Lightweight Regression Model with Prediction Interval Estimation for Computer Vision-based Winter Road Surface Condition Monitoring

Risto Ojala, Alvari Seppanen

Research output: Contribution to journalArticleScientificpeer-review

1 Citation (Scopus)

Abstract

Winter conditions pose several challenges for automated driving applications. A key challenge during winter is accurate assessment of road surface condition, as its impact on friction is a critical parameter for safely and reliably controlling a vehicle. This paper proposes a deep learning regression model, SIWNet, capable of estimating road surface friction properties from camera images. SIWNet extends state of the art by including an uncertainty estimation mechanism in the architecture. This is achieved by including an additional head in the network, which estimates a prediction interval. The prediction interval head is trained with a maximum likelihood loss function. The model was trained and tested with the SeeingThroughFog dataset, which features corresponding road friction sensor readings and images from an instrumented vehicle. Acquired results highlight the functionality of the prediction interval estimation of SIWNet, while the network also achieved similar point estimate accuracy as the previous state of the art. Furthermore, the SIWNet architecture offers a more favourable balance of accuracy and computational load than previous state-of-the-art models.

Original languageEnglish
Pages (from-to)1-13
Number of pages13
JournalIEEE Transactions on Intelligent Vehicles
DOIs
Publication statusE-pub ahead of print - 28 Feb 2024
MoE publication typeA1 Journal article-refereed

Keywords

  • Computational modeling
  • Computer vision
  • convolutional neural networks
  • Estimation
  • Friction
  • intelligent vehicles
  • Monitoring
  • Roads
  • Tires
  • Uncertainty
  • vehicle safety

Fingerprint

Dive into the research topics of 'Lightweight Regression Model with Prediction Interval Estimation for Computer Vision-based Winter Road Surface Condition Monitoring'. Together they form a unique fingerprint.

Cite this