Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.30765/er.3383

Deep recurrent visual place recognition based on softmax fine-tuned image representations

Jurica Maltar ; J. J. Strossmayer University of Osijek, School of Applied Mathematics and Informatics, Osijek, Croatia *
Ivan Marković ; University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia
Domagoj Matijević ; J. J. Strossmayer University of Osijek, School of Applied Mathematics and Informatics, Osijek, Croatia
Ivan Petrović ; University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Croatia

* Dopisni autor.


Puni tekst: engleski pdf 1.046 Kb

preuzimanja: 0

citiraj


Sažetak

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.

Ključne riječi

visual place recognition; deep convolutional neural networks; recurrent neural networks; softmax regression; SeqSLAM

Hrčak ID:

349926

URI

https://hrcak.srce.hr/349926

Datum izdavanja:

29.7.2026.

Posjeta: 0 *