImage(bmpSource, template.BmpWidth, template.BmpHeight);
}
bmp = ImgOper.Grayscale(bmpSource);
int[,] igram = ImgOper.Integrogram(bmp, 1);
sf = new SampleFeature();
sf.GroupNum = template.GroupNum;
sf.FeatureNum = template.FeatureNum;
sf.SampleType = sampletype;
sf.FeatureValue = BaseClassifierTemplate.GetFeatureCodeGroup(igram, bmp.Width, bmp.Height, template, 0, 0);
}
return(sf);
}
/// <summary>
/// 用模板去检测图像中的物体
/// </summary>
/// <param name="bmpSource">源图像，需24位或32位真彩位图</param>
/// <param name="template">基础分类器模板</param>
/// <param name="fern">Fern</param>
/// <returns></returns>
public static RectangleCollection DetectObject(Bitmap bmpSource, BaseClassifierTemplate template, Fern fern)
{
RectangleCollection rc = new RectangleCollection();
Bitmap bmp = bmpSource;
if (bmpSource.Width < template.BmpWidth || bmpSource.Height < template.BmpHeight)
{
return(null);
}
if (bmp != null && (bmp.PixelFormat == PixelFormat.Format24bppRgb || bmp.PixelFormat ==
PixelFormat.Format32bppRgb || bmp.PixelFormat == PixelFormat.Format32bppArgb))
{
UInt32[] featurecode = null;
bmp = ImgOper.Grayscale(bmpSource);
int[,] igram = ImgOper.Integrogram(bmp, 1);
while (template.BmpWidth < bmp.Width && template.BmpHeight < bmp.Height)
{
for (int y = 0; y < bmp.Height - template.BmpHeight + 1; y += (template.BmpHeight / 10))
{
for (int x = 0; x < bmp.Width - template.BmpWidth + 1; x += (template.BmpWidth / 10))
{
//int posnum = 0;
//int negnum = 0;
featurecode = BaseClassifierTemplate.GetFeatureCodeGroup(igram, bmp.Width, bmp.Height, template, x, y);
double prob = 0;
for (int i = 0; i < template.GroupNum; i++)
{
prob += fern.Probability[featurecode[i]];
//prob = fern.Probability[featurecode[i]];
//if (prob > 0.5)
//{
// posnum++;
//}
//else
//{
// negnum++;
//}
}
prob = prob / template.GroupNum;
if (prob > 0.5)
//if (posnum > negnum)
{
Rectangle rect = new Rectangle(x, y, template.BmpWidth, template.BmpHeight);
rc.Add(rect);
}
}
}
template.ResizeTemplate(1.2);
}
}
return(rc);
}
/// <summary>
/// 负样本检测专家，专门检测被误判为正的负样本和增加负样本集合
/// </summary>
/// <param name="detectCollection">检测模块产生的区域集合</param>
/// <param name="trackerRect">跟踪模块产生的区域</param>
/// <param name="bmp">被检测的位图</param>
/// <returns>返回最可信对象区域</returns>
public Rectangle NegativeExpert(RectangleCollection detectCollection, RectangleF trackerRect, Bitmap bmp)
{
// 复制一个矩形集合是为了让NExpert独立与PExpert
RectangleCollection newRectCollection = new RectangleCollection();
if (detectCollection != null)
{
foreach (Rectangle detectrect in detectCollection)
{
newRectCollection.Add(detectrect);
}
}
if (trackerRect != Rectangle.Empty)
{
// 将跟踪到的目标也加入待评估的对象集合
newRectCollection.Add(new Rectangle((int)trackerRect.X, (int)trackerRect.Y, (int)trackerRect.Width, (int)trackerRect.Height));
}
DateTime dt = DateTime.Now;
// 最可信的对象
Rectangle confidentRect = MinDistanceObject(newRectCollection, bmp);
double elapse = DateTime.Now.Subtract(dt).TotalMilliseconds;
if (confidentRect != Rectangle.Empty)
{
newRectCollection.Remove(confidentRect);
}
dt = DateTime.Now;
foreach (Rectangle rect in newRectCollection)
{
// 判断目标是否确实为背景，正距离归一化系数大于0.5
// 目标加入负样本队列的第一道关，目标必须看起来像负样本（正距离归一化系数大于0.5）
if (MinDistance(rect, bmp) > Parameter.MEDIAN_COEF)
{
double areainsect = AreaProportion(confidentRect, rect);
// 与最可信对象交集面积小于AREA_INTERSECT_PROPORTION的为负样本，加入负样本列表
if (areainsect < Parameter.AREA_INTERSECT_PROPORTION)
{
Bitmap patch = ImgOper.CutImage(bmp, rect.X, rect.Y, rect.Width, rect.Height);
TrainNegative(patch);
}
}
}
elapse = DateTime.Now.Subtract(dt).TotalMilliseconds;
return(confidentRect);
}
/// <summary>
/// 正样本检测专家，专门检测被误判为负的正样本
/// </summary>
/// <param name="detectCollection">检测模块产生的区域集合</param>
/// <param name="trackerRect">跟踪模块产生的区域</param>
/// <param name="bmp">被检测位图</param>
public void PositiveExpert(RectangleCollection detectCollection, RectangleF trackerRect, Bitmap bmp)
{
double areaproportion = 0;
bool nointersect = true; // 指明跟踪模块和检测模块得到的区域是否无交集
