HOG特征可视化
版权声明：本文为博主原创文章，转载请注明出处。 https://cloud.tencent.com/developer/article/1435170
可视化说明
在之前博客HOG原理及OpenCV实现中，我们解释了HOG算法的原理。最终提取到的特征就是一串向量，其实我们并不知道它具体是什么样子，也不知道它到底是不是能体现目标区域与非目标区域的差异。为了解决这个问题，我们需要对HOG特征做可视化处理。
HOG特征首先去计算每个像素的梯度，然后建立滑动窗口，在滑动窗中建立滑动块，在块中建立等分的单元（cell）。我们仔细思考下这个过程，一个块在滑动时，每次包含的单元是不同的，但是对于一个单元而言，它是不随块滑动而改变的。这就意味着，如果块尺寸，块步长，单元尺寸确定了，一个窗口中的单元数目与它们中分别包含的像素就确定了。HOG的可视化就是利用这一点，它可视化的东西就是一个单元内的bin投票结果。
为了让下面的过程变得更直观，我们将整个图像作为一个检测窗来使用，也就是说不存在滑动窗的概念。
特别要注意，这应该是HOG最容易产生异常的地方。下面的图片本来是个900×600900×600900\times600的尺寸，但是我对它做了缩放，调整成904×600904×600904\times600。这是为了让904的范围内可以滑出整数个块，因为此时HOG在使用默认参数，即块尺寸16×1616×1616\times16，块步长8×88×88\times8。
900−168=110.5900−168=110.5
\frac{900-16}{8}=110.5
904−168=111904−168=111
\frac{904-16}{8}=111
代码实现
#include <iostream>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/opencv.hpp>
using namespace cv;
using namespace std;
// HOGDescriptor visual_imagealizer
// adapted for arbitrary size of feature sets and training images
Mat get_hogdescriptor_visual_image(Mat& origImg,
vector<float>& descriptorValues,
Size winSize,
Size cellSize,
int scaleFactor,
double viz_factor)
{
Mat visual_image;
resize(origImg, visual_image, Size(origImg.cols*scaleFactor, origImg.rows*scaleFactor));
int gradientBinSize = 9;
// dividing 180° into 9 bins, how large (in rad) is one bin?
float radRangeForOneBin = 3.14/(float)gradientBinSize;
// prepare data structure: 9 orientation / gradient strenghts for each cell
int cells_in_x_dir = winSize.width / cellSize.width;
int cells_in_y_dir = winSize.height / cellSize.height;
int totalnrofcells = cells_in_x_dir * cells_in_y_dir;
float*** gradientStrengths = new float**[cells_in_y_dir];
int** cellUpdateCounter = new int*[cells_in_y_dir];
for (int y=0; y<cells_in_y_dir; y++)
{
gradientStrengths[y] = new float*[cells_in_x_dir];
cellUpdateCounter[y] = new int[cells_in_x_dir];
for (int x=0; x<cells_in_x_dir; x++)
{
gradientStrengths[y][x] = new float[gradientBinSize];
cellUpdateCounter[y][x] = 0;
for (int bin=0; bin<gradientBinSize; bin++)
gradientStrengths[y][x][bin] = 0.0;
}
}
// nr of blocks = nr of cells - 1
// since there is a new block on each cell (overlapping blocks!) but the last one
int blocks_in_x_dir = cells_in_x_dir - 1;
int blocks_in_y_dir = cells_in_y_dir - 1;
// compute gradient strengths per cell
int descriptorDataIdx = 0;
int cellx = 0;
int celly = 0;
for (int blockx=0; blockx<blocks_in_x_dir; blockx++)
{
for (int blocky=0; blocky<blocks_in_y_dir; blocky++)
{
// 4 cells per block ...
for (int cellNr=0; cellNr<4; cellNr++)
{
// compute corresponding cell nr
int cellx = blockx;
int celly = blocky;
if (cellNr==1) celly++;
if (cellNr==2) cellx++;
if (cellNr==3)
{
cellx++;
celly++;
}
for (int bin=0; bin<gradientBinSize; bin++)
{
float gradientStrength = descriptorValues[ descriptorDataIdx ];
descriptorDataIdx++;
gradientStrengths[celly][cellx][bin] += gradientStrength;
} // for (all bins)
// note: overlapping blocks lead to multiple updates of this sum!
