【高性能计算】CUDA编程之OpenCV的应用（教程与代码-4）

• imread命令将返回以蓝色、绿色和红色（BGR格式）开头的三个通道
• 处理视频的main函数中需要做的第一件事是创建VideoCapture对象。 GPU
• CUDA模块中的函数都定义在cv::cuda命名空间中，将设备上配置给图像数据用的显存块作为其参数。
• gettickcount函数返回启动系统后经过的时间（以毫秒为单位）
• 使用具有CUDA的opencv进行阈值滤波

#include 
#include "opencv2/opencv.hpp"
int main (int argc, char* argv[])
{
 cv::Mat h_img1 = cv::imread("images/cameraman.tif", 0);
cv::cuda::GpuMat d_result1,d_result2,d_result3,d_result4,d_result5, d_img1;
//Measure initial time ticks
int64 work_begin = cv::getTickCount(); 
d_img1.upload(h_img1);
cv::cuda::threshold(d_img1, d_result1, 128.0, 255.0, cv::THRESH_BINARY);
cv::cuda::threshold(d_img1, d_result2, 128.0, 255.0, cv::THRESH_BINARY_INV);
cv::cuda::threshold(d_img1, d_result3, 128.0, 255.0, cv::THRESH_TRUNC);
cv::cuda::threshold(d_img1, d_result4, 128.0, 255.0, cv::THRESH_TOZERO);
cv::cuda::threshold(d_img1, d_result5, 128.0, 255.0, cv::THRESH_TOZERO_INV);
cv::Mat h_result1,h_result2,h_result3,h_result4,h_result5;
d_result1.download(h_result1);
d_result2.download(h_result2);
d_result3.download(h_result3);
d_result4.download(h_result4);
d_result5.download(h_result5);
//Measure difference in time ticks
int64 delta = cv::getTickCount() - work_begin;
double freq = cv::getTickFrequency();
//Measure frames per second
double work_fps = freq / delta;
std::cout <<"Performance of Thresholding on GPU: " <<std::endl;
std::cout <<"Time: " << (1/work_fps) <<std::endl;
std::cout <<"FPS: " <<work_fps <<std::endl;
 return 0;
}

• 使用cuda+opencv修改图像大小

#include 
#include "opencv2/opencv.hpp"
#include 
#include "opencv2/opencv.hpp"
int main ()
{
    cv::Mat h_img1 = cv::imread("images/cameraman.tif",0);
    cv::cuda::GpuMat d_img1,d_result1,d_result2;
    d_img1.upload(h_img1);
    int width= d_img1.cols;
    int height = d_img1.size().height;
    cv::cuda::resize(d_img1,d_result1,cv::Size(200, 200), cv::INTER_CUBIC);
    cv::cuda::resize(d_img1,d_result2,cv::Size(0.5*width, 0.5*height), cv::INTER_LINEAR);    
    cv::Mat h_result1,h_result2;
    d_result1.download(h_result1);
    d_result2.download(h_result2);
    cv::imshow("Original Image ", h_img1);
    cv::imshow("Resized Image", h_result1);
    cv::imshow("Resized Image 2", h_result2);
    cv::imwrite("Resized1.png", h_result1);
    cv::imwrite("Resized2.png", h_result2);
    cv::waitKey();
    return 0;
}

• 使用HARR进行人脸检测

#include 
#include 
using namespace cv;
using namespace std;
int main()
{
    VideoCapture cap(0);
    if (!cap.isOpened()) {
        cerr << "Can not open video source";
        return -1;
    }
    std::vector<cv::Rect> h_found;
    cv::Ptr<cv::cuda::CascadeClassifier> cascade = cv::cuda::CascadeClassifier::create("haarcascade_frontalface_alt2.xml");
    cv::cuda::GpuMat d_frame, d_gray, d_found;
    while(1)
    {
        Mat frame;
        if ( !cap.read(frame) ) {
            cerr << "Can not read frame from webcam";
            return -1;
        }
        d_frame.upload(frame);
        cv::cuda::cvtColor(d_frame, d_gray, cv::COLOR_BGR2GRAY);
        cascade->detectMultiScale(d_gray, d_found);
        cascade->convert(d_found, h_found);
        
        for(int i = 0; i < h_found.size(); ++i)
        {
              rectangle(frame, h_found[i], Scalar(0,255,255), 5);
        }
        imshow("Result", frame);
        if (waitKey(1) == 'q') {
            break;
        }
    }
    return 0;
}

总结

本教程是自己学习CUDA所遇到的一些概念与总结，由于CUDA主要是一个应用，还是以代码为主，加速算法与硬件息息相关，干了很久深度学习了，对于硬件的知识已经遗忘很多，后续还是复习一些硬件知识后再继续深入吧。