train _cascade 源码阅读之HOG特征
2016-05-09 11:00
501 查看
本文讨论OpenCV train_cascade 级联分类器中的HOG特征实现，HOG特征原理可以参考此文。特征的初始化框架和LBP
特征是一致的，感兴趣可以参考
train_cascade 源码阅读之LBP 特征中的介绍。HOG，即Histogram
of Oriented Gradient 方向梯度直方图，常用于解决人体目标的检测的图像描述子，用来表达人体，提取人体外形信息和运动信息形成丰富的特征集。
生成过程： 检测窗口--> 归一化图像--> 计算梯度-->对每一个cell块对梯度直方图进行规定权重的投影 --> 对每个重叠block块内的cell进行对比度归一化 --> 把所有block内的直方图向量一起组合成一个大的HOG特征向量。（参考自 blog.sina.com.cn/s/blog_60e6e3d50101bkpn.html）
在HOG特征的操作中，与前述的Haar特征与LBP特征不同的是，初始时矩阵不再是单一的一个sum，而是一个矩阵向量hist，其中含有9个类似sum一样的矩阵，分别存放每一个方向的结果。
[cpp] view
plain copy
class CvHOGEvaluator : public CvFeatureEvaluator
{
public:
……
virtual void setImage(const cv::Mat& img, uchar clsLabel, int idx);
virtual float operator()(
int varIdx,
int sampleIdx) const;
……
protected:
virtual void generateFeatures();
virtual void integralHistogram(
const cv::Mat &img,
std::vector<cv::Mat> &histogram,
cv::Mat &norm,
int nbins) const;
class Feature
{
public:
Feature();
Feature( int offset, int x, int y, int cellW, int cellH );
float calc(
const std::vector<cv::Mat> &_hists,
const cv::Mat &_normSum, size_t y,
int featComponent ) const;
void write( cv::FileStorage &fs ) const;
void write( cv::FileStorage &fs, int varIdx ) const;
cv::Rect rect[N_CELLS]; //cells
struct
{
int p0, p1, p2, p3;
} fastRect[N_CELLS];
};
std::vector<Feature> features;
cv::Mat normSum; //for nomalization calculation (L1 or L2)
std::vector<cv::Mat> hist;
};
接下来是初始化积分图操作下标的过程。
[cpp] view
plain copy
void CvHOGEvaluator::generateFeatures()
{
int offset = winSize.width + 1;
Size blockStep;
int x, y, t, w, h;
for (t = 8; t <= winSize.width/2; t+=8)
//t = size of a cell. blocksize = 4*cellSize
{
blockStep = Size(4,4);
w = 2*t; //width of a block
h = 2*t; //height of a block
for (x = 0; x <= winSize.width - w; x += blockStep.width)
{
for (y = 0; y <= winSize.height - h; y += blockStep.height)
{
features.push_back(Feature(offset, x, y, t, t));
}
}
w = 2*t;
h = 4*t;
for (x = 0; x <= winSize.width - w; x += blockStep.width)
{
for (y = 0; y <= winSize.height - h; y += blockStep.height)
{
features.push_back(Feature(offset, x, y, t, 2*t));
}
}
w = 4*t;
h = 2*t;
for (x = 0; x <= winSize.width - w; x += blockStep.width)
{
for (y = 0; y <= winSize.height - h; y += blockStep.height)
{
features.push_back(Feature(offset, x, y, 2*t, t));
}
}
}
numFeatures = (int)features.size();
}
t表示cell的尺寸，一个block含有2×2个cell，因此，t需要不大于winSize.width/2，在这里采用了三种不同的形状，block遍历的step是4×4的。输入给Feature的构造参数是偏移量，左上角坐标点，和cell的宽高。
接下来看Feature的构造。
[cpp] view
plain copy
CvHOGEvaluator::Feature::Feature( int offset, int x, int y, int cellW, int cellH )
{
rect[0] = Rect(x, y, cellW, cellH); //cell0
rect[1] = Rect(x+cellW, y, cellW, cellH); //cell1
rect[2] = Rect(x, y+cellH, cellW, cellH); //cell2
rect[3] = Rect(x+cellW, y+cellH, cellW, cellH); //cell3
for (int i = 0; i < N_CELLS; i++)
{
CV_SUM_OFFSETS(fastRect[i].p0, fastRect[i].p1, fastRect[i].p2, fastRect[i].p3, rect[i], offset);
}
}
分别创建了四个cell矩形，CV_SUM_OFFSET宏计算的是矩形上的点在拉成行向量的积分图中的偏移量。
