SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras

04/09/2021
by   Varun Ravi Kumar, et al.
17

A 360 perception of scene geometry is essential for automated driving, notably for parking and urban driving scenarios. Typically, it is achieved using surround-view fisheye cameras, focusing on the near-field area around the vehicle. The majority of current depth estimation approaches focus on employing just a single camera, which cannot be straightforwardly generalized to multiple cameras. The depth estimation model must be tested on a variety of cameras equipped to millions of cars with varying camera geometries. Even within a single car, intrinsics vary due to manufacturing tolerances. Deep learning models are sensitive to these changes, and it is practically infeasible to train and test on each camera variant. As a result, we present novel camera-geometry adaptive multi-scale convolutions which utilize the camera parameters as a conditional input, enabling the model to generalize to previously unseen fisheye cameras. Additionally, we improve the distance estimation by pairwise and patchwise vector-based self-attention encoder networks. We evaluate our approach on the Fisheye WoodScape surround-view dataset, significantly improving over previous approaches. We also show a generalization of our approach across different camera viewing angles and perform extensive experiments to support our contributions. To enable comparison with other approaches, we evaluate the front camera data on the KITTI dataset (pinhole camera images) and achieve state-of-the-art performance among self-supervised monocular methods. An overview video with qualitative results is provided at https://youtu.be/bmX0UcU9wtA. Baseline code and dataset will be made public.

READ FULL TEXT

page 1

page 4

page 5

page 7

page 10

research
03/16/2018

Monocular Fisheye Camera Depth Estimation Using Semi-supervised Sparse Velodyne Data

Near field depth estimation around a self driving car is an important fu...
research
04/07/2022

SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation

Depth estimation from images serves as the fundamental step of 3D percep...
research
08/10/2020

SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving

State-of-the-art self-supervised learning approaches for monocular depth...
research
07/13/2020

UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Models

In classical computer vision, rectification is an integral part of multi...
research
04/03/2019

CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth

Single-view depth estimation suffers from the problem that a network tra...
research
11/13/2018

Self-Supervised Learning of Depth and Camera Motion from 360° Videos

As 360 cameras become prevalent in many autonomous systems (e.g., self-d...
research
06/08/2022

Learning Ego 3D Representation as Ray Tracing

A self-driving perception model aims to extract 3D semantic representati...

Please sign up or login with your details

Forgot password? Click here to reset