You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi!
First of all thanks for providing such a framework!
I face the problem that the object recognition of the coca cola from the tutorial [1] results in an segmentation fault, sometimes immediately, sometimes after a couple seconds. If the object detections runs a couple seconds it actually looks quite good (tables are detected and all coca cola cans).
Sometimes it crashes before it publishes anything, sometimes after it starts to publish /tabletop/clusters. So it is pretty random.
Same happens if I just run the tabletop detector from the tutorial [1].
I installed the whole object recognition kitchen via apt-get install ros-indigo-object-recognition-*.
Any ideas or recommendations?
Does anyone have the same setup - Gazebo Simulation and ORK?
Attached the output of an example where it worked 5-10 seconds. rosrun object_recognition_core detection -crospack find object_recognition_tabletop`/conf/detection.object.ros.ork
[ INFO] [1464289564.666542750]: Initialized ROS. node_name: /object_recognition_server
[ INFO] [1464289564.846052493]: System already initialized. node_name: /object_recognition_server
[ INFO] [1464289565.088817256]: System already initialized. node_name: /object_recognition_server
[ INFO] [1464289565.093691792]: Subscribed to topic:/camera/depth_registered/camera_info [queue_size: 1][tcp_nodelay: 0]
[ INFO] [1464289565.095981799]: Subscribed to topic:/camera/rgb/camera_info [queue_size: 1][tcp_nodelay: 0]
[ INFO] [1464289565.097790576]: Subscribed to topic:/camera/depth_registered/image_raw [queue_size: 1][tcp_nodelay: 0]
[ INFO] [1464289565.099613283]: Subscribed to topic:/camera/rgb/image_color [queue_size: 1][tcp_nodelay: 0]
Hi!
First of all thanks for providing such a framework!
I face the problem that the object recognition of the coca cola from the tutorial [1] results in an segmentation fault, sometimes immediately, sometimes after a couple seconds. If the object detections runs a couple seconds it actually looks quite good (tables are detected and all coca cola cans).
Sometimes it crashes before it publishes anything, sometimes after it starts to publish /tabletop/clusters. So it is pretty random.
Same happens if I just run the tabletop detector from the tutorial [1].
I installed the whole object recognition kitchen via apt-get install ros-indigo-object-recognition-*.
Any ideas or recommendations?
Does anyone have the same setup - Gazebo Simulation and ORK?
Attached the output of an example where it worked 5-10 seconds.
rosrun object_recognition_core detection -c
rospack find object_recognition_tabletop`/conf/detection.object.ros.ork[ INFO] [1464289564.666542750]: Initialized ROS. node_name: /object_recognition_server
[ INFO] [1464289564.846052493]: System already initialized. node_name: /object_recognition_server
[ INFO] [1464289565.088817256]: System already initialized. node_name: /object_recognition_server
[ INFO] [1464289565.093691792]: Subscribed to topic:/camera/depth_registered/camera_info [queue_size: 1][tcp_nodelay: 0]
[ INFO] [1464289565.095981799]: Subscribed to topic:/camera/rgb/camera_info [queue_size: 1][tcp_nodelay: 0]
[ INFO] [1464289565.097790576]: Subscribed to topic:/camera/depth_registered/image_raw [queue_size: 1][tcp_nodelay: 0]
[ INFO] [1464289565.099613283]: Subscribed to topic:/camera/rgb/image_color [queue_size: 1][tcp_nodelay: 0]
126 :: 0.5 , 1 , 0.995004 , /base_link , /head_mount_kinect_rgb_optical_frame
[ INFO] [1464289567.148092868]: publishing to topic:/tabletop/clusters
[ INFO] [1464289567.148537079]: publishing to topic:/table_array
No models found for method "mesh"
[ INFO] [1464289567.195154380]: publishing to topic:/recognized_object_array
Segmentation fault (core dumped)
`
[1] http://wg-perception.github.io/ork_tutorials/tutorial02/tutorial.html
The text was updated successfully, but these errors were encountered: