Title :
Figure/ground segregation from human cues
Author :
Arsenio, Artur M.
Author_Institution :
Comput. Sci. & Artificial Intelligence Lab., MIT, Cambridge, MA, USA
fDate :
28 Sept.-2 Oct. 2004
Abstract :
This paper presents a new embodied approach for object segmentation by a humanoid robot. It relies on interactions with a human teacher that drives the robot through the process of segmenting objects from arbitrarily complex, non-static images. Objects from a large spectrum of different scenarios were successfully segmented by the proposed algorithms.
Keywords :
active vision; humanoid robots; image segmentation; robot vision; figure segregation; ground segregation; human cue; humanoid robot; object segmentation; Actuators; Books; Computer science; Humanoid robots; Humans; Image segmentation; Layout; Object detection; Object segmentation; Robustness;
Conference_Titel :
Intelligent Robots and Systems, 2004. (IROS 2004). Proceedings. 2004 IEEE/RSJ International Conference on
Print_ISBN :
0-7803-8463-6
DOI :
10.1109/IROS.2004.1389917
