1. 編譯完成之后就可以使用了，按照說明我們可以知道，首先開啟roscore

再打開一個命令窗口使用命令：rosrun ORB_SLAM ORB_SLAM PATH_TO_VOCABULARY PATH_TO_SETTINGS_FILE

其中ORB_SLAM PATH_TO_VOCABULARY：是一種樹型數(shù)據(jù)結構模型，ORB-SLAM里面主要用來做回訪(loop-closure)檢 測，對于不同數(shù)據(jù)集嚴格來說需要離線單獨處理生成，但一般成像條件都差不多所以對于不同圖像數(shù)據(jù)集可以使用相同的詞匯數(shù)據(jù)文件（相當于一個數(shù)據(jù)庫文件，方 便快速保存和查詢視覺特征信息）。雖然是TXT文件，打開就是許多數(shù)字而已。（https://answers.cosrobotics.org/question/184/guan-yu-orb_slamyun-xing-yi-ji-rgb-d-datasetde-xiang-ji-can-shu-de-wen-ti/）

PATH_TO_SETTINGS_FILE：這個很容易理解就是相機的內參；

然后我們輸入命令如圖所示：

我們查看ORB_SLAM節(jié)點的topic

salm@salm:~$ rtopic? list -v
Published topics:
?* /ORB_SLAM/Map [visualization_msgs/Marker] 1 publisher
?* /ORB_SLAM/Frame [sensor_msgs/Image] 1 publisher
?* /rosout [rosgraph_msgs/Log] 1 publisher
?* /tf [tf2_msgs/TFMessage] 1 publisher
?* /rosout_agg [rosgraph_msgs/Log] 1 publisher

Subscribed topics:
?* /camera/image_raw [sensor_msgs/Image] 1 subscriber
?* /rosout [rosgraph_msgs/Log] 1 subscriber

（1）知道該節(jié)點是訂閱/camera/image_raw這個topic,然后被 ORB_SLALM 節(jié)點處理后的圖像幀被發(fā)布到話題 ORB_SLAM/Frame 中，可以通過使用 image_view 功能包來查看

rosrun image_view image_view image:=/ORB_SLAM/Frame _autosize:=true

（2）ORB_SLAM 節(jié)點處理得到的地圖被發(fā)布到話題 /ORB_SLAM/Map 中，攝像機當前位姿和地圖全局坐標原點通過 /tf 功能包分別發(fā)布到話題 /ORB_SLAM/Camera 和話題 /ORB_SLAM/World 中，通過運行 rviz 功能包來查看地圖：

rosrun rviz rviz -d Data/rviz.rviz

這都是我們在訂閱了/camera/image_raw才能看到的試驗結果，那么我們從那里得到/camera/image_raw這個節(jié)點呢？

//

?那么我就嘗試首先發(fā)布一個經(jīng)典的圖片topic 給ORB_SLAM節(jié)點:

（1）首先進入自己的工作空間catkin_ws,然后進入src,使用catkin_pkg_create命令創(chuàng)建我的功能包

? ? 參考 ? ? ? ? ??http://wiki.ros.org/image_transport/Tutorials ??

???????????????????? http://wiki.ros.org/ROS/Tutorials/WritingPublisherSubscriber%28c%2B%2B%29

? ? ? ? ? ? ?$ cd catkin_ws/$ cd src/$ catkin_create_pkg learning_image_transport image_transport cv_bridge
? ? ? ? ? ? ?$ cd ..
? ? ? ? ? ? ?$ catkin_make
? ? ? ? ? ? ?$ cd src
? ? ? ? ? ? ?$ vi my_publisher.cpp 
輸入：

#include <ros/ros.h> ? ? ? ? ? ? ? ? ? ? ??
#include <image_transport/image_transport.h>
#include <opencv2/highgui/highgui.hpp>
#include <cv_bridge/cv_bridge.h> ? ?//非常有用的功能包，實現(xiàn)ROS與OPENCV圖像的轉換int main(int argc, char** argv)
{ros::init(argc, argv, "image_publisher");ros::NodeHandle nh;image_transport::ImageTransport it(nh);image_transport::Publisher pub = it.advertise("camera/image_raw", 1); ?//這里我們發(fā)布的主題要與ORB_SLAM節(jié)點訂閱的話題一致//cv::Mat image = cv::imread(argv[1], CV_LOAD_IMAGE_COLOR);cv::Mat image = cv::imread("/home/salm/myopencv/lena.jpg",1); ?//寫入自己要載入的圖像位置cv::waitKey(30);sensor_msgs::ImagePtr msg = cv_bridge::CvImage(std_msgs::Header(), "bgr8", image).toImageMsg(); ? ?//這一句就是把圖像讀入并轉為opencv可處理的圖像ros::Rate loop_rate(5);while (nh.ok()) {pub.publish(msg);ros::spinOnce();loop_rate.sleep();}
}

