Improving vehicle re‐identification using CNN latent spaces: Metrics comparison and track‐to‐track extension - Archive ouverte HAL Access content directly
Journal Articles IET Computer Vision Year : 2021

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

Sylvie Chambon
Vincent Charvillat
  • Function : Author
  • PersonId : 964946
  • IdRef : 07812459X
Alain Crouzil
André Péninou

Abstract

Herein, the problem of vehicle re-identification using distance comparison of images in CNN latent spaces is addressed. First, the impact of the distance metrics, comparing performances obtained with different metrics is studied: 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. Overall, independently of the CNN used, MCD outperforms MED, commonly used in the literature. These results are confirmed on other vehicle retrieval datasets. Second, the state-of-the-art image-to-track process (I2TP) is extended to a track-to-track process (T2TP). The three distance metrics are extended to measure distance between tracks, enabling T2TP. T2TP and I2TP are compared 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 with I2TP, especially when coupled with MCD-based metrics.
Fichier principal
Vignette du fichier
cvi2.12010.pdf (1.12 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

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

Licence

Attribution - NonCommercial - NoDerivatives

Identifiers

Cite

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-03126045v2⟩
387 View
199 Download

Altmetric

Share

Gmail Facebook X LinkedIn More