DocumentCode :
662732
Title :
Gesture recognition for moving RGB-D sensor
Author :
Hanguen Kim ; Soon-Hyuk Hong ; Soo Hyung Kim ; Youn, Pillip ; Seonjin Ha ; Hyun Myung
Author_Institution :
Dept. of Civil & Environ. Eng., KAIST (Korea Adv. Inst. of Sci. & Technol.), Daejeon, South Korea
fYear :
2013
fDate :
24-26 Oct. 2013
Firstpage :
1
Lastpage :
3
Abstract :
Many studies have been conducted to achieve natural interaction between robots and humans. Except for a few works, however, most gesture recognition algorithms are designed with an assumption that the sensor does not move. To resolve this problem, we propose an algorithm that can robustly recognize gestures while the robot is moving.
Keywords :
gesture recognition; human-robot interaction; image sensors; mobile robots; robot vision; gesture recognition algorithms; human-robot interaction; moving RGB-D sensor; Image segmentation; Integrated optics; Optical imaging; Optical sensors; Real-time systems; Robustness; Gesture recognition; Motion context; Multi-layer perceptron; Skeleton extraction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Robotics (ISR), 2013 44th International Symposium on
Conference_Location :
Seoul
Type :
conf
DOI :
10.1109/ISR.2013.6695628
Filename :
6695628
Link To Document :
بازگشت