积分图中的坐标算好了，再看积分图的生成过程。
[cpp] view
plain copy
void CvHOGEvaluator::
setImage(const Mat &img, uchar clsLabel, int idx)
{
CV_DbgAssert( !hist.empty());
CvFeatureEvaluator::setImage( img, clsLabel, idx );
vector<Mat> integralHist;
for (int bin = 0; bin < N_BINS; bin++)
{
integralHist.push_back(
Mat(winSize.height + 1,
winSize.width + 1,
hist[bin].type(),
hist[bin].ptr<float>((int)idx)) );
}
Mat integralNorm(
winSize.height + 1,
winSize.width + 1,
normSum.type(),
normSum.ptr<float>((int)idx));
integralHistogram(img, integralHist, integralNorm, (int)N_BINS);
}
与LBP，Haar相同，新建Mat，传入积分图的数据地址，不同的是这里是矩阵向量，保存9个方向的积分图。这里没有使用OpenCV自带的integral直接计算积分图，而是自行实现了一个。
[cpp] view
plain copy
void CvHOGEvaluator::integralHistogram(
const Mat &img,
vector<Mat> &histogram,
Mat &norm,
int nbins) const
{
CV_Assert( img.type() == CV_8U || img.type() == CV_8UC3 );
int x, y, binIdx;
Size gradSize(img.size());
Size histSize(histogram[0].size());
Mat grad(gradSize, CV_32F);
Mat qangle(gradSize, CV_8U);
AutoBuffer<int> mapbuf(gradSize.width + gradSize.height + 4);
int* xmap = (int*)mapbuf + 1;
int* ymap = xmap + gradSize.width + 2;
const int borderType = (int)BORDER_REPLICATE;
for( x = -1; x < gradSize.width + 1; x++ )
xmap[x] = borderInterpolate(x, gradSize.width, borderType);
for( y = -1; y < gradSize.height + 1; y++ )
ymap[y] = borderInterpolate(y, gradSize.height, borderType);
int width = gradSize.width;
AutoBuffer<float> _dbuf(width*4);
float* dbuf = _dbuf;
Mat Dx(1, width, CV_32F, dbuf);
Mat Dy(1, width, CV_32F, dbuf + width);
Mat Mag(1, width, CV_32F, dbuf + width*2);
Mat Angle(1, width, CV_32F, dbuf + width*3);
float angleScale = (float)(nbins/CV_PI);
for( y = 0; y < gradSize.height; y++ )
{
const uchar* currPtr = img.data + img.step*ymap[y];
const uchar* prevPtr = img.data + img.step*ymap[y-1];
const uchar* nextPtr = img.data + img.step*ymap[y+1];
float* gradPtr = (float*)grad.ptr(y);
uchar* qanglePtr = (uchar*)qangle.ptr(y);
for( x = 0; x < width; x++ )
{
dbuf[x] = (float)(currPtr[xmap[x+1]] - currPtr[xmap[x-1]]);
dbuf[width + x] = (float)(nextPtr[xmap[x]] - prevPtr[xmap[x]]);
}
cartToPolar( Dx, Dy, Mag, Angle, false );
for( x = 0; x < width; x++ )
{
float mag = dbuf[x+width*2];
float angle = dbuf[x+width*3];
angle = angle*angleScale - 0.5f;
int bidx = cvFloor(angle);
angle -= bidx;
if( bidx < 0 )
bidx += nbins;
else if( bidx >= nbins )
bidx -= nbins;
qanglePtr[x] = (uchar)bidx;
gradPtr[x] = mag;
}
}
integral(grad, norm, grad.depth());
float* histBuf;
const float* magBuf;
const uchar* binsBuf;
int binsStep = (int)( qangle.step / sizeof(uchar) );
int histStep = (int)( histogram[0].step / sizeof(float) );
int magStep = (int)( grad.step / sizeof(float) );
for( binIdx = 0; binIdx < nbins; binIdx++ )
{
histBuf = (float*)histogram[binIdx].data;
magBuf = (const float*)grad.data;
binsBuf = (const uchar*)qangle.data;
memset( histBuf, 0, histSize.width * sizeof(histBuf[0]) );
histBuf += histStep + 1;
