Title :
Visual recognition of a door and its knob for a humanoid robot
Author :
Kwak, Nosan ; Arisumi, Hitoshi ; YOKOI, Kazuhito
Author_Institution :
Mechatron. & Manuf. Technol. Center, Samsung Electron. Co., Ltd., Suwon, South Korea
Abstract :
This paper deals with the practical problem of how a humanoid robot recognizes a door and its knob in an office environment. This is the initial work where a humanoid robot recognizes, approaches, and opens a door. We propose an integrated solution for visual recognition of a door and its knob with minor constraints. In our approach, the door recognition is transformed into the classification problem of feature points, which can be done quickly enough to conduct it on-line. The knob is extracted by a segmentation method and a few thresholds: blob size, blob ratio, and the distance from the floor. We show in the experiment that our humanoid robot can recognize a door and its knob reliably and quickly.
Keywords :
doors; feature extraction; handles; humanoid robots; image classification; image segmentation; object recognition; robot vision; blob ratio; blob size; classification problem; door knob; door opening; feature points; humanoid robot; knob extraction; office environment; segmentation method; visual recognition; Cameras; Feature extraction; Humanoid robots; Legged locomotion; Robot vision systems; Visualization;
Conference_Titel :
Robotics and Automation (ICRA), 2011 IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-61284-386-5
DOI :
10.1109/ICRA.2011.5979608