if (trackerRect == Rectangle.Empty)
{
return;
}
foreach (Rectangle rect in detectCollection)
{
areaproportion = AreaProportion(trackerRect, rect);
if (areaproportion > Parameter.AREA_INTERSECT_PROPORTION)
{
nointersect = false;
break;
}
}
// 没有交集，说明存在被误判为负的正样例
if (nointersect)
{
// 判断跟踪到的目标是否确实为要识别的物体，正距离归一化系数小于0.5
// 目标加入正样本队列的第一道关，目标必须看起来像正样本（正距离归一化系数小于0.5）
if (MinDistance(trackerRect, bmp) < Parameter.MEDIAN_COEF)
{
for (double lrshift = (-1) * Parameter.SHIFT_BORDER; lrshift < Parameter.SHIFT_BORDER + Parameter.SHIFT_INTERVAL; lrshift += Parameter.SHIFT_INTERVAL)
{
for (double tbshift = (-1) * Parameter.SHIFT_BORDER; tbshift < Parameter.SHIFT_BORDER + Parameter.SHIFT_INTERVAL; tbshift += Parameter.SHIFT_INTERVAL)
{
if (trackerRect.X + lrshift >= 0 && trackerRect.X + trackerRect.Width - 1 + lrshift < bmp.Width - 1 &&
trackerRect.Y + tbshift >= 0 && trackerRect.Y + trackerRect.Height - 1 + tbshift < bmp.Height - 1)
{
Bitmap patch = ImgOper.CutImage(bmp, (int)(trackerRect.X + lrshift), (int)(trackerRect.Y + tbshift),
(int)trackerRect.Width, (int)trackerRect.Height);
TrainPositive(patch);
}
}
}
}
}
}
/// <summary>
/// 计算正样本最大相关系数，数值越大，被检测对象越接近目标
/// </summary>
/// <param name="rect">检测目标区域</param>
/// <param name="bmp">位图</param>
/// <returns>正样本最大相关系数</returns>
public double MostAssociate(Rectangle rect, Bitmap bmp)
{
double maxcoef = 0; // 返回值
double coef = 0;
double maxposcoef = 0;
double maxnegcoef = 0;
if (rect == Rectangle.Empty)
{
return(maxcoef);
}
Bitmap patch = ImgOper.CutImage(bmp, rect.X, rect.Y, rect.Width, rect.Height);
patch = ImgOper.ResizeImage(patch, Parameter.DETECT_WINDOW_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height);
patch = ImgOper.Grayscale(patch);
foreach (ValuedBitmap posbmp in PosMapCollection)
{
coef = ImgStatCompute.ComputeAssociationCoef(patch, posbmp.VBitmap);
if (maxposcoef < coef)
{
maxposcoef = coef;
}
}
foreach (ValuedBitmap negbmp in NegMapCollection)
{
coef = ImgStatCompute.ComputeAssociationCoef(patch, negbmp.VBitmap);
if (maxnegcoef < coef)
{
maxnegcoef = coef;
}
}
if (maxnegcoef != 0 || maxposcoef != 0)
{
maxcoef = maxposcoef / (maxposcoef + maxnegcoef);
}
return(maxcoef);
}
/// <summary>
/// 直接计算两幅灰度图的相关系数
/// </summary>
/// <param name="bmpX"></param>
/// <param name="bmpY"></param>
/// <returns></returns>
public static double ComputeAssociationCoef(Bitmap bmpX, Bitmap bmpY)
{
int[,] igramX1 = null; //第一幅图像的标准积分图
int[,] igramX2 = null; //第一幅图像的平方积分图
int[,] igramY1 = null; //第二幅图像的标准积分图
int[,] igramY2 = null; //第二幅图像的平方积分图
int[,] igramXY1 = null; //两幅图像相乘积分图
if (bmpX != null && bmpX.PixelFormat == PixelFormat.Format8bppIndexed &&
bmpY != null && bmpY.PixelFormat == PixelFormat.Format8bppIndexed &&
bmpX.Width == bmpY.Width && bmpX.Height == bmpY.Height)
{
Rectangle rect = new Rectangle(0, 0, bmpX.Width, bmpY.Height);
igramX1 = ImgOper.Integrogram(bmpX, 1);
igramX2 = ImgOper.Integrogram(bmpX, 2);
igramY1 = ImgOper.Integrogram(bmpY, 1);
igramY2 = ImgOper.Integrogram(bmpY, 2);
igramXY1 = ImgOper.Integrogram(bmpX, bmpY, 1);
return(ComputeAssociationCoef(igramX1, igramX2, igramY1, igramY2, igramXY1, rect));
}
return(0);
}
private void btnOk_Click(object sender, EventArgs e)
{
Bitmap patch = null;
if (pri_tld != null && pri_bmp != null && pri_choose_rect != Rectangle.Empty)
{
for (double lrshift = (-1) * Parameter.SHIFT_BORDER; lrshift < Parameter.SHIFT_BORDER + Parameter.SHIFT_INTERVAL; lrshift += Parameter.SHIFT_INTERVAL)
{
for (double tbshift = (-1) * Parameter.SHIFT_BORDER; tbshift < Parameter.SHIFT_BORDER + Parameter.SHIFT_INTERVAL; tbshift += Parameter.SHIFT_INTERVAL)
{
if (pri_choose_rect.X + lrshift >= 0 && pri_choose_rect.X + pri_choose_rect.Width - 1 + lrshift < pri_bmp.Width - 1 &&
pri_choose_rect.Y + tbshift >= 0 && pri_choose_rect.Y + pri_choose_rect.Height - 1 + tbshift < pri_bmp.Height - 1)
{
patch = ImgOper.CutImage(pri_bmp, (int)(pri_choose_rect.X + lrshift), (int)(pri_choose_rect.Y + tbshift),
