Shape and appearance context modeling: A fast framework for matching the appearance of people

Doretto, G., Wang, X., Sebastian, T. B., Rittscher, J., and Tu, P.
Shape and appearance context modeling: A fast framework for matching the appearance of people. Technical Report 2007GRC594, GE Global Research, 2007. Visualization and Computer Vision Laboratory

Download

(unavailable)

Abstract

In this work we develop appearance models for computing the similarity between image regions containing deformable objects of a given class in realtime. We introduce the concept of shape and appearance context. The main idea is to model the spatial distribution of the appearance relative to each of the object parts. Estimating the model entails computing occurrence matrices. We introduce a generalization of the integral image and integral histogram frameworks, and prove that it can be used to dramatically speed up occurrence computation. We demonstrate the ability of this framework to recognize an individual walking across a network of cameras. Finally, we show that the proposed approach outperforms several other methods.

@TECHREPORT{dorettoWSRT07tr,
  author = {Doretto, G. and Wang, X. and Sebastian, T. B. and Rittscher, J. and
	Tu, P.},
  title = {Shape and appearance context modeling: {A} fast framework for matching
	the appearance of people},
  institution = {GE Global Research},
  year = {2007},
  number = {2007GRC594},
  address = {Niskayuna, NY, USA},
  month = {June},
  note = {Visualization and Computer Vision Laboratory},
  bib2html_pubtype = {Tech Reports},
  bib2html_rescat = {Video Surveillance, Integral Image Computations, Appearance Modeling,
	Shape and Appearance Modeling, Track Matching},
  abstract = {In this work we develop appearance models for computing the similarity
	between image regions containing deformable objects of a given class
	in realtime. We introduce the concept of shape and appearance context.
	The main idea is to model the spatial distribution of the appearance
	relative to each of the object parts. Estimating the model entails
	computing occurrence matrices. We introduce a generalization of the
	integral image and integral histogram frameworks, and prove that
	it can be used to dramatically speed up occurrence computation. We
	demonstrate the ability of this framework to recognize an individual
	walking across a network of cameras. Finally, we show that the proposed
	approach outperforms several other methods.},
  file = {dorettoWSRT07tr.pdf:doretto\\report\\dorettoWSRT07tr.pdf:PDF},
  keywords = {integral image, integral histogram, integral computation, co-occurrence
	matrix, correlogram, appearance modeling, bag-of-features, histogram
	of oriented gradients, occurrence, appearance context, shape context,
	shape and appearance context, person reacquisition, person reidentification,
	track linking},
  owner = {doretto},
  pdf = {doretto\report\dorettoWSRT07tr.pdf},
  timestamp = {2007.01.20}
}

Generated by bib2html.pl (written by Patrick Riley )