Eduardo Borges

Eduardo Borges

Robotics and Computer Vision

Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

The Impact of Loss Functions and Architectures in Object Re-Identification: A Comparative Study

👨🏻‍🏫 Published in 24th International Conference on Robotics, Automation and Mobile Robotics (ROBOT), 2025

📝 A comprehensive evaluation of loss functions and backbone architectures for RGB and depth-based object re-identification on the KITTI-ReID dataset, highlighting the strengths of transformer models and contrastive losses for robust MOT pipelines.

Recommended citation: L. Garrote, E. Borges, A. Mendes and U. J. Nunes (2025). "The Impact of Loss Functions and Architectures in Object Re-Identification: A Comparative Study." 24th International Conference on Robotics, Automation and Mobile Robotics (ROBOT), 2025.

DepthTriFusion: A Three-Stream RGB-LiDAR-Normal Pipeline for Depth Estimation

👨🏻‍🏫 Published in 24th International Conference on Robotics, Automation and Mobile Robotics (ROBOT), 2025

📝 A three-stream multimodal depth estimation architecture that fuses RGB, LiDAR and surface normals to deliver more accurate and structurally consistent depth maps for autonomous mobile robots.

Recommended citation: M. Abreu, E. Borges, L. Garrote, A. Mendes and U. J. Nunes (2025). "DepthTriFusion: A Three-Stream RGB–LiDAR–Normal Pipeline for Depth Estimation." 24th International Conference on Robotics, Automation and Mobile Robotics (ROBOT), 2025.

Safer and Trustworthier Navigation of Automated Vehicles

👨🏻‍🏫 Published in 25th International Conference on Control Systems and Computer Science (CSCS), 2025

📝 A framework for safer and more trustworthy automated driving that combines robust object detection under adverse weather, risk-aware trajectory planning in camera networks, and template-based natural-language explanations for navigation decisions.

Recommended citation: M. Aleksandrov, K. Yordanova, E. Borges, D. Soares, T. Barros and C. Premebida (2025). "Safer and Trustworthier Navigation of Automated Vehicles." 25th International Conference on Control Systems and Computer Science (CSCS), Bucharest, Romania, 2025, pp. 183-189, doi: 10.1109/CSCS66924.2025.00035.
Download Paper | Download Bibtex

A Modular Multimodal Multi-Object Tracking-by-Detection Approach, with Applications in Outdoor and Indoor Environments

👨🏻‍🏫 Published in 21st International Conference on Informatics in Control, Automation and Robotics (ICINCO), 2024

📝 A modular multimodal tracking-by-detection system for autonomous mobile robots that fuses 3D point-cloud (PointPillars + AB3DMOT) and 2D (YOLOv8) detectors to improve multi-object detection and tracking robustness — validated on KITTI.

Recommended citation: Borges, E., Garrote, L., Nunes, U. J. (2024). "A Modular Multimodal Multi-Object Tracking-by-Detection Approach, with Applications in Outdoor and Indoor Environments." In Proceedings of the 21st International Conference on Informatics in Control, Automation and Robotics (ICINCO 2024) - Volume 2
Download Paper | Download Bibtex