for( y = 0; y < qangle.rows; y++ )
{
histBuf[-1] = 0.f;
float strSum = 0.f;
for( x = 0; x < qangle.cols; x++ )
{
if( binsBuf[x] == binIdx )
strSum += magBuf[x];
histBuf[x] = histBuf[-histStep + x] + strSum;
}
histBuf += histStep;
binsBuf += binsStep;
magBuf += magStep;
}
}
}
看完了代码才知道，以前对HOG特征的理解是有偏差的，尤其是在梯度的计算上，犯了严重的想当然的错误。特征计算完成后，调用integral计算平方积分图，再根据角度，将幅值放到每个积分直方图中。
最后通过如下方式调用计算HOG特征，并进行归一化。
[cpp] view
plain copy
inline float CvHOGEvaluator::Feature::calc(
const std::vector<cv::Mat>& _hists,
const cv::Mat& _normSum, size_t y,
int featComponent ) const
{
float normFactor;
float res;
int binIdx = featComponent % N_BINS;
int cellIdx = featComponent / N_BINS;
const float *phist = _hists[binIdx].ptr<float>((int)y);
res = phist[fastRect[cellIdx].p0]
- phist[fastRect[cellIdx].p1]
- phist[fastRect[cellIdx].p2]
+ phist[fastRect[cellIdx].p3];
const float *pnormSum = _normSum.ptr<float>((int)y);
normFactor = (float)(pnormSum[fastRect[0].p0]
- pnormSum[fastRect[1].p1]
- pnormSum[fastRect[2].p2]
+ pnormSum[fastRect[3].p3]);
res = (res > 0.001f) ? ( res / (normFactor + 0.001f) ) : 0.f;
//for cutting negative values, which apper due to floating precision
return res;
}
特征是一致的，感兴趣可以参考
train_cascade 源码阅读之LBP 特征中的介绍。HOG，即Histogram
of Oriented Gradient 方向梯度直方图，常用于解决人体目标的检测的图像描述子，用来表达人体，提取人体外形信息和运动信息形成丰富的特征集。
生成过程： 检测窗口--> 归一化图像--> 计算梯度-->对每一个cell块对梯度直方图进行规定权重的投影 --> 对每个重叠block块内的cell进行对比度归一化 --> 把所有block内的直方图向量一起组合成一个大的HOG特征向量。（参考自 blog.sina.com.cn/s/blog_60e6e3d50101bkpn.html）
在HOG特征的操作中，与前述的Haar特征与LBP特征不同的是，初始时矩阵不再是单一的一个sum，而是一个矩阵向量hist，其中含有9个类似sum一样的矩阵，分别存放每一个方向的结果。
[cpp] view
plain copy
class CvHOGEvaluator : public CvFeatureEvaluator
{
public:
……
virtual void setImage(const cv::Mat& img, uchar clsLabel, int idx);
virtual float operator()(
int varIdx,
int sampleIdx) const;
……
protected:
virtual void generateFeatures();
virtual void integralHistogram(
const cv::Mat &img,
std::vector<cv::Mat> &histogram,
cv::Mat &norm,
int nbins) const;
class Feature
{
public:
Feature();
Feature( int offset, int x, int y, int cellW, int cellH );
float calc(
const std::vector<cv::Mat> &_hists,
const cv::Mat &_normSum, size_t y,
int featComponent ) const;
void write( cv::FileStorage &fs ) const;
void write( cv::FileStorage &fs, int varIdx ) const;
cv::Rect rect[N_CELLS]; //cells
struct
{
int p0, p1, p2, p3;
} fastRect[N_CELLS];
};
std::vector<Feature> features;
cv::Mat normSum; //for nomalization calculation (L1 or L2)
std::vector<cv::Mat> hist;
};
接下来是初始化积分图操作下标的过程。
[cpp] view
plain copy
void CvHOGEvaluator::generateFeatures()
{
int offset = winSize.width + 1;
Size blockStep;
int x, y, t, w, h;
for (t = 8; t <= winSize.width/2; t+=8)
//t = size of a cell. blocksize = 4*cellSize
{
blockStep = Size(4,4);
w = 2*t; //width of a block
h = 2*t; //height of a block
for (x = 0; x <= winSize.width - w; x += blockStep.width)
{
for (y = 0; y <= winSize.height - h; y += blockStep.height)
{
features.push_back(Feature(offset, x, y, t, t));
}
}
w = 2*t;
h = 4*t;
