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转换为灰度(如果可能),使用 ROI 或滚动您自己的 ASM AVX 函数以使用每 1/3(或您需要的任何缩放因子)行和列调整大小。调整大小功能相当优化。
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,另一种方法是在启用 CUDA 的 GPU 上调整大小。但是,您在选择卡时必须小心,因为您需要足够高的内存带宽以适应从 GPU 内存上传和下载图像所花费的时间。
请注意,当图像在 GPU 内存上不可用时,CPU 在灰度上优于 GPU。如果图像在 GPU 内存上可用,那么对于 Color,它使用 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 采集卡来实现这一点。
在 Xeon E5 v2 @ 3.0Ghz 680GTX 上进行了基准测试