Abstract | ||
---|---|---|
Person re-identification tackles the problem whether an observed person of interest reappears in a network of cameras. The difficulty primarily originates from few samples per class but large amounts of intra-class variations in real scenarios: illumination, pose and viewpoint changes across cameras. So far, proposals in the literature have treated this either as a matching problem focusing on feature representation or as a classification/ranking problem relying on metric optimization. This paper presents a new way called Common-Near-Neighbor Analysis, which to some extent combines the strengths of these two methodologies. It analyzes the commonness of the near neighbors of each pair of samples in a learned metric space, measured by a novel rank-order based dissimilarity. Our method, using only color cue, has been tested on widely-used benchmark datasets, showing significant performance improvement over the state-of-the-art. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ICIP.2012.6467186 | ICIP |
Keywords | Field | DocType |
metric optimization,optimisation,feature representation,image matching,lighting,color cue,camera network,ranking problem,performance improvement,common-nearneighbor analysis,image recognition,widely-used benchmark datasets,metric learning,intraclass variations,biometrics (access control),feature extraction,image classification,classification problem,cameras,person re-identification,matching problem,common-near-neighbor analysis,novel rank-order based dissimilarity,illumination,pose changes,viewpoint changes,person reidentification,illumination changes,real scenarios,image colour analysis | Computer vision,Biometrics access control,Ranking,Pattern recognition,Image matching,Computer science,Feature extraction,Artificial intelligence,Metric space,Contextual image classification,Performance improvement | Conference |
ISSN | ISBN | Citations |
1522-4880 E-ISBN : 978-1-4673-2532-5 | 978-1-4673-2532-5 | 20 |
PageRank | References | Authors |
0.75 | 5 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei Li | 1 | 59 | 5.16 |
Yang Wu | 2 | 20 | 0.75 |
Masayuki Mukunoki | 3 | 199 | 21.86 |
Michihiko Minoh | 4 | 349 | 58.69 |