[Journal Paper] Classification of Local Eigen-Dissimilarities for Person Re-Identification
Title: Classification of Local Eigen-Dissimilarities for Person Re-Identification
Authors : Niki Martinel , Christian Micheloni
Journal: IEEE Signal Processing Letters 22 (4): 455-459, 2015
Proposed system overview. Local image dissimilarities are computed for each of the patches into which the given images are split. Then PCA
projection is applied to get the LEDs and the magnitude of them along the new basis is used to learn the parameter of the decision boundary that separates
the set of positive and negative LEDs.The task of re-identifying a person that moves across cameras fields-of-view is a challenge to the community known as the person re-identification problem.
State-of-the art approaches are either based on direct modeling and matching of the human appearance or on machine learning-based techniques.
In this work we introduce a novel approach that studies densely localized image dissimilarities in a low dimensional space and uses those to re-identify between persons in a supervised classification framework.
To achieve the goal:1) we compute the localized image dissimilarity between a pair of images;
2) we learn the lower dimensional space of such localized image dissimilarities, known as the “local eigen-dissimilarities (LEDs) space;
3) we train a binary classifier to discriminate between LEDs computed for a positive pair (images are for a same person) from the ones computed for a negative pair (images are for different persons).We show the competitive performance of our approach on two publicly available benchmark datasets.
