Improving vehicle re‐identification using CNN latent spaces: Metrics comparison and track‐to‐track extension - Computational Imaging and Vision Accéder directement au contenu
Article Dans Une Revue IET Computer Vision Année : 2021

Improving vehicle re‐identification using CNN latent spaces: Metrics comparison and track‐to‐track extension

Patrice Guyot
Sylvie Chambon
Vincent Charvillat
  • Fonction : Auteur
  • PersonId : 964946
  • IdRef : 07812459X
Alain Crouzil
André Péninou

Résumé

This paper addresses the problem of vehicle re-identification using distance comparison of images in CNN latent spaces.Firstly, we study the impact of the distance metrics, comparing performances obtained with different metrics: the minimal Euclidean distance (MED), the minimal cosine distance (MCD), and the residue of the sparse coding reconstruction (RSCR). These metrics are applied using features extracted from five different CNN architectures, namely ResNet18, AlexNet, VGG16, InceptionV3 and DenseNet201. We use the specific vehicle re-identification dataset VeRi to fine-tune these CNNs and evaluate results. In overall, independently of the CNN used, MCD outperforms MED, commonly used in the literature. These results are confirmed on other vehicle retrieval datasets. Secondly, we extend the state-of-the-art image-to-track process (I2TP) to a track-to-track process (T2TP). The three distance metrics are extended to measure distance between tracks, enabling T2TP. We compared T2TP with I2TP using the same CNN models. Results show that T2TP outperforms I2TP for MCD and RSCR. T2TP combining DenseNet201 and MCD-based metrics exhibits the best performances, outperforming the state-of-the-art I2TP-based models. Finally, experiments highlight two main results: i) the impact of metric choice in vehicle re-identification, and ii) T2TP improves the performances compared to I2TP, especially when coupled with MCD-based metrics.
Fichier principal
Vignette du fichier
Improving vehicle re‐identification using CNN latent spaces.pdf (1004.65 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03126045 , version 1 (29-03-2021)
hal-03126045 , version 2 (15-11-2021)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

Citer

Geoffrey Roman Jimenez, Patrice Guyot, Thierry Malon, Sylvie Chambon, Vincent Charvillat, et al.. Improving vehicle re‐identification using CNN latent spaces: Metrics comparison and track‐to‐track extension. IET Computer Vision, 2021, 15 (2), pp.85-98. ⟨10.1049/cvi2.12010⟩. ⟨hal-03126045v1⟩

Collections

SMS
386 Consultations
196 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More