DT-SLAM: Dynamic Thresholding Based Corner Point Extraction in SLAM System

R. Wu, Matthew Pike, Boon Giin Lee

IEEE Access, June 2021

[DOI] [Cite]

R. Wu, Matthew Pike, Boon Giin Lee. 2021. DT-SLAM: Dynamic Thresholding Based Corner Point Extraction in SLAM System. In IEEE Access. DOI:https://doi.org/10.1109/ACCESS.2021.3092000

R. Wu and Matthew Pike and Boon Giin Lee. (2021). DT-SLAM: Dynamic Thresholding Based Corner Point Extraction in SLAM System. IEEE Access. https://doi.org/10.1109/ACCESS.2021.3092000

R. Wu and Matthew Pike and Boon Giin Lee. "DT-SLAM: Dynamic Thresholding Based Corner Point Extraction in SLAM System." IEEE Access, 2021. https://doi.org/10.1109/ACCESS.2021.3092000

R. Wu, Matthew Pike, Boon Giin Lee. 2021. DT-SLAM: Dynamic Thresholding Based Corner Point Extraction in SLAM System. IEEE Access. doi:10.1109/ACCESS.2021.3092000

R. Wu and Matthew Pike and Boon Giin Lee, "DT-SLAM: Dynamic Thresholding Based Corner Point Extraction in SLAM System," IEEE Access, 2021. doi: 10.1109/ACCESS.2021.3092000

@article{ieee-access-2021,
  title={DT-SLAM: Dynamic Thresholding Based Corner Point Extraction in SLAM System},
  author={R. Wu and Matthew Pike and Boon Giin Lee},
  journal={IEEE Access},
  year={2021},
  doi={10.1109/ACCESS.2021.3092000}
}

SLAM, corner point detection, localization, indoor-mapping, computer vision, image processing

Abstract

Visual localization estimation is highly dependent on the quality of video frames or captured images. Estimation quality may be affected by poor visibility, low background texture, and overexposure. Low-quality frames with blurred edges and poor contrast pose tremendous difficulties for corner point detection in SLAM, impacting the overall accuracy of estimation. This paper introduces DT-SLAM, a dynamic self-adaptive threshold (DSAT) approach for ORB corner point extraction in FAST to improve SLAM’s localization performance. The proposed method replaces the existing static threshold-based ORB extraction approach, enabling improved performance in complex real-world scenes. In addition, this study introduces a threshold switching mechanism (TSM) to replace the existing SLAM’s frame-level and cell-level thresholds for corner point extraction. The proposed DT-SLAM approach is validated using the TUM RGB-D and EuRoC benchmark datasets for location tracking performances. The results indicate that the proposed DT-SLAM outperforms the current state-of-the-art ORB-SLAM3, especially in challenging environments.