Skip to content

rvarun7777/FisheyeDistanceNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 

Repository files navigation

OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving

The repository contains a boilerplate code to encourage further research in building a unified perception model for autonomous driving.

Varun Ravi Kumar, Sandesh Athni Hiremath, Markus Bach, Stefan Milz, Christian Witt, Clément Pinard, Senthil Yogamani and Patrick Mäder

Abstract

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 resampling 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. Qualitative results on an unseen fisheye video demonstrate impressive performance.

Method

Selection_137

The first row represents our ego masks as described in Section Masking Static Pixels and Ego Mask, , indicate which pixel coordinates are valid when constructing from and from respectively. The second row indicates the masking of static pixels computed after 2 epochs, where black pixels are filtered from the photometric loss (i.e. ). It prevents dynamic objects at similar speed as the ego car and low texture regions from contaminating the loss. The masks are computed for forward and backward sequences from the input sequence and reconstructed images using Eq. 11 in our paper as described in Section Masking Static Pixels and Ego Mask. The third row represents the distance estimates corresponding to their input frames. Finally, the vehicle's odometry data is used to resolve the scale factor issue.

[Full paper] [YouTube]

Demo

Quantitaive Results

Selection_138

Citation

Please use the following citation when referencing our work:

@article{kumar2019fisheyedistancenet,
  title={FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Driving},
  author={Kumar, Varun Ravi and Hiremath, Sandesh Athni and Milz, Stefan and Witt, Christian and Pinnard, Clement and Yogamani, Senthil and Mader, Patrick},
  journal={arXiv preprint arXiv:1910.04076},
  year={2019}
}