(int)pri_choose_rect.Width, (int)pri_choose_rect.Height);
pri_tld.TrainPositive(patch);
//patch.Save("Image\\VideoSave\\" + DateTime.Now.ToString("yyyyMMddhhmmss") + ".jpg");
}
}
}
for (int row = 0; row < pri_bmp.Height - Parameter.DETECT_WINDOW_SIZE.Height + 1; row += Parameter.DETECT_WINDOW_SIZE.Height)
{
for (int col = 0; col < pri_bmp.Width - Parameter.DETECT_WINDOW_SIZE.Width + 1; col += Parameter.DETECT_WINDOW_SIZE.Width)
{
Rectangle rect = new Rectangle(col, row, pri_choose_rect.Width, pri_choose_rect.Height);
double areaportion = pri_tld.AreaProportion(rect, pri_choose_rect);
if (areaportion < Parameter.AREA_INTERSECT_PROPORTION)
{
patch = ImgOper.CutImage(pri_bmp, rect.X, rect.Y, rect.Width, rect.Height);
pri_tld.TrainNegative(patch);
}
}
}
}
pri_player.Start();
this.Close();
}
/// <summary>
/// 用训练好的模型测试已标记样本的类别
/// </summary>
/// <param name="sample">已标记样本图像</param>
/// <param name="template">基础分类器模板</param>
/// <param name="fern">Fern</param>
/// <returns>返回测试结果，类别</returns>
public static int DetectSample(Bitmap sample, BaseClassifierTemplate template, Fern fern)
{
Bitmap bmp = null;
if (sample.Width != template.BmpWidth || sample.Height != template.BmpHeight)
{
bmp = ImgOper.ResizeImage(sample, template.BmpWidth, template.BmpHeight);
}
else
{
bmp = sample;
}
if (bmp != null && (bmp.PixelFormat == PixelFormat.Format24bppRgb || bmp.PixelFormat ==
PixelFormat.Format32bppRgb || bmp.PixelFormat == PixelFormat.Format32bppArgb))
{
bmp = ImgOper.Grayscale(bmp);
int[,] igram = ImgOper.Integrogram(bmp, 1);
UInt32[] featurecode = BaseClassifierTemplate.GetFeatureCodeGroup(igram, bmp.Width, bmp.Height, template, 0, 0);
double prob = 0;
for (int i = 0; i < template.GroupNum; i++)
{
prob += fern.Probability[featurecode[i]];
}
prob = prob / template.GroupNum;
if (prob > 0.5)
{
return(1);
}
else
{
return(-1);
}
}
return(0);
}
/// <summary>
/// 高斯卷积（模糊）
/// </summary>
/// <param name="bmp">原位图</param>
///// <param name="sigma">sigma</param>
///// <param name="lenght">卷积核边长（像素）</param>
public static Bitmap GaussianConvolution(Bitmap bmpSource, double sigma, int length
)
{
Bitmap bmp = null;
double[] gaussian_coef = new double[length];
for (int i = 0; i < length; i++)
{
gaussian_coef[i] = Math.Pow(Math.E, -((i - length / 2) * (i - length / 2)) / (2 * sigma * sigma)) / Math.Sqrt(2 * Math.PI) * sigma;
}
if (bmpSource == null)
{
return(bmp);
}
if (bmpSource.PixelFormat == PixelFormat.Format24bppRgb || bmpSource.PixelFormat ==
PixelFormat.Format32bppRgb || bmpSource.PixelFormat == PixelFormat.Format32bppArgb)
{
bmpSource = ImgOper.Grayscale(bmpSource);
}
if (bmpSource.PixelFormat != PixelFormat.Format8bppIndexed)
{
return(bmp);
}
int width = bmpSource.Width;
int height = bmpSource.Height;
Rectangle rect = new Rectangle(0, 0, width, height);
BitmapData dataSource = bmpSource.LockBits(rect, ImageLockMode.ReadOnly, bmpSource.PixelFormat);
// Stride为位图中每一行以4字节对齐的行宽
int strideSource = dataSource.Stride;
double[,] bmpdata1 = new double[height, width];
double[,] bmpdata2 = new double[height, width];
unsafe
{
byte * ptrSource = (byte *)dataSource.Scan0.ToPointer();
byte * ptr1;
double d = 0; // 临时计算某点上的卷积值
byte minvalue = 255;
byte maxvalue = 0;
double minvalue_double = double.MaxValue;
double maxvalue_double = 0;
for (int row = 0; row < height; row++)
{
for (int col = 0; col < width; col++)
{
// 位图的在内存中的排列是从左到右，从下到上的，但BitmapData貌似做了优化，把位图数据在内存中的排列
// 顺序改为与坐标系一致，即从左到右、从上到下
ptr1 = ptrSource + row * strideSource + col;
d = 0;
for (int i = 0; i < length; i++)
{
if (col + i - length / 2 >= 0 && col + i - length / 2 < width)
{
d += *(ptr1 + i - length / 2) * gaussian_coef[i];
}
}
bmpdata1[row, col] = d;
if (*ptr1 > maxvalue)
{
maxvalue = *ptr1;
}
if (*ptr1 < minvalue)
{
minvalue = *ptr1;
}
}
}
for (int col = 0; col < width; col++)
{
for (int row = 0; row < height; row++)
{
d = 0;
for (int i = 0; i < length; i++)
{
if (row + i - length / 2 >= 0 && row + i - length / 2 < height)