之后在CMakefile.txt文件添加

add_executable(my_publisher src/my_publisher.cpp)
target_link_libraries(my_publisher ${catkin_LIBRARIES} ${OpenCV_LIBRARIES})

進行catkin_make即可我們運行查看一下實現(xiàn)的結果：

?????????????????????????????????????????????????????? $ rosrun learning_image_transport? my_publisher

　　　　　　　　　　　　　　　? $? rosrun ORB_SLAM ORB_SLAM Data/ORBvoc.txt Data/Settings.yaml

?????????????????????????????????????????????????????? $? rosrun image_view image_view image:=/ORB_SLAM/Frame _autosize:=true

??????????????????????????????????????????????????????????????????

就是這個結果，因為我也是一邊學習，一邊實現(xiàn)，我自己也不知道里面使用的算法，具體為什么會這樣，這也是不斷學習的原因

（2）那現(xiàn)在我再發(fā)布一個動態(tài)的topic 用攝像頭捕捉的話題發(fā)布給ORB_SLAM,看看實現(xiàn)結果：

?與之前的一樣，仍然在src 文件下???? $ vi? image_converter.cpp

輸入：

#include <ros/ros.h>
#include <image_transport/image_transport.h>
#include <cv_bridge/cv_bridge.h>
#include <sensor_msgs/image_encodings.h>
#include <opencv2/imgproc/imgproc.hpp> //include the headers for OPENCV's image processing and GUI module 
#include <opencv2/highgui/highgui.hpp>  //static const std::string OPENCV_WINDOW = "Image window";   //define show image guiclass ImageConverter
{ros::NodeHandle nh_;                    //define Nodehandleimage_transport::ImageTransport it_;    //use this to create a publisher or subscriberimage_transport::Subscriber image_sub_; //image_transport::Publisher image_pub_;public:ImageConverter(): it_(nh_){// Subscrive to input video feed and publish output video feedimage_sub_ = it_.subscribe("/usb_cam/image_raw", 1, &ImageConverter::imageCb, this);//image_pub_ = it_.advertise("/image_converter/output_video", 1);image_pub_ = it_.advertise("/camera/image_raw", 1);cv::namedWindow(OPENCV_WINDOW);    //Opencv HighGUI calls to create/destroy a display window on start-up / shutdon}~ImageConverter(){cv::destroyWindow(OPENCV_WINDOW);}void imageCb(const sensor_msgs::ImageConstPtr& msg){cv_bridge::CvImagePtr cv_ptr;try{cv_ptr = cv_bridge::toCvCopy(msg, sensor_msgs::image_encodings::BGR8);}catch (cv_bridge::Exception& e){ROS_ERROR("cv_bridge exception: %s", e.what());return;}cv::imshow(OPENCV_WINDOW, cv_ptr->image);cv::waitKey(3);// Output modified video streamimage_pub_.publish(cv_ptr->toImageMsg());}
};int main(int argc, char** argv)
{ros::init(argc, argv, "image_converter");ImageConverter ic;ros::spin();return 0;
}

?同理 添加

?????????????????????????? add_executable(image_converter src/image_converter.cpp)
?????????????????????????? target_link_libraries(image_converter ${catkin_LIBRARIES} ${OpenCV_LIBRARIES})

當然前提是電腦有攝像頭，并且下載了USB攝像頭的驅動：https://github.com/bosch-ros-pkg/usb_cam

輸入以下命令：?????????????????????????????

???????????????????????????????????????????????????? ? $? roslaunch usb_cam usb_cam-test.launch

（在啟動攝像頭可能會遇到一些問題吧，比如出現(xiàn)? Webcam: expected picture but didn't get it...就要修改launch文件下的 "pixel_format"，比如有mjpeg ,yuyv等）

?????????????????????????????????????????????????????? $? rosrun learning_image_transport image_converter

　　　　　　　　　　　　　　　? $? rosrun ORB_SLAM ORB_SLAM Data/ORBvoc.txt Data/Settings.yaml

?????????????????????????????????????????????????????? $? rosrun image_view image_view image:=/ORB_SLAM/Frame _autosize:=true

?

版權所有，轉載請注明出處 http://www.cnblogs.com/li-yao7758258/p/5912663.html

總結

以上是生活随笔為你收集整理的运行ORB-SLAM笔记_使用篇（二）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內容還不錯，歡迎將生活随笔推薦給好友。