Pose estimation of rigid transparent objects in transparent clutter

Transparent objects are ubiquitous in human environments but, due to their special interaction with light, very few vision methods exist to identify them. We propose a new algorithm for recognition and pose estimation of rigid transparent objects which can deal with overlapping instances and cluttered environments. Using an active depth sensor for segmentation of the objects and 2d edge analysis for pose estimation, we are able to provide accurate identification and position. The proposed method is evaluated on a Microsoft Kinect and also on a PR2 robot. Results show that the algorithm is robust and accurate enough for robotic grasping and that it can be used in practical applications like table cleaning.