Deep recurrent visual place recognition based on softmax fine-tuned image representations
Engineering review · 29.07.2026 · 46 (2)
DOI: 10.30765/er.3383 ↗Kurz gefasst
Fachartikel in der Zeitschrift Engineering review, online erschienen am 29.07.2026. Verfasst von Jurica Maltar und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Visual place recognition aims to identify previously visited locations from image representations that are robust to viewpoint and environmental changes. Deep convolutional neural network features perform well for this task, yet they are typically pretrained for classification or segmentation – objectives that do not account for the sequential nature of place recognition. In mobile robotics, exploiting image sequences can further improve performance. We propose softmax-based fine-tuning of a convolutional network extended with a recurrent model to enhance place recognition on image sequences. Experiments on two public datasets show that the proposed representation consistently outperforms competing approaches across all evaluated methods.
Zitieren
APA
Maltar, J., Marković, I., Matijević, D., & Petrović, I. (2026). Deep recurrent visual place recognition based on softmax fine-tuned image representations. Engineering review, 46(2). https://doi.org/10.30765/er.3383
Vancouver
Maltar J, Marković I, Matijević D, Petrović I. Deep recurrent visual place recognition based on softmax fine-tuned image representations. Engineering review. 2026;46(2). doi:10.30765/er.3383
BibTeX
@article{Maltar2026,
author = {Maltar, Jurica and Marković, Ivan and Matijević, Domagoj and Petrović, Ivan},
title = {Deep recurrent visual place recognition based on softmax fine-tuned image representations},
journal = {Engineering review},
year = {2026},
volume = {46},
number = {2},
doi = {10.30765/er.3383}
}
EUVIMED