Learning feature aggregation in temporal domain for re-identification

• Published in: Computer vision and image understanding Vol. 192; p. 102883
• Main Authors: Špaňhel, Jakub, Sochor, Jakub, Juránek, Roman, Dobeš, Petr, Bartl, Vojtěch, Herout, Adam
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01-03-2020
• Subjects: 68T45; 68U10; 68T10; 62M45
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2019.102883

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.
•The novel method for object re-id using feature aggregation in temporal domain – LFTD.•The novel challenging dataset for visual vehicle re-identification called CarsReId74k.•The comparison of different feature weighting methods for object re-identification.•The novel Euclidean-based metric for feature vector comparison.