Back to articles
Articles
Volume: 33 | Article ID: art00011
Image
FisheyeDistanceNet++: Self-Supervised Fisheye Distance Estimation with Self-Attention, Robust Loss Function and Camera View Generalization
  DOI :  10.2352/ISSN.2470-1173.2021.17.AVM-181  Published OnlineJanuary 2021
Abstract

FisheyeDistanceNet [1] proposed a self-supervised monocular depth estimation method for fisheye cameras with a large field of view (> 180°). To achieve scale-invariant depth estimation, FisheyeDistanceNet supervises depth map predictions over multiple scales during training. To overcome this bottleneck, we incorporate self-attention layers and robust loss function [2] to FisheyeDistanceNet. A general adaptive robust loss function helps obtain sharp depth maps without a need to train over multiple scales and allows us to learn hyperparameters in loss function to aid in better optimization in terms of convergence speed and accuracy. We also ablate the importance of Instance Normalization over Batch Normalization in the network architecture. Finally, we generalize the network to be invariant to camera views by training multiple perspectives using front, rear, and side cameras. Proposed algorithm improvements, FisheyeDistanceNet++, result in 30% relative improvement in RMSE while reducing the training time by 25% on the WoodScape dataset. We also obtain state-of-the-art results on the KITTI dataset, in comparison to other self-supervised monocular methods.

Subject Areas :
Views 229
Downloads 113
 articleview.views 229
 articleview.downloads 113
  Cite this article 

Varun Ravi Kumar, Senthil Yogamani, Stefan Milz, Patrick Mäder, "FisheyeDistanceNet++: Self-Supervised Fisheye Distance Estimation with Self-Attention, Robust Loss Function and Camera View Generalizationin Proc. IS&T Int’l. Symp. on Electronic Imaging: Autonomous Vehicles and Machines,  2021,  pp 181-1 - 181-11,  https://doi.org/10.2352/ISSN.2470-1173.2021.17.AVM-181

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2021
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
IS&T 7003 Kilworth Lane, Springfield, VA 22151 USA