English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper addresses the problem of vehicle re-identification using distancecomparison of images in CNN latent spaces.  Firstly, we study the impact of the distance metrics, comparing performancesobtained with different metrics: the minimal Euclidean distance (MED), theminimal cosine distance (MCD), and the residue of the sparse codingreconstruction (RSCR). These metrics are applied using features extracted fromfive different CNN architectures, namely ResNet18, AlexNet, VGG16, InceptionV3and DenseNet201. We use the specific vehicle re-identification dataset VeRi tofine-tune these CNNs and evaluate results. In overall, independently of the CNNused, MCD outperforms MED, commonly used in the literature. These results areconfirmed on other vehicle retrieval datasets. Secondly, we extend thestate-of-the-art image-to-track process (I2TP) to a track-to-track process(T2TP). The three distance metrics are extended to measure distance betweentracks, enabling T2TP. We compared T2TP with I2TP using the same CNN models.Results show that T2TP outperforms I2TP for MCD and RSCR. T2TP combiningDenseNet201 and MCD-based metrics exhibits the best performances, outperformingthe state-of-the-art I2TP-based models. Finally, experiments highlight two mainresults: i) the impact of metric choice in vehicle re-identification, and ii)T2TP improves the performances compared to I2TP, especially when coupled withMCD-based metrics.

Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extension