San Francisco World: Leveraging Structural Regularities of Slope for 3-DoF Visual Compass

IEEE RA-L Submission
Jungil Ham1*, Minji Kim1, Suyoung Kang2, Kyungdon Joo3, Haoang Li4, Pyojin Kim1†
1 Gwangju Institute of Science and Technology (GIST) 2 Sookmyung Women’s University 3 UNIST 4 Hong Kong University of Science and Technology
Paper Video Code Video for Response Letter

Supplementary Video for the Response Letter

Abstract

We propose the San Francisco world (SFW) model, a novel structural model inspired by San Francisco’s hilly terrain. Our SFW consists of a single vertical dominant direction (VDD), two horizontal dominant directions (HDDs), and four sloping dominant directions (SDDs) sharing a common inclination angle. Leveraging the structural regularities of SFW, such as uniform inclination angle and geometric patterns of the four SDDs, we design an efficient and robust DD/vanishing point estimation method by aggregating sloping line normals on the Gaussian sphere. We further utilize the structural patterns of SFW for the 3-DoF visual compass, the rotational motion tracking from a single line and plane, which corresponds to the theoretical minimal sampling for 3-DoF rotation estimation. Our method demonstrates enhanced adaptability in more challenging scenes and the highest rotational tracking accuracy compared to state-of-the-art methods.

BibTeX

@article{ham2024sfw,
  author    = {Jungil Ham, Minji Kim, Suyoung Kang, Kyungdon Joo, Haoang Li, Pyojin Kim},
  title     = {San Francisco World: Leveraging Structural Regularities of Slope for 3-DoF Visual Compass},
  journal   = {arXiv preprint arXiv:2403.15951},
  year      = {2024},
}