We are excited to announce that our research group has successfully published two new papers in recent weeks, showcasing our latest advancements in imagery-based position estimation and acoustic localization.

Our first paper, titled “Enhancing the Accuracy of Aerial Imagery-Based Object Position Estimation,” was published at the International Conference on Pattern Recognition (ICPR) 2026. Authored by Zsombor Páncsics, Csaba Marosi, Zsombor Széplaki, Zoltán Berényi, Gergely Treplán, Szende Sándor, Levente Hajder, and Imre Benedek Juhász, this research presents new methods for improving the precision of object position estimation using aerial imagery. 🔗 Read the full paper on Springer

Additionally, our work on audio-based detection, “ALEV: Acoustic Localization of Emergency Vehicles at Extreme SNR via Attention U-Net Denoising and Particle-Filtered DOA Estimation,” has been accepted and published at the 17th International Conference on Information, Intelligence, Systems & Applications (IISA). Congratulations to authors Tarlan Ahadli, Levente Hajder, and Bandó Kovács for their excellent work on this challenging topic. 🔗 Read the full paper on IEEE Xplore

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Explore More

Videótár

Önvezető rendszerek fejlesztése az ELTE Informatikai Karán – Nyílt Nap 2023.01.20. Computer Vision Research at the ELTE Faculty of Informatics GCVG bemutatkozó videó Relative planar motion for vehicle-mounted cameras from

Ongoing project: horizon line detection

We are pleased to announce the launch of our latest research initiative focusing on automated horizon line detection. Accurate horizon estimation is a fundamental challenge in computer vision, playing a

Fast Surface Normal Estimation from Affine Transformations

We have a novel paper, accepted for ICCV2023. Authors: Levente Hajder, Lajos Lóczi, Daniel Barath Abstract We present a new solver for estimating a surface normal from a single affine