{
d += bmpdata1[row + i - length / 2, col] * gaussian_coef[i];
}
}
bmpdata2[row, col] = d;
if (d > maxvalue_double)
{
maxvalue_double = d;
}
if (d < minvalue_double)
{
minvalue_double = d;
}
}
}
for (int row = 0; row < height; row++)
{
for (int col = 0; col < width; col++)
{
ptr1 = ptrSource + row * strideSource + col;
*ptr1 = (byte)(bmpdata2[row, col] * (maxvalue - minvalue) / (maxvalue_double - minvalue_double));
}
}
bmpSource.UnlockBits(dataSource);
bmp = bmpSource;
}
return(bmp);
}
private void videoSourcePlayer1_NewFrame(object sender, ref Bitmap image)
{
Bitmap nowImg = AForge.Imaging.Image.Clone(image);
nowImg = ImgOper.Grayscale(nowImg);
// 做高斯模糊，取样和检测都会影响到
nowImg = ImgOper.GaussianConvolution(nowImg, Parameter.GAUSSIAN_SIGMA, Parameter.GAUSSIAN_SIZE);
// 将图像传递到取样窗口
pri_bmp = AForge.Imaging.Image.Clone(nowImg);
double elapse = 0;
DateTime dt = DateTime.Now;
pri_obj_regions = pri_tld.HogDetect(nowImg);
elapse = DateTime.Now.Subtract(dt).TotalMilliseconds;
float[] vect = new float[3]; // 描述区域位移和缩放
//nowImg.Save("Image\\VideoSave\\" + DateTime.Now.ToString("yyyyMMddhhmmss") + ".jpg");
ArrayList points = null;
if (pri_optical.IPoints == null || pri_tracker_rect == Rectangle.Empty)
{
pri_optical.I = pri_optical.TransformBmpToLayerImg(nowImg);
// 尚未确定跟踪对象，不需要PositiveExpert
pri_tracker_rect = pri_tld.NegativeExpert(pri_obj_regions, pri_tracker_rect, nowImg);
pri_optical.IPoints = new ArrayList();
points = pri_optical.ChooseRectRandomPoints(pri_tracker_rect, Parameter.INITIAL_POINTS_NUMBER);
foreach (PointF pt in points)
{
pri_optical.IPoints.Add(new PointF(pt.X, pt.Y));
}
}
else
{
if (pri_optical.J != null)
{
pri_optical.I = pri_optical.J;
pri_optical.IPoints = pri_optical.JPoints;
}
pri_optical.J = pri_optical.TransformBmpToLayerImg(nowImg);
//pri_optical.JPoints = new ArrayList();
// 跟踪时wx和wy设为3，或者更大
dt = DateTime.Now;
vect = pri_optical.ComputerDisplacement(pri_optical.I, pri_optical.J, pri_optical.IPoints,
1, 3, 3, 20, 0.2f, ref pri_optical.IPoints, ref pri_optical.JPoints);
elapse = DateTime.Now.Subtract(dt).TotalMilliseconds;
if (vect != null)
{
pri_tracker_rect.X = pri_tracker_rect.X + vect[0];
pri_tracker_rect.Y = pri_tracker_rect.Y + vect[1];
pri_tracker_rect.Width = pri_tracker_rect.Width * vect[2];
pri_tracker_rect.Height = pri_tracker_rect.Height * vect[2];
if (pri_tracker_rect.X < 0)
{
pri_tracker_rect.Width = pri_tracker_rect.Width + pri_tracker_rect.X;
pri_tracker_rect.X = 0;
}
else if (pri_tracker_rect.X + pri_tracker_rect.Width - 1 > nowImg.Width - 1)
{
pri_tracker_rect.Width = nowImg.Width - pri_tracker_rect.X;
}
if (pri_tracker_rect.Y < 0)
{
pri_tracker_rect.Height = pri_tracker_rect.Height + pri_tracker_rect.Y;
pri_tracker_rect.Y = 0;
}
else if (pri_tracker_rect.Y + pri_tracker_rect.Height - 1 > nowImg.Height - 1)
{
pri_tracker_rect.Height = nowImg.Height - pri_tracker_rect.Y;
}
}
else
{
pri_tracker_rect = Rectangle.Empty;
}
// 在跟踪框被NExpert产生的最可信对象替代前保存原始状态
if (pri_tracker_rect != Rectangle.Empty)
{
pri_obj_rect = new RectangleF(pri_tracker_rect.X, pri_tracker_rect.Y, pri_tracker_rect.Width, pri_tracker_rect.Height);
}
dt = DateTime.Now;
// 有跟踪对象时，PositvieExpert与NegativeExpert都开始工作
pri_tld.PositiveExpert(pri_obj_regions, pri_tracker_rect, nowImg);
elapse = DateTime.Now.Subtract(dt).TotalMilliseconds;
dt = DateTime.Now;
pri_tracker_rect = pri_tld.NegativeExpert(pri_obj_regions, pri_tracker_rect, nowImg);
elapse = DateTime.Now.Subtract(dt).TotalMilliseconds;
pri_optical.JPoints = new ArrayList();
points = pri_optical.ChooseRectRandomPoints(pri_tracker_rect, Parameter.INITIAL_POINTS_NUMBER);
// 如果pri_tracker_rect为空，则pri_optical.JPoints为空，那么下次跟踪的pri_optical.Ipoints也为空，无法继续跟踪
foreach (PointF pt in points)
{
pri_optical.JPoints.Add(new PointF(pt.X, pt.Y));
}
}
Graphics g = Graphics.FromImage(image);
Pen pen = new Pen(Color.Red);
if (pri_tracker_rect != Rectangle.Empty)
{
