在ORB_SLAM2中使用自己的视频

参考教程：https://blog.csdn.net/ykwjt/article/details/88090748
这篇教程中关于使用自己的视频以运行ORB SLAM2好像有点问题，和同学komorebi_fresh（https://me.csdn.net/weixin_44270815）花了点时间解决了

注意：在文件夹ORB_SLAM2中建立下面的myvideo myvideo.yaml myvideo.cpp文件，以及自己的视频，如下图，否则会出现错误

一、新建myvideo.yaml

cd ORB_SLAM2 #ORB_SLAM2的路径要根据自己的路径，我的ORB_SLAM2是在ros的工作空间里
gedit myvideo.yaml

在新建的文件中输入下面的代码：

%YAML:1.0
 
#--------------------------------------------------------------------------------------------
# Camera Parameters. Adjust them!
#--------------------------------------------------------------------------------------------
 
# Camera calibration and distortion parameters (OpenCV) 
Camera.fx: 500.0
Camera.fy: 500.0
Camera.cx: 320.0
Camera.cy: 240.0
 
Camera.k1: 0
Camera.k2: 0
Camera.p1: 0
Camera.p2: 0
Camera.k3: 0
 
# Camera frames per second 
Camera.fps: 30.0
 
# Color order of the images (0: BGR, 1: RGB. It is ignored if images are grayscale)
Camera.RGB: 0
 
#--------------------------------------------------------------------------------------------
# ORB Parameters
#--------------------------------------------------------------------------------------------
 
# ORB Extractor: Number of features per image
ORBextractor.nFeatures: 1000
 
# ORB Extractor: Scale factor between levels in the scale pyramid     
ORBextractor.scaleFactor: 1.2
 
# ORB Extractor: Number of levels in the scale pyramid    
ORBextractor.nLevels: 8
 
# ORB Extractor: Fast threshold
# Image is divided in a grid. At each cell FAST are extracted imposing a minimum response.
# Firstly we impose iniThFAST. If no corners are detected we impose a lower value minThFAST
# You can lower these values if your images have low contrast            
ORBextractor.iniThFAST: 10
ORBextractor.minThFAST: 5
 
#--------------------------------------------------------------------------------------------
# Viewer Parameters
#--------------------------------------------------------------------------------------------
Viewer.KeyFrameSize: 0.05
Viewer.KeyFrameLineWidth: 1
Viewer.GraphLineWidth: 0.9
Viewer.PointSize: 2
Viewer.CameraSize: 0.08
Viewer.CameraLineWidth: 3
Viewer.ViewpointX: 0
Viewer.ViewpointY: -0.7
Viewer.ViewpointZ: -1.8
Viewer.ViewpointF: 500

二、新建myvideo.cpp

gedit myvideo.cpp

在新建的文件中输入下面的代码：

#include <opencv2/opencv.hpp>
#include "System.h"
#include <string>
#include <chrono>   // for time stamp
#include <iostream>
using namespace std;
// 参数文件与字典文件
// 如果你系统上的路径不同，请修改它
string parameterFile = "./myvideo.yaml";
string vocFile = "./Vocabulary/ORBvoc.txt";
// 视频文件
string videoFile = "./myvideo.mp4";
int main(int argc, char **argv) {
 // 声明 ORB-SLAM2 系统
    ORB_SLAM2::System SLAM(vocFile, parameterFile, ORB_SLAM2::System::MONOCULAR, true);
 // 获取视频图像
  cv::VideoCapture cap(videoFile);    // change to 0 if you want to use USB camera.
  // 记录系统时间
  auto start = chrono::system_clock::now();

while (1) {
        cv::Mat frame;
        cap >> frame;   // 读取相机数据

        if ( frame.data == nullptr )
            continue;
        // rescale because image is too large
        cv::Mat frame_resized;
        cv::resize(frame, frame_resized, cv::Size(640,360));
        auto now = chrono::system_clock::now();
        auto timestamp = chrono::duration_cast<chrono::milliseconds>(now - start);
        SLAM.TrackMonocular(frame_resized, double(timestamp.count())/1000.0);
        cv::waitKey(30);
    }
    return 0;


}

三、修改CMakeLists.txt

打开文件夹ORB_SLAM2里的CMakeLists.txt添加下面的代码

#生成调用myvideo.mp4 可执行文件
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${PROJECT_SOURCE_DIR})
add_executable(myvideo myvideo.cpp)
target_link_libraries(myvideo ${PROJECT_NAME})

四、编译和运行

cd ORB_SLAM2
mkdir build
cd build
cmake ..
make -j
cd ..
./myvideo  #(执行)

之后对myvideo.cpp进行修改后都要再次编译才能运行。