使用OpenCV的Sobel操作计算图像梯度方向 [英] Calculating image gradient direction using OpenCV's Sobel operation

问题描述

我试图使用OpenCV的Sobel方法的结果来确定图像梯度方向。

我理解这应该是一个非常简单的任务，我认为我理解这个理论，但实现这一点比我想象的更具挑战性。

我希望梯度方向在0-360度之间，但是我的代码显示所有的梯度在180 - 270度之间。

提交了此代码的以前版本，其中包括整数除法问题。我已经解决了这个问题，但它没有解决限制角度方向的问题。

我已经走过所有的代码，但我只是看不到我的方向， m错了？任何人都可以发现我的错误？

谢谢。

  void getGradients IplImage * original，cv :: Mat * gradArray）
 {
 cv :: Mat original_Mat（original，true）; 
 
 //将其转换为灰色
 cv :: cvtColor（original_Mat，original_Mat，CV_RGB2GRAY）; 
 // cv :: blur（original_Mat，original_Mat，cv :: Size（7,7））; 
 
 ///生成grad_x和grad_y 
 cv :: Mat grad_x = cv :: Mat :: zeros（original-> height，original-> width，CV_16S）; 
 cv :: Mat grad_y = cv :: Mat :: zeros（original-> height，original-> width，CV_16S）; 
 
 ///渐变X 
 cv :: Sobel（original_Mat，grad_x，CV_16S，1，0，3）; 
 
 ///渐变Y 
 cv :: Sobel（original_Mat，grad_y，CV_16S，0，1，3）; 
 
 uchar * pixelX = grad_x.data; 
 uchar * pixelY = grad_y.data; 
 uchar * grad1 = gradArray [0] .data; 
 uchar * grad2 = gradArray [1] .data; 
 uchar * grad3 = gradArray [2] .data; 
 uchar * grad4 = gradArray [3] .data; 
 uchar * grad5 = gradArray [4] .data; 
 uchar * grad6 = gradArray [5] .data; 
 uchar * grad7 = gradArray [6] .data; 
 uchar * grad8 = gradArray [7] .data; 
 int count = 0; 
 int min = 999999; 
 int max = -1; 
 
 for（int i = 0; i< grad_x.rows * grad_x.cols; i ++）
 {
 double directionRAD = atan2（pixelY [i]，pixelX [i ]）; 
 int directionDEG =（int）（180 + directionRAD / M_PI * 180）; 
 
 if（directionDEG  if（directionDEG> max）{max = directionDEG;} 
 
 if（directionDEG> ; = 0&& directionDEG <= 45）{grad1 [i] = 255; count ++;} 
 if（directionDEG> = 45&& directionDEG< = 90）{grad2 [i] = 255; count ++;} 
 if（directionDEG> = 90&& directionDEG< = 135）{grad3 [i] = 255; count ++;} 
 if（directionDEG> = 135&& directionDEG< = 190）{grad4 [i] = 255; count ++;} 
 if（directionDEG> = 190&& directionDEG< = 225）{grad5 [i] = 255; count ++;} 
 if（directionDEG> = 225&& directionDEG< = 270）{grad6 [i] = 255; count ++;} 
 if（directionDEG> = 270&& directionDEG< = 315）{grad7 [i] = 255; count ++;} 
 if（directionDEG> = 315&& directionDEG< = 360）{grad8 [i] = 255; count ++;} 
 
 if（directionDEG <0 || directionDEG> 360）
 {
 cout<<方法中给出的奇怪梯度方向：getGradients。 
} 
 
} 
  

}

解决方案

grad_x 和 grad_y

但是，您声明了 pixelX 和 pixelY 指向8位字节的指针。因此 pixelX [1] 是第一个渐变的第二个字节，而不是第二个渐变。

  short * pixelX = grad_x.ptr< short>（0）; 
 short * pixelY = grad_y.ptr< short>（0）; 
  

I am attempting to determine the image gradient direction using the results from OpenCV's Sobel method.

I understand this should be a very simple task, I think I understand the theory but implementing this has been more challenging than I thought.

I would expect the gradient directions to be between 0-360 degrees, however my code shows all gradients fall between 180 - 270 degrees.

I submitted a previous version of this code which included an integer division issue. I have fixed this but it has not solved the problem of a restricted angle of direction.

I have stepped through all the code but I just can't see where I'm going wrong? Can anyone spot my mistake?

Thanks.

void getGradients(IplImage* original, cv::Mat* gradArray)
{
cv::Mat original_Mat(original, true);

// Convert it to gray
cv::cvtColor( original_Mat, original_Mat, CV_RGB2GRAY );
//cv::blur(original_Mat, original_Mat, cv::Size(7,7));

/// Generate grad_x and grad_y
cv::Mat grad_x = cv::Mat::zeros(original->height, original->width, CV_16S); 
cv::Mat grad_y = cv::Mat::zeros(original->height, original->width, CV_16S);

/// Gradient X
cv::Sobel(original_Mat, grad_x, CV_16S, 1, 0, 3);

/// Gradient Y
cv::Sobel(original_Mat, grad_y, CV_16S, 0, 1, 3);

uchar* pixelX = grad_x.data;
uchar* pixelY = grad_y.data;
uchar* grad1 = gradArray[0].data;
uchar* grad2 = gradArray[1].data;
uchar* grad3 = gradArray[2].data;
uchar* grad4 = gradArray[3].data;
uchar* grad5 = gradArray[4].data;
uchar* grad6 = gradArray[5].data;
uchar* grad7 = gradArray[6].data;
uchar* grad8 = gradArray[7].data;
int count = 0;
int min = 999999;
int max = -1;

for(int i = 0; i < grad_x.rows * grad_x.cols; i++) 
{
        double directionRAD = atan2(pixelY[i], pixelX[i]);
        int directionDEG = (int)(180 + directionRAD / M_PI * 180);

        if(directionDEG < min){min = directionDEG;}
        if(directionDEG > max){max = directionDEG;}

        if(directionDEG >= 0 && directionDEG <= 45)         { grad1[i] = 255; count++;}         
        if(directionDEG >= 45 && directionDEG <= 90)        { grad2[i] = 255; count++;}         
        if(directionDEG >= 90 && directionDEG <= 135)       { grad3[i] = 255; count++;}         
        if(directionDEG >= 135 && directionDEG <= 190)      { grad4[i] = 255; count++;}         
        if(directionDEG >= 190 && directionDEG <= 225)      { grad5[i] = 255; count++;}         
        if(directionDEG >= 225 && directionDEG <= 270)      { grad6[i] = 255; count++;}     
        if(directionDEG >= 270 && directionDEG <= 315)      { grad7[i] = 255; count++;}
        if(directionDEG >= 315 && directionDEG <= 360)      { grad8[i] = 255; count++;}

        if(directionDEG < 0 || directionDEG > 360)
        {
            cout<<"Weird gradient direction given in method: getGradients.";
        }

}

}

解决方案

grad_x and grad_y are Mats of type CV_16SC1, that is every pixel in them takes up two bytes.

However you declare pixelX and pixelY to pointers to 8 bit bytes. Therefore pixelX[1] is the second byte of the first gradient, rather than the second gradient.

You need

short* pixelX = grad_x.ptr<short>(0);
short* pixelY = grad_y.ptr<short>(0);

这篇关于使用OpenCV的Sobel操作计算图像梯度方向的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！