g.DrawRectangle(pen, pri_tracker_rect.X, pri_tracker_rect.Y, pri_tracker_rect.Width, pri_tracker_rect.Height);
FontFamily f = new FontFamily("宋体");
Font font = new System.Drawing.Font(f, 12);
SolidBrush myBrush = new SolidBrush(Color.Blue);
StringBuilder str = new StringBuilder();
if (vect != null)
{
str.AppendFormat("跟踪框相对位移：({0}, {1})，缩放：{2} \r\n" +
"跟踪产生的Rectangle：({3}, {4}, {5}, {6}) \r\n" +
"最可信的Rectangle：({7}, {8}, {9}, {10})", vect[0], vect[1], vect[2],
pri_obj_rect.X, pri_obj_rect.Y, pri_obj_rect.Width, pri_obj_rect.Height,
pri_tracker_rect.X, pri_tracker_rect.Y, pri_tracker_rect.Width, pri_tracker_rect.Height);
}
else
{
str.AppendFormat("最可信的Rectangle：({0}, {1}, {2}, {3})", pri_tracker_rect.X, pri_tracker_rect.Y, pri_tracker_rect.Width, pri_tracker_rect.Height);
}
g.DrawString(str.ToString(), font, myBrush, 0, 0);
}
//if (pri_obj_regions != null && pri_obj_regions.Count > 0)
//{
// foreach (Rectangle rect in pri_obj_regions)
// {
// g.DrawRectangle(pen, rect.X, rect.Y, rect.Width, rect.Height);
// }
//}
}
/// <summary>
/// 计算最近正样本距离系数，按照距离而不是相关系数，这样效率高，系数越小，检测对象越接近目标
/// </summary>
/// <param name="rect">检测目标区域</param>
/// <param name="bmp">整幅位图</param>
/// <returns>最近距离系数， double.MaxValue表示计算异常或没计算</returns>
public double MinDistance(RectangleF rect, Bitmap bmp)
{
double mindistance = double.MaxValue; // 返回值
double dist = double.MaxValue;
double minposdist = double.MaxValue;
double minnegdist = double.MaxValue;
if (rect == Rectangle.Empty)
{
return(mindistance);
}
DateTime dt = DateTime.Now;
double elapse = 0;
Bitmap patch = ImgOper.CutImage(bmp, (int)rect.X, (int)rect.Y, (int)rect.Width, (int)rect.Height);
patch = ImgOper.ResizeImage(patch, Parameter.DETECT_WINDOW_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height);
patch = ImgOper.Grayscale(patch);
int[,] patchgram = ImgOper.Integrogram(patch, 1);
byte[] patchdata = ImgOper.GetGraybmpData(patch);
double patchmean = (double)patchgram[patch.Height - 1, patch.Width - 1] / (double)(patch.Width * patch.Height);
double[] patchdatad = new double[patchdata.Length];
for (int i = 0; i < patchdata.Length; i++)
{
patchdatad[i] = patchdata[i] - patchmean;
}
foreach (ValuedBitmap posbmp in PosMapCollection)
{
int[,] posgram = ImgOper.Integrogram(posbmp.VBitmap, 1);
byte[] posdata = ImgOper.GetGraybmpData(posbmp.VBitmap);
double posmean = (double)posgram[posbmp.VBitmap.Height - 1, posbmp.VBitmap.Width - 1] / (double)(posbmp.VBitmap.Width * posbmp.VBitmap.Height);
double[] posdatad = new double[posdata.Length];
for (int i = 0; i < posdata.Length; i++)
{
posdatad[i] = posdata[i] - posmean;
}
dist = ImgStatCompute.ComputeDistance(patchdatad, posdatad);
if (dist < minposdist)
{
minposdist = dist;
}
}
foreach (ValuedBitmap negbmp in NegMapCollection)
{
int[,] neggram = ImgOper.Integrogram(negbmp.VBitmap, 1);
byte[] negdata = ImgOper.GetGraybmpData(negbmp.VBitmap);
double negmean = (double)neggram[negbmp.VBitmap.Height - 1, negbmp.VBitmap.Width - 1] / (double)(negbmp.VBitmap.Width * negbmp.VBitmap.Height);
double[] negdatad = new double[negdata.Length];
for (int i = 0; i < negdata.Length; i++)
{
negdatad[i] = negdata[i] - negmean;
}
dist = ImgStatCompute.ComputeDistance(patchdatad, negdatad);
if (dist < minnegdist)
{
minnegdist = dist;
}
}
if (minnegdist != 0 || minposdist != 0)
{
// 带归一化的系数，如果用minposdist/minnegdist，值可能会溢出
mindistance = minposdist / (minposdist + minnegdist);
}
elapse = DateTime.Now.Subtract(dt).TotalMilliseconds;
return(mindistance);
}
/// <summary>
/// 训练正样本
/// </summary>
/// <param name="bmp">正样本位图</param>
public void TrainPositive(Bitmap bmp)
{
Bitmap samplebmp = null;
double neg_distance = 0;
double pos_distance = 0;
bool hasinserted = false; // 指明样本是否已插入队列
samplebmp = ImgOper.ResizeImage(bmp, Parameter.DETECT_WINDOW_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height);
samplebmp = ImgOper.Grayscale(samplebmp);
for (double angle = (-1) * Parameter.ANGLE_BORDER; angle < Parameter.ANGLE_BORDER; angle += Parameter.ANGLE_INTERVAL)
