search

NVIDIA-ISAAC-ROS / isaac_ros_depth_segmentation

NVIDIA-accelerated, deep learned depth segmentation and obstacle field ranging using Bi3D
Apache License 2.0
45 stars 8 forks source link

bi3d_output not shown #4

Closed jocacace closed 1 year ago

jocacace commented 1 year ago

Hi guys,

I am successfully able to run the example using the nvidia docker. I am using the following command:

ros2 run isaac_ros_bi3d isaac_ros_bi3d_visualizer.py \
--rosbag_path /workspaces/isaac_ros-dev/src/isaac_ros_proximity_segmentation/resources/rosbags/bi3dnode_rosbag/ \
--max_disparity_value 50

However, I am able to get the image from rqt (the input image), while I am not able to get the bi3d_output. The image windows is not open and I cannot see the result of the segmentation. Do you have any hint?

Regards,

jaiveersinghNV commented 1 year ago

The output from the Isaac ROS Bi3D node is a ROS2 DisparityImage, not a regular ROS2 Image. As a result, this output topic cannot be visualized in tools like rqt or rviz. This is why we provide the standalone isaac_ros_bi3d_visualizer.py script.