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.
|Titel||IEEE International Conference on Image Processing|
|Udgivelses sted||Abu Dhabi|
|Forlag||IEEE Signal Processing Society|
|Status||Udgivet - 2020|
Lejbølle, A. R., Krogh, B., Nasrollahi, K., & Moeslund, T. B. (2020). One-to-one person re-identification for queue time estimation. I IEEE International Conference on Image Processing IEEE Signal Processing Society.