Balancing Speed and Accuracy: A Comparative Analysis of Segment Anything-Based Models for Robotic Indoor Semantic Mapping

Bruno G. Ferreira, Bruno G. Ferreira, Bruno G. Ferreira, Bruno G. Ferreira, Armando Sousa, Armando Sousa, Luis Paulo Reis, Luis Paulo Reis

2025

Abstract

Semantic segmentation is a relevant process for creating the rich semantic maps required for indoor navigation by autonomous robots. While foundation models like Segment Anything Model (SAM) have significantly advanced the field by enabling object segmentation without prior references, selecting an efficient variant for real-time robotics applications remains a challenge due to the trade-off between performance and accuracy. This paper evaluates three such variants - FastSAM, MobileSAM, and SAM 2 - comparing their speed and accuracy to determine their suitability for semantic mapping tasks. The models were assessed within the Robot@VirtualHome dataset across 30 distinct scenes, with performance quantified using Frames Per Second (FPS), Precision, Recall, and an Over-Segmentation metric, which quantifies the fragmentation of an object into multiple masks, preventing high quality semantic segmentation. The results reveal distinct performance profiles: FastSAM achieves the highest speed but exhibits poor precision and significant mask fragmentation. Conversely, SAM 2 provides the highest precision but is computationally intensive for real-time applications. MobileSAM emerges as the most balanced model, delivering high recall, good precision, and viable processing speed, with minimal over-segmentation. We conclude that MobileSAM offers the most effective trade-off between segmentation quality and efficiency, making it a good candidate for indoor semantic mapping in robotics.

Paper Citation

in Harvard Style

Ferreira B., Sousa A. and Reis L. (2025). Balancing Speed and Accuracy: A Comparative Analysis of Segment Anything-Based Models for Robotic Indoor Semantic Mapping. In Proceedings of the 22nd International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO; ISBN 978-989-758-770-2, SciTePress, pages 321-328. DOI: 10.5220/0013778500003982

in Bibtex Style

@conference{icinco25,
author={Bruno Ferreira and Armando Sousa and Luis Reis},
title={Balancing Speed and Accuracy: A Comparative Analysis of Segment Anything-Based Models for Robotic Indoor Semantic Mapping},
booktitle={Proceedings of the 22nd International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO},
year={2025},
pages={321-328},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013778500003982},
isbn={978-989-758-770-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 22nd International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO
TI - Balancing Speed and Accuracy: A Comparative Analysis of Segment Anything-Based Models for Robotic Indoor Semantic Mapping
SN - 978-989-758-770-2
AU - Ferreira B.
AU - Sousa A.
AU - Reis L.
PY - 2025
SP - 321
EP - 328
DO - 10.5220/0013778500003982
PB - SciTePress