Twisted window search for efficient shape localization


Journal Article

Many computer vision systems approximate targets' shape with rectangular bounding boxes. This choice trades localization accuracy for efficient computation. We propose twisted window search, a strict generalization over rectangular window search, for the globally optimal localization of a target's shape. Despite its generality, we show that the new algorithm runs in O(n 3), an asymptotic time complexity that is no greater than that of rectangular window search on an image of resolution n × n. We demonstrate improved results of twisted window search for localizing and tracking non-rigid objects with significant orientation, scale and shape change. Twisted window search runs at nearly 10 frames per second in our MATLAB/C implementation on images of resolution 240 × 320 on a quad-core laptop. © 2012 IEEE.

Full Text

Duke Authors

Cited Authors

  • Gu, S; Zheng, Y; Tomasi, C

Published Date

  • October 1, 2012

Published In

Start / End Page

  • 167 - 173

International Standard Serial Number (ISSN)

  • 1063-6919

Digital Object Identifier (DOI)

  • 10.1109/CVPR.2012.6247672

Citation Source

  • Scopus