Twisted window search for efficient shape localization

Steve Gu, Ying Zheng, Carlo Tomasi

Abstract: 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 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> ), 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.