Woodscape Fisheye Semantic Segmentation for Autonomous Driving -- CVPR 2021 OmniCV Workshop Challenge

TL;DR

This paper introduces the WoodScape fisheye semantic segmentation challenge for autonomous driving, highlighting the unique difficulties of fisheye perception and showcasing the top-performing methods and their improvements over baseline models.

Contribution

It presents one of the first benchmarks for fisheye semantic segmentation, providing a dataset, challenge setup, and analysis of state-of-the-art approaches.

Findings

Top teams achieved significantly higher mean IoU than baseline

The challenge attracted 71 global teams and 395 submissions

Analysis of failure cases suggests future research directions

Abstract

We present the WoodScape fisheye semantic segmentation challenge for autonomous driving which was held as part of the CVPR 2021 Workshop on Omnidirectional Computer Vision (OmniCV). This challenge is one of the first opportunities for the research community to evaluate the semantic segmentation techniques targeted for fisheye camera perception. Due to strong radial distortion standard models don't generalize well to fisheye images and hence the deformations in the visual appearance of objects and entities needs to be encoded implicitly or as explicit knowledge. This challenge served as a medium to investigate the challenges and new methodologies to handle the complexities with perception on fisheye images. The challenge was hosted on CodaLab and used the recently released WoodScape dataset comprising of 10k samples. In this paper, we provide a summary of the competition which attracted the participation of 71 global teams and a total of 395 submissions. The top teams recorded significantly improved mean IoU and accuracy scores over the baseline PSPNet with ResNet-50 backbone. We summarize the methods of winning algorithms and analyze the failure cases. We conclude by providing future directions for the research.