Name
Abstract | ||
|---|---|---|
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: i) we compute the localized image dissimilarity between a pair of images; ii) we learn the lower dimensional space of such localized image dissimilarities, known as the “local eigen-dissimilarities” (LEDs) space; iii) 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. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/LSP.2014.2362573 | Signal Processing Letters, IEEE |
Keywords | Field | DocType |
image classification,image matching,learning (artificial intelligence),led space,benchmark dataset,binary classifier,camera fields-of-view,dimensional space,human appearance matching,local eigen-dissimilarity classification,localized image dissimilarity,machine learning-based technique,person reidentification problem,supervised classification framework,eigen-representation,pairwise appearance modeling,person re-identification,learning artificial intelligence,principal component analysis,computational modeling,measurement,light emitting diodes,vectors | Computer vision,Pattern recognition,Binary classification,Artificial intelligence,Mathematics,Principal component analysis | Journal |
Volume | Issue | ISSN |
22 | 4 | 1070-9908 |
Citations | PageRank | References |
13 | 0.51 | 25 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Niki Martinel | 1 | 349 | 24.39 |
| C. Micheloni | 2 | 934 | 62.52 |