for (x = 0; x <= winSize.width - w; x += blockStep.width)
{
for (y = 0; y <= winSize.height - h; y += blockStep.height)
{
features.push_back(Feature(offset, x, y, t, 2*t));
}
}
w = 4*t;
h = 2*t;
for (x = 0; x <= winSize.width - w; x += blockStep.width)
{
for (y = 0; y <= winSize.height - h; y += blockStep.height)
{
features.push_back(Feature(offset, x, y, 2*t, t));
}
}
}
numFeatures = (int)features.size();
}
t表示cell的尺寸，一个block含有2×2个cell，因此，t需要不大于winSize.width/2，在这里采用了三种不同的形状，block遍历的step是4×4的。输入给Feature的构造参数是偏移量，左上角坐标点，和cell的宽高。
接下来看Feature的构造。
[cpp] view
plain copy
CvHOGEvaluator::Feature::Feature( int offset, int x, int y, int cellW, int cellH )
{
rect[0] = Rect(x, y, cellW, cellH); //cell0
rect[1] = Rect(x+cellW, y, cellW, cellH); //cell1
rect[2] = Rect(x, y+cellH, cellW, cellH); //cell2
rect[3] = Rect(x+cellW, y+cellH, cellW, cellH); //cell3
for (int i = 0; i < N_CELLS; i++)
{
CV_SUM_OFFSETS(fastRect[i].p0, fastRect[i].p1, fastRect[i].p2, fastRect[i].p3, rect[i], offset);
}
}
分别创建了四个cell矩形，CV_SUM_OFFSET宏计算的是矩形上的点在拉成行向量的积分图中的偏移量。
积分图中的坐标算好了，再看积分图的生成过程。
[cpp] view
plain copy
void CvHOGEvaluator::
setImage(const Mat &img, uchar clsLabel, int idx)
{
CV_DbgAssert( !hist.empty());
CvFeatureEvaluator::setImage( img, clsLabel, idx );
vector<Mat> integralHist;
for (int bin = 0; bin < N_BINS; bin++)
{
integralHist.push_back(
Mat(winSize.height + 1,
winSize.width + 1,
hist[bin].type(),
hist[bin].ptr<float>((int)idx)) );
}
Mat integralNorm(
winSize.height + 1,
winSize.width + 1,
normSum.type(),
normSum.ptr<float>((int)idx));
integralHistogram(img, integralHist, integralNorm, (int)N_BINS);
}
与LBP，Haar相同，新建Mat，传入积分图的数据地址，不同的是这里是矩阵向量，保存9个方向的积分图。这里没有使用OpenCV自带的integral直接计算积分图，而是自行实现了一个。
[cpp] view
plain copy
void CvHOGEvaluator::integralHistogram(
const Mat &img,
vector<Mat> &histogram,
Mat &norm,
int nbins) const
{
CV_Assert( img.type() == CV_8U || img.type() == CV_8UC3 );
int x, y, binIdx;
Size gradSize(img.size());
Size histSize(histogram[0].size());
Mat grad(gradSize, CV_32F);
Mat qangle(gradSize, CV_8U);
AutoBuffer<int> mapbuf(gradSize.width + gradSize.height + 4);
int* xmap = (int*)mapbuf + 1;
int* ymap = xmap + gradSize.width + 2;
const int borderType = (int)BORDER_REPLICATE;
for( x = -1; x < gradSize.width + 1; x++ )
xmap[x] = borderInterpolate(x, gradSize.width, borderType);
for( y = -1; y < gradSize.height + 1; y++ )
ymap[y] = borderInterpolate(y, gradSize.height, borderType);
int width = gradSize.width;
AutoBuffer<float> _dbuf(width*4);
float* dbuf = _dbuf;
Mat Dx(1, width, CV_32F, dbuf);
Mat Dy(1, width, CV_32F, dbuf + width);
Mat Mag(1, width, CV_32F, dbuf + width*2);
Mat Angle(1, width, CV_32F, dbuf + width*3);
float angleScale = (float)(nbins/CV_PI);
for( y = 0; y < gradSize.height; y++ )
{
const uchar* currPtr = img.data + img.step*ymap[y];
const uchar* prevPtr = img.data + img.step*ymap[y-1];
const uchar* nextPtr = img.data + img.step*ymap[y+1];
float* gradPtr = (float*)grad.ptr(y);
