No version for distro foxy. Known supported distros are highlighted in the buttons above.
No version for distro eloquent. Known supported distros are highlighted in the buttons above.
No version for distro dashing. Known supported distros are highlighted in the buttons above.
No version for distro noetic. Known supported distros are highlighted in the buttons above.

asr_psm package from asr_psm repo

asr_psm

Package Summary

Tags No category tags.
Version 1.0.0
License BSD
Build type CATKIN
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/asr-ros/asr_psm.git
VCS Type git
VCS Version master
Last Updated 2019-11-14
Dev Status UNMAINTAINED
CI status No Continuous Integration
Released UNRELEASED
Package Tags No category tags.
Contributing Help Wanted (0)
Good First Issues (0)
Pull Requests to Review (0)

Package Description

This package contains a system to recognize scenes called the Probabilistic Scene Model (PSM). It uses objects and relative poses (relations) between the objects. The realations can be dynamic and each object can be a reference object. The system consists of a training subsystem that trains new scenes and a scene inference subsystem that calculates scene probabilities of previously trained scenes.

Additional Links

No additional links.

Maintainers

  • Meißner Pascal

Authors

  • Braun Kai, Gehrung Joachim, Heizmann Heinrich, Meißner Pascal
General / Acquisition:
----------------------
    1. Call "start_cameras.launch" and "start_recognition_system.launch" to start add required nodes like visualization, cameras, coordinate transformations and object detectors.
    2. When you want to record data instead of processing it online (former is necessary when learning scene models), call the script "start_recording_localizer_input_and_results.sh SEQUENCE_ID" or "start_recording_objects_only.sh SEQUENCE_ID". The resulting file is called "OBJ_SEQUENCE_ID.bag".

Scene Model Learning:
----------------------------------
    3. For getting one scene: Call "roslaunch asr_psm start_scene_graph_generation.launch scene_id:=SCENE_NAME" in launch directory. The scene graph generator started by the launch file collects all published object messages and processes them. This means that either online data or a rosbag file could be used. Press the key 'p' to publish the results.
       => Please take into account, that only one object per type in each scene is currently supported. This holds especially if objects of the same type appear across multiple trajectory recordings for one scene.
    4. Use the script "start_recording_scene_graph.sh SEQUENCE_ID" in the scripts directory to capture the output. The resulting file is called "SCENEGRAPH_SEQUENCE_ID.bag".
    5. To learn the model specify the name to the bagfile(s) in the launch file "learner.launch" and launch it with "roslaunch asr_psm learner.launch".

Inference:
----------------------------------
    6. Start the image aquisition with "roslaunch asr_psm start_cameras.launch".
    7. Start the object detectors with "roslaunch asr_psm start_recognition_system.launch".
    8. Edit the "inference.launch" file to fit your needs and launch it using the command "roslaunch asr_psm inference.launch". The results will be visualized in RVIZ, on demand a gnuplot graph showing the scene probabilities can be summoned.

CHANGELOG
No CHANGELOG found.

Wiki Tutorials

See ROS Wiki Tutorials for more details.

Source Tutorials

Not currently indexed.

Launch files

  • launch/learner.launch
    • Launches the learner for probabilistic scene models. Incoming AsrScenGraph messages are collected and being used for model learning.
  • launch/start_scene_graph_generation.launch
    • Please take into account that recognition_for_grasping does not set AsrObject identifier yet. Therefore all measured object locations of the same object type are accumulated into one trajectory even for multiple objects.
  • launch/start_cameras.launch
    • Launches the whole system for probabilistic scene recognition.
  • launch/validator.launch
    • Launches the validator, which tests the given model against the given test sets and counts false recognitions and runtime. Calculates some statistical values (average of runtime and false recognitions, ratio of false recognition against number of sets). Writes the results as csv to the given file
  • launch/tracking/start_tracking.launch
    • Launches the whole system for probabilistic scene recognition.
  • launch/go.launch
    • Launches camera and recognition system.
  • launch/combinatorial_learner.launch
    • Launches the learner for probabilistic scene models. This launch file is specifically designed for launching the learner to use combinatorial optimization to generate object relation graphs. Incoming AsrScenGraph messages are collected and being used for model learning.
  • launch/inf_screen.launch
    • Launches the inference engine for probabilistic scene recognition. Incoming AsrObject messages are being processed and the results used for scene recognition.
  • launch/inference.launch
    • Launches the inference engine for probabilistic scene recognition. Incoming AsrObject messages are being processed and the results used for scene recognition.

