我正在尝试对视频的帧运行 ORB OpenCV 算法，我注意到 CPU 版本的执行速度比 GPU 版本快得多。这是代码：
#include <iostream>
#include "opencv2/core/core.hpp"
#include "opencv2/features2d/features2d.hpp"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/gpu/gpu.hpp"
#include <fstream>
#include <sstream>
#include <math.h>
#include <omp.h>
#include <algorithm>
#include <vector>
#include <string>
using namespace cv;
using namespace std;
using namespace cv::gpu;
void process_cpu(string vid, int start_frame, int end_frame)
{
VideoCapture myCapture(vid);
Mat frame, gray_frame;
ORB myOrb(400);
Mat descriptors;
vector<KeyPoint> keypoints;
myCapture.set(CV_CAP_PROP_POS_FRAMES, start_frame);
for (int i=0; i<end_frame-start_frame; i++) {
myCapture.read(frame);
cvtColor(frame, gray_frame, CV_RGB2GRAY);
myOrb(gray_frame, Mat(), keypoints, descriptors);
}
myCapture.release();
}
void process_gpu(string vid, int start_frame, int end_frame)
{
VideoCapture myCapture(vid);
Mat frame, gray_frame;
GpuMat gpu_frame;
ORB_GPU myOrb(400);
GpuMat keypoints, descriptors;
myCapture.set(CV_CAP_PROP_POS_FRAMES, start_frame);
for (int i=0; i<end_frame-start_frame; i++) {
myCapture.read(frame);
cvtColor(frame, gray_frame, CV_RGB2GRAY);
gpu_frame.upload(gray_frame);
myOrb.blurForDescriptor = true;
myOrb(gpu_frame, GpuMat(), keypoints, descriptors);
}
myCapture.release();
}
int main (int argc, char* argv[])
{
int n = 4;
VideoCapture myCapture(argv[1]);
double frameNumber = myCapture.get(CV_CAP_PROP_FRAME_COUNT);
myCapture.release();
double TimeStart = 0;
double TotalTime = 0;
TimeStart = (double)getTickCount();
process_gpu(argv[1], 0, frameNumber);
TotalTime = (double)getTickCount() - TimeStart;
TotalTime = TotalTime / getTickFrequency();
cout << "Gpu Time : " << TotalTime << endl;
TimeStart = (double)getTickCount();
process_cpu(argv[1], 0, frameNumber);
TotalTime = (double)getTickCount() - TimeStart;
TotalTime = TotalTime / getTickFrequency();
cout << "Cpu Time : " << TotalTime << endl;
return -1;
}
在 3000 帧和 720x480 分辨率的视频上运行此程序后，GPU 时间为 54 秒，CPU 时间为 24 秒。我与其他视频（不是高清）得到了类似的结果。电脑规格：
i7-4770K CPU 3.50 GHz
英伟达 GeForce GTX 650
- 16 GB 内存
其他特征检测/描述算法（如 SURF）在我的机器上使用 GPU 实现时执行得更快。
有没有人在他的机器上比较过 ORB 的两种实现？