add megapose pipeline diagram in documentation

lagadic · Aug 21, 2023 · dbab55d · dbab55d
1 parent 7b7d44b
commit dbab55d
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 4 deletions.
diff --git a/doc/image/tutorial/tracking/megapose/megapose_pipeline.png b/doc/image/tutorial/tracking/megapose/megapose_pipeline.png
diff --git a/doc/tutorial/tracking/tutorial-tracking-megapose.dox b/doc/tutorial/tracking/tutorial-tracking-megapose.dox
@@ -28,19 +28,25 @@ It has however, several drawbacks:
     You may thus require a way to detect the object, such as an object detection neural network (available in ViSP with the class vpDetectorDNNOpenCV, see \ref tutorial-detection-dnn).
     For initial tests, the bounding box can also be provided by the user via click.
 
+For the 3D model and detection inputs required by megapose, we provide tutorials to help you get setup. See \ref tutorial-megapose-model for the 3D model creation and \ref tutorial-synthetic-blenderproc to train a detection network.
+With these tutorials and the tools presented therein, the work to use megapose can be almost fully automated as summed up in the figure below:
+
+\image html tutorial/tracking/megapose/megapose_pipeline.png
+
+
 
 The MegaPose integration in ViSP is based on a client-server model:
 - The client, that uses either vpMegaPose or vpMegaPoseTracker, is C++-based. It sends pose estimation requests to the server.
-- The server is written in Python. It wraps around the MegaPose model. Each time a pose estimation is requested, the server reshapes the data and forwards it to MegaPose. 
-  It then sends back the information to the client. 
+- The server is written in Python. It wraps around the MegaPose model. Each time a pose estimation is requested, the server reshapes the data and forwards it to MegaPose.
+  It then sends back the information to the client.
 
-\note The computer running the server needs a GPU. The client can run on the same computer as the server. It can also run on another computer without a GPU. 
-  As Ethernet is used to communicate between client and server, both computers must be accessible on the Ethernet network.
+\note The computer running the server needs a GPU. The client can run on the same computer as the server. It can also run on another computer without a GPU. To obtain have a decent tracking speed, it is recommended to have both machines on the same network.
 
 This tutorial will explain how to install and run MegaPose and
 then demonstrate its usage with a simple object tracking application.
 
 
+
 \section megapose_install Installation
 
 \subsection megapose_cpp_install Installing the client