[Documentation] [TitleIndex] [WordIndex

Only released in EOL distros:  

tabletop_object_perception: active_realtime_segmentation | fast_plane_detection | object_recognition_gui | object_segmentation_gui | tabletop_collision_map_processing | tabletop_object_detector

pr2_object_manipulation: active_realtime_segmentation | fast_plane_detection | manipulation_worlds | object_recognition_gui | object_segmentation_gui | pick_and_place_demo_app | pr2_create_object_model | pr2_grasp_adjust | pr2_gripper_grasp_controller | pr2_gripper_grasp_planner_cluster | pr2_gripper_reactive_approach | pr2_gripper_sensor_action | pr2_gripper_sensor_controller | pr2_gripper_sensor_msgs | pr2_handy_tools | pr2_interactive_gripper_pose_action | pr2_interactive_manipulation | pr2_interactive_object_detection | pr2_manipulation_controllers | pr2_marker_control | pr2_navigation_controllers | pr2_object_manipulation_launch | pr2_object_manipulation_msgs | pr2_pick_and_place_demos | pr2_pick_and_place_tutorial | pr2_tabletop_manipulation_launch | pr2_wrappers | rgbd_assembler | robot_self_filter_color | segmented_clutter_grasp_planner | tabletop_collision_map_processing | tabletop_object_detector | tf_throttle

Package Summary

A package for interactive object segmentation.


This package provides a graphical user interface in form of an rviz plugin for interactive object segmentation. The segmentation method comes from the active_realtime_segmentation package. This iterative methods needs initialisation of object hypotheses. In this interactive segmentation scenario, this is provided by the user through clicks or selection of rectangular regions. The GUI also provides the possibilities to change the parameters of the segmentation method.

Example Inputs and Results

Here is an example initialisation on RGB-D data from the textured light stereo on the PR2 and the corresponding result. Color information from the wide-field stereo is ported to the monochrome narrow-stereo of PR2 through the rgbd_assembler package.

PR2_Stereo_init.jpg PR2_stereo.jpg

Here are examples for RGB-D data collected from the kinect.

kinect_init.jpg kinect_result.jpg

2024-05-25 13:14