3D depth sensors such as LIDARs and RGB-D cameras have become a popular choice for indoor localization and mapping. However, due to the lack of direct frame-to-frame correspondences, the tracking traditionally relies on the iterative closest point technique which does not scale well with the number of points. In this paper, we build on top of more recent and effcient density distribution alignment methods, and notably push the idea towards a highly effcient and reliable solution for full 6DoF motion estimation with only depth information. We propose a divide-and-conquer technique during which the estimation of the rotation and the three degrees of freedom of the translation are all decoupled from one another. The rotation is estimated absolutely and drift-free by exploiting the orthogonal structure in man-made environments. The underlying algorithm is an effcient extension of the mean-shift paradigm to manifold-constrained multiple-mode tracking. Dedicated projections subsequently enable the estimation of the translation through three simple 1D density alignment steps that can be executed in parallel. An extensive evaluation on both simulated and publicly available real datasets comparing several existing methods demonstrates outstanding performance at low computational cost.

Low-drift rotation estimation is a crucial part of any accurate odometry system. In this paper, we focus on the problem of 3D rotation estimation with dense depth sensors in environments that consist of piece-wise planar structures, such as corridors and office rooms. An efficient mean-shift paradigm is developed to extract and track planar modes in the surface normal vector distribution on the unit sphere. Robust and piecewise drift-free behavior is achieved by registering the bundle of planar modes from the current frame with respect to a reference frame using a general `1-norm regression scheme. We furthermore add a memory scheme to the regular birth and death of modes, which further compensates accumulated rotational drift when previously discovered modes are revisited. We discuss the robustness issue and evaluate our algorithm on both custom synthetic as well as real publicly available datasets. Our experimental results demonstrate high robustness and effectiveness of the proposed algorithm.

@inproceedings{zhou2016real,
  title={Real-time rotation estimation for dense depth sensors in piece-wise planar environments},
  author={Zhou, Yi and Kneip, Laurent and Li, Hongdong},
  booktitle={Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on},
  pages={2271--2278},
  year={2015},
  organization={IEEE}
  }

Determining the fundamental matrix from a collection of inter-frame homographies (more than two) is a classical problem. The compatibility relationship between the fundamental matrix and any of the ideally consistent homographies can be used to compute the fundamental matrix. Using the direct linear transformation (DLT), the compatibility equation can be translated into a least squares problem and can be easily solved via SVD decomposition. However, this solution is extremely susceptible to noise and motion inconsistencies, hence rarely used. Inspired by the normalized eight-point algorithm, we show that a relatively simple but non-trivial two-step normalization of the input homographies achieves the desired effect, and the results are at last comparable to the less attractive hallucinated points method. The algorithm is theoretically justified and verified by experiments on both synthetic and real data.

@inproceedings{zhou2015revisit,
  title={A Revisit of Methods for Determining the Fundamental Matrix with Planes},
  author={Zhou, Yi and Kneip, Laurent and Li, Hongdong},
  booktitle={Digital Image Computing: Techniques and Applications (DICTA), 2015 International Conference on},
  pages={1--7},
  year={2015},
  organization={IEEE}
  }

This paper introduces a novel strategy for real-time monocular camera tracking over the recently introduced, efficient semi-dense depth maps. We employ a geometric iterative closest point technique instead of a photometric error criterion, which has the conceptual advantage of requiring neither isotropic enlargement of the employed semidense regions, nor pyramidal subsampling. We outline the detailed concepts leading to robustness and efficiency even for large frame-to-frame disparities. We demonstrate successful real-time processing over very large view-point changes and significantly corrupted semi-dense depth-maps, thus underlining the validity of our geometric approach.

@inproceedings{BMVC2015_100,
  title={SDICP: Semi-Dense Tracking based on Iterative Closest Points},
  author={Laurent Kneip and Zhou Yi and Hongdong Li},
  year={2015},
  month={September},
  pages={100.1-100.12},
  articleno={100},
  numpages={12},
  booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
  publisher={BMVA Press},
  editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
  doi={10.5244/C.29.100},
  isbn={1-901725-53-7},
  url={https://dx.doi.org/10.5244/C.29.100}
}