D2.1 Report on user behavior
V. Charissi, M. Lohse, C. Zaga, V. Evers - University of Twente
This deliverable presents the first results of WP 2 (Robust User Interaction in Crowded Environments). It addresses mainly T2.1 (User Behavior Analysis and Scenario Definition) based on a contextual analysis on children's
collaborative play (without robot) and a first user study on children's engagement with a robot. It also includes a first corpus of annotated data from the first user study.
Object relation dataset
S. Krivic - University of Innsbruck
This dataset contains the set of possible object-object spatial relations. Learning object-object relations is a difficult problem with sparse, noisy, corrupted and incomplete information which makes it an interesting and challenging machine learning problem. We formulate this problem as the problem of learning missing edges in a multigraph.
TUW Toy Models Dataset
This website provides models of various toys learned using a mobile robot with an Asus Xtion Pro Live. Each model consists of a point cloud of the complete object and the set of all training views with their poses relative to the first view and with a segmentation mask per view. The dataset also contains mesh models for some of the objects.
The model database consists of 19 objects, where some objects are modelled more than once in different poses (lying on different sides). The database contains rigid (plastic) as well as soft (plush animals) objects.
TUW Object Instance Recognition Dataset
This website provides annotated RGB-D point clouds of indoor environments. The TUW dataset contains sequences of point clouds in 15 static and 3 partly dynamic environments. Each view of a scene presents multiple objects; some object instances occur multiple times and are highly occluded in certain views. The model database consists of 17 models with a maximum extent of 30 cm, which are partly symmetric and/or lack distinctive surface texture. The dataset consists of the reconstructed 3D object models, the individual key frames of the models, test scenes and the 6DOF pose of each object present in the respective view. Each point cloud is represented by RGB color, depth and normal information.
Furthermore, we provide annotation for the Willow and Challenge dataset.