EXC_BAD_ACCESS while Calculating Descriptor

edit

I try to calculate a SIFT Descriptor out of KeyPoints found by the FAST Corner Detection. For that, I adapted some functions from the Sift.cpp and changed them so they can be used with FAST generated KeyPoints with nonmaxsuppression. While I try to calculate the Descriptor I get an EXC_BAD_ACCESS Error and I cant find the origin of this Error. I tried to make a example as small as possible of my code where the Error is generated with no constants or aliases. When you want to know more about the full code see my Git or look at this Question where already some things have been explained in the comments. You can get the Example Image with this Link Now the code:

#include <opencv2/opencv.hpp>
#include <opencv2/core/hal/hal.hpp>

using namespace cv;
int descriptorSize() {
    // Descr_Width * Descr_Width * Descr_hist_bins
    return 3*3*4;
}

static void calcSiftDescriptor( const Mat& img, Point2f ptf, float ori, float scl,
                           int d, int n, float* dst )
{
    Point pt(cvRound(ptf.x), cvRound(ptf.y));
    float cos_t = cosf(ori*(float)(CV_PI/180));
    float sin_t = sinf(ori*(float)(CV_PI/180));
    float bins_per_rad = n / 360.f;
    float exp_scale = -1.f/(d * d * 0.5f);
    // 3.f = Descr_scale_factor
    float hist_width = 3.f * scl;
    int radius = cvRound(hist_width * 1.4142135623730951f * (d + 1) * 0.5f);
    // Clip the radius to the diagonal of the image to avoid autobuffer too large exception
    radius = std::min(radius, (int) sqrt(((double) img.cols)*img.cols + ((double) img.rows)*img.rows));
    cos_t /= hist_width;
    sin_t /= hist_width;

    int i, j, k, len = (radius*2+1)*(radius*2+1), histlen = (d+2)*(d+2)*(n+2);
    int rows = img.rows, cols = img.cols;

    AutoBuffer<float> buf(len*6 + histlen);
    float *X = buf, *Y = X + len, *Mag = Y, *Ori = Mag + len, *W = Ori + len;
    float *RBin = W + len, *CBin = RBin + len, *hist = CBin + len;

    for( i = 0; i < d+2; i++ )
    {
        for( j = 0; j < d+2; j++ )
            for( k = 0; k < n+2; k++ )
                hist[(i*(d+2) + j)*(n+2) + k] = 0.;
    }

    for( i = -radius, k = 0; i <= radius; i++ )
        for( j = -radius; j <= radius; j++ )
        {
            // Calculate sample's histogram array coords rotated relative to ori.
            // Subtract 0.5 so samples that fall e.g. in the center of row 1 (i.e.
            // r_rot = 1.5) have full weight placed in row 1 after interpolation.
            float c_rot = j * cos_t - i * sin_t;
            float r_rot = j * sin_t + i * cos_t;
            float rbin = r_rot + d/2 - 0.5f;
            float cbin = c_rot + d/2 - 0.5f;
            int r = pt.y + i, c = pt.x + j;

            if( rbin > -1 && rbin < d && cbin > -1 && cbin < d &&
               r > 0 && r < rows - 1 && c > 0 && c < cols - 1 )
            {
                float dx = (float)(img.at<float>(r, c+1) - img.at<float>(r, c-1));
                float dy = (float)(img.at<float>(r-1, c) - img.at<float>(r+1, c));
                X[k] = dx; Y[k] = dy; RBin[k] = rbin; CBin[k] = cbin;
                W[k] = (c_rot * c_rot + r_rot * r_rot)*exp_scale;
                k++;
            }
        }

    len = k;
    cv::hal::fastAtan2(Y, X, Ori ...