Name
Title | ||
|---|---|---|
Evaluation of multi feature fusion at score-level for appearance-based person re-identification |
Abstract | ||
|---|---|---|
Robust appearance-based person re-identification can only be achieved by combining multiple diverse features describing the subject. Since individual features perform different, it is not trivial to combine them. Often this problem is bypassed by concatenating all feature vectors and learning a distance metric for the combined feature vector. However, to perform well, metric learning approaches need many training samples which are not available in most real-world applications. In contrast, in our approach we perform score-level fusion to combine the matching scores of different features. To evaluate which score-level fusion techniques perform best for appearance-based person re-identification, we examine several score normalization and feature weighting approaches employing the the widely used and very challenging VIPeR dataset. Experiments show that in fusing a large ensemble of features, the proposed score-level fusion approach outperforms linear metric learning approaches which fuse at feature-level. Furthermore, a combination of linear metric learning and score-level fusion even outperforms the currently best non-linear kernel-based metric learning approaches, regarding both accuracy and computation time. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/IJCNN.2015.7280360 | 2015 International Joint Conference on Neural Networks (IJCNN) |
Keywords | Field | DocType |
multifeature fusion,robust appearance-based person re-identification,multiple diverse feature,feature vector,distance metric,score-level fusion,matching score,feature weighting approach,nonlinear kernel-based metric learning approach | Kernel (linear algebra),Weighting,Feature vector,Normalization (statistics),Pattern recognition,Computer science,Feature (computer vision),Metric (mathematics),Feature extraction,Artificial intelligence,Concatenation,Machine learning | Conference |
ISSN | Citations | PageRank |
2161-4393 | 8 | 0.49 |
References | Authors | |
15 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Markus Eisenbach | 1 | 37 | 6.76 |
| Alexander Kolarow | 2 | 35 | 2.95 |
| Alexander Vorndran | 3 | 8 | 0.49 |
| Julia Niebling | 4 | 8 | 0.49 |
| Horst-Michael Gross | 5 | 761 | 92.05 |