{
Bitmap bmpclone = ImgOper.RotateImage(samplebmp, angle);
bmpclone = ImgOper.ResizeImage(bmpclone, Parameter.DETECT_WINDOW_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height);
for (double scale = (-1) * Parameter.SCALE_BORDER; scale < Parameter.SCALE_BORDER; scale += Parameter.SCALE_INTERVAL)
{
// 往两个方向去，所以是减号
IntPoint lt = new IntPoint((int)(bmpclone.Width * scale / 2), (int)(bmpclone.Height * scale / 2));
IntPoint rt = new IntPoint(bmpclone.Width - 1 - (int)(bmpclone.Width * scale / 2), (int)(bmpclone.Height * scale / 2));
IntPoint rb = new IntPoint(bmpclone.Width - 1 - (int)(bmpclone.Width * scale / 2), bmpclone.Height - 1 - (int)(bmpclone.Height * scale / 2));
IntPoint lb = new IntPoint((int)(bmpclone.Width * scale / 2), bmpclone.Height - 1 - (int)(bmpclone.Height * scale / 2));
Bitmap scalebmp = ImgOper.QuadrilateralTransform(bmpclone, lt, rt, rb, lb);
HogGram hogGram = HogGram.GetHogFromBitmap(scalebmp, Parameter.CELL_SIZE.Width, Parameter.CELL_SIZE.Height, Parameter.PART_NUMBER);
NormBlockVectorGram blockGram = new NormBlockVectorGram(hogGram, Parameter.BLOCK_SIZE.Width, Parameter.BLOCK_SIZE.Height);
Rectangle rect = new Rectangle(0, 0, hogGram.HogSize.Width, hogGram.HogSize.Height);
double[] vect = blockGram.GetHogWindowVec(rect);
if (Dimension != 0 && vect.Length != Dimension)
{
throw new Exception("输入正样本的尺寸与其他样本尺寸不一致！");
}
ValuedBitmap vbmp = null;
if (NegCenter != null && PosCenter != null)
{
// 计算离正负中心的距离
for (int i = 0; i < vect.Length; i++)
{
neg_distance += Math.Abs(vect[i] - NegCenter[i]);
pos_distance += Math.Abs(vect[i] - PosCenter[i]);
}
// 与负样本中心重合时，说明是负样本，不能插入正样本队列
if (neg_distance == 0)
{
return;
}
// 检测到的正样本加入样本队列的第二道关，如果不够接近正样本中心，就无法加入队列
// 按照Hog检测的判定条件，正距离乘以Parameter.POS_DIST_COEF，使其避开边界
if (neg_distance < pos_distance * Parameter.POS_DIST_COEF)
{
return;
}
// 带归一化的系数，如果用pos_distance/neg_distance，值可能会溢出;
// 将pos_distance / (pos_distance + neg_distance)作为正样本的评价系数，值越小越接近正样本
vbmp = new ValuedBitmap(scalebmp, pos_distance / (pos_distance + neg_distance));
}
else
{
// 如果正或负样本库还没建立起来，则Val暂时赋值为1
vbmp = new ValuedBitmap(scalebmp, 1);
}
// 检测到的正样本加入样本队列的第三道关，与正样本评价系数的有序队列比较后，决定是否加入样本队列
hasinserted = InsertValuedBitmap(ref PosMapCollection, vbmp, Parameter.POS_LIMITED_NUMBER);
PosLength = PosMapCollection.Count;
//// 人工观察正样本插入情况
//if (hasinserted && vbmp != null)
//{
// vbmp.VBitmap.Save("Image\\pos_save\\" + poscnt + "_" + vbmp.Val + ".jpg");
// poscnt++;
//}
// 如果样本已经插入队列，说明样本比较可信，重新计算样本中心
if (hasinserted)
{
if (PosCenter == null)
{
Dimension = vect.Length;
PosCenter = new double[Dimension];
}
for (int i = 0; i < Dimension; i++)
{
PosCenter[i] = (PosCenter[i] * PosLength + vect[i]) / (PosLength + 1);
}
}
}
}
}
/// <summary>
/// 计算最近正样本距离系数，按照距离而不是相关系数，这样效率高，系数越小，检测对象越接近目标
/// </summary>
/// <param name="rect">检测目标区域</param>
/// <param name="bmp">位图</param>
/// <returns>最近距离系数， double.MaxValue表示计算异常或没计算</returns>
private double NearestNeighbour(Rectangle rect, Bitmap bmp)
{
Bitmap sample = null;
Bitmap detect = null;
Rectangle gramRect = Rectangle.Empty;
HogGram sampleHGram = null;
HogGram detectHGram = null;
NormBlockVectorGram sampleBlock = null;
NormBlockVectorGram detectBlock = null;
double[] detectvect = null;
double[] samplevect = null;
ArrayList posvects = null;
ArrayList negvects = null;
double minposdist = double.MaxValue;
double minnegdist = double.MaxValue;
double dist = 0;
double nearestdist = double.MaxValue;
if (PosLength == 0 || NegLength == 0)
{
return(nearestdist);
}
// 正样本载入
posvects = new ArrayList();
for (int i = 0; i < PosLength; i++)
{
sample = PosMapCollection[i].VBitmap;
sample = ImgOper.ResizeImage(sample, Parameter.DETECT_WINDOW_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height);
sample = ImgOper.Grayscale(sample);
sampleHGram = HogGram.GetHogFromBitmap(sample, Parameter.CELL_SIZE.Width, Parameter.CELL_SIZE.Height, Parameter.PART_NUMBER);
