Paper Info
Title
Finger-motion capture device with few restriction of users' movement for control of humanoid robot
Abstract
It is important to decrease restriction of users' finger motions. The purpose of this study is to develop a hand-finger motion capture device which uses a miniature camera and small single board computer to decrease restriction of users' movement. The most accurate estimations require data matching with a large database. A compact computer usually has few memory and low machine power, however. We avoided this problem by reducing frequently used image characteristics from 1,600 dimensions to 64 dimensions of characteristic quantities. This saved on memory and lowered computational cost while achieving high accuracy and speed. To enable an operator to wear the device comfortably, the camera was placed as close to the back of the hand as possible to enable handfinger estimation from images without fingertips. The result showed that the mean value and standard deviation of estimated errors in the angles of joints, and time required for processing per input image were -6.0±6.9 degree and 158.7ms, respectively for the conventional system, whereas they were -5.7±7.2degree and 25.0ms, respectively for our system. The results obtained from the experiments suggested that the same level of high-accuracy and the time required for processing can be considerably reduced.
Year
DOI
Venue
2016
10.1109/ICIT.2016.7474729
2016 IEEE International Conference on Industrial Technology (ICIT)
Keywords
Field
DocType
wearable hand capture,hand-finger shape estimation,dimension compression of image characteristic quantity,hand-finger image with no fingertip,robot control
Motion capture,Computer vision,Mean value,Simulation,Finger tracking,Single-board computer,Operator (computer programming),Artificial intelligence,Engineering,Standard deviation,Humanoid robot
Conference
Citations 
PageRank 
References 
0
0.34
6
Authors
2
Name
Order
Citations
PageRank
Motomasa Tomida163.95
Kiyoshi Hoshino26122.33