uchar* qanglePtr = (uchar*)qangle.ptr(y);
for( x = 0; x < width; x++ )
{
dbuf[x] = (float)(currPtr[xmap[x+1]] - currPtr[xmap[x-1]]);
dbuf[width + x] = (float)(nextPtr[xmap[x]] - prevPtr[xmap[x]]);
}
cartToPolar( Dx, Dy, Mag, Angle, false );
for( x = 0; x < width; x++ )
{
float mag = dbuf[x+width*2];
float angle = dbuf[x+width*3];
angle = angle*angleScale - 0.5f;
int bidx = cvFloor(angle);
angle -= bidx;
if( bidx < 0 )
bidx += nbins;
else if( bidx >= nbins )
bidx -= nbins;
qanglePtr[x] = (uchar)bidx;
gradPtr[x] = mag;
}
}
integral(grad, norm, grad.depth());
float* histBuf;
const float* magBuf;
const uchar* binsBuf;
int binsStep = (int)( qangle.step / sizeof(uchar) );
int histStep = (int)( histogram[0].step / sizeof(float) );
int magStep = (int)( grad.step / sizeof(float) );
for( binIdx = 0; binIdx < nbins; binIdx++ )
{
histBuf = (float*)histogram[binIdx].data;
magBuf = (const float*)grad.data;
binsBuf = (const uchar*)qangle.data;
memset( histBuf, 0, histSize.width * sizeof(histBuf[0]) );
histBuf += histStep + 1;
for( y = 0; y < qangle.rows; y++ )
{
histBuf[-1] = 0.f;
float strSum = 0.f;
for( x = 0; x < qangle.cols; x++ )
{
if( binsBuf[x] == binIdx )
strSum += magBuf[x];
histBuf[x] = histBuf[-histStep + x] + strSum;
}
histBuf += histStep;
binsBuf += binsStep;
magBuf += magStep;
}
}
}
看完了代码才知道，以前对HOG特征的理解是有偏差的，尤其是在梯度的计算上，犯了严重的想当然的错误。特征计算完成后，调用integral计算平方积分图，再根据角度，将幅值放到每个积分直方图中。
最后通过如下方式调用计算HOG特征，并进行归一化。
[cpp] view
plain copy
inline float CvHOGEvaluator::Feature::calc(
const std::vector<cv::Mat>& _hists,
const cv::Mat& _normSum, size_t y,
int featComponent ) const
{
float normFactor;
float res;
int binIdx = featComponent % N_BINS;
int cellIdx = featComponent / N_BINS;
const float *phist = _hists[binIdx].ptr<float>((int)y);
res = phist[fastRect[cellIdx].p0]
- phist[fastRect[cellIdx].p1]
- phist[fastRect[cellIdx].p2]
+ phist[fastRect[cellIdx].p3];
const float *pnormSum = _normSum.ptr<float>((int)y);
normFactor = (float)(pnormSum[fastRect[0].p0]
- pnormSum[fastRect[1].p1]
- pnormSum[fastRect[2].p2]
+ pnormSum[fastRect[3].p3]);
res = (res > 0.001f) ? ( res / (normFactor + 0.001f) ) : 0.f;
//for cutting negative values, which apper due to floating precision
return res;
}
内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 
相关文章推荐
- train_cascade 源码阅读之LBP特征
- train_cascade 源码阅读之Haar特征
- 经验：人工智能威力初显，想养一只阿尔法狗帮我画图
- Entity Framework插入数据报错：Validation failed for one or more entities
- -XX:+PrintGCDetails 打印GC详细信息
- CDISC SDTM SU domain 学习笔记
- Ex2010-02 How to Reconnect a Disconnected Mailbox in 2010
- 11. Container With Most Wate
- Contains Duplicate
- juce中的BailOutChecker
- hdu3446 daizhenyang's chess 【一般图匹配】
- 利用Gensim训练关于英文维基百科的Word2Vec模型（Training Word2Vec Model on English Wikipedia by Gensim）
- Andorid总结 - AIDL
- shiro中的filterChainDefinitions
- 442 - Matrix Chain Multiplication
- HDU 3420 Bus Fair（贪心）
- 【LeetCode】Factorial Trailing Zeroes 解题报告
- haartraining生成.xml文件过程
- haartraining前将统一图片尺寸方法
- 514 - Rails