Multi-Camera Person Re-Identification Based on Trajectory Data
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 custo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/20/11578 |
| _version_ | 1797574797820952576 |
|---|---|
| author | Diogo Mendes Simão Correia Pedro Jorge Tomás Brandão Patrícia Arriaga Luís Nunes |
| author_facet | Diogo Mendes Simão Correia Pedro Jorge Tomás Brandão Patrícia Arriaga Luís Nunes |
| author_sort | Diogo Mendes |
| collection | DOAJ |
| description | 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%. |
| first_indexed | 2024-03-10T21:27:13Z |
| format | Article |
| id | doaj.art-366e9fe315584f6bb52bd45c0be13b98 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T21:27:13Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-366e9fe315584f6bb52bd45c0be13b982023-11-19T15:34:09ZengMDPI AGApplied Sciences2076-34172023-10-0113201157810.3390/app132011578Multi-Camera Person Re-Identification Based on Trajectory DataDiogo Mendes0Simão Correia1Pedro Jorge2Tomás Brandão3Patrícia Arriaga4Luís Nunes5ISCTE—University Institute of Lisbon, 1649-026 Lisbon, PortugalISCTE—University Institute of Lisbon, 1649-026 Lisbon, PortugalISCTE—University Institute of Lisbon, 1649-026 Lisbon, PortugalISCTE—University Institute of Lisbon, 1649-026 Lisbon, PortugalISCTE—University Institute of Lisbon, 1649-026 Lisbon, PortugalISCTE—University Institute of Lisbon, 1649-026 Lisbon, PortugalThis 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%.https://www.mdpi.com/2076-3417/13/20/11578person re-identificationtrajectorymulti-cameraobject detectionobject trackingcomputer vision |
| spellingShingle | Diogo Mendes Simão Correia Pedro Jorge Tomás Brandão Patrícia Arriaga Luís Nunes Multi-Camera Person Re-Identification Based on Trajectory Data Applied Sciences person re-identification trajectory multi-camera object detection object tracking computer vision |
| title | Multi-Camera Person Re-Identification Based on Trajectory Data |
| title_full | Multi-Camera Person Re-Identification Based on Trajectory Data |
| title_fullStr | Multi-Camera Person Re-Identification Based on Trajectory Data |
| title_full_unstemmed | Multi-Camera Person Re-Identification Based on Trajectory Data |
| title_short | Multi-Camera Person Re-Identification Based on Trajectory Data |
| title_sort | multi camera person re identification based on trajectory data |
| topic | person re-identification trajectory multi-camera object detection object tracking computer vision |
| url | https://www.mdpi.com/2076-3417/13/20/11578 |
| work_keys_str_mv | AT diogomendes multicamerapersonreidentificationbasedontrajectorydata AT simaocorreia multicamerapersonreidentificationbasedontrajectorydata AT pedrojorge multicamerapersonreidentificationbasedontrajectorydata AT tomasbrandao multicamerapersonreidentificationbasedontrajectorydata AT patriciaarriaga multicamerapersonreidentificationbasedontrajectorydata AT luisnunes multicamerapersonreidentificationbasedontrajectorydata |