// we therefore keep track how often a cell was updated,
// to compute average gradient strengths
cellUpdateCounter[celly][cellx]++;
} // for (all cells)
} // for (all block x pos)
} // for (all block y pos)
// compute average gradient strengths
for (int celly=0; celly<cells_in_y_dir; celly++)
{
for (int cellx=0; cellx<cells_in_x_dir; cellx++)
{
float NrUpdatesForThisCell = (float)cellUpdateCounter[celly][cellx];
// compute average gradient strenghts for each gradient bin direction
for (int bin=0; bin<gradientBinSize; bin++)
{
gradientStrengths[celly][cellx][bin] /= NrUpdatesForThisCell;
}
}
}
cout << "descriptorDataIdx = " << descriptorDataIdx << endl;
// draw cells
for (int celly=0; celly<cells_in_y_dir; celly++)
{
for (int cellx=0; cellx<cells_in_x_dir; cellx++)
{
int drawX = cellx * cellSize.width;
int drawY = celly * cellSize.height;
int mx = drawX + cellSize.width/2;
int my = drawY + cellSize.height/2;
rectangle(visual_image,
Point(drawX*scaleFactor,drawY*scaleFactor),
Point((drawX+cellSize.width)*scaleFactor,
(drawY+cellSize.height)*scaleFactor),
CV_RGB(100,100,100),
1);
// draw in each cell all 9 gradient strengths
for (int bin=0; bin<gradientBinSize; bin++)
{
float currentGradStrength = gradientStrengths[celly][cellx][bin];
// no line to draw?
if (currentGradStrength==0)
continue;
float currRad = bin * radRangeForOneBin + radRangeForOneBin/2;
float dirVecX = cos( currRad );
float dirVecY = sin( currRad );
float maxVecLen = cellSize.width/2;
float scale = viz_factor; // just a visual_imagealization scale,
// to see the lines better
// compute line coordinates
float x1 = mx - dirVecX * currentGradStrength * maxVecLen * scale;
float y1 = my - dirVecY * currentGradStrength * maxVecLen * scale;
float x2 = mx + dirVecX * currentGradStrength * maxVecLen * scale;
float y2 = my + dirVecY * currentGradStrength * maxVecLen * scale;
// draw gradient visual_imagealization
line(visual_image,
Point(x1*scaleFactor,y1*scaleFactor),
Point(x2*scaleFactor,y2*scaleFactor),
CV_RGB(0,0,255),
1);
} // for (all bins)
} // for (cellx)
} // for (celly)
// don't forget to free memory allocated by helper data structures!
for (int y=0; y<cells_in_y_dir; y++)
{
for (int x=0; x<cells_in_x_dir; x++)
{
delete[] gradientStrengths[y][x];
}
delete[] gradientStrengths[y];
delete[] cellUpdateCounter[y];
}
delete[] gradientStrengths;
delete[] cellUpdateCounter;
return visual_image;
}
int main()
{
HOGDescriptor hog;
hog.winSize=Size(904,600);
vector<float> des;
Mat src = imread("timg.jpg");
Mat dst ;
resize(src,dst,Size(904,600));
imshow("src",src);
hog.compute(dst,des);
cout<<des.size()<<endl;
Mat background = Mat::zeros(Size(904,600),CV_8UC1);
Mat background_hog = get_hogdescriptor_visual_image(background,des,hog.winSize,hog.cellSize,1,2.0);
imshow("HOG特征1",background_hog);
imwrite("特征可视化1.jpg",background_hog);
Mat src_hog = get_hogdescriptor_visual_image(src,des,hog.winSize,hog.cellSize,1,2.0);
imshow("HOG特征2",src_hog);
imwrite("特征可视化2.jpg",src_hog);
waitKey();
return 0;
} 
本文参与 腾讯云自媒体分享计划，分享自作者个人站点/博客。
原始发表：2018年04月11日，如有侵权请联系 cloudcommunity@tencent.com 删除
评论
登录后参与评论
推荐阅读
目录