Low-latency perception in off-road dynamical low visibility environments
作者：
Highlights：
• Autonomous vehicles and ADAS able to drive on unpaved urban and rural roads.
• Developing countries have unpaved roads; open-pit industry has off-road environment.
• Datasets for off-road track including impairments to exploit visibility condition.
• Deep Supervised Learning for semantic segmentation track in adverse conditions.
• Computational cost to embed DL for field tests and the Jaccard index for evaluation.
摘要
•Autonomous vehicles and ADAS able to drive on unpaved urban and rural roads.•Developing countries have unpaved roads; open-pit industry has off-road environment.•Datasets for off-road track including impairments to exploit visibility condition.•Deep Supervised Learning for semantic segmentation track in adverse conditions.•Computational cost to embed DL for field tests and the Jaccard index for evaluation.
论文关键词：Autonomous Vehicle,ADAS,Perception,Deep Learning,Supervised learning,CNN,Real-time segmentation,Off-road
论文评审过程：Received 23 December 2020, Revised 5 February 2022, Accepted 26 March 2022, Available online 6 April 2022, Version of Record 18 April 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117010
