Image update: in the Tracking thread, the following statement is used in the Track() function to update the image display: mpFrameDrawer->Update(this) 2.View thread code 1) View thread creation Zoom out and you can see the trajectory of the camera, as shown in the following figure: The green one is the display of the current camera, and the blue one is the display of the historical camera. The lower window is used to display the camera pose (that is, key frame) and map points (each map point has corresponding relationship with the feature points in the image). The green square and circle in the image mark the ORB feature points extracted from the image. The upper window always displays one image after another. ORB-SLAM2 code reading notes (1): from mono_kitti single operation starts Using KITTI's monocular data set to run ORB-SLAM2 system, we can see the map display interface is the VIew thread to display. Therefore, in fact, the best way to understand what the View thread has done is to correspond with the Pangolin interface in the code according to the running results of ORB-SLAM2. The visualization of ORB-SLAM2 is mainly realized by using Pangolin, which also uses the opencv interface. 3) Draw the current camera position in the mapĤ) Draws the key frame before the current camera in the mapĦ) The image frame marked with feature points is displayed in the window
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |