Agent-based moving object correspondence using differential discriminative diagnosis

Abstract
We propose a novel method for temporally and spa- tially corresponding moving objects by automatically learning the relevance of the objects' appearance features to the task of discrimination. Efficient correspondence is achieved by enforcing temporal consistency of the rele- vances for a particular object. Relevances are learned using a technique we have termed "differential discrimi- native diagnosis." An agent is assigned to each moving object in the scene. The agent possesses the basic capabil- ity to decide whether or not an object in the scene is the one it represents. Each agent customizes itself to the object by means of differential discriminative diagnosis as the object persists in the scene. We explain this correspon- dence scheme as applied to the task of corresponding mov- ing people in a surveillance system.

This publication has 13 references indexed in Scilit: