The Journal of Korea Robotics Society (로봇학회논문지)

Korea Robotics Society (한국로봇학회)
권호 표지
DOI QR코드

DOI QR Code

Photorealistic Real-Time Dense 3D Mesh Mapping for AUV

자율 수중 로봇을 위한 사실적인 실시간 고밀도 3차원 Mesh 지도 작성

  • Jungwoo Lee (Dept. Electrical and Computer Engineering, Inha University) ;
  • Younggun Cho (Dept. Electrical and Computer Engineering, Inha University)
  • Received : 2024.01.19
  • Accepted : 2024.03.13
  • Published : 2024.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a photorealistic real-time dense 3D mapping system that utilizes a neural network-based image enhancement method and mesh-based map representation. Due to the characteristics of the underwater environment, where problems such as hazing and low contrast occur, it is hard to apply conventional simultaneous localization and mapping (SLAM) methods. At the same time, the behavior of Autonomous Underwater Vehicle (AUV) is computationally constrained. In this paper, we utilize a neural network-based image enhancement method to improve pose estimation and mapping quality and apply a sliding window-based mesh expansion method to enable lightweight, fast, and photorealistic mapping. To validate our results, we utilize real-world and indoor synthetic datasets. We performed qualitative validation with the real-world dataset and quantitative validation by modeling images from the indoor synthetic dataset as underwater scenes.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (RS2023-00302589), Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2022-0-00448) and the Korea Institute of Marine Science and Technology Promotion (KIMST), funded by the Ministry of Oceans and Fisheries (20210562).

References

  1. Y. Cho, Y.-S. Shin, and A. Kim, "Online depth estimation and application to underwater image dehazing," OCEANS 2016 MTS/IEEE Monterey, Monterey, USA, pp. 1-7, 2016, DOI: 10.1109/OCEANS.2016.7761109.
  2. G. Yang, G. Kang, J. Lee, and Y. Cho, "Joint-ID: Transformer-based Joint Image Enhancement and Depth Estimation for Underwater Environments," IEEE Sensors Journal, vol. 24, no. 3, pp. 3113-3122, Feb., 2023, DOI: 10.1109/JSEN.2023.3338730.
  3. R. A. Newcombe, S. Izadi AU, O. Hilliges, D. Molyneaux, D. Kim, A. J. Davison, P. Kohi, J. Shotton, S. Hodges, and A. Fitzgibbon, "KinectFusion: Real-time dense surface mapping and tracking," 2011 10th IEEE International Symposium on Mixed and Augmented Reality, Basel, Switzerland, pp. 127-136, 2011, DOI: 10.1109/ISMAR.2011.6092378.
  4. H. Oleynikova, Z. Taylor, M. Fehr, R. Siegwart, and J. Nieto, "Voxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning," 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, pp. 1366-1373, 2017, DOI: 10.1109/IROS.2017.8202315.
  5. A. Rosinol, T. Sattler, M. Pollefeys, and L. Carlone, "Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities," 2019 International Conference on Robotics and Automation (ICRA), Montreal, Canada, pp. 8220-8226, 2019, DOI: 10.1109/ICRA.2019.8794456.
  6. R. Mur-Artal and J. D. Tardos, "ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras," IEEE Transactions on Robotics, vol. 33, no. 5, pp. 1255-1262, Oct., 2017, DOI: 10.1109/TRO.2017.2705103.
  7. A. Bowyer, "Computing Dirichlet tessellations," The Computer Journal, vol. 24, no. 2, pp. 162-166, Jan., 1981, DOI: 10.1093/comjnl/24.2.162.
  8. J. Shi and Tomasi, "Good features to track," 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 593-600, 1994, DOI: 10.1109/CVPR.1994.323794.
  9. Y. Randall and T. Treibitz, "Flsea: Underwater visual-inertial and stereo-vision forward-looking datasets," arXiv:2302.12772, 2023, DOI: 10.48550/arXiv.2302.12772.
  10. A. Handa, T. Whelan, J. McDonald and A. J. Davison, "A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM," 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, China, pp. 1524-153, 2014, DOI: 10.1109/ICRA.2014.6907054.
  11. J. Y. Chiang and Y.-C. Chen, "Underwater image enhancement by wavelength compensation and dehazing," IEEE Trans. Image Process., vol. 21, no. 4, pp. 1756-1769, Apr., 2012, DOI: 10.1109/TIP.2011.2179666.
  12. MichaelGrupp, [Online], https://github.com/MichaelGrupp/evo, Accessed: Jun. 02, 2023.