Tracking-based Interactive Segmentation of Textureless Objects
This paper describes an object segmentation ap-
proach for autonomous (humanoid) service robots acting in
human living environments. The proposed system allows a robot
to effectively segment textureless objects in cluttered scenes by
leveraging its manipulation capabilities. In this approach, the
cluttered scenes are first statically segmented using part-graph-
based hashing and then the interactive perception is deployed in
order to resolve possibly ambiguous static segmentation. In the
second step the RGBD (RGB + Depth) features, estimated on
the RGBD point cloud from the Kinect sensor, are extracted and
tracked while the motion is induced into a scene. The resulting
tracked feature trajectories are then assigned to their correspond-
ing object by using a graph-based clustering algorithm, which
edges measure the distance dissimilarity between the tracked
RGBD features. In the final step, dense model reconstruction
based on region growing algorithm is applied. We evaluated the
approach on a set of scenes which consist of various textureless
flat (e.g. box-like) and round (e.g. cylinder-like) objects and the
combination thereof.
On this page of the site you can watch the video online Tracking-based Interactive Segmentation of Textureless Objects with a duration of hours minute second in good quality, which was uploaded by the user iasTUMUNICH 16 September 2012, share the link with friends and acquaintances, this video has already been watched 1,421 times on youtube and it was liked by 6 viewers. Enjoy your viewing!
