ROS package that can filter geometry defined in URDF models from Kinect depth images. Can also preprocess data for the OpenNI tracker, to remove backgrounds, robots etc.
Other
89
stars
46
forks
source link
How can I use realtime_urdf_filter.launch in PR2? #4
I changed original launch file and wrote as below, but the /openni/depth_registered_filtered/image_rect wasn't published as we expected.(We expected the arm pointclouds are removed.)
We also changed the filter parameters sometimes, but it didn't make a difference.
How should change the setting or is there anything we need to do other than this?
fixed_frame: /world
camera_frame: /openni_rgb_optical_frame
camera_offset:
translation: [0.0, 0.0, 0.0]
rotation: [0.0, 0.0, 0.0, 1.0]
# There is one entry for each URDIF that should be filtered
models:
- model: "robot_description"
tf_prefix: ""
# how far in front of the robot model is still deleted? (e.g. 0.05 = 5cm)
depth_distance_threshold: 0.05
show_gui: true
filter_replace_value: 5.0
The output image is below.
Top windows is show_gui's view and bottom window shows /openni/depth_registered_filtered/image_rect.
I changed original launch file and wrote as below, but the /openni/depth_registered_filtered/image_rect wasn't published as we expected.(We expected the arm pointclouds are removed.)
We also changed the filter parameters sometimes, but it didn't make a difference. How should change the setting or is there anything we need to do other than this?
realtime_urdf_filter.launch
fillter_paramters.xml
The output image is below. Top windows is show_gui's view and bottom window shows /openni/depth_registered_filtered/image_rect.
Thanks.