PCR-ORB: Enhanced ORB-SLAM3 with Point Cloud Refinement Using Deep Learning-Based Dynamic Object Filtering

TL;DR

PCR-ORB enhances ORB-SLAM3 by integrating deep learning-based point cloud refinement and multi-stage filtering to improve SLAM accuracy in dynamic environments, demonstrating significant improvements in certain scenarios.

Contribution

This work introduces a novel integration of deep learning-based point cloud refinement into ORB-SLAM3, employing real-time semantic segmentation and multi-stage filtering to mitigate dynamic object interference.

Findings

Significant improvement in ATE RMSE on KITTI sequence 04 (25.9%)

30.4% improvement in ATE median in specific sequences

Mixed performance across different environmental conditions

Abstract

Visual Simultaneous Localization and Mapping (vSLAM) systems encounter substantial challenges in dynamic environments where moving objects compromise tracking accuracy and map consistency. This paper introduces PCR-ORB (Point Cloud Refinement ORB), an enhanced ORB-SLAM3 framework that integrates deep learning-based point cloud refinement to mitigate dynamic object interference. Our approach employs YOLOv8 for semantic segmentation combined with CUDA-accelerated processing to achieve real-time performance. The system implements a multi-stage filtering strategy encompassing ground plane estimation, sky region removal, edge filtering, and temporal consistency validation. Comprehensive evaluation on the KITTI dataset (sequences 00-09) demonstrates performance characteristics across different environmental conditions and scene types. Notable improvements are observed in specific sequences, with sequence 04 achieving 25.9% improvement in ATE RMSE and 30.4% improvement in ATE median. However, results show mixed performance across sequences, indicating scenario-dependent effectiveness. The implementation provides insights into dynamic object filtering challenges and opportunities for robust navigation in complex environments.