Unknown CUDA error : Gpu API call

edit

I'm trying to make a simple program using CUDA for Opencv on ubuntu 14.04. But whenever I try to call any function in the gpu header file it gives me the same error
Opencv error : Gpu API call (unknown error)
Here is the sample code I'm trying to run

#include <iostream>
#include <vector>

#include "opencv/cv.h"
#include "opencv2/core/core.hpp"
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/video/video.hpp"
#include "opencv2/gpu/gpu.hpp"

using namespace std;
using namespace cv;
using namespace cv::gpu;

static void download(const GpuMat& d_mat, vector<Point2f>& vec)
{
    vec.resize(d_mat.cols);
    Mat mat(1, d_mat.cols, CV_32FC2, (void*)&vec[0]);
    d_mat.download(mat);
}

static void download(const GpuMat& d_mat, vector<uchar>& vec)
{
    vec.resize(d_mat.cols);
    Mat mat(1, d_mat.cols, CV_8UC1, (void*)&vec[0]);
    d_mat.download(mat);
}

static void drawArrows(Mat& frame, const vector<Point2f>& prevPts, const vector<Point2f>& nextPts, const vector<uchar>& status, Scalar line_color = Scalar(0, 0, 255))
{
    for (size_t i = 0; i < prevPts.size(); ++i)
    {
        if (status[i])
        {
            int line_thickness = 1;

            Point p = prevPts[i];
            Point q = nextPts[i];

            double angle = atan2((double) p.y - q.y, (double) p.x - q.x);

            double hypotenuse = sqrt( (double)(p.y - q.y)*(p.y - q.y) + (double)(p.x - q.x)*(p.x - q.x) );

            if (hypotenuse < 1.0)
                continue;

            // Here we lengthen the arrow by a factor of three.
            q.x = (int) (p.x - 3 * hypotenuse * cos(angle));
            q.y = (int) (p.y - 3 * hypotenuse * sin(angle));

            // Now we draw the main line of the arrow.
            line(frame, p, q, line_color, line_thickness);

            // Now draw the tips of the arrow. I do some scaling so that the
            // tips look proportional to the main line of the arrow.

            p.x = (int) (q.x + 9 * cos(angle + CV_PI / 4));
            p.y = (int) (q.y + 9 * sin(angle + CV_PI / 4));
            line(frame, p, q, line_color, line_thickness);

            p.x = (int) (q.x + 9 * cos(angle - CV_PI / 4));
            p.y = (int) (q.y + 9 * sin(angle - CV_PI / 4));
            line(frame, p, q, line_color, line_thickness);
        }
    }
}

template <typename T> inline T clamp (T x, T a, T b)
{
    return ((x) > (a) ? ((x) < (b) ? (x) : (b)) : (a));
}

template <typename T> inline T mapValue(T x, T a, T b, T c, T d)
{
    x = clamp(x, a, b);
    return c + (d - c) * (x - a) / (b - a);
}

static void getFlowField(const Mat& u, const Mat& v, Mat& flowField)
{
    float maxDisplacement = 1.0f;

    for (int i = 0; i < u.rows; ++i)
    {
        const float* ptr_u = u.ptr<float>(i);
        const float* ptr_v = v.ptr<float>(i);

        for (int j = 0; j < u.cols; ++j)
        {
            float d = max(fabsf(ptr_u[j]), fabsf(ptr_v[j]));

            if (d > maxDisplacement)
                maxDisplacement = d;
        }
    }

    flowField.create(u.size(), CV_8UC4);

    for (int i = 0; i < flowField.rows; ++i)
    {
        const float* ptr_u = u.ptr<float>(i);
        const float* ptr_v = v.ptr<float>(i);


        Vec4b* row = flowField.ptr<Vec4b>(i);

        for (int j = 0; j < flowField.cols; ++j)
        {
            row[j][0 ...