Publication Details
Learning Feature Aggregation in Temporal Domain for Re-Identification
Sochor Jakub, Ing., Ph.D.
Juránek Roman, Ing., Ph.D. (DCGM)
Dobeš Petr, Ing. (DCGM)
Bartl Vojtěch, Ing., Ph.D. (DCGM)
Herout Adam, prof. Ing., Ph.D. (DCGM)
person re-identification, vehicle re-identification, feature aggregation,
temporal domain, neural network, traffic surveillance
Person re-identification is a standard and established problem in the computer
vision community. In recent years, vehicle re-identification is also getting more
attention. In this paper, we focus on both these tasks and propose a method for
aggregation of features in temporal domain as it is common to have multiple
observations of the same object. The aggregation is based on weighting different
elements of the feature vectors by different weights and it is trained in an
end-to-end manner by a Siamese network. The experimental results show that our
method outperforms other existing methods for feature aggregation in temporal
domain on both vehicle and person re-identification tasks. Furthermore, to push
research in vehicle re-identification further, we introduce a novel dataset
CarsReId74k. The dataset is not limited to frontal/rear viewpoints. It contains
17,681 unique vehicles, 73,976 observed tracks, and 277,236 positive pairs. The
dataset was captured by 66 cameras from various angles.
@article{BUT161466,
author="Jakub {Špaňhel} and Jakub {Sochor} and Roman {Juránek} and Petr {Dobeš} and Vojtěch {Bartl} and Adam {Herout}",
title="Learning Feature Aggregation in Temporal Domain for Re-Identification",
journal="COMPUTER VISION AND IMAGE UNDERSTANDING",
year="2020",
volume="192",
number="11",
pages="1--12",
doi="10.1016/j.cviu.2019.102883",
issn="1077-3142",
url="https://www.sciencedirect.com/science/article/pii/S107731421830393X"
}