Woodscape Fisheye Object Detection for Autonomous Driving -- CVPR 2022 OmniCV Workshop Challenge

TL;DR

This paper introduces the first competition on fisheye camera object detection for autonomous driving, analyzing methods that operate directly on distorted images without rectification, and presents results from 120 global teams.

Contribution

It presents the WoodScape fisheye object detection challenge, encouraging models to handle fisheye images natively, and provides a comprehensive analysis of participant methods and results.

Findings

120 teams participated in the challenge

Multiple novel methods were proposed for fisheye detection

Analysis shows effectiveness of native fisheye processing approaches

Abstract

Object detection is a comprehensively studied problem in autonomous driving. However, it has been relatively less explored in the case of fisheye cameras. The strong radial distortion breaks the translation invariance inductive bias of Convolutional Neural Networks. Thus, we present the WoodScape fisheye object detection challenge for autonomous driving which was held as part of the CVPR 2022 Workshop on Omnidirectional Computer Vision (OmniCV). This is one of the first competitions focused on fisheye camera object detection. We encouraged the participants to design models which work natively on fisheye images without rectification. We used CodaLab to host the competition based on the publicly available WoodScape fisheye dataset. In this paper, we provide a detailed analysis on the competition which attracted the participation of 120 global teams and a total of 1492 submissions. We briefly discuss the details of the winning methods and analyze their qualitative and quantitative results.