Abstract
Measuring queue times at an airport check-point is essential in order to regulate staff allocation and maintain a low queue time. In this paper, we propose a method to measure queue times based on person re-identification. Specifically, we cap- ture passenger features from entrance and exit points of an air- port check-point and match features to determine queue times of passengers. However, a passenger seen at the entrance po- tentially can be matched to multiple passengers seen at the exit. Therefore, to increase the precision of re-identification, we propose a simple, yet effective, assignment algorithm that assigns each passenger seen at the exit to only a single pas- senger seen at the entrance. Through experiments on a dataset collected from an airport immigration check-point, we show that our proposed assignment increases precision and recall by 22 % and 16 %, respectively, to naively assigning the best match.
Originalsprog | Engelsk |
---|---|
Titel | 2020 IEEE International Conference on Image Processing (ICIP) |
Antal sider | 5 |
Udgivelsessted | Abu Dhabi |
Forlag | IEEE Signal Processing Society |
Publikationsdato | 2020 |
Artikelnummer | 9191293 |
ISBN (Trykt) | 978-1-7281-6394-9, 978-1-7281-6396-3 |
ISBN (Elektronisk) | 978-1-7281-6395-6 |
DOI | |
Status | Udgivet - 2020 |
Begivenhed | 2020 IEEE International Conference on Image Processing (ICIP) - Abu Dhabi, United Arab Emirates Varighed: 25 okt. 2020 → 28 okt. 2020 |
Konference
Konference | 2020 IEEE International Conference on Image Processing (ICIP) |
---|---|
Land/Område | United Arab Emirates |
By | Abu Dhabi |
Periode | 25/10/2020 → 28/10/2020 |
Navn | IEEE International Conference on Image Processing (ICIP) |
---|---|
ISSN | 2381-8549 |