Home // PATTERNS 2015, The Seventh International Conferences on Pervasive Patterns and Applications // View article

The Effect of 2nd-Order Shape Prediction on Tracking non-Rigid Object

Authors:
Kenji Nishida
Takumi Kobayashi
Jun Fujiki

Keywords: Tracking non-rigid objects, Chamfer distance, Shape prediction.

Abstract:
For the tracking of non-rigid objects, we have previously proposed a shape-based predict-and-track algorithm. The method was built upon the similarity between the predicted and actual object shapes. The object shape was predicted from the movement of feature points, which were approximated by a second-order Taylor expansion. Approximate first-order movements, the so-called optical flows, were simultaneously exploited by chamfer matching of edgelets. In this paper, the effect of second-order shape prediction is quantitatively analyzed by tracking a non-rigid skier object. The method exhibits superior shape prediction performance compared to a simple linear prediction method.

Pages: 60 to 63

Copyright: Copyright (c) IARIA, 2015

Publication date: March 22, 2015

Published in: conference

ISSN: 2308-3557

ISBN: 978-1-61208-393-3

Location: Nice, France

Dates: from March 22, 2015 to March 27, 2015