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.

BibTeX

@TechReport{dorettoWSRT07tr,
  Title                    = {Shape and appearance context modeling: {A} fast framework for matching the appearance of people},
  Author                   = {Doretto, G. and Wang, X. and Sebastian, T. B. and Rittscher, J. and Tu, P.},
  Institution              = {GE Global Research},
  Year                     = {2007},
  Address                  = {Niskayuna, NY, USA},
  Month                    = {June},
  Note                     = {Visualization and Computer Vision Laboratory},
  Number                   = {2007GRC594},
  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.},
  Bib2html_pubtype         = {Tech Reports},
  Bib2html_rescat          = {Video Surveillance, Integral Image Computations, Appearance Modeling, Shape and Appearance Modeling, Track Matching},
  File                     = {dorettoWSRT07tr.pdf:doretto\\report\\dorettoWSRT07tr.pdf:PDF;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},
  Timestamp                = {2007.01.20}
}