Skip to content

Fast features for time constrained object detection

by Gary Overett, Lars Petersson
2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 ()
Get full text at journal

Abstract

This paper concerns itself with the development and design of fast features suitable for time constrained object detection. Primarily we consider three aspects of feature design; the form of the precomputed datatype (e.g. the integral image), the form of the features themselves (i.e. the measurements made of an image), and the models/weak- learners used to construct weak classifiers (class, non-class statistics). The paper is laid out as a guide to feature designers, demonstrating how appropriate choices in combining the above three characteristics can prevent bottlenecks in the run-time evaluation of classifiers. This leads to reductions in the computational time of the features themselves and, by providing more discriminant features, reductions in the time taken to reach specific classification error rates. Results are compared using variants of the well known Haar-like feature types, Rectangular Histogram of Oriented Gradient (RHOG) features and a special set of Histogram of Oriented Gradient features which are highly optimized for speed. Experimental results suggest the adoption of this set of features for time-critical applications. Time-constrained comparisons are presented using pedestrian and road sign detection problems. Comparison results are presented on time-error plots, which are a replacement of the traditional ROC performance curves.

Cite this document (BETA)

Readership Statistics

29 Readers on Mendeley
by Discipline
 
79% Computer Science
 
14% Engineering
 
3% Agricultural and Biological Sciences
by Academic Status
 
38% Student > Ph. D. Student
 
24% Student > Master
 
21% Researcher
by Country
 
3% Australia
 
3% Russia
 
3% United Kingdom

Sign up today - FREE

Mendeley saves you time finding and organizing research. Learn more

  • All your research in one place
  • Add and import papers easily
  • Access it anywhere, anytime

Start using Mendeley in seconds!

Sign up & Download

Already have an account? Sign in