Title :
Visual object recognition for robot tasks in real-life scenarios
Author :
Martinez-Martin, Ester ; del Pobil, Angel P.
Author_Institution :
Dept. of Eng. & Comput. Sci., Univ. Jaume-I, Castellon, Spain
fDate :
Oct. 30 2013-Nov. 2 2013
Abstract :
On the way to autonomous robotic systems, key issues are object detection and recognition. In this paper, we aim at robustly detecting and recognizing different objects in real-life scenarios from a visual input when robot manipulation is the goal task. For that, and based on the human vision system performance, the system computes object´s colour, motion and shape cues and combines them in a probabilistic manner to accurately achieve object identification and recognition task. More-over, a Graphical Processing Unit (GPU) is used to fulfill the requirement for real-time visual data processing. In addition, it has been implemented and tested on a robotic platform.
Keywords :
dexterous manipulators; graphics processing units; image colour analysis; image motion analysis; object detection; object recognition; probability; robot vision; GPU; autonomous robotic systems; graphical processing unit; human vision system performance; object colour cues; object detection; object identification; object motion cues; object shape cues; probability; real-life scenarios; real-time visual data processing; robot manipulation; robot tasks; visual input; visual object recognition; object recognition; robotics; visual processing;
Conference_Titel :
Ubiquitous Robots and Ambient Intelligence (URAI), 2013 10th International Conference on
Conference_Location :
Jeju
Print_ISBN :
978-1-4799-1195-0
DOI :
10.1109/URAI.2013.6677413
