Using TM ROS Driver to get EIH images
Updated on 2026 / 08 / 27
Examples are valid for :
TMflow Software Version: 2.16 or above
TM Robot :HW3.2 or above only
ROS version:ROS 2 Foxy
Others:Experienced in installation and basic operation of the TM ROS driver.
The TM ROS Driver can receive source images from vision tasks (External Detection) and publish them as ROS Topics. Users can follow the steps below to proceed.
Please clone and build the TM ROS Driver repository into the corresponding workspace.
Please clone and build the TM ROS Driver repository into the corresponding workspace

Run the TM Vision ROS Driver,

Then, on the robot, create and edit a Vision Node within the flow project.

Set the vision job type to AOI-only. Configure the correct initial position and camera parameters.

Then, select "Find > External Detection" to add an external detection node to the vision workflow.

Now, configure the External Detection function. To test the connection with the TM ROS Driver, enter http://<ip address>:6189/api in the "Get" field, and then click "Send". Here, <ip address> refers to the IP address of the computer running the TM Vision ROS driver. If everything is working correctly, the text box will receive a message in JSON format. Next, set the URL for the Inference POST to http://<ip address>:6189/api/DET, and set the remaining parameters. For more information on external detection, please refer to the "Software Manual: TMvision".

The image topic (techman_image) will start publishing after the flow project runs.
{workspace}$ source ./install/setup.bash
{workspace}$ ros2 run image_sub sub_img
Additionally, users can subscribe to this image topic using their own ROS Node, or run the example program provided in the repository.


Was this article helpful ?







