OpenCV ORB GPU的实现速度比CPU慢

OpenCV ORB GPU implementation slower than CPU

本文关键字：CPU 速度 实现 ORB GPU OpenCV      更新时间：2023-10-16

我试图将ORB OpenCV算法运行到视频的帧，我注意到CPU版本的执行速度比GPU版本快得多。下面是代码:

#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后，GPU时间为54秒，CPU时间为24秒。我在其他视频(非高清)上得到了类似的结果。电脑规格:

  • i7-4770K CPU 3.50 GHz

  • NVIDIA 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实现时会执行得更快。

有人在他的机器上比较过ORB的两种实现吗?

摘自本文:

cv::ORB应用高斯模糊(大约20行)在计算描述符之前。这是无法控制的通过公共接口。

cv::gpu::ORB_GPU有一个public成员bool blurForDescriptor默认构造为false。当我把它设为true时，我发现最小/平均/最大汉明距离下降到0/7.2/30位，其中似乎更合理。

相关文章：