《Real-Time Semantic Segmentation for Fisheye Urban Driving Images Based on ERFNet †》阅读感悟

又是一篇关于鱼眼图像的文章，这类文章实在太少，所以相关文章，都显得弥足珍贵。

IEEE上下载需要注册，所以干脆直接在线读得了。

This paper is an extended version of our paper published in Sáez, A.; Bergasa, L.M.; Romeral, E.; López, E.; Barea, R.; Sanz, R. CNN-based Fisheye Image Real-Time Semantic Segmentation. In Proceedings of IEEE Intelligent Vehicles Symposium (IV), Changshu, China, 26–30 June 2018.

Abstract: 

The interest in fisheye cameras has recently risen in the autonomous vehicles field, as they are able to reduce the complexity of perception systems while improving the management of dangerous driving situations. However, the strong distortion inherent to these cameras makes the usage of conventional computer vision algorithms difficult and has prevented the development of these devices. This paper presents a methodology that provides real-time semantic segmentation on fisheye cameras leveraging only synthetic images. Furthermore, we propose some Convolutional Neural Networks(CNN) architectures based on Efficient Residual Factorized Network(ERFNet) that demonstrate notable skills handling distortion and a new training strategy that improves the segmentation on the image borders. Our proposals are compared to similar state-of-the-art works showing an outstanding performance and tested in an unknown real world scenario using a fisheye camera integrated in an open-source autonomous electric car, showing a high domain adaptation capability.

1. Introduction

介绍了一下fisheye的优缺点以及这篇论文的结构。

2. Related Work