Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/29667
Autoria: | Mendes, D. Correia, S. Jorge, P. Brandão, T. Arriaga, P. Nunes, L. |
Data: | 2023 |
Título próprio: | Multi-camera person re-identification based on trajectory data |
Título da revista: | Applied Sciences |
Volume: | 13 |
Número: | 20 |
Referência bibliográfica: | Mendes, D., Correia, S., Jorge, P., Brandão, T., Arriaga, P., & Nunes, L. (2023). Multi-camera person re-identification based on trajectory data. Applied Sciences, 13(20), 11578. https://dx.doi.org/10.3390/app132011578 |
ISSN: | 2076-3417 |
DOI (Digital Object Identifier): | 10.3390/app132011578 |
Palavras-chave: | Person re-identification Trajectory Multi-camera Object detection Object tracking Computer vision |
Resumo: | This study presents a trajectory-based person re-identification algorithm, embedded in a tool to detect and track customers present in a large retail store, in a multi-camera environment. The customer trajectory data are obtained from video surveillance images captured by multiple cameras, and customers are detected and tracked along the frames that compose the videos. Due to the characteristics of a multi-camera environment or the occurrence of occlusions, caused by objects such as shelves or counters, different identifiers are assigned to each person when, in fact, they should be identified with a unique identifier. Thus, the proposed tool tries to solve this problem in a scenario where there are constraints in using images of people due to data privacy concerns. The results show that our method was able to correctly re-identify the customers present in the store with a re-identification rate of 82%. |
Arbitragem científica: | yes |
Acesso: | Acesso Aberto |
Aparece nas coleções: | CIS-RI - Artigos em revistas científicas internacionais com arbitragem científica ISTAR-RI - Artigos em revistas científicas internacionais com arbitragem científica |
Ficheiros deste registo:
Ficheiro | Tamanho | Formato | |
---|---|---|---|
article_98448.pdf | 3,2 MB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.