Fisheye cameras are commonly used in applications like autonomous driving and surveillance to provide a large field of view 180°. However, they come at the cost of strong non-linear distortions which require more complex algorithms. In this paper, we explore Euclidean distance estimation on fisheye cameras for automotive scenes. Obtaining accurate and dense depth supervision is difficult in practice, but self-supervised learning approaches show promising results and could potentially overcome the problem. We present a novel self-supervised scale-aware framework for learning Euclidean distance and ego-motion from raw monocular fisheye videos without applying rectification. While it is possible to perform piece-wise linear approximation of fisheye projection surface and apply standard rectilinear models, it has its own set of issues like re-sampling distortion and discontinuities in transition regions. To encourage further research in this area, we will release our dataset as part of the WoodScape project. We further evaluated the proposed algorithm on the KITTI dataset and obtained state-of-the-art results comparable to other self-supervised monocular methods.

@inproceedings{ravikumar2020fisheyedistancenet,

  title   = {{Fisheyedistancenet: Self-supervised scale-aware distance estimation using monocular fisheye camera for autonomous driving}},

  author    = {Ravi Kumar, Varun and Hiremath, Sandesh Athni and Bach, Markus and Milz, Stefan and Witt, Christian and Pinard, Cl{\'e}ment and Yogamani, Senthil and M{\"a}der, Patrick},

  year      = 2020,

  booktitle = {2020 IEEE International Conference on Robotics and Automation (ICRA)},

  pages     = {574--581},

  organization = {IEEE}

}