Title | ||
---|---|---|
Video Sequences Association for People Re-identification across Multiple Non-overlapping Cameras |
Abstract | ||
---|---|---|
This paper presents a solution of the appearance-based people re-identification problem in a surveillance system including multiple cameras with different fields of vision. We first utilize different color-based features, combined with several illuminant invariant normalizations in order to characterize the silhouettes in static frames. A graph-based approach which is capable of learning the global structure of the manifold and preserving the properties of the original data in a lower dimensional representation is then introduced to reduce the effective working space and to realize the comparison of the video sequences. The global system was tested on a real data set collected by two cameras installed on board a train. The experimental results show that the combination of color-based features, invariant normalization procedures and the graph-based approach leads to very satisfactory results. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-04146-4_21 | ICIAP |
Keywords | Field | DocType |
original data,illuminant invariant normalization,people re-identification,different color-based feature,graph-based approach,global structure,global system,color-based feature,multiple non-overlapping cameras,invariant normalization procedure,different field,video sequences association | Graph,Computer vision,Normalization (statistics),Dimensionality reduction,Global structure,Pattern recognition,Computer science,Standard illuminant,Artificial intelligence,Invariant (mathematics),Nonlinear dimensionality reduction,Manifold | Conference |
Volume | ISSN | Citations |
5716 | 0302-9743 | 30 |
PageRank | References | Authors |
1.14 | 14 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dung Nghi Truong Cong | 1 | 53 | 4.14 |
Catherine Achard | 2 | 158 | 19.60 |
Louahdi Khoudour | 3 | 117 | 14.20 |
Lounis Douadi | 4 | 44 | 2.59 |