sampleBlock = new NormBlockVectorGram(sampleHGram, Parameter.BLOCK_SIZE.Width, Parameter.BLOCK_SIZE.Height);
gramRect = new Rectangle(0, 0, sampleHGram.HogSize.Width, sampleHGram.HogSize.Height);
samplevect = sampleBlock.GetHogWindowVec(gramRect);
posvects.Add(samplevect);
}
// 负样本载入
negvects = new ArrayList();
for (int i = 0; i < NegLength; i++)
{
sample = NegMapCollection[i].VBitmap;
sample = ImgOper.ResizeImage(sample, Parameter.DETECT_WINDOW_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height);
sample = ImgOper.Grayscale(sample);
sampleHGram = HogGram.GetHogFromBitmap(sample, Parameter.CELL_SIZE.Width, Parameter.CELL_SIZE.Height, Parameter.PART_NUMBER);
sampleBlock = new NormBlockVectorGram(sampleHGram, Parameter.BLOCK_SIZE.Width, Parameter.BLOCK_SIZE.Height);
gramRect = new Rectangle(0, 0, sampleHGram.HogSize.Width, sampleHGram.HogSize.Height);
samplevect = sampleBlock.GetHogWindowVec(gramRect);
negvects.Add(samplevect);
}
detect = ImgOper.CutImage(bmp, rect.X, rect.Y, rect.Width, rect.Height);
detect = ImgOper.ResizeImage(detect, Parameter.DETECT_WINDOW_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height);
detect = ImgOper.Grayscale(detect);
detectHGram = HogGram.GetHogFromBitmap(detect, Parameter.CELL_SIZE.Width, Parameter.CELL_SIZE.Height, Parameter.PART_NUMBER);
detectBlock = new NormBlockVectorGram(detectHGram, Parameter.BLOCK_SIZE.Width, Parameter.BLOCK_SIZE.Height);
gramRect = new Rectangle(0, 0, detectHGram.HogSize.Width, detectHGram.HogSize.Height);
detectvect = detectBlock.GetHogWindowVec(gramRect);
foreach (double[] svect in posvects)
{
dist = ImgStatCompute.ComputeDistance(detectvect, svect);
if (dist < minposdist)
{
minposdist = dist;
}
}
foreach (double[] svect in negvects)
{
dist = ImgStatCompute.ComputeDistance(detectvect, svect);
if (dist < minnegdist)
{
minnegdist = dist;
}
}
if (minnegdist != 0 || minposdist != 0)
{
nearestdist = minposdist / (minposdist + minnegdist);
}
return(nearestdist);
}
/// <summary>
/// Hog检测, 被检测到图像自动缩放到BMPLIMITSIZE容忍范围内，并在检测完后将检测框自动放大之前缩小的倍率
/// </summary>
/// <param name="bmp">位图</param>
public RectangleCollection HogDetect(Bitmap bmp)
{
RectangleCollection resultCollection = null;
if (bmp == null)
{
return(null);
}
if (NegCenter == null && PosCenter == null)
{
return(null);
}
DateTime dt = DateTime.Now;
double elapse = 0;
// 针对原图的缩放倍率
double se = 1;
if (bmp.Width > Parameter.BMPLIMITSIZE.Width || bmp.Height > Parameter.BMPLIMITSIZE.Height)
{
se = bmp.Width / (double)Parameter.BMPLIMITSIZE.Width > bmp.Height / (double)Parameter.BMPLIMITSIZE.Height ?
bmp.Width / (double)Parameter.BMPLIMITSIZE.Width : bmp.Height / (double)Parameter.BMPLIMITSIZE.Height;
bmp = ImgOper.ResizeImage(bmp, (int)(bmp.Width / se), (int)(bmp.Height / se));
}
bmp = ImgOper.Grayscale(bmp);
//bmp = ImgOper.GaussianConvolution(bmp, GAUSSIAN_SIGMA, GAUSSIAN_SIZE); // 高斯卷积，使得图像平滑
// 所有层的检测结果
ArrayList resultlayers = new ArrayList();
// 初始缩放因子
double scalecoef = 1.0;
Bitmap scalebmp = null;
int newwidth = (int)(bmp.Width / scalecoef);
int newheight = (int)(bmp.Height / scalecoef);
// 每层最小距离点的集合
ArrayList idx_layermindistance = new ArrayList();
int cnt = 0;
do
{
scalebmp = ImgOper.ResizeImage(bmp, newwidth, newheight);
HogGram hogGram = HogGram.GetHogFromBitmap(scalebmp, Parameter.CELL_SIZE.Width, Parameter.CELL_SIZE.Height, Parameter.PART_NUMBER);
NormBlockVectorGram blockGram = new NormBlockVectorGram(hogGram, Parameter.BLOCK_SIZE.Width, Parameter.BLOCK_SIZE.Height);
DetectResultLayer detectlayer = new DetectResultLayer();
// !!!!!!检测窗口的像素尺寸必须能被cell尺寸整除!!!!!!像素尺寸除以hog尺寸就是检测窗口的尺寸
detectlayer.DetectResult = blockGram.DetectImgByHogWindow(
new Size(Parameter.DETECT_WINDOW_SIZE.Width / Parameter.CELL_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height / Parameter.CELL_SIZE.Height),
NegCenter, PosCenter, Parameter.POS_DIST_COEF);
if (detectlayer.DetectResult == null)
{
return(null);
}
detectlayer.ScaleCoef = scalecoef;
resultlayers.Add(detectlayer); // 本层检测结果加入队列
