Accelerating pattern matching or how much can you slide?

Authors:
Ofir Pele;Michael Werman
Affiliations:
School of Computer Science and Engineering, The Hebrew University of Jerusalem;School of Computer Science and Engineering, The Hebrew University of Jerusalem
Venue:
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Year:
2007

Citing 5
Cited 1

Non-parametric local transforms for computing visual correspondence

ECCV '94 Proceedings of the third European conference on Computer Vision (Vol. II)
Digital Image Processing

Digital Image Processing
Computing 2-D Min, Median, and Max Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Performance Evaluation of Local Descriptors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Keypoint Recognition Using Randomized Trees

IEEE Transactions on Pattern Analysis and Machine Intelligence

Tracking pedestrian with multi-component online deformable part-based model

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a method that accelerates pattern matching. The distance between a pattern and a window is usually close to the distance of the pattern to the adjacement windows due to image smoothness. We show how to exploit this fact to reduce the running time of pattern matching by adaptively sliding the window often by more than one pixel. The decision how much we can slide is based on a novel rank we define for each feature in the pattern. Implemented on a Pentium 4 3GHz processor, detection of a pattern with 7569 pixels in a 640 × 480 pixel image requires only 3.4ms.