IRAF-SLAM: An Illumination-Robust and Adaptive Feature-Culling Front-End for Visual SLAM in Challenging Environments

TL;DR

IRAF-SLAM introduces an adaptive front-end with image enhancement, dynamic feature extraction, and feature culling to improve visual SLAM robustness in challenging lighting conditions, reducing failures and increasing accuracy.

Contribution

This paper presents IRAF-SLAM, a novel adaptive front-end for vSLAM that enhances robustness against illumination changes through image preprocessing, dynamic feature detection, and reliable feature filtering.

Findings

Significantly reduces tracking failures in adverse lighting.

Achieves higher trajectory accuracy compared to existing methods.

Effective in complex environments with dynamic objects and low texture.

Abstract

Robust Visual SLAM (vSLAM) is essential for autonomous systems operating in real-world environments, where challenges such as dynamic objects, low texture, and critically, varying illumination conditions often degrade performance. Existing feature-based SLAM systems rely on fixed front-end parameters, making them vulnerable to sudden lighting changes and unstable feature tracking. To address these challenges, we propose ``IRAF-SLAM'', an Illumination-Robust and Adaptive Feature-Culling front-end designed to enhance vSLAM resilience in complex and challenging environments. Our approach introduces: (1) an image enhancement scheme to preprocess and adjust image quality under varying lighting conditions; (2) an adaptive feature extraction mechanism that dynamically adjusts detection sensitivity based on image entropy, pixel intensity, and gradient analysis; and (3) a feature culling strategy that filters out unreliable feature points using density distribution analysis and a lighting impact factor. Comprehensive evaluations on the TUM-VI and European Robotics Challenge (EuRoC) datasets demonstrate that IRAF-SLAM significantly reduces tracking failures and achieves superior trajectory accuracy compared to state-of-the-art vSLAM methods under adverse illumination conditions. These results highlight the effectiveness of adaptive front-end strategies in improving vSLAM robustness without incurring significant computational overhead. The implementation of IRAF-SLAM is publicly available at https://thanhnguyencanh. github.io/IRAF-SLAM/.