Shape and Appearance Context Modeling

TLDR

The study introduces shape and appearance context and develops appearance models to compute similarity between image regions of deformable objects in real time. The authors model the spatial distribution of appearance relative to object parts, estimate the model via occurrence matrices, and generalize integral image and histogram frameworks to accelerate computation. The framework successfully recognizes individuals across camera networks and outperforms several existing methods.

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.