Generating object hypotheses in natural scenes through human-robot interaction

We propose a method for interactive modeling ofobjects and object relations based on real-time segmentation ofvideo sequences. In interaction with a human, the robot canperform multi-object segmentation through principled model-ing of physical constraints. The key contribution is an efficientmulti-labeling framework, that allows object modeling anddisambiguation in natural scenes. Object modeling and labelingis done in a real-time, to which hypotheses and constraintsdenoting relations between objects can be added incrementally.Through instructions such as key presses or spoken words, ascene can be segmented in regions corresponding to multiplephysical objects. The approach solves some of the difficultproblems related to disambiguation of objects merged due totheir direct physical contact. Results show that even a limited setof simple interactions with a human operator can substantiallyimprove segmentation results.© 2011 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. QC 2011110