In this paper we explore ways to address the issue of dataset bias in person re-identification by using data augmentation to increase the variability of the available datasets, and we introduce a novel data augmentation method for re-identification based on changing the image background. We show that use of data augmentation can improve the cross-dataset generalisation of convolutional network based re-identification systems, and that changing the image background yields further improvements.
|Title of host publication
|Proceedings of 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
|Institute of Electrical and Electronics Engineers Inc.
|Number of pages
|Published - Aug 2015
| 3rd AMMDS Workshop - AVSS 2015: Activity Monitoring by Multiple Distributed Sensing - Karlsruhe, Germany
Duration: 25 Aug 2015 → …
|3rd AMMDS Workshop - AVSS 2015: Activity Monitoring by Multiple Distributed Sensing
|25/08/2015 → …