New Zealand Journal of Agricultural Research abstracts
An efficient method for processing a large-scale motion database in
agriculture informatisation
Jian Xiang
ZheJiang University of Science and Technology
310023, Hangzhou
PR China
freexiang@gmail.com
Abstract In this paper, a novel approach is presented for
motion information retrieval based on a reference index that reduces
the number of costly distance computations for similar measures. Due to
high dimensionality of motion’s features, the nonlinear Principal
Component Analysis (PCA) dimension reduction is used. An algorithmic
framework is used to approximate the optimal mapping function by a
Radial Basis Function (RBF) for handling new data. Then, a reference
index is built based on selecting a small set of representative motion
clips in the database. This way we can get a candidate set by
abandoning most unrelated motion clips to reduce the number of costly
similarity measures significantly. Experimental results show that our
methods are effective for data processing in large-scale databases of
agriculture informatisation.
Keywords agriculture informatisation;
motion; nonlinear PCA;
RBF; reference index
A07064; Online publication date 4 December 2007; Received and
accepted 10 August 2007
New Zealand Journal of Agricultural Research, 2007, Vol. 50:
573–581
0028–8233/07/5005–0573 © The Royal Society of New Zealand 2007
PDF file of entire paper: Print-quality
(1286K) | screen-quality (501K)
This year's abstracts |
Journal home page |
All abstracts |
Publishing home page
