调整cv :: Mat大小的最有效方法

Question

所有

我正在编写一个图像处理程序，在一帧中使用cv :: resize（INTER_LINEAR）数百次。但是，我发现cv :: resize（）是一个cpu杀手，它是我程序中的热点。是否有更好的方法来以更少的CPU使用率来调整图像大小？

代码有点像这样：

void process(const cv::Mat& frame) {
    for(int i = 0; i < COUNTS; ++i) {
        int new_rows = CalculateHeight();
        int new_cols = CalculateWidth();
        cv::Mat new_img;
        cv::resize(frame, new_mg, cv::Size(new_cols, new_rows));
        // ...
    }
    // ...
}

谢谢！

Answer 1

这是我使用OpenCV函数调整随机图像大小10,000次所做的一些测试的结果。最好的解决方案似乎是在调整大小之前使用ROI或滚动您自己的ASM AVX函数以使用每1/3（或您需要的缩放比例）行和列来转换为灰度（如果可能）。调整大小功能是相当优化的。

Colour
INTER_LINEAR 7953.89ms
INTER_LINEAR GPU 2252.72ms
INTER_LINEAR GPU MEMIO 23303.7ms
INTER_NEAREST 7297.58ms
INTER_NEAREST GPU 906.336ms
INTER_NEAREST GPU MEMIO 22374.1ms
BORDER_DEFAULT 47488.8ms
BORDER_REFLECT 47515.4ms
BORDER_REPLICATE 47516ms
BORDER_WRAP 47980.7ms
PYR GPU 4126.93ms

Grayscale
INTER_LINEAR 413.789ms
INTER_LINEAR GPU 1027.85ms
INTER_LINEAR GPU MEMIO 9568.99ms
INTER_NEAREST 978.89ms
INTER_NEAREST GPU 747.621ms
INTER_NEAREST GPU MEMIO 9346.28ms
BORDER_DEFAULT 19266.7ms
BORDER_REFLECT 19274.1ms
BORDER_REPLICATE 19300.8ms
BORDER_WRAP 19386.3ms
PYR GPU 2272.7ms


#include "opencv2/opencv.hpp"
#include "opencv2/cudaimgproc.hpp"
#include "opencv2/cudawarping.hpp"

#include <iostream>
#include <string>
#include <chrono>

using namespace std;
using namespace cv;

template <typename T>
double resizePerfEval(const Mat& frame, unsigned int n, T resizeFlag) {

    auto start = chrono::steady_clock::now();

    for (auto i = 0; i < n; i++) {
        Mat temp;
        resize(frame, temp, Size(), 0.5, 0.5, resizeFlag); 
    }

    return chrono::duration <double, milli>(chrono::steady_clock::now() - start).count();
}

template <typename T>
double pyramidPerfEval(const Mat& frame, unsigned int n, T border) {

    auto start = chrono::steady_clock::now();
    Size s(frame.cols / 2, frame.rows / 2);

    for (auto i = 0; i < n; i++) {
        Mat tmp;
        pyrDown(frame, tmp, s, border); 
    }

    return chrono::duration <double, milli>(chrono::steady_clock::now() - start).count();
}

template <typename T>
double resizePerfEvalGPU(const Mat& frame, unsigned int n, T resizeFlag, bool uploadDownload=false) {

    auto start = chrono::steady_clock::now();

    Mat tmp;
    cuda::GpuMat frame_d, temp;
    frame_d.upload(frame);

    for (auto i = 0; i < n; i++) {          

        cuda::resize(frame_d, temp, Size(), 0.5, 0.5, resizeFlag);
        if (uploadDownload) {
            temp.download(tmp);
            frame_d.upload(frame);
        }
    }

    return chrono::duration <double, milli>(chrono::steady_clock::now() - start).count();
}

double pyramidPerfEvalGPU(const Mat& frame, unsigned int n, bool uploadDownload = false) {

    auto start = chrono::steady_clock::now();

    Mat tmp;
    cuda::GpuMat frame_d, temp;
    frame_d.upload(frame);

    for (auto i = 0; i < n; i++) {      

        cuda::pyrDown(frame_d, temp);
        if (uploadDownload) {
            temp.download(tmp);
            frame_d.upload(frame);
        }

    }

    return chrono::duration <double, milli>(chrono::steady_clock::now() - start).count();
}


void runTest(const Mat& frame, unsigned int n) {

    cout << "INTER_LINEAR "     << resizePerfEval(frame, n, INTER_LINEAR) << "ms" << endl;
    cout << "INTER_LINEAR GPU " << resizePerfEvalGPU(frame, n, INTER_LINEAR) << "ms" << endl;
    cout << "INTER_LINEAR GPU MEMIO " << resizePerfEvalGPU(frame, n, INTER_LINEAR, true) << "ms" << endl;

    cout << "INTER_NEAREST "    << resizePerfEval(frame, n, INTER_NEAREST) << "ms" << endl;
    cout << "INTER_NEAREST GPU "    << resizePerfEvalGPU(frame, n, INTER_NEAREST) << "ms" << endl;
    cout << "INTER_NEAREST GPU MEMIO " << resizePerfEvalGPU(frame, n, INTER_NEAREST, true) << "ms" << endl;

    cout << "BORDER_DEFAULT "   << pyramidPerfEval(frame, n, BORDER_DEFAULT) << "ms" << endl;
    cout << "BORDER_REFLECT "   << pyramidPerfEval(frame, n, BORDER_REFLECT) << "ms" << endl;
    cout << "BORDER_REPLICATE " << pyramidPerfEval(frame, n, BORDER_REPLICATE) << "ms" << endl;
    cout << "BORDER_WRAP "      << pyramidPerfEval(frame, n, BORDER_WRAP) << "ms" << endl;
    cout << "PYR GPU "          << pyramidPerfEvalGPU(frame, n) << "ms" << endl;

}

int main(int argc, char* argv[])
{

    Mat gsframe, frame = Mat::ones(Size(1920, 1080), CV_8UC3);
    randu(frame, Scalar::all(0), Scalar::all(255));
    cvtColor(frame, gsframe, CV_BGR2GRAY);
    auto n = 10000;

    cout << "Colour" << endl;
    runTest(frame, n);

    cout << endl << "Grayscale" << endl;
    runTest(gsframe, n);    

    return 0;
}

如果算法在PC上运行，则另一种方法是在启用CUDA的GPU上调整大小。您在选择卡时必须小心，因为您需要足够的内存带宽以适应从GPU内存上载和下载图像所花费的时间。

从结果中注意到，CPU在灰度级上击败了GPU，并且图像在GPU内存上不可用。如果图像在GPU内存中可用，则对于Color，其使用GPU的速度提高了3.5倍（特别是对于非常大的图像尺寸）。对于高端应用，可以使用带有GPUDirect的NVIDIA采集卡来实现。

基准测试是在Xeon E5 v2 @ 3.0Ghz 680GTX上进行的