In video surveillance, person re-identification (re-id) is probably the open challenge, when dealing with a camera network with non-overlapped fields of view. Re-id allows the association of different instances of the same person across different locations and time. A large number of approaches have emerged in the last 5 years, often proposing novel visual features specifically designed to highlight the most discriminant aspects of people, which are invariant to pose, scale and illumination. In this chapter, we follow this line, presenting a strategy with three important keycharacteristics that differentiate it with respect to the state of the art: (1) a symmetrydriven method to automatically segment salient body parts, (2) an accumulation of features making the descriptormore robust to appearance variations, and (3) a person re-identification procedure casted as an image retrieval problem, which can be easily embedded into a multi-person tracking scenario, as the observation model.
File in questo prodotto:
Non ci sono file associati a questo prodotto.