Contextual Intelligent Decisions: Expert Moderation of Machine Outputs for Fair Assessment of Commercial Driving

Mase, Jimiama Mafeni; Pekaslan, Direnc; Agrawal, Utkarsh; Mesgarpour, Mohammad; Chapman, Peter M.; Torres, Mercedes Torres; Figueredo, Grazziela P.

doi:10.48550/arxiv.2202.09816

Cited by 2 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different types of weather severely affect traffic flow, driving performance, and vehicle and road safety [ 1 ]. Statistics from the Federal Highway Administration show that increased amount of accidents and congestion are usually directly associated with hostile weather [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning with Attention Mechanisms for Road Weather Detection

Samo

Mase

Figueredo

2023

Sensors

View full text Add to dashboard Cite

There is great interest in automatically detecting road weather and understanding its impacts on the overall safety of the transport network. This can, for example, support road condition-based maintenance or even serve as detection systems that assist safe driving during adverse climate conditions. In computer vision, previous work has demonstrated the effectiveness of deep learning in predicting weather conditions from outdoor images. However, training deep learning models to accurately predict weather conditions using real-world road-facing images is difficult due to: (1) the simultaneous occurrence of multiple weather conditions; (2) imbalanced occurrence of weather conditions throughout the year; and (3) road idiosyncrasies, such as road layouts, illumination, and road objects, etc. In this paper, we explore the use of a focal loss function to force the learning process to focus on weather instances that are hard to learn with the objective of helping address data imbalances. In addition, we explore the attention mechanism for pixel-based dynamic weight adjustment to handle road idiosyncrasies using state-of-the-art vision transformer models. Experiments with a novel multi-label road weather dataset show that focal loss significantly increases the accuracy of computer vision approaches for imbalanced weather conditions. Furthermore, vision transformers outperform current state-of-the-art convolutional neural networks in predicting weather conditions with a validation accuracy of 92% and an F1-score of 81.22%, which is impressive considering the imbalanced nature of the dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning with Attention Mechanisms for Road Weather Detection

Samo

Mase

Figueredo

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Different types of weather severely affect traffic flow, driving performance, vehicle and road safety [1]. Statistics from the Federal Highway Administration show that increased amount of accidents and congestion are usually directly associated with hostile weather [2].…”

Section: Introductionmentioning

confidence: 99%

Looking Deeper into Images for Autonomous Road Weather Detection

Samo¹,

MASE²,

Figueredo³

2022

Preprint

View full text Add to dashboard Cite

There is great interest in automatically detecting road weather and understanding its impacts on the overall safety of the transport network. This can, for example, support road condition-based maintenance or even serve as detection systems that assist safe driving during adverse climate conditions. In computer vision, previous work has demonstrated the effectiveness of deep learning in predicting weather conditions from outdoor images. However, training deep learning models to accurately predict weather conditions using real-world road-facing images is difficult due to: (1) the simultaneous occurrence of multiple weather conditions; (2) imbalanced occurrence of weather conditions throughout the year; and (3) road idiosyncrasies, such as road layouts, illumination, road objects etc. In this paper, we explore the use of focal loss function to force the learning process to focus on weather instances that are hard to learn with the objective to help address data imbalance. In addition, we explore the attention mechanism for pixel based dynamic weight adjustment to handle road idiosyncrasies using state-of-the-art vision transformer models. Experiments with a novel multi-label road weather dataset show that focal loss significantly increases the accuracy of computer vision approaches for imbalanced weather conditions. Furthermore, vision transformers outperforms current state-of-the-art convolutional neural networks in predicting weather conditions with a validation accuracy of 92% and F1-score of 81.22%, which is impressive considering the imbalanced nature of the dataset.

show abstract

Contextual Intelligent Decisions: Expert Moderation of Machine Outputs for Fair Assessment of Commercial Driving

Cited by 2 publications

References 29 publications

Deep Learning with Attention Mechanisms for Road Weather Detection

Deep Learning with Attention Mechanisms for Road Weather Detection

Looking Deeper into Images for Autonomous Road Weather Detection

Contact Info

Product

Resources

About