scalecoef *= Parameter.SCALE_COEF; // 逐次缩小图像
newwidth = (int)(bmp.Width / scalecoef);
newheight = (int)(bmp.Height / scalecoef);
cnt++;
} while (newwidth > 2 * Parameter.DETECT_WINDOW_SIZE.Width && newheight > 2 * Parameter.DETECT_WINDOW_SIZE.Height);
elapse = DateTime.Now.Subtract(dt).TotalSeconds;
// 框出所有可能的物体
WindowResult[] wr = null;
Rectangle rect;
double mindist = -1;
WindowResult min_obj = null;
double min_scalecoef = 1;
resultCollection = new RectangleCollection();
foreach (DetectResultLayer layer in resultlayers)
{
wr = layer.DetectResult;
for (int i = 0; i < wr.Length; i++)
{
if (wr[i].label == 1)
{
if (mindist == -1 || mindist > wr[i].PosDistance)
{
mindist = wr[i].PosDistance;
min_obj = wr[i];
min_scalecoef = layer.ScaleCoef;
}
rect = new Rectangle((int)(wr[i].ImageRegion.X * layer.ScaleCoef * se),
(int)(wr[i].ImageRegion.Y * layer.ScaleCoef * se),
(int)(wr[i].ImageRegion.Width * layer.ScaleCoef * se),
(int)(wr[i].ImageRegion.Height * layer.ScaleCoef * se));
resultCollection.Add(rect);
}
}
}
//rect = new Rectangle((int)(min_obj.ImageRegion.X * min_scalecoef * se),
// (int)(min_obj.ImageRegion.Y * min_scalecoef * se),
// (int)(min_obj.ImageRegion.Width * min_scalecoef * se),
// (int)(min_obj.ImageRegion.Height * min_scalecoef * se));
//resultCollection.Add(rect);
return(resultCollection);
}
/// <summary>
/// 训练负样本
/// </summary>
/// <param name="bmp">负样本位图</param>
public void TrainNegative(Bitmap bmp)
{
Bitmap samplebmp = null;
double neg_distance = 0;
double pos_distance = 0;
bool hasinserted = false; // 指明样本是否已插入队列
if (bmp.Width / Parameter.DETECT_WINDOW_SIZE.Width > bmp.Height / Parameter.DETECT_WINDOW_SIZE.Height)
{
samplebmp = ImgOper.ResizeImage(bmp,
(int)(bmp.Width * Parameter.DETECT_WINDOW_SIZE.Height / bmp.Height), Parameter.DETECT_WINDOW_SIZE.Height);
}
else
{
samplebmp = ImgOper.ResizeImage(bmp, Parameter.DETECT_WINDOW_SIZE.Width,
(int)(bmp.Height * Parameter.DETECT_WINDOW_SIZE.Width / bmp.Width));
}
samplebmp = ImgOper.CutImage(samplebmp, 0, 0, Parameter.DETECT_WINDOW_SIZE.Width, Parameter.DETECT_WINDOW_SIZE.Height);
samplebmp = ImgOper.Grayscale(samplebmp);
HogGram hogGram = HogGram.GetHogFromBitmap(samplebmp, Parameter.CELL_SIZE.Width, Parameter.CELL_SIZE.Height, Parameter.PART_NUMBER);
NormBlockVectorGram blockGram = new NormBlockVectorGram(hogGram, Parameter.BLOCK_SIZE.Width, Parameter.BLOCK_SIZE.Height);
Rectangle rect = new Rectangle(0, 0, hogGram.HogSize.Width, hogGram.HogSize.Height);
double[] vect = blockGram.GetHogWindowVec(rect);
if (Dimension != 0 && vect.Length != Dimension)
{
throw new Exception("输入负样本的尺寸与其他样本尺寸不一致！");
}
ValuedBitmap vbmp = null;
if (PosCenter != null && NegCenter != null)
{
// 计算离正负中心的距离
for (int i = 0; i < vect.Length; i++)
{
neg_distance += Math.Abs(vect[i] - NegCenter[i]);
pos_distance += Math.Abs(vect[i] - PosCenter[i]);
}
// 与正样本中心重合时，说明是正样本，不能插入负样本队列
if (pos_distance == 0)
{
return;
}
// 负样本加入样本队列的第二道关，如果不够接近负样本中心，就无法加入队列
// 按照Hog检测的判定条件，正距离乘以Parameter.POS_DIST_COEF，使其避开边界
if (pos_distance * Parameter.POS_DIST_COEF < neg_distance)
{
return;
}
// 带归一化的系数，如果用neg_distance / pos_distance，值可能会溢出;
// 将neg_distance / (pos_distance + neg_distance)作为负样本的评价系数，值越小越接近负样本
vbmp = new ValuedBitmap(samplebmp, neg_distance / (pos_distance + neg_distance));
}
else
{
// 如果正样本库还没建立起来，则Val暂时赋值为1
vbmp = new ValuedBitmap(samplebmp, 1);
}
// 负样本加入样本队列的第三道关，与负样本评价系数的有序队列比较后，决定是否加入样本队列
hasinserted = InsertValuedBitmap(ref NegMapCollection, vbmp, Parameter.NEG_LIMITED_NUMBER);
NegLength = NegMapCollection.Count;
//// 人工观察负样本插入情况
//if (hasinserted && vbmp != null)
//{
// vbmp.VBitmap.Save("Image\\neg_save\\" + negcnt + "_" + vbmp.Val + ".jpg");
// negcnt++;
//}
// 如果样本已经插入队列，说明样本比较可信，重新计算样本中心
if (hasinserted)
{
if (NegCenter == null)
{
Dimension = vect.Length;
NegCenter = new double[Dimension];
}
for (int i = 0; i < Dimension; i++)
{
NegCenter[i] = (NegCenter[i] * NegLength + vect[i]) / (NegLength + 1);
}
}
}