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged asr_psm at answers.ros.org

asr_psm package from asr_psm repo

asr_psm

Package Summary

Tags No category tags.
Version 1.0.0
License BSD
Build type CATKIN
Use RECOMMENDED

Repository Summary

Checkout URI https://github.com/asr-ros/asr_psm.git
VCS Type git
VCS Version master
Last Updated 2019-11-14
Dev Status UNMAINTAINED
CI status No Continuous Integration
Released UNRELEASED
Package Tags No category tags.
Contributing Help Wanted (0)
Good First Issues (0)
Pull Requests to Review (0)

Package Description

This package contains a system to recognize scenes called the Probabilistic Scene Model (PSM). It uses objects and relative poses (relations) between the objects. The realations can be dynamic and each object can be a reference object. The system consists of a training subsystem that trains new scenes and a scene inference subsystem that calculates scene probabilities of previously trained scenes.

Additional Links

No additional links.

Maintainers

  • Meißner Pascal

Authors

  • Braun Kai, Gehrung Joachim, Heizmann Heinrich, Meißner Pascal
General / Acquisition:
----------------------
    1. Call "start_cameras.launch" and "start_recognition_system.launch" to start add required nodes like visualization, cameras, coordinate transformations and object detectors.
    2. When you want to record data instead of processing it online (former is necessary when learning scene models), call the script "start_recording_localizer_input_and_results.sh SEQUENCE_ID" or "start_recording_objects_only.sh SEQUENCE_ID". The resulting file is called "OBJ_SEQUENCE_ID.bag".

Scene Model Learning:
----------------------------------
    3. For getting one scene: Call "roslaunch asr_psm start_scene_graph_generation.launch scene_id:=SCENE_NAME" in launch directory. The scene graph generator started by the launch file collects all published object messages and processes them. This means that either online data or a rosbag file could be used. Press the key 'p' to publish the results.
       => Please take into account, that only one object per type in each scene is currently supported. This holds especially if objects of the same type appear across multiple trajectory recordings for one scene.
    4. Use the script "start_recording_scene_graph.sh SEQUENCE_ID" in the scripts directory to capture the output. The resulting file is called "SCENEGRAPH_SEQUENCE_ID.bag".
    5. To learn the model specify the name to the bagfile(s) in the launch file "learner.launch" and launch it with "roslaunch asr_psm learner.launch".

Inference:
----------------------------------
    6. Start the image aquisition with "roslaunch asr_psm start_cameras.launch".
    7. Start the object detectors with "roslaunch asr_psm start_recognition_system.launch".
    8. Edit the "inference.launch" file to fit your needs and launch it using the command "roslaunch asr_psm inference.launch". The results will be visualized in RVIZ, on demand a gnuplot graph showing the scene probabilities can be summoned.

CHANGELOG
No CHANGELOG found.

Wiki Tutorials

See ROS Wiki Tutorials for more details.

Source Tutorials

Not currently indexed.

Launch files

  • launch/learner.launch
    • Launches the learner for probabilistic scene models. Incoming AsrScenGraph messages are collected and being used for model learning.
  • launch/start_scene_graph_generation.launch
    • Please take into account that recognition_for_grasping does not set AsrObject identifier yet. Therefore all measured object locations of the same object type are accumulated into one trajectory even for multiple objects.
  • launch/start_cameras.launch
    • Launches the whole system for probabilistic scene recognition.
  • launch/validator.launch
    • Launches the validator, which tests the given model against the given test sets and counts false recognitions and runtime. Calculates some statistical values (average of runtime and false recognitions, ratio of false recognition against number of sets). Writes the results as csv to the given file
  • launch/tracking/start_tracking.launch
    • Launches the whole system for probabilistic scene recognition.
  • launch/go.launch
    • Launches camera and recognition system.
  • launch/combinatorial_learner.launch
    • Launches the learner for probabilistic scene models. This launch file is specifically designed for launching the learner to use combinatorial optimization to generate object relation graphs. Incoming AsrScenGraph messages are collected and being used for model learning.
  • launch/inf_screen.launch
    • Launches the inference engine for probabilistic scene recognition. Incoming AsrObject messages are being processed and the results used for scene recognition.
  • launch/inference.launch
    • Launches the inference engine for probabilistic scene recognition. Incoming AsrObject messages are being processed and the results used for scene recognition.

Messages

No message files found.

Services

No service files found

Plugins

No plugins found.

Recent questions tagged asr_psm at answers.ros.org

No version for distro ardent. Known supported distros are highlighted in the buttons above.
No version for distro bouncy. Known supported distros are highlighted in the buttons above.
No version for distro crystal. Known supported distros are highlighted in the buttons above.
No version for distro lunar. Known supported distros are highlighted in the buttons above.
No version for distro jade. Known supported distros are highlighted in the buttons above.
No version for distro indigo. Known supported distros are highlighted in the buttons above.
No version for distro hydro. Known supported distros are highlighted in the buttons above.