# Integrating voxel mapping with deep network-based point-line feature fusion for robust SLAM

## TL;DR

This paper improves visual SLAM systems by combining voxel mapping and deep learning to better handle low-texture and unstructured environments.

## Contribution

The novel integration of custom voxel mapping and a depth map neural network enhances feature fusion and robustness in SLAM.

## Key findings

- Combining voxel mapping with sparse SLAM improves matching robustness and 3D reconstruction in low-texture regions.
- Fusion of point and line features via a neural network boosts joint feature matching efficiency and localization accuracy.
- The method shows improved environmental adaptability in challenging real-world scenarios.

## Abstract

The present study addresses the issues of feature loss and map consistency in visual SLAM under low-texture, low-light, and unstructured scenes by proposing an improved system based on ORB-SLAM3. The following innovative features are worthy of note: Firstly, a combination of custom voxel mapping and sparse SLAM is proposed for the purpose of enhancing matching robustness and 3D reconstruction quality in low-texture regions. Secondly, the utilization of a depth map neural network for the fusion of point and line features is suggested. Tests on public datasets and other unstructured scenes demonstrate that this method significantly improves joint feature matching efficiency, validating the complementary advantages of point and line features. The results indicate a considerable boost in both localization accuracy and environmental adaptability in challenging scenarios, setting the foundation for more reliable SLAM applications in real-world conditions.