Capturing Omni-Range Context for Omnidirectional Segmentation

03/09/2021
by   Kailun Yang, et al.
8

Convolutional Networks (ConvNets) excel at semantic segmentation and have become a vital component for perception in autonomous driving. Enabling an all-encompassing view of street-scenes, omnidirectional cameras present themselves as a perfect fit in such systems. Most segmentation models for parsing urban environments operate on common, narrow Field of View (FoV) images. Transferring these models from the domain they were designed for to 360-degree perception, their performance drops dramatically, e.g., by an absolute 30.0 FoV and structural distribution between the imaging domains, we introduce Efficient Concurrent Attention Networks (ECANets), directly capturing the inherent long-range dependencies in omnidirectional imagery. In addition to the learned attention-based contextual priors that can stretch across 360-degree images, we upgrade model training by leveraging multi-source and omni-supervised learning, taking advantage of both: Densely labeled and unlabeled data originating from multiple datasets. To foster progress in panoramic image segmentation, we put forward and extensively evaluate models on Wild PAnoramic Semantic Segmentation (WildPASS), a dataset designed to capture diverse scenes from all around the globe. Our novel model, training regimen and multi-source prediction fusion elevate the performance (mIoU) to new state-of-the-art results on the public PASS (60.2 (69.0

READ FULL TEXT

page 1

page 3

page 5

page 6

page 8

research
09/17/2019

DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing

Semantically interpreting the traffic scene is crucial for autonomous tr...
research
10/24/2018

The UAVid Dataset for Video Semantic Segmentation

Video semantic segmentation has been one of the research focus in comput...
research
01/31/2020

Universal Semantic Segmentation for Fisheye Urban Driving Images

Semantic segmentation is a critical method in the field of autonomous dr...
research
10/03/2022

Masked Supervised Learning for Semantic Segmentation

Self-attention is of vital importance in semantic segmentation as it ena...
research
08/12/2021

Memory-based Semantic Segmentation for Off-road Unstructured Natural Environments

With the availability of many datasets tailored for autonomous driving i...
research
03/19/2022

Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning

Autonomous vehicles utilize urban scene segmentation to understand the r...
research
03/01/2021

Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning

In this work, we introduce panoramic panoptic segmentation as the most h...

Please sign up or login with your details